Merge pull request #221 from CartoDB/add-warning

Add warning about updating dependencies

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,10 @@
+
+- [ ] All declared geometries are `geometry(Geometry, 4326)` for general geoms, or `geometry(Point, 4326)`
+- [ ] Existing functions in crankshaft python library called from the extension are kept at least from version N to version N+1 (to avoid breakage during upgrades).
+- [ ] Docs for public-facing functions are written
+- [ ] New functions follow the naming conventions: `CDB_NameOfFunction`. Where internal functions begin with an underscore
+- [ ] Video explaining the analysis and showing examples 
+- [ ] Analysis Documentation written [template](https://docs.google.com/a/cartodb.com/document/d/1X2KOtaiEBKWNMp8UjwcLB-kE9aIOw09aOjX3oaCjeME/edit?usp=sharing)
+- [ ] Smoke test written
+- [ ] Hand-off document for camshaft node written
+- [ ] If function is in Python, code conforms to [PEP8 Style Guide](https://www.python.org/dev/peps/pep-0008/)

.gitignore

@@ -0,0 +1,4 @@
+envs/
+*.pyc
+.DS_Store
+.idea/

.travis.yml

@@ -0,0 +1,48 @@
+language: c
+sudo: required
+
+env:
+  global:
+    - PAGER=cat
+    - PGUSER=postgres
+    - PGDATABASE=postgres
+    - PGOPTIONS='-c client_min_messages=NOTICE'
+
+jobs:
+  include:
+    - env: POSTGRESQL_VERSION="9.6" POSTGIS_VERSION="2.5"
+      dist: xenial
+    - env: POSTGRESQL_VERSION="10" POSTGIS_VERSION="2.5"
+      dist: xenial
+    - env: POSTGRESQL_VERSION="11" POSTGIS_VERSION="2.5"
+      dist: xenial
+    - env: POSTGRESQL_VERSION="12" POSTGIS_VERSION="3"
+      dist: bionic
+
+before_install:
+
+  - sudo apt-get install -y --allow-unauthenticated --no-install-recommends --no-install-suggests postgresql-$POSTGRESQL_VERSION postgresql-client-$POSTGRESQL_VERSION postgresql-server-dev-$POSTGRESQL_VERSION postgresql-common
+  - if [[ $POSTGRESQL_VERSION == '9.6' ]]; then sudo apt-get install -y postgresql-contrib-9.6; fi;
+  - sudo apt-get install -y --allow-unauthenticated postgresql-$POSTGRESQL_VERSION-postgis-$POSTGIS_VERSION postgresql-$POSTGRESQL_VERSION-postgis-$POSTGIS_VERSION-scripts postgis
+
+  # For pre12, install plpython2. For PG12 install plpython3
+  - if [[ $POSTGRESQL_VERSION != '12' ]]; then sudo apt-get install -y postgresql-plpython-$POSTGRESQL_VERSION python python-pip python-software-properties python-joblib python-nose python-setuptools; else sudo apt-get install -y postgresql-plpython3-12 python3 python3-pip python3-software-properties python3-joblib python3-nose python3-setuptools; fi;
+  - if [[ $POSTGRESQL_VERSION == '12' ]]; then echo -e "joblib==0.11\nnumpy==1.13.3\nscipy==0.19.1\npysal==1.14.3\nscikit-learn==0.19.1" > ./src/py/crankshaft/requirements.txt && sed -i -e "s/.*install_requires.*$/    install_requires=['joblib==0.11.0', 'numpy==1.13.3', 'scipy==0.19.1', 'pysal==1.14.3', 'scikit-learn==0.19.1'],/g" ./src/py/crankshaft/setup.py; fi;
+
+  - sudo pg_dropcluster --stop $POSTGRESQL_VERSION main
+  - sudo rm -rf /etc/postgresql/$POSTGRESQL_VERSION /var/lib/postgresql/$POSTGRESQL_VERSION
+  - sudo pg_createcluster -u postgres $POSTGRESQL_VERSION main --start -- -A trust
+  - export PGPORT=$(pg_lsclusters | grep $POSTGRESQL_VERSION | awk '{print $3}')
+
+install:
+  - sudo make install
+
+script:
+  - make test
+  - ./check-compatibility.sh
+
+after_failure:
+  - pg_lsclusters
+  - cat src/pg/test/regression.diffs
+  - echo $PGPORT
+  - cat /var/log/postgresql/postgresql-$POSTGRESQL_VERSION-main.log

CONTRIBUTING.md

@@ -1,84 +1,65 @@
-# Contributing guide
+# Development process
 
-## How to add new functions
+For any modification of crankshaft, such as adding new features,
+refactoring or bugfixing, a topic branch must be created out of the `develop`.
 
-Try to put as little logic in the SQL extension as possible and
-just use it as a wrapper to the Python module functionality.
+Modifications are done inside `src/pg/sql` and `src/py/crankshaft`.
 
-Once a function is defined it should never change its signature in subsequent
-versions. To change a function's signature a new function with a different
-name must be created.
+When adding a new PostgreSQL function or modifying an exiting one make sure that the
+[VOLATILITY](https://www.postgresql.org/docs/current/static/xfunc-volatility.html) and [PARALLEL](https://www.postgresql.org/docs/9.6/static/parallel-safety.html) categories are updated accordingly.
+As PARALLEL labels need to be stripped for incompatible PostgreSQL versions
+please use _PARALLEL SAFE/RESTRICTED/UNSAFE_ in uppercase so it's handled
+automatically.
 
-### Version numbers
+Take into account:
 
-The version of both the SQL extension and the Python package shall
-follow the[Semantic Versioning 2.0](http://semver.org/) guidelines:
+*  Tests must be added for any new functionality
+   (inside `src/pg/test`, `src/py/crankshaft/test`) as well as to
+   detect any bugs that are being fixed.
+*  Add or modify the corresponding documentation files in the `doc` folder.
+*  Naming conventions for function names:
+   - use `CamelCase`
+   - prefix "public" functions with `CDB_`. E.g: `CDB_SpatialMarkovTrend`
+   - prefix "private" functions with an underscore. E.g: `_CDB_MyObscureInternalImplementationDetail`
 
-* When backwards incompatibility is introduced the major number is incremented
-* When functionally is added (in a backwards-compatible manner) the minor number
-  is incremented
-* When only fixes are introduced (backwards-compatible) the patch number is
-  incremented
+Once the code is ready to be tested, update the local development installation
+with `sudo make install`.
+This will update the 'dev' version of the extension in `src/pg/` and
+make it available to PostgreSQL.
 
-### Python Package
+Run the tests with `make test`.
 
-...
+Update extension in a working database with:
 
-### SQL Extension
-
-* Generate a **new subfolder version** for `sql` and `test` folders to define
-  the new functions and tests
-  - Use symlinks to avoid file duplication between versions that don't update them
-  - Add new files or modify copies of the old files to add new functions or
-    modify existing functions (remember to rename a function if the signature
-    changes)
-  - Add or modify the corresponding documentation files in the `doc` folder.
-    Since we expect to have highly technical functions here, an extense
-    background explanation would be of great help to users of this extension.
-  - Create tests for the new functions/behaviour
-
-* Generate the **upgrade and downgrade files** for the extension
-
-* Update the control file and the Makefile to generate the complete SQL
-  file for the new created version. After running `make` a new
-  file `crankshaft--X.Y.Z.sql` will be created for the current version.
-  Additional files for migrating to/from the previous version A.B.Z should be
-  created:
-  - `crankshaft--X.Y.Z--A.B.C.sql`
-  - `crankshaft--A.B.C--X.Y.Z.sql`
-  All these new files must be added to git and pushed.
-
-* Update the public docs! ;-)
-
-## Conventions
-
-# SQL
-
-Use snake case (i.e. `snake_case` and not `CamelCase`) for all
-functions. Prefix functions intended for public use with `cdb_`
-and private functions (to be used only internally inside
-the extension)  with `_cdb_`.
-
-# Python
-
-...
-
-## Testing
-
-Running just the Python tests:
-
-```
-(cd python && make test)
+```sql
+ALTER EXTENSION crankshaft UPDATE TO 'current';
+ALTER EXTENSION crankshaft UPDATE TO 'dev';
 ```
 
-Installing the Extension and running just the PostgreSQL tests:
-
-```
-(cd pg && sudo make install && PGUSER=postgres make installcheck)
+If the extension has not previously been installed in a database,
+it can be installed directly with:
+```sql
+CREATE EXTENSION crankshaft WITH VERSION 'dev' CASCADE;
 ```
 
-Installing and testing everything:
+Once the feature or bugfix is completed and all the tests are passing
+a pull request shall be created, reviewed by a peer
+and then merged back into the `develop` branch once all the CI tests pass.
 
