使用pandas从excel工作表列创建字典

Question

我试图解析包含n个.xslx文件的目录，并创建一个.py文件，该文件只是前两列的字典，但我遇到了这样的问题:使用代码，它只附加目录中2个工作簿的第一个工作表。以下是我到目前为止编写的代码

import os
import xlrd
import pandas as pd
import pprint
import json

pp = pprint.PrettyPrinter(indent=4)

def get_did(xlsx, dbd):
    dbd = pd.read_excel(xlsx, index_col=0, usecols="A,B").to_dict()
    with open("db.py", 'a', newline='') as f:
        json.dump(dbd, f, sort_keys=True, indent=4)

path = os.getcwd()
filenames = os.listdir(path)

dbd = {}

for filename in filenames:
    if filename.endswith('.xlsx'):
        get_did(filename, dbd)

print(dbd)

我正在处理的数据在第一列中只有一个ID号，在第二列中有一个描述字符串，因此输出如下所示

{
    "Description": {
        "1": "45KV Suspension Polymer-DE",
        "2": "45KV Post Tie Polymer",
        "3": "45KV Post Vert SAC Polymer",
        "4": "45KV Post Hor SAC Polymer",
        "5": "35KV Post Tie",
        "6": "35KV Post Vertical SAC",
        "7": "45KV Post Vertical SAC",
        "8": "35KV Post Horizontal SAC",
                ...
        "72": "69KV Post Hor LAC Polymer",
        "73": "69KV Post Vert LAC Polymer",
        "74": "69KV Post Vert LAC Poly-Dbl",
        "75": "15KV Suspension Polymer",
        "76": "15KV Suspension Polymer-DE"
    }
}{
    "Size": {
        "1": "1/4\" EHS",
        "2": "5/16\" EHS",
        "3": "7/16\" EHS",
        "4": "9/16\" EHS",
        "5": "1/2\" AW",
        "6": "3#7 HS CW",
        "7": "7#8 HS CW",
        "8": "7#6 EHS CW",
        "9": "19#9 EHS CW",
        "10": "1/4\" GLV (3#7)"
    }
}

Answer 1

基本思想如下，你可以输出任何你喜欢的格式，但最常见的类型是'.csv'，'.txt‘或excel：

import os
import pandas as pd

path =os.chdir(r"yourdirectory")     
datalist=[]
mydict = {}

for file in os.listdir():
    filelist = [f for f in os.listdir() if f.endswith("xlsx")]

for fs in filelist:    
    df = pd.read_excel(fs, sep = '\t') 

    datalist.append(df)

alldata = pd.concat(datalist)
mydict = dict(zip(alldata[alldata.columns[0]], alldata[alldata.columns[1]]))

print(mydict)