move to class-based module

src/pg/sql/10_moran.sql

@@ -10,9 +10,11 @@ CREATE OR REPLACE FUNCTION
       id_col TEXT DEFAULT 'cartodb_id')
 RETURNS TABLE (moran NUMERIC, significance NUMERIC)
 AS $$
-  from crankshaft.clustering import moran
+  from crankshaft.clustering import Moran
   # TODO: use named parameters or a dictionary
-  return moran(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col)
+  moran = Moran()
+  return moran.global_stat(subquery, column_name, w_type,
+                           num_ngbrs, permutations, geom_col, id_col)
 $$ LANGUAGE plpythonu;
 
 -- Moran's I Local (internal function)
@@ -27,9 +29,11 @@ CREATE OR REPLACE FUNCTION
       id_col TEXT)
 RETURNS TABLE (moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
 AS $$
-  from crankshaft.clustering import moran_local
+  from crankshaft.clustering import Moran
+  moran = Moran()
   # TODO: use named parameters or a dictionary
-  return moran_local(subquery, column_name, w_type, num_ngbrs, permutations, geom_col, id_col)
+  return moran.local_stat(subquery, column_name, w_type,
+                          num_ngbrs, permutations, geom_col, id_col)
 $$ LANGUAGE plpythonu;
 
 -- Moran's I Local (public-facing function)
@@ -120,9 +124,11 @@ CREATE OR REPLACE FUNCTION
       id_col TEXT DEFAULT 'cartodb_id')
 RETURNS TABLE (moran FLOAT, significance FLOAT)
 AS $$
-  from crankshaft.clustering import moran_local
+  from crankshaft.clustering import Moran
+  moran = Moran()
   # TODO: use named parameters or a dictionary
-  return moran_rate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+  return moran.global_rate_stat(subquery, numerator, denominator, w_type,
+                                num_ngbrs, permutations, geom_col, id_col)
 $$ LANGUAGE plpythonu;
 
 
@@ -140,9 +146,10 @@ CREATE OR REPLACE FUNCTION
 RETURNS
 TABLE(moran NUMERIC, quads TEXT, significance NUMERIC, rowid INT, vals NUMERIC)
 AS $$
-  from crankshaft.clustering import moran_local_rate
+  from crankshaft.clustering import Moran
+  moran = Moran()
   # TODO: use named parameters or a dictionary
-  return moran_local_rate(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
+  return moran.local_rate_stat(subquery, numerator, denominator, w_type, num_ngbrs, permutations, geom_col, id_col)
 $$ LANGUAGE plpythonu;
 
 -- Moran's I Local Rate (public-facing function)

src/py/crankshaft/crankshaft/clustering/moran.py

@@ -15,7 +15,23 @@ import crankshaft.pysal_utils as pu
 # High level interface ---------------------------------------
 
 
-def moran(subquery, attr_name,
+class QueryRunner:
+    def get_result(self, query):
+        try:
+            data = plpy.execute(query)
+        except plpy.SPIError, err:
+            plpy.error("k-means (spatial) cluster analysis failed: %s" % err)
+        return data
+
+
+class Moran:
+    def __init__(self, query_runner=None):
+        if query_runner is None:
+            self.query_runner = QueryRunner()
+        else:
+            self.query_runner = query_runner
+
+    def global_stat(self, subquery, attr_name,
                     w_type, num_ngbrs, permutations, geom_col, id_col):
         """
         Moran's I (global)
@@ -31,14 +47,7 @@ def moran(subquery, attr_name,
 
         query = pu.construct_neighbor_query(w_type, qvals)
 
-    try:
+        result = self.query_runner.get_result(query)
-        result = plpy.execute(query)
-        # if there are no neighbors, exit
-        if len(result) == 0:
-            return pu.empty_zipped_array(2)
-    except plpy.SPIError, e:
-        plpy.error('Analysis failed: %s' % e)
-        return pu.empty_zipped_array(2)
 
         # collect attributes
         attr_vals = pu.get_attributes(result)
@@ -52,8 +61,7 @@ def moran(subquery, attr_name,
 
         return zip([moran_global.I], [moran_global.EI])
 
-
+    def local_stat(self, subquery, attr,
-def moran_local(subquery, attr,
                    w_type, num_ngbrs, permutations, geom_col, id_col):
         """
         Moran's I implementation for PL/Python
@@ -71,14 +79,7 @@ def moran_local(subquery, attr,
 
         query = pu.construct_neighbor_query(w_type, qvals)
 
-    try:
+        result = self.query_runner.get_result(query)
-        result = plpy.execute(query)
-        # if there are no neighbors, exit
-        if len(result) == 0:
-            return pu.empty_zipped_array(5)
-    except plpy.SPIError, e:
-        plpy.error('Analysis failed: %s' % e)
-        return pu.empty_zipped_array(5)
 
         attr_vals = pu.get_attributes(result)
         weight = pu.get_weight(result, w_type, num_ngbrs)
@@ -92,8 +93,7 @@ def moran_local(subquery, attr,
 
         return zip(lisa.Is, quads, lisa.p_sim, weight.id_order, lisa.y)
 
-
+    def global_rate_stat(self, subquery, numerator, denominator,
-def moran_rate(subquery, numerator, denominator,
                          w_type, num_ngbrs, permutations, geom_col, id_col):
         """
         Moran's I Rate (global)
@@ -108,14 +108,7 @@ def moran_rate(subquery, numerator, denominator,
 
         query = pu.construct_neighbor_query(w_type, qvals)
 
-    try:
+        result = self.query_runner.get_result(query)
-        result = plpy.execute(query)
-        # if there are no neighbors, exit
-        if len(result) == 0:
-            return pu.empty_zipped_array(2)
-    except plpy.SPIError, e:
-        plpy.error('Analysis failed: %s' % e)
-        return pu.empty_zipped_array(2)
 
         # collect attributes
         numer = pu.get_attributes(result, 1)
@@ -129,8 +122,7 @@ def moran_rate(subquery, numerator, denominator,
 
         return zip([lisa_rate.I], [lisa_rate.EI])
 
-
+    def local_rate_stat(self, subquery, numerator, denominator,
-def moran_local_rate(subquery, numerator, denominator,
                         w_type, num_ngbrs, permutations, geom_col, id_col):
         """
             Moran's I Local Rate
@@ -148,14 +140,7 @@ def moran_local_rate(subquery, numerator, denominator,
 
         query = pu.construct_neighbor_query(w_type, qvals)
 
-    try:
+        result = self.query_runner.get_result(query)
-        result = plpy.execute(query)
-        # if there are no neighbors, exit
-        if len(result) == 0:
-            return pu.empty_zipped_array(5)
-    except plpy.SPIError, e:
-        plpy.error('Analysis failed: %s' % e)
-        return pu.empty_zipped_array(5)
 
         # collect attributes
         numer = pu.get_attributes(result, 1)
@@ -172,9 +157,9 @@ def moran_local_rate(subquery, numerator, denominator,
 
         return zip(lisa.Is, quads, lisa.p_sim, weight.id_order, lisa.y)
 
-
+    def local_bivariate_stat(self, subquery, attr1, attr2,
-def moran_local_bv(subquery, attr1, attr2,
+                             permutations, geom_col, id_col,
-                   permutations, geom_col, id_col, w_type, num_ngbrs):
+                             w_type, num_ngbrs):
         """
             Moran's I (local) Bivariate (untested)
         """
@@ -188,15 +173,7 @@ def moran_local_bv(subquery, attr1, attr2,
 
         query = pu.construct_neighbor_query(w_type, qvals)
 
-    try:
+        result = self.query_runner.get_result(query)
-        result = plpy.execute(query)
-        # if there are no neighbors, exit
-        if len(result) == 0:
-            return pu.empty_zipped_array(4)
-    except plpy.SPIError:
-        plpy.error("Error: areas of interest query failed, "
-                   "check input parameters")
-        return pu.empty_zipped_array(4)
 
         # collect attributes
         attr1_vals = pu.get_attributes(result, 1)