+
+## Relevant development targets in the Makefile
+
+```shell
+# Show a short description of the available targets
+make help
+
+# Generate the extension scripts and install the python package.
+sudo make install
+
+#  Run the tests against the installed extension.
+make test
 ```
-sudo make install && PGUSER=postgres make testinstalled
-```
+
+## Submitting contributions
+
+Before opening a pull request (or submitting a contribution) you will need to sign a Contributor License Agreement (CLA) before making a submission, [learn more here](https://carto.com/contributions).

DEPLOYING.md

@@ -1,43 +0,0 @@
-# Workflow
-
-... (branching/merging flow)
-
-# Deployment
-
-...
-
-Deployment to db servers: the next command will install both the Python
-package and the extension.
-
-```
-sudo make install
-```
-
-Installing only the Python package:
-
-```
-sudo pip install python/crankshaft --upgrade
-```
-
-Caveat: note that `pip install ./crankshaft` will install
-from local files, but `pip install crankshaft` will not.
-
-CI: Install and run the tests on the installed extension and package:
-
-```
-(sudo make install && PGUSER=postgres make testinstalled)
-```
-
-Installing the extension in user databases:
-Once installed in a server, the extension can be added
-to a database with the next SQL command:
-
-```
-CREATE EXTENSION crankshaft;
-```
-
-To upgrade the extension to an specific version X.Y.Z:
-
-```
-ALTER EXTENSION crankshaft UPGRADE TO 'X.Y.Z';
-```

Makefile

@@ -1,13 +1,64 @@
-EXT_DIR = pg
-PYP_DIR = python
+include ./Makefile.global
+
+EXT_DIR = src/pg
+PYP_DIR = src/py
 
 .PHONY: install
 .PHONY: run_tests
+.PHONY: release
+.PHONY: deploy
 
-install:
+# Generate and install developmet versions of the extension
+# and python package.
+# The extension is named 'dev' with a 'current' alias for easily upgrading.
+# Requires sudo.
+install: ## Generate and install development version of the extension; requires sudo.
 	$(MAKE) -C $(PYP_DIR) install
 	$(MAKE) -C $(EXT_DIR) install
 
-testinstalled:
-	$(MAKE) -C $(PYP_DIR) testinstalled
-	$(MAKE) -C $(EXT_DIR) installcheck
+# Run the tests for the installed development extension and
+# python package
+test:   ## Run the tests for the development version of the extension
+	$(MAKE) -C $(PYP_DIR) test
+	$(MAKE) -C $(EXT_DIR) test
+
+# Generate a new release into release
+release: ## Generate a new release of the extension.
+	$(MAKE) -C $(EXT_DIR) release
+	$(MAKE) -C $(PYP_DIR) release
+
+# Install the current release.
+# Requires sudo.
+# Use the RELEASE_VERSION environment variable to deploy a specific version:
+#     sudo make deploy RELEASE_VERSION=1.0.0
+deploy:
+	$(MAKE) -C $(EXT_DIR) deploy
+	$(MAKE) -C $(PYP_DIR) deploy
+
+# Cleanup development extension script files
+clean-dev: ## clean up development extension script files
+	rm -f src/pg/$(EXTENSION)--*.sql
+
+# Cleanup all releases
+clean-releases: ## clean up all releases
+	rm -rf release/python/*
+	rm -f release/$(EXTENSION)--*.sql
+	rm -f release/$(EXTENSION).control
+
+# Cleanup current/specific version
+clean-release: ## clean up current release
+	rm -rf release/python/$(RELEASE_VERSION)
+	rm -f release/$(RELEASE_VERSION)--*.sql
+
+clean-all: clean-dev clean-release
+
+help:
+	@IFS=$$'\n' ; \
+	help_lines=(`fgrep -h "##" $(MAKEFILE_LIST) | fgrep -v fgrep | sed -e 's/\\$$//'`); \
+	for help_line in $${help_lines[@]}; do \
+		IFS=$$'#' ; \
+		help_split=($$help_line) ; \
+		help_command=`echo $${help_split[0]} | sed -e 's/^ *//' -e 's/ *$$//'` ; \
+		help_info=`echo $${help_split[2]} | sed -e 's/^ *//' -e 's/ *$$//'` ; \
+		printf "%-30s %s\n" $$help_command $$help_info ; \
+	done

Makefile.global

@@ -0,0 +1,23 @@
+SELF_DIR         := $(dir $(lastword $(MAKEFILE_LIST)))
+EXTENSION         = crankshaft
+PACKAGE           = crankshaft
+EXTVERSION        = $(shell grep default_version $(SELF_DIR)/src/pg/$(EXTENSION).control | sed -e "s/default_version[[:space:]]*=[[:space:]]*'\([^']*\)'/\1/")
+RELEASE_VERSION  ?= $(EXTVERSION)
+
+SED               = sed
+AWK               = awk
+
+PG_CONFIG         = pg_config
+PG_VERSION_1000  := $(shell $(PG_CONFIG) --version | $(AWK) '{$$2*=1000; print $$2}')
+PG_PARALLEL      := $(shell [ $(PG_VERSION_1000) -ge 9600 ] && echo true)
+
+PG_12plus        := $(shell [ $(PG_VERSION_1000) -ge 12000 ] && echo true)
+PYTHON3          ?= $(PG_12plus)
+
+ifeq ($(PYTHON3), true)
+PIP              := python3 -m pip
+NOSETESTS         = nosetests3
+else
+PIP              := python2 -m pip
+NOSETESTS         = nosetests
+endif

NEWS.md

@@ -0,0 +1,108 @@
+0.9.0 (2019-12-23)
+------------------
+* Compatibility with PG12.
+* Compatibility with python3 (enable with PYTHON3=true env variable, default in PG12+).
+
+0.8.2 (2019-02-07)
+------------------
+* Update dependencies to match what it's being used in production.
+* Update travis to xenial, PG10 and 11, and postgis 2.5
+* Compatibility with PG11
+
+0.8.1 (2018-03-12)
+------------------
+* Adds improperly added version files
+
+0.8.0 (2018-03-12)
+------------------
+* Adds `CDB_MoransILocal*` functions that return spatial lag [#202](https://github.com/CartoDB/crankshaft/pull/202)
+
+0.7.0 (2018-02-23)
+------------------
+* Updated Moran and Markov documentation [#179](https://github.com/CartoDB/crankshaft/pull/179) [#155](https://github.com/CartoDB/crankshaft/pull/155)
+* Updated examples in documentation [#193](https://github.com/CartoDB/crankshaft/pull/193)
+* Better error management for empty values [#157](https://github.com/CartoDB/crankshaft/pull/157)
+* Added nonspatial kmeans with class framework [#150](https://github.com/CartoDB/crankshaft/pull/150)
+* Added multipolygons and geometry collections support to PIA analyssis [#165](https://github.com/CartoDB/crankshaft/pull/165)
+* Upgraded PySAL to v1.14.3 [#198](https://github.com/CartoDB/crankshaft/pull/198)
+
+0.6.1 (2017-11-23)
+------------------
+* Added VOLATILITY and PARALLEL categories to PostgreSQL functions [#183](https://github.com/CartoDB/crankshaft/pull/183)
+
+0.6.0 (2017-11-08)
+------------------
+* Adds new functions: `CDB_GWR` and `CDB_GWR_Predict`
+
+0.5.2 (2017-05-12)
+------------------
+* Fixes missing comma for dict creation #172
+
+0.5.1 (2016-12-12)
+------------------
+* Fixed problem with the upgrade file from 0.4.2 to 0.5.0 that hasn't changes that should be there (as per ethervoid).
+
+0.5.0 (2016-12-12)
+------------------
+* Updated PULL_REQUEST_TEMPLATE
+* Fixed a bug that flips the order of the numerator in denominator for calculating using Moran Local Rate because previously the code sorted the keys alphabetically.
+* Add new CDB_GetisOrdsG functions. Getis-Ord's G\* is a geo-statistical measurement of the intensity of clustering of high or low values
+* Add new outlier detection functions: CDB_StaticOutlier, CDB_PercentOutlier and CDB_StdDevOutlier
+* Updates in the framework for accessing the Python functions.
+
+0.4.2 (2016-09-22)
+------------------
+* Bugfix for cdb_areasofinterestglobal: import correct modules
+
+0.4.1 (2016-09-21)
+------------------
+* Let the user set the resolution in CDB_Contour function
+* Add Nearest Neighbors method to CDB_SpatialInterpolation
+* Improve error reporting for moran and markov functions
+
+0.4.0 (2016-08-30)
+------------------
+* Add CDB_Contour
+* Add CDB_PIA
+* Add CDB_Densify
+* Add CDB_TINmap
+
+0.3.1 (2016-08-18)
+------------------
+* Fix Voronoi projection issue
+* Fix Voronoi spurious segments issue
+* Add tests for interpolation
+
+0.3.0 (2016-08-17)
+------------------
+* Adds Voronoi function
+* Fixes barycenter method in interpolation
+
+0.2.0 (2016-08-11)
+------------------
+* Adds Gravity Model
+
+0.1.0 (2016-06-29)
+------------------
+* Adds Spatial Markov function
+* Adds Spacial interpolation function
+* Adds `CDB_pyAgg (columns Numeric[])` helper function
+* Adds Segmentation Functions
+
+0.0.4 (2016-06-20)
+------------------
+* Remove cartodb extension dependency from tests
+* Declare all correct dependencies with correct versions in setup.py
+
+0.0.3 (2016-06-16)
+------------------
+* Adds new functions: kmeans, weighted centroids.
+* Replaces moran functions with new areas of interest naming.
+
+0.0.2 (2016-03-16)
+------------------
+* New versioning approach using per-version Python virtual environments
+
+0.0.1 (2016-02-22)
+------------------
+* Preliminar release

README.md

@@ -1,14 +1,59 @@
-# crankshaft
+# Crankshaft [![Build Status](https://travis-ci.org/CartoDB/crankshaft.svg?branch=develop)](https://travis-ci.org/CartoDB/crankshaft)
 
-CartoDB Spatial Analysis extension for PostgreSQL.
+CARTO Spatial Analysis extension for PostgreSQL.
 
 ## Code organization
 
-* *pg* contains the PostgreSQL extension source code
-* *python* Python module
-
-FIXME: should it be `./extension` and `./lib/python' ?
+* `doc/` documentation
+* `src/` source code
+ - `pg/` contains the PostgreSQL extension source code
+ - `py/` Python module source code
+* `release` released versions
 
 ## Requirements
 
-* pip
+* PostgreSQL
+* plpythonu (for PG12+, plpython3u) and postgis extensions
+* python-scipy system package (see [src/py/README.md](https://github.com/CartoDB/crankshaft/blob/develop/src/py/README.md))
+
+# Development Process
+
+We use the branch `develop` as the main integration branch for development. The `master` is reserved to handle releases.
+
+The process is as follows:
+
+1. Create a new **topic branch** from `develop` for any new feature or bugfix and commit their changes to it:
+
+  ```shell
+  git fetch && git checkout -b my-cool-feature origin/develop
+  ```
+1. Code, commit, push, repeat.
+1. Write some **tests** for your feature or bugfix.
+1. Update the [NEWS.md](https://github.com/CartoDB/crankshaft/blob/develop/NEWS.md) doc.
+1. Create a pull request and mention relevant people for a **peer review**.
+1. Address the comments and improvements you get from the peer review.
+
+In order for a pull request to be accepted, the following criteria should be met:
+* The peer review should pass and no major issue should be left unaddressed.
+* CI tests must pass (travis will take care of that).
+
+
+## Development Guidelines
+
+For a detailed description of the development process please see
+the [CONTRIBUTING.md](https://github.com/CartoDB/crankshaft/blob/develop/CONTRIBUTING.md) guide.
+
+
+## Testing
+
+The tests (both for SQL and Python) are executed by running, from the top directory:
+
+```shell
+sudo make install
+make test
+```
+
+## Release
+
+The release process is described in the
+[RELEASE.md](https://github.com/CartoDB/crankshaft/blob/develop/RELEASE.md) guide and is the responsibility of the designated *release manager*.

RELEASE.md

@@ -0,0 +1,55 @@
+# Release & Deployment Process
+
+:warning: Do not forget about updating dependencies in `cartodb-platform` and `carto-postgres-artifacts` :warning:
+
+## Release steps
+* Make sure `develop` branch passes all the tests.
+* Merge `develop` into `master`
+* Update the version number in `src/pg/crankshaft.control`.
+* Generate the next release files with this command:
+
+  ```shell
+  make release
+  ```
+* Generate an upgrade path from the previous to the next release by copying the generated release file. E.g:
+
+  ```shell
+  cp release/crankshaft--X.Y.Z.sql release/crankshaft--A.B.C--X.Y.Z.sql
+  ```
+  NOTE: you can rely on this thanks to the compatibility checks.
+  TODO: automate this step [#94](https://github.com/CartoDB/crankshaft/issues/94)
+
+    * Update the [NEWS.md](https://github.com/CartoDB/crankshaft/blob/master/NEWS.md) file
+    * Commit and push the generated files.
+    * Tag the release:
+
+  ```
+  git tag -a X.Y.Z -m "Release X.Y.Z"
+  git push origin X.Y.Z
+  ```
+
+* Deploy and test in staging
+* Merge `master` into **`stable`**
+* Deploy and test in production
+* Merge `master` into **`develop`**
+
+
+## Some remarks
+* Version numbers shall follow [Semantic Versioning 2.0](http://semver.org/).
+* CI tests will take care of **forward compatibility** of the extension at postgres level.
+* **Major version changes** (breaking forward compatibility) are a major event and are out of the scope of this doc. They **shall be avoided as much as we can**.
+* We will go forward, never backwards. **Generating upgrade paths automatically is easy** and we'll rely on the CI checks for that.
+
+## Deploy commands
+
+The new release can be deployed for staging/smoke tests with this command:
+
+  ```shell
+  sudo make deploy
+  ```
+
+To install a specific version 'X.Y.Z' different from the default one:
+
+  ```shell
+  sudo make deploy RELEASE_VERSION=X.Y.Z
+  ```

TODO.md

@@ -1,9 +0,0 @@
-* [x] Support versioning
-* [x] Test use of `plpy` from python Package
-* [x] Add `pysal` etc. dependencies
-* [x] Define documentation practices (general, per extension/package?)
-* [x] Add initial function set (WIP)
-* Unify style of function comments
-* [x] Add integration tests
-* Make target to open a new version development (create symlinks, etc.)
-* [x] Should add cartodb ext. as a dependency?

carto-package.json

@@ -0,0 +1,20 @@
+{
+    "name": "crankshaft",
+    "current_version": {
+        "requires": {
+            "postgres": ">=9.5.0",
+            "postgis": ">=2.2.0.0",
+            "python": ">=2.7.0",
+            "joblib": "0.8.3",
+            "numpy": "1.6.1",
+            "scipy": "0.14.0",
+            "pysal": "1.14.3",
+            "scikit-learn": "0.14.1"
+        },
+        "works_with": {
+        }
+    },
+
+    "exceptional_versions": {
+    }
+}

check-compatibility.sh

@@ -0,0 +1,143 @@
+#!/bin/bash
+
+export PGUSER=postgres
+
+DBNAME=crankshaft_compatcheck
+
+function die {
+    echo $1
+    exit -1
+}
+
+# Create fresh DB
+psql -c "CREATE DATABASE $DBNAME;" || die "Could not create DB"
+
+# Hook for cleanup
+function cleanup {
+    psql -c "DROP DATABASE IF EXISTS crankshaft_compatcheck;"
+}
+trap cleanup EXIT
+
+# Deploy previous release
+(cd src/py && sudo make deploy RUN_OPTIONS="--no-deps") || die "Could not deploy python extension"
+(cd src/pg && sudo make deploy) || die " Could not deploy last release"
+psql -c "SELECT * FROM pg_available_extension_versions WHERE name LIKE 'crankshaft';"
+
+# Install in the fresh DB
+psql $DBNAME <<'EOF'
+-- Create role publicuser if it does not exist
+DO
+$$
+BEGIN
+   IF NOT EXISTS (
+      SELECT *
+      FROM   pg_catalog.pg_user
+      WHERE  usename = 'publicuser') THEN
+
+      CREATE ROLE publicuser LOGIN;
+   END IF;
+END
+$$ LANGUAGE plpgsql;
+
+-- Install the default version
+CREATE EXTENSION crankshaft CASCADE;
+\dx
+EOF
+
+
+# Check PG version
+PG_VERSION=`psql -q -t -c "SELECT current_setting('server_version_num')"`
+
+# Save public function signatures
+if [[ "$PG_VERSION" -lt 110000 ]]; then
+    psql $DBNAME -c "
+    CREATE TABLE release_function_signatures AS
+    SELECT
+        p.proname as name,
+        pg_catalog.pg_get_function_result(p.oid) as result_type,
+        pg_catalog.pg_get_function_arguments(p.oid) as arguments,
+    CASE
+        WHEN p.proisagg THEN 'agg'
+        WHEN p.proiswindow THEN 'window'
+        WHEN p.prorettype = 'pg_catalog.trigger'::pg_catalog.regtype THEN 'trigger'
+        ELSE 'normal'
+    END as type
+    FROM pg_catalog.pg_proc p
+        LEFT JOIN pg_catalog.pg_namespace n ON n.oid = p.pronamespace
+    WHERE
+        n.nspname = 'cdb_crankshaft'
+        AND p.proname LIKE 'cdb_%'
+    ORDER BY 1, 2, 4;"
+else
+    psql $DBNAME -c "
+    CREATE TABLE release_function_signatures AS
+    SELECT
+        p.proname as name,
+        pg_catalog.pg_get_function_result(p.oid) as result_type,
+        pg_catalog.pg_get_function_arguments(p.oid) as arguments,
+    CASE    WHEN p.prokind = 'a' THEN 'agg'
+            WHEN p.prokind = 'w' THEN 'window'
+            WHEN p.prorettype = 'pg_catalog.trigger'::pg_catalog.regtype THEN 'trigger'
+            ELSE 'normal'
+    END as type
+    FROM pg_catalog.pg_proc p
+        LEFT JOIN pg_catalog.pg_namespace n ON n.oid = p.pronamespace
+    WHERE
+        n.nspname = 'cdb_crankshaft'
+        AND p.proname LIKE 'cdb_%'
+    ORDER BY 1, 2, 4;"
+fi
+
+# Deploy current dev branch
+make clean-dev || die "Could not clean dev files"
+sudo make install || die "Could not deploy current dev branch"
+
+# Check it can be upgraded
+psql $DBNAME -c "ALTER EXTENSION crankshaft update to 'dev';" || die "Cannot upgrade to dev version"
+
+if [[ $PG_VERSION -lt 110000 ]]; then
+    psql $DBNAME -c "
+    CREATE TABLE dev_function_signatures AS
+        SELECT  p.proname as name,
+                pg_catalog.pg_get_function_result(p.oid) as result_type,
+                pg_catalog.pg_get_function_arguments(p.oid) as arguments,
+                CASE    WHEN p.proisagg     THEN 'agg'
+                        WHEN p.proiswindow  THEN 'window'
+                        WHEN p.prorettype = 'pg_catalog.trigger'::pg_catalog.regtype THEN 'trigger'
+                        ELSE 'normal'
+                END as type
+        FROM pg_catalog.pg_proc p
+            LEFT JOIN pg_catalog.pg_namespace n ON n.oid = p.pronamespace
+        WHERE
+            n.nspname = 'cdb_crankshaft'
+            AND p.proname LIKE 'cdb_%'
+        ORDER BY 1, 2, 4;"
+else
+    psql $DBNAME -c "
+    CREATE TABLE dev_function_signatures AS
+        SELECT  p.proname as name,
+                pg_catalog.pg_get_function_result(p.oid) as result_type,
+                pg_catalog.pg_get_function_arguments(p.oid) as arguments,
+                CASE    WHEN p.prokind = 'a' THEN 'agg'
+                        WHEN p.prokind = 'w' THEN 'window'
+                        WHEN p.prorettype = 'pg_catalog.trigger'::pg_catalog.regtype THEN 'trigger'
+                        ELSE 'normal'
+                END as type
+        FROM pg_catalog.pg_proc p
+            LEFT JOIN pg_catalog.pg_namespace n ON n.oid = p.pronamespace
+        WHERE
+            n.nspname = 'cdb_crankshaft'
+            AND p.proname LIKE 'cdb_%'
+        ORDER BY 1, 2, 4;"
+fi
+
+
+echo "Functions in development not in latest release (ok):"
+psql $DBNAME -c "SELECT * FROM dev_function_signatures EXCEPT SELECT * FROM release_function_signatures;"
+
+echo "Functions in latest release not in development (compat issue):"
+psql $DBNAME -c "SELECT * FROM release_function_signatures EXCEPT SELECT * FROM dev_function_signatures;"
+
+# Fail if there's a signature mismatch / missing functions
+psql $DBNAME -c "SELECT * FROM release_function_signatures EXCEPT SELECT * FROM dev_function_signatures;" | fgrep '(0 rows)' \
+    || die "Function signatures changed"

check-up-to-date-with-master.sh

@@ -0,0 +1,24 @@
+#!/bin/bash
+
+CURRENT_BRANCH=$(git rev-parse --abbrev-ref HEAD)
+
+if [[ "$CURRENT_BRANCH" == "master" || "$CURRENT_BRANCH" == "HEAD" ]]
+then
+    echo "master branch or detached HEAD"
+    exit 0
+fi
+
+# Add remote-master
+git remote add -t master remote-master https://github.com/CartoDB/crankshaft.git
+
+# Fetch master reference
+git fetch --depth=1 remote-master master
+
+# Compare HEAD with master
+# NOTE: travis by default uses --depth=50 so we are actually checking that the tip
+# of the branch is no more than 50 commits away from master as well.
+git rev-list HEAD | grep $(git rev-parse remote-master/master) ||
+    { echo "Your branch is not up to date with latest release";
+      echo "Please update it by running the following:";
+      echo "    git fetch && git merge origin/develop";
+      false; }

doc/02_moran.md

@@ -0,0 +1,309 @@
+## Moran's I - Spatial Autocorrelation
+
+Note: these functions are replacing the functions in the _Areas of Interest_ family (still documented below). `CDB_MoransILocal` and `CDB_MoransILocalRate` perform the same analysis as their `CDB_AreasOfInterest*` counterparts but return spatial lag information, which is needed for creating the Moran's I scatter plot. It recommended to use the `CDB_MoransILocal*` variants instead as they will be maintained and improved going foward.
+
+A family of analyses to uncover groupings of areas with consistently high or low values (clusters) and smaller areas with values unlike those around them (outliers). A cluster is labeled by an 'HH' (high value compared to the entire dataset in an area with other high values), or its opposite 'LL'. An outlier is labeled by an 'LH' (low value surrounded by high values) or an 'HL' (the opposite). Each cluster and outlier classification has an associated p-value, a measure of how significant the pattern of highs and lows is compared to a random distribution.
+
+These functions have two forms: local and global. The local versions classify every input geometry while the global function gives a rating of the overall clustering characteristics of the dataset. Both forms accept an optional denomiator (see the rate versions) if, for example, working with count data and a denominator is needed.
+
+### Notes
+
+*   Rows with null values will be omitted from this analysis. To ensure they are added to the analysis, fill the null-valued cells with an appropriate value such as the mean of a column, the mean of the most recent two time steps, or use a `LEFT JOIN` to get null outputs from the analysis.
+*   Input query can only accept tables (datasets) in the users database account. Common table expressions (CTEs) do not work as an input unless specified within the `subquery` argument.
+
+### CDB_MoransILocal(subquery text, column_name text)
+
+
+This function classifies your data as being part of a cluster, as an outlier, or not part of a pattern based the significance of a classification. The classification happens through an autocorrelation statistic called Local Moran's I.
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| subquery | TEXT | SQL query that exposes the data to be analyzed (e.g., `SELECT * FROM interesting_table`). This query must have the geometry column name `the_geom` and id column name `cartodb_id` unless otherwise specified in the input arguments |
+| column_name | TEXT | Name of column (e.g., should be `'interesting_value'` instead of `interesting_value` without single quotes) used for the analysis. |
+| weight type (optional) | TEXT | Type of weight to use when finding neighbors. Currently available options are 'knn' (default) and 'queen'. Read more about weight types in [PySAL's weights documentation](https://pysal.readthedocs.io/en/v1.11.0/users/tutorials/weights.html). |
+| num_ngbrs (optional) | INT | Number of neighbors if using k-nearest neighbors weight type. Defaults to 5. |
+| permutations (optional) | INT | Number of permutations to check against a random arrangement of the values in `column_name`. This influences the accuracy of the output field `significance`. Defaults to 99. |
+| geom_col (optional) | TEXT | The column name for the geometries. Defaults to `'the_geom'` |
+| id_col (optional) | TEXT | The column name for the unique ID of each geometry/value pair. Defaults to `'cartodb_id'`. |
+
+#### Returns
+
+A table with the following columns.
+
+| Column Name | Type | Description |
+|-------------|------|-------------|
+| quads | TEXT | Classification of geometry. Result is one of 'HH' (a high value with neighbors high on average), 'LL' (opposite of 'HH'), 'HL' (a high value surrounded by lows on average), and 'LH' (opposite of 'HL'). Null values are returned when nulls exist in the original data. |
+| significance | NUMERIC | The statistical significance (from 0 to 1) of a cluster or outlier classification. Lower numbers are more significant. |
+| spatial\_lag | NUMERIC | The 'average' of the neighbors of the value in this row. The average is calculated from it's neighborhood -- defined by `weight_type`. |
+| spatial\_lag\_std | NUMERIC | The standardized version of `spatial_lag` -- that is, centered on the mean and divided by the standard deviation. Useful as the y-axis in a Moran's I scatter plot. |
+| orig\_val | NUMERIC | Values from `column_name`. |
+| orig\_val\_std | NUMERIC | Values from `column_name` but centered on the mean and divided by the standard devation. Useful as the x-axis in Moran's I scatter plots. |
+| moran\_stat | NUMERIC | Value of Moran's I (spatial autocorrelation measure) for the geometry with id of `rowid` |
+| rowid | INT | Row id of the values which correspond to the input rows. |
+
+
+
+#### Example Usage
+
+```sql
+SELECT
+  c.the_geom,
+  m.quads,
+  m.significance,
+  c.num_cyclists_per_total_population
+FROM
+  cdb_crankshaft.CDB_MoransILocal(
+    'SELECT * FROM commute_data'
+    'num_cyclists_per_total_population') As m
+JOIN commute_data As c
+ON c.cartodb_id = m.rowid;
+```
+
+
+### CDB_MoransILocalRate(subquery text, numerator text, denominator text)
+
+Just like `CDB_MoransILocal`, this function classifies your data as being part of a cluster, as an outlier, or not part of a pattern based the significance of a classification. This function differs in that it calculates the classifications based on input `numerator` and `denominator` columns for finding the areas where there are clusters and outliers for the resulting rate of those two values.
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| subquery | TEXT | SQL query that exposes the data to be analyzed (e.g., `SELECT * FROM interesting_table`). This query must have the geometry column name `the_geom` and id column name `cartodb_id` unless otherwise specified in the input arguments |
+| numerator | TEXT | Name of the numerator for forming a rate to be used in analysis. |
+| denominator | TEXT | Name of the denominator for forming a rate to be used in analysis. |
+| weight type (optional) | TEXT | Type of weight to use when finding neighbors. Currently available options are 'knn' (default) and 'queen'. Read more about weight types in [PySAL's weights documentation](https://pysal.readthedocs.io/en/v1.11.0/users/tutorials/weights.html). |
+| num_ngbrs (optional) | INT | Number of neighbors if using k-nearest neighbors weight type. Defaults to 5. |
+| permutations (optional) | INT | Number of permutations to check against a random arrangement of the values in `column_name`. This influences the accuracy of the output field `significance`. Defaults to 99. |
+| geom_col (optional) | TEXT | The column name for the geometries. Defaults to `the_geom` |
+| id_col (optional) | TEXT | The column name for the unique ID of each geometry/value pair. Defaults to `cartodb_id`. |
+
+#### Returns
+
+A table with the following columns.
+
+| Column Name | Type | Description |
+|-------------|------|-------------|
+| quads | TEXT | Classification of geometry. Result is one of 'HH' (a high value with neighbors high on average), 'LL' (opposite of 'HH'), 'HL' (a high value surrounded by lows on average), and 'LH' (opposite of 'HL'). Null values are returned when nulls exist in the original data. |
+| significance | NUMERIC | The statistical significance (from 0 to 1) of a cluster or outlier classification. Lower numbers are more significant. |
+| spatial\_lag | NUMERIC | The 'average' of the neighbors of the value in this row. The average is calculated from it's neighborhood -- defined by `weight_type`. |
+| spatial\_lag\_std | NUMERIC | The standardized version of `spatial_lag` -- that is, centered on the mean and divided by the standard deviation. |
+| orig\_val | NUMERIC | Standardized rate (centered on the mean and normalized by the standard deviation) calculated from `numerator` and `denominator`. This is calculated by [Assuncao Rate](http://pysal.readthedocs.io/en/latest/library/esda/smoothing.html?highlight=assuncao#pysal.esda.smoothing.assuncao_rate) in the PySAL library. |
+| orig\_val\_std | NUMERIC | Values from `column_name` but centered on the mean and divided by the standard devation. Useful as the x-axis in Moran's I scatter plots. |
+| moran\_stat | NUMERIC | Value of Moran's I (spatial autocorrelation measure) for the geometry with id of `rowid` |
+| rowid | INT | Row id of the values which correspond to the input rows. |
+A table with the following columns. |
+
+#### Example Usage
+
+```sql
+SELECT
+  c.the_geom,
+  m.quads,
+  m.significance,
+  c.cyclists_per_total_population
+FROM
+    cdb_crankshaft.CDB_MoransILocalRate(
+        'SELECT * FROM commute_data'
+        'num_cyclists',
+        'total_population') As m
+JOIN commute_data As c
+ON c.cartodb_id = m.rowid;
+```
+
+### CDB_AreasOfInterestLocal(subquery text, column_name text) (deprecated)
+
+This function classifies your data as being part of a cluster, as an outlier, or not part of a pattern based the significance of a classification. The classification happens through an autocorrelation statistic called Local Moran's I.
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| subquery | TEXT | SQL query that exposes the data to be analyzed (e.g., `SELECT * FROM interesting_table`). This query must have the geometry column name `the_geom` and id column name `cartodb_id` unless otherwise specified in the input arguments |
+| column_name | TEXT | Name of column (e.g., should be `'interesting_value'` instead of `interesting_value` without single quotes) used for the analysis. |
+| weight type (optional) | TEXT | Type of weight to use when finding neighbors. Currently available options are 'knn' (default) and 'queen'. Read more about weight types in [PySAL's weights documentation](https://pysal.readthedocs.io/en/v1.11.0/users/tutorials/weights.html). |
+| num_ngbrs (optional) | INT | Number of neighbors if using k-nearest neighbors weight type. Defaults to 5. |
+| permutations (optional) | INT | Number of permutations to check against a random arrangement of the values in `column_name`. This influences the accuracy of the output field `significance`. Defaults to 99. |
+| geom_col (optional) | TEXT | The column name for the geometries. Defaults to `'the_geom'` |
+| id_col (optional) | TEXT | The column name for the unique ID of each geometry/value pair. Defaults to `'cartodb_id'`. |
+
+#### Returns
+
+A table with the following columns.
+
+| Column Name | Type | Description |
+|-------------|------|-------------|
+| moran | NUMERIC | Value of Moran's I (spatial autocorrelation measure) for the geometry with id of `rowid` |
+| quads | TEXT | Classification of geometry. Result is one of 'HH' (a high value with neighbors high on average), 'LL' (opposite of 'HH'), 'HL' (a high value surrounded by lows on average), and 'LH' (opposite of 'HL'). Null values are returned when nulls exist in the original data. |
+| significance | NUMERIC | The statistical significance (from 0 to 1) of a cluster or outlier classification. Lower numbers are more significant. |
+| rowid | INT | Row id of the values which correspond to the input rows. |
+| vals | NUMERIC | Values from `'column_name'`. |
+
+
+
+#### Example Usage
+
+```sql
+SELECT
+  c.the_geom,
+  aoi.quads,
+  aoi.significance,
+  c.num_cyclists_per_total_population
+FROM
+  cdb_crankshaft.CDB_AreasOfInterestLocal(
+    'SELECT * FROM commute_data'
+    'num_cyclists_per_total_population') As aoi
+JOIN commute_data As c
+ON c.cartodb_id = aoi.rowid;
+```
+
+### CDB_AreasOfInterestGlobal(subquery text, column_name text) (deprecated)
+
+This function identifies the extent to which geometries cluster (the groupings of geometries with similarly high or low values relative to the mean) or form outliers (areas where geometries have values opposite of their neighbors). The output of this function gives values between -1 and 1 as well as a significance of that classification. Values close to 0 mean that there is little to no distribution of values as compared to what one would see in a randomly distributed collection of geometries and values.
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| subquery | TEXT | SQL query that exposes the data to be analyzed (e.g., `SELECT * FROM interesting_table`). This query must have the geometry column name `the_geom` and id column name `cartodb_id` unless otherwise specified in the input arguments |
+| column_name | TEXT | Name of column (e.g., should be `'interesting_value'` instead of `interesting_value` without single quotes) used for the analysis. |
+| weight type (optional) | TEXT | Type of weight to use when finding neighbors. Currently available options are 'knn' (default) and 'queen'. Read more about weight types in [PySAL's weights documentation](https://pysal.readthedocs.io/en/v1.11.0/users/tutorials/weights.html). |
+| num_ngbrs (optional) | INT | Number of neighbors if using k-nearest neighbors weight type. Defaults to 5. |
+| permutations (optional) | INT | Number of permutations to check against a random arrangement of the values in `column_name`. This influences the accuracy of the output field `significance`. Defaults to 99. |
+| geom_col (optional) | TEXT | The column name for the geometries. Defaults to `'the_geom'` |
+| id_col (optional) | TEXT | The column name for the unique ID of each geometry/value pair. Defaults to `'cartodb_id'`. |
+
+#### Returns
+
+A table with the following columns.
+
+| Column Name | Type | Description |
+|-------------|------|-------------|
+| moran | NUMERIC | Value of Moran's I (spatial autocorrelation measure) for the entire dataset. Values closer to one indicate cluster, closer to -1 mean more outliers, and near zero indicates a random distribution of data. |
+| significance | NUMERIC | The statistical significance of the `moran` measure. |
+
+#### Examples
+
+```sql
+SELECT
+    *
+FROM
+    cdb_crankshaft.CDB_AreasOfInterestGlobal(
+        'SELECT * FROM commute_data',
+        'num_cyclists_per_total_population')
+```
+
+### CDB_AreasOfInterestLocalRate(subquery text, numerator_column text, denominator_column text) (deprecated)
+
+Just like `CDB_AreasOfInterestLocal`, this function classifies your data as being part of a cluster, as an outlier, or not part of a pattern based the significance of a classification. This function differs in that it calculates the classifications based on input `numerator` and `denominator` columns for finding the areas where there are clusters and outliers for the resulting rate of those two values.
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| subquery | TEXT | SQL query that exposes the data to be analyzed (e.g., `SELECT * FROM interesting_table`). This query must have the geometry column name `the_geom` and id column name `cartodb_id` unless otherwise specified in the input arguments |
+| numerator | TEXT | Name of the numerator for forming a rate to be used in analysis. |
+| denominator | TEXT | Name of the denominator for forming a rate to be used in analysis. |
+| weight type (optional) | TEXT | Type of weight to use when finding neighbors. Currently available options are 'knn' (default) and 'queen'. Read more about weight types in [PySAL's weights documentation](https://pysal.readthedocs.io/en/v1.11.0/users/tutorials/weights.html). |
+| num_ngbrs (optional) | INT | Number of neighbors if using k-nearest neighbors weight type. Defaults to 5. |
+| permutations (optional) | INT | Number of permutations to check against a random arrangement of the values in `column_name`. This influences the accuracy of the output field `significance`. Defaults to 99. |
+| geom_col (optional) | TEXT | The column name for the geometries. Defaults to `'the_geom'` |
+| id_col (optional) | TEXT | The column name for the unique ID of each geometry/value pair. Defaults to `'cartodb_id'`. |
