Adding a segmentation version that doesn't use query string passing

src/pg/sql/05_segmentation.sql

@@ -1,3 +1,41 @@
+
+CREATE OR REPLACE FUNCTION
+  CDB_CreateAndPredictSegment(
+    target NUMERIC[],
+    features NUMERIC[],
+    target_features NUMERIC[],
+    target_ids NUMERIC[],
+    n_estimators INTEGER DEFAULT 1200,
+    max_depth INTEGER DEFAULT 3,
+    subsample DOUBLE PRECISION DEFAULT 0.5,
+    learning_rate DOUBLE PRECISION DEFAULT 0.01,
+    min_samples_leaf INTEGER DEFAULT 1
+  )
+RETURNS TABLE( cartodb_id Numeric, prediction Numeric , accuracy Numeric)
+AS $$
+    import numpy as np 
+    import plpy 
+
+    from crankshaft.segmentation import create_and_predict_segment_agg
+    model_params = { 'n_estimators' : n_estimators, 
+                     'max_depth' : max_depth, 
+                     'subsample' : subsample, 
+                     'learning_rate' : learning_rate, 
+                     'min_samples_leaf' : min_samples_leaf} 
+  
+    def unpack2D(data):
+        dimension = data.pop(0)
+        a = np.array(data, dtype=float)
+        return a.reshape(len(a)/dimension, dimension)
+
+    return create_and_predict_segment_agg( np.array(target, dtype=float), 
+            unpack2D(features), 
+            unpack2D(target_features), 
+            target_ids,
+            model_params)
+
+$$ Language plpythonu;
+
 CREATE OR REPLACE FUNCTION
   CDB_CreateAndPredictSegment (
       query TEXT,
@@ -16,4 +54,3 @@ AS $$
   model_params = {'n_estimators': n_estimators, 'max_depth':max_depth, 'subsample' : subsample, 'learning_rate': learning_rate, 'min_samples_leaf' : min_samples_leaf} 
   return create_and_predict_segment(query,variable_name,target_table, model_params)
 $$ LANGUAGE plpythonu;
-

src/py/crankshaft/crankshaft/segmentation/segmentation.py

@@ -29,6 +29,18 @@ def get_data(variable, feature_columns, query):
 
     return replace_nan_with_mean(target), replace_nan_with_mean(features)
 
+
+def create_and_predict_segment_agg(target, features, target_features, target_ids,model_parameters):
+    clean_target = replace_nan_with_mean(target)
+    clean_features = replace_nan_with_mean(features)
+    target_features = replace_nan_with_mean(target_features)
+
+    model, accuracy = train_model(clean_target,clean_features, model_parameters, 0.2)
+    prediction = model.predict(target_features)
+    return zip(target_ids, prediction, np.full(prediction.shape, accuracy))
+
+
+
 def create_and_predict_segment(query,variable,target_query,model_params):
     """
     generate a segment with machine learning
@@ -48,9 +60,7 @@ def create_and_predict_segment(query,variable,target_query,model_params):
 def train_model(target,features,model_params,test_split):
     features_train, features_test, target_train, target_test = train_test_split(features, target, test_size=test_split)
     model = GradientBoostingRegressor(**model_params)
-    plpy.notice('training the model: fitting to data')
     model.fit(features_train, target_train)
-    plpy.notice('model trained')
     accuracy = calculate_model_accuracy(model,features,target)
     return model, accuracy
 
@@ -82,10 +92,8 @@ def predict_segment(model,features,target_query):
 
         #Need to fix this. Should be global mean. This will cause weird effects
         batch  = replace_nan_with_mean(batch)
-        plpy.notice(len(batch))
         prediction   = model.predict(batch)
         results.append(prediction)
-        plpy.notice('predicting: predicted')
 
 
     cartodb_ids = plpy.execute('select array_agg(cartodb_id order by cartodb_id) as cartodb_ids from ({0}) a '.format(target_query))[0]['cartodb_ids']