Python:正则表达式或字典

Question

我有一个 DataFrame 列，其中有一个我想要解析的长字符串。我是正则表达式的新手，还没有使用过它。我下面的内容最多只返回名字。我想知道对于正则表达式来说解析这个字符串是否更容易，或者创建一个字典来迭代是否更容易。这是我现在所拥有的。顺序并不总是相同的(C、W、D、G、UTIL)，我将编写一个 for 循环来迭代多行，就像这一个一样。

import pandas as pd
import numpy as np
import re

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'])

df['C1'] = re.findall(r" C \w+",str(df['Lineup']))
df['C2'] = re.findall(r'C \w+',str(df['Lineup']))
df['W1'] = re.findall(r'W \w+',str(df['Lineup']))
df['W2'] = re.findall(r'W \w+',str(df['Lineup']))
df['W3'] = re.findall(r'W \w+',str(df['Lineup']))
df['D1'] = re.findall(r'D \w+',str(df['Lineup']))
df['D1'] = re.findall(r'D \w+',str(df['Lineup']))
df['G']= re.findall(r'G \w+',str(df['Lineup']))
df['UTIL'] = re.findall(r'UTIL \w+',str(df['Lineup']))

我正在寻找将这些值存储到 DF 中的方法。

df['C1'] = Mark Scheifele df['C2'] = Pierre-Luc Dubois df['W1'] = Mats Zuccarello df['W2'] = Oliver Bjorkstrand df['W3'] = Nick Foligno df['D1'] = Ryan Suter df['D2'] = Seth Jones df['G']= Devan Dubnyk df['UTIL'] = Zach Parise

结果数据框 df_result = pd.DataFrame(data=np.array([['Mark Scheifele','Pierre-Luc Dubois','Mats Zuccarello','Oliver Bjorkstrand','Nick Foligno','Ryan Suter','Seth Jones','Devan Dubnyk','Zach Parise'],['Boone Jenner','Pierre-Luc Dubois','Mats Zuccarello','Oliver Bjorkstrand','Nick Foligno','Ryan Suter','Seth Jones','Devan Dubnyk','Kyle Connor']]), columns=['C1','C2','W1','W2','W3','D1','D2','G','UTIL'])

Answer 1

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

最终数据框请参见下图。这应该适用于任意数量的行: