Python:Regex或Dictionary

Question

我有一个DataFrame列，其中有一个要解析的长字符串。我对regex是新手，还没有使用过它。下面我只返回了我的名字。。充其量。我想知道正则表达式解析这个字符串或创建字典进行迭代是否更容易。这是我目前的情况。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，就像下面这样

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

df['C1'] = Mark Scheifeledf['C2'] = Pierre-Luc Duboisdf['W1'] = Mats Zuccarellodf['W2'] = Oliver Bjorkstranddf['W3'] = Nick Folignodf['D1'] = Ryan Suterdf['D2'] = Seth Jonesdf['G']= Devan Dubnykdf['UTIL'] = Zach Parise

结果数据帧 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

此版本将使您能够拥有随机顺序、长度（不同的ids计数）以及更多。但是，它依赖于完全大写的单词是id的指示符

import pandas as pd

def get_df(string):

    result = [[key, f"{string[i + 1]} {string[i + 2]}"] for i, key in enumerate(string) if key.isupper()]

    occurs = {}

    for data in result:
        if data[0] not in occurs:
            occurs[data[0]] = 1
            data[0] = f"{data[0]}1"
        else:
            occurs[data[0]] += 1
            data[0] = f"{data[0]}{occurs[data[0]]}"

    return pd.DataFrame(data=[[i[1] for i in result]], columns=[i[0] for i in result])

data = ['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']


for i in data:
    print(get_df(i.split()))

如果希望将返回的数据帧附加在一起，请尝试此操作，希望返回的数据与目标数据相同

df = pd.DataFrame()

for i in data:
    df = df.append(get_df(i.split()))
    print(get_df(i.split()))


                  C1                 C2          D1          D2            G1        UTIL1               W1                  W2            W3
0     Mark Scheifele  Pierre-Luc Dubois  Ryan Suter  Seth Jones  Devan Dubnyk  Zach Parise  Mats Zuccarello  Oliver Bjorkstrand  Nick Foligno
0  Pierre-Luc Dubois       Boone Jenner  Ryan Suter  Seth Jones  Devan Dubnyk  Kyle Connor  Mats Zuccarello  Oliver Bjorkstrand  Nick Foligno

Answer 2

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

最后的数据帧请参见下图。这适用于任意数量的行：