pipeline_functions.py 文件源码

def split_df_col2cols(dataframe, split_col, split_char, new_colnames, delete_old = False):
    # # Splits a column into multiple columns
    # dataframe : pandas dataframe to be processed
    # split_col : chr string of the column name to be split
    # split_char : chr to split the col on
    # new_colnames : list of new name for the columns
    # delete_old : logical True / False, remove original column?
    # ~~~~~~~~~~~~~~~~ #
    import pandas as pd
    import numpy as np
    # pl.my_debugger(globals().copy())
    # my_debugger(locals().copy())
    # save the split column as a separate object
    new_cols = dataframe[split_col].astype(np.object_).str.split(split_char).apply(pd.Series, 1)
    # if all values were NaN, no split occured, only one col exists still
    if len(new_cols.columns) < len(new_colnames):
        # create the missing cols, fill with NaN
        for i in range(len(new_cols.columns), len(new_colnames)):
            new_cols[new_colnames[i]] = np.nan
    # rename the cols
    new_cols.columns = new_colnames
    # remove the original column from the df
    if delete_old is True:
        del dataframe[split_col]
    # merge with df
    new_df = dataframe.join(new_cols)
    return new_df