在 Pandas 中使用 Dictionary 进行 VLookup（然后替换）？

Question

我想用字典替换 Pandas 数据框中的值

DataFrame = games-u-q-s.csv：

blue1   blue2   blue3   blue4   blue5   red1    red2    red3    red4    red5    winner
8       432     96      11      112     104     498     122     238     412     0
119     39      76      10      35      54      25      120     157     92      0
57      63      29      61      36      90      19      412     92      22      0

第 1 - 10 列包含以 winner 列作为标签的 champId

字典 = champNum.csv

champId champNum
266     1
103     2
84      3
12      4
32      5
34      6
1       7
.       .
.       .
143     138

并将其另存为dataset_feature_champion_number.csv

我想将champId 转换为champNum 并期望输出如下：

blue1   blue2   blue3   blue4   blue5   red1    red2    red3    red4    red5    winner
125     11      59      70      124     36      129     20      135     111     0
23      40      77      53      95      67      73      37      132     91      0
69      13      116     81      22      68      127     111     91      8       0

这是代码：

import csv
import os
import numpy as np
import pandas as pd

def createDictionary(csvfile):
    with open(csvfile, mode='r') as data:
        reader = csv.reader(data)
        dict = {int(rows[0]):int(rows[1]) for rows in reader}

    return dict

def convertDataframeToChampNum(csvfile,dictionary):
    df = pd.read_csv(csvfile)
    temp1 = df.iloc[:,1:11]
    temp2 = df['winner']
    temp3 = temp1.applymap(dictionary.get)
    champNum = temp3.join(temp2)
    return champNum

def saveAsCSV(dataframe):
    dataframe.to_csv("dataset_feature_champion_number.csv")

def main():
    diction = createDictionary("champNum.csv")
    dataset = convertDataframeToChampNum("games-u-q-s.csv",diction)
    saveAsCSV(dataset)

if __name__ =='__main__':
    main()

我遇到了很多错误：

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-19-f86679fc49f9> in <module>()
     27 
     28 if __name__ =='__main__':
---> 29     main()

<ipython-input-19-f86679fc49f9> in main()
     22 
     23 def main():
---> 24     diction = createDictionary("champNum.csv")
     25     dataset = convertDataframeToChampNum("games-u-q-s.csv",diction)
     26     saveAsCSV(dataset)

<ipython-input-19-f86679fc49f9> in createDictionary(csvfile)
      7     with open(csvfile, mode='r') as data:
      8         reader = csv.reader(data)
----> 9         dict = {int(rows[0]):int(rows[1]) for rows in reader}
     10     return dict
     11 

<ipython-input-19-f86679fc49f9> in <dictcomp>(.0)
      7     with open(csvfile, mode='r') as data:
      8         reader = csv.reader(data)
----> 9         dict = {int(rows[0]):int(rows[1]) for rows in reader}
     10     return dict
     11 

ValueError: invalid literal for int() with base 10: 'champNum'

Answer 1

我想你在找pandas.DataFrame.transform：

>>> a = pd.DataFrame([[1,2,3,4,5],[6,7,8,9,10]])
>>> a
   0  1  2  3   4
0  1  2  3  4   5
1  6  7  8  9  10
>>> a.transform(lambda x: -x)
   0  1  2  3   4
0 -1 -2 -3 -4  -5
1 -6 -7 -8 -9 -10

或者，应用于您的问题

df = pd.DataFrame({'blue1': [8,  119,  57], 
                   'blue2': [432,  39,  63], 
                   'blue3': [96,  76,  29], 
                   'blue4': [11,  10,  61], 
                   'blue5': [112,  35,  36], 
                   'red1': [104,  54,  90], 
                   'red2': [498,  25,  19], 
                   'red3': [122,  120,  412], 
                   'red4': [238,  157,  92], 
                   'red5': [412,  92,  22], 
                   'winner': [0,  0,  0]})
transform_dict = {266: 1, 103: 2, ...}
df.transform(lambda x: transform_dict[x] if x in transform_dict else None)