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

re-edits

Browse Source
This commit is contained in:
mehak-sachdeva 2017-02-22 18:01:10 -05:00
parent 5a46f8da71
commit 456e68c9fc
1 changed files with 9 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
src/py/crankshaft/crankshaft/segmentation/segmentation.py
View File

@ -7,11 +7,10 @@ from sklearn.ensemble import GradientBoostingRegressor
from sklearn import metrics from sklearn import metrics
from sklearn.cross_validation import train_test_split from sklearn.cross_validation import train_test_split
from crankshaft.analysis_data_provider import AnalysisDataProvider from crankshaft.analysis_data_provider import AnalysisDataProvider
from mock_plpy import MockCursor
# NOTE: added optional param here # NOTE: added optional param here
class Segmentation(object): class Segmentation(object):
""" """
Add docstring Add docstring
@ -82,7 +81,7 @@ class Segmentation(object):
''' '''
rowid = [{'ids': [2.9, 4.9, 4, 5, 6]}] rowid = [{'ids': [2.9, 4.9, 4, 5, 6]}]
''' '''
return zip(rowid[0]['id_col'], result, accuracy_array) return zip(rowid[0]['ids'], result, accuracy_array)
def predict_segment(self, model, feature_columns, target_query, def predict_segment(self, model, feature_columns, target_query,
feature_means): feature_means):
@ -101,33 +100,20 @@ class Segmentation(object):
"feature_columns": feature_columns} "feature_columns": feature_columns}
results = [] results = []
cursor = self.data_provider.get_segmentation_predict_data(params) cursors = self.data_provider.get_segmentation_predict_data(params)
cursor = MockCursor(cursor)
''' '''
cursor = [{'feature_columns': [{'features': (0.81140362630858487, cursors = [{'features': [[m1[0],m2[0],m3[0]],[m1[1],m2[1],m3[1]],
0.65758478086896821, [m1[2],m2[2],m3[2]]]}]
0)}]}]
''' '''
while True: while True:
batch = [] rows = cursors.fetch(batch_size)
rows = cursor.fetch(batch_size)
if not rows: if not rows:
break break
for row in rows: batch = np.row_stack([np.array(row['features'])
max = len(rows[0]['feature_columns']) for row in rows]).astype(float)
for c in range(max):
batch = np.append(batch, np.row_stack([np.array(row
['feature_columns']
[c]
['features'])])
.astype(float))
# batch = np.row_stack([np.array(row['features'])
# for row in rows]).astype(float)
co = len(rows[0]['feature_columns'][0]['features'])
batch = batch.reshape((batch_size, co))
batch = replace_nan_with_mean(batch, feature_means)[0] batch = replace_nan_with_mean(batch, feature_means)[0]
prediction = model.predict(batch) prediction = model.predict(batch)
results.append(prediction) results.append(prediction)