Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- def select_features_lasso(data, output_feature, input_features = None, user_standardization = True, user_max_iterations = 100,
- user_epsilon = 1.35):
- """
- data(Spark Dataframe): The data needed to perform feature selection on. It
- is a precondition that the data be clean and already have the schema the user
- wishes to work with
- output_feature(String): The name of the feature which is to be predicted
- (expected for there to be a feature )
- input_features(String List): A list of the names
- """
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement