:py:mod:`ForeTiS.preprocess.raw_data_functions`
===============================================

.. py:module:: ForeTiS.preprocess.raw_data_functions


Module Contents
---------------


Functions
~~~~~~~~~

.. autoapisummary::

   ForeTiS.preprocess.raw_data_functions.drop_columns
   ForeTiS.preprocess.raw_data_functions.drop_rows_by_dates
   ForeTiS.preprocess.raw_data_functions.custom_resampler
   ForeTiS.preprocess.raw_data_functions.get_one_hot_encoded_df
   ForeTiS.preprocess.raw_data_functions.get_simple_imputer
   ForeTiS.preprocess.raw_data_functions.get_iter_imputer
   ForeTiS.preprocess.raw_data_functions.get_knn_imputer
   ForeTiS.preprocess.raw_data_functions.encode_cyclical_features



.. py:function:: drop_columns(df, columns)

   Function dropping all columns specified

   :param df: dataset used for dropping
   :param columns: columns which should be dropped


.. py:function:: drop_rows_by_dates(df, start, end)

   Function dropping rows within specified dates

   :param df: dataset used for dropping
   :param start: start date for dropped period
   :param end: end date for dropped period


.. py:function:: custom_resampler(arraylike, target_column)

   Custom resampling function when resampling frequency of dataset

   :param arraylike: Series to use for calculation
   :param target_column: choosen target column

   :return: sum or mean of arraylike or 1


.. py:function:: get_one_hot_encoded_df(df, columns_to_encode)

   Function delivering dataframe with specified columns one hot encoded

   :param df: dataset to use for encoding
   :param columns_to_encode: columns to encode

   :return: dataset with encoded columns


.. py:function:: get_simple_imputer(df, strategy = 'mean')

   Get simple imputer for each column according to specified strategy

   :param df: DataFrame to impute
   :param strategy: strategy to use, e.g. 'mean' or 'median'

   :return: imputer


.. py:function:: get_iter_imputer(df, sample_posterior = True, max_iter = 100, min_value = 0, max_value = None)

   Multivariate, iterative imputer fitted to df with specified parameters

   :param df: DataFrame to fit for imputation
   :param sample_posterior: sample from predictive posterior of fitted estimator (standard: BayesianRidge())
   :param max_iter: maximum number of iterations for imputation
   :param min_value: min value for imputation
   :param max_value: max value for imputation

   :return: imputer


.. py:function:: get_knn_imputer(df, n_neighbors = 10)

   Imputer of missing values according to k-nearest neighbors in feature space

   :param df: DataFrame to use for imputation
   :param n_neighbors: number of neighbors to use for imputation

   :return: imputer


.. py:function:: encode_cyclical_features(df, columns)

   Function that encodes the cyclic features to sinus and cosinus distribution

   :param df: DataFrame to use for imputation
   :param columns: columns that should be encoded