cartodb4/crankshaft
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

move query generation to inside analysis data provider class

Browse Source
This commit is contained in:
Andy Eschbacher 2016-11-22 15:20:14 +00:00
parent 6fe4fc9668
commit db501a2f02
5 changed files with 47 additions and 55 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/py/crankshaft/crankshaft/analysis_data_provider.py
View File

@ -1,10 +1,12 @@
"""class for fetching data"""
import plpy
import pysal_utils as pu
class AnalysisDataProvider:
def get_markov(self, query):
def get_markov(self, w_type, params):
try:
query = pu.construct_neighbor_query(w_type, params)
data = plpy.execute(query)
if len(data) == 0:
@ -14,10 +16,12 @@ class AnalysisDataProvider:
except plpy.SPIError, err:
plpy.error('Analysis failed: %s' % err)
def get_moran(self, query):
def get_moran(self, w_type, params):
"""fetch data for moran's i analyses"""
try:
query = pu.construct_neighbor_query(w_type, params)
data = plpy.execute(query)
# if there are no neighbors, exit
if len(data) == 0:
return pu.empty_zipped_array(2)

76
src/py/crankshaft/crankshaft/clustering/moran.py
View File

@ -31,15 +31,13 @@ class Moran:
core clusters with PySAL.
Andy Eschbacher
"""
qvals = OrderedDict([("id_col", id_col),
("attr1", attr_name),
("geom_col", geom_col),
("subquery", subquery),
("num_ngbrs", num_ngbrs)])
params = OrderedDict([("id_col", id_col),
("attr1", attr_name),
("geom_col", geom_col),
("subquery", subquery),
("num_ngbrs", num_ngbrs)])
query = pu.construct_neighbor_query(w_type, qvals)
result = self.data_provider.get_moran(query)
result = self.data_provider.get_moran(w_type, params)
# collect attributes
attr_vals = pu.get_attributes(result)
@ -63,15 +61,13 @@ class Moran:
# geometries with attributes that are null are ignored
# resulting in a collection of not as near neighbors
qvals = OrderedDict([("id_col", id_col),
("attr1", attr),
("geom_col", geom_col),
("subquery", subquery),
("num_ngbrs", num_ngbrs)])
params = OrderedDict([("id_col", id_col),
("attr1", attr),
("geom_col", geom_col),
("subquery", subquery),
("num_ngbrs", num_ngbrs)])
query = pu.construct_neighbor_query(w_type, qvals)
result = self.data_provider.get_moran(query)
result = self.data_provider.get_moran(w_type, params)
attr_vals = pu.get_attributes(result)
weight = pu.get_weight(result, w_type, num_ngbrs)
@ -91,16 +87,14 @@ class Moran:
Moran's I Rate (global)
Andy Eschbacher
"""
qvals = OrderedDict([("id_col", id_col),
("attr1", numerator),
("attr2", denominator)
("geom_col", geom_col),
("subquery", subquery),
("num_ngbrs", num_ngbrs)])
params = OrderedDict([("id_col", id_col),
("attr1", numerator),
("attr2", denominator)
("geom_col", geom_col),
("subquery", subquery),
("num_ngbrs", num_ngbrs)])
query = pu.construct_neighbor_query(w_type, qvals)
result = self.data_provider.get_moran(query)
result = self.data_provider.get_moran(w_type, params)
# collect attributes
numer = pu.get_attributes(result, 1)
@ -123,16 +117,14 @@ class Moran:
# geometries with values that are null are ignored
# resulting in a collection of not as near neighbors
qvals = OrderedDict([("id_col", id_col),
("numerator", numerator),
("denominator", denominator),
("geom_col", geom_col),
("subquery", subquery),
("num_ngbrs", num_ngbrs)])
params = OrderedDict([("id_col", id_col),
("numerator", numerator),
("denominator", denominator),
("geom_col", geom_col),
("subquery", subquery),
("num_ngbrs", num_ngbrs)])
query = pu.construct_neighbor_query(w_type, qvals)
result = self.data_provider.get_moran(query)
result = self.data_provider.get_moran(w_type, params)
# collect attributes
numer = pu.get_attributes(result, 1)
@ -156,16 +148,14 @@ class Moran:
Moran's I (local) Bivariate (untested)
"""
qvals = OrderedDict([("id_col", id_col),
("attr1", attr1),
("attr2", attr2),
("geom_col", geom_col),
("subquery", subquery),
("num_ngbrs", num_ngbrs)])
params = OrderedDict([("id_col", id_col),
("attr1", attr1),
("attr2", attr2),
("geom_col", geom_col),
("subquery", subquery),
("num_ngbrs", num_ngbrs)])
query = pu.construct_neighbor_query(w_type, qvals)
result = self.data_provider.get_moran(query)
result = self.data_provider.get_moran(w_type, params)
# collect attributes
attr1_vals = pu.get_attributes(result, 1)

14
src/py/crankshaft/crankshaft/space_time_dynamics/markov.py
View File

@ -54,15 +54,13 @@ class Markov:
if len(time_cols) < 2:
plpy.error('More than one time column needs to be passed')
qvals = {"id_col": id_col,
"time_cols": time_cols,
"geom_col": geom_col,
"subquery": subquery,
"num_ngbrs": num_ngbrs}
params = {"id_col": id_col,
"time_cols": time_cols,
"geom_col": geom_col,
"subquery": subquery,
"num_ngbrs": num_ngbrs}
query = pu.construct_neighbor_query(w_type, qvals)
query_result = self.data_provider.get_markov(query)
query_result = self.data_provider.get_markov(w_type, params)
# build weight
weights = pu.get_weight(query_result, w_type)

2
src/py/crankshaft/test/test_clustering_kmeans.py
View File

@ -21,7 +21,7 @@ class FakeDataProvider(AnalysisDataProvider):
def __init__(self, mocked_result):
self.mocked_result = mocked_result
def get_spatial_kmeans(self, w_type, params):
def get_spatial_kmeans(self, query):
return self.mocked_result
def get_nonspatial_kmeans(self, query, standarize):

2
src/py/crankshaft/test/test_space_time_dynamics.py
View File

@ -17,7 +17,7 @@ class FakeDataProvider(AnalysisDataProvider):
def __init__(self, data):
self.mock_result = data
def get_markov(self, query):
def get_markov(self, w_type, params):
return self.mock_result