update math features wrapper

alpha_automl/builtin_primitives/math_features.py

@@ -0,0 +1,48 @@
+import numpy as np
+import pandas as pd
+from alpha_automl.base_primitive import BasePrimitive
+from feature_engine.creation import MathFeatures
+
+class MathFeaturesSum(BasePrimitive):
+    def __init__(self, columns):
+        self.math_features = MathFeatures(variables=columns, func='sum')
+
+    def fit(self, X, y=None):
+        self.math_features.fit(X)
+        return self
+
+    def transform(self, X):
+        return self.math_features.transform(X)
+
+class MathFeaturesMean(BasePrimitive):
+    def __init__(self, columns):
+        self.math_features = MathFeatures(variables=columns, func='mean')
+
+    def fit(self, X, y=None):
+        self.math_features.fit(X)
+        return self
+
+    def transform(self, X):
+        return self.math_features.transform(X)
+
+class MathFeaturesStd(BasePrimitive):
+    def __init__(self, columns):
+        self.math_features = MathFeatures(variables=columns, func='std')
+
+    def fit(self, X, y=None):
+        self.math_features.fit(X)
+        return self
+
+    def transform(self, X):
+        return self.math_features.transform(X)
+
+class MathFeaturesProd(BasePrimitive):
+    def __init__(self, columns):
+        self.math_features = MathFeatures(variables=columns, func='prod')
+
+    def fit(self, X, y=None):
+        self.math_features.fit(X)
+        return self
+
+    def transform(self, X):
+        return self.math_features.transform(X)

alpha_automl/data_profiler.py

@@ -43,8 +43,8 @@ def profile_data(X):
         if 'missing_values_ratio' in profiled_column:
             metadata['missing_values'] = True
 
-    metadata['numeric_columns'] = list(X.select_dtypes(include=['int64', 'float64']).columns)
-    metadata['categorical_columns'] = list(X.select_dtypes(include=['object', 'category']).columns)
+    metadata['numeric_columns'] = [(index_column, column_name) for index_column, column_name in enumerate(X.columns) if X[column_name].dtype in ['int64', 'float64']]
+    metadata['categorical_columns'] = [(index_column, column_name) for index_column, column_name in enumerate(X.columns) if X[column_name].dtype in ['object', 'category']]
 
     logger.debug(f'Results of profiling data: non-numeric features = {str(metadata["nonnumeric_columns"].keys())}, '
                 f'useless columns = {str(metadata["useless_columns"])}, '

alpha_automl/pipeline_synthesis/pipeline_builder.py

@@ -38,17 +38,6 @@ def change_default_hyperparams(primitive_object):
         primitive_object.set_params(algorithm='SAMME')
 
 
-def create_math_features(primitive_type, columns):
-    if primitive_type == "sum":
-        return MathFeatures(variables=columns, func='sum')
-    elif primitive_type == "mean":
-        return MathFeatures(variables=columns, func='mean')
-    elif primitive_type == "std":
-        return MathFeatures(variables=columns, func='std')
-    elif primitive_type == "prod":
-        return MathFeatures(variables=columns, func='prod')
-
-
 def extract_estimators(pipeline_primitives, all_primitives):
     estimators = []
     estimator_name, estimator_obj = pipeline_primitives.pop()
@@ -118,9 +107,8 @@ def make_primitive_objects(self, primitives):
             elif primitive_type == 'CLASSIFICATION_MULTI_ENSEMBLER' or primitive_type == 'REGRESSION_MULTI_ENSEMBLER':
                 estimators = extract_estimators(pipeline_primitives, self.all_primitives)
                 primitive_object = create_object(primitive_name, {'estimators': estimators})
-            elif "feature_engine.creation" in primitive_name:
-                primitive_name_type = primitive_name.split('-')[1]
-                primitive_object = create_math_features(primitive_name_type, list(range(len(numeric_columns))))
+            elif "alpha_automl.builtin_primitives.math_features" in primitive_name:
+                primitive_object = create_object(primitive_name, {'columns': [column_name for _, column_name in numeric_columns]})
             elif self.all_primitives[primitive_name]['origin'] == NATIVE_PRIMITIVE:  # It's an installed primitive
                 primitive_object = create_object(primitive_name, EXTRA_PARAMS.get(primitive_name, None))
             else:

alpha_automl/resource/primitives_hierarchy.json

@@ -21,10 +21,10 @@
     ],
     "FEATURE_GENERATOR": [
         "sklearn.preprocessing.PolynomialFeatures",
-        "feature_engine.creation.math_features.MathFeatures-sum",
-        "feature_engine.creation.math_features.MathFeatures-mean",
-        "feature_engine.creation.math_features.MathFeatures-prod",
-        "feature_engine.creation.math_features.MathFeatures-std"
+        "alpha_automl.builtin_primitives.math_features.MathFeaturesSum",
+        "alpha_automl.builtin_primitives.math_features.MathFeaturesMean",
+        "alpha_automl.builtin_primitives.math_features.MathFeaturesProd",
+        "alpha_automl.builtin_primitives.math_features.MathFeaturesStd"
     ],
     "FEATURE_SCALER": [
         "sklearn.preprocessing.MaxAbsScaler",