+
+#### Returns
+
+A table with the following columns.
+
+| Column Name | Type | Description |
+|-------------|------|-------------|
+| moran | NUMERIC | Value of Moran's I (spatial autocorrelation measure) for the geometry with id of `rowid` |
+| quads | TEXT | Classification of geometry. Result is one of 'HH' (a high value with neighbors high on average), 'LL' (opposite of 'HH'), 'HL' (a high value surrounded by lows on average), and 'LH' (opposite of 'HL'). Null values are returned when nulls exist in the original data. |
+| significance | NUMERIC | The statistical significance (from 0 to 1) of a cluster or outlier classification. Lower numbers are more significant. |
+| rowid | INT | Row id of the values which correspond to the input rows. |
+| vals | NUMERIC | Standardized rate (centered on the mean and normalized by the standard deviation) calculated from `numerator` and `denominator`. This is calculated by [Assuncao Rate](http://pysal.readthedocs.io/en/latest/library/esda/smoothing.html?highlight=assuncao#pysal.esda.smoothing.assuncao_rate) in the PySAL library. |
+
+
+#### Example Usage
+
+```sql
+SELECT
+  c.the_geom,
+  aoi.quads,
+  aoi.significance,
+  c.cyclists_per_total_population
+FROM
+    cdb_crankshaft.CDB_AreasOfInterestLocalRate(
+        'SELECT * FROM commute_data'
+        'num_cyclists',
+        'total_population') As aoi
+JOIN commute_data As c
+ON c.cartodb_id = aoi.rowid;
+```
+
+### CDB_AreasOfInterestGlobalRate(subquery text, column_name text) (deprecated)
+
+This function identifies the extent to which geometries cluster (the groupings of geometries with similarly high or low values relative to the mean) or form outliers (areas where geometries have values opposite of their neighbors). The output of this function gives values between -1 and 1 as well as a significance of that classification. Values close to 0 mean that there is little to no distribution of values as compared to what one would see in a randomly distributed collection of geometries and values.
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| subquery | TEXT | SQL query that exposes the data to be analyzed (e.g., `SELECT * FROM interesting_table`). This query must have the geometry column name `the_geom` and id column name `cartodb_id` unless otherwise specified in the input arguments |
+| numerator | TEXT | Name of the numerator for forming a rate to be used in analysis. |
+| denominator | TEXT | Name of the denominator for forming a rate to be used in analysis. |
+| weight type (optional) | TEXT | Type of weight to use when finding neighbors. Currently available options are 'knn' (default) and 'queen'. Read more about weight types in [PySAL's weights documentation](https://pysal.readthedocs.io/en/v1.11.0/users/tutorials/weights.html). |
+| num_ngbrs (optional) | INT | Number of neighbors if using k-nearest neighbors weight type. Defaults to 5. |
+| permutations (optional) | INT | Number of permutations to check against a random arrangement of the values in `column_name`. This influences the accuracy of the output field `significance`. Defaults to 99. |
+| geom_col (optional) | TEXT | The column name for the geometries. Defaults to `'the_geom'` |
+| id_col (optional) | TEXT | The column name for the unique ID of each geometry/value pair. Defaults to `'cartodb_id'`. |
+
+#### Returns
+
+A table with the following columns.
+
+| Column Name | Type | Description |
+|-------------|------|-------------|
+| moran | NUMERIC | Value of Moran's I (spatial autocorrelation measure) for the entire dataset. Values closer to one indicate cluster, closer to -1 mean more outliers, and near zero indicates a random distribution of data. |
+| significance | NUMERIC | The statistical significance of the `moran` measure. |
+
+#### Examples
+
+```sql
+SELECT
+    *
+FROM
+    cdb_crankshaft.CDB_AreasOfInterestGlobalRate(
+        'SELECT * FROM commute_data',
+        'num_cyclists',
+        'total_population')
+```
+
+## Hotspot, Coldspot, and Outlier Functions
+
+These functions are convenience functions for extracting only information that you are interested in exposing based on the outputs of the `CDB_MoransI*` functions. For instance, you can use `CDB_GetSpatialHotspots` to output only the classifications of `HH` and `HL`.
+
+### Non-rate functions
+
+#### CDB_GetSpatialHotspots
+This function's inputs and outputs exactly mirror `CDB_AreasOfInterestLocal` except that the outputs are filtered to be only 'HH' and 'HL' (areas of high values). For more information about this function's use, see `CDB_AreasOfInterestLocal`.
+
+#### CDB_GetSpatialColdspots
+This function's inputs and outputs exactly mirror `CDB_AreasOfInterestLocal` except that the outputs are filtered to be only 'LL' and 'LH' (areas of low values). For more information about this function's use, see `CDB_AreasOfInterestLocal`.
+
+#### CDB_GetSpatialOutliers
+This function's inputs and outputs exactly mirror `CDB_AreasOfInterestLocal` except that the outputs are filtered to be only 'HL' and 'LH' (areas where highs or lows are surrounded by opposite values on average). For more information about this function's use, see `CDB_AreasOfInterestLocal`.
+
+### Rate functions
+
+#### CDB_GetSpatialHotspotsRate
+
+This function's inputs and outputs exactly mirror `CDB_AreasOfInterestLocalRate` except that the outputs are filtered to be only 'HH' and 'HL' (areas of high values). For more information about this function's use, see `CDB_AreasOfInterestLocalRate`.
+
+#### CDB_GetSpatialColdspotsRate
+
+This function's inputs and outputs exactly mirror `CDB_AreasOfInterestLocalRate` except that the outputs are filtered to be only 'LL' and 'LH' (areas of low values). For more information about this function's use, see `CDB_AreasOfInterestLocalRate`.
+
+#### CDB_GetSpatialOutliersRate
+
+This function's inputs and outputs exactly mirror `CDB_AreasOfInterestLocalRate` except that the outputs are filtered to be only 'HL' and 'LH' (areas where highs or lows are surrounded by opposite values on average). For more information about this function's use, see `CDB_AreasOfInterestLocalRate`.

doc/04_markov.md

@@ -0,0 +1,58 @@
+## Spatial Markov
+
+### CDB_SpatialMarkovTrend(subquery text, column_names text array)
+
+This function takes time series data associated with geometries and outputs likelihoods that the next value of a geometry will move up, down, or stay static as compared to the most recent measurement. For more information, read about [Spatial Dynamics in PySAL](https://pysal.readthedocs.io/en/v1.11.0/users/tutorials/dynamics.html).
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| subquery | TEXT | SQL query that exposes the data to be analyzed (e.g., `SELECT * FROM real_estate_history`). This query must have the geometry column name `the_geom` and id column name `cartodb_id` unless otherwise specified in the input arguments. Tables in queries must exist in user's database (i.e., no CTEs at present) |
+| column_names | TEXT Array | Names of column that form the history of measurements for the geometries (e.g., `Array['y2011', 'y2012', 'y2013', 'y2014', 'y2015', 'y2016']`). |
+| num_classes (optional) | INT | Number of quantile classes to separate data into. |
+| weight type (optional) | TEXT | Type of weight to use when finding neighbors. Currently available options are 'knn' (default) and 'queen'. Read more about weight types in [PySAL's weights documentation](https://pysal.readthedocs.io/en/v1.11.0/users/tutorials/weights.html). |
+| num_ngbrs (optional) | INT | Number of neighbors if using k-nearest neighbors weight type. Defaults to 5. |
+| permutations (optional) | INT | Number of permutations to check against a random arrangement of the values in `column_name`. This influences the accuracy of the output field `significance`. Defaults to 99. |
+| geom_col (optional) | TEXT | The column name for the geometries. Defaults to `'the_geom'` |
+| id_col (optional) | TEXT | The column name for the unique ID of each geometry/value pair. Defaults to `'cartodb_id'`. |
+
+#### Returns
+
+A table with the following columns.
+
+| Column Name | Type | Description |
+|-------------|------|-------------|
+| trend | NUMERIC | The probability that the measure at this location will move up (a positive number) or down (a negative number) |
+| trend_up | NUMERIC | The probability that a measure will move up in subsequent steps of time |
+| trend_down | NUMERIC | The probability that a measure will move down in subsequent steps of time |
+| volatility | NUMERIC | A measure of the variance of the probabilities returned from the Spatial Markov predictions |
+| rowid | NUMERIC | id of the row that corresponds to the `id_col` (by default `cartodb_id` of the input rows)  |
+
+
+#### Notes
+
+*   Rows will null values will be omitted from this analysis. To ensure they are added to the analysis, fill the null-valued cells with an appropriate value such as the mean of a column, the mean of the most recent two time steps, etc.
+*   Input query can only accept tables (datasets) in the users database account. Common table expressions (CTEs) do not work as an input unless specified in the `subquery` parameter.
+
+
+#### Example Usage
+
+```sql
+SELECT
+  c.cartodb_id,
+  c.the_geom,
+  c.the_geom_webmercator,
+  m.trend,
+  m.trend_up,
+  m.trend_down,
+  m.volatility
+FROM
+  cdb_crankshaft.CDB_SpatialMarkovTrend(
+    'SELECT * FROM nyc_real_estate'
+    Array['m03y2009', 'm03y2010', 'm03y2011',
+          'm03y2012', 'm03y2013', 'm03y2014',
+          'm03y2015','m03y2016']) As m
+JOIN nyc_real_estate As c
+ON c.cartodb_id = m.rowid;
+```

doc/04_pyAgg.md

@@ -0,0 +1,23 @@
+## PyAgg Helper Function 
+
+### CDB_pyAgg (columns Numeric[])
+
+Currently it's not possible to pass a multidiemensional array between plpsql and plpythonu. This function aims to
+help fix that by aggergating the columns provided in the argument across rows in to a rows * columns + 1 length 1D array. The first element of the array is the array\_length of the columns argument so that python can reconstruct 
+the 2D array. 
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| columns | NUMERIC[] | The columns to aggregate across rows|
+
+#### Returns
+
+A table with the following columns.
+
+| Column Name | Type | Description |
+|-------------|------|-------------|
+| result | NUMERIC[] | An columns * rows + 1 array where the first entry is the no of columns|
+
+

doc/07_gravity.md

@@ -0,0 +1,81 @@
+## Gravity Model
+
+Gravity Models are derived from Newton's Law of Gravity and are used to predict the interaction between a group of populated areas (sources) and a specific target among a group of potential targets, in terms of an attraction factor (weight)
+
+**CDB_Gravity** is based on the model defined in *Huff's Law of Shopper attraction (1963)*
+
+### CDB_Gravity(t_id bigint[], t_geom geometry[], t_weight numeric[], s_id bigint[], s_geom geometry[], s_pop numeric[], target bigint, radius integer, minval numeric DEFAULT -10e307)
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| t_id     | bigint[]    | Array of targets ID |
+| t_geom   | geometry[]  | Array of targets' geometries |
+| t_weight | numeric[]   | Array of targets's weights |
+| s_id     | bigint[]    | Array of sources ID |
+| s_geom   | geometry[]  | Array of sources' geometries |
+| s_pop    | numeric[]   | Array of sources's population |
+| target   | bigint      | ID of the target under study |
+| radius   | integer     | Radius in meters around the target under study that will be taken into account|
+| minval (optional)   | numeric     | Lowest accepted value of weight, defaults to numeric min_value |
+
+### CDB_Gravity( target_query text, weight_column text, source_query text, pop_column text, target bigint, radius integer, minval numeric DEFAULT -10e307)
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| target_query     | text    | Query that defines targets |
+| weight_column   | text  | Column name of weights |
+| source_query     | text    | Query that defines sources |
+| pop_column   | text  | Column name of population |
+| target   | bigint      | cartodb_id of the target under study |
+| radius   | integer     | Radius in meters around the target under study that will be taken into account|
+| minval (optional)   | numeric     | Lowest accepted value of weight, defaults to numeric min_value |
+
+
+### Returns
+
+| Column Name | Type | Description |
+|-------------|------|-------------|
+| the_geom  | geometry | Geometries of the sources within the radius |
+| source_id | bigint  | ID of the source |
+| target_id | bigint  | Target ID from input |
+| dist      | numeric | Distance in meters source to target (if not points, distance between centroids) |
+| h         | numeric | Probability of patronage |
+| hpop      | numeric | Patronaging population |
+
+
+#### Example Usage
+
+```sql
+with t as (
+SELECT
+    array_agg(cartodb_id::bigint) as id,
+    array_agg(the_geom) as g,
+    array_agg(coalesce(gla, 0)::numeric) as w
+FROM
+    centros_comerciales_de_madrid
+WHERE not no_cc
+),
+s as (
+SELECT
+    array_agg(cartodb_id::bigint) as id,
+    array_agg(center) as g,
+    array_agg(coalesce(t1_1, 0)::numeric) as p
+FROM
+    sscc_madrid
+)
+SELECT
+    g.the_geom,
+    trunc(g.h, 2) as h,
+    round(g.hpop) as hpop,
+    trunc(g.dist/1000, 2) as dist_km
+FROM
+    t,
+    s,
+    cdb_crankshaft.CDB_Gravity(t.id, t.g, t.w, s.id, s.g, s.p, newmall_ID, 100000, 5000) as g
+```
+
+

doc/08_interpolation.md

@@ -0,0 +1,61 @@
+## Spacial interpolation
+
+Function to interpolate a numeric attribute of a point in a scatter dataset of points, using one of three methos:
+
+* [Nearest neighbor(s)](https://en.wikipedia.org/wiki/Nearest-neighbor_interpolation)
+* [Barycentric](https://en.wikipedia.org/wiki/Barycentric_coordinate_system)
+* [IDW](https://en.wikipedia.org/wiki/Inverse_distance_weighting)
+
+### CDB_SpatialInterpolation (query text, point geometry, method integer DEFAULT 1, p1 integer DEFAULT 0, ps integer DEFAULT 0)
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| query   | text | query that returns at least `the_geom` and a numeric value as `attrib` |
+| point   | geometry | The target point to calc the value |
+| method   | integer     | 0:nearest neighbor, 1: barycentric, 2: IDW|
+| p1   | integer     | limit the number of neighbors, IDW: 0->no limit, NN: 0-> closest one|
+| p2   | integer     | IDW: order of distance decay, 0-> order 1|
+
+### CDB_SpatialInterpolation (geom geometry[], values numeric[], point geometry, method integer DEFAULT 1, p1 integer DEFAULT 0, ps integer DEFAULT 0)
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| geom   | geometry[]  | Array of points's geometries |
+| values | numeric[]   | Array of points' values for the param under study|
+| point   | geometry | The target point to calc the value |
+| method   | integer     | 0:nearest neighbor, 1: barycentric, 2: IDW|
+| p1   | integer     | limit the number of neighbors, IDW: 0->no limit, NN: 0-> closest one|
+| p2   | integer     | IDW: order of distance decay, 0-> order 1|
+
+### Returns
+
+| Column Name | Type | Description |
+|-------------|------|-------------|
+| value  | numeric | Interpolated value at the given point, `-888.888` if the given point is out of the boundaries of the source points set |
+
+Default values:
+* -888.888: when using Barycentric, the target point is out of the realm of the input points
+* -777.777: asking for a method not available
+
+#### Example Usage
+
+```sql
+WITH a as (
+    SELECT
+        array_agg(the_geom) as geomin,
+        array_agg(temp::numeric) as colin
+    FROM table_4804232032
+)
+SELECT
+    cdb_crankshaft.CDB_SpatialInterpolation(
+        geomin,
+        colin,
+        CDB_latlng(41.38, 2.15),
+        1)
+FROM
+    a
+```

doc/09_voronoi.md

@@ -0,0 +1,46 @@
+## Voronoi
+
+Function to construct the [Voronoi Diagram](https://en.wikipedia.org/wiki/Voronoi_diagram) from a dataset of scatter points, clipped to the significant area
+
+PostGIS wil include this in future versions ([doc for dev branch](http://postgis.net/docs/manual-dev/ST_Voronoi.html)) and will perform faster for sure, but in the meantime...
+
+
+### CDB_Voronoi (geom geometry[], buffer numeric DEFAULT 0.5, tolerance numeric DEFAULT 1e-9)
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| geom   | geometry[]  | Array of points's geometries |
+| buffer | numeric   | enlargment ratio for the envelope area used for the restraints|
+| tolerance   | numeric |  Delaunay tolerance, optional |
+
+### Returns
+
+| Column Name | Type | Description |
+|-------------|------|-------------|
+| geom  | geometry collection | Collection of polygons of the Voronoi cells|
+
+
+#### Example Usage
+
+```sql
+WITH a AS (
+    SELECT
+        ARRAY[
+            ST_GeomFromText('POINT(2.1744 41.403)', 4326),
+            ST_GeomFromText('POINT(2.1228 41.380)', 4326),
+            ST_GeomFromText('POINT(2.1511 41.374)', 4326),
+            ST_GeomFromText('POINT(2.1528 41.413)', 4326),
+            ST_GeomFromText('POINT(2.165 41.391)', 4326),
+            ST_GeomFromText('POINT(2.1498 41.371)', 4326),
+            ST_GeomFromText('POINT(2.1533 41.368)', 4326),
+            ST_GeomFromText('POINT(2.131386 41.41399)', 4326)
+        ] AS geomin
+)
+SELECT
+    ST_TRANSFORM(
+        (ST_Dump(cdb_crankshaft.CDB_Voronoi(geomin, 0.2, 1e-9))).geom,
+        3857) as the_geom_webmercator
+FROM a;
+```

doc/11_kmeans.md

@@ -0,0 +1,122 @@
+## K-Means Functions
+
+k-means clustering is a popular technique for finding clusters in data by minimizing the intra-cluster 'distance' and maximizing the inter-cluster 'distance'. The distance is defined in the parameter space of the variables entered.
+
+### CDB_KMeans(subquery text, no_clusters integer)
+
+This function attempts to find `no_clusters` clusters within the input data based on the geographic distribution. It will return a table with ids and the cluster classification of each point input assuming `the_geom` is not null-valued. If `the_geom` is null-valued, the point will not be considered in the analysis.
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| subquery | TEXT | SQL query that exposes the data to be analyzed (e.g., `SELECT * FROM interesting_table`). This query must have the geometry column name `the_geom` and id column name `cartodb_id` unless otherwise specified in the input arguments |
+| no\_clusters | INTEGER | The number of clusters to find |
+
+#### Returns
+
+A table with the following columns.
+
+| Column Name | Type | Description |
+|-------------|------|-------------|
+| cartodb\_id | INTEGER | The row id of the row from the input table |
+| cluster\_no | INTEGER | The cluster that this point belongs to |
+
+
+#### Example Usage
+
+```sql
+SELECT
+    customers.*,
+    km.cluster_no
+FROM
+    cdb_crankshaft.CDB_KMeans('SELECT * from customers' , 6) As km,
+    customers
+WHERE
+    customers.cartodb_id = km.cartodb_id
+```
+
+### CDB_WeightedMean(subquery text, weight_column text, category_column text)
+
+Function that computes the weighted centroid of a number of clusters by some weight column.
+
+### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| subquery | TEXT | SQL query that exposes the data to be analyzed (e.g., `SELECT * FROM interesting_table`). This query must have the geometry column and the columns specified as the weight and category columns|
+| weight\_column | TEXT | The name of the column to use as a weight |
+| category\_column | TEXT | The name of the column to use as a category |
+
+### Returns
+
+A table with the following columns.
+
+| Column Name | Type | Description |
+|-------------|------|-------------|
+| the\_geom | GEOMETRY | A point for the weighted cluster center |
+| class | INTEGER | The cluster class |
+
+### Example Usage
+
+```sql
+SELECT
+    ST_Transform(km.the_geom, 3857) As the_geom_webmercator,
+    km.class
+FROM
+    cdb_crankshaft.CDB_WeightedMean(
+        'SELECT *, customer_value FROM customers',
+        'customer_value',
+        'cluster_no') As km
+```
+
+## CDB_KMeansNonspatial(subquery text, colnames text[], no_clusters int)
+
+K-means clustering classifies the rows of your dataset into `no_clusters` by finding the centers (means) of the variables in `colnames` and classifying each row by it's proximity to the nearest center. This method partitions space into distinct Voronoi cells.
+
+As a standard machine learning method, k-means clustering is an unsupervised learning technique that finds the natural clustering of values. For instance, it is useful for finding subgroups in census data leading to demographic segmentation.
+
+### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| query | TEXT | SQL query to expose the data to be used in the analysis (e.g., `SELECT * FROM iris_data`). It should contain at least the columns specified in `colnames` and the `id_colname`. |
+| colnames | TEXT[] | Array of columns to be used in the analysis (e.g., `Array['petal_width', 'sepal_length', 'petal_length']`). |
+| no\_clusters | INTEGER | Number of clusters for the classification of the data |
+| id\_col (optional) | TEXT | The id column (default: 'cartodb_id') for identifying rows |
+| standarize (optional) | BOOLEAN | Setting this to true (default) standardizes the data to have a mean at zero and a standard deviation of 1 |
+
+### Returns
+
+A table with the following columns.
+
+| Column | Type | Description |
+|--------|------|-------------|
+| cluster_label | TEXT | Label that a cluster belongs to, number from 0 to `no_clusters - 1`. |
+| cluster_center | JSON | Center of the cluster that a row belongs to. The keys of the JSON object are the `colnames`, with values that are the center of the respective cluster |
+| silhouettes | NUMERIC | [Silhouette score](http://scikit-learn.org/stable/modules/generated/sklearn.metrics.silhouette_score.html#sklearn.metrics.silhouette_score) of the cluster label |
+| inertia | NUMERIC | Sum of squared distances of samples to their closest cluster center |
+| rowid | BIGINT | id of the original row for associating back with the original data |
+
+### Example Usage
+
+```sql
+SELECT
+    customers.*,
+    km.cluster_label,
+    km.cluster_center,
+    km.silhouettes
+FROM
+    cdb_crankshaft.CDB_KMeansNonspatial(
+        'SELECT * FROM customers',
+        Array['customer_value', 'avg_amt_spent', 'home_median_income'],
+        7) As km,
+    customers
+WHERE
+    customers.cartodb_id = km.rowid
+```
+
+### Resources
+
+-   Read more in [scikit-learn's documentation](http://scikit-learn.org/stable/modules/clustering.html#k-means)
+-   [K-means basics](https://www.datascience.com/blog/introduction-to-k-means-clustering-algorithm-learn-data-science-tutorials)

doc/12_segmentation.md

@@ -0,0 +1,83 @@
+
+## Segmentation Functions
+
+### CDB_CreateAndPredictSegment(query TEXT, variable_name TEXT, target_query TEXT)
+
+This function trains a [Gradient Boosting](http://scikit-learn.org/stable/modules/generated/sklearn.ensemble.GradientBoostingRegressor.html) model to attempt to predict the target data and then generates predictions for new data.
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| query | TEXT | The input query to train the algorithm, which should have both the variable of interest and the features that will be used to predict it |
+| variable\_name| TEXT | Specify the variable in the query to predict, all other columns are assumed to be features |
+| target\_table | TEXT | The query which returns the `cartodb_id` and features for the rows your would like to predict the target variable for |
+| n\_estimators (optional) | INTEGER DEFAULT 1200 | Number of estimators to be used. Values should be between 1 and x. |
+| max\_depth (optional) | INTEGER DEFAULT 3 | Max tree depth. Values should be between 1 and n. |
+| subsample (optional)  | DOUBLE PRECISION DEFAULT 0.5 | Subsample parameter for GradientBooster. Values should be within the range 0 to 1. |
+| learning\_rate (optional) | DOUBLE PRECISION DEFAULT 0.01 | Learning rate for the GradientBooster. Values should be between 0 and 1 (??) |
+| min\_samples\_leaf (optional) | INTEGER DEFAULT 1 | Minimum samples to use per leaf. Values should range from x to y |
+
+#### Returns
+
+A table with the following columns.
+
+| Column Name | Type | Description |
+|-------------|------|-------------|
+| cartodb\_id | INTEGER | The CartoDB id of the row in the target\_query |
+| prediction | NUMERIC | The predicted value of the variable of interest |
+| accuracy | NUMERIC | The mean squared accuracy of the model. |
+
+#### Example Usage
+
+```sql
+SELECT * from cdb_crankshaft.CDB_CreateAndPredictSegment(
+'SELECT agg, median_rent::numeric, male_pop::numeric, female_pop::numeric FROM late_night_agg',
+'agg',
+'SELECT row_number() OVER () As cartodb_id, median_rent, male_pop, female_pop FROM ml_learning_ny');
+```
+
+### CDB_CreateAndPredictSegment(target numeric[], train_features numeric[], prediction_features numeric[], prediction_ids numeric[])
+
+This function trains a [Gradient Boosting](http://scikit-learn.org/stable/modules/generated/sklearn.ensemble.GradientBoostingRegressor.html) model to attempt to predict the target data and then generates predictions for new data.
+
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| target | numeric[] | An array of target values of the variable you want to predict|
+| train\_features| numeric[] | 1D array of length n features \* n\_rows + 1 with the first entry in the array being the number of features in each row. These are the features the model will be trained on. CDB\_Crankshaft.CDB_pyAgg(Array[feature1, feature2, feature3]::numeric[]) can be used to construct this. |
+| prediction\_features | numeric[] | 1D array of length nfeatures\* n\_rows\_ + 1 with the first entry in the array being the number of features in each row. These are the features that will be used to predict the target variable  CDB\_Crankshaft.CDB\_pyAgg(Array[feature1, feature2, feature3]::numeric[]) can be used to construct this.  |
+| prediction\_ids | numeric[] | 1D array of length n\_rows with the ids that can use used to re-join the data with inputs |
+| n\_estimators (optional) | INTEGER DEFAULT 1200 | Number of estimators to be used |
+| max\_depth (optional) | INTEGER DEFAULT 3 | Max tree depth |
+| subsample (optional)  | DOUBLE PRECISION DEFAULT 0.5 | Subsample parameter for GradientBooster|
+| learning\_rate (optional) | DOUBLE PRECISION DEFAULT 0.01 | Learning rate for the GradientBooster |
+| min\_samples\_leaf (optional) | INTEGER DEFAULT 1 | Minimum samples to use per leaf |
+
+
+#### Returns
+
+A table with the following columns.
+
+| Column Name | Type | Description |
+|-------------|------|-------------|
+| cartodb\_id | INTEGER | The CartoDB id of the row in the target\_query |
+| prediction | NUMERIC | The predicted value of the variable of interest |
+| accuracy | NUMERIC | The mean squared accuracy of the model. |
+
+#### Example Usage
+
+```sql
+WITH training As (
+    SELECT array_agg(agg) As target,
+           cdb_crankshaft.CDB_PyAgg(Array[median_rent, male_pop, female_pop]::Numeric[]) As features
+    FROM late_night_agg),
+target AS (
+    SELECT cdb_crankshaft.CDB_PyAgg(Array[median_rent, male_pop, female_pop]::Numeric[]) As features,
+     array_agg(cartodb_id) As cartodb_ids FROM late_night_agg)
+
+SELECT cdb_crankshaft.CDB_CreateAndPredictSegment(training.target, training.features, target.features, target.cartodb_ids)
+FROM training, target;
+```

doc/13_PIA.md

@@ -0,0 +1,39 @@
+## Pole of inaccessibility (PIA)
+
+Function to find the [PIA](https://en.wikipedia.org/wiki/Pole_of_inaccessibility) from a given polygon and tolerance, following the quadtree approach by [Vladimir Agafonkin](https://github.com/mourner) described [here](https://github.com/mapbox/polylabel)
+
+
+
+### CDB_PIA (polygon geometry, tolerance numeric DEFAULT 1.0)
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| polygon   | geometry  | Target polygon |
+| tolerance   | numeric | Threshold to decide to take a cell into account |
+
+### Returns
+
+| Column Name | Type | Description |
+|-------------|------|-------------|
+| point  | geometry| Pole of inaccessibility |
+
+
+#### Example Usage
+
+```sql
+WITH a as (
+    SELECT
+        ST_GeomFromText(
+            'POLYGON((-432540.453078056 4949775.20452642,-432329.947920966 4951361.232584,-431245.028163694 4952223.31516671,-429131.071033529 4951768.00415574,-424622.07505895 4952843.13503987,-423688.327170174 4953499.20752423,-424086.294349759 4954968.38274191,-423068.388925945 4954378.63345336,-423387.653225542 4953355.67417084,-420594.869840519 4953781.00230592,-416026.095299382 4951484.06849063,-412483.018546414 4951024.5410983,-410490.399661215 4954502.24032205,-408186.197521284 4956398.91417441,-407627.262358013 4959300.94633864,-406948.770061627 4959874.85407739,-404949.583326472 4959047.74518163,-402570.908447199 4953743.46829807,-400971.358683991 4952193.11680804,-403533.488084088 4949649.89857885,-406335.177028373 4950193.19571096,-407790.456731515 4952391.46015616,-412060.672398345 4950381.2389307,-410716.93482498 4949156.7509561,-408464.162289794 4943912.8940387,-409350.599394983 4942819.84896006,-408087.791091424 4942451.6711778,-407274.045613725 4940572.4807777,-404446.196589102 4939976.71501489,-402422.964843936 4940450.3670813,-401010.654464241 4939054.8061663,-397647.247369412 4940679.80737878,-395658.413346901 4940528.84765185,-395536.852462953 4938829.79565997,-394268.923462818 4938003.7277717,-393388.720249116 4934757.80596815,-392393.301362444 4934326.71675815,-392573.527618037 4932323.40974412,-393464.640141837 4931903.10653605,-393085.597275686 4931094.7353605,-398426.261165985 4929156.87541607,-398261.174361137 4926238.00816416,-394045.059966834 4925765.18668498,-392982.960705174 4926391.81893628,-393090.272694301 4927176.84692181,-391648.240010564 4924626.06386961,-391889.914625075 4923086.14787613,-394345.177314013 4923235.086036,-395550.878718795 4917812.79243978,-399009.463978251 4912927.7157945,-398948.794855767 4911941.91010796,-398092.636652078 4911806.57392519,-401991.601817112 4911722.9204501,-406225.972607907 4914505.47286319,-411104.994569885 4912569.26941163,-412925.513522316 4913030.3608866,-414630.148884835 4914436.69169949,-414207.691417276 4919205.78028405,-418306.141109809 4917994.9580478,-424184.700779621 4918938.12432889,-426816.961458921 4923664.37379373,-420956.324227126 4923381.98014807,-420186.661267781 4924286.48693378,-420943.411166194 4926812.76394433,-419779.45457046 4928527.43466337,-419768.767899344 4930681.94459216,-421911.668097113 4930432.40620397,-423482.386112205 4933451.28047252,-427272.814773717 4934151.56473242,-427144.908678797 4939731.77191996,-428982.125554848 4940522.84445172,-428986.133056516 4942437.17281266,-431237.792396792 4947309.68284815,-432476.889648814 4947791.74800037,-432540.453078056 4949775.20452642))',
+            3857) as g
+),
+b as (
+    SELECT ST_Transform(g, 4326) as g
+    FROM a
+)
+SELECT
+    ST_AsText(cdb_crankshaft.CDB_PIA(g))
+FROM b
+```

doc/14_densify.md

@@ -0,0 +1,45 @@
+## Densify function
+
+Iterative densification of a set of scattered points using Delaunay triangulation. The new points are located at the centroids of the grid cells and  have as assigned value the barycentric average value of the cell's vertex.
+
+### CDB_Densify(geomin geometry[], colin numeric[], iterations integer)
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| geomin   | geometry[]  | Array of points geometries |
+| colin | numeric[]   | Array of points' values |
+| iterations   | integer     | Number of iterations |
+
+### Returns
+
+Returns a table object
+
+| Name | Type | Description |
+|------|------|-------------|
+| geomout   | geometry  | Geometries of new dataset of points|
+| colout | numeric   | Values of points|
+
+#### Example Usage
+
+```sql
+WITH data as (
+    SELECT
+        ARRAY[7.0,8.0,1.0,2.0,3.0,5.0,6.0,4.0] as colin,
+        ARRAY[
+            ST_GeomFromText('POINT(2.1744 41.4036)'),
+            ST_GeomFromText('POINT(2.1228 41.3809)'),
+            ST_GeomFromText('POINT(2.1511 41.3742)'),
+            ST_GeomFromText('POINT(2.1528 41.4136)'),
+            ST_GeomFromText('POINT(2.165 41.3917)'),
+            ST_GeomFromText('POINT(2.1498 41.3713)'),
+            ST_GeomFromText('POINT(2.1533 41.3683)'),
+            ST_GeomFromText('POINT(2.131386 41.413998)')
+        ] as geomin
+)
+SELECT cdb_crankshaft.CDB_Densify(geomin, colin, 2)
+FROM data
+```
+
+

doc/15_tinmap.md

@@ -0,0 +1,44 @@
+## TINMAP function
+
+Generates a fake contour map, in the form of a TIN map, from a set of scattered points.Depends on **CDB_Densify**.
+
+Its iterative nature lets the user smooth the final result as much as desired, but with a exponential time cost increase.
+
+### CDB_TINmap(geomin geometry[], colin numeric[], iterations integer)
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| geomin   | geometry[]  | Array of points geometries |
+| colin | numeric[]   | Array of points' values |
+| iterations   | integer     | Number of iterations |
+
+### Returns
+
+Returns a table object
+
+| Name | Type | Description |
+|------|------|-------------|
+| geomout   | geometry  | Geometries of new dataset of polygons|
+| colout | numeric   | Values of each cell|
+
+#### Example Usage
+
+```sql
+WITH data as (
+    SELECT
+        ARRAY[7.0,8.0,1.0,2.0,3.0,5.0,6.0,4.0] as colin,
+        ARRAY[ST_GeomFromText('POINT(2.1744 41.4036)'),
+			ST_GeomFromText('POINT(2.1228 41.3809)'),
+			ST_GeomFromText('POINT(2.1511 41.3742)'),
+			ST_GeomFromText('POINT(2.1528 41.4136)'),
+			ST_GeomFromText('POINT(2.165 41.3917)'),
+			ST_GeomFromText('POINT(2.1498 41.3713)'),
+			ST_GeomFromText('POINT(2.1533 41.3683)'),
+			ST_GeomFromText('POINT(2.131386 41.413998)')] as geomin
+)
+SELECT cdb_crankshaft.CDB_TINmap(geomin, colin, 2)
+FROM data
+```
+

doc/16_getis_ord_gstar.md

@@ -0,0 +1,40 @@
+## Getis-Ord's G\*
+
+Getis-Ord's G\* is a geo-statistical measurement of the intensity of clustering of high or low values. The clustering of high values can be referred to as "hotspots" because these are areas of high activity or large (relative to the global mean) measurement values. Coldspots are clustered areas with low activity or small measurement values.
+
+### CDB_GetisOrdsG(subquery text, column_name text)
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| subquery | text | A query of the data you want to pass to the function. It must include `column_name`, a geometry column (usually `the_geom`) and an id column (usually `cartodb_id`) |
+| column_name | text | This is the column of interest for performing this analysis on. This column should be a numeric type. |
+| w_type (optional) | text | Type of weight to use when finding neighbors. Currently available options are 'knn' (default) and 'queen'. Read more about weight types in [PySAL's weights documentation.](https://pysal.readthedocs.io/en/v1.11.0/users/tutorials/weights.html) |
+| num_ngbrs (optional) | integer | Default: 5. If `knn` is chosen, this will set the number of neighbors. If `knn` is not chosen, any entered value will be ignored. Use `NULL` if not choosing `knn`. |
