{"id":1099585,"date":"2025-01-08T15:32:04","date_gmt":"2025-01-08T07:32:04","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1099585.html"},"modified":"2025-01-08T15:32:08","modified_gmt":"2025-01-08T07:32:08","slug":"%e6%96%87%e4%bb%b6%e4%bf%9d%e5%ad%98%e5%bd%a2%e6%95%b0%e6%8d%ae%e9%9b%86-%e5%a6%82%e4%bd%95%e8%bd%bd%e5%85%a5python-2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1099585.html","title":{"rendered":"\u6587\u4ef6\u4fdd\u5b58\u5f62\u6570\u636e\u96c6 \u5982\u4f55\u8f7d\u5165python"},"content":{"rendered":"

\"\u6587\u4ef6\u4fdd\u5b58\u5f62\u6570\u636e\u96c6<\/p>\n

\u5f00\u5934\u6bb5\u843d: \u6587\u4ef6\u4fdd\u5b58\u5f62\u6570\u636e\u96c6\u7684\u8f7d\u5165\u65b9\u6cd5\u6709\u5f88\u591a\u79cd\u3001\u53ef\u4ee5\u901a\u8fc7\u4e0d\u540c\u7684\u5e93\u6765\u8f7d\u5165\u4e0d\u540c\u683c\u5f0f\u7684\u6570\u636e\u3001\u4f8b\u5982pandas\u3001numpy\u3001csv\u7b49\u3002<\/strong> \u5176\u4e2d\uff0cpandas\u5e93\u662f\u6700\u5e38\u7528\u7684\u5e93\u4e4b\u4e00\uff0c\u56e0\u4e3a\u5b83\u63d0\u4f9b\u4e86\u5f3a\u5927\u7684\u6570\u636e\u8bfb\u53d6\u548c\u5904\u7406\u529f\u80fd\u3002\u901a\u8fc7pandas\u5e93\uff0c\u6211\u4eec\u53ef\u4ee5\u65b9\u4fbf\u5730\u8f7d\u5165CSV\u3001Excel\u3001JSON\u7b49\u591a\u79cd\u683c\u5f0f\u7684\u6570\u636e\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528pandas\u5e93\u8f7d\u5165\u6587\u4ef6\u4fdd\u5b58\u5f62\u6570\u636e\u96c6\uff0c\u5e76\u5c55\u793a\u4e00\u4e9b\u5b9e\u7528\u7684\u4ee3\u7801\u793a\u4f8b\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u4f7f\u7528pandas\u8f7d\u5165CSV\u6587\u4ef6<\/h3>\n<\/p>\n

CSV\uff08Comma Separated Values\uff09\u6587\u4ef6\u662f\u6700\u5e38\u89c1\u7684\u6570\u636e\u6587\u4ef6\u683c\u5f0f\u4e4b\u4e00\u3002pandas\u5e93\u63d0\u4f9b\u4e86read_csv<\/code>\u51fd\u6570\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u8bfb\u53d6CSV\u6587\u4ef6\u3002<\/p>\n<\/p>\n

import pandas as pd<\/p>\n
\u8bfb\u53d6CSV\u6587\u4ef6<\/strong><\/h2>\n
data = pd.read_csv('path\/to\/your\/file.csv')<\/p>\n
\u67e5\u770b\u524d\u51e0\u884c\u6570\u636e<\/strong><\/h2>\n
print(data.head())<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u4f7f\u7528read_csv<\/code>\u51fd\u6570\u65f6\uff0c\u53ef\u4ee5\u901a\u8fc7\u53c2\u6570\u6307\u5b9a\u66f4\u591a\u9009\u9879\uff0c\u4f8b\u5982\u5206\u9694\u7b26\u3001\u7f16\u7801\u65b9\u5f0f\u3001\u662f\u5426\u5305\u542b\u8868\u5934\u7b49\u3002<\/p>\n<\/p>\n
data = pd.read_csv('path\/to\/your\/file.csv', sep=',', encoding='utf-8', header=0)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u4f7f\u7528pandas\u8f7d\u5165Excel\u6587\u4ef6<\/h3>\n<\/p>\n
