From c48ae50ade2c27f37c67d06f43beb0df9b94071d Mon Sep 17 00:00:00 2001
From: Andy Eschbacher <andy.eschbacher@gmail.com>
Date: Fri, 9 Feb 2018 16:22:10 -0500
Subject: [PATCH] small syntax fixes

---
 src/pg/sql/11_kmeans.sql                         | 16 +++++++++++-----
 .../crankshaft/crankshaft/clustering/kmeans.py   |  4 ++--
 2 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/src/pg/sql/11_kmeans.sql b/src/pg/sql/11_kmeans.sql
index f840e31..708c3c6 100644
--- a/src/pg/sql/11_kmeans.sql
+++ b/src/pg/sql/11_kmeans.sql
@@ -24,12 +24,18 @@ $$ LANGUAGE plpythonu VOLATILE PARALLEL UNSAFE;
 --              deviation of 1
 -- id_colname: name of the id column
 
-CREATE OR REPLACE FUNCTION CDB_KMeansBalanced(query text, no_clusters integer, value_col TEXT default NULL, no_init integer default 20, max_per_cluster float default NULL )
-RETURNS table (cartodb_id integer, cluster_no integer) as $$
+CREATE OR REPLACE FUNCTION CDB_KMeansBalanced(
+    query text,
+    no_clusters integer,
+    value_col TEXT default NULL,
+    no_init integer default 20,
+    max_per_cluster float default NULL)
+RETURNS table(cartodb_id integer, cluster_no integer)
+AS $$
 
-  from crakshaft.clustering import KmeansBallanced
-  kmeans = KmeansBallanced()
-  return kmeans.spatial_balanced(query,no_clusters,no_init, max_per_cluster, value_col)
+from crankshaft.clustering import KmeansBalanced
+kmeans = KmeansBalanced()
+return kmeans.spatial_balanced(query,no_clusters,no_init, max_per_cluster, value_col)
 
 $$ LANGUAGE plpythonu VOLATILE PARALLEL UNSAFE;
 
diff --git a/src/py/crankshaft/crankshaft/clustering/kmeans.py b/src/py/crankshaft/crankshaft/clustering/kmeans.py
index 949aa29..97f5cbd 100644
--- a/src/py/crankshaft/crankshaft/clustering/kmeans.py
+++ b/src/py/crankshaft/crankshaft/clustering/kmeans.py
@@ -1,5 +1,5 @@
 from sklearn.cluster import KMeans
-from balanced_kmeans import BalancedGroupsKMeans
+from .balanced_kmeans import BalancedGroupsKMeans
 
 import numpy as np
 
@@ -51,7 +51,7 @@ class Kmeans(object):
         if target_per_cluster is None:
            target_per_cluster = total_value / float(no_clusters)
 
-        km = KmeansBallanced(n_clusters=17,max_iter=100, max_cluster_size=target_per_cluster)
+        km = BalancedGroupsKMeans(n_clusters=17,max_iter=100, max_cluster_size=target_per_cluster)
         labels = km.fit_predict(zip(xs,ys), values=values)
         return zip(ids,labels)