+| permutations (optional) | integer | The number of permutations for calculating p-values. Default: 999 |
+| geom_col (optional) | text | The column where the geometry information is stored. The format must be PostGIS Geometry type (SRID 4326). Default: `the_geom`. |
+| id_col (optional) | text | The column that has the unique row identifier. |
+
+### Returns
+
+Returns a table with the following columns.
+
+| Name | Type | Description |
+|------|------|-------------|
+| z_score | numeric | z-score, a measure of the intensity of clustering of high values (hotspots) or low values (coldspots). Positive values represent 'hotspots', while negative values represent 'coldspots'. |
+| p_value | numeric  | p-value, a measure of the significance of the intensity of clustering |
+| p_z_sim | numeric | p-value based on standard normal approximation from permutations |
+| rowid | integer | The original `id_col` that can be used to associate the outputs with the original geometry and inputs |
+
+#### Example Usage
+
+The following query returns the original table augmented with the values calculated from the Getis-Ord's G\* analysis.
+
+```sql
+SELECT i.*, m.z_score, m.p_value
+  FROM cdb_crankshaft.CDB_GetisOrdsG('SELECT * FROM incident_reports_clustered',
+                                     'num_incidents') As m
+  JOIN incident_reports_clustered As i
+    ON i.cartodb_id = m.rowid;
+```

doc/18_outliers.md

@@ -0,0 +1,163 @@
+## Outlier Detection
+
+This set of functions detects the presence of outliers. There are three functions for finding outliers from non-spatial data:
+
+1. Static Outliers
+1. Percentage Outliers
+1. Standard Deviation Outliers
+
+### CDB_StaticOutlier(column_value numeric, threshold numeric)
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| column_value | numeric | The column of values on which to apply the threshold |
+| threshold | numeric | The static threshold which is used to indicate whether a `column_value` is an outlier or not |
+
+### Returns
+
+Returns a boolean (true/false) depending on whether a value is above or below (or equal to) the threshold
+
+| Name | Type | Description |
+|------|------|-------------|
+| outlier | boolean | classification of whether a row is an outlier or not |
+
+#### Example Usage
+
+With a table `website_visits` and a column of the number of website visits in units of 10,000 visits:
+
+```
+| id | visits_10k |
+|----|------------|
+| 1  | 1 |
+| 2  | 3 |
+| 3  | 5 |
+| 4  | 1 |
+| 5  | 32 |
+| 6  | 3 |
+| 7  | 57 |
+| 8  | 2 |
+```
+
+```sql
+SELECT
+  id,
+  cdb_crankshaft.CDB_StaticOutlier(visits_10k, 11.0) As outlier,
+  visits_10k
+FROM website_visits
+```
+
+```
+| id | outlier | visits_10k |
+|----|---------|------------|
+| 1  | f | 1 |
+| 2  | f | 3 |
+| 3  | f | 5 |
+| 4  | f | 1 |
+| 5  | t | 32 |
+| 6  | f | 3 |
+| 7  | t | 57 |
+| 8  | f | 2 |
+```
+
+### CDB_PercentOutlier(column_values numeric[], outlier_fraction numeric, ids int[])
+
+`CDB_PercentOutlier` calculates whether or not a value falls above a given threshold based on a percentage above the mean value of the input values.
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| column_values | numeric[] | An array of the values to calculate the outlier classification on |
+| outlier_fraction | numeric | The threshold above which a column value divided by the mean of all values is considered an outlier |
+| ids | int[] | An array of the unique row ids of the input data (usually `cartodb_id`) |
+
+### Returns
+
+Returns a table of the outlier classification with the following columns
+
+| Name | Type | Description |
+|------|------|-------------|
+| is_outlier | boolean  | classification of whether a row is an outlier or not |
+| rowid | int | original row id (e.g., input `cartodb_id`) of the row which has the outlier classification |
+
+#### Example Usage
+
+This example find outliers which are more than 100% larger than the average (that is, more than 2.0 times larger).
+
+```sql
+WITH cte As (
+  SELECT
+    unnest(Array[1,2,3,4,5,6,7,8]) As id,
+    unnest(Array[1,3,5,1,32,3,57,2]) As visits_10k
+  )
+SELECT
+  (cdb_crankshaft.CDB_PercentOutlier(array_agg(visits_10k), 2.0, array_agg(id))).*
+FROM cte;
+```
+
+Output
+```
+| outlier | rowid |
+|---------+-------|
+| f | 1 |
+| f | 2 |
+| f | 3 |
+| f | 4 |
+| t | 5 |
+| f | 6 |
+| t | 7 |
+| f | 8 |
+```
+
+### CDB_StdDevOutlier(column_values numeric[], num_deviations numeric, ids int[], is_symmetric boolean DEFAULT true)
+
+`CDB_StdDevOutlier` calculates whether or not a value falls above or below a given threshold based on the number of standard deviations from the mean.
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| column_values | numeric[] | An array of the values to calculate the outlier classification on |
+| num_deviations | numeric | The threshold in units of standard deviation |
+| ids | int[] | An array of the unique row ids of the input data (usually `cartodb_id`) |
+| is_symmetric (optional) | boolean | Consider outliers that are symmetric about the mean (default: true) |
+
+### Returns
+
+Returns a table of the outlier classification with the following columns
+
+| Name | Type | Description |
+|------|------|-------------|
+| is_outlier | boolean  | classification of whether a row is an outlier or not |
+| rowid | int | original row id (e.g., input `cartodb_id`) of the row which has the outlier classification |
+
+#### Example Usage
+
+This example find outliers which are more than 100% larger than the average (that is, more than 2.0 times larger).
+
+```sql
+WITH cte As (
+  SELECT
+    unnest(Array[1,2,3,4,5,6,7,8]) As id,
+    unnest(Array[1,3,5,1,32,3,57,2]) As visits_10k
+  )
+SELECT
+  (cdb_crankshaft.CDB_StdDevOutlier(array_agg(visits_10k), 2.0, array_agg(id))).*
+FROM cte;
+```
+
+Output
+```
+| outlier | rowid |
+|---------+-------|
+| f | 1 |
+| f | 2 |
+| f | 3 |
+| f | 4 |
+| f | 5 |
+| f | 6 |
+| t | 7 |
+| f | 8 |
+```

doc/19_contour.md

@@ -0,0 +1,50 @@
+## Contour maps
+
+Function to generate a contour map from an scatter dataset of points, using one of these three methods:
+
+* [Nearest neighbor](https://en.wikipedia.org/wiki/Nearest-neighbor_interpolation)
+* [Barycentric](https://en.wikipedia.org/wiki/Barycentric_coordinate_system)
+* [IDW](https://en.wikipedia.org/wiki/Inverse_distance_weighting)
+
+### CDB_Contour (geom geometry[], values numeric[], resolution integer, buffer numeric, method, classmethod integer, steps integer)
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| geom   | geometry[]  | Array of points's geometries |
+| values | numeric[]   | Array of points' values for the param under study|
+| buffer   | numeric     | Value between 0 and 1 for spatial buffer of the set of points
+| method   | integer     | 0:nearest neighbor, 1: barycentric, 2: IDW|
+| classmethod   | integer     | 0:equals, 1: heads&tails, 2:jenks, 3:quantiles |
+| steps   | integer     | Number of steps in the classification|
+| max_time   | integer     | if <= 0: max processing time in seconds (smart resolution) , if >0: resolution in meters
+
+### Returns
+Returns a table object
+
+| Name | Type | Description |
+|------|------|-------------|
+| the_geom   | geometry  | Geometries of the classified contour map|
+| avg_value | numeric   | Avg value of the area|
+| min_value | numeric   | Min value of the area|
+| max_value | numeric   | Max value of the areal|
+| bin | integer   | Index of the class of the area|
+
+#### Example Usage
+
+```sql
+WITH a AS (
+    SELECT
+    ARRAY[800, 700, 600, 500, 400, 300, 200, 100]::numeric[] AS vals,
+    ARRAY[ST_GeomFromText('POINT(2.1744 41.403)',4326),ST_GeomFromText('POINT(2.1228 41.380)',4326),ST_GeomFromText('POINT(2.1511 41.374)',4326),ST_GeomFromText('POINT(2.1528 41.413)',4326),ST_GeomFromText('POINT(2.165 41.391)',4326),ST_GeomFromText('POINT(2.1498 41.371)',4326),ST_GeomFromText('POINT(2.1533 41.368)',4326),ST_GeomFromText('POINT(2.131386 41.41399)',4326)] AS g
+),
+b as(
+SELECT
+    foo.*
+FROM
+    a,
+    cdb_crankshaft.CDB_contour(a.g, a.vals,  0.0, 1, 3, 5, 60) foo
+)
+SELECT bin, avg_value from b order by bin;
+```

doc/21_gwr.md

@@ -0,0 +1,128 @@
+## Regression
+
+### Predictive geographically weighted regression (GWR)
+
+Predictive GWR generates estimates of the dependent variable at locations where it has not been observed. It predicts these unknown values by first using the GWR model estimation analysis with known data values of the dependent and independent variables sampled from around the prediction location(s) to build a geographically weighted, spatially-varying regression model. It then uses this model and known values of the independent variables at the prediction locations to predict the value of the dependent variable where it is otherwise unknown.
+
+For predictive GWR to work, a dataset needs known independent variables, some known dependent variables, and some unknown dependent variables. The dataset also needs to have geometry data (e.g., point, lines, or polygons).
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| subquery | TEXT | SQL query that expose the data to be analyzed (e.g., `SELECT * FROM regression_inputs`). This query must have the geometry column name (see the optional `geom_col` for default), the id column name (see `id_col`), and the dependent (`dep_var`) and independent (`ind_vars`) column names. |
+| dep_var | TEXT | Name of the dependent variable in the regression model |
+| ind_vars | TEXT[] | Text array of independent variable column names used in the model to describe the dependent variable. |
+| bw (optional) | NUMERIC | Value of bandwidth. If `NULL` then select optimal (default). |
+| fixed (optional) | BOOLEAN | True for distance based kernel function and False (default) for adaptive (nearest neighbor) kernel function. Defaults to `False`. |
+| kernel (optional)| TEXT | Type of kernel function used to weight observations. One of `gaussian`, `bisquare` (default), or `exponential`. |
+
+
+#### Returns
+
+| Column Name | Type | Description |
+|-------------|------|-------------|
+| coeffs | JSON | JSON object with parameter estimates for each of the dependent variables. The keys of the JSON object are the dependent variables, with values corresponding to the parameter estimate. |
+| stand_errs | JSON | Standard errors for each of the dependent variables. The keys of the JSON object are the dependent variables, with values corresponding to the respective standard errors. |
+| t_vals | JSON | T-values for each of the dependent variables. The keys of the JSON object are the dependent variable names, with values corresponding to the respective t-value. |
+| predicted | NUMERIC | predicted value of y |
+| residuals | NUMERIC | residuals of the response |
+| r_squared | NUMERIC | R-squared for the parameter fit |
+| bandwidth | NUMERIC | bandwidth value consisting of either a distance or N nearest neighbors |
+| rowid | INTEGER | row id of the original row |
+
+
+#### Example Usage
+
+```sql
+SELECT
+  g.cartodb_id,
+  g.the_geom,
+  g.the_geom_webmercator,
+  (gwr.coeffs->>'pctblack')::numeric as coeff_pctblack,
+  (gwr.coeffs->>'pctrural')::numeric as coeff_pctrural,
+  (gwr.coeffs->>'pcteld')::numeric as coeff_pcteld,
+  (gwr.coeffs->>'pctpov')::numeric as coeff_pctpov,
+  gwr.residuals
+FROM cdb_crankshaft.CDB_GWR_Predict('select * from g_utm'::text,   
+  'pctbach'::text,
+  Array['pctblack', 'pctrural', 'pcteld', 'pctpov']) As gwr
+JOIN g_utm as g
+on g.cartodb_id = gwr.rowid
+```
+
+Note: See [PostgreSQL syntax for parsing JSON objects](https://www.postgresql.org/docs/9.5/static/functions-json.html).
+
+### Geographically weighted regression model estimation
+
+This analysis generates the model coefficients for a geographically weighted, spatially-varying regression. The model coefficients, along with their respective statistics, allow one to make inferences or describe a dependent variable based on a set of independent variables. Similar to traditional linear regression, GWR takes a linear combination of independent variables and a known dependent variable to estimate an optimal set of coefficients. The model coefficients are spatially varying (controlled by the `bandwidth` and `fixed` parameters), so that the model output is allowed to vary from geometry to geometry. This allows GWR to capture non-stationarity -- that is, how local processes vary over space. In contrast, coefficients obtained from estimating a traditional linear regression model assume that processes are constant over space.
+
+#### Arguments
+
+| Name | Type | Description |
+|------|------|-------------|
+| subquery | TEXT | SQL query that expose the data to be analyzed (e.g., `SELECT * FROM regression_inputs`). This query must have the geometry column name (see the optional `geom_col` for default), the id column name (see `id_col`), dependent and independent column names. |
+| dep_var | TEXT | name of the dependent variable in the regression model |
+| ind_vars | TEXT[] | Text array of independent variables used in the model to describe the dependent variable |
+| bw (optional) | NUMERIC | Value of bandwidth. If `NULL` then select optimal (default). |
+| fixed (optional) | BOOLEAN | True for distance based kernel function and False for adaptive (nearest neighbor) kernel function (default). Defaults to false. |
+| kernel | TEXT | Type of kernel function used to weight observations. One of `gaussian`, `bisquare` (default), or `exponential`. |
+
+
+#### Returns
+
+| Column Name | Type | Description |
+|-------------|------|-------------|
+| coeffs | JSON | JSON object with parameter estimates for each of the dependent variables. The keys of the JSON object are the dependent variables, with values corresponding to the parameter estimate. |
+| stand_errs | JSON | Standard errors for each of the dependent variables. The keys of the JSON object are the dependent variables, with values corresponding to the respective standard errors. |
+| t_vals | JSON | T-values for each of the dependent variables. The keys of the JSON object are the dependent variable names, with values corresponding to the respective t-value. |
+| predicted | NUMERIC | predicted value of y |
+| residuals | NUMERIC | residuals of the response |
+| r_squared | NUMERIC | R-squared for the parameter fit |
+| bandwidth | NUMERIC | bandwidth value consisting of either a distance or N nearest neighbors |
+| rowid | INTEGER | row id of the original row |
+
+
+#### Example Usage
+
+```sql
+SELECT
+  g.cartodb_id,
+  g.the_geom,
+  g.the_geom_webmercator,
+  (gwr.coeffs->>'pctblack')::numeric as coeff_pctblack,
+  (gwr.coeffs->>'pctrural')::numeric as coeff_pctrural,
+  (gwr.coeffs->>'pcteld')::numeric as coeff_pcteld,
+  (gwr.coeffs->>'pctpov')::numeric as coeff_pctpov,
+  gwr.residuals
+FROM cdb_crankshaft.CDB_GWR('select * from g_utm'::text, 'pctbach'::text, Array['pctblack', 'pctrural', 'pcteld', 'pctpov']) As gwr
+JOIN g_utm as g
+on g.cartodb_id = gwr.rowid
+```
+
+Note: See [PostgreSQL syntax for parsing JSON objects](https://www.postgresql.org/docs/9.5/static/functions-json.html).
+
+
+## Advanced reading
+
+*   Fotheringham, A. Stewart, Chris Brunsdon, and Martin Charlton. 2002. Geographically Weighted Regression: The Analysis of Spatially Varying Relationships. John Wiley & Sons. <http://www.wiley.com/WileyCDA/WileyTitle/productCd-0471496162.html>
+
+*   Brunsdon, Chris, A. Stewart Fotheringham, and Martin E. Charlton. 1996. "Geographically Weighted Regression: A Method for Exploring Spatial Nonstationarity." Geographical Analysis 28 (4): 281–98. <http://onlinelibrary.wiley.com/doi/10.1111/j.1538-4632.1996.tb00936.x/abstract>
+
+*   Brunsdon, Chris, Stewart Fotheringham, and Martin Charlton. 1998. "Geographically Weighted Regression." Journal of the Royal Statistical Society: Series D (The Statistician) 47 (3): 431–43. <http://onlinelibrary.wiley.com/doi/10.1111/1467-9884.00145/abstract>
+
+*   Fotheringham, A. S., M. E. Charlton, and C. Brunsdon. 1998. "Geographically Weighted Regression: A Natural Evolution of the Expansion Method for Spatial Data Analysis." Environment and Planning A 30 (11): 1905–27. doi:10.1068/a301905. <https://www.researchgate.net/publication/23538637_Geographically_Weighted_Regression_A_Natural_Evolution_Of_The_Expansion_Method_for_Spatial_Data_Analysis>
+
+### GWR for prediction
+
+*   Harris, P., A. S. Fotheringham, R. Crespo, and M. Charlton. 2010. "The Use of Geographically Weighted Regression for Spatial Prediction: An Evaluation of Models Using Simulated Data Sets." Mathematical Geosciences 42 (6): 657–80. doi:10.1007/s11004-010-9284-7. <https://www.researchgate.net/publication/225757830_The_Use_of_Geographically_Weighted_Regression_for_Spatial_Prediction_An_Evaluation_of_Models_Using_Simulated_Data_Sets>
+
+### GWR in application
+
+*   Cahill, Meagan, and Gordon Mulligan. 2007. "Using Geographically Weighted Regression to Explore Local Crime Patterns." Social Science Computer Review 25 (2): 174–93. doi:10.1177/0894439307298925. <http://isites.harvard.edu/fs/docs/icb.topic923297.files/174.pdf>
+
+*   Gilbert, Angela, and Jayajit Chakraborty. 2011. "Using Geographically Weighted Regression for Environmental Justice Analysis: Cumulative Cancer Risks from Air Toxics in Florida." Social Science Research 40 (1): 273–86. doi:10.1016/j.ssresearch.2010.08.006. <http://scholarcommons.usf.edu/cgi/viewcontent.cgi?article=2985&context=etd>
+
+*   Ali, Kamar, Mark D. Partridge, and M. Rose Olfert. 2007. "Can Geographically Weighted Regressions Improve Regional Analysis and Policy Making?" International Regional Science Review 30 (3): 300–329. doi:10.1177/0160017607301609. <https://www.researchgate.net/publication/249682503_Can_Geographically_Weighted_Regressions_Improve_Regional_Analysis_and_Policy_Making>
+
+*   Lu, Binbin, Martin Charlton, and A. Stewart Fotheringhama. 2011. "Geographically Weighted Regression Using a Non-Euclidean Distance Metric with a Study on London House Price Data." Procedia Environmental Sciences, Spatial Statistics 2011: Mapping Global Change, 7: 92–97. doi:10.1016/j.proenv.2011.07.017. <https://www.researchgate.net/publication/261960122_Geographically_weighted_regression_with_a_non-Euclidean_distance_metric_A_case_study_using_hedonic_house_price_data>

doc/docs_template.md

@@ -0,0 +1,24 @@
+
+## Name
+
+## Synopsis
+
+## Description
+
+Availability: v...
+
+## Examples
+
+```SQL
+-- example of the function in use
+SELECT cdb_awesome_function(the_geom, 'total_pop')
+FROM table_name
+```
+
+## API Usage
+
+_asdf_
+
+## See Also
+
+_Other function pages_

pg/.gitignore

@@ -1,3 +0,0 @@
-regression.diffs
-regression.out
-results/

pg/Makefile

@@ -1,30 +0,0 @@
-# Makefile to generate the extension out of separate sql source files.
-# Once a version is released, it is not meant to be changed. E.g: once version 0.0.1 is out, it SHALL NOT be changed.
-
-EXTENSION    = crankshaft
-EXTVERSION   = $(shell grep default_version $(EXTENSION).control | sed -e "s/default_version[[:space:]]*=[[:space:]]*'\([^']*\)'/\1/")
-
-# The new version to be generated from templates
-NEW_EXTENSION_ARTIFACT = $(EXTENSION)--$(EXTVERSION).sql
-
-# DATA is a special variable used by postgres build infrastructure
-# These are the files to be installed in the server shared dir,
-# for installation from scratch, upgrades and downgrades.
-# @see http://www.postgresql.org/docs/current/static/extend-pgxs.html
-DATA =  $(NEW_EXTENSION_ARTIFACT)
-
-SOURCES_DATA_DIR = sql/$(EXTVERSION)
-SOURCES_DATA = $(wildcard sql/$(EXTVERSION)/*.sql)
-
-# The extension installation artifacts are stored in the base subdirectory
-$(NEW_EXTENSION_ARTIFACT): $(SOURCES_DATA)
-	rm -f $@
-	cat $(SOURCES_DATA_DIR)/*.sql >> $@
-
-REGRESS = $(notdir $(basename $(wildcard test/$(EXTVERSION)/sql/*test.sql)))
-TEST_DIR = test/$(EXTVERSION)
-REGRESS_OPTS = --inputdir='$(TEST_DIR)' --outputdir='$(TEST_DIR)'
-
-PG_CONFIG = pg_config
-PGXS := $(shell $(PG_CONFIG) --pgxs)
-include $(PGXS)

pg/README.md

@@ -1,7 +0,0 @@
-
-# Running the tests:
-
-```
-sudo make install
-PGUSER=postgres make installcheck
-```

pg/doc/02_moran.md

@@ -1,71 +0,0 @@
-### Moran's I
-
-#### What is Moran's I and why is it significant for CartoDB?
-
-Moran's I is a geostatistical calculation which gives a measure of the global
-clustering and presence of outliers within the geographies in a map. Here global
-means over all of the geographies in a dataset. Imagine mapping the incidence
-rates of cancer in neighborhoods of a city. If there were areas covering several
-neighborhoods with abnormally low rates of cancer, those areas are positively
-spatially correlated with one another and would be considered a cluster. If
-there was a single neighborhood with a high rate but with all neighbors on
-average having a low rate, it would be considered a spatial outlier.
-
-While Moran's I gives a global snapshot, there are local indicators for
-clustering called Local Indicators of Spatial Autocorrelation. Clustering is a
-process related to autocorrelation -- i.e., a process that compares a
-geography's attribute to the attribute in neighbor geographies.
-
-For the example of cancer rates in neighborhoods, since these neighborhoods have
-a high value for rate of cancer, and all of their neighbors do as well, they are
-designated as "High High" or simply **HH**. For areas with multiple neighborhoods
-with low rates of cancer, they are designated as "Low Low" or **LL**. HH and LL
-naturally fit into the concept of clustering and are in the correlated
-variables.
-
-"Anticorrelated" geogs are in **LH** and **HL** regions -- that is, regions
-where a geog has a high value and it's neighbors, on average, have a low value
-(or vice versa). An example of this is a "gated community" or placement of a
-city housing project in a rich region. These deliberate developments have
-opposite median income as compared to the neighbors around them. They have a
-high (or low) value while their neighbors have a low (or high) value. They exist
-typically as islands, and in rare circumstances can extend as chains dividing
-**LL** or **HH**.
-
-Strong policies such as rent stabilization (probably) tend to prevent the
-clustering of high rent areas as they integrate middle class incomes. Luxury
-apartment buildings, which are a kind of gated community, probably tend to skew
-an area's median income upwards while housing projects have the opposite effect.
-What are the nuggets in the analysis?
-
-Two functions are available to compute Moran I statistics:
-
-* `cdb_moran_local` computes Moran I measures, quad classification and
-  significance values from numerial values associated to geometry entities
-  in an input table. The geometries should be contiguous polygons When
-  then `queen` `w_type` is used.
-* `cdb_moran_local_rate` computes the same statistics using a ratio between
-  numerator and denominator columns of a table.
-
-The parameters for `cdb_moran_local` are:
-
-* `table` name of the table that contains the data values
-* `attr` name of the column
-* `signficance` significance threshold for the quads values
-* `num_ngbrs` number of neighbors to consider (default: 5)
-* `permutations` number of random permutations for calculation of
-  pseudo-p values (default: 99)
-* `geom_column` number of the geometry column (default: "the_geom")
-* `id_col` PK column of the table (default: "cartodb_id")
-* `w_type` Weight types: can be "knn" for k-nearest neighbor weights
-  or "queen" for contiguity based weights.
-
-The function returns a table with the following columns:
-
-* `moran` Moran's value
-* `quads` quad classification ('HH', 'LL', 'HL', 'LH' or 'Not significant')
-* `significance` significance value
-* `ids` id of the corresponding record in the input table
-
-Function `cdb_moran_local_rate` only differs in that the `attr` input
-parameter is substituted by `numerator` and `denominator`.

pg/test/0.0.1/expected/01_install_test.out

@@ -1,6 +0,0 @@
--- Install dependencies
-CREATE EXTENSION plpythonu;
-CREATE EXTENSION postgis;
-CREATE EXTENSION cartodb;
--- Install the extension
-CREATE EXTENSION crankshaft;

pg/test/0.0.1/expected/02_moran_test.out

@@ -1,260 +0,0 @@
-\i test/fixtures/ppoints.sql
--- test table (spanish province centroids with some invented values)
-CREATE TABLE ppoints (cartodb_id integer, the_geom geometry, the_geom_webmercator geometry, code text, region_code text, value float);
-INSERT INTO ppoints VALUES
-( 1,'0101000020E6100000A8306DC0CBC305C051D14B6CE56A4540'::geometry,ST_Transform('0101000020E6100000A8306DC0CBC305C051D14B6CE56A4540'::geometry, 3857),'01','16',0.5),
-( 4,'0101000020E6100000E220A4362DC202C0FD8AFA5119994240'::geometry,ST_Transform('0101000020E6100000E220A4362DC202C0FD8AFA5119994240'::geometry, 3857),'04','01',0.1),
-( 5,'0101000020E610000004377E573AC813C0CB5871BB17494440'::geometry,ST_Transform('0101000020E610000004377E573AC813C0CB5871BB17494440'::geometry, 3857),'05','07',0.3),
-( 2,'0101000020E610000000F49BE19BAFFFBF639958FDA6694340'::geometry,ST_Transform('0101000020E610000000F49BE19BAFFFBF639958FDA6694340'::geometry, 3857),'02','08',0.7),
-( 3,'0101000020E61000005D0B7E63C832E2BFDB63EB00443D4340'::geometry,ST_Transform('0101000020E61000005D0B7E63C832E2BFDB63EB00443D4340'::geometry, 3857),'03','10',0.2),
-( 6,'0101000020E61000006F3742B7FB9018C0DD967DC4D95A4340'::geometry,ST_Transform('0101000020E61000006F3742B7FB9018C0DD967DC4D95A4340'::geometry, 3857),'06','11',0.05),
-( 7,'0101000020E6100000E4BB36995F4C0740EAC0E5CA9FC94340'::geometry,ST_Transform('0101000020E6100000E4BB36995F4C0740EAC0E5CA9FC94340'::geometry, 3857),'07','04',0.4),
-( 8,'0101000020E61000003D43CC6CAFBEFF3F6B52E66F91DD4440'::geometry,ST_Transform('0101000020E61000003D43CC6CAFBEFF3F6B52E66F91DD4440'::geometry, 3857),'08','09',0.7),
-( 9,'0101000020E61000003CC797BD99AF0CC0495A87FA312F4540'::geometry,ST_Transform('0101000020E61000003CC797BD99AF0CC0495A87FA312F4540'::geometry, 3857),'09','07',0.5),
-(13,'0101000020E61000001CAA00A9F19F0EC05DF9267B7A764340'::geometry,ST_Transform('0101000020E61000001CAA00A9F19F0EC05DF9267B7A764340'::geometry, 3857),'13','08',0.4),
-(16,'0101000020E6100000D8208F3CBC9001C065638DC1B1F24340'::geometry,ST_Transform('0101000020E6100000D8208F3CBC9001C065638DC1B1F24340'::geometry, 3857),'16','08',0.4),
-(17,'0101000020E6100000E9E6A94A71630540AD7A0CB062104540'::geometry,ST_Transform('0101000020E6100000E9E6A94A71630540AD7A0CB062104540'::geometry, 3857),'17','09',0.6),
-(18,'0101000020E6100000719792D59E240AC098AC548E00A84240'::geometry,ST_Transform('0101000020E6100000719792D59E240AC098AC548E00A84240'::geometry, 3857),'18','01',0.3),
-(19,'0101000020E6100000972C878B50FD04C0123C881D1F684440'::geometry,ST_Transform('0101000020E6100000972C878B50FD04C0123C881D1F684440'::geometry, 3857),'19','08',0.7),
-(21,'0101000020E6100000F7893E9934511BC0EAA4BF03E1C94240'::geometry,ST_Transform('0101000020E6100000F7893E9934511BC0EAA4BF03E1C94240'::geometry, 3857),'21','01',0.1),
-(22,'0101000020E6100000572C2123B2A8B2BF7ED7FABAFD194540'::geometry,ST_Transform('0101000020E6100000572C2123B2A8B2BF7ED7FABAFD194540'::geometry, 3857),'22','02',0.4),
-(25,'0101000020E6100000461B67D688C4F03FD990EEC3A0054540'::geometry,ST_Transform('0101000020E6100000461B67D688C4F03FD990EEC3A0054540'::geometry, 3857),'25','09',0.4),
-(26,'0101000020E6100000A139FB06E82204C0539D84F62E234540'::geometry,ST_Transform('0101000020E6100000A139FB06E82204C0539D84F62E234540'::geometry, 3857),'26','17',0.6),
-(27,'0101000020E6100000A92E54E618C91DC00D3A947B81814540'::geometry,ST_Transform('0101000020E6100000A92E54E618C91DC00D3A947B81814540'::geometry, 3857),'27','12',0.3),
-(28,'0101000020E6100000971DC8B682BC0DC016D0E8055F3F4440'::geometry,ST_Transform('0101000020E6100000971DC8B682BC0DC016D0E8055F3F4440'::geometry, 3857),'28','13',0.8),
-(30,'0101000020E6100000A2DC1964A8C5F7BF19299C994D004340'::geometry,ST_Transform('0101000020E6100000A2DC1964A8C5F7BF19299C994D004340'::geometry, 3857),'30','14',0.1),
-(31,'0101000020E6100000DCA1FCC87B56FABF9B88E9D866554540'::geometry,ST_Transform('0101000020E6100000DCA1FCC87B56FABF9B88E9D866554540'::geometry, 3857),'31','15',0.9),
-(32,'0101000020E6100000E1517AFCD15E1EC0A18D8D4825194540'::geometry,ST_Transform('0101000020E6100000E1517AFCD15E1EC0A18D8D4825194540'::geometry, 3857),'32','12',0.3),
-(33,'0101000020E6100000A7FF33825AF917C0FABE7DFB6BA54540'::geometry,ST_Transform('0101000020E6100000A7FF33825AF917C0FABE7DFB6BA54540'::geometry, 3857),'33','03',0.4),
-(34,'0101000020E6100000FB4E4EBEB72412C0898E7240982F4540'::geometry,ST_Transform('0101000020E6100000FB4E4EBEB72412C0898E7240982F4540'::geometry, 3857),'34','07',0.3),
-(35,'0101000020E6100000224682B01B1A2DC011091656CC5C3C40'::geometry,ST_Transform('0101000020E6100000224682B01B1A2DC011091656CC5C3C40'::geometry, 3857),'35','05',0.3),
-(36,'0101000020E6100000F7C9447110EC20C04C5D4823C7374540'::geometry,ST_Transform('0101000020E6100000F7C9447110EC20C04C5D4823C7374540'::geometry, 3857),'36','12',0.2),
-(37,'0101000020E610000053D6A26DFB4218C09D58FAE209674440'::geometry,ST_Transform('0101000020E610000053D6A26DFB4218C09D58FAE209674440'::geometry, 3857),'37','07',0.5),
-(38,'0101000020E6100000B1D1B5FC910431C03C0C89BA03503C40'::geometry,ST_Transform('0101000020E6100000B1D1B5FC910431C03C0C89BA03503C40'::geometry, 3857),'38','05',0.4),
-(39,'0101000020E610000086E6FEE1BD1E10C00417096748994540'::geometry,ST_Transform('0101000020E610000086E6FEE1BD1E10C00417096748994540'::geometry, 3857),'39','06',0.6),
-(40,'0101000020E6100000FB51C33F733710C038D01729E4954440'::geometry,ST_Transform('0101000020E6100000FB51C33F733710C038D01729E4954440'::geometry, 3857),'40','07',0.5),
-(41,'0101000020E6100000912D6FDA28BB16C031321F08C4B74240'::geometry,ST_Transform('0101000020E6100000912D6FDA28BB16C031321F08C4B74240'::geometry, 3857),'41','01',0.4),
-(42,'0101000020E6100000554432EABEB504C069ECD78775CF4440'::geometry,ST_Transform('0101000020E6100000554432EABEB504C069ECD78775CF4440'::geometry, 3857),'42','07',0.2),
-(43,'0101000020E6100000157F117C1A2EEA3F027CD1F2368B4440'::geometry,ST_Transform('0101000020E6100000157F117C1A2EEA3F027CD1F2368B4440'::geometry, 3857),'43','09',0.3),
-(44,'0101000020E610000051AA5B1BD718EABFEE67613BA4544440'::geometry,ST_Transform('0101000020E610000051AA5B1BD718EABFEE67613BA4544440'::geometry, 3857),'44','02',0.2),
-(45,'0101000020E610000022C5C01BB69710C08563BC1499E54340'::geometry,ST_Transform('0101000020E610000022C5C01BB69710C08563BC1499E54340'::geometry, 3857),'45','08',0.3),
-(46,'0101000020E6100000D5FCF78A11A0E9BFDEA46F8E64AF4340'::geometry,ST_Transform('0101000020E6100000D5FCF78A11A0E9BFDEA46F8E64AF4340'::geometry, 3857),'46','10',0.2),
-(47,'0101000020E61000003AE63525866313C02100050B2BD14440'::geometry,ST_Transform('0101000020E61000003AE63525866313C02100050B2BD14440'::geometry, 3857),'47','07',0.3),
-(48,'0101000020E610000030F187FD1FD206C0C767E1496C9E4540'::geometry,ST_Transform('0101000020E610000030F187FD1FD206C0C767E1496C9E4540'::geometry, 3857),'48','16',0.5),
-(49,'0101000020E61000009C22867B12EC17C006C5F40C14DD4440'::geometry,ST_Transform('0101000020E61000009C22867B12EC17C006C5F40C14DD4440'::geometry, 3857),'49','07',0.2),
-(50,'0101000020E6100000F7D5EFC62D08F1BF69D1231D68CF4440'::geometry,ST_Transform('0101000020E6100000F7D5EFC62D08F1BF69D1231D68CF4440'::geometry, 3857),'50','02',0.6),
-(51,'0101000020E61000005B0E1F8DAA5F15C0530BFE285BF24140'::geometry,ST_Transform('0101000020E61000005B0E1F8DAA5F15C0530BFE285BF24140'::geometry, 3857),'51','18',0.01),
-(10,'0101000020E61000000FD65D82AEA418C06192D1351FDB4340'::geometry,ST_Transform('0101000020E61000000FD65D82AEA418C06192D1351FDB4340'::geometry, 3857),'10','11',0.04),
-(11,'0101000020E6100000B305531DAB0A17C0DEAFCD4EE5464240'::geometry,ST_Transform('0101000020E6100000B305531DAB0A17C0DEAFCD4EE5464240'::geometry, 3857),'11','01',0.08),
-(12,'0101000020E610000059721A7297C9C2BF9EBE383BE51E4440'::geometry,ST_Transform('0101000020E610000059721A7297C9C2BF9EBE383BE51E4440'::geometry, 3857),'12','10',0.2),
-(14,'0101000020E610000000C86313AF3C13C0E530879C10FF4240'::geometry,ST_Transform('0101000020E610000000C86313AF3C13C0E530879C10FF4240'::geometry, 3857),'14','01',0.2),
-(15,'0101000020E61000002A475497B6ED20C06643D4131A904540'::geometry,ST_Transform('0101000020E61000002A475497B6ED20C06643D4131A904540'::geometry, 3857),'15','12',0.3),
-(20,'0101000020E6100000F975566FAD8D01C0E840C33F67924540'::geometry,ST_Transform('0101000020E6100000F975566FAD8D01C0E840C33F67924540'::geometry, 3857),'20','16',0.8),
-(23,'0101000020E610000025FA13E595880BC022BB07131D024340'::geometry,ST_Transform('0101000020E610000025FA13E595880BC022BB07131D024340'::geometry, 3857),'23','01',0.1),
-(24,'0101000020E61000009C5F91C5095C17C0C78784B15A4F4540'::geometry,ST_Transform('0101000020E61000009C5F91C5095C17C0C78784B15A4F4540'::geometry, 3857),'24','07',0.3),
-(29,'0101000020E6100000C34D4A5B48E712C092E680892C684240'::geometry,ST_Transform('0101000020E6100000C34D4A5B48E712C092E680892C684240'::geometry, 3857),'29','01',0.3),
-(52,'0101000020E6100000406A545EB29A07C04E5F0BDA39A54140'::geometry,ST_Transform('0101000020E6100000406A545EB29A07C04E5F0BDA39A54140'::geometry, 3857),'52','19',0.01)
-\i test/fixtures/ppoints2.sql
--- test table (spanish province centroids with some invented values)
-CREATE TABLE ppoints2 (cartodb_id integer, the_geom geometry, code text, region_code text, numerator float, denominator float);
-INSERT INTO ppoints2 VALUES
-( 1,'0101000020E6100000A8306DC0CBC305C051D14B6CE56A4540'::geometry,'01','16',0.5, 1.0),
-( 4,'0101000020E6100000E220A4362DC202C0FD8AFA5119994240'::geometry,'04','01',0.1, 1.0),
-( 5,'0101000020E610000004377E573AC813C0CB5871BB17494440'::geometry,'05','07',0.3, 1.0),
-( 2,'0101000020E610000000F49BE19BAFFFBF639958FDA6694340'::geometry,'02','08',0.7, 1.0),
-( 3,'0101000020E61000005D0B7E63C832E2BFDB63EB00443D4340'::geometry,'03','10',0.2, 1.0),
-( 6,'0101000020E61000006F3742B7FB9018C0DD967DC4D95A4340'::geometry,'06','11',0.05, 1.0),
-( 7,'0101000020E6100000E4BB36995F4C0740EAC0E5CA9FC94340'::geometry,'07','04',0.4, 1.0),
-( 8,'0101000020E61000003D43CC6CAFBEFF3F6B52E66F91DD4440'::geometry,'08','09',0.7, 1.0),
-( 9,'0101000020E61000003CC797BD99AF0CC0495A87FA312F4540'::geometry,'09','07',0.5, 1.0),
-(13,'0101000020E61000001CAA00A9F19F0EC05DF9267B7A764340'::geometry,'13','08',0.4, 1.0),
-(16,'0101000020E6100000D8208F3CBC9001C065638DC1B1F24340'::geometry,'16','08',0.4, 1.0),
-(17,'0101000020E6100000E9E6A94A71630540AD7A0CB062104540'::geometry,'17','09',0.6, 1.0),
-(18,'0101000020E6100000719792D59E240AC098AC548E00A84240'::geometry,'18','01',0.3, 1.0),
-(19,'0101000020E6100000972C878B50FD04C0123C881D1F684440'::geometry,'19','08',0.7, 1.0),
-(21,'0101000020E6100000F7893E9934511BC0EAA4BF03E1C94240'::geometry,'21','01',0.1, 1.0),
-(22,'0101000020E6100000572C2123B2A8B2BF7ED7FABAFD194540'::geometry,'22','02',0.4, 1.0),
-(25,'0101000020E6100000461B67D688C4F03FD990EEC3A0054540'::geometry,'25','09',0.4, 1.0),
-(26,'0101000020E6100000A139FB06E82204C0539D84F62E234540'::geometry,'26','17',0.6, 1.0),
-(27,'0101000020E6100000A92E54E618C91DC00D3A947B81814540'::geometry,'27','12',0.3, 1.0),
-(28,'0101000020E6100000971DC8B682BC0DC016D0E8055F3F4440'::geometry,'28','13',0.8, 1.0),
-(30,'0101000020E6100000A2DC1964A8C5F7BF19299C994D004340'::geometry,'30','14',0.1, 1.0),
