Python：正则表达式或字典

import pandas as pd
import numpy as np
import re
def calc_col(col):
    '''This function takes a string,
    finds the upper case letters or words placed as delimeter,
    converts it to a list,
    adds a number to the list elements if recurring.
    Eg. input list :['W','W','W','D','D','G','C','C','UTIL']
    o/p list: ['W1','W2','W3','D1','D2','G','C1','C2','UTIL']
    '''
    col_list = re.findall(" ?([A-Z]+) ", col)
    col_list2 = []
    for i in col_list:
        cnt = col_list.count(i)
        if cnt == 1:
            col_list2.append(i)
        if cnt > 1:
            if i in " ".join(col_list2):
                continue;
            col_list2 += [i+str(k) for k in range(1,cnt+1)] 
    return col_list2

df = pd.DataFrame(data=np.array([['C Mark Scheifele C Pierre-Luc Dubois UTIL Zach Parise W Mats Zuccarello W Oliver Bjorkstrand W Nick Foligno D Ryan Suter D Seth Jones G Devan Dubnyk'],['UTIL Kyle Connor C Pierre-Luc Dubois C Boone Jenner W Mats Zuccarello W Oliver Bjorkstrand W Nick Foligno D Ryan Suter D Seth Jones G Devan Dubnyk']]), columns=['Lineup'])
extr_row = df['Lineup'].replace(to_replace =" ?[A-Z]+ ", value="\n", regex = True) #split the rows on 

df_final = pd.DataFrame(columns = sorted(calc_col(df['Lineup'].iloc[0]))) #Create an empty data frame df3 with sorted columns

for i in range(len(extr_row)): #traverse all the rows in the original dataframe and append the formatted rows to df3
    df_temp = pd.DataFrame((extr_row.values[i].split("\n")[1:])).T
    df_temp.columns = calc_col(df['Lineup'].iloc[i])
    df_temp= df_temp[sorted(df_temp)]
    df_final = df_final.append(df_temp)
df_final.reset_index(drop = True, inplace = True)
df_final

请参阅下面的图片以获取最终数据帧。这适用于任何数量的行：