{"id":1133704,"date":"2025-01-08T21:08:59","date_gmt":"2025-01-08T13:08:59","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1133704.html"},"modified":"2025-01-08T21:09:02","modified_gmt":"2025-01-08T13:09:02","slug":"%e5%a6%82%e4%bd%95%e5%b0%86data%e6%96%87%e4%bb%b6%e5%af%bc%e5%85%a5%e5%88%b0python%e4%b8%ad","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1133704.html","title":{"rendered":"\u5982\u4f55\u5c06DATA\u6587\u4ef6\u5bfc\u5165\u5230python\u4e2d"},"content":{"rendered":"

\"\u5982\u4f55\u5c06DATA\u6587\u4ef6\u5bfc\u5165\u5230python\u4e2d\"<\/p>\n

\u5982\u4f55\u5c06DATA\u6587\u4ef6\u5bfc\u5165\u5230Python\u4e2d<\/strong><\/p>\n<\/p>\n

\u5bfc\u5165DATA\u6587\u4ef6\u5230Python\u4e2d\u6709\u591a\u79cd\u65b9\u6cd5\uff0c\u5305\u62ec\u4f7f\u7528pandas\u3001\u4f7f\u7528csv\u6a21\u5757\u3001\u4f7f\u7528numpy\u3001\u4f7f\u7528pickle\u6a21\u5757\u3002<\/strong> \u5728\u8fd9\u4e9b\u65b9\u6cd5\u4e2d\uff0c\u4f7f\u7528pandas\u662f\u6700\u4e3a\u5e38\u89c1\u548c\u63a8\u8350\u7684<\/strong>\uff0c\u56e0\u4e3a\u5b83\u4e0d\u4ec5\u652f\u6301\u591a\u79cd\u6587\u4ef6\u683c\u5f0f\uff0c\u800c\u4e14\u64cd\u4f5c\u7b80\u4fbf\u3001\u529f\u80fd\u5f3a\u5927\u3002\u4e0b\u9762\u6211\u4eec\u5c06\u5177\u4f53\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528\u8fd9\u4e9b\u65b9\u6cd5\u5bfc\u5165DATA\u6587\u4ef6\uff0c\u5e76\u8be6\u7ec6\u8bb2\u89e3\u5982\u4f55\u4f7f\u7528pandas\u8fdb\u884c\u6570\u636e\u5904\u7406\u3002<\/p>\n<\/p>\n

\n

\u4e00\u3001\u4f7f\u7528Pandas\u5bfc\u5165DATA\u6587\u4ef6<\/h3>\n<\/p>\n

Pandas\u662f\u4e00\u4e2a\u5f3a\u5927\u7684Python\u6570\u636e\u5206\u6790\u5e93\uff0c\u652f\u6301\u591a\u79cd\u6570\u636e\u683c\u5f0f\uff0c\u5305\u62ecCSV\u3001Excel\u3001SQL\u6570\u636e\u5e93\u7b49\u3002\u4f7f\u7528Pandas\u5bfc\u5165DATA\u6587\u4ef6\u7684\u6b65\u9aa4\u5982\u4e0b\uff1a<\/p>\n<\/p>\n

1\u3001\u5b89\u88c5\u548c\u5bfc\u5165Pandas<\/h4>\n<\/p>\n

\u9996\u5148\uff0c\u4f60\u9700\u8981\u786e\u4fdd\u5df2\u5b89\u88c5Pandas\u5e93\u3002\u5982\u679c\u672a\u5b89\u88c5\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n