-(31,'0101000020E6100000DCA1FCC87B56FABF9B88E9D866554540'::geometry,'31','15',0.9, 1.0),
-(32,'0101000020E6100000E1517AFCD15E1EC0A18D8D4825194540'::geometry,'32','12',0.3, 1.0),
-(33,'0101000020E6100000A7FF33825AF917C0FABE7DFB6BA54540'::geometry,'33','03',0.4, 1.0),
-(34,'0101000020E6100000FB4E4EBEB72412C0898E7240982F4540'::geometry,'34','07',0.3, 1.0),
-(35,'0101000020E6100000224682B01B1A2DC011091656CC5C3C40'::geometry,'35','05',0.3, 1.0),
-(36,'0101000020E6100000F7C9447110EC20C04C5D4823C7374540'::geometry,'36','12',0.2, 1.0),
-(37,'0101000020E610000053D6A26DFB4218C09D58FAE209674440'::geometry,'37','07',0.5, 1.0),
-(38,'0101000020E6100000B1D1B5FC910431C03C0C89BA03503C40'::geometry,'38','05',0.4, 1.0),
-(39,'0101000020E610000086E6FEE1BD1E10C00417096748994540'::geometry,'39','06',0.6, 1.0),
-(40,'0101000020E6100000FB51C33F733710C038D01729E4954440'::geometry,'40','07',0.5, 1.0),
-(41,'0101000020E6100000912D6FDA28BB16C031321F08C4B74240'::geometry,'41','01',0.4, 1.0),
-(42,'0101000020E6100000554432EABEB504C069ECD78775CF4440'::geometry,'42','07',0.2, 1.0),
-(43,'0101000020E6100000157F117C1A2EEA3F027CD1F2368B4440'::geometry,'43','09',0.3, 1.0),
-(44,'0101000020E610000051AA5B1BD718EABFEE67613BA4544440'::geometry,'44','02',0.2, 1.0),
-(45,'0101000020E610000022C5C01BB69710C08563BC1499E54340'::geometry,'45','08',0.3, 1.0),
-(46,'0101000020E6100000D5FCF78A11A0E9BFDEA46F8E64AF4340'::geometry,'46','10',0.2, 1.0),
-(47,'0101000020E61000003AE63525866313C02100050B2BD14440'::geometry,'47','07',0.3, 1.0),
-(48,'0101000020E610000030F187FD1FD206C0C767E1496C9E4540'::geometry,'48','16',0.5, 1.0),
-(49,'0101000020E61000009C22867B12EC17C006C5F40C14DD4440'::geometry,'49','07',0.2, 1.0),
-(50,'0101000020E6100000F7D5EFC62D08F1BF69D1231D68CF4440'::geometry,'50','02',0.6, 1.0),
-(51,'0101000020E61000005B0E1F8DAA5F15C0530BFE285BF24140'::geometry,'51','18',0.01, 1.0),
-(10,'0101000020E61000000FD65D82AEA418C06192D1351FDB4340'::geometry,'10','11',0.04, 1.0),
-(11,'0101000020E6100000B305531DAB0A17C0DEAFCD4EE5464240'::geometry,'11','01',0.08, 1.0),
-(12,'0101000020E610000059721A7297C9C2BF9EBE383BE51E4440'::geometry,'12','10',0.2, 1.0),
-(14,'0101000020E610000000C86313AF3C13C0E530879C10FF4240'::geometry,'14','01',0.2, 1.0),
-(15,'0101000020E61000002A475497B6ED20C06643D4131A904540'::geometry,'15','12',0.3, 1.0),
-(20,'0101000020E6100000F975566FAD8D01C0E840C33F67924540'::geometry,'20','16',0.8, 1.0),
-(23,'0101000020E610000025FA13E595880BC022BB07131D024340'::geometry,'23','01',0.1, 1.0),
-(24,'0101000020E61000009C5F91C5095C17C0C78784B15A4F4540'::geometry,'24','07',0.3, 1.0),
-(29,'0101000020E6100000C34D4A5B48E712C092E680892C684240'::geometry,'29','01',0.3, 1.0),
-(52,'0101000020E6100000406A545EB29A07C04E5F0BDA39A54140'::geometry,'52','19',0.0, 1.01)
--- Moral functions perform some nondeterministic computations
--- (to estimate the significance); we will set the seeds for the RNGs
--- that affect those results to have repeateble results
-SELECT cdb_crankshaft._cdb_random_seeds(1234);
- _cdb_random_seeds 
--------------------
- 
-(1 row)
-
-SELECT ppoints.code, m.quads
-  FROM ppoints
-  JOIN cdb_crankshaft.cdb_moran_local('ppoints', 'value') m
-    ON ppoints.cartodb_id = m.ids
-  ORDER BY ppoints.code;
-NOTICE:  ** Constructing query
-CONTEXT:  PL/Python function "cdb_moran_local"
-NOTICE:  ** Query returned with 52 rows
-CONTEXT:  PL/Python function "cdb_moran_local"
-NOTICE:  ** Finished calculations
-CONTEXT:  PL/Python function "cdb_moran_local"
- code |      quads      
-------+-----------------
- 01   | HH
- 02   | HL
- 03   | Not significant
- 04   | Not significant
- 05   | Not significant
- 06   | Not significant
- 07   | Not significant
- 08   | Not significant
- 09   | Not significant
- 10   | Not significant
- 11   | LL
- 12   | Not significant
- 13   | Not significant
- 14   | Not significant
- 15   | Not significant
- 16   | HH
- 17   | Not significant
- 18   | Not significant
- 19   | Not significant
- 20   | HH
- 21   | LL
- 22   | Not significant
- 23   | Not significant
- 24   | Not significant
- 25   | HH
- 26   | HH
- 27   | Not significant
- 28   | Not significant
- 29   | LL
- 30   | Not significant
- 31   | HH
- 32   | Not significant
- 33   | Not significant
- 34   | Not significant
- 35   | LL
- 36   | Not significant
- 37   | Not significant
- 38   | HL
- 39   | Not significant
- 40   | Not significant
- 41   | HL
- 42   | LH
- 43   | Not significant
- 44   | Not significant
- 45   | LH
- 46   | Not significant
- 47   | Not significant
- 48   | HH
- 49   | Not significant
- 50   | Not significant
- 51   | LL
- 52   | LL
-(52 rows)
-
-SELECT cdb_crankshaft._cdb_random_seeds(1234);
- _cdb_random_seeds 
--------------------
- 
-(1 row)
-
-SELECT ppoints2.code, m.quads
-  FROM ppoints2
-  JOIN cdb_crankshaft.cdb_moran_local_rate('ppoints2', 'numerator', 'denominator') m
-    ON ppoints2.cartodb_id = m.ids
-  ORDER BY ppoints2.code;
-NOTICE:  ** Constructing query
-CONTEXT:  PL/Python function "cdb_moran_local_rate"
-NOTICE:  ** Query returned with 51 rows
-CONTEXT:  PL/Python function "cdb_moran_local_rate"
-NOTICE:  ** Finished calculations
-CONTEXT:  PL/Python function "cdb_moran_local_rate"
- code |      quads      
-------+-----------------
- 01   | LL
- 02   | Not significant
- 03   | Not significant
- 04   | Not significant
- 05   | Not significant
- 06   | Not significant
- 07   | Not significant
- 08   | Not significant
- 09   | LL
- 10   | Not significant
- 11   | HH
- 12   | Not significant
- 13   | Not significant
- 14   | Not significant
- 15   | Not significant
- 16   | Not significant
- 17   | LL
- 18   | Not significant
- 19   | Not significant
- 20   | LL
- 21   | Not significant
- 22   | Not significant
- 23   | Not significant
- 24   | Not significant
- 25   | LL
- 26   | LL
- 27   | Not significant
- 28   | Not significant
- 29   | LH
- 30   | Not significant
- 31   | LL
- 32   | Not significant
- 33   | Not significant
- 34   | Not significant
- 35   | LH
- 36   | Not significant
- 37   | Not significant
- 38   | LH
- 39   | Not significant
- 40   | Not significant
- 41   | LH
- 42   | HL
- 43   | Not significant
- 44   | Not significant
- 45   | LL
- 46   | Not significant
- 47   | Not significant
- 48   | LL
- 49   | Not significant
- 50   | Not significant
- 51   | Not significant
-(51 rows)
-

pg/test/0.0.1/expected/03_overlap_sum_test.out

@@ -1,23 +0,0 @@
-\i test/fixtures/polyg_values.sql
-CREATE TABLE values (cartodb_id integer, value float, the_geom geometry);
-INSERT INTO values(cartodb_id, value, the_geom) VALUES
-(1,10,'0106000020E61000000100000001030000000100000005000000E5AF3500C03608C08068629111374440C7BC0A00C00F02C0AC0551523B414440C7BC0A00C0A700C0CAF23B6E74FB4340A7267FFFFF5206C0FBB7E41B7EE74340E5AF3500C03608C08068629111374440'::geometry),
-(2,20,'0106000020E610000001000000010300000001000000050000002439EC00804AF7BF07D6CCB5C3064440C7BC0A00C0A700C0CAF23B6E74FB4340C7BC0A00C00F02C0AC0551523B414440E20CD5FFFF30FABFBE4F76AFEA4B44402439EC00804AF7BF07D6CCB5C3064440'::geometry)
-SELECT round(cdb_crankshaft.cdb_overlap_sum(
-  '0106000020E61000000100000001030000000100000004000000FFFFFFFFFF3604C09A0B9ECEC42E444000000000C060FBBF30C7FD70E01D44400000000040AD02C06481F1C8CD034440FFFFFFFFFF3604C09A0B9ECEC42E4440'::geometry,
-  'values', 'value'
-), 2);
- round 
--------
-  4.42
-(1 row)
-
-SELECT round(cdb_crankshaft.cdb_overlap_sum(
-  '0106000020E61000000100000001030000000100000004000000FFFFFFFFFF3604C09A0B9ECEC42E444000000000C060FBBF30C7FD70E01D44400000000040AD02C06481F1C8CD034440FFFFFFFFFF3604C09A0B9ECEC42E4440'::geometry,
-  'values', 'value', schema_name := 'public'
-), 2);
- round 
--------
-  4.42
-(1 row)
-

pg/test/0.0.1/results/01_install_test.out

@@ -1,6 +0,0 @@
--- Install dependencies
-CREATE EXTENSION plpythonu;
-CREATE EXTENSION postgis;
-CREATE EXTENSION cartodb;
--- Install the extension
-CREATE EXTENSION crankshaft;

pg/test/0.0.1/sql/01_install_test.sql

@@ -1,7 +0,0 @@
--- Install dependencies
-CREATE EXTENSION plpythonu;
-CREATE EXTENSION postgis;
-CREATE EXTENSION cartodb;
-
--- Install the extension
-CREATE EXTENSION crankshaft;

pg/test/0.0.1/sql/02_moran_test.sql

@@ -1,21 +0,0 @@
-\i test/fixtures/ppoints.sql
-\i test/fixtures/ppoints2.sql
-
--- Moral functions perform some nondeterministic computations
--- (to estimate the significance); we will set the seeds for the RNGs
--- that affect those results to have repeateble results
-SELECT cdb_crankshaft._cdb_random_seeds(1234);
-
-SELECT ppoints.code, m.quads
-  FROM ppoints
-  JOIN cdb_crankshaft.cdb_moran_local('ppoints', 'value') m
-    ON ppoints.cartodb_id = m.ids
-  ORDER BY ppoints.code;
-
-SELECT cdb_crankshaft._cdb_random_seeds(1234);
-
-SELECT ppoints2.code, m.quads
-  FROM ppoints2
-  JOIN cdb_crankshaft.cdb_moran_local_rate('ppoints2', 'numerator', 'denominator') m
-    ON ppoints2.cartodb_id = m.ids
-  ORDER BY ppoints2.code;

python/.gitignore

@@ -1 +0,0 @@
-*.pyc

python/Makefile

@@ -1,11 +0,0 @@
-# Install the package (needs root privileges)
-install:
-	pip install ./crankshaft --upgrade
-
-# Test from source code
-test:
-	(cd crankshaft && nosetests test/)
-
-# Test currently installed package
-testinstalled:
-	nosetests crankshaft/test/

python/README.md

@@ -1,9 +0,0 @@
-# Crankshaft Python Package
-
-...
-### Run the tests
-
-```bash
-cd crankshaft
-nosetests test/
-```

release/crankshaft--0.0.1--0.0.2.sql

@@ -0,0 +1,74 @@
+CREATE OR REPLACE FUNCTION cdb_crankshaft.cdb_crankshaft_version()
+RETURNS text AS $$
+  SELECT '0.0.2'::text;
+$$ language 'sql' STABLE STRICT;
+
+CREATE OR REPLACE FUNCTION cdb_crankshaft._cdb_crankshaft_internal_version()
+RETURNS text AS $$
+  SELECT installed_version FROM pg_available_extensions where name='crankshaft' and pg_available_extensions IS NOT NULL;
+$$ language 'sql' STABLE STRICT;
+CREATE OR REPLACE FUNCTION cdb_crankshaft._cdb_crankshaft_virtualenvs_path()
+RETURNS text
+AS $$
+  BEGIN
+    RETURN '/home/ubuntu/crankshaft/envs';
+  END;
+$$ language plpgsql IMMUTABLE STRICT;
+
+CREATE OR REPLACE FUNCTION cdb_crankshaft._cdb_crankshaft_activate_py()
+RETURNS VOID
+AS $$
+    import os
+    # plpy.notice('%',str(os.environ))
+    # activate virtualenv
+    crankshaft_version = plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_internal_version()')[0]['_cdb_crankshaft_internal_version']
+    base_path = plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_virtualenvs_path()')[0]['_cdb_crankshaft_virtualenvs_path']
+    default_venv_path = os.path.join(base_path, crankshaft_version)
+    venv_path =  os.environ.get('CRANKSHAFT_VENV', default_venv_path)
+    activate_path = venv_path + '/bin/activate_this.py'
+    exec(open(activate_path).read(), dict(__file__=activate_path))
+$$ LANGUAGE plpythonu;
+
+CREATE OR REPLACE FUNCTION
+cdb_crankshaft._cdb_random_seeds (seed_value INTEGER) RETURNS VOID
+AS $$
+  plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
+  from crankshaft import random_seeds
+  random_seeds.set_random_seeds(seed_value)
+$$ LANGUAGE plpythonu;
+-- Moran's I
+CREATE OR REPLACE FUNCTION
+cdb_crankshaft.cdb_moran_local (
+      t TEXT,
+  	  attr TEXT,
+  	  significance float DEFAULT 0.05,
+  	  num_ngbrs INT DEFAULT 5,
+  	  permutations INT DEFAULT 99,
+  	  geom_column TEXT DEFAULT 'the_geom',
+  	  id_col TEXT DEFAULT 'cartodb_id',
+      w_type TEXT DEFAULT 'knn')
+RETURNS TABLE (moran FLOAT, quads TEXT, significance FLOAT, ids INT)
+AS $$
+  plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
+  from crankshaft.clustering import moran_local
+  # TODO: use named parameters or a dictionary
+  return moran_local(t, attr, significance, num_ngbrs, permutations, geom_column, id_col, w_type)
+$$ LANGUAGE plpythonu;
+
+CREATE OR REPLACE FUNCTION
+cdb_crankshaft.cdb_moran_local_rate(t TEXT,
+		 numerator TEXT,
+		 denominator TEXT,
+		 significance FLOAT DEFAULT 0.05,
+		 num_ngbrs INT DEFAULT 5,
+		 permutations INT DEFAULT 99,
+		 geom_column TEXT DEFAULT 'the_geom',
+		 id_col TEXT DEFAULT 'cartodb_id',
+		 w_type TEXT DEFAULT 'knn')
+RETURNS TABLE(moran FLOAT, quads TEXT, significance FLOAT, ids INT, y numeric)
+AS $$
+  plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
+  from crankshaft.clustering import moran_local_rate
+  # TODO: use named parameters or a dictionary
+  return moran_local_rate(t, numerator, denominator, significance, num_ngbrs, permutations, geom_column, id_col, w_type)
+$$ LANGUAGE plpythonu;

release/crankshaft--0.0.1.sql

@@ -1,3 +1,6 @@
+--DO NOT MODIFY THIS FILE, IT IS GENERATED AUTOMATICALLY FROM SOURCES
+-- Complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION crankshaft" to load this file. \quit
 -- Internal function.
 -- Set the seeds of the RNGs (Random Number Generators)
 -- used internally.
@@ -133,4 +136,13 @@ BEGIN
   RETURN ST_Collect(points);
 END;
 $$
-LANGUAGE plpgsql VOLATILE
+LANGUAGE plpgsql VOLATILE;
+-- Make sure by default there are no permissions for publicuser
+-- NOTE: this happens at extension creation time, as part of an implicit transaction.
+-- REVOKE ALL PRIVILEGES ON SCHEMA cdb_crankshaft FROM PUBLIC, publicuser CASCADE;
+
+-- Grant permissions on the schema to publicuser (but just the schema)
+GRANT USAGE ON SCHEMA cdb_crankshaft TO publicuser;
+
+-- Revoke execute permissions on all functions in the schema by default
+-- REVOKE EXECUTE ON ALL FUNCTIONS IN SCHEMA cdb_crankshaft FROM PUBLIC, publicuser;

release/crankshaft--0.0.2--0.0.1.sql

@@ -1,6 +1,12 @@
--- Moran's I
 CREATE OR REPLACE FUNCTION
-  cdb_moran_local (
+cdb_crankshaft._cdb_random_seeds (seed_value INTEGER) RETURNS VOID
+AS $$
+  from crankshaft import random_seeds
+  random_seeds.set_random_seeds(seed_value)
+$$ LANGUAGE plpythonu;
+
+CREATE OR REPLACE FUNCTION
+cdb_crankshaft.cdb_moran_local (
       t TEXT,
   	  attr TEXT,
   	  significance float DEFAULT 0.05,
@@ -16,9 +22,8 @@ AS $$
   return moran_local(t, attr, significance, num_ngbrs, permutations, geom_column, id_col, w_type)
 $$ LANGUAGE plpythonu;
 
--- Moran's I Local Rate
 CREATE OR REPLACE FUNCTION
-  cdb_moran_local_rate(t TEXT,
+cdb_crankshaft.cdb_moran_local_rate(t TEXT,
 		 numerator TEXT,
 		 denominator TEXT,
 		 significance FLOAT DEFAULT 0.05,
@@ -33,3 +38,7 @@ AS $$
   # TODO: use named parameters or a dictionary
   return moran_local_rate(t, numerator, denominator, significance, num_ngbrs, permutations, geom_column, id_col, w_type)
 $$ LANGUAGE plpythonu;
+
+DROP FUNCTION IF EXISTS cdb_crankshaft.cdb_crankshaft_version();
+DROP FUNCTION IF EXISTS cdb_crankshaft._cdb_crankshaft_internal_version();
+DROP FUNCTION IF EXISTS cdb_crankshaft._cdb_crankshaft_activate_py();

release/crankshaft--0.0.2--0.0.3.sql

@@ -0,0 +1,413 @@
+--DO NOT MODIFY THIS FILE, IT IS GENERATED AUTOMATICALLY FROM SOURCES
+-- Complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION crankshaft" to load this file. \quit
+
+-- [MANUALLY] DROP FUNCTIONS REMOVED SINCE 0.0.2 version
+
+DROP FUNCTION IF EXISTS cdb_moran_local(TEXT, TEXT, float, INT, INT, TEXT, TEXT, TEXT);
+DROP FUNCTION IF EXISTS cdb_moran_local_rate(TEXT, TEXT, TEXT, FLOAT, INT, INT, TEXT, TEXT, TEXT);
+DROP FUNCTION IF EXISTS _cdb_crankshaft_virtualenvs_path();
+DROP FUNCTION IF EXISTS _cdb_crankshaft_activate_py();
+
+-- [END MANUALLY] DROP FUNCTIONS REMOVED SINCE 0.0.2 version
+
+-- Version number of the extension release
+CREATE OR REPLACE FUNCTION cdb_crankshaft_version()
+    RETURNS text AS $$
+  SELECT '0.0.3'::text;
+$$ language 'sql' STABLE STRICT;
+
+-- Internal identifier of the installed extension instence
+-- e.g. 'dev' for current development version
+CREATE OR REPLACE FUNCTION _cdb_crankshaft_internal_version()
+    RETURNS text AS $$
+  SELECT installed_version FROM pg_available_extensions where name='crankshaft' and pg_available_extensions IS NOT NULL;
+$$ language 'sql' STABLE STRICT;
+-- Internal function.
+-- Set the seeds of the RNGs (Random Number Generators)
+-- used internally.
+CREATE OR REPLACE FUNCTION
+    _cdb_random_seeds (seed_value INTEGER) RETURNS VOID
+AS $$
+  from crankshaft import random_seeds
+  random_seeds.set_random_seeds(seed_value)
+$$ LANGUAGE plpythonu;
+-- Moran's I Global Measure (public-facing)
+CREATE OR REPLACE FUNCTION
+    CDB_AreasOfInterestGlobal(
+    subquery TEXT,
+    column_name TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS TABLE (moran NUMERIC, significance NUMERIC)
+AS $$
+  from crankshaft.clustering import moran_local
+  # TODO: use named parameters or a dictionary
+  return moran(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+-- Moran's I Local (internal function)
+CREATE OR REPLACE FUNCTION
+    _CDB_AreasOfInterestLocal(
+    subquery TEXT,
+    column_name TEXT,
+    w_type TEXT,
+    num_ngbrs INT,
+    permutations INT,
+    geom_col TEXT,
+    id_col TEXT)
+    RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+  from crankshaft.clustering import moran_local
+  # TODO: use named parameters or a dictionary
+  return moran_local(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+-- Moran's I Local (public-facing function)
+CREATE OR REPLACE FUNCTION
+    CDB_AreasOfInterestLocal(
+    subquery TEXT,
+    column_name TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col);
+
+$$ LANGUAGE SQL;
+
+-- Moran's I only for HH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+    CDB_GetSpatialHotspots(
+    subquery TEXT,
+    column_name TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HH', 'HL');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I only for LL and LH (public-facing function)
+CREATE OR REPLACE FUNCTION
+    CDB_GetSpatialColdspots(
+    subquery TEXT,
+    attr TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, attr, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('LL', 'LH');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I only for LH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+    CDB_GetSpatialOutliers(
+    subquery TEXT,
+    attr TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, attr, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HL', 'LH');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Global Rate (public-facing function)
+CREATE OR REPLACE FUNCTION
+    CDB_AreasOfInterestGlobalRate(
+    subquery TEXT,
+    numerator TEXT,
+    denominator TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS TABLE (moran FLOAT, significance FLOAT)
+AS $$
+  from crankshaft.clustering import moran_local
+  # TODO: use named parameters or a dictionary
+  return moran_rate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+
+-- Moran's I Local Rate (internal function)
+CREATE OR REPLACE FUNCTION
+    _CDB_AreasOfInterestLocalRate(
+    subquery TEXT,
+    numerator TEXT,
+    denominator TEXT,
+    w_type TEXT,
+    num_ngbrs INT,
+    permutations INT,
+    geom_col TEXT,
+    id_col TEXT)
+    RETURNS
+        TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+  from crankshaft.clustering import moran_local_rate
+  # TODO: use named parameters or a dictionary
+  return moran_local_rate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+-- Moran's I Local Rate (public-facing function)
+CREATE OR REPLACE FUNCTION
+    CDB_AreasOfInterestLocalRate(
+    subquery TEXT,
+    numerator TEXT,
+    denominator TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS
+        TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col);
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Local Rate only for HH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+    CDB_GetSpatialHotspotsRate(
+    subquery TEXT,
+    numerator TEXT,
+    denominator TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS
+        TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HH', 'HL');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Local Rate only for LL and LH (public-facing function)
+CREATE OR REPLACE FUNCTION
+    CDB_GetSpatialColdspotsRate(
+    subquery TEXT,
+    numerator TEXT,
+    denominator TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS
+        TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('LL', 'LH');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Local Rate only for LH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+    CDB_GetSpatialOutliersRate(
+    subquery TEXT,
+    numerator TEXT,
+    denominator TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS
+        TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HL', 'LH');
+
+$$ LANGUAGE SQL;
+CREATE OR REPLACE FUNCTION  CDB_KMeans(query text, no_clusters integer,no_init integer default 20)
+    RETURNS table (cartodb_id integer, cluster_no integer) as $$
+    
+    from crankshaft.clustering import kmeans
+    return kmeans(query,no_clusters,no_init)
+
+$$ language plpythonu;
+
+
+CREATE OR REPLACE FUNCTION CDB_WeightedMeanS(state Numeric[],the_geom GEOMETRY(Point, 4326), weight NUMERIC)
+    RETURNS Numeric[] AS
+    $$
+DECLARE 
+    newX NUMERIC;
+    newY NUMERIC;
+    newW NUMERIC;
+BEGIN
+    IF weight IS NULL OR the_geom IS NULL THEN 
+        newX = state[1];
+        newY = state[2];
+        newW = state[3];
+    ELSE
+        newX = state[1] + ST_X(the_geom)*weight;
+        newY = state[2] + ST_Y(the_geom)*weight;
+        newW = state[3] + weight;
+    END IF;
+    RETURN Array[newX,newY,newW];
+
+END
+$$ LANGUAGE plpgsql;
+
+CREATE OR REPLACE FUNCTION CDB_WeightedMeanF(state Numeric[])
+    RETURNS GEOMETRY AS
+    $$
+BEGIN
+    IF state[3] = 0 THEN 
+        RETURN ST_SetSRID(ST_MakePoint(state[1],state[2]), 4326);
+    ELSE 
+        RETURN ST_SETSRID(ST_MakePoint(state[1]/state[3], state[2]/state[3]),4326);
+    END IF;
+END
+$$ LANGUAGE plpgsql;
+
+CREATE AGGREGATE CDB_WeightedMean(geometry(Point, 4326), NUMERIC)(
+SFUNC = CDB_WeightedMeanS,
+FINALFUNC = CDB_WeightedMeanF,
+STYPE = Numeric[],
+INITCOND = "{0.0,0.0,0.0}"
+);
+-- Function by Stuart Lynn for a simple interpolation of a value
+-- from a polygon table over an arbitrary polygon
+-- (weighted by the area proportion overlapped)
+-- Aereal weighting is a very simple form of aereal interpolation.
+--
+-- Parameters:
+--   * geom a Polygon geometry which defines the area where a value will be
+--     estimated as the area-weighted sum of a given table/column
+--   * target_table_name table name of the table that provides the values
+--   * target_column column name of the column that provides the values
+--   * schema_name optional parameter to defina the schema the target table
+--     belongs to, which is necessary if its not in the search_path.
+--     Note that target_table_name should never include the schema in it.
+-- Return value:
+--   Aereal-weighted interpolation of the column values over the geometry
+CREATE OR REPLACE
+FUNCTION cdb_overlap_sum(geom geometry, target_table_name text, target_column text, schema_name text DEFAULT NULL)
+    RETURNS numeric AS
+    $$
+    DECLARE
+        result numeric;
+        qualified_name text;
+    BEGIN
+        IF schema_name IS NULL THEN
+            qualified_name := Format('%I', target_table_name);
+        ELSE
+            qualified_name := Format('%I.%s', schema_name, target_table_name);
+        END IF;
+        EXECUTE Format('
+    SELECT sum(%I*ST_Area(St_Intersection($1, a.the_geom))/ST_Area(a.the_geom))
+    FROM %s AS a
+    WHERE $1 && a.the_geom
+  ', target_column, qualified_name)
+        USING geom
+        INTO result;
+        RETURN result;
+    END;
+    $$ LANGUAGE plpgsql;
+--
+-- Creates N points randomly distributed arround the polygon
+--
+-- @param g - the geometry to be turned in to points
+--
+-- @param no_points - the number of points to generate
+--
+-- @params max_iter_per_point - the function generates points in the polygon's bounding box
+-- and discards points which don't lie in the polygon. max_iter_per_point specifies how many
+-- misses per point the funciton accepts before giving up.
+--
+-- Returns: Multipoint with the requested points
+CREATE OR REPLACE FUNCTION cdb_dot_density(geom geometry , no_points Integer, max_iter_per_point Integer DEFAULT 1000)
+    RETURNS GEOMETRY AS $$
+DECLARE
+    extent GEOMETRY;
+    test_point Geometry;
+    width                NUMERIC;
+    height               NUMERIC;
+    x0                   NUMERIC;
+    y0                   NUMERIC;
+    xp                   NUMERIC;
+    yp                   NUMERIC;
+    no_left              INTEGER;
+    remaining_iterations INTEGER;
+    points               GEOMETRY[];
+    bbox_line            GEOMETRY;
+    intersection_line    GEOMETRY;
+BEGIN
+    extent  := ST_Envelope(geom);
+    width   := ST_XMax(extent) - ST_XMIN(extent);
+    height  := ST_YMax(extent) - ST_YMIN(extent);
+    x0 	  := ST_XMin(extent);
+    y0 	  := ST_YMin(extent);
+    no_left := no_points;
+
+    LOOP
+        if(no_left=0) THEN
+            EXIT;
+        END IF;
+        yp = y0 + height*random();
+        bbox_line  = ST_MakeLine(
+            ST_SetSRID(ST_MakePoint(yp, x0),4326),
+            ST_SetSRID(ST_MakePoint(yp, x0+width),4326)
+        );
+        intersection_line = ST_Intersection(bbox_line,geom);
+        test_point = ST_LineInterpolatePoint(st_makeline(st_linemerge(intersection_line)),random());
+        points := points || test_point;
+        no_left = no_left - 1 ;
+    END LOOP;
+    RETURN ST_Collect(points);
+END;
+$$
+LANGUAGE plpgsql VOLATILE;
+-- Make sure by default there are no permissions for publicuser
+-- NOTE: this happens at extension creation time, as part of an implicit transaction.
+-- REVOKE ALL PRIVILEGES ON SCHEMA cdb_crankshaft FROM PUBLIC, publicuser CASCADE;
+
+-- Grant permissions on the schema to publicuser (but just the schema)
+GRANT USAGE ON SCHEMA cdb_crankshaft TO publicuser;
+
+-- Revoke execute permissions on all functions in the schema by default
+-- REVOKE EXECUTE ON ALL FUNCTIONS IN SCHEMA cdb_crankshaft FROM PUBLIC, publicuser;

release/crankshaft--0.0.2.sql

@@ -0,0 +1,186 @@
+--DO NOT MODIFY THIS FILE, IT IS GENERATED AUTOMATICALLY FROM SOURCES
+-- Complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION crankshaft" to load this file. \quit
+-- Version number of the extension release
+CREATE OR REPLACE FUNCTION cdb_crankshaft_version()
+RETURNS text AS $$
+  SELECT '0.0.2'::text;
+$$ language 'sql' STABLE STRICT;
+
+-- Internal identifier of the installed extension instence
+-- e.g. 'dev' for current development version
+CREATE OR REPLACE FUNCTION _cdb_crankshaft_internal_version()
+RETURNS text AS $$
+  SELECT installed_version FROM pg_available_extensions where name='crankshaft' and pg_available_extensions IS NOT NULL;
+$$ language 'sql' STABLE STRICT;
+CREATE OR REPLACE FUNCTION _cdb_crankshaft_virtualenvs_path()
+RETURNS text
+AS $$
+  BEGIN
+    -- RETURN '/opt/virtualenvs/crankshaft';
+    RETURN '/home/ubuntu/crankshaft/envs';
+  END;
+$$ language plpgsql IMMUTABLE STRICT;
+
+-- Use the crankshaft python module
+CREATE OR REPLACE FUNCTION _cdb_crankshaft_activate_py()
+RETURNS VOID
+AS $$
+    import os
+    # plpy.notice('%',str(os.environ))
+    # activate virtualenv
+    crankshaft_version = plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_internal_version()')[0]['_cdb_crankshaft_internal_version']
+    base_path = plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_virtualenvs_path()')[0]['_cdb_crankshaft_virtualenvs_path']
+    default_venv_path = os.path.join(base_path, crankshaft_version)
+    venv_path =  os.environ.get('CRANKSHAFT_VENV', default_venv_path)
+    activate_path = venv_path + '/bin/activate_this.py'
+    exec(open(activate_path).read(), dict(__file__=activate_path))
+$$ LANGUAGE plpythonu;
+-- Internal function.
+-- Set the seeds of the RNGs (Random Number Generators)
+-- used internally.
+CREATE OR REPLACE FUNCTION
+_cdb_random_seeds (seed_value INTEGER) RETURNS VOID
+AS $$
+  plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
+  from crankshaft import random_seeds
+  random_seeds.set_random_seeds(seed_value)
+$$ LANGUAGE plpythonu;
+-- Moran's I
+CREATE OR REPLACE FUNCTION
+  cdb_moran_local (
+      t TEXT,
+  	  attr TEXT,
+  	  significance float DEFAULT 0.05,
+  	  num_ngbrs INT DEFAULT 5,
+  	  permutations INT DEFAULT 99,
+  	  geom_column TEXT DEFAULT 'the_geom',
+  	  id_col TEXT DEFAULT 'cartodb_id',
+      w_type TEXT DEFAULT 'knn')
+RETURNS TABLE (moran FLOAT, quads TEXT, significance FLOAT, ids INT)
+AS $$
+  plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
+  from crankshaft.clustering import moran_local
+  # TODO: use named parameters or a dictionary
+  return moran_local(t, attr, significance, num_ngbrs, permutations, geom_column, id_col, w_type)
+$$ LANGUAGE plpythonu;
+
+-- Moran's I Local Rate
+CREATE OR REPLACE FUNCTION
+  cdb_moran_local_rate(t TEXT,
+		 numerator TEXT,
+		 denominator TEXT,
+		 significance FLOAT DEFAULT 0.05,
+		 num_ngbrs INT DEFAULT 5,
+		 permutations INT DEFAULT 99,
+		 geom_column TEXT DEFAULT 'the_geom',
+		 id_col TEXT DEFAULT 'cartodb_id',
+		 w_type TEXT DEFAULT 'knn')
+RETURNS TABLE(moran FLOAT, quads TEXT, significance FLOAT, ids INT, y numeric)
+AS $$
+  plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
+  from crankshaft.clustering import moran_local_rate
+  # TODO: use named parameters or a dictionary
+  return moran_local_rate(t, numerator, denominator, significance, num_ngbrs, permutations, geom_column, id_col, w_type)
+$$ LANGUAGE plpythonu;
+-- Function by Stuart Lynn for a simple interpolation of a value
+-- from a polygon table over an arbitrary polygon
+-- (weighted by the area proportion overlapped)
+-- Aereal weighting is a very simple form of aereal interpolation.
+--
+-- Parameters:
+--   * geom a Polygon geometry which defines the area where a value will be
+--     estimated as the area-weighted sum of a given table/column
+--   * target_table_name table name of the table that provides the values
+--   * target_column column name of the column that provides the values
+--   * schema_name optional parameter to defina the schema the target table
+--     belongs to, which is necessary if its not in the search_path.
+--     Note that target_table_name should never include the schema in it.
+-- Return value:
+--   Aereal-weighted interpolation of the column values over the geometry
+CREATE OR REPLACE
+FUNCTION cdb_overlap_sum(geom geometry, target_table_name text, target_column text, schema_name text DEFAULT NULL)
+  RETURNS numeric AS
+$$
+DECLARE
+	result numeric;
+  qualified_name text;
+BEGIN
+  IF schema_name IS NULL THEN
+    qualified_name := Format('%I', target_table_name);
+  ELSE
+    qualified_name := Format('%I.%s', schema_name, target_table_name);
+  END IF;
+  EXECUTE Format('
+    SELECT sum(%I*ST_Area(St_Intersection($1, a.the_geom))/ST_Area(a.the_geom))
+    FROM %s AS a
+    WHERE $1 && a.the_geom
+  ', target_column, qualified_name)
+  USING geom
+  INTO result;
+  RETURN result;
+END;
+$$ LANGUAGE plpgsql;
+--
+-- Creates N points randomly distributed arround the polygon
+--
+-- @param g - the geometry to be turned in to points
+--
+-- @param no_points - the number of points to generate
+--
+-- @params max_iter_per_point - the function generates points in the polygon's bounding box
+-- and discards points which don't lie in the polygon. max_iter_per_point specifies how many
+-- misses per point the funciton accepts before giving up.
+--
+-- Returns: Multipoint with the requested points
+CREATE OR REPLACE FUNCTION cdb_dot_density(geom geometry , no_points Integer, max_iter_per_point Integer DEFAULT 1000)
+RETURNS GEOMETRY AS $$
+DECLARE
+  extent GEOMETRY;
+  test_point Geometry;
+  width                NUMERIC;
+  height               NUMERIC;
+  x0                   NUMERIC;
+  y0                   NUMERIC;
+  xp                   NUMERIC;
+  yp                   NUMERIC;
+  no_left              INTEGER;
+  remaining_iterations INTEGER;
+  points               GEOMETRY[];
+  bbox_line            GEOMETRY;
+  intersection_line    GEOMETRY;
+BEGIN
+  extent  := ST_Envelope(geom);
+  width   := ST_XMax(extent) - ST_XMIN(extent);
+  height  := ST_YMax(extent) - ST_YMIN(extent);
+  x0 	  := ST_XMin(extent);
+  y0 	  := ST_YMin(extent);
+  no_left := no_points;
+
+  LOOP
+    if(no_left=0) THEN
+      EXIT;
+    END IF;
+    yp = y0 + height*random();
+    bbox_line  = ST_MakeLine(
+      ST_SetSRID(ST_MakePoint(yp, x0),4326),
+      ST_SetSRID(ST_MakePoint(yp, x0+width),4326)
+    );
+    intersection_line = ST_Intersection(bbox_line,geom);
+  	test_point = ST_LineInterpolatePoint(st_makeline(st_linemerge(intersection_line)),random());
+	  points := points || test_point;
+	  no_left = no_left - 1 ;
+  END LOOP;
+  RETURN ST_Collect(points);
+END;
+$$
+LANGUAGE plpgsql VOLATILE;
+-- Make sure by default there are no permissions for publicuser
+-- NOTE: this happens at extension creation time, as part of an implicit transaction.
+-- REVOKE ALL PRIVILEGES ON SCHEMA cdb_crankshaft FROM PUBLIC, publicuser CASCADE;
+
+-- Grant permissions on the schema to publicuser (but just the schema)
+GRANT USAGE ON SCHEMA cdb_crankshaft TO publicuser;
+
+-- Revoke execute permissions on all functions in the schema by default
+-- REVOKE EXECUTE ON ALL FUNCTIONS IN SCHEMA cdb_crankshaft FROM PUBLIC, publicuser;

release/crankshaft--0.0.3--0.0.2.sql

@@ -0,0 +1,209 @@
+--DO NOT MODIFY THIS FILE, IT IS GENERATED AUTOMATICALLY FROM SOURCES
+-- Complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION crankshaft" to load this file. \quit
+
+-- [MANUALLY] DROP FUNCTIONS INTRODUCED IN 0.0.3 version
+
+DROP FUNCTION IF EXISTS CDB_AreasOfInterestGlobal(TEXT,TEXT,TEXT,INT,INT,TEXT,TEXT);
+DROP FUNCTION IF EXISTS _CDB_AreasOfInterestLocal(TEXT,TEXT,TEXT,INT,INT,TEXT,TEXT);
+DROP FUNCTION IF EXISTS CDB_AreasOfInterestLocal(TEXT,TEXT,TEXT,INT,INT,TEXT,TEXT);
+DROP FUNCTION IF EXISTS CDB_GetSpatialHotspots(TEXT,TEXT,TEXT,INT,INT,TEXT,TEXT);
+DROP FUNCTION IF EXISTS CDB_GetSpatialColdspots(TEXT,TEXT,TEXT,INT,INT,TEXT,TEXT);
+DROP FUNCTION IF EXISTS CDB_GetSpatialOutliers(TEXT,TEXT,TEXT,INT,INT,TEXT,TEXT);
+DROP FUNCTION IF EXISTS CDB_AreasOfInterestGlobalRate(TEXT,TEXT,TEXT,TEXT,INT,INT,TEXT,TEXT);
+DROP FUNCTION IF EXISTS CDB_AreasOfInterestLocalRate(TEXT,TEXT,TEXT,TEXT,INT,INT,TEXT,TEXT);
+DROP FUNCTION IF EXISTS _CDB_AreasOfInterestLocalRate(TEXT,TEXT,TEXT,TEXT,INT,INT,TEXT,TEXT);
+DROP FUNCTION IF EXISTS CDB_GetSpatialHotspotsRate(TEXT,TEXT,TEXT,TEXT,INT,INT,TEXT,TEXT);
+DROP FUNCTION IF EXISTS CDB_GetSpatialColdspotsRate(TEXT,TEXT,TEXT,TEXT,INT,INT,TEXT,TEXT);
+DROP FUNCTION IF EXISTS CDB_GetSpatialOutliersRate(TEXT,TEXT,TEXT,TEXT,INT,INT,TEXT,TEXT);
+DROP FUNCTION IF EXISTS CDB_KMeans(text,integer,integer);
+DROP AGGREGATE IF EXISTS CDB_WeightedMean(geometry(Point, 4326), NUMERIC);
+DROP FUNCTION IF EXISTS CDB_WeightedMeanS(Numeric[], GEOMETRY(Point, 4326), NUMERIC);
+DROP FUNCTION IF EXISTS CDB_WeightedMeanF(Numeric[]);
+
+
+-- [END MANUALLY] DROP FUNCTIONS INTRODUCED IN 0.0.3 version
+
+-- Version number of the extension release
+CREATE OR REPLACE FUNCTION cdb_crankshaft_version()
+RETURNS text AS $$
+  SELECT '0.0.2'::text;
+$$ language 'sql' STABLE STRICT;
+
+-- Internal identifier of the installed extension instence
+-- e.g. 'dev' for current development version
+CREATE OR REPLACE FUNCTION _cdb_crankshaft_internal_version()
+RETURNS text AS $$