Excel\u6587\u4ef6\u4e5f\u662f\u5e38\u89c1\u7684\u6570\u636e\u6587\u4ef6\u683c\u5f0f\u4e4b\u4e00\uff0cpandas\u5e93\u63d0\u4f9b\u4e86read_excel<\/code>\u51fd\u6570\u6765\u8bfb\u53d6Excel\u6587\u4ef6\u3002<\/p>\n<\/p>\n
# \u8bfb\u53d6Excel\u6587\u4ef6<\/p>\n
data = pd.read_excel('path\/to\/your\/file.xlsx')<\/p>\n
\u67e5\u770b\u524d\u51e0\u884c\u6570\u636e<\/strong><\/h2>\n
print(data.head())<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u540c\u6837\u5730\uff0c\u53ef\u4ee5\u901a\u8fc7\u53c2\u6570\u6307\u5b9a\u66f4\u591a\u9009\u9879\uff0c\u4f8b\u5982\u5de5\u4f5c\u8868\u540d\u79f0\u3001\u5217\u7d22\u5f15\u3001\u6570\u636e\u7c7b\u578b\u7b49\u3002<\/p>\n<\/p>\n
data = pd.read_excel('path\/to\/your\/file.xlsx', sheet_name='Sheet1', header=0, dtype={'Column1': str})<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u4f7f\u7528pandas\u8f7d\u5165JSON\u6587\u4ef6<\/h3>\n<\/p>\n
JSON\uff08JavaScript Object Notation\uff09\u662f\u4e00\u79cd\u8f7b\u91cf\u7ea7\u7684\u6570\u636e\u4ea4\u6362\u683c\u5f0f\uff0cpandas\u5e93\u63d0\u4f9b\u4e86read_json<\/code>\u51fd\u6570\u6765\u8bfb\u53d6JSON\u6587\u4ef6\u3002<\/p>\n<\/p>\n
# \u8bfb\u53d6JSON\u6587\u4ef6<\/p>\n
data = pd.read_json('path\/to\/your\/file.json')<\/p>\n
\u67e5\u770b\u524d\u51e0\u884c\u6570\u636e<\/strong><\/h2>\n
print(data.head())<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u53ef\u4ee5\u901a\u8fc7\u53c2\u6570\u6307\u5b9a\u66f4\u591a\u9009\u9879\uff0c\u4f8b\u5982JSON\u7684\u683c\u5f0f\u3001\u7f16\u7801\u65b9\u5f0f\u7b49\u3002<\/p>\n<\/p>\n
data = pd.read_json('path\/to\/your\/file.json', orient='records', encoding='utf-8')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u4f7f\u7528numpy\u8f7d\u5165\u6587\u672c\u6587\u4ef6<\/h3>\n<\/p>\n
\u5bf9\u4e8e\u4e00\u4e9b\u7b80\u5355\u7684\u6587\u672c\u6587\u4ef6\u6570\u636e\uff0c\u53ef\u4ee5\u4f7f\u7528numpy\u5e93\u7684loadtxt<\/code>\u51fd\u6570\u6765\u8bfb\u53d6\u3002<\/p>\n<\/p>\n
import numpy as np<\/p>\n
\u8bfb\u53d6\u6587\u672c\u6587\u4ef6<\/strong><\/h2>\n
data = np.loadtxt('path\/to\/your\/file.txt')<\/p>\n
\u67e5\u770b\u6570\u636e<\/strong><\/h2>\n
print(data)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u53ef\u4ee5\u901a\u8fc7\u53c2\u6570\u6307\u5b9a\u66f4\u591a\u9009\u9879\uff0c\u4f8b\u5982\u5206\u9694\u7b26\u3001\u6570\u636e\u7c7b\u578b\u3001\u8df3\u8fc7\u7684\u884c\u6570\u7b49\u3002<\/p>\n<\/p>\n
data = np.loadtxt('path\/to\/your\/file.txt', delimiter=',', dtype=float, skiprows=1)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u4f7f\u7528csv\u6a21\u5757\u8bfb\u53d6CSV\u6587\u4ef6<\/h3>\n<\/p>\n
Python\u7684csv\u6a21\u5757\u662f\u5185\u7f6e\u7684\u6807\u51c6\u5e93\uff0c\u53ef\u4ee5\u7528\u6765\u8bfb\u53d6\u548c\u5199\u5165CSV\u6587\u4ef6\u3002<\/p>\n<\/p>\n
import csv<\/p>\n
\u8bfb\u53d6CSV\u6587\u4ef6<\/strong><\/h2>\n
with open('path\/to\/your\/file.csv', newline='') as csvfile:<\/p>\n
    reader = csv.reader(csvfile)<\/p>\n
    for row in reader:<\/p>\n
        print(row)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u53ef\u4ee5\u901a\u8fc7\u53c2\u6570\u6307\u5b9a\u66f4\u591a\u9009\u9879\uff0c\u4f8b\u5982\u5206\u9694\u7b26\u3001\u5f15\u7528\u5b57\u7b26\u7b49\u3002<\/p>\n<\/p>\n
with open('path\/to\/your\/file.csv', newline='', encoding='utf-8') as csvfile:<\/p>\n
    reader = csv.reader(csvfile, delimiter=',', quotechar='"')<\/p>\n
    for row in reader:<\/p>\n
        print(row)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516d\u3001\u4f7f\u7528openpyxl\u8bfb\u53d6Excel\u6587\u4ef6<\/h3>\n<\/p>\n
openpyxl\u662f\u4e00\u4e2a\u53ef\u4ee5\u7528\u6765\u5904\u7406Excel\u6587\u4ef6\u7684\u7b2c\u4e09\u65b9\u5e93\uff0c\u652f\u6301\u8bfb\u53d6\u548c\u5199\u5165Excel\u6587\u4ef6\u3002<\/p>\n<\/p>\n
from openpyxl import load_workbook<\/p>\n
\u8bfb\u53d6Excel\u6587\u4ef6<\/strong><\/h2>\n
wb = load_workbook('path\/to\/your\/file.xlsx')<\/p>\n
sheet = wb.active<\/p>\n
\u67e5\u770b\u524d\u51e0\u884c\u6570\u636e<\/strong><\/h2>\n
for row in sheet.iter_rows(min_row=1, max_col=3, max_row=5, values_only=True):<\/p>\n
    print(row)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e03\u3001\u4f7f\u7528json\u6a21\u5757\u8bfb\u53d6JSON\u6587\u4ef6<\/h3>\n<\/p>\n
Python\u7684json\u6a21\u5757\u662f\u5185\u7f6e\u7684\u6807\u51c6\u5e93\uff0c\u53ef\u4ee5\u7528\u6765\u89e3\u6790\u548c\u751f\u6210JSON\u6570\u636e\u3002<\/p>\n<\/p>\n
import json<\/p>\n
\u8bfb\u53d6JSON\u6587\u4ef6<\/strong><\/h2>\n
with open('path\/to\/your\/file.json') as jsonfile:<\/p>\n
    data = json.load(jsonfile)<\/p>\n
\u67e5\u770b\u6570\u636e<\/strong><\/h2>\n
print(data)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516b\u3001\u7efc\u5408\u793a\u4f8b<\/h3>\n<\/p>\n
\u6700\u540e\uff0c\u6211\u4eec\u7ed3\u5408\u524d\u9762\u4ecb\u7ecd\u7684\u65b9\u6cd5\uff0c\u5c55\u793a\u4e00\u4e2a\u7efc\u5408\u793a\u4f8b\uff0c\u5982\u4f55\u5728\u5b9e\u9645\u9879\u76ee\u4e2d\u8f7d\u5165\u4e0d\u540c\u683c\u5f0f\u7684\u6570\u636e\u6587\u4ef6\u3002<\/p>\n<\/p>\n
import pandas as pd<\/p>\n
import numpy as np<\/p>\n
import csv<\/p>\n
from openpyxl import load_workbook<\/p>\n
import json<\/p>\n
\u8bfb\u53d6CSV\u6587\u4ef6<\/strong><\/h2>\n
csv_data = pd.read_csv('path\/to\/your\/file.csv')<\/p>\n
print("CSV Data:\\n", csv_data.head())<\/p>\n
\u8bfb\u53d6Excel\u6587\u4ef6<\/strong><\/h2>\n
excel_data = pd.read_excel('path\/to\/your\/file.xlsx')<\/p>\n
print("Excel Data:\\n", excel_data.head())<\/p>\n
\u8bfb\u53d6JSON\u6587\u4ef6<\/strong><\/h2>\n
with open('path\/to\/your\/file.json') as jsonfile:<\/p>\n
    json_data = json.load(jsonfile)<\/p>\n
print("JSON Data:\\n", json_data)<\/p>\n
\u8bfb\u53d6\u6587\u672c\u6587\u4ef6<\/strong><\/h2>\n
txt_data = np.loadtxt('path\/to\/your\/file.txt', delimiter=',', dtype=float, skiprows=1)<\/p>\n
print("Text Data:\\n", txt_data)<\/p>\n
\u8bfb\u53d6CSV\u6587\u4ef6\u4f7f\u7528csv\u6a21\u5757<\/strong><\/h2>\n
with open('path\/to\/your\/file.csv', newline='', encoding='utf-8') as csvfile:<\/p>\n
    reader = csv.reader(csvfile, delimiter=',', quotechar='"')<\/p>\n
    for row in reader:<\/p>\n
        print("CSV Row:", row)<\/p>\n
\u8bfb\u53d6Excel\u6587\u4ef6\u4f7f\u7528openpyxl<\/strong><\/h2>\n
wb = load_workbook('path\/to\/your\/file.xlsx')<\/p>\n
sheet = wb.active<\/p>\n
for row in sheet.iter_rows(min_row=1, max_col=3, max_row=5, values_only=True):<\/p>\n
    print("Excel Row:", row)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7\u4ee5\u4e0a\u4ecb\u7ecd\u548c\u793a\u4f8b\u4ee3\u7801\uff0c\u53ef\u4ee5\u770b\u51fa\uff0cPython\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u5e93\u548c\u51fd\u6570\u6765\u8f7d\u5165\u5404\u79cd\u6587\u4ef6\u4fdd\u5b58\u5f62\u6570\u636e\u96c6\u3002\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\u548c\u5de5\u5177\uff0c\u53ef\u4ee5\u5927\u5927\u63d0\u9ad8\u6570\u636e\u5904\u7406\u7684\u6548\u7387\u548c\u51c6\u786e\u6027\u3002\u5e0c\u671b\u8fd9\u7bc7\u6587\u7ae0\u5bf9\u4f60\u6709\u6240\u5e2e\u52a9\uff0c\u80fd\u591f\u5728\u5b9e\u9645\u9879\u76ee\u4e2d\u7075\u6d3b\u8fd0\u7528\u8fd9\u4e9b\u65b9\u6cd5\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u5728Python\u4e2d\u8bfb\u53d6\u6587\u4ef6\u4fdd\u5b58\u7684\u5f62\u6570\u636e\u96c6\uff1f<\/strong>
\u5728Python\u4e2d\uff0c\u8bfb\u53d6\u6587\u4ef6\u4fdd\u5b58\u7684\u5f62\u6570\u636e\u96c6\u901a\u5e38\u53ef\u4ee5\u4f7f\u7528pandas<\/code>\u5e93\u3002\u4f7f\u7528pandas.read_csv()<\/code>\u51fd\u6570\u53ef\u4ee5\u65b9\u4fbf\u5730\u8f7d\u5165CSV\u683c\u5f0f\u7684\u6570\u636e\u96c6\u3002\u800c\u5bf9\u4e8e\u5176\u4ed6\u683c\u5f0f\uff0c\u5982Excel\u6216JSON\uff0c\u5219\u53ef\u4ee5\u4f7f\u7528pandas.read_excel()<\/code>\u6216pandas.read_json()<\/code>\u3002\u786e\u4fdd\u5728\u8f7d\u5165\u4e4b\u524d\u5b89\u88c5\u76f8\u5e94\u7684\u5e93\uff0c\u5e76\u6839\u636e\u6587\u4ef6\u7684\u5b9e\u9645\u8def\u5f84\u548c\u6587\u4ef6\u540d\u8fdb\u884c\u8c03\u7528\u3002<\/p>\n