pip install pandas<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u7136\u540e\uff0c\u5728Python\u811a\u672c\u4e2d\u5bfc\u5165Pandas\uff1a<\/p>\n<\/p>\n
import pandas as pd<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u8bfb\u53d6CSV\u6587\u4ef6<\/h4>\n<\/p>\n
\u5047\u8bbe\u4f60\u7684DATA\u6587\u4ef6\u662fCSV\u683c\u5f0f\uff0c\u53ef\u4ee5\u4f7f\u7528pd.read_csv()<\/code>\u51fd\u6570\u8bfb\u53d6\u6570\u636e\uff1a<\/p>\n<\/p>\n
data = pd.read_csv('path_to_your_file.csv')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u8fd9\u4e2a\u51fd\u6570\u4f1a\u8fd4\u56de\u4e00\u4e2aDataFrame\u5bf9\u8c61\uff0c\u5305\u542b\u4e86CSV\u6587\u4ef6\u4e2d\u7684\u6240\u6709\u6570\u636e\u3002<\/p>\n<\/p>\n
3\u3001\u8bfb\u53d6Excel\u6587\u4ef6<\/h4>\n<\/p>\n
\u5982\u679c\u4f60\u7684DATA\u6587\u4ef6\u662fExcel\u683c\u5f0f\uff0c\u53ef\u4ee5\u4f7f\u7528pd.read_excel()<\/code>\u51fd\u6570\uff1a<\/p>\n<\/p>\n
data = pd.read_excel('path_to_your_file.xlsx')<\/p>\n
<\/code><\/pre>\n<\/p>\n
4\u3001\u8bfb\u53d6SQL\u6570\u636e\u5e93<\/h4>\n<\/p>\n
Pandas\u8fd8\u53ef\u4ee5\u76f4\u63a5\u4eceSQL\u6570\u636e\u5e93\u4e2d\u8bfb\u53d6\u6570\u636e\uff0c\u9996\u5148\u9700\u8981\u5b89\u88c5SQLAlchemy\u5e93\uff1a<\/p>\n<\/p>\n
pip install sqlalchemy<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u7136\u540e\u4f7f\u7528\u4ee5\u4e0b\u4ee3\u7801\u8fde\u63a5\u5230\u6570\u636e\u5e93\u5e76\u8bfb\u53d6\u6570\u636e\uff1a<\/p>\n<\/p>\n
from sqlalchemy import create_engine<\/p>\n
engine = create_engine('sqlite:\/\/\/path_to_your_database.db')<\/p>\n
data = pd.read_sql('SELECT * FROM table_name', engine)<\/p>\n
<\/code><\/pre>\n<\/p>\n
5\u3001\u8bfb\u53d6JSON\u6587\u4ef6<\/h4>\n<\/p>\n
\u5982\u679cDATA\u6587\u4ef6\u662fJSON\u683c\u5f0f\uff0c\u53ef\u4ee5\u4f7f\u7528pd.read_json()<\/code>\u51fd\u6570\uff1a<\/p>\n<\/p>\n
data = pd.read_json('path_to_your_file.json')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u4f7f\u7528CSV\u6a21\u5757\u5bfc\u5165DATA\u6587\u4ef6<\/h3>\n<\/p>\n
Python\u5185\u7f6e\u7684csv\u6a21\u5757\u4e5f\u53ef\u4ee5\u7528\u6765\u8bfb\u53d6CSV\u6587\u4ef6\u3002\u867d\u7136\u529f\u80fd\u4e0d\u5982Pandas\u5f3a\u5927\uff0c\u4f46\u5728\u4e00\u4e9b\u7b80\u5355\u5e94\u7528\u4e2d\u4e5f\u975e\u5e38\u5b9e\u7528\u3002<\/p>\n<\/p>\n
1\u3001\u5bfc\u5165CSV\u6a21\u5757<\/h4>\n<\/p>\n
import csv<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u8bfb\u53d6CSV\u6587\u4ef6<\/h4>\n<\/p>\n
\u4f7f\u7528csv.reader()<\/code>\u51fd\u6570\u8bfb\u53d6CSV\u6587\u4ef6\uff1a<\/p>\n<\/p>\n
with open('path_to_your_file.csv', mode='r') as file:<\/p>\n
    csv_reader = csv.reader(file)<\/p>\n
    for row in csv_reader:<\/p>\n
        print(row)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u4f7f\u7528Numpy\u5bfc\u5165DATA\u6587\u4ef6<\/h3>\n<\/p>\n
Numpy\u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u6570\u503c\u8ba1\u7b97\u5e93\uff0c\u7279\u522b\u9002\u7528\u4e8e\u5904\u7406\u5927\u578b\u6570\u7ec4\u548c\u77e9\u9635\u3002\u4f60\u53ef\u4ee5\u4f7f\u7528Numpy\u8bfb\u53d6CSV\u6587\u4ef6\u3002<\/p>\n<\/p>\n
1\u3001\u5b89\u88c5\u548c\u5bfc\u5165Numpy<\/h4>\n<\/p>\n
\u9996\u5148\uff0c\u786e\u4fdd\u5df2\u5b89\u88c5Numpy\u5e93\uff1a<\/p>\n<\/p>\n
