creating the spatial lag function

src/pg/sql/21_spatial_lag.sql

@@ -0,0 +1,17 @@
+-- Spatial Lag with kNN neighbors (internal function)
+CREATE OR REPLACE FUNCTION
+  CDB_SpatialLag(
+      subquery TEXT,
+      column_name TEXT,
+      w_type TEXT,
+      num_ngbrs INT,
+      geom_col TEXT,
+      id_col TEXT)
+RETURNS TABLE (lag NUMERIC, rowid INT)
+AS $$
+  from crankshaft.spatial_lag import Spatial
+  spatial = Spatial()
+  # TODO: use named parameters or a dictionary
+  return spatial.spatial_lag(subquery, column_name, w_type,
+                          num_ngbrs, geom_col, id_col)
+$$ LANGUAGE plpythonu;

src/py/crankshaft/crankshaft/analysis_data_provider.py

@@ -30,7 +30,7 @@ class AnalysisDataProvider:
         except plpy.SPIError, err:
             plpy.error('Analysis failed: %s' % err)
 
-    def get_moran(self, w_type, params):
+    def get_neighbor(self, w_type, params):
         """fetch data for moran's i analyses"""
         try:
             query = pu.construct_neighbor_query(w_type, params)

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

@@ -36,7 +36,7 @@ class Moran:
                               ("subquery", subquery),
                               ("num_ngbrs", num_ngbrs)])
 
-        result = self.data_provider.get_moran(w_type, params)
+        result = self.data_provider.get_neighbor(w_type, params)
 
         # collect attributes
         attr_vals = pu.get_attributes(result)
@@ -66,7 +66,7 @@ class Moran:
                               ("subquery", subquery),
                               ("num_ngbrs", num_ngbrs)])
 
-        result = self.data_provider.get_moran(w_type, params)
+        result = self.data_provider.get_neighbor(w_type, params)
 
         attr_vals = pu.get_attributes(result)
         weight = pu.get_weight(result, w_type, num_ngbrs)
@@ -93,7 +93,7 @@ class Moran:
                               ("subquery", subquery),
                               ("num_ngbrs", num_ngbrs)])
 
-        result = self.data_provider.get_moran(w_type, params)
+        result = self.data_provider.get_neighbor(w_type, params)
 
         # collect attributes
         numer = pu.get_attributes(result, 1)
@@ -123,7 +123,7 @@ class Moran:
                               ("subquery", subquery),
                               ("num_ngbrs", num_ngbrs)])
 
-        result = self.data_provider.get_moran(w_type, params)
+        result = self.data_provider.get_neighbor(w_type, params)
 
         # collect attributes
         numer = pu.get_attributes(result, 1)
@@ -154,7 +154,7 @@ class Moran:
                               ("subquery", subquery),
                               ("num_ngbrs", num_ngbrs)])
 
-        result = self.data_provider.get_moran(w_type, params)
+        result = self.data_provider.get_neighbor(w_type, params)
 
         # collect attributes
         attr1_vals = pu.get_attributes(result, 1)

src/py/crankshaft/crankshaft/spatial_lag/__init__.py

@@ -0,0 +1,2 @@
+"""Import all functions from for clustering"""
+from spatial_lag import *

src/py/crankshaft/crankshaft/spatial_lag/spatial_lag.py

@@ -0,0 +1,46 @@
+"""
+Spatial Lag (using local kNN neighbors identifying spatial lag for a feature)
+"""
+
+import pysal as ps
+from collections import OrderedDict
+from crankshaft.analysis_data_provider import AnalysisDataProvider
+
+# crankshaft module
+import crankshaft.pysal_utils as pu
+
+# High level interface ---------------------------------------
+
+
+class Spatial:
+    def __init__(self, data_provider=None):
+        if data_provider is None:
+            self.data_provider = AnalysisDataProvider()
+        else:
+            self.data_provider = data_provider
+
+    def spatial_lag(self, subquery, attr,
+                    w_type, num_ngbrs, geom_col, id_col):
+        """
+        Querying spatial lags for kNN neighbors
+        """
+
+        # geometries with attributes that are null are ignored
+        # resulting in a collection of not as near neighbors
+
+        params = OrderedDict([("id_col", id_col),
+                              ("attr1", attr),
+                              ("geom_col", geom_col),
+                              ("subquery", subquery),
+                              ("num_ngbrs", num_ngbrs)])
+
+        result = self.data_provider.get_neighbor(w_type, params)
+
+        attr_vals = pu.get_attributes(result)
+        weight = pu.get_weight(result, w_type, num_ngbrs)
+
+        # calculate spatial_lag values
+
+        lag = ps.weights.spatial_lag.lag_spatial(weight, attr_vals)
+
+        return zip(lag, weight.id_order)