cartodb/crankshaft
1
0
Fork 0
mirror of https://github.com/CartoDB/crankshaft.git synced 2024-11-01 10:20:48 +08:00
Code Issues Packages Projects Releases Wiki Activity

changes cluster centers to json

Browse Source
This commit is contained in:
Andy Eschbacher 2016-11-10 16:56:04 +00:00
parent a188b2e104
commit 64c4b6611c
2 changed files with 7 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/pg/sql/11_kmeans.sql
View File

@ -15,14 +15,14 @@ CREATE OR REPLACE FUNCTION CDB_KMeansNonspatial(
query TEXT, query TEXT,
colnames TEXT[], colnames TEXT[],
num_clusters INTEGER, num_clusters INTEGER,
id_col TEXT DEFAULT 'cartodb_id', id_colname TEXT DEFAULT 'cartodb_id',
standarize BOOLEAN DEFAULT true standarize BOOLEAN DEFAULT true
) )
RETURNS TABLE(cluster_label text, cluster_center text, rowid bigint) AS $$ RETURNS TABLE(cluster_label text, cluster_center json, rowid bigint) AS $$
from crankshaft.clustering import kmeans_nonspatial from crankshaft.clustering import kmeans_nonspatial
return kmeans_nonspatial(query, colnames, num_clusters, return kmeans_nonspatial(query, colnames, num_clusters,
id_col, standarize) id_colname, standarize)
$$ LANGUAGE plpythonu; $$ LANGUAGE plpythonu;

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

@ -40,6 +40,7 @@ def kmeans_nonspatial(query, colnames, num_clusters=5,
num_clusters (int): number of clusters (greater than zero) num_clusters (int): number of clusters (greater than zero)
id_col (string): name of the input id_column id_col (string): name of the input id_column
""" """
import json
out_id_colname = 'rowids' out_id_colname = 'rowids'
# TODO: need a random seed? # TODO: need a random seed?
@ -60,7 +61,7 @@ def kmeans_nonspatial(query, colnames, num_clusters=5,
# fill array with values for k-means 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, out_id_colname))
else: else:
cluster_columns = _extract_columns(db_resp, id_col=out_id_colname) cluster_columns = _extract_columns(db_resp, id_col=out_id_colname)
@ -69,8 +70,9 @@ def kmeans_nonspatial(query, colnames, num_clusters=5,
kmeans = KMeans(n_clusters=num_clusters, kmeans = KMeans(n_clusters=num_clusters,
random_state=0).fit(cluster_columns) random_state=0).fit(cluster_columns)
centers = [json.dumps(dict(zip(colnames, c))) for c in kmeans.cluster_centers_[kmeans.labels_]]
return zip(kmeans.labels_, return zip(kmeans.labels_,
map(str, kmeans.cluster_centers_[kmeans.labels_]), centers,
db_resp[0][out_id_colname]) db_resp[0][out_id_colname])