通过名称列表 [] 或逗号分隔选择或匹配特定列

Question

我有一个目录；在这个目录里面有很多不同的扩展文件的子文件夹，所以我只想读取 xlsx 文件，然后我想通过指定名称来匹配列。喜欢使用列表 [] 或逗号分隔条件。然后我想从我指定的列中获取内容。有些文件只有一张，有些有两张。所有文件的列中的名称都相同。但内容不同。所以，我需要帮助让代码通过文件并仅搜索应在代码中指定的列名，然后将它们组合到一个 xlsx 文件 output.xlsx

import pandas as pd
import numpy as np
import os
import xlrd
from xlrd import open_workbook
import sys
import xlsxwriter as xlsw
#import shutil

dataframes = []

path = r'C:\Users\malotaibi\Documents\mofaq', for root, subdirs, files in os.walk(path):,for file in files:, if file.endswith(".xlsx"):,f = (os.path.join(root, file)),print(f),dataframes.append(f),all_data = pd.DataFrame (),for f in dataframes:,dataframes = pd.read_excel(f, sheet_name=None) ,print(dataframes),list = dataframes[['Id', 'Original id', 'Name', 'Logic/Query', 'Comments']], collection= [list],join = pd.concat(collection),join.to_excel("output.xlsx")

Traceback（最近一次调用最后一次）：文件 “C:\Users\malotaibi\Desktop\dd.py”，第 39 行，在 list = dataframes[['Id', 'Original id', 'Name', 'Logic/Query', 'Comments']] TypeError: unhashable type: 'list'

Answer 1

您的代码可能是：

import pandas as pd
import numpy as np
import os
import xlrd
from xlrd import open_workbook
import sys
import xlsxwriter as xlsw
#import shutil

dataframes = []

path = r'C:\Users\malotaibi\Documents\mofaq'
for root, subdirs, files in os.walk(path):
    for file in files:
        if file.endswith(".xlsx"):
            f = (os.path.join(root, file))
            print(f)
            dataframes.append(f)
all_data = pd.DataFrame ()
for f in dataframes:
    dataframes = pd.read_excel(f, sheet_name=None)
    print(dataframes)
    list = dataframes[['Id', 'Original id', 'Name', 'Logic/Query', 'Comments']]
    collection= [list]
    join = pd.concat(collection)
    join.to_excel("output.xlsx")

试试这个：

import pandas as pd
import numpy as np
import os
import xlrd
from xlrd import open_workbook
import sys
import xlsxwriter as xlsw
#import shutil

dataframes = []

path = r'C:\Users\jainil\Documents'
for root, subdirs, files in os.walk(path):
    for file in files:
        if file.endswith(".xlsx"):
            f = (os.path.join(root, file))
            print(f)
            dataframes.append(f)
all_data = pd.DataFrame ()
for f in dataframes:
    dataframes = pd.read_excel(f, sheet_name=None)
    print(dataframes)
    list = dataframes['Sheet1']
    list=list['Id', 'Original id', 'Name', 'Logic/Query', 'Comments']
    collection= [list]
    join = pd.concat(collection)
    join.to_excel("output.xlsx")
    print(join)

所以你可以试试：

import pandas as pd
import numpy as np
import os
import xlrd
from xlrd import open_workbook
import sys
import xlsxwriter as xlsw
#import shutil

dataframes = []

path = r'C:\Users\jainil\Documents'
for root, subdirs, files in os.walk(path):
    for file in files:
        if file.endswith(".xlsx"):
            f = (os.path.join(root, file))
            print(f)
            dataframes.append(f)
all_data = pd.DataFrame ()
join=pd.DataFrame(columns=['Id', 'Original id', 'Name', 'Logic/Query', 'Comments'])
for f in dataframes:
    dataframes = pd.read_excel(f, sheet_name=None)
    print(dataframes)
    list = dataframes['Sheet1']
    list=list['Id', 'Original id', 'Name', 'Logic/Query', 'Comments']
    collection= [list]
    join = pd.concat(join,collection)


join.to_excel("output.xlsx")
print(join)