pip install numpy<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u7136\u540e\uff0c\u5728Python\u811a\u672c\u4e2d\u5bfc\u5165Numpy\uff1a<\/p>\n<\/p>\n
import numpy as np<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u8bfb\u53d6CSV\u6587\u4ef6<\/h4>\n<\/p>\n
\u4f7f\u7528np.loadtxt()<\/code>\u51fd\u6570\u8bfb\u53d6CSV\u6587\u4ef6\uff1a<\/p>\n<\/p>\n
data = np.loadtxt('path_to_your_file.csv', delimiter=',')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u4f7f\u7528Pickle\u6a21\u5757\u5bfc\u5165DATA\u6587\u4ef6<\/h3>\n<\/p>\n
Pickle\u6a21\u5757\u53ef\u4ee5\u5e8f\u5217\u5316\u548c\u53cd\u5e8f\u5217\u5316Python\u5bf9\u8c61\uff0c\u9002\u7528\u4e8e\u5b58\u50a8\u548c\u8bfb\u53d6Python\u6570\u636e\u7ed3\u6784\u3002<\/p>\n<\/p>\n
1\u3001\u5bfc\u5165Pickle\u6a21\u5757<\/h4>\n<\/p>\n
import pickle<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u8bfb\u53d6Pickle\u6587\u4ef6<\/h4>\n<\/p>\n
\u4f7f\u7528pickle.load()<\/code>\u51fd\u6570\u8bfb\u53d6Pickle\u6587\u4ef6\uff1a<\/p>\n<\/p>\n
with open('path_to_your_file.pkl', 'rb') as file:<\/p>\n
    data = pickle.load(file)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u4f7f\u7528\u5176\u4ed6\u65b9\u6cd5\u5bfc\u5165DATA\u6587\u4ef6<\/h3>\n<\/p>\n
\u9664\u4e86\u4e0a\u8ff0\u5e38\u7528\u65b9\u6cd5\u5916\uff0c\u8fd8\u6709\u4e00\u4e9b\u5176\u4ed6\u7684\u5e93\u548c\u65b9\u6cd5\u53ef\u4ee5\u7528\u6765\u5bfc\u5165DATA\u6587\u4ef6\uff0c\u5982openpyxl\u3001xlrd\u7b49\u3002<\/p>\n<\/p>\n
1\u3001\u4f7f\u7528Openpyxl\u8bfb\u53d6Excel\u6587\u4ef6<\/h4>\n<\/p>\n
Openpyxl\u5e93\u4e13\u95e8\u7528\u4e8e\u5904\u7406Excel\u6587\u4ef6\uff1a<\/p>\n<\/p>\n
from openpyxl import load_workbook<\/p>\n
workbook = load_workbook('path_to_your_file.xlsx')<\/p>\n
sheet = workbook.active<\/p>\n
data = [[cell.value for cell in row] for row in sheet.iter_rows()]<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u4f7f\u7528xlrd\u8bfb\u53d6Excel\u6587\u4ef6<\/h4>\n<\/p>\n
xlrd\u5e93\u4e5f\u662f\u4e00\u4e2a\u5904\u7406Excel\u6587\u4ef6\u7684\u5e93\uff1a<\/p>\n<\/p>\n
import xlrd<\/p>\n
workbook = xlrd.open_workbook('path_to_your_file.xls')<\/p>\n
sheet = workbook.sheet_by_index(0)<\/p>\n
data = [[sheet.cell_value(r, c) for c in range(sheet.ncols)] for r in range(sheet.nrows)]<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516d\u3001\u603b\u7ed3<\/h3>\n<\/p>\n
\u5bfc\u5165DATA\u6587\u4ef6\u5230Python\u4e2d\u662f\u6570\u636e\u5904\u7406\u7684\u7b2c\u4e00\u6b65\uff0c\u9009\u62e9\u5408\u9002\u7684\u5de5\u5177\u548c\u65b9\u6cd5\u53ef\u4ee5\u5927\u5927\u63d0\u9ad8\u6548\u7387\u3002Pandas\u662f\u6700\u4e3a\u63a8\u8350\u7684\u5de5\u5177<\/strong>\uff0c\u4e0d\u4ec5\u652f\u6301\u591a\u79cd\u6570\u636e\u683c\u5f0f\uff0c\u800c\u4e14\u64cd\u4f5c\u7b80\u4fbf\u3001\u529f\u80fd\u5f3a\u5927\u3002\u540c\u65f6\uff0cPython\u5185\u7f6e\u7684csv\u6a21\u5757\u3001Numpy\u548cPickle\u4e5f\u63d0\u4f9b\u4e86\u591a\u79cd\u9009\u62e9\uff0c\u9002\u7528\u4e8e\u4e0d\u540c\u7684\u5e94\u7528\u573a\u666f\u3002\u901a\u8fc7\u672c\u6587\u7684\u4ecb\u7ecd\uff0c\u5e0c\u671b\u4f60\u80fd\u627e\u5230\u9002\u5408\u81ea\u5df1\u9700\u6c42\u7684\u65b9\u6cd5\uff0c\u987a\u5229\u5b8c\u6210\u6570\u636e\u5bfc\u5165\u5de5\u4f5c\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u5728Python\u4e2d\u8bfb\u53d6DATA\u6587\u4ef6\u7684\u5185\u5bb9\uff1f<\/strong>
