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

adding silhouette

Browse Source
This commit is contained in:
Andy Eschbacher 2016-11-15 00:15:23 +01:00
parent 64c4b6611c
commit b6dae5e380
1 changed files with 9 additions and 1 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

@ -41,6 +41,8 @@ def kmeans_nonspatial(query, colnames, num_clusters=5,
id_col (string): name of the input id_column id_col (string): name of the input id_column
""" """
import json import json
from sklearn import metrics
out_id_colname = 'rowids' out_id_colname = 'rowids'
# TODO: need a random seed? # TODO: need a random seed?
@ -70,7 +72,13 @@ 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_]] centers = [json.dumps(dict(zip(colnames, c)))
for c in kmeans.cluster_centers_[kmeans.labels_]]
silhouettes = metrics.silhouette_samples(cluster_columns,
labels,
metric='sqeuclidean')
return zip(kmeans.labels_, return zip(kmeans.labels_,
centers, centers,
db_resp[0][out_id_colname]) db_resp[0][out_id_colname])