wrangler.py 文件源码

def _starts_with_output(data, col):

    '''

    Helper function for to_integers in cases where
    the feature is categorized based on a common
    first character of a string.

    '''

    data[col] = data[col].fillna('0')
    temp_df = _category_starts_with(data, col)
    temp_df['start_char'] = temp_df[0]
    temp_df = temp_df.drop(0, axis=1)
    reference_df = temp_df.set_index('start_char').transpose()
    temp_list = []
    for i in range(len(data[col])):
        for c in temp_df['start_char']:
            if data[col][i].startswith(c) == True:
                temp_list.append(reference_df[c][0])
    if len(data[col]) != len(temp_list):
        print "AUTONOMIO ERROR: length of input and output do not match"
    else:
        return pd.Series(temp_list)