From 3e0dba35221cdbc5a66f4e9064ba73dba81c8775 Mon Sep 17 00:00:00 2001 From: Andy Eschbacher Date: Tue, 18 Oct 2016 21:13:34 -0600 Subject: [PATCH] update comments --- src/py/crankshaft/crankshaft/clustering/kmeans.py | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/src/py/crankshaft/crankshaft/clustering/kmeans.py b/src/py/crankshaft/crankshaft/clustering/kmeans.py index 84f83f7..21d76ea 100644 --- a/src/py/crankshaft/crankshaft/clustering/kmeans.py +++ b/src/py/crankshaft/crankshaft/clustering/kmeans.py @@ -5,7 +5,8 @@ import numpy as np def kmeans(query, no_clusters, no_init=20): """ - + find centers based on clusteres of latitude/longitude pairs + query: SQL query that has a WGS84 geometry (the_geom) """ full_query = ''' SELECT array_agg(cartodb_id ORDER BY cartodb_id) as ids, @@ -17,8 +18,9 @@ def kmeans(query, no_clusters, no_init=20): try: data = plpy.execute(full_query) except plpy.SPIError, err: - plpy.error("KMeans cluster failed: %s" % err) + plpy.error("k-means (spatial) cluster analysis failed: %s" % err) + # Unpack query response xs = data[0]['xs'] ys = data[0]['ys'] ids = data[0]['ids'] @@ -55,9 +57,9 @@ def kmeans_nonspatial(query, colnames, num_clusters=5, try: db_resp = plpy.execute(full_query) except plpy.SPIError, err: - plpy.error('k-means cluster analysis failed: %s' % err) + plpy.error("k-means (non-spatial) cluster analysis failed: %s" % err) - # fill array with values for kmeans clustering + # fill array with values for k-means clustering if standarize: cluster_columns = _scale_data( _extract_columns(db_resp, id_col=out_id_colname))