+  SELECT installed_version FROM pg_available_extensions where name='crankshaft' and pg_available_extensions IS NOT NULL;
+$$ language 'sql' STABLE STRICT;
+CREATE OR REPLACE FUNCTION _cdb_crankshaft_virtualenvs_path()
+RETURNS text
+AS $$
+  BEGIN
+    -- RETURN '/opt/virtualenvs/crankshaft';
+    RETURN '/home/ubuntu/crankshaft/envs';
+  END;
+$$ language plpgsql IMMUTABLE STRICT;
+
+-- Use the crankshaft python module
+CREATE OR REPLACE FUNCTION _cdb_crankshaft_activate_py()
+RETURNS VOID
+AS $$
+    import os
+    # plpy.notice('%',str(os.environ))
+    # activate virtualenv
+    crankshaft_version = plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_internal_version()')[0]['_cdb_crankshaft_internal_version']
+    base_path = plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_virtualenvs_path()')[0]['_cdb_crankshaft_virtualenvs_path']
+    default_venv_path = os.path.join(base_path, crankshaft_version)
+    venv_path =  os.environ.get('CRANKSHAFT_VENV', default_venv_path)
+    activate_path = venv_path + '/bin/activate_this.py'
+    exec(open(activate_path).read(), dict(__file__=activate_path))
+$$ LANGUAGE plpythonu;
+-- Internal function.
+-- Set the seeds of the RNGs (Random Number Generators)
+-- used internally.
+CREATE OR REPLACE FUNCTION
+_cdb_random_seeds (seed_value INTEGER) RETURNS VOID
+AS $$
+  plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
+  from crankshaft import random_seeds
+  random_seeds.set_random_seeds(seed_value)
+$$ LANGUAGE plpythonu;
+-- Moran's I
+CREATE OR REPLACE FUNCTION
+  cdb_moran_local (
+      t TEXT,
+  	  attr TEXT,
+  	  significance float DEFAULT 0.05,
+  	  num_ngbrs INT DEFAULT 5,
+  	  permutations INT DEFAULT 99,
+  	  geom_column TEXT DEFAULT 'the_geom',
+  	  id_col TEXT DEFAULT 'cartodb_id',
+      w_type TEXT DEFAULT 'knn')
+RETURNS TABLE (moran FLOAT, quads TEXT, significance FLOAT, ids INT)
+AS $$
+  plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
+  from crankshaft.clustering import moran_local
+  # TODO: use named parameters or a dictionary
+  return moran_local(t, attr, significance, num_ngbrs, permutations, geom_column, id_col, w_type)
+$$ LANGUAGE plpythonu;
+
+-- Moran's I Local Rate
+CREATE OR REPLACE FUNCTION
+  cdb_moran_local_rate(t TEXT,
+		 numerator TEXT,
+		 denominator TEXT,
+		 significance FLOAT DEFAULT 0.05,
+		 num_ngbrs INT DEFAULT 5,
+		 permutations INT DEFAULT 99,
+		 geom_column TEXT DEFAULT 'the_geom',
+		 id_col TEXT DEFAULT 'cartodb_id',
+		 w_type TEXT DEFAULT 'knn')
+RETURNS TABLE(moran FLOAT, quads TEXT, significance FLOAT, ids INT, y numeric)
+AS $$
+  plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
+  from crankshaft.clustering import moran_local_rate
+  # TODO: use named parameters or a dictionary
+  return moran_local_rate(t, numerator, denominator, significance, num_ngbrs, permutations, geom_column, id_col, w_type)
+$$ LANGUAGE plpythonu;
+-- Function by Stuart Lynn for a simple interpolation of a value
+-- from a polygon table over an arbitrary polygon
+-- (weighted by the area proportion overlapped)
+-- Aereal weighting is a very simple form of aereal interpolation.
+--
+-- Parameters:
+--   * geom a Polygon geometry which defines the area where a value will be
+--     estimated as the area-weighted sum of a given table/column
+--   * target_table_name table name of the table that provides the values
+--   * target_column column name of the column that provides the values
+--   * schema_name optional parameter to defina the schema the target table
+--     belongs to, which is necessary if its not in the search_path.
+--     Note that target_table_name should never include the schema in it.
+-- Return value:
+--   Aereal-weighted interpolation of the column values over the geometry
+CREATE OR REPLACE
+FUNCTION cdb_overlap_sum(geom geometry, target_table_name text, target_column text, schema_name text DEFAULT NULL)
+  RETURNS numeric AS
+$$
+DECLARE
+	result numeric;
+  qualified_name text;
+BEGIN
+  IF schema_name IS NULL THEN
+    qualified_name := Format('%I', target_table_name);
+  ELSE
+    qualified_name := Format('%I.%s', schema_name, target_table_name);
+  END IF;
+  EXECUTE Format('
+    SELECT sum(%I*ST_Area(St_Intersection($1, a.the_geom))/ST_Area(a.the_geom))
+    FROM %s AS a
+    WHERE $1 && a.the_geom
+  ', target_column, qualified_name)
+  USING geom
+  INTO result;
+  RETURN result;
+END;
+$$ LANGUAGE plpgsql;
+--
+-- Creates N points randomly distributed arround the polygon
+--
+-- @param g - the geometry to be turned in to points
+--
+-- @param no_points - the number of points to generate
+--
+-- @params max_iter_per_point - the function generates points in the polygon's bounding box
+-- and discards points which don't lie in the polygon. max_iter_per_point specifies how many
+-- misses per point the funciton accepts before giving up.
+--
+-- Returns: Multipoint with the requested points
+CREATE OR REPLACE FUNCTION cdb_dot_density(geom geometry , no_points Integer, max_iter_per_point Integer DEFAULT 1000)
+RETURNS GEOMETRY AS $$
+DECLARE
+  extent GEOMETRY;
+  test_point Geometry;
+  width                NUMERIC;
+  height               NUMERIC;
+  x0                   NUMERIC;
+  y0                   NUMERIC;
+  xp                   NUMERIC;
+  yp                   NUMERIC;
+  no_left              INTEGER;
+  remaining_iterations INTEGER;
+  points               GEOMETRY[];
+  bbox_line            GEOMETRY;
+  intersection_line    GEOMETRY;
+BEGIN
+  extent  := ST_Envelope(geom);
+  width   := ST_XMax(extent) - ST_XMIN(extent);
+  height  := ST_YMax(extent) - ST_YMIN(extent);
+  x0 	  := ST_XMin(extent);
+  y0 	  := ST_YMin(extent);
+  no_left := no_points;
+
+  LOOP
+    if(no_left=0) THEN
+      EXIT;
+    END IF;
+    yp = y0 + height*random();
+    bbox_line  = ST_MakeLine(
+      ST_SetSRID(ST_MakePoint(yp, x0),4326),
+      ST_SetSRID(ST_MakePoint(yp, x0+width),4326)
+    );
+    intersection_line = ST_Intersection(bbox_line,geom);
+  	test_point = ST_LineInterpolatePoint(st_makeline(st_linemerge(intersection_line)),random());
+	  points := points || test_point;
+	  no_left = no_left - 1 ;
+  END LOOP;
+  RETURN ST_Collect(points);
+END;
+$$
+LANGUAGE plpgsql VOLATILE;
+-- Make sure by default there are no permissions for publicuser
+-- NOTE: this happens at extension creation time, as part of an implicit transaction.
+-- REVOKE ALL PRIVILEGES ON SCHEMA cdb_crankshaft FROM PUBLIC, publicuser CASCADE;
+
+-- Grant permissions on the schema to publicuser (but just the schema)
+GRANT USAGE ON SCHEMA cdb_crankshaft TO publicuser;
+
+-- Revoke execute permissions on all functions in the schema by default
+-- REVOKE EXECUTE ON ALL FUNCTIONS IN SCHEMA cdb_crankshaft FROM PUBLIC, publicuser;

release/crankshaft--0.0.3--0.0.4.sql

@@ -0,0 +1,8 @@
+--DO NOT MODIFY THIS FILE, IT IS GENERATED AUTOMATICALLY FROM SOURCES
+-- Complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION crankshaft" to load this file. \quit
+-- Version number of the extension release
+CREATE OR REPLACE FUNCTION cdb_crankshaft_version()
+RETURNS text AS $$
+  SELECT '0.0.4'::text;
+$$ language 'sql' STABLE STRICT;

release/crankshaft--0.0.3.sql

@@ -0,0 +1,403 @@
+--DO NOT MODIFY THIS FILE, IT IS GENERATED AUTOMATICALLY FROM SOURCES
+-- Complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION crankshaft" to load this file. \quit
+-- Version number of the extension release
+CREATE OR REPLACE FUNCTION cdb_crankshaft_version()
+RETURNS text AS $$
+  SELECT '0.0.3'::text;
+$$ language 'sql' STABLE STRICT;
+
+-- Internal identifier of the installed extension instence
+-- e.g. 'dev' for current development version
+CREATE OR REPLACE FUNCTION _cdb_crankshaft_internal_version()
+RETURNS text AS $$
+  SELECT installed_version FROM pg_available_extensions where name='crankshaft' and pg_available_extensions IS NOT NULL;
+$$ language 'sql' STABLE STRICT;
+-- Internal function.
+-- Set the seeds of the RNGs (Random Number Generators)
+-- used internally.
+CREATE OR REPLACE FUNCTION
+_cdb_random_seeds (seed_value INTEGER) RETURNS VOID
+AS $$
+  from crankshaft import random_seeds
+  random_seeds.set_random_seeds(seed_value)
+$$ LANGUAGE plpythonu;
+-- Moran's I Global Measure (public-facing)
+CREATE OR REPLACE FUNCTION
+  CDB_AreasOfInterestGlobal(
+      subquery TEXT,
+      column_name TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS TABLE (moran NUMERIC, significance NUMERIC)
+AS $$
+  from crankshaft.clustering import moran_local
+  # TODO: use named parameters or a dictionary
+  return moran(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+-- Moran's I Local (internal function)
+CREATE OR REPLACE FUNCTION
+  _CDB_AreasOfInterestLocal(
+      subquery TEXT,
+      column_name TEXT,
+      w_type TEXT,
+      num_ngbrs INT,
+      permutations INT,
+      geom_col TEXT,
+      id_col TEXT)
+RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+  from crankshaft.clustering import moran_local
+  # TODO: use named parameters or a dictionary
+  return moran_local(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+-- Moran's I Local (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_AreasOfInterestLocal(
+    subquery TEXT,
+    column_name TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col);
+
+$$ LANGUAGE SQL;
+
+-- Moran's I only for HH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialHotspots(
+    subquery TEXT,
+    column_name TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HH', 'HL');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I only for LL and LH (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialColdspots(
+    subquery TEXT,
+    attr TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, attr, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('LL', 'LH');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I only for LH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialOutliers(
+    subquery TEXT,
+    attr TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, attr, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HL', 'LH');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Global Rate (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_AreasOfInterestGlobalRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS TABLE (moran FLOAT, significance FLOAT)
+AS $$
+  from crankshaft.clustering import moran_local
+  # TODO: use named parameters or a dictionary
+  return moran_rate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+
+-- Moran's I Local Rate (internal function)
+CREATE OR REPLACE FUNCTION
+  _CDB_AreasOfInterestLocalRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT,
+      num_ngbrs INT,
+      permutations INT,
+      geom_col TEXT,
+      id_col TEXT)
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+  from crankshaft.clustering import moran_local_rate
+  # TODO: use named parameters or a dictionary
+  return moran_local_rate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+-- Moran's I Local Rate (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_AreasOfInterestLocalRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col);
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Local Rate only for HH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialHotspotsRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HH', 'HL');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Local Rate only for LL and LH (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialColdspotsRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('LL', 'LH');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Local Rate only for LH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialOutliersRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HL', 'LH');
+
+$$ LANGUAGE SQL;
+CREATE OR REPLACE FUNCTION  CDB_KMeans(query text, no_clusters integer,no_init integer default 20)
+RETURNS table (cartodb_id integer, cluster_no integer) as $$
+    
+    from crankshaft.clustering import kmeans
+    return kmeans(query,no_clusters,no_init)
+
+$$ language plpythonu;
+
+
+CREATE OR REPLACE FUNCTION CDB_WeightedMeanS(state Numeric[],the_geom GEOMETRY(Point, 4326), weight NUMERIC)
+RETURNS Numeric[] AS 
+$$
+DECLARE 
+    newX NUMERIC;
+    newY NUMERIC;
+    newW NUMERIC;
+BEGIN
+    IF weight IS NULL OR the_geom IS NULL THEN 
+        newX = state[1];
+        newY = state[2];
+        newW = state[3];
+    ELSE
+        newX = state[1] + ST_X(the_geom)*weight;
+        newY = state[2] + ST_Y(the_geom)*weight;
+        newW = state[3] + weight;
+    END IF;
+    RETURN Array[newX,newY,newW];
+
+END
+$$ LANGUAGE plpgsql;
+
+CREATE OR REPLACE FUNCTION CDB_WeightedMeanF(state Numeric[])
+RETURNS GEOMETRY AS 
+$$
+BEGIN
+    IF state[3] = 0 THEN 
+        RETURN ST_SetSRID(ST_MakePoint(state[1],state[2]), 4326);
+    ELSE 
+        RETURN ST_SETSRID(ST_MakePoint(state[1]/state[3], state[2]/state[3]),4326);
+    END IF;
+END
+$$ LANGUAGE plpgsql;
+
+CREATE AGGREGATE CDB_WeightedMean(geometry(Point, 4326), NUMERIC)(
+    SFUNC = CDB_WeightedMeanS,
+    FINALFUNC = CDB_WeightedMeanF,
+    STYPE = Numeric[],
+    INITCOND = "{0.0,0.0,0.0}" 
+);
+-- Function by Stuart Lynn for a simple interpolation of a value
+-- from a polygon table over an arbitrary polygon
+-- (weighted by the area proportion overlapped)
+-- Aereal weighting is a very simple form of aereal interpolation.
+--
+-- Parameters:
+--   * geom a Polygon geometry which defines the area where a value will be
+--     estimated as the area-weighted sum of a given table/column
+--   * target_table_name table name of the table that provides the values
+--   * target_column column name of the column that provides the values
+--   * schema_name optional parameter to defina the schema the target table
+--     belongs to, which is necessary if its not in the search_path.
+--     Note that target_table_name should never include the schema in it.
+-- Return value:
+--   Aereal-weighted interpolation of the column values over the geometry
+CREATE OR REPLACE
+FUNCTION cdb_overlap_sum(geom geometry, target_table_name text, target_column text, schema_name text DEFAULT NULL)
+  RETURNS numeric AS
+$$
+DECLARE
+	result numeric;
+  qualified_name text;
+BEGIN
+  IF schema_name IS NULL THEN
+    qualified_name := Format('%I', target_table_name);
+  ELSE
+    qualified_name := Format('%I.%s', schema_name, target_table_name);
+  END IF;
+  EXECUTE Format('
+    SELECT sum(%I*ST_Area(St_Intersection($1, a.the_geom))/ST_Area(a.the_geom))
+    FROM %s AS a
+    WHERE $1 && a.the_geom
+  ', target_column, qualified_name)
+  USING geom
+  INTO result;
+  RETURN result;
+END;
+$$ LANGUAGE plpgsql;
+--
+-- Creates N points randomly distributed arround the polygon
+--
+-- @param g - the geometry to be turned in to points
+--
+-- @param no_points - the number of points to generate
+--
+-- @params max_iter_per_point - the function generates points in the polygon's bounding box
+-- and discards points which don't lie in the polygon. max_iter_per_point specifies how many
+-- misses per point the funciton accepts before giving up.
+--
+-- Returns: Multipoint with the requested points
+CREATE OR REPLACE FUNCTION cdb_dot_density(geom geometry , no_points Integer, max_iter_per_point Integer DEFAULT 1000)
+RETURNS GEOMETRY AS $$
+DECLARE
+  extent GEOMETRY;
+  test_point Geometry;
+  width                NUMERIC;
+  height               NUMERIC;
+  x0                   NUMERIC;
+  y0                   NUMERIC;
+  xp                   NUMERIC;
+  yp                   NUMERIC;
+  no_left              INTEGER;
+  remaining_iterations INTEGER;
+  points               GEOMETRY[];
+  bbox_line            GEOMETRY;
+  intersection_line    GEOMETRY;
+BEGIN
+  extent  := ST_Envelope(geom);
+  width   := ST_XMax(extent) - ST_XMIN(extent);
+  height  := ST_YMax(extent) - ST_YMIN(extent);
+  x0 	  := ST_XMin(extent);
+  y0 	  := ST_YMin(extent);
+  no_left := no_points;
+
+  LOOP
+    if(no_left=0) THEN
+      EXIT;
+    END IF;
+    yp = y0 + height*random();
+    bbox_line  = ST_MakeLine(
+      ST_SetSRID(ST_MakePoint(yp, x0),4326),
+      ST_SetSRID(ST_MakePoint(yp, x0+width),4326)
+    );
+    intersection_line = ST_Intersection(bbox_line,geom);
+  	test_point = ST_LineInterpolatePoint(st_makeline(st_linemerge(intersection_line)),random());
+	  points := points || test_point;
+	  no_left = no_left - 1 ;
+  END LOOP;
+  RETURN ST_Collect(points);
+END;
+$$
+LANGUAGE plpgsql VOLATILE;
+-- Make sure by default there are no permissions for publicuser
+-- NOTE: this happens at extension creation time, as part of an implicit transaction.
+-- REVOKE ALL PRIVILEGES ON SCHEMA cdb_crankshaft FROM PUBLIC, publicuser CASCADE;
+
+-- Grant permissions on the schema to publicuser (but just the schema)
+GRANT USAGE ON SCHEMA cdb_crankshaft TO publicuser;
+
+-- Revoke execute permissions on all functions in the schema by default
+-- REVOKE EXECUTE ON ALL FUNCTIONS IN SCHEMA cdb_crankshaft FROM PUBLIC, publicuser;

release/crankshaft--0.0.4--0.0.3.sql

@@ -0,0 +1,8 @@
+--DO NOT MODIFY THIS FILE, IT IS GENERATED AUTOMATICALLY FROM SOURCES
+-- Complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION crankshaft" to load this file. \quit
+-- Version number of the extension release
+CREATE OR REPLACE FUNCTION cdb_crankshaft_version()
+RETURNS text AS $$
+  SELECT '0.0.3'::text;
+$$ language 'sql' STABLE STRICT;

release/crankshaft--0.0.4--0.1.0.sql

@@ -0,0 +1,258 @@
+--DO NOT MODIFY THIS FILE, IT IS GENERATED FROM SOURCES
+
+-- Complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION crankshaft" to load this file. \quit
+
+--------------------------------------------------------------------------------
+
+-- Version number of the extension release
+CREATE OR REPLACE FUNCTION cdb_crankshaft_version()
+RETURNS text AS $$
+  SELECT '0.1.0'::text;
+$$ language 'sql' STABLE STRICT;
+
+--------------------------------------------------------------------------------
+
+-- PyAgg stuff
+CREATE OR REPLACE FUNCTION
+    CDB_PyAggS(current_state Numeric[], current_row Numeric[]) 
+    returns NUMERIC[] as $$
+    BEGIN
+        if array_upper(current_state,1) is null  then
+            RAISE NOTICE 'setting state %',array_upper(current_row,1);
+            current_state[1] = array_upper(current_row,1);
+        end if;
+        return array_cat(current_state,current_row) ;
+    END
+    $$ LANGUAGE plpgsql;
+
+
+CREATE AGGREGATE CDB_PyAgg(NUMERIC[])(
+    SFUNC = CDB_PyAggS,
+    STYPE = Numeric[],
+    INITCOND = "{}" 
+);
+
+--------------------------------------------------------------------------------
+
+-- Segmentation stuff
+CREATE OR REPLACE FUNCTION
+  CDB_CreateAndPredictSegment(
+    target NUMERIC[],
+    features NUMERIC[],
+    target_features NUMERIC[],
+    target_ids NUMERIC[],
+    n_estimators INTEGER DEFAULT 1200,
+    max_depth INTEGER DEFAULT 3,
+    subsample DOUBLE PRECISION DEFAULT 0.5,
+    learning_rate DOUBLE PRECISION DEFAULT 0.01,
+    min_samples_leaf INTEGER DEFAULT 1)
+RETURNS TABLE(cartodb_id NUMERIC, prediction NUMERIC, accuracy NUMERIC)
+AS $$
+    import numpy as np
+    import plpy
+
+    from crankshaft.segmentation import create_and_predict_segment_agg
+    model_params = {'n_estimators': n_estimators,
+                    'max_depth': max_depth,
+                    'subsample': subsample,
+                    'learning_rate': learning_rate,
+                    'min_samples_leaf': min_samples_leaf}
+
+    def unpack2D(data):
+        dimension = data.pop(0)
+        a = np.array(data, dtype=float)
+        return a.reshape(len(a)/dimension, dimension)
+
+    return create_and_predict_segment_agg(np.array(target, dtype=float),
+            unpack2D(features),
+            unpack2D(target_features),
+            target_ids,
+            model_params)
+
+$$ LANGUAGE plpythonu;
+
+CREATE OR REPLACE FUNCTION
+  CDB_CreateAndPredictSegment (
+      query TEXT,
+      variable_name TEXT,
+      target_table TEXT,
+      n_estimators INTEGER DEFAULT 1200,
+      max_depth INTEGER DEFAULT 3,
+      subsample DOUBLE PRECISION DEFAULT 0.5,
+      learning_rate DOUBLE PRECISION DEFAULT 0.01,
+      min_samples_leaf INTEGER DEFAULT 1)
+RETURNS TABLE (cartodb_id TEXT, prediction NUMERIC, accuracy NUMERIC)
+AS $$
+  from crankshaft.segmentation import create_and_predict_segment
+  model_params = {'n_estimators': n_estimators, 'max_depth':max_depth, 'subsample' : subsample, 'learning_rate': learning_rate, 'min_samples_leaf' : min_samples_leaf}
+  return create_and_predict_segment(query,variable_name,target_table, model_params)
+$$ LANGUAGE plpythonu;
+
+--------------------------------------------------------------------------------
+
+-- Spatial interpolation
+
+-- 0: nearest neighbor
+-- 1: barymetric
+-- 2: IDW
+
+CREATE OR REPLACE FUNCTION CDB_SpatialInterpolation(
+    IN query text,
+    IN point geometry,
+    IN method integer DEFAULT 1,
+    IN p1 numeric DEFAULT 0,
+    IN p2 numeric DEFAULT 0
+    )
+RETURNS numeric AS
+$$
+DECLARE
+    gs geometry[];
+    vs numeric[];
+    output numeric;
+BEGIN
+    EXECUTE 'WITH a AS('||query||') SELECT array_agg(the_geom), array_agg(attrib) FROM a' INTO gs, vs;
+    SELECT CDB_SpatialInterpolation(gs, vs, point, method, p1,p2) INTO output FROM a;
+
+    RETURN output;
+END;
+$$
+language plpgsql IMMUTABLE;
+
+CREATE OR REPLACE FUNCTION CDB_SpatialInterpolation(
+    IN geomin geometry[],
+    IN colin numeric[],
+    IN point geometry,
+    IN method integer DEFAULT 1,
+    IN p1 numeric DEFAULT 0,
+    IN p2 numeric DEFAULT 0
+    )
+RETURNS numeric AS
+$$
+DECLARE
+    gs geometry[];
+    vs numeric[];
+    gs2 geometry[];
+    vs2 numeric[];
+    g geometry;
+    vertex geometry[];
+    sg numeric;
+    sa numeric;
+    sb numeric;
+    sc numeric;
+    va numeric;
+    vb numeric;
+    vc numeric;
+    output numeric;
+BEGIN
+    output :=  -999.999;
+    -- nearest
+    IF method = 0 THEN
+
+        WITH    a as (SELECT unnest(geomin) as g, unnest(colin) as v)
+        SELECT a.v INTO output FROM a ORDER BY point<->a.g LIMIT 1;
+        RETURN output;
+
+    -- barymetric
+    ELSIF method = 1 THEN
+        WITH    a as (SELECT unnest(geomin) AS e),
+                b as (SELECT ST_DelaunayTriangles(ST_Collect(a.e),0.001, 0) AS t FROM a),
+                c as (SELECT (ST_Dump(t)).geom as v FROM b),
+                d as (SELECT v FROM c WHERE ST_Within(point, v))
+            SELECT v INTO g FROM d;
+        IF g is null THEN
+            -- out of the realm of the input data
+            RETURN -888.888;
+        END IF;
+        -- vertex of the selected cell
+        WITH a AS (SELECT (ST_DumpPoints(g)).geom AS v)
+                SELECT array_agg(v) INTO vertex FROM a;
+
+            -- retrieve the value of each vertex
+        WITH a AS(SELECT unnest(vertex) as geo, unnest(colin) as c)
+            SELECT c INTO va FROM a WHERE ST_Equals(geo, vertex[1]);
+        WITH a AS(SELECT unnest(vertex) as geo, unnest(colin) as c)
+            SELECT c INTO vb FROM a WHERE ST_Equals(geo, vertex[2]);
+        WITH a AS(SELECT unnest(vertex) as geo, unnest(colin) as c)
+                SELECT c INTO vc FROM a WHERE ST_Equals(geo, vertex[3]);
+
+        SELECT ST_area(g), ST_area(ST_MakePolygon(ST_MakeLine(ARRAY[point, vertex[2], vertex[3], point]))), ST_area(ST_MakePolygon(ST_MakeLine(ARRAY[point, vertex[1], vertex[3], point]))), ST_area(ST_MakePolygon(ST_MakeLine(ARRAY[point,vertex[1],vertex[2], point]))) INTO sg, sa, sb, sc;
+
+        output := (coalesce(sa,0) * coalesce(va,0) + coalesce(sb,0) * coalesce(vb,0) + coalesce(sc,0) * coalesce(vc,0)) / coalesce(sg);
+        RETURN output;
+
+    -- IDW
+    -- p1: limit the number of neighbors, 0->no limit
+    -- p2: order of distance decay, 0-> order 1
+    ELSIF method = 2 THEN
+
+        IF p2 = 0 THEN
+            p2 := 1;
+        END IF;
+
+        WITH    a as (SELECT unnest(geomin) as g, unnest(colin) as v),
+                b as (SELECT a.g, a.v FROM a ORDER BY point<->a.g)
+        SELECT array_agg(b.g), array_agg(b.v) INTO gs, vs FROM b;
+        IF p1::integer>0 THEN
+            gs2:=gs;
+            vs2:=vs;
+            FOR i IN 1..p1
+            LOOP
+                gs2 := gs2 || gs[i];
+                vs2 := vs2 || vs[i];
+            END LOOP;
+        ELSE
+            gs2:=gs;
+            vs2:=vs;
+        END IF;
+
+        WITH    a as (SELECT unnest(gs2) as g, unnest(vs2) as v),
+                b as (
+                    SELECT
+                    (1/ST_distance(point, a.g)^p2::integer) as k,
+                    (a.v/ST_distance(point, a.g)^p2::integer) as f
+                    FROM a
+                )
+        SELECT sum(b.f)/sum(b.k) INTO output FROM b;
+        RETURN output;
+
+    END IF;
+
+    RETURN -777.777;
+
+END;
+$$
+language plpgsql IMMUTABLE;
+
+
+--------------------------------------------------------------------------------
+
+-- Spatial Markov
+
+-- input table format:
+-- id | geom | date_1 | date_2 | date_3
+--  1 | Pt1  | 12.3   | 13.1   | 14.2
+--  2 | Pt2  | 11.0   | 13.2   | 12.5
+--  ...
+-- Sample Function call:
+-- SELECT CDB_SpatialMarkov('SELECT * FROM real_estate',
+--                          Array['date_1', 'date_2', 'date_3'])
+
+CREATE OR REPLACE FUNCTION
+  CDB_SpatialMarkovTrend (
+      subquery TEXT,
+      time_cols TEXT[],
+      num_classes INT DEFAULT 7,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+  	  permutations INT DEFAULT 99,
+  	  geom_col TEXT DEFAULT 'the_geom',
+  	  id_col TEXT DEFAULT 'cartodb_id')
+RETURNS TABLE (trend NUMERIC, trend_up NUMERIC, trend_down NUMERIC, volatility NUMERIC, rowid INT)
+AS $$
+
+  from crankshaft.space_time_dynamics import spatial_markov_trend
+
+  ## TODO: use named parameters or a dictionary
+  return spatial_markov_trend(subquery, time_cols, num_classes, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;

release/crankshaft--0.0.4.sql

@@ -0,0 +1,403 @@
+--DO NOT MODIFY THIS FILE, IT IS GENERATED AUTOMATICALLY FROM SOURCES
+-- Complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION crankshaft" to load this file. \quit
+-- Version number of the extension release
+CREATE OR REPLACE FUNCTION cdb_crankshaft_version()
+RETURNS text AS $$
+  SELECT '0.0.4'::text;
+$$ language 'sql' STABLE STRICT;
+
+-- Internal identifier of the installed extension instence
+-- e.g. 'dev' for current development version
+CREATE OR REPLACE FUNCTION _cdb_crankshaft_internal_version()
+RETURNS text AS $$
+  SELECT installed_version FROM pg_available_extensions where name='crankshaft' and pg_available_extensions IS NOT NULL;
+$$ language 'sql' STABLE STRICT;
+-- Internal function.
+-- Set the seeds of the RNGs (Random Number Generators)
+-- used internally.
+CREATE OR REPLACE FUNCTION
+_cdb_random_seeds (seed_value INTEGER) RETURNS VOID
+AS $$
+  from crankshaft import random_seeds
+  random_seeds.set_random_seeds(seed_value)
+$$ LANGUAGE plpythonu;
+-- Moran's I Global Measure (public-facing)
+CREATE OR REPLACE FUNCTION
+  CDB_AreasOfInterestGlobal(
+      subquery TEXT,
+      column_name TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS TABLE (moran NUMERIC, significance NUMERIC)
+AS $$
+  from crankshaft.clustering import moran_local
+  # TODO: use named parameters or a dictionary
+  return moran(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+-- Moran's I Local (internal function)
+CREATE OR REPLACE FUNCTION
+  _CDB_AreasOfInterestLocal(
+      subquery TEXT,
+      column_name TEXT,
+      w_type TEXT,
+      num_ngbrs INT,
+      permutations INT,
+      geom_col TEXT,
+      id_col TEXT)
+RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+  from crankshaft.clustering import moran_local
+  # TODO: use named parameters or a dictionary
+  return moran_local(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+-- Moran's I Local (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_AreasOfInterestLocal(
+    subquery TEXT,
+    column_name TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col);
+
+$$ LANGUAGE SQL;
+
+-- Moran's I only for HH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialHotspots(
+    subquery TEXT,
+    column_name TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HH', 'HL');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I only for LL and LH (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialColdspots(
+    subquery TEXT,
+    attr TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, attr, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('LL', 'LH');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I only for LH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialOutliers(
+    subquery TEXT,
+    attr TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, attr, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HL', 'LH');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Global Rate (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_AreasOfInterestGlobalRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS TABLE (moran FLOAT, significance FLOAT)
+AS $$
+  from crankshaft.clustering import moran_local
+  # TODO: use named parameters or a dictionary
+  return moran_rate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+
+-- Moran's I Local Rate (internal function)
+CREATE OR REPLACE FUNCTION
+  _CDB_AreasOfInterestLocalRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT,
+      num_ngbrs INT,
+      permutations INT,
+      geom_col TEXT,
+      id_col TEXT)
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+  from crankshaft.clustering import moran_local_rate
+  # TODO: use named parameters or a dictionary
+  return moran_local_rate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+-- Moran's I Local Rate (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_AreasOfInterestLocalRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col);
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Local Rate only for HH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialHotspotsRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HH', 'HL');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Local Rate only for LL and LH (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialColdspotsRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('LL', 'LH');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Local Rate only for LH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialOutliersRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HL', 'LH');
+
+$$ LANGUAGE SQL;
+CREATE OR REPLACE FUNCTION  CDB_KMeans(query text, no_clusters integer,no_init integer default 20)
+RETURNS table (cartodb_id integer, cluster_no integer) as $$
+    
+    from crankshaft.clustering import kmeans
+    return kmeans(query,no_clusters,no_init)
+
+$$ language plpythonu;
+
+
+CREATE OR REPLACE FUNCTION CDB_WeightedMeanS(state Numeric[],the_geom GEOMETRY(Point, 4326), weight NUMERIC)
+RETURNS Numeric[] AS 
+$$
+DECLARE 
+    newX NUMERIC;
+    newY NUMERIC;
+    newW NUMERIC;
+BEGIN
+    IF weight IS NULL OR the_geom IS NULL THEN 
+        newX = state[1];
+        newY = state[2];
+        newW = state[3];
+    ELSE
+        newX = state[1] + ST_X(the_geom)*weight;
+        newY = state[2] + ST_Y(the_geom)*weight;
+        newW = state[3] + weight;
+    END IF;
+    RETURN Array[newX,newY,newW];
+
+END
+$$ LANGUAGE plpgsql;
+
+CREATE OR REPLACE FUNCTION CDB_WeightedMeanF(state Numeric[])
+RETURNS GEOMETRY AS 
+$$
+BEGIN
+    IF state[3] = 0 THEN 
+        RETURN ST_SetSRID(ST_MakePoint(state[1],state[2]), 4326);
+    ELSE 
+        RETURN ST_SETSRID(ST_MakePoint(state[1]/state[3], state[2]/state[3]),4326);
+    END IF;
+END
+$$ LANGUAGE plpgsql;
+
+CREATE AGGREGATE CDB_WeightedMean(geometry(Point, 4326), NUMERIC)(
+    SFUNC = CDB_WeightedMeanS,
+    FINALFUNC = CDB_WeightedMeanF,
+    STYPE = Numeric[],
+    INITCOND = "{0.0,0.0,0.0}" 
+);
+-- Function by Stuart Lynn for a simple interpolation of a value
+-- from a polygon table over an arbitrary polygon
+-- (weighted by the area proportion overlapped)
+-- Aereal weighting is a very simple form of aereal interpolation.
+--
+-- Parameters:
+--   * geom a Polygon geometry which defines the area where a value will be
+--     estimated as the area-weighted sum of a given table/column
+--   * target_table_name table name of the table that provides the values
+--   * target_column column name of the column that provides the values
+--   * schema_name optional parameter to defina the schema the target table
+--     belongs to, which is necessary if its not in the search_path.
+--     Note that target_table_name should never include the schema in it.
+-- Return value:
+--   Aereal-weighted interpolation of the column values over the geometry
+CREATE OR REPLACE
+FUNCTION cdb_overlap_sum(geom geometry, target_table_name text, target_column text, schema_name text DEFAULT NULL)
+  RETURNS numeric AS
+$$
+DECLARE
+	result numeric;
+  qualified_name text;
+BEGIN
+  IF schema_name IS NULL THEN
+    qualified_name := Format('%I', target_table_name);
+  ELSE
+    qualified_name := Format('%I.%s', schema_name, target_table_name);
+  END IF;
+  EXECUTE Format('
+    SELECT sum(%I*ST_Area(St_Intersection($1, a.the_geom))/ST_Area(a.the_geom))
+    FROM %s AS a
+    WHERE $1 && a.the_geom
+  ', target_column, qualified_name)
+  USING geom
+  INTO result;
+  RETURN result;
+END;
+$$ LANGUAGE plpgsql;
+--
+-- Creates N points randomly distributed arround the polygon
+--
+-- @param g - the geometry to be turned in to points
+--
+-- @param no_points - the number of points to generate
+--
+-- @params max_iter_per_point - the function generates points in the polygon's bounding box
+-- and discards points which don't lie in the polygon. max_iter_per_point specifies how many
+-- misses per point the funciton accepts before giving up.
+--
+-- Returns: Multipoint with the requested points
+CREATE OR REPLACE FUNCTION cdb_dot_density(geom geometry , no_points Integer, max_iter_per_point Integer DEFAULT 1000)
+RETURNS GEOMETRY AS $$
+DECLARE
+  extent GEOMETRY;
+  test_point Geometry;
+  width                NUMERIC;
+  height               NUMERIC;
+  x0                   NUMERIC;
+  y0                   NUMERIC;
+  xp                   NUMERIC;
+  yp                   NUMERIC;
+  no_left              INTEGER;
+  remaining_iterations INTEGER;
+  points               GEOMETRY[];
+  bbox_line            GEOMETRY;
+  intersection_line    GEOMETRY;
+BEGIN
+  extent  := ST_Envelope(geom);
+  width   := ST_XMax(extent) - ST_XMIN(extent);
+  height  := ST_YMax(extent) - ST_YMIN(extent);
+  x0 	  := ST_XMin(extent);
+  y0 	  := ST_YMin(extent);
+  no_left := no_points;
+
+  LOOP
+    if(no_left=0) THEN
+      EXIT;
+    END IF;
+    yp = y0 + height*random();
+    bbox_line  = ST_MakeLine(
+      ST_SetSRID(ST_MakePoint(yp, x0),4326),
+      ST_SetSRID(ST_MakePoint(yp, x0+width),4326)
+    );
+    intersection_line = ST_Intersection(bbox_line,geom);
+  	test_point = ST_LineInterpolatePoint(st_makeline(st_linemerge(intersection_line)),random());
+	  points := points || test_point;
+	  no_left = no_left - 1 ;
+  END LOOP;
+  RETURN ST_Collect(points);
+END;
+$$
+LANGUAGE plpgsql VOLATILE;
+-- Make sure by default there are no permissions for publicuser
+-- NOTE: this happens at extension creation time, as part of an implicit transaction.