\u5728Python\u4e2d\u5904\u7406\u5927\u578b\u6570\u636e\u96c6\u65f6\u6709\u4ec0\u4e48\u5efa\u8bae\uff1f<\/strong>
\u5904\u7406\u5927\u578b\u6570\u636e\u96c6\u65f6\uff0c\u53ef\u4ee5\u8003\u8651\u4f7f\u7528dask<\/code>\u5e93\uff0c\u5b83\u80fd\u591f\u5904\u7406\u6bd4\u5185\u5b58\u8fd8\u5927\u7684\u6570\u636e\u96c6\uff0c\u5e76\u63d0\u4f9b\u4e0epandas<\/code>\u7c7b\u4f3c\u7684API\u3002\u6b64\u5916\uff0c\u4f7f\u7528chunksize<\/code>\u53c2\u6570\u5728pandas<\/code>\u7684\u8bfb\u53d6\u51fd\u6570\u4e2d\u5206\u6279\u8bfb\u53d6\u6570\u636e\u4e5f\u662f\u4e00\u4e2a\u6709\u6548\u7684\u7b56\u7565\uff0c\u4ee5\u51cf\u5c11\u5185\u5b58\u5360\u7528\u548c\u63d0\u9ad8\u6548\u7387\u3002<\/p>\n
\u5982\u4f55\u68c0\u67e5\u8f7d\u5165\u7684\u6570\u636e\u96c6\u662f\u5426\u6b63\u786e\uff1f<\/strong>
\u5728\u6210\u529f\u8f7d\u5165\u6570\u636e\u96c6\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528dataframe.head()<\/code>\u65b9\u6cd5\u67e5\u770b\u524d\u51e0\u884c\u6570\u636e\uff0c\u786e\u8ba4\u6570\u636e\u683c\u5f0f\u662f\u5426\u7b26\u5408\u9884\u671f\u3002\u540c\u65f6\uff0c\u4f7f\u7528dataframe.info()<\/code>\u53ef\u4ee5\u83b7\u53d6\u6570\u636e\u96c6\u7684\u603b\u4f53\u4fe1\u606f\uff0c\u5305\u62ec\u6570\u636e\u7c7b\u578b\u548c\u7f3a\u5931\u503c\u60c5\u51b5\uff0c\u8fd9\u6837\u80fd\u591f\u786e\u4fdd\u6570\u636e\u8f7d\u5165\u7684\u51c6\u786e\u6027\u548c\u5b8c\u6574\u6027\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5f00\u5934\u6bb5\u843d: \u6587\u4ef6\u4fdd\u5b58\u5f62\u6570\u636e\u96c6\u7684\u8f7d\u5165\u65b9\u6cd5\u6709\u5f88\u591a\u79cd\u3001\u53ef\u4ee5\u901a\u8fc7\u4e0d\u540c\u7684\u5e93\u6765\u8f7d\u5165\u4e0d\u540c\u683c\u5f0f\u7684\u6570\u636e\u3001\u4f8b\u5982pandas\u3001num […]","protected":false},"author":3,"featured_media":1099595,"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\/1099585"}],"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=1099585"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1099585\/revisions"}],"predecessor-version":[{"id":1099599,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1099585\/revisions\/1099599"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1099595"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1099585"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1099585"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1099585"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}