expose floor variable and new test file

src/pg/sql/22_maxp.sql

@@ -4,6 +4,7 @@ CREATE OR REPLACE FUNCTION
   CDB_MaxP(
       subquery TEXT,
       colnames TEXT[],
+      floor_variable TEXT,
       min_size int default 1,
       initial int default 99,
       geom_col TEXT DEFAULT 'the_geom',
@@ -12,5 +13,5 @@ RETURNS TABLE (region_class text, p_val numeric, rowid bigint)
 AS $$
   from crankshaft.clustering import MaxP
   maxp = MaxP()
-  return maxp.maxp(subquery, colnames, floor=min_size)
+  return maxp.maxp(subquery, colnames, floor_variable, floor=min_size)
 $$ LANGUAGE plpythonu;

src/py/crankshaft/crankshaft/analysis_data_provider.py

@@ -67,7 +67,7 @@ class AnalysisDataProvider:
             plpy.error('Analysis failed: %s' % err)
 
     def get_maxp(self, params):
-        """fetch data for spatial markov"""
+        """fetch data for max-p"""
         try:
             query = pu.construct_neighbor_query('queen', params)
             data = plpy.execute(query)

src/py/crankshaft/crankshaft/clustering/maxp.py

@@ -5,6 +5,7 @@
 import pysal as ps
 import numpy as np
 import random
+import time
 
 import crankshaft.pysal_utils as pu
 from crankshaft.analysis_data_provider import AnalysisDataProvider
@@ -17,16 +18,20 @@ class MaxP:
         else:
             self.data_provider = AnalysisDataProvider()
 
-    def maxp(self, subquery, colnames, floor=1,
-             geom_col='the_geom', id_col='cartodb_id'):
+    def maxp(self, subquery, colnames, floor_variable,
+            floor=1,
+            geom_col='the_geom', id_col='cartodb_id'):
         """
             Inputs:
             @param subquery (text): subquery to expose the data need for the
                                     analysis. This query needs to expose all
                                     of the columns in `colnames`, `id_col`, and
                                     `geom_col`
-            @param colnames (list): list of column names (as strings)
-            @param floor (float): ...
+            @param colnames (list): list of column names (as strings). This is
+                                    used to calculate intra-regional homogeneity.
+            @param floor_variable (text): name of column variable for the floor
+            @param floor (int): the minimum bound for a variable that has to be
+                                obtained in each region,
             @param geom_col (text): geometry column used for calculating the
                                     spatial neighborhood
             @param id_col (text): id column used for keeping the identity of
@@ -39,23 +44,29 @@ class MaxP:
         params = {'subquery': subquery,
                   'colnames': colnames,
                   'id_col': id_col,
-                  'geom_col': geom_col}
+                  'geom_col': geom_col,
+                  'floor_variable':floor_variable,
+                  }
 
         resp = self.data_provider.get_maxp(params)
-
         attr_vals = pu.get_attributes(resp, len(colnames))
-
+        floor_column_id = colnames.index(floor_variable)
+        # print "floor_column_id: ", floor_column_id
         weight = pu.get_weight(resp, w_type='queen')
+        start_time = time.time()
         r = ps.Maxp(weight, attr_vals,
                     floor=floor,
-                    floor_variable=np.ones((weight.n, 1)))
-
+                    floor_variable= attr_vals.transpose()[floor_column_id],
+                    initial=10)
+        # print r.regions
         cluster_classes = get_cluster_classes(weight.id_order, r.regions)
         r.inference()
+        # print "elapsed time: ", time.time() - start_time
         return zip(cluster_classes, [r.pvalue] * len(weight.id_order),
                    weight.id_order)
 
 
+
 def get_cluster_classes(ids, clusters):
     """
 

src/py/crankshaft/test/test_clustering_maxp.py

@@ -0,0 +1,62 @@
+import unittest
+import numpy as np
+
+
+# from mock_plpy import MockPlPy
+# plpy = MockPlPy()
+#
+# import sys
+# sys.modules['plpy'] = plpy
+from helper import fixture_file
+from crankshaft.clustering import MaxP
+from crankshaft.analysis_data_provider import AnalysisDataProvider
+import crankshaft.clustering as cc
+
+from crankshaft import random_seeds
+import json
+from collections import OrderedDict
+
+
+class FakeDataProvider(AnalysisDataProvider):
+    def __init__(self, fixturedata):
+        self.your_maxp_data = fixturedata
+
+    def get_maxp(self, params):
+        """
+          Replace this function name with the one used in your algorithm,
+          and make sure to use the same function signature that is written
+          for this algo in analysis_data_provider.py
+        """
+        return self.your_maxp_data
+
+class MaxPTest(unittest.TestCase):
+    """Testing class for max-p regionalization"""
+
+    def setUp(self):
+        self.neighbor_data = json.loads(
+          open(fixture_file('maxp.json')).read())
+        self.neighbor_data = self.neighbor_data['rows']
+        self.params = {"subquery": "select * from fake_table",
+                       "colnames": ['population','median_hh_income'],
+                       "floor_variable": 'population',
+                       "floor": 260000}
+
+    def test_maxp(self):
+        """
+        """
+        data = [{'id': d['id'],
+                 'attr1': d['attr1'],
+                 'attr2':d['attr2'],
+                 'neighbors': d['neighbors']} for d in self.neighbor_data]
+
+        random_seeds.set_random_seeds(1234)
+        maxp = MaxP(FakeDataProvider(data))
+        regions = maxp.maxp('select * from research_nothing',['population','median_hh_income'],floor_variable='population',floor=260000)
+        region_labels = [a[0] for a in regions]
+        data_regionalized = zip(data,region_labels)
+        for i in set(region_labels):
+            sum_pop = 0
+            for n in data_regionalized:
+                if n[1] == i:
+                    sum_pop += n[0]['attr1']
+            self.assertGreaterEqual(sum_pop, 260000)