DATA\u6587\u4ef6\u901a\u5e38\u5305\u542b\u7ed3\u6784\u5316\u6216\u975e\u7ed3\u6784\u5316\u7684\u6570\u636e\uff0c\u8bfb\u53d6\u8fd9\u4e9b\u6587\u4ef6\u53ef\u4ee5\u4f7f\u7528Python\u5185\u7f6e\u7684\u6587\u4ef6\u64cd\u4f5c\u6216\u7279\u5b9a\u5e93\u3002\u53ef\u4ee5\u5229\u7528open()<\/code>\u51fd\u6570\u6765\u8bfb\u53d6\u6587\u4ef6\u5185\u5bb9\uff0c\u6216\u8005\u4f7f\u7528pandas<\/code>\u5e93\uff0c\u901a\u8fc7pd.read_csv()<\/code>\u7b49\u51fd\u6570\u6765\u8bfb\u53d6\u66f4\u4e3a\u590d\u6742\u7684\u6570\u636e\u6587\u4ef6\u3002\u786e\u4fdd\u5728\u8bfb\u53d6\u65f6\u6307\u5b9a\u6b63\u786e\u7684\u5206\u9694\u7b26\u548c\u7f16\u7801\u683c\u5f0f\u3002<\/p>\n
\u6709\u54ea\u4e9bPython\u5e93\u53ef\u4ee5\u5e2e\u52a9\u5bfc\u5165DATA\u6587\u4ef6\uff1f<\/strong>
\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528\u591a\u79cd\u5e93\u6765\u5bfc\u5165DATA\u6587\u4ef6\u3002pandas<\/code>\u662f\u6700\u5e38\u7528\u7684\u5e93\u4e4b\u4e00\uff0c\u9002\u5408\u5904\u7406\u8868\u683c\u6570\u636e\u3002\u5bf9\u4e8e\u6587\u672c\u6587\u4ef6\uff0ccsv<\/code>\u5e93\u4e5f\u5f88\u6709\u5e2e\u52a9\u3002\u82e5DATA\u6587\u4ef6\u662f\u4ee5JSON\u683c\u5f0f\u5b58\u50a8\u7684\uff0c\u53ef\u4ee5\u4f7f\u7528json<\/code>\u5e93\u8fdb\u884c\u89e3\u6790\u3002\u6b64\u5916\uff0cnumpy<\/code>\u5e93\u4e5f\u53ef\u4ee5\u7528\u4e8e\u8bfb\u53d6\u6570\u503c\u6570\u636e\uff0c\u7279\u522b\u662f\u5f53\u6587\u4ef6\u683c\u5f0f\u4e3a\u6570\u7ec4\u65f6\u3002<\/p>\n
\u5982\u4f55\u5904\u7406\u5bfc\u5165\u540e\u7684\u6570\u636e\u4ee5\u4fbf\u8fdb\u4e00\u6b65\u5206\u6790\uff1f<\/strong>
\u4e00\u65e6DATA\u6587\u4ef6\u88ab\u6210\u529f\u5bfc\u5165\u5230Python\u4e2d\uff0c\u53ef\u4ee5\u5bf9\u6570\u636e\u8fdb\u884c\u591a\u79cd\u5904\u7406\u3002\u5229\u7528pandas<\/code>\u5e93\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u8fdb\u884c\u6570\u636e\u6e05\u6d17\u3001\u7b5b\u9009\u3001\u5206\u7ec4\u548c\u805a\u5408\u7b49\u64cd\u4f5c\u3002\u4f7f\u7528matplotlib<\/code>\u6216seaborn<\/code>\u7b49\u53ef\u89c6\u5316\u5e93\uff0c\u53ef\u4ee5\u5c06\u6570\u636e\u53ef\u89c6\u5316\uff0c\u4ee5\u4fbf\u8fdb\u884c\u66f4\u6df1\u5165\u7684\u5206\u6790\u3002\u786e\u4fdd\u5728\u5206\u6790\u524d\uff0c\u68c0\u67e5\u6570\u636e\u7684\u5b8c\u6574\u6027\u548c\u51c6\u786e\u6027\uff0c\u4ee5\u907f\u514d\u6f5c\u5728\u7684\u95ee\u9898\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5982\u4f55\u5c06DATA\u6587\u4ef6\u5bfc\u5165\u5230Python\u4e2d \u5bfc\u5165DATA\u6587\u4ef6\u5230Python\u4e2d\u6709\u591a\u79cd\u65b9\u6cd5\uff0c\u5305\u62ec\u4f7f\u7528pandas\u3001\u4f7f\u7528 […]","protected":false},"author":3,"featured_media":1133710,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1133704"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=1133704"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1133704\/revisions"}],"predecessor-version":[{"id":1133712,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1133704\/revisions\/1133712"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1133710"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1133704"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1133704"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1133704"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}