column_importance_sorter_df#
- column_importance_sorter_df(df: DataFrame, ds: Dataset, feature_importances: Series, n_top: int = 10, col: Optional[Hashable] = None) DataFrame [source]#
Return the dataframe of columns sorted and limited by feature importance.
- Parameters
- dfpd.DataFrame
DataFrame to sort
- dstabular.Dataset
dataset used to fit the model
- feature_importancespd.Series
feature importance normalized to 0-1 indexed by feature names
- n_topint , default: 10
amount of columns to show ordered by feature importance (date, index, label are first)
- colt.Optional[Hashable] , default: None
name of column to sort the dataframe
- Returns
- pd.DataFrame
the dataframe sorted and limited by feature importance.