cartodb4/crankshaft
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

outputting consistent labels and centers

Browse Source
This commit is contained in:
Andy Eschbacher 2016-10-13 15:52:00 +00:00
parent 5d2a1881b1
commit 0feaf36cf6
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/py/crankshaft/crankshaft/clustering/kmeans.py
View File

@ -53,14 +53,13 @@ def kmeans_nonspatial(query, colnames, num_clusters=5,
try:
db_resp = plpy.execute(full_query)
plpy.notice('query: %s' % full_query)
except plpy.SPIError, err:
plpy.error('k-means cluster analysis failed: %s' % err)
# fill array with values for kmeans clustering
if standarize:
cluster_columns = scale_data(
extract_columns(db_resp, id_col='cartodb_id'))
extract_columns(db_resp, id_col=out_id_colname))
else:
cluster_columns = extract_columns(db_resp)
@ -69,7 +68,8 @@ def kmeans_nonspatial(query, colnames, num_clusters=5,
kmeans = KMeans(n_clusters=num_clusters,
random_state=0).fit(cluster_columns)
return zip(kmeans.labels_, map(str, kmeans.cluster_centers_),
return zip(kmeans.labels_,
map(str, kmeans.cluster_centers_[kmeans.labels_]),
db_resp[0][out_id_colname])