+-- REVOKE ALL PRIVILEGES ON SCHEMA cdb_crankshaft FROM PUBLIC, publicuser CASCADE;
+
+-- Grant permissions on the schema to publicuser (but just the schema)
+GRANT USAGE ON SCHEMA cdb_crankshaft TO publicuser;
+
+-- Revoke execute permissions on all functions in the schema by default
+-- REVOKE EXECUTE ON ALL FUNCTIONS IN SCHEMA cdb_crankshaft FROM PUBLIC, publicuser;

release/crankshaft--0.1.0--0.0.4.sql

@@ -0,0 +1,81 @@
+--DO NOT MODIFY THIS FILE, IT IS GENERATED FROM SOURCES
+
+-- Complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION crankshaft" to load this file. \quit
+
+-- Version number of the extension release
+CREATE OR REPLACE FUNCTION cdb_crankshaft_version()
+RETURNS text AS $$
+  SELECT '0.0.4'::text;
+$$ language 'sql' STABLE STRICT;
+
+--------------------------------------------------------------------------------
+
+-- Spatial Markov
+
+DROP FUNCTION
+  CDB_SpatialMarkovTrend (
+      subquery TEXT,
+      time_cols TEXT[],
+      num_classes INT,
+      w_type TEXT,
+      num_ngbrs INT,
+  	  permutations INT,
+  	  geom_col TEXT,
+  	  id_col TEXT);
+
+
+--------------------------------------------------------------------------------
+
+-- Spatial interpolation
+
+DROP FUNCTION CDB_SpatialInterpolation(
+    IN geomin geometry[],
+    IN colin numeric[],
+    IN point geometry,
+    IN method integer,
+    IN p1 numeric,
+    IN p2 numeric
+    );
+
+DROP FUNCTION CDB_SpatialInterpolation(
+    IN query text,
+    IN point geometry,
+    IN method integer,
+    IN p1 numeric,
+    IN p2 numeric
+    );
+
+--------------------------------------------------------------------------------
+
+-- Segmentation stuff
+
+DROP FUNCTION
+  CDB_CreateAndPredictSegment (
+      query TEXT,
+      variable_name TEXT,
+      target_table TEXT,
+      n_estimators INTEGER,
+      max_depth INTEGER,
+      subsample DOUBLE PRECISION,
+      learning_rate DOUBLE PRECISION,
+      min_samples_leaf INTEGER);
+
+DROP FUNCTION
+  CDB_CreateAndPredictSegment(
+    target NUMERIC[],
+    features NUMERIC[],
+    target_features NUMERIC[],
+    target_ids NUMERIC[],
+    n_estimators INTEGER,
+    max_depth INTEGER,
+    subsample DOUBLE PRECISION,
+    learning_rate DOUBLE PRECISION,
+    min_samples_leaf INTEGER);
+
+--------------------------------------------------------------------------------
+
+-- PyAgg stuff
+
+DROP AGGREGATE CDB_PyAgg(NUMERIC[]);
+DROP FUNCTION CDB_PyAggS(Numeric[], Numeric[]);

release/crankshaft--0.1.0--0.2.0.sql

@@ -0,0 +1,827 @@
+--DO NOT MODIFY THIS FILE, IT IS GENERATED AUTOMATICALLY FROM SOURCES
+-- Complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION crankshaft" to load this file. \quit
+-- Version number of the extension release
+CREATE OR REPLACE FUNCTION cdb_crankshaft_version()
+RETURNS text AS $$
+  SELECT '0.2.0'::text;
+$$ language 'sql' STABLE STRICT;
+
+-- Internal identifier of the installed extension instence
+-- e.g. 'dev' for current development version
+CREATE OR REPLACE FUNCTION _cdb_crankshaft_internal_version()
+RETURNS text AS $$
+  SELECT installed_version FROM pg_available_extensions where name='crankshaft' and pg_available_extensions IS NOT NULL;
+$$ language 'sql' STABLE STRICT;
+-- Internal function.
+-- Set the seeds of the RNGs (Random Number Generators)
+-- used internally.
+CREATE OR REPLACE FUNCTION
+_cdb_random_seeds (seed_value INTEGER) RETURNS VOID
+AS $$
+  from crankshaft import random_seeds
+  random_seeds.set_random_seeds(seed_value)
+$$ LANGUAGE plpythonu;
+CREATE OR REPLACE FUNCTION
+    CDB_PyAggS(current_state Numeric[], current_row Numeric[]) 
+    returns NUMERIC[] as $$
+    BEGIN
+        if array_upper(current_state,1) is null  then
+            RAISE NOTICE 'setting state %',array_upper(current_row,1);
+            current_state[1] = array_upper(current_row,1);
+        end if;
+        return array_cat(current_state,current_row) ;
+    END
+    $$ LANGUAGE plpgsql;
+
+-- Create aggregate if it did not exist
+DO $$
+BEGIN
+    IF NOT EXISTS (
+        SELECT *
+        FROM pg_catalog.pg_proc p
+            LEFT JOIN pg_catalog.pg_namespace n ON n.oid = p.pronamespace
+        WHERE n.nspname = 'cdb_crankshaft'
+            AND p.proname = 'cdb_pyagg'
+            AND p.proisagg)
+    THEN
+        CREATE AGGREGATE CDB_PyAgg(NUMERIC[]) (
+            SFUNC = CDB_PyAggS,
+            STYPE = Numeric[],
+            INITCOND = "{}"
+        );
+    END IF;
+END
+$$ LANGUAGE plpgsql;
+
+CREATE OR REPLACE FUNCTION
+  CDB_CreateAndPredictSegment(
+    target NUMERIC[],
+    features NUMERIC[],
+    target_features NUMERIC[],
+    target_ids NUMERIC[],
+    n_estimators INTEGER DEFAULT 1200,
+    max_depth INTEGER DEFAULT 3,
+    subsample DOUBLE PRECISION DEFAULT 0.5,
+    learning_rate DOUBLE PRECISION DEFAULT 0.01,
+    min_samples_leaf INTEGER DEFAULT 1)
+RETURNS TABLE(cartodb_id NUMERIC, prediction NUMERIC, accuracy NUMERIC)
+AS $$
+    import numpy as np
+    import plpy
+
+    from crankshaft.segmentation import create_and_predict_segment_agg
+    model_params = {'n_estimators': n_estimators,
+                    'max_depth': max_depth,
+                    'subsample': subsample,
+                    'learning_rate': learning_rate,
+                    'min_samples_leaf': min_samples_leaf}
+
+    def unpack2D(data):
+        dimension = data.pop(0)
+        a = np.array(data, dtype=float)
+        return a.reshape(len(a)/dimension, dimension)
+
+    return create_and_predict_segment_agg(np.array(target, dtype=float),
+            unpack2D(features),
+            unpack2D(target_features),
+            target_ids,
+            model_params)
+
+$$ LANGUAGE plpythonu;
+
+CREATE OR REPLACE FUNCTION
+  CDB_CreateAndPredictSegment (
+      query TEXT,
+      variable_name TEXT,
+      target_table TEXT,
+      n_estimators INTEGER DEFAULT 1200,
+      max_depth INTEGER DEFAULT 3,
+      subsample DOUBLE PRECISION DEFAULT 0.5,
+      learning_rate DOUBLE PRECISION DEFAULT 0.01,
+      min_samples_leaf INTEGER DEFAULT 1)
+RETURNS TABLE (cartodb_id TEXT, prediction NUMERIC, accuracy NUMERIC)
+AS $$
+  from crankshaft.segmentation import create_and_predict_segment
+  model_params = {'n_estimators': n_estimators, 'max_depth':max_depth, 'subsample' : subsample, 'learning_rate': learning_rate, 'min_samples_leaf' : min_samples_leaf}
+  return create_and_predict_segment(query,variable_name,target_table, model_params)
+$$ LANGUAGE plpythonu;
+CREATE OR REPLACE FUNCTION CDB_Gravity(
+    IN target_query text,
+    IN weight_column text,
+    IN source_query text,
+    IN pop_column text,
+    IN target bigint,
+    IN radius integer,
+    IN minval numeric DEFAULT -10e307
+    )
+RETURNS TABLE(
+    the_geom geometry,
+    source_id bigint,
+    target_id bigint,
+    dist numeric,
+    h numeric,
+    hpop numeric)  AS $$
+DECLARE
+    t_id bigint[];
+    t_geom geometry[];
+    t_weight numeric[];
+    s_id bigint[];
+    s_geom geometry[];
+    s_pop numeric[];
+BEGIN
+    EXECUTE 'WITH foo as('+target_query+') SELECT array_agg(cartodb_id), array_agg(the_geom), array_agg(' || weight_column || ') FROM foo' INTO t_id, t_geom, t_weight;
+    EXECUTE 'WITH foo as('+source_query+') SELECT array_agg(cartodb_id), array_agg(the_geom), array_agg(' || pop_column || ') FROM foo' INTO s_id, s_geom, s_pop;
+    RETURN QUERY
+    SELECT g.* FROM t, s, CDB_Gravity(t_id, t_geom, t_weight, s_id, s_geom, s_pop, target, radius, minval) g;
+END;
+$$ language plpgsql;
+
+CREATE OR REPLACE FUNCTION CDB_Gravity(
+    IN t_id bigint[],
+    IN t_geom geometry[],
+    IN t_weight numeric[],
+    IN s_id bigint[],
+    IN s_geom geometry[],
+    IN s_pop numeric[],
+    IN target bigint,
+    IN radius integer,
+    IN minval numeric DEFAULT -10e307
+    )
+RETURNS TABLE(
+    the_geom geometry,
+    source_id bigint,
+    target_id bigint,
+    dist numeric,
+    h numeric,
+    hpop numeric)  AS $$
+DECLARE
+    t_type text;
+    s_type text;
+    t_center geometry[];
+    s_center geometry[];
+BEGIN
+    t_type := GeometryType(t_geom[1]);
+    s_type := GeometryType(s_geom[1]);
+    IF t_type = 'POINT' THEN
+        t_center := t_geom;
+    ELSE
+        WITH tmp as (SELECT unnest(t_geom) as g) SELECT array_agg(ST_Centroid(g)) INTO t_center FROM tmp;
+    END IF;
+    IF s_type = 'POINT' THEN
+        s_center := s_geom;
+    ELSE
+        WITH tmp as (SELECT unnest(s_geom) as g) SELECT array_agg(ST_Centroid(g)) INTO s_center FROM tmp;
+    END IF;
+    RETURN QUERY
+        with target0 as(
+            SELECT unnest(t_center) as tc, unnest(t_weight) as tw, unnest(t_id) as td
+        ),
+        source0 as(
+            SELECT unnest(s_center) as sc, unnest(s_id) as sd, unnest (s_geom) as sg, unnest(s_pop) as sp
+        ),
+        prev0 as(
+            SELECT
+                source0.sg,
+                source0.sd as sourc_id,
+                coalesce(source0.sp,0) as sp,
+                target.td as targ_id,
+                coalesce(target.tw,0) as tw,
+                GREATEST(1.0,ST_Distance(geography(target.tc), geography(source0.sc)))::numeric as distance
+            FROM source0
+            CROSS JOIN LATERAL
+                (
+                SELECT
+                    *
+                FROM target0
+                    WHERE tw > minval
+                    AND ST_DWithin(geography(source0.sc), geography(tc), radius)
+                ) AS target
+        ),
+        deno as(
+            SELECT
+                sourc_id,
+                sum(tw/distance) as h_deno
+            FROM
+                prev0
+            GROUP BY sourc_id
+        )
+        SELECT
+            p.sg as the_geom,
+            p.sourc_id as source_id,
+            p.targ_id as target_id,
+            case when p.distance > 1 then p.distance else 0.0 end as dist,
+            100*(p.tw/p.distance)/d.h_deno as h,
+            p.sp*(p.tw/p.distance)/d.h_deno as hpop
+        FROM
+            prev0 p,
+            deno d
+        WHERE
+            p.targ_id = target AND
+            p.sourc_id = d.sourc_id;
+END;
+$$ language plpgsql;
+-- 0: nearest neighbor
+-- 1: barymetric
+-- 2: IDW
+
+CREATE OR REPLACE FUNCTION CDB_SpatialInterpolation(
+    IN query text,
+    IN point geometry,
+    IN method integer DEFAULT 1,
+    IN p1 numeric DEFAULT 0,
+    IN p2 numeric DEFAULT 0
+    )
+RETURNS numeric AS
+$$
+DECLARE
+    gs geometry[];
+    vs numeric[];
+    output numeric;
+BEGIN
+    EXECUTE 'WITH a AS('||query||') SELECT array_agg(the_geom), array_agg(attrib) FROM a' INTO gs, vs;
+    SELECT CDB_SpatialInterpolation(gs, vs, point, method, p1,p2) INTO output FROM a;
+
+    RETURN output;
+END;
+$$
+language plpgsql IMMUTABLE;
+
+CREATE OR REPLACE FUNCTION CDB_SpatialInterpolation(
+    IN geomin geometry[],
+    IN colin numeric[],
+    IN point geometry,
+    IN method integer DEFAULT 1,
+    IN p1 numeric DEFAULT 0,
+    IN p2 numeric DEFAULT 0
+    )
+RETURNS numeric AS
+$$
+DECLARE
+    gs geometry[];
+    vs numeric[];
+    gs2 geometry[];
+    vs2 numeric[];
+    g geometry;
+    vertex geometry[];
+    sg numeric;
+    sa numeric;
+    sb numeric;
+    sc numeric;
+    va numeric;
+    vb numeric;
+    vc numeric;
+    output numeric;
+BEGIN
+    output :=  -999.999;
+    -- nearest
+    IF method = 0 THEN
+
+        WITH    a as (SELECT unnest(geomin) as g, unnest(colin) as v)
+        SELECT a.v INTO output FROM a ORDER BY point<->a.g LIMIT 1;
+        RETURN output;
+
+    -- barymetric
+    ELSIF method = 1 THEN
+        WITH    a as (SELECT unnest(geomin) AS e),
+                b as (SELECT ST_DelaunayTriangles(ST_Collect(a.e),0.001, 0) AS t FROM a),
+                c as (SELECT (ST_Dump(t)).geom as v FROM b),
+                d as (SELECT v FROM c WHERE ST_Within(point, v))
+            SELECT v INTO g FROM d;
+        IF g is null THEN
+            -- out of the realm of the input data
+            RETURN -888.888;
+        END IF;
+        -- vertex of the selected cell
+        WITH a AS (SELECT (ST_DumpPoints(g)).geom AS v)
+                SELECT array_agg(v) INTO vertex FROM a;
+
+            -- retrieve the value of each vertex
+        WITH a AS(SELECT unnest(vertex) as geo, unnest(colin) as c)
+            SELECT c INTO va FROM a WHERE ST_Equals(geo, vertex[1]);
+        WITH a AS(SELECT unnest(vertex) as geo, unnest(colin) as c)
+            SELECT c INTO vb FROM a WHERE ST_Equals(geo, vertex[2]);
+        WITH a AS(SELECT unnest(vertex) as geo, unnest(colin) as c)
+                SELECT c INTO vc FROM a WHERE ST_Equals(geo, vertex[3]);
+
+        SELECT ST_area(g), ST_area(ST_MakePolygon(ST_MakeLine(ARRAY[point, vertex[2], vertex[3], point]))), ST_area(ST_MakePolygon(ST_MakeLine(ARRAY[point, vertex[1], vertex[3], point]))), ST_area(ST_MakePolygon(ST_MakeLine(ARRAY[point,vertex[1],vertex[2], point]))) INTO sg, sa, sb, sc;
+
+        output := (coalesce(sa,0) * coalesce(va,0) + coalesce(sb,0) * coalesce(vb,0) + coalesce(sc,0) * coalesce(vc,0)) / coalesce(sg);
+        RETURN output;
+
+    -- IDW
+    -- p1: limit the number of neighbors, 0->no limit
+    -- p2: order of distance decay, 0-> order 1
+    ELSIF method = 2 THEN
+
+        IF p2 = 0 THEN
+            p2 := 1;
+        END IF;
+
+        WITH    a as (SELECT unnest(geomin) as g, unnest(colin) as v),
+                b as (SELECT a.g, a.v FROM a ORDER BY point<->a.g)
+        SELECT array_agg(b.g), array_agg(b.v) INTO gs, vs FROM b;
+        IF p1::integer>0 THEN
+            gs2:=gs;
+            vs2:=vs;
+            FOR i IN 1..p1
+            LOOP
+                gs2 := gs2 || gs[i];
+                vs2 := vs2 || vs[i];
+            END LOOP;
+        ELSE
+            gs2:=gs;
+            vs2:=vs;
+        END IF;
+
+        WITH    a as (SELECT unnest(gs2) as g, unnest(vs2) as v),
+                b as (
+                    SELECT
+                    (1/ST_distance(point, a.g)^p2::integer) as k,
+                    (a.v/ST_distance(point, a.g)^p2::integer) as f
+                    FROM a
+                )
+        SELECT sum(b.f)/sum(b.k) INTO output FROM b;
+        RETURN output;
+
+    END IF;
+
+    RETURN -777.777;
+
+END;
+$$
+language plpgsql IMMUTABLE;
+-- Moran's I Global Measure (public-facing)
+CREATE OR REPLACE FUNCTION
+  CDB_AreasOfInterestGlobal(
+      subquery TEXT,
+      column_name TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS TABLE (moran NUMERIC, significance NUMERIC)
+AS $$
+  from crankshaft.clustering import moran_local
+  # TODO: use named parameters or a dictionary
+  return moran(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+-- Moran's I Local (internal function)
+CREATE OR REPLACE FUNCTION
+  _CDB_AreasOfInterestLocal(
+      subquery TEXT,
+      column_name TEXT,
+      w_type TEXT,
+      num_ngbrs INT,
+      permutations INT,
+      geom_col TEXT,
+      id_col TEXT)
+RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+  from crankshaft.clustering import moran_local
+  # TODO: use named parameters or a dictionary
+  return moran_local(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+-- Moran's I Local (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_AreasOfInterestLocal(
+    subquery TEXT,
+    column_name TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col);
+
+$$ LANGUAGE SQL;
+
+-- Moran's I only for HH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialHotspots(
+    subquery TEXT,
+    column_name TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HH', 'HL');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I only for LL and LH (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialColdspots(
+    subquery TEXT,
+    attr TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, attr, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('LL', 'LH');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I only for LH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialOutliers(
+    subquery TEXT,
+    attr TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, attr, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HL', 'LH');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Global Rate (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_AreasOfInterestGlobalRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS TABLE (moran FLOAT, significance FLOAT)
+AS $$
+  from crankshaft.clustering import moran_local
+  # TODO: use named parameters or a dictionary
+  return moran_rate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+
+-- Moran's I Local Rate (internal function)
+CREATE OR REPLACE FUNCTION
+  _CDB_AreasOfInterestLocalRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT,
+      num_ngbrs INT,
+      permutations INT,
+      geom_col TEXT,
+      id_col TEXT)
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+  from crankshaft.clustering import moran_local_rate
+  # TODO: use named parameters or a dictionary
+  return moran_local_rate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+-- Moran's I Local Rate (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_AreasOfInterestLocalRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col);
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Local Rate only for HH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialHotspotsRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HH', 'HL');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Local Rate only for LL and LH (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialColdspotsRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('LL', 'LH');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Local Rate only for LH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialOutliersRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HL', 'LH');
+
+$$ LANGUAGE SQL;
+CREATE OR REPLACE FUNCTION  CDB_KMeans(query text, no_clusters integer,no_init integer default 20)
+RETURNS table (cartodb_id integer, cluster_no integer) as $$
+    
+    from crankshaft.clustering import kmeans
+    return kmeans(query,no_clusters,no_init)
+
+$$ language plpythonu;
+
+
+CREATE OR REPLACE FUNCTION CDB_WeightedMeanS(state Numeric[],the_geom GEOMETRY(Point, 4326), weight NUMERIC)
+RETURNS Numeric[] AS 
+$$
+DECLARE 
+    newX NUMERIC;
+    newY NUMERIC;
+    newW NUMERIC;
+BEGIN
+    IF weight IS NULL OR the_geom IS NULL THEN 
+        newX = state[1];
+        newY = state[2];
+        newW = state[3];
+    ELSE
+        newX = state[1] + ST_X(the_geom)*weight;
+        newY = state[2] + ST_Y(the_geom)*weight;
+        newW = state[3] + weight;
+    END IF;
+    RETURN Array[newX,newY,newW];
+
+END
+$$ LANGUAGE plpgsql;
+
+CREATE OR REPLACE FUNCTION CDB_WeightedMeanF(state Numeric[])
+RETURNS GEOMETRY AS 
+$$
+BEGIN
+    IF state[3] = 0 THEN 
+        RETURN ST_SetSRID(ST_MakePoint(state[1],state[2]), 4326);
+    ELSE 
+        RETURN ST_SETSRID(ST_MakePoint(state[1]/state[3], state[2]/state[3]),4326);
+    END IF;
+END
+$$ LANGUAGE plpgsql;
+
+-- Create aggregate if it did not exist
+DO $$
+BEGIN
+    IF NOT EXISTS (
+        SELECT *
+        FROM pg_catalog.pg_proc p
+            LEFT JOIN pg_catalog.pg_namespace n ON n.oid = p.pronamespace
+        WHERE n.nspname = 'cdb_crankshaft'
+            AND p.proname = 'cdb_weightedmean'
+            AND p.proisagg)
+    THEN
+        CREATE AGGREGATE CDB_WeightedMean(geometry(Point, 4326), NUMERIC) (
+            SFUNC = CDB_WeightedMeanS,
+            FINALFUNC = CDB_WeightedMeanF,
+            STYPE = Numeric[],
+            INITCOND = "{0.0,0.0,0.0}" 
+        );
+    END IF;
+END
+$$ LANGUAGE plpgsql;
+-- Spatial Markov
+
+-- input table format:
+-- id | geom | date_1 | date_2 | date_3
+--  1 | Pt1  | 12.3   | 13.1   | 14.2
+--  2 | Pt2  | 11.0   | 13.2   | 12.5
+--  ...
+-- Sample Function call:
+-- SELECT CDB_SpatialMarkov('SELECT * FROM real_estate',
+--                          Array['date_1', 'date_2', 'date_3'])
+
+CREATE OR REPLACE FUNCTION
+  CDB_SpatialMarkovTrend (
+      subquery TEXT,
+      time_cols TEXT[],
+      num_classes INT DEFAULT 7,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+  	  permutations INT DEFAULT 99,
+  	  geom_col TEXT DEFAULT 'the_geom',
+  	  id_col TEXT DEFAULT 'cartodb_id')
+RETURNS TABLE (trend NUMERIC, trend_up NUMERIC, trend_down NUMERIC, volatility NUMERIC, rowid INT)
+AS $$
+
+  from crankshaft.space_time_dynamics import spatial_markov_trend
+
+  ## TODO: use named parameters or a dictionary
+  return spatial_markov_trend(subquery, time_cols, num_classes, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+-- input table format: identical to above but in a predictable format
+-- Sample function call:
+-- SELECT cdb_spatial_markov('SELECT * FROM real_estate',
+--                           'date_1')
+
+
+-- CREATE OR REPLACE FUNCTION
+--   cdb_spatial_markov (
+--       subquery TEXT,
+--       time_col_min text,
+--       time_col_max text,
+--       date_format text, -- '_YYYY_MM_DD'
+--       num_time_per_bin INT DEFAULT 1,
+--   	  permutations INT DEFAULT 99,
+--   	  geom_column TEXT DEFAULT 'the_geom',
+--   	  id_col TEXT DEFAULT 'cartodb_id',
+--       w_type TEXT DEFAULT 'knn',
+--       num_ngbrs int DEFAULT 5)
+-- RETURNS TABLE (moran FLOAT, quads TEXT, significance FLOAT, ids INT)
+-- AS $$
+--   plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
+--   from crankshaft.clustering import moran_local
+--   # TODO: use named parameters or a dictionary
+--   return spatial_markov(subquery, time_cols, permutations, geom_column, id_col, w_type, num_ngbrs)
+-- $$ LANGUAGE plpythonu;
+--
+-- -- input table format:
+-- -- id | geom | date  | measurement
+-- --  1 | Pt1  | 12/3  | 13.2
+-- --  2 | Pt2  | 11/5  | 11.3
+-- --  3 | Pt1  | 11/13 | 12.9
+-- --  4 | Pt3  | 12/19 | 10.1
+-- -- ...
+--
+-- CREATE OR REPLACE FUNCTION
+--   cdb_spatial_markov (
+--       subquery TEXT,
+--       time_col text,
+--       num_time_per_bin INT DEFAULT 1,
+--   	  permutations INT DEFAULT 99,
+--   	  geom_column TEXT DEFAULT 'the_geom',
+--   	  id_col TEXT DEFAULT 'cartodb_id',
+--       w_type TEXT DEFAULT 'knn',
+--       num_ngbrs int DEFAULT 5)
+-- RETURNS TABLE (moran FLOAT, quads TEXT, significance FLOAT, ids INT)
+-- AS $$
+--   plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
+--   from crankshaft.clustering import moran_local
+--   # TODO: use named parameters or a dictionary
+--   return spatial_markov(subquery, time_cols, permutations, geom_column, id_col, w_type, num_ngbrs)
+-- $$ LANGUAGE plpythonu;
+-- Function by Stuart Lynn for a simple interpolation of a value
+-- from a polygon table over an arbitrary polygon
+-- (weighted by the area proportion overlapped)
+-- Aereal weighting is a very simple form of aereal interpolation.
+--
+-- Parameters:
+--   * geom a Polygon geometry which defines the area where a value will be
+--     estimated as the area-weighted sum of a given table/column
+--   * target_table_name table name of the table that provides the values
+--   * target_column column name of the column that provides the values
+--   * schema_name optional parameter to defina the schema the target table
+--     belongs to, which is necessary if its not in the search_path.
+--     Note that target_table_name should never include the schema in it.
+-- Return value:
+--   Aereal-weighted interpolation of the column values over the geometry
+CREATE OR REPLACE
+FUNCTION cdb_overlap_sum(geom geometry, target_table_name text, target_column text, schema_name text DEFAULT NULL)
+  RETURNS numeric AS
+$$
+DECLARE
+	result numeric;
+  qualified_name text;
+BEGIN
+  IF schema_name IS NULL THEN
+    qualified_name := Format('%I', target_table_name);
+  ELSE
+    qualified_name := Format('%I.%s', schema_name, target_table_name);
+  END IF;
+  EXECUTE Format('
+    SELECT sum(%I*ST_Area(St_Intersection($1, a.the_geom))/ST_Area(a.the_geom))
+    FROM %s AS a
+    WHERE $1 && a.the_geom
+  ', target_column, qualified_name)
+  USING geom
+  INTO result;
+  RETURN result;
+END;
+$$ LANGUAGE plpgsql;
+--
+-- Creates N points randomly distributed arround the polygon
+--
+-- @param g - the geometry to be turned in to points
+--
+-- @param no_points - the number of points to generate
+--
+-- @params max_iter_per_point - the function generates points in the polygon's bounding box
+-- and discards points which don't lie in the polygon. max_iter_per_point specifies how many
+-- misses per point the funciton accepts before giving up.
+--
+-- Returns: Multipoint with the requested points
+CREATE OR REPLACE FUNCTION cdb_dot_density(geom geometry , no_points Integer, max_iter_per_point Integer DEFAULT 1000)
+RETURNS GEOMETRY AS $$
+DECLARE
+  extent GEOMETRY;
+  test_point Geometry;
+  width                NUMERIC;
+  height               NUMERIC;
+  x0                   NUMERIC;
+  y0                   NUMERIC;
+  xp                   NUMERIC;
+  yp                   NUMERIC;
+  no_left              INTEGER;
+  remaining_iterations INTEGER;
+  points               GEOMETRY[];
+  bbox_line            GEOMETRY;
+  intersection_line    GEOMETRY;
+BEGIN
+  extent  := ST_Envelope(geom);
+  width   := ST_XMax(extent) - ST_XMIN(extent);
+  height  := ST_YMax(extent) - ST_YMIN(extent);
+  x0 	  := ST_XMin(extent);
+  y0 	  := ST_YMin(extent);
+  no_left := no_points;
+
+  LOOP
+    if(no_left=0) THEN
+      EXIT;
+    END IF;
+    yp = y0 + height*random();
+    bbox_line  = ST_MakeLine(
+      ST_SetSRID(ST_MakePoint(yp, x0),4326),
+      ST_SetSRID(ST_MakePoint(yp, x0+width),4326)
+    );
+    intersection_line = ST_Intersection(bbox_line,geom);
+  	test_point = ST_LineInterpolatePoint(st_makeline(st_linemerge(intersection_line)),random());
+	  points := points || test_point;
+	  no_left = no_left - 1 ;
+  END LOOP;
+  RETURN ST_Collect(points);
+END;
+$$
+LANGUAGE plpgsql VOLATILE;
+-- Make sure by default there are no permissions for publicuser
+-- NOTE: this happens at extension creation time, as part of an implicit transaction.
+-- REVOKE ALL PRIVILEGES ON SCHEMA cdb_crankshaft FROM PUBLIC, publicuser CASCADE;
+
+-- Grant permissions on the schema to publicuser (but just the schema)
+GRANT USAGE ON SCHEMA cdb_crankshaft TO publicuser;
+
+-- Revoke execute permissions on all functions in the schema by default
+-- REVOKE EXECUTE ON ALL FUNCTIONS IN SCHEMA cdb_crankshaft FROM PUBLIC, publicuser;

release/crankshaft--0.1.0.sql

@@ -0,0 +1,686 @@
+--DO NOT MODIFY THIS FILE, IT IS GENERATED AUTOMATICALLY FROM SOURCES
+-- Complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION crankshaft" to load this file. \quit
+-- Version number of the extension release
+CREATE OR REPLACE FUNCTION cdb_crankshaft_version()
+RETURNS text AS $$
+  SELECT '0.1.0'::text;
+$$ language 'sql' STABLE STRICT;
+
+-- Internal identifier of the installed extension instence
+-- e.g. 'dev' for current development version
+CREATE OR REPLACE FUNCTION _cdb_crankshaft_internal_version()
+RETURNS text AS $$
+  SELECT installed_version FROM pg_available_extensions where name='crankshaft' and pg_available_extensions IS NOT NULL;
+$$ language 'sql' STABLE STRICT;
+-- Internal function.
+-- Set the seeds of the RNGs (Random Number Generators)
+-- used internally.
+CREATE OR REPLACE FUNCTION
+_cdb_random_seeds (seed_value INTEGER) RETURNS VOID
+AS $$
+  from crankshaft import random_seeds
+  random_seeds.set_random_seeds(seed_value)
+$$ LANGUAGE plpythonu;
+CREATE OR REPLACE FUNCTION
+    CDB_PyAggS(current_state Numeric[], current_row Numeric[]) 
+    returns NUMERIC[] as $$
+    BEGIN
+        if array_upper(current_state,1) is null  then
+            RAISE NOTICE 'setting state %',array_upper(current_row,1);
+            current_state[1] = array_upper(current_row,1);
+        end if;
+        return array_cat(current_state,current_row) ;
+    END
+    $$ LANGUAGE plpgsql;
+
+
+CREATE AGGREGATE CDB_PyAgg(NUMERIC[])(
+    SFUNC = CDB_PyAggS,
+    STYPE = Numeric[],
+    INITCOND = "{}" 
+);
+
+
+CREATE OR REPLACE FUNCTION
+  CDB_CreateAndPredictSegment(
+    target NUMERIC[],
+    features NUMERIC[],
+    target_features NUMERIC[],
+    target_ids NUMERIC[],
+    n_estimators INTEGER DEFAULT 1200,
+    max_depth INTEGER DEFAULT 3,
+    subsample DOUBLE PRECISION DEFAULT 0.5,
+    learning_rate DOUBLE PRECISION DEFAULT 0.01,
+    min_samples_leaf INTEGER DEFAULT 1)
+RETURNS TABLE(cartodb_id NUMERIC, prediction NUMERIC, accuracy NUMERIC)
+AS $$
+    import numpy as np
+    import plpy
+
+    from crankshaft.segmentation import create_and_predict_segment_agg
+    model_params = {'n_estimators': n_estimators,
+                    'max_depth': max_depth,
+                    'subsample': subsample,
+                    'learning_rate': learning_rate,
+                    'min_samples_leaf': min_samples_leaf}
+
+    def unpack2D(data):
+        dimension = data.pop(0)
+        a = np.array(data, dtype=float)
+        return a.reshape(len(a)/dimension, dimension)
+
+    return create_and_predict_segment_agg(np.array(target, dtype=float),
+            unpack2D(features),
+            unpack2D(target_features),
+            target_ids,
+            model_params)
+
+$$ LANGUAGE plpythonu;
+
+CREATE OR REPLACE FUNCTION
+  CDB_CreateAndPredictSegment (
+      query TEXT,
+      variable_name TEXT,
+      target_table TEXT,
+      n_estimators INTEGER DEFAULT 1200,
+      max_depth INTEGER DEFAULT 3,
+      subsample DOUBLE PRECISION DEFAULT 0.5,
+      learning_rate DOUBLE PRECISION DEFAULT 0.01,
+      min_samples_leaf INTEGER DEFAULT 1)
+RETURNS TABLE (cartodb_id TEXT, prediction NUMERIC, accuracy NUMERIC)
+AS $$
+  from crankshaft.segmentation import create_and_predict_segment
+  model_params = {'n_estimators': n_estimators, 'max_depth':max_depth, 'subsample' : subsample, 'learning_rate': learning_rate, 'min_samples_leaf' : min_samples_leaf}
+  return create_and_predict_segment(query,variable_name,target_table, model_params)
+$$ LANGUAGE plpythonu;
+-- 0: nearest neighbor
+-- 1: barymetric
+-- 2: IDW
+
+CREATE OR REPLACE FUNCTION CDB_SpatialInterpolation(
+    IN query text,
+    IN point geometry,
+    IN method integer DEFAULT 1,
+    IN p1 numeric DEFAULT 0,
+    IN p2 numeric DEFAULT 0
+    )
+RETURNS numeric AS
+$$
+DECLARE
+    gs geometry[];
+    vs numeric[];
+    output numeric;
+BEGIN
+    EXECUTE 'WITH a AS('||query||') SELECT array_agg(the_geom), array_agg(attrib) FROM a' INTO gs, vs;
+    SELECT CDB_SpatialInterpolation(gs, vs, point, method, p1,p2) INTO output FROM a;
+
+    RETURN output;
+END;
+$$
+language plpgsql IMMUTABLE;
+
+CREATE OR REPLACE FUNCTION CDB_SpatialInterpolation(
+    IN geomin geometry[],
+    IN colin numeric[],
+    IN point geometry,
+    IN method integer DEFAULT 1,
+    IN p1 numeric DEFAULT 0,
+    IN p2 numeric DEFAULT 0
+    )
+RETURNS numeric AS
+$$
+DECLARE
+    gs geometry[];
+    vs numeric[];
+    gs2 geometry[];
+    vs2 numeric[];
+    g geometry;
+    vertex geometry[];
+    sg numeric;
+    sa numeric;
+    sb numeric;
+    sc numeric;
+    va numeric;
+    vb numeric;
+    vc numeric;
+    output numeric;
+BEGIN
+    output :=  -999.999;
+    -- nearest
+    IF method = 0 THEN
+
+        WITH    a as (SELECT unnest(geomin) as g, unnest(colin) as v)
+        SELECT a.v INTO output FROM a ORDER BY point<->a.g LIMIT 1;
+        RETURN output;
+
+    -- barymetric
+    ELSIF method = 1 THEN
+        WITH    a as (SELECT unnest(geomin) AS e),
+                b as (SELECT ST_DelaunayTriangles(ST_Collect(a.e),0.001, 0) AS t FROM a),
+                c as (SELECT (ST_Dump(t)).geom as v FROM b),
+                d as (SELECT v FROM c WHERE ST_Within(point, v))
+            SELECT v INTO g FROM d;
+        IF g is null THEN
+            -- out of the realm of the input data
+            RETURN -888.888;
+        END IF;
+        -- vertex of the selected cell
+        WITH a AS (SELECT (ST_DumpPoints(g)).geom AS v)
+                SELECT array_agg(v) INTO vertex FROM a;
+
+            -- retrieve the value of each vertex
+        WITH a AS(SELECT unnest(vertex) as geo, unnest(colin) as c)
+            SELECT c INTO va FROM a WHERE ST_Equals(geo, vertex[1]);
+        WITH a AS(SELECT unnest(vertex) as geo, unnest(colin) as c)
+            SELECT c INTO vb FROM a WHERE ST_Equals(geo, vertex[2]);
+        WITH a AS(SELECT unnest(vertex) as geo, unnest(colin) as c)
+                SELECT c INTO vc FROM a WHERE ST_Equals(geo, vertex[3]);
+
+        SELECT ST_area(g), ST_area(ST_MakePolygon(ST_MakeLine(ARRAY[point, vertex[2], vertex[3], point]))), ST_area(ST_MakePolygon(ST_MakeLine(ARRAY[point, vertex[1], vertex[3], point]))), ST_area(ST_MakePolygon(ST_MakeLine(ARRAY[point,vertex[1],vertex[2], point]))) INTO sg, sa, sb, sc;
+
+        output := (coalesce(sa,0) * coalesce(va,0) + coalesce(sb,0) * coalesce(vb,0) + coalesce(sc,0) * coalesce(vc,0)) / coalesce(sg);
+        RETURN output;
+
+    -- IDW
+    -- p1: limit the number of neighbors, 0->no limit
+    -- p2: order of distance decay, 0-> order 1
+    ELSIF method = 2 THEN
+
+        IF p2 = 0 THEN
+            p2 := 1;
+        END IF;
+
+        WITH    a as (SELECT unnest(geomin) as g, unnest(colin) as v),
+                b as (SELECT a.g, a.v FROM a ORDER BY point<->a.g)
+        SELECT array_agg(b.g), array_agg(b.v) INTO gs, vs FROM b;
+        IF p1::integer>0 THEN
+            gs2:=gs;
+            vs2:=vs;
+            FOR i IN 1..p1
+            LOOP
+                gs2 := gs2 || gs[i];
+                vs2 := vs2 || vs[i];
+            END LOOP;
+        ELSE
+            gs2:=gs;
+            vs2:=vs;
+        END IF;
+
+        WITH    a as (SELECT unnest(gs2) as g, unnest(vs2) as v),
+                b as (
+                    SELECT
+                    (1/ST_distance(point, a.g)^p2::integer) as k,
+                    (a.v/ST_distance(point, a.g)^p2::integer) as f
+                    FROM a
+                )
+        SELECT sum(b.f)/sum(b.k) INTO output FROM b;
+        RETURN output;
+
+    END IF;
+
+    RETURN -777.777;
+
+END;
+$$
+language plpgsql IMMUTABLE;
+-- Moran's I Global Measure (public-facing)
+CREATE OR REPLACE FUNCTION
+  CDB_AreasOfInterestGlobal(
+      subquery TEXT,
+      column_name TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS TABLE (moran NUMERIC, significance NUMERIC)
+AS $$
+  from crankshaft.clustering import moran_local
+  # TODO: use named parameters or a dictionary
+  return moran(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+-- Moran's I Local (internal function)
+CREATE OR REPLACE FUNCTION
+  _CDB_AreasOfInterestLocal(
+      subquery TEXT,
+      column_name TEXT,
+      w_type TEXT,
+      num_ngbrs INT,
+      permutations INT,
+      geom_col TEXT,
+      id_col TEXT)
+RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+  from crankshaft.clustering import moran_local
+  # TODO: use named parameters or a dictionary
+  return moran_local(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+-- Moran's I Local (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_AreasOfInterestLocal(
+    subquery TEXT,
+    column_name TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col);
+
+$$ LANGUAGE SQL;
+
+-- Moran's I only for HH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialHotspots(
+    subquery TEXT,
