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

small updates for readability

Browse Source
This commit is contained in:
Andy Eschbacher 2016-10-21 10:13:21 -06:00
parent 3c6d73b7e2
commit 4389c9538d
1 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
src/py/crankshaft/crankshaft/clustering/kmeans.py
View File

@ -74,15 +74,15 @@ def kmeans_nonspatial(query, colnames, num_clusters=5,
db_resp[0][out_id_colname])
def _extract_columns(db_resp, id_col):
def _extract_columns(db_resp, id_col_name):
"""
Extract the features from the query and pack them into a NumPy array
db_resp (plpy data object): result of the kmeans request
id_col (string): name of column which has the row id (not a feature of
the analysis)
id_col_name (string): name of column which has the row id (not a
feature of the analysis)
"""
return np.array([db_resp[0][c] for c in db_resp.colnames()
if c != id_col],
if c != id_col_name],
dtype=float).T
# -- Preprocessing steps
@ -91,7 +91,8 @@ def _extract_columns(db_resp, id_col):
def _scale_data(features):
"""
Scale all input columns to center on 0 with a standard devation of 1
features (numpy array): an array of dimension (n_features, n_samples)
features (numpy matrix): features of dimension (n_features, n_samples)
"""
from sklearn.preprocessing import StandardScaler
return StandardScaler().fit_transform(features)