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

update comments

Browse Source
This commit is contained in:
Andy Eschbacher 2016-10-18 21:13:34 -06:00
parent f0c6cca766
commit 3e0dba3522
1 changed files with 6 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
src/py/crankshaft/crankshaft/clustering/kmeans.py
View File

@ -5,7 +5,8 @@ import numpy as np
def kmeans(query, no_clusters, no_init=20): 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 = ''' full_query = '''
SELECT array_agg(cartodb_id ORDER BY cartodb_id) as ids, SELECT array_agg(cartodb_id ORDER BY cartodb_id) as ids,
@ -17,8 +18,9 @@ def kmeans(query, no_clusters, no_init=20):
try: try:
data = plpy.execute(full_query) data = plpy.execute(full_query)
except plpy.SPIError, err: 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'] xs = data[0]['xs']
ys = data[0]['ys'] ys = data[0]['ys']
ids = data[0]['ids'] ids = data[0]['ids']
@ -55,9 +57,9 @@ def kmeans_nonspatial(query, colnames, num_clusters=5,
try: try:
db_resp = plpy.execute(full_query) db_resp = plpy.execute(full_query)
except plpy.SPIError, err: 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: if standarize:
cluster_columns = _scale_data( cluster_columns = _scale_data(
_extract_columns(db_resp, id_col=out_id_colname)) _extract_columns(db_resp, id_col=out_id_colname))