cryptodatapy.transform.clean
============================

.. py:module:: cryptodatapy.transform.clean


Classes
-------

.. autoapisummary::

   cryptodatapy.transform.clean.CleanData


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

.. py:class:: CleanData(df: pandas.DataFrame)

   Cleans data to improve data quality.


   .. py:attribute:: raw_df


   .. py:attribute:: df


   .. py:attribute:: excluded_cols
      :value: None



   .. py:attribute:: outliers
      :value: None



   .. py:attribute:: yhat
      :value: None



   .. py:attribute:: repaired_df
      :value: None



   .. py:attribute:: filtered_df
      :value: None



   .. py:attribute:: filtered_tickers
      :value: None



   .. py:attribute:: summary


   .. py:method:: initialize_summary() -> None

      Initializes summary dataframe with data quality metrics.



   .. py:method:: check_types() -> None

      Checks data types of columns and converts them to the appropriate data types.

      :returns: CleanData object
      :rtype: CleanData



   .. py:method:: filter_outliers(od_method: str = 'mad', excl_cols: Optional[Union[str, list]] = None, **kwargs) -> CleanData

      Filters outliers.

      :param od_method: Outlier detection method to use for filtering.
      :type od_method: str, {'atr', 'iqr', 'mad', 'z_score', 'ewma', 'stl', 'seasonal_decomp', 'prophet'}, default z_score
      :param excl_cols: Name of columns to exclude from outlier filtering.
      :type excl_cols: str or list

      :returns: CleanData object
      :rtype: CleanData



   .. py:method:: repair_outliers(imp_method: str = 'interpolate', **kwargs) -> CleanData

      Repairs outliers using an imputation method.

      :param imp_method: Imputation method used to replace filtered outliers.
      :type imp_method: str, {"fwd_fill', 'interpolate', 'fcst'}, default 'fwd_fill'

      :returns: CleanData object
      :rtype: CleanData



   .. py:method:: filter_avg_trading_val(thresh_val: int = 10000000, window_size: int = 30) -> CleanData

      Filters values below a threshold of average trading value (price * volume/size in quote currency) over some
      lookback window, replacing them with NaNs.

      :param thresh_val: Threshold/cut-off for avg trading value.
      :type thresh_val: int, default 10,000,000
      :param window_size: Size of rolling window.
      :type window_size: int, default 30

      :returns: CleanData object
      :rtype: CleanData



   .. py:method:: filter_missing_vals_gaps(gap_window: int = 30) -> CleanData

      Filters values before a large gap of missing values, replacing them with NaNs.

      :param gap_window: Size of window where all values are missing (NaNs).
      :type gap_window: int, default 30

      :returns: CleanData object
      :rtype: CleanData



   .. py:method:: filter_min_nobs(ts_obs: int = 100, cs_obs: int = 2) -> CleanData

      Removes tickers from dataframe if the ticker has less than a minimum number of observations.

      :param ts_obs: Minimum number of observations for field/column over time series.
      :type ts_obs: int, default 100
      :param cs_obs: Minimum number of observations for tickers over the cross-section.
      :type cs_obs: int, default 5

      :returns: CleanData object
      :rtype: CleanData



   .. py:method:: filter_delisted_tickers(method: str = 'replace') -> CleanData

      Removes delisted tickers from dataframe.

      :param method: Method to use for handling delisted tickers.
      :type method: str, {'replace', 'remove'}, default 'replace'

      :returns: CleanData object
      :rtype: CleanData



   .. py:method:: filter_tickers(tickers_list) -> CleanData

      Removes specified tickers from dataframe.

      :param tickers_list: List of tickers to be removed. Can be used to remove tickers to be excluded from data analysis,
                           e.g. stablecoins or indexes.
      :type tickers_list: str or list

      :returns: CleanData object
      :rtype: CleanData



   .. py:method:: show_plot(plot_series: tuple = ('BTC', 'close'), compare_series: bool = True) -> None

      Plots clean time series and compares it to the raw series.

      :param plot_series: Plots the time series of a specific (ticker, field) tuple.
      :type plot_series: tuple, optional, default('BTC', 'close')
      :param compare_series: Compares clean time series with raw series
      :type compare_series: bool, default True



   .. py:method:: get(attr='df') -> pandas.DataFrame

      Returns GetData object attribute.

      :param attr: GetData object attribute to return
      :type attr: str, {'df', 'outliers', 'yhat', 'filtered_tickers', 'summary'}, default 'df'

      :returns: CleanData object
      :rtype: CleanData