From 9a80244e76df5c33034cd0fdc0ce34dade3a193e Mon Sep 17 00:00:00 2001
From: Andy Eschbacher <andy.eschbacher@gmail.com>
Date: Tue, 6 Dec 2016 10:14:37 -0500
Subject: [PATCH] adds tests and pgsql file

---
 src/pg/sql/11_kmeans.sql                      | 19 +++++++++
 .../crankshaft/test/test_clustering_kmeans.py | 39 ++++++++++++++++---
 2 files changed, 52 insertions(+), 6 deletions(-)

diff --git a/src/pg/sql/11_kmeans.sql b/src/pg/sql/11_kmeans.sql
index 0899e81..6100d27 100644
--- a/src/pg/sql/11_kmeans.sql
+++ b/src/pg/sql/11_kmeans.sql
@@ -9,6 +9,25 @@ RETURNS table (cartodb_id integer, cluster_no integer) as $$
 
 $$ LANGUAGE plpythonu;
 
+-- Non-spatial k-means clustering
+-- query: sql query to retrieve all the needed data
+
+CREATE OR REPLACE FUNCTION CDB_KMeansNonspatial(
+  query TEXT,
+  colnames TEXT[],
+  num_clusters INTEGER,
+  id_colname TEXT DEFAULT 'cartodb_id',
+  standarize BOOLEAN DEFAULT true
+)
+RETURNS TABLE(cluster_label text, cluster_center json, silhouettes numeric, rowid bigint) AS $$
+
+    from crankshaft.clustering import Kmeans
+    kmeans = Kmeans()
+    return kmeans.nonspatial(query, colnames, num_clusters,
+                             id_colname, standarize)
+$$ LANGUAGE plpythonu;
+
+
 
 CREATE OR REPLACE FUNCTION CDB_WeightedMeanS(state Numeric[],the_geom GEOMETRY(Point, 4326), weight NUMERIC)
 RETURNS Numeric[] AS
diff --git a/src/py/crankshaft/test/test_clustering_kmeans.py b/src/py/crankshaft/test/test_clustering_kmeans.py
index 93633b0..5e096ca 100644
--- a/src/py/crankshaft/test/test_clustering_kmeans.py
+++ b/src/py/crankshaft/test/test_clustering_kmeans.py
@@ -2,17 +2,12 @@ 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 Kmeans
 from crankshaft.analysis_data_provider import AnalysisDataProvider
 import crankshaft.clustering as cc
-
 from crankshaft import random_seeds
+
 import json
 from collections import OrderedDict
 
@@ -54,3 +49,35 @@ class KMeansTest(unittest.TestCase):
         self.assertEqual(len(np.unique(labels)), 2)
         self.assertEqual(len(c1), 20)
         self.assertEqual(len(c2), 20)
+
+
+class KMeansNonspatialTest(unittest.TestCase):
+    """Testing class for k-means non-spatial"""
+
+    def setUp(self):
+        self.params = {"subquery": "SELECT * FROM TABLE",
+                       "n_clusters": 5}
+
+    def test_kmeans_nonspatial(self):
+        """
+            test for k-means non-spatial
+        """
+        # data from:
+        # http://scikit-learn.org/stable/modules/generated/sklearn.cluster.KMeans.html#sklearn-cluster-kmeans
+        data_raw = [OrderedDict([("col1", [1, 1, 1, 4, 4, 4]),
+                                 ("col2", [2, 4, 0, 2, 4, 0]),
+                                 ("rowids", [1, 2, 3, 4, 5, 6])])]
+
+        random_seeds.set_random_seeds(1234)
+        kmeans = Kmeans(FakeQueryRunner(data_raw))
+        clusters = kmeans.nonspatial('subquery', ['col1', 'col2'], 2)
+        print str([c[0] for c in clusters])
+
+        cl1 = clusters[0][0]
+        cl2 = clusters[3][0]
+
+        for idx, val in enumerate(clusters):
+            if idx < 3:
+                self.assertEqual(val[0], cl1)
+            else:
+                self.assertEqual(val[0], cl2)