+    column_name TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HH', 'HL');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I only for LL and LH (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialColdspots(
+    subquery TEXT,
+    attr TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, attr, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('LL', 'LH');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I only for LH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialOutliers(
+    subquery TEXT,
+    attr TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, attr, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HL', 'LH');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Global Rate (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_AreasOfInterestGlobalRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS TABLE (moran FLOAT, significance FLOAT)
+AS $$
+  from crankshaft.clustering import moran_local
+  # TODO: use named parameters or a dictionary
+  return moran_rate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+
+-- Moran's I Local Rate (internal function)
+CREATE OR REPLACE FUNCTION
+  _CDB_AreasOfInterestLocalRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT,
+      num_ngbrs INT,
+      permutations INT,
+      geom_col TEXT,
+      id_col TEXT)
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+  from crankshaft.clustering import moran_local_rate
+  # TODO: use named parameters or a dictionary
+  return moran_local_rate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+-- Moran's I Local Rate (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_AreasOfInterestLocalRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col);
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Local Rate only for HH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialHotspotsRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HH', 'HL');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Local Rate only for LL and LH (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialColdspotsRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('LL', 'LH');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Local Rate only for LH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialOutliersRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HL', 'LH');
+
+$$ LANGUAGE SQL;
+CREATE OR REPLACE FUNCTION  CDB_KMeans(query text, no_clusters integer,no_init integer default 20)
+RETURNS table (cartodb_id integer, cluster_no integer) as $$
+    
+    from crankshaft.clustering import kmeans
+    return kmeans(query,no_clusters,no_init)
+
+$$ language plpythonu;
+
+
+CREATE OR REPLACE FUNCTION CDB_WeightedMeanS(state Numeric[],the_geom GEOMETRY(Point, 4326), weight NUMERIC)
+RETURNS Numeric[] AS 
+$$
+DECLARE 
+    newX NUMERIC;
+    newY NUMERIC;
+    newW NUMERIC;
+BEGIN
+    IF weight IS NULL OR the_geom IS NULL THEN 
+        newX = state[1];
+        newY = state[2];
+        newW = state[3];
+    ELSE
+        newX = state[1] + ST_X(the_geom)*weight;
+        newY = state[2] + ST_Y(the_geom)*weight;
+        newW = state[3] + weight;
+    END IF;
+    RETURN Array[newX,newY,newW];
+
+END
+$$ LANGUAGE plpgsql;
+
+CREATE OR REPLACE FUNCTION CDB_WeightedMeanF(state Numeric[])
+RETURNS GEOMETRY AS 
+$$
+BEGIN
+    IF state[3] = 0 THEN 
+        RETURN ST_SetSRID(ST_MakePoint(state[1],state[2]), 4326);
+    ELSE 
+        RETURN ST_SETSRID(ST_MakePoint(state[1]/state[3], state[2]/state[3]),4326);
+    END IF;
+END
+$$ LANGUAGE plpgsql;
+
+CREATE AGGREGATE CDB_WeightedMean(geometry(Point, 4326), NUMERIC)(
+    SFUNC = CDB_WeightedMeanS,
+    FINALFUNC = CDB_WeightedMeanF,
+    STYPE = Numeric[],
+    INITCOND = "{0.0,0.0,0.0}" 
+);
+-- Spatial Markov
+
+-- input table format:
+-- id | geom | date_1 | date_2 | date_3
+--  1 | Pt1  | 12.3   | 13.1   | 14.2
+--  2 | Pt2  | 11.0   | 13.2   | 12.5
+--  ...
+-- Sample Function call:
+-- SELECT CDB_SpatialMarkov('SELECT * FROM real_estate',
+--                          Array['date_1', 'date_2', 'date_3'])
+
+CREATE OR REPLACE FUNCTION
+  CDB_SpatialMarkovTrend (
+      subquery TEXT,
+      time_cols TEXT[],
+      num_classes INT DEFAULT 7,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+  	  permutations INT DEFAULT 99,
+  	  geom_col TEXT DEFAULT 'the_geom',
+  	  id_col TEXT DEFAULT 'cartodb_id')
+RETURNS TABLE (trend NUMERIC, trend_up NUMERIC, trend_down NUMERIC, volatility NUMERIC, rowid INT)
+AS $$
+
+  from crankshaft.space_time_dynamics import spatial_markov_trend
+
+  ## TODO: use named parameters or a dictionary
+  return spatial_markov_trend(subquery, time_cols, num_classes, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+-- input table format: identical to above but in a predictable format
+-- Sample function call:
+-- SELECT cdb_spatial_markov('SELECT * FROM real_estate',
+--                           'date_1')
+
+
+-- CREATE OR REPLACE FUNCTION
+--   cdb_spatial_markov (
+--       subquery TEXT,
+--       time_col_min text,
+--       time_col_max text,
+--       date_format text, -- '_YYYY_MM_DD'
+--       num_time_per_bin INT DEFAULT 1,
+--   	  permutations INT DEFAULT 99,
+--   	  geom_column TEXT DEFAULT 'the_geom',
+--   	  id_col TEXT DEFAULT 'cartodb_id',
+--       w_type TEXT DEFAULT 'knn',
+--       num_ngbrs int DEFAULT 5)
+-- RETURNS TABLE (moran FLOAT, quads TEXT, significance FLOAT, ids INT)
+-- AS $$
+--   plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
+--   from crankshaft.clustering import moran_local
+--   # TODO: use named parameters or a dictionary
+--   return spatial_markov(subquery, time_cols, permutations, geom_column, id_col, w_type, num_ngbrs)
+-- $$ LANGUAGE plpythonu;
+--
+-- -- input table format:
+-- -- id | geom | date  | measurement
+-- --  1 | Pt1  | 12/3  | 13.2
+-- --  2 | Pt2  | 11/5  | 11.3
+-- --  3 | Pt1  | 11/13 | 12.9
+-- --  4 | Pt3  | 12/19 | 10.1
+-- -- ...
+--
+-- CREATE OR REPLACE FUNCTION
+--   cdb_spatial_markov (
+--       subquery TEXT,
+--       time_col text,
+--       num_time_per_bin INT DEFAULT 1,
+--   	  permutations INT DEFAULT 99,
+--   	  geom_column TEXT DEFAULT 'the_geom',
+--   	  id_col TEXT DEFAULT 'cartodb_id',
+--       w_type TEXT DEFAULT 'knn',
+--       num_ngbrs int DEFAULT 5)
+-- RETURNS TABLE (moran FLOAT, quads TEXT, significance FLOAT, ids INT)
+-- AS $$
+--   plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
+--   from crankshaft.clustering import moran_local
+--   # TODO: use named parameters or a dictionary
+--   return spatial_markov(subquery, time_cols, permutations, geom_column, id_col, w_type, num_ngbrs)
+-- $$ LANGUAGE plpythonu;
+-- Function by Stuart Lynn for a simple interpolation of a value
+-- from a polygon table over an arbitrary polygon
+-- (weighted by the area proportion overlapped)
+-- Aereal weighting is a very simple form of aereal interpolation.
+--
+-- Parameters:
+--   * geom a Polygon geometry which defines the area where a value will be
+--     estimated as the area-weighted sum of a given table/column
+--   * target_table_name table name of the table that provides the values
+--   * target_column column name of the column that provides the values
+--   * schema_name optional parameter to defina the schema the target table
+--     belongs to, which is necessary if its not in the search_path.
+--     Note that target_table_name should never include the schema in it.
+-- Return value:
+--   Aereal-weighted interpolation of the column values over the geometry
+CREATE OR REPLACE
+FUNCTION cdb_overlap_sum(geom geometry, target_table_name text, target_column text, schema_name text DEFAULT NULL)
+  RETURNS numeric AS
+$$
+DECLARE
+	result numeric;
+  qualified_name text;
+BEGIN
+  IF schema_name IS NULL THEN
+    qualified_name := Format('%I', target_table_name);
+  ELSE
+    qualified_name := Format('%I.%s', schema_name, target_table_name);
+  END IF;
+  EXECUTE Format('
+    SELECT sum(%I*ST_Area(St_Intersection($1, a.the_geom))/ST_Area(a.the_geom))
+    FROM %s AS a
+    WHERE $1 && a.the_geom
+  ', target_column, qualified_name)
+  USING geom
+  INTO result;
+  RETURN result;
+END;
+$$ LANGUAGE plpgsql;
+--
+-- Creates N points randomly distributed arround the polygon
+--
+-- @param g - the geometry to be turned in to points
+--
+-- @param no_points - the number of points to generate
+--
+-- @params max_iter_per_point - the function generates points in the polygon's bounding box
+-- and discards points which don't lie in the polygon. max_iter_per_point specifies how many
+-- misses per point the funciton accepts before giving up.
+--
+-- Returns: Multipoint with the requested points
+CREATE OR REPLACE FUNCTION cdb_dot_density(geom geometry , no_points Integer, max_iter_per_point Integer DEFAULT 1000)
+RETURNS GEOMETRY AS $$
+DECLARE
+  extent GEOMETRY;
+  test_point Geometry;
+  width                NUMERIC;
+  height               NUMERIC;
+  x0                   NUMERIC;
+  y0                   NUMERIC;
+  xp                   NUMERIC;
+  yp                   NUMERIC;
+  no_left              INTEGER;
+  remaining_iterations INTEGER;
+  points               GEOMETRY[];
+  bbox_line            GEOMETRY;
+  intersection_line    GEOMETRY;
+BEGIN
+  extent  := ST_Envelope(geom);
+  width   := ST_XMax(extent) - ST_XMIN(extent);
+  height  := ST_YMax(extent) - ST_YMIN(extent);
+  x0 	  := ST_XMin(extent);
+  y0 	  := ST_YMin(extent);
+  no_left := no_points;
+
+  LOOP
+    if(no_left=0) THEN
+      EXIT;
+    END IF;
+    yp = y0 + height*random();
+    bbox_line  = ST_MakeLine(
+      ST_SetSRID(ST_MakePoint(yp, x0),4326),
+      ST_SetSRID(ST_MakePoint(yp, x0+width),4326)
+    );
+    intersection_line = ST_Intersection(bbox_line,geom);
+  	test_point = ST_LineInterpolatePoint(st_makeline(st_linemerge(intersection_line)),random());
+	  points := points || test_point;
+	  no_left = no_left - 1 ;
+  END LOOP;
+  RETURN ST_Collect(points);
+END;
+$$
+LANGUAGE plpgsql VOLATILE;
+-- Make sure by default there are no permissions for publicuser
+-- NOTE: this happens at extension creation time, as part of an implicit transaction.
+-- REVOKE ALL PRIVILEGES ON SCHEMA cdb_crankshaft FROM PUBLIC, publicuser CASCADE;
+
+-- Grant permissions on the schema to publicuser (but just the schema)
+GRANT USAGE ON SCHEMA cdb_crankshaft TO publicuser;
+
+-- Revoke execute permissions on all functions in the schema by default
+-- REVOKE EXECUTE ON ALL FUNCTIONS IN SCHEMA cdb_crankshaft FROM PUBLIC, publicuser;

release/crankshaft--0.2.0.sql

@@ -0,0 +1,827 @@
+--DO NOT MODIFY THIS FILE, IT IS GENERATED AUTOMATICALLY FROM SOURCES
+-- Complain if script is sourced in psql, rather than via CREATE EXTENSION
+\echo Use "CREATE EXTENSION crankshaft" to load this file. \quit
+-- Version number of the extension release
+CREATE OR REPLACE FUNCTION cdb_crankshaft_version()
+RETURNS text AS $$
+  SELECT '0.2.0'::text;
+$$ language 'sql' STABLE STRICT;
+
+-- Internal identifier of the installed extension instence
+-- e.g. 'dev' for current development version
+CREATE OR REPLACE FUNCTION _cdb_crankshaft_internal_version()
+RETURNS text AS $$
+  SELECT installed_version FROM pg_available_extensions where name='crankshaft' and pg_available_extensions IS NOT NULL;
+$$ language 'sql' STABLE STRICT;
+-- Internal function.
+-- Set the seeds of the RNGs (Random Number Generators)
+-- used internally.
+CREATE OR REPLACE FUNCTION
+_cdb_random_seeds (seed_value INTEGER) RETURNS VOID
+AS $$
+  from crankshaft import random_seeds
+  random_seeds.set_random_seeds(seed_value)
+$$ LANGUAGE plpythonu;
+CREATE OR REPLACE FUNCTION
+    CDB_PyAggS(current_state Numeric[], current_row Numeric[]) 
+    returns NUMERIC[] as $$
+    BEGIN
+        if array_upper(current_state,1) is null  then
+            RAISE NOTICE 'setting state %',array_upper(current_row,1);
+            current_state[1] = array_upper(current_row,1);
+        end if;
+        return array_cat(current_state,current_row) ;
+    END
+    $$ LANGUAGE plpgsql;
+
+-- Create aggregate if it did not exist
+DO $$
+BEGIN
+    IF NOT EXISTS (
+        SELECT *
+        FROM pg_catalog.pg_proc p
+            LEFT JOIN pg_catalog.pg_namespace n ON n.oid = p.pronamespace
+        WHERE n.nspname = 'cdb_crankshaft'
+            AND p.proname = 'cdb_pyagg'
+            AND p.proisagg)
+    THEN
+        CREATE AGGREGATE CDB_PyAgg(NUMERIC[]) (
+            SFUNC = CDB_PyAggS,
+            STYPE = Numeric[],
+            INITCOND = "{}"
+        );
+    END IF;
+END
+$$ LANGUAGE plpgsql;
+
+CREATE OR REPLACE FUNCTION
+  CDB_CreateAndPredictSegment(
+    target NUMERIC[],
+    features NUMERIC[],
+    target_features NUMERIC[],
+    target_ids NUMERIC[],
+    n_estimators INTEGER DEFAULT 1200,
+    max_depth INTEGER DEFAULT 3,
+    subsample DOUBLE PRECISION DEFAULT 0.5,
+    learning_rate DOUBLE PRECISION DEFAULT 0.01,
+    min_samples_leaf INTEGER DEFAULT 1)
+RETURNS TABLE(cartodb_id NUMERIC, prediction NUMERIC, accuracy NUMERIC)
+AS $$
+    import numpy as np
+    import plpy
+
+    from crankshaft.segmentation import create_and_predict_segment_agg
+    model_params = {'n_estimators': n_estimators,
+                    'max_depth': max_depth,
+                    'subsample': subsample,
+                    'learning_rate': learning_rate,
+                    'min_samples_leaf': min_samples_leaf}
+
+    def unpack2D(data):
+        dimension = data.pop(0)
+        a = np.array(data, dtype=float)
+        return a.reshape(len(a)/dimension, dimension)
+
+    return create_and_predict_segment_agg(np.array(target, dtype=float),
+            unpack2D(features),
+            unpack2D(target_features),
+            target_ids,
+            model_params)
+
+$$ LANGUAGE plpythonu;
+
+CREATE OR REPLACE FUNCTION
+  CDB_CreateAndPredictSegment (
+      query TEXT,
+      variable_name TEXT,
+      target_table TEXT,
+      n_estimators INTEGER DEFAULT 1200,
+      max_depth INTEGER DEFAULT 3,
+      subsample DOUBLE PRECISION DEFAULT 0.5,
+      learning_rate DOUBLE PRECISION DEFAULT 0.01,
+      min_samples_leaf INTEGER DEFAULT 1)
+RETURNS TABLE (cartodb_id TEXT, prediction NUMERIC, accuracy NUMERIC)
+AS $$
+  from crankshaft.segmentation import create_and_predict_segment
+  model_params = {'n_estimators': n_estimators, 'max_depth':max_depth, 'subsample' : subsample, 'learning_rate': learning_rate, 'min_samples_leaf' : min_samples_leaf}
+  return create_and_predict_segment(query,variable_name,target_table, model_params)
+$$ LANGUAGE plpythonu;
+CREATE OR REPLACE FUNCTION CDB_Gravity(
+    IN target_query text,
+    IN weight_column text,
+    IN source_query text,
+    IN pop_column text,
+    IN target bigint,
+    IN radius integer,
+    IN minval numeric DEFAULT -10e307
+    )
+RETURNS TABLE(
+    the_geom geometry,
+    source_id bigint,
+    target_id bigint,
+    dist numeric,
+    h numeric,
+    hpop numeric)  AS $$
+DECLARE
+    t_id bigint[];
+    t_geom geometry[];
+    t_weight numeric[];
+    s_id bigint[];
+    s_geom geometry[];
+    s_pop numeric[];
+BEGIN
+    EXECUTE 'WITH foo as('+target_query+') SELECT array_agg(cartodb_id), array_agg(the_geom), array_agg(' || weight_column || ') FROM foo' INTO t_id, t_geom, t_weight;
+    EXECUTE 'WITH foo as('+source_query+') SELECT array_agg(cartodb_id), array_agg(the_geom), array_agg(' || pop_column || ') FROM foo' INTO s_id, s_geom, s_pop;
+    RETURN QUERY
+    SELECT g.* FROM t, s, CDB_Gravity(t_id, t_geom, t_weight, s_id, s_geom, s_pop, target, radius, minval) g;
+END;
+$$ language plpgsql;
+
+CREATE OR REPLACE FUNCTION CDB_Gravity(
+    IN t_id bigint[],
+    IN t_geom geometry[],
+    IN t_weight numeric[],
+    IN s_id bigint[],
+    IN s_geom geometry[],
+    IN s_pop numeric[],
+    IN target bigint,
+    IN radius integer,
+    IN minval numeric DEFAULT -10e307
+    )
+RETURNS TABLE(
+    the_geom geometry,
+    source_id bigint,
+    target_id bigint,
+    dist numeric,
+    h numeric,
+    hpop numeric)  AS $$
+DECLARE
+    t_type text;
+    s_type text;
+    t_center geometry[];
+    s_center geometry[];
+BEGIN
+    t_type := GeometryType(t_geom[1]);
+    s_type := GeometryType(s_geom[1]);
+    IF t_type = 'POINT' THEN
+        t_center := t_geom;
+    ELSE
+        WITH tmp as (SELECT unnest(t_geom) as g) SELECT array_agg(ST_Centroid(g)) INTO t_center FROM tmp;
+    END IF;
+    IF s_type = 'POINT' THEN
+        s_center := s_geom;
+    ELSE
+        WITH tmp as (SELECT unnest(s_geom) as g) SELECT array_agg(ST_Centroid(g)) INTO s_center FROM tmp;
+    END IF;
+    RETURN QUERY
+        with target0 as(
+            SELECT unnest(t_center) as tc, unnest(t_weight) as tw, unnest(t_id) as td
+        ),
+        source0 as(
+            SELECT unnest(s_center) as sc, unnest(s_id) as sd, unnest (s_geom) as sg, unnest(s_pop) as sp
+        ),
+        prev0 as(
+            SELECT
+                source0.sg,
+                source0.sd as sourc_id,
+                coalesce(source0.sp,0) as sp,
+                target.td as targ_id,
+                coalesce(target.tw,0) as tw,
+                GREATEST(1.0,ST_Distance(geography(target.tc), geography(source0.sc)))::numeric as distance
+            FROM source0
+            CROSS JOIN LATERAL
+                (
+                SELECT
+                    *
+                FROM target0
+                    WHERE tw > minval
+                    AND ST_DWithin(geography(source0.sc), geography(tc), radius)
+                ) AS target
+        ),
+        deno as(
+            SELECT
+                sourc_id,
+                sum(tw/distance) as h_deno
+            FROM
+                prev0
+            GROUP BY sourc_id
+        )
+        SELECT
+            p.sg as the_geom,
+            p.sourc_id as source_id,
+            p.targ_id as target_id,
+            case when p.distance > 1 then p.distance else 0.0 end as dist,
+            100*(p.tw/p.distance)/d.h_deno as h,
+            p.sp*(p.tw/p.distance)/d.h_deno as hpop
+        FROM
+            prev0 p,
+            deno d
+        WHERE
+            p.targ_id = target AND
+            p.sourc_id = d.sourc_id;
+END;
+$$ language plpgsql;
+-- 0: nearest neighbor
+-- 1: barymetric
+-- 2: IDW
+
+CREATE OR REPLACE FUNCTION CDB_SpatialInterpolation(
+    IN query text,
+    IN point geometry,
+    IN method integer DEFAULT 1,
+    IN p1 numeric DEFAULT 0,
+    IN p2 numeric DEFAULT 0
+    )
+RETURNS numeric AS
+$$
+DECLARE
+    gs geometry[];
+    vs numeric[];
+    output numeric;
+BEGIN
+    EXECUTE 'WITH a AS('||query||') SELECT array_agg(the_geom), array_agg(attrib) FROM a' INTO gs, vs;
+    SELECT CDB_SpatialInterpolation(gs, vs, point, method, p1,p2) INTO output FROM a;
+
+    RETURN output;
+END;
+$$
+language plpgsql IMMUTABLE;
+
+CREATE OR REPLACE FUNCTION CDB_SpatialInterpolation(
+    IN geomin geometry[],
+    IN colin numeric[],
+    IN point geometry,
+    IN method integer DEFAULT 1,
+    IN p1 numeric DEFAULT 0,
+    IN p2 numeric DEFAULT 0
+    )
+RETURNS numeric AS
+$$
+DECLARE
+    gs geometry[];
+    vs numeric[];
+    gs2 geometry[];
+    vs2 numeric[];
+    g geometry;
+    vertex geometry[];
+    sg numeric;
+    sa numeric;
+    sb numeric;
+    sc numeric;
+    va numeric;
+    vb numeric;
+    vc numeric;
+    output numeric;
+BEGIN
+    output :=  -999.999;
+    -- nearest
+    IF method = 0 THEN
+
+        WITH    a as (SELECT unnest(geomin) as g, unnest(colin) as v)
+        SELECT a.v INTO output FROM a ORDER BY point<->a.g LIMIT 1;
+        RETURN output;
+
+    -- barymetric
+    ELSIF method = 1 THEN
+        WITH    a as (SELECT unnest(geomin) AS e),
+                b as (SELECT ST_DelaunayTriangles(ST_Collect(a.e),0.001, 0) AS t FROM a),
+                c as (SELECT (ST_Dump(t)).geom as v FROM b),
+                d as (SELECT v FROM c WHERE ST_Within(point, v))
+            SELECT v INTO g FROM d;
+        IF g is null THEN
+            -- out of the realm of the input data
+            RETURN -888.888;
+        END IF;
+        -- vertex of the selected cell
+        WITH a AS (SELECT (ST_DumpPoints(g)).geom AS v)
+                SELECT array_agg(v) INTO vertex FROM a;
+
+            -- retrieve the value of each vertex
+        WITH a AS(SELECT unnest(vertex) as geo, unnest(colin) as c)
+            SELECT c INTO va FROM a WHERE ST_Equals(geo, vertex[1]);
+        WITH a AS(SELECT unnest(vertex) as geo, unnest(colin) as c)
+            SELECT c INTO vb FROM a WHERE ST_Equals(geo, vertex[2]);
+        WITH a AS(SELECT unnest(vertex) as geo, unnest(colin) as c)
+                SELECT c INTO vc FROM a WHERE ST_Equals(geo, vertex[3]);
+
+        SELECT ST_area(g), ST_area(ST_MakePolygon(ST_MakeLine(ARRAY[point, vertex[2], vertex[3], point]))), ST_area(ST_MakePolygon(ST_MakeLine(ARRAY[point, vertex[1], vertex[3], point]))), ST_area(ST_MakePolygon(ST_MakeLine(ARRAY[point,vertex[1],vertex[2], point]))) INTO sg, sa, sb, sc;
+
+        output := (coalesce(sa,0) * coalesce(va,0) + coalesce(sb,0) * coalesce(vb,0) + coalesce(sc,0) * coalesce(vc,0)) / coalesce(sg);
+        RETURN output;
+
+    -- IDW
+    -- p1: limit the number of neighbors, 0->no limit
+    -- p2: order of distance decay, 0-> order 1
+    ELSIF method = 2 THEN
+
+        IF p2 = 0 THEN
+            p2 := 1;
+        END IF;
+
+        WITH    a as (SELECT unnest(geomin) as g, unnest(colin) as v),
+                b as (SELECT a.g, a.v FROM a ORDER BY point<->a.g)
+        SELECT array_agg(b.g), array_agg(b.v) INTO gs, vs FROM b;
+        IF p1::integer>0 THEN
+            gs2:=gs;
+            vs2:=vs;
+            FOR i IN 1..p1
+            LOOP
+                gs2 := gs2 || gs[i];
+                vs2 := vs2 || vs[i];
+            END LOOP;
+        ELSE
+            gs2:=gs;
+            vs2:=vs;
+        END IF;
+
+        WITH    a as (SELECT unnest(gs2) as g, unnest(vs2) as v),
+                b as (
+                    SELECT
+                    (1/ST_distance(point, a.g)^p2::integer) as k,
+                    (a.v/ST_distance(point, a.g)^p2::integer) as f
+                    FROM a
+                )
+        SELECT sum(b.f)/sum(b.k) INTO output FROM b;
+        RETURN output;
+
+    END IF;
+
+    RETURN -777.777;
+
+END;
+$$
+language plpgsql IMMUTABLE;
+-- Moran's I Global Measure (public-facing)
+CREATE OR REPLACE FUNCTION
+  CDB_AreasOfInterestGlobal(
+      subquery TEXT,
+      column_name TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS TABLE (moran NUMERIC, significance NUMERIC)
+AS $$
+  from crankshaft.clustering import moran_local
+  # TODO: use named parameters or a dictionary
+  return moran(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+-- Moran's I Local (internal function)
+CREATE OR REPLACE FUNCTION
+  _CDB_AreasOfInterestLocal(
+      subquery TEXT,
+      column_name TEXT,
+      w_type TEXT,
+      num_ngbrs INT,
+      permutations INT,
+      geom_col TEXT,
+      id_col TEXT)
+RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+  from crankshaft.clustering import moran_local
+  # TODO: use named parameters or a dictionary
+  return moran_local(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+-- Moran's I Local (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_AreasOfInterestLocal(
+    subquery TEXT,
+    column_name TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col);
+
+$$ LANGUAGE SQL;
+
+-- Moran's I only for HH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialHotspots(
+    subquery TEXT,
+    column_name TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HH', 'HL');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I only for LL and LH (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialColdspots(
+    subquery TEXT,
+    attr TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, attr, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('LL', 'LH');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I only for LH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialOutliers(
+    subquery TEXT,
+    attr TEXT,
+    w_type TEXT DEFAULT 'knn',
+    num_ngbrs INT DEFAULT 5,
+    permutations INT DEFAULT 99,
+    geom_col TEXT DEFAULT 'the_geom',
+    id_col TEXT DEFAULT 'cartodb_id')
+    RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocal(subquery, attr, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HL', 'LH');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Global Rate (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_AreasOfInterestGlobalRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS TABLE (moran FLOAT, significance FLOAT)
+AS $$
+  from crankshaft.clustering import moran_local
+  # TODO: use named parameters or a dictionary
+  return moran_rate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+
+-- Moran's I Local Rate (internal function)
+CREATE OR REPLACE FUNCTION
+  _CDB_AreasOfInterestLocalRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT,
+      num_ngbrs INT,
+      permutations INT,
+      geom_col TEXT,
+      id_col TEXT)
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+  from crankshaft.clustering import moran_local_rate
+  # TODO: use named parameters or a dictionary
+  return moran_local_rate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+-- Moran's I Local Rate (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_AreasOfInterestLocalRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col);
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Local Rate only for HH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialHotspotsRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HH', 'HL');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Local Rate only for LL and LH (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialColdspotsRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('LL', 'LH');
+
+$$ LANGUAGE SQL;
+
+-- Moran's I Local Rate only for LH and HL (public-facing function)
+CREATE OR REPLACE FUNCTION
+  CDB_GetSpatialOutliersRate(
+      subquery TEXT,
+      numerator TEXT,
+      denominator TEXT,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+      permutations INT DEFAULT 99,
+      geom_col TEXT DEFAULT 'the_geom',
+      id_col TEXT DEFAULT 'cartodb_id')
+RETURNS
+TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
+AS $$
+
+  SELECT moran, quads, significance, rowid, vals
+  FROM cdb_crankshaft._CDB_AreasOfInterestLocalRate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+  WHERE quads IN ('HL', 'LH');
+
+$$ LANGUAGE SQL;
+CREATE OR REPLACE FUNCTION  CDB_KMeans(query text, no_clusters integer,no_init integer default 20)
+RETURNS table (cartodb_id integer, cluster_no integer) as $$
+    
+    from crankshaft.clustering import kmeans
+    return kmeans(query,no_clusters,no_init)
+
+$$ language plpythonu;
+
+
+CREATE OR REPLACE FUNCTION CDB_WeightedMeanS(state Numeric[],the_geom GEOMETRY(Point, 4326), weight NUMERIC)
+RETURNS Numeric[] AS 
+$$
+DECLARE 
+    newX NUMERIC;
+    newY NUMERIC;
+    newW NUMERIC;
+BEGIN
+    IF weight IS NULL OR the_geom IS NULL THEN 
+        newX = state[1];
+        newY = state[2];
+        newW = state[3];
+    ELSE
+        newX = state[1] + ST_X(the_geom)*weight;
+        newY = state[2] + ST_Y(the_geom)*weight;
+        newW = state[3] + weight;
+    END IF;
+    RETURN Array[newX,newY,newW];
+
+END
+$$ LANGUAGE plpgsql;
+
+CREATE OR REPLACE FUNCTION CDB_WeightedMeanF(state Numeric[])
+RETURNS GEOMETRY AS 
+$$
+BEGIN
+    IF state[3] = 0 THEN 
+        RETURN ST_SetSRID(ST_MakePoint(state[1],state[2]), 4326);
+    ELSE 
+        RETURN ST_SETSRID(ST_MakePoint(state[1]/state[3], state[2]/state[3]),4326);
+    END IF;
+END
+$$ LANGUAGE plpgsql;
+
+-- Create aggregate if it did not exist
+DO $$
+BEGIN
+    IF NOT EXISTS (
+        SELECT *
+        FROM pg_catalog.pg_proc p
+            LEFT JOIN pg_catalog.pg_namespace n ON n.oid = p.pronamespace
+        WHERE n.nspname = 'cdb_crankshaft'
+            AND p.proname = 'cdb_weightedmean'
+            AND p.proisagg)
+    THEN
+        CREATE AGGREGATE CDB_WeightedMean(geometry(Point, 4326), NUMERIC) (
+            SFUNC = CDB_WeightedMeanS,
+            FINALFUNC = CDB_WeightedMeanF,
+            STYPE = Numeric[],
+            INITCOND = "{0.0,0.0,0.0}" 
+        );
+    END IF;
+END
+$$ LANGUAGE plpgsql;
+-- Spatial Markov
+
+-- input table format:
+-- id | geom | date_1 | date_2 | date_3
+--  1 | Pt1  | 12.3   | 13.1   | 14.2
+--  2 | Pt2  | 11.0   | 13.2   | 12.5
+--  ...
+-- Sample Function call:
+-- SELECT CDB_SpatialMarkov('SELECT * FROM real_estate',
+--                          Array['date_1', 'date_2', 'date_3'])
+
+CREATE OR REPLACE FUNCTION
+  CDB_SpatialMarkovTrend (
+      subquery TEXT,
+      time_cols TEXT[],
+      num_classes INT DEFAULT 7,
+      w_type TEXT DEFAULT 'knn',
+      num_ngbrs INT DEFAULT 5,
+  	  permutations INT DEFAULT 99,
+  	  geom_col TEXT DEFAULT 'the_geom',
+  	  id_col TEXT DEFAULT 'cartodb_id')
+RETURNS TABLE (trend NUMERIC, trend_up NUMERIC, trend_down NUMERIC, volatility NUMERIC, rowid INT)
+AS $$
+
+  from crankshaft.space_time_dynamics import spatial_markov_trend
+
+  ## TODO: use named parameters or a dictionary
+  return spatial_markov_trend(subquery, time_cols, num_classes, w_type, num_ngbrs, permutations, geom_col, id_col)
+$$ LANGUAGE plpythonu;
+
+-- input table format: identical to above but in a predictable format
+-- Sample function call:
+-- SELECT cdb_spatial_markov('SELECT * FROM real_estate',
+--                           'date_1')
+
+
+-- CREATE OR REPLACE FUNCTION
+--   cdb_spatial_markov (
+--       subquery TEXT,
+--       time_col_min text,
+--       time_col_max text,
+--       date_format text, -- '_YYYY_MM_DD'
+--       num_time_per_bin INT DEFAULT 1,
+--   	  permutations INT DEFAULT 99,
+--   	  geom_column TEXT DEFAULT 'the_geom',
+--   	  id_col TEXT DEFAULT 'cartodb_id',
+--       w_type TEXT DEFAULT 'knn',
+--       num_ngbrs int DEFAULT 5)
+-- RETURNS TABLE (moran FLOAT, quads TEXT, significance FLOAT, ids INT)
+-- AS $$
+--   plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
+--   from crankshaft.clustering import moran_local
+--   # TODO: use named parameters or a dictionary
+--   return spatial_markov(subquery, time_cols, permutations, geom_column, id_col, w_type, num_ngbrs)
+-- $$ LANGUAGE plpythonu;
+--
+-- -- input table format:
+-- -- id | geom | date  | measurement
+-- --  1 | Pt1  | 12/3  | 13.2
+-- --  2 | Pt2  | 11/5  | 11.3
+-- --  3 | Pt1  | 11/13 | 12.9
+-- --  4 | Pt3  | 12/19 | 10.1
+-- -- ...
+--
+-- CREATE OR REPLACE FUNCTION
+--   cdb_spatial_markov (
+--       subquery TEXT,
+--       time_col text,
+--       num_time_per_bin INT DEFAULT 1,
+--   	  permutations INT DEFAULT 99,
+--   	  geom_column TEXT DEFAULT 'the_geom',
+--   	  id_col TEXT DEFAULT 'cartodb_id',
+--       w_type TEXT DEFAULT 'knn',
+--       num_ngbrs int DEFAULT 5)
+-- RETURNS TABLE (moran FLOAT, quads TEXT, significance FLOAT, ids INT)
+-- AS $$
+--   plpy.execute('SELECT cdb_crankshaft._cdb_crankshaft_activate_py()')
+--   from crankshaft.clustering import moran_local
+--   # TODO: use named parameters or a dictionary
+--   return spatial_markov(subquery, time_cols, permutations, geom_column, id_col, w_type, num_ngbrs)
+-- $$ LANGUAGE plpythonu;
+-- Function by Stuart Lynn for a simple interpolation of a value
+-- from a polygon table over an arbitrary polygon
+-- (weighted by the area proportion overlapped)
+-- Aereal weighting is a very simple form of aereal interpolation.
+--
+-- Parameters:
+--   * geom a Polygon geometry which defines the area where a value will be
+--     estimated as the area-weighted sum of a given table/column
+--   * target_table_name table name of the table that provides the values
+--   * target_column column name of the column that provides the values
+--   * schema_name optional parameter to defina the schema the target table
+--     belongs to, which is necessary if its not in the search_path.
+--     Note that target_table_name should never include the schema in it.
+-- Return value:
+--   Aereal-weighted interpolation of the column values over the geometry
+CREATE OR REPLACE
+FUNCTION cdb_overlap_sum(geom geometry, target_table_name text, target_column text, schema_name text DEFAULT NULL)
+  RETURNS numeric AS
+$$
+DECLARE
+	result numeric;
+  qualified_name text;
+BEGIN
+  IF schema_name IS NULL THEN
+    qualified_name := Format('%I', target_table_name);
+  ELSE
+    qualified_name := Format('%I.%s', schema_name, target_table_name);
+  END IF;
+  EXECUTE Format('
+    SELECT sum(%I*ST_Area(St_Intersection($1, a.the_geom))/ST_Area(a.the_geom))
+    FROM %s AS a
+    WHERE $1 && a.the_geom
+  ', target_column, qualified_name)
+  USING geom
+  INTO result;
+  RETURN result;
+END;
+$$ LANGUAGE plpgsql;
+--
+-- Creates N points randomly distributed arround the polygon
+--
+-- @param g - the geometry to be turned in to points
+--
+-- @param no_points - the number of points to generate
+--
+-- @params max_iter_per_point - the function generates points in the polygon's bounding box
+-- and discards points which don't lie in the polygon. max_iter_per_point specifies how many
+-- misses per point the funciton accepts before giving up.
+--
+-- Returns: Multipoint with the requested points
+CREATE OR REPLACE FUNCTION cdb_dot_density(geom geometry , no_points Integer, max_iter_per_point Integer DEFAULT 1000)
+RETURNS GEOMETRY AS $$
+DECLARE
+  extent GEOMETRY;
+  test_point Geometry;
+  width                NUMERIC;
+  height               NUMERIC;
+  x0                   NUMERIC;
+  y0                   NUMERIC;
+  xp                   NUMERIC;
+  yp                   NUMERIC;
+  no_left              INTEGER;
+  remaining_iterations INTEGER;
+  points               GEOMETRY[];
+  bbox_line            GEOMETRY;
+  intersection_line    GEOMETRY;
+BEGIN
+  extent  := ST_Envelope(geom);
+  width   := ST_XMax(extent) - ST_XMIN(extent);
+  height  := ST_YMax(extent) - ST_YMIN(extent);
+  x0 	  := ST_XMin(extent);
+  y0 	  := ST_YMin(extent);
+  no_left := no_points;
+
+  LOOP
+    if(no_left=0) THEN
+      EXIT;
+    END IF;
+    yp = y0 + height*random();
+    bbox_line  = ST_MakeLine(
+      ST_SetSRID(ST_MakePoint(yp, x0),4326),
+      ST_SetSRID(ST_MakePoint(yp, x0+width),4326)
+    );
+    intersection_line = ST_Intersection(bbox_line,geom);
+  	test_point = ST_LineInterpolatePoint(st_makeline(st_linemerge(intersection_line)),random());
+	  points := points || test_point;
+	  no_left = no_left - 1 ;
+  END LOOP;
+  RETURN ST_Collect(points);
+END;
+$$
+LANGUAGE plpgsql VOLATILE;
+-- Make sure by default there are no permissions for publicuser
+-- NOTE: this happens at extension creation time, as part of an implicit transaction.
+-- REVOKE ALL PRIVILEGES ON SCHEMA cdb_crankshaft FROM PUBLIC, publicuser CASCADE;
+
+-- Grant permissions on the schema to publicuser (but just the schema)
+GRANT USAGE ON SCHEMA cdb_crankshaft TO publicuser;
+
+-- Revoke execute permissions on all functions in the schema by default
+-- REVOKE EXECUTE ON ALL FUNCTIONS IN SCHEMA cdb_crankshaft FROM PUBLIC, publicuser;

release/crankshaft.control

@@ -1,5 +1,5 @@
 comment = 'CartoDB Spatial Analysis extension'
-default_version = '0.0.1'
-requires = 'plpythonu, postgis, cartodb'
+default_version = '0.9.0'
+requires = 'plpython3u, postgis'
 superuser = true
 schema = cdb_crankshaft