class PreprocessedData:
"""
This class combines the feature engineering and feature selection
class to one to preprocess the data.
It takes in the cleaned data and the y_column_name(ratings)
"""
def __init__(self, data, y_column_name):
self.data = data
self.y_column_name = y_column_name
self.feature_engineering = FeatureEngineering(data, y_column_name)
self.feature_selection = FeatureSelection(data, y_column_name)
def preprocess_my_data(self, num_of_features_to_select):
"""
This method preprocesses the cleaned data and performs
feature selection to select best n-features
:param num_of_features_to_select: n-best features of the model
:return: Full preprocesse data with n-selected features
"""
self.data = self.feature_engineering.input_rare_categorical()
self.data = self.feature_engineering.encode_categorical_features()
self.data = self.feature_engineering.scale_features()
self.data = self.feature_selection.perform_feature_selection(
num_of_features_to_select)
return self.data
class ProcessedData:
def __init__(self, train, test, id_column, y_column_name):
self.train = train
self.test = test
self.y_column_name = y_column_name
self.id_column = id_column
self.data = pd.concat([self.train, self.test], ignore_index=True)
self.feature_engineering = FeatureEngineering(self.train, self.test,
self.id_column,
self.y_column_name)
self.feature_selection = FeatureSelection(self.train, self.test,
self.id_column,
self.y_column_name)
def preprocess_my_data(self, num_of_features_to_select):
self.data = self.feature_engineering.scale_features()
self.data = self.feature_selection.perform_feature_selection(
num_of_features_to_select)
return self.data
class PreprocessedData:
def __init__(self, train, test, id_column, y_column_name):
self.train = train
self.test = test
self.y_column_name = y_column_name
self.id_column = id_column
self.data = pd.concat([train, test], ignore_index=True)
self.feature_engineering = FeatureEngineering(train, test, id_column,
y_column_name)
self.feature_selection = FeatureSelection(train, test, id_column,
y_column_name)
def preprocess_my_data(self, num_of_features_to_select):
self.data = self.feature_engineering.fill_na_categorical()
self.data = self.feature_engineering.fill_na_numerical()
self.data = self.feature_engineering.input_rare_categorical()
self.data = self.feature_engineering.label_encoder()
self.data = self.feature_engineering.get_scale_features()
self.data = self.feature_selection.perform_feature_selection(
num_of_features_to_select)
return self.data