{"id":1005001,"date":"2024-12-27T10:31:44","date_gmt":"2024-12-27T02:31:44","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1005001.html"},"modified":"2024-12-27T10:31:48","modified_gmt":"2024-12-27T02:31:48","slug":"python%e5%a6%82%e4%bd%95%e7%94%a8csv%e6%96%87%e4%bb%b6","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1005001.html","title":{"rendered":"python\u5982\u4f55\u7528csv\u6587\u4ef6"},"content":{"rendered":"

\"python\u5982\u4f55\u7528csv\u6587\u4ef6\"<\/p>\n

\u5728Python\u4e2d\u5904\u7406CSV\u6587\u4ef6\u662f\u4e00\u9879\u5e38\u89c1\u7684\u4efb\u52a1\uff0c\u5c24\u5176\u662f\u5728\u6570\u636e\u5206\u6790\u548c\u6570\u636e\u5904\u7406\u9886\u57df\u3002Python\u63d0\u4f9b\u4e86\u591a\u4e2a\u5e93\u6765\u5904\u7406CSV\u6587\u4ef6\uff0c\u5176\u4e2d\u5305\u62ec\u5185\u7f6e\u7684csv<\/code>\u6a21\u5757\u3001pandas<\/code>\u5e93\u7b49\u3002\u8981\u5728Python\u4e2d\u4f7f\u7528CSV\u6587\u4ef6\uff0c\u53ef\u4ee5\u901a\u8fc7\u5bfc\u5165csv\u6a21\u5757\u6765\u8bfb\u53d6\u548c\u5199\u5165CSV\u6587\u4ef6\u3001\u4f7f\u7528pandas\u5e93\u8fdb\u884c\u6570\u636e\u5206\u6790\u3001\u5904\u7406\u7f3a\u5931\u6570\u636e\u7b49\u3002<\/strong>\u4e0b\u9762\u6211\u4eec\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u8fd9\u4e9b\u65b9\u6cd5\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u4f7f\u7528CSV\u6a21\u5757\u8bfb\u53d6\u548c\u5199\u5165CSV\u6587\u4ef6<\/h2>\n<\/p>\n

1.1 \u4f7f\u7528CSV\u6a21\u5757\u8bfb\u53d6CSV\u6587\u4ef6<\/h3>\n<\/p>\n

Python\u5185\u7f6e\u7684csv<\/code>\u6a21\u5757\u63d0\u4f9b\u4e86\u8bfb\u53d6CSV\u6587\u4ef6\u7684\u529f\u80fd\uff0c\u4f7f\u7528\u65b9\u4fbf\u3002\u8981\u8bfb\u53d6CSV\u6587\u4ef6\uff0c\u53ef\u4ee5\u4f7f\u7528csv.reader<\/code>\u51fd\u6570\u3002\u4e0b\u9762\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u4f8b\u5b50\uff1a<\/p>\n<\/p>\n

import csv<\/p>\n
\u6253\u5f00CSV\u6587\u4ef6<\/strong><\/h2>\n
with open('example.csv', 'r') as csvfile:<\/p>\n
    csvreader = csv.reader(csvfile)<\/p>\n
    # \u8bfb\u53d6CSV\u6587\u4ef6\u7684\u8868\u5934<\/p>\n
    header = next(csvreader)<\/p>\n
    print(f'Header: {header}')<\/p>\n
    # \u8bfb\u53d6CSV\u6587\u4ef6\u7684\u6bcf\u4e00\u884c<\/p>\n
    for row in csvreader:<\/p>\n
        print(row)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528open<\/code>\u51fd\u6570\u6253\u5f00CSV\u6587\u4ef6\uff0c\u5e76\u4f7f\u7528csv.reader<\/code>\u8bfb\u53d6\u6587\u4ef6\u5185\u5bb9\u3002next(csvreader)<\/code>\u7528\u4e8e\u8bfb\u53d6\u6587\u4ef6\u7684\u8868\u5934\uff0c\u7136\u540e\u901a\u8fc7\u5faa\u73af\u904d\u5386\u6bcf\u4e00\u884c\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n
1.2 \u4f7f\u7528CSV\u6a21\u5757\u5199\u5165CSV\u6587\u4ef6<\/h3>\n<\/p>\n
\u5199\u5165CSV\u6587\u4ef6\u4e5f\u975e\u5e38\u7b80\u5355\uff0c\u53ef\u4ee5\u4f7f\u7528csv.writer<\/code>\u51fd\u6570\u3002\u4e0b\u9762\u662f\u4e00\u4e2a\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
import csv<\/p>\n
\u8981\u5199\u5165\u7684\u6570\u636e<\/strong><\/h2>\n
data = [<\/p>\n
    ['Name', 'Age', 'City'],<\/p>\n
    ['Alice', 30, 'New York'],<\/p>\n
    ['Bob', 25, 'Los Angeles'],<\/p>\n
    ['Charlie', 35, 'Chicago']<\/p>\n
]<\/p>\n
\u6253\u5f00CSV\u6587\u4ef6<\/strong><\/h2>\n
with open('output.csv', 'w', newline='') as csvfile:<\/p>\n
    csvwriter = csv.writer(csvfile)<\/p>\n
    # \u5199\u5165\u6570\u636e<\/p>\n
    for row in data:<\/p>\n
        csvwriter.writerow(row)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u5c06\u6570\u636e\u5199\u5165\u540d\u4e3aoutput.csv<\/code>\u7684\u6587\u4ef6\u4e2d\u3002newline=''<\/code>\u53c2\u6570\u7528\u4e8e\u907f\u514d\u5728Windows\u7cfb\u7edf\u4e2d\u51fa\u73b0\u7a7a\u884c\u7684\u95ee\u9898\u3002<\/p>\n<\/p>\n
\u4e8c\u3001\u4f7f\u7528Pandas\u5e93\u5904\u7406CSV\u6587\u4ef6<\/h2>\n<\/p>\n
2.1 \u4f7f\u7528Pandas\u8bfb\u53d6CSV\u6587\u4ef6<\/h3>\n<\/p>\n
Pandas\u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u6570\u636e\u5206\u6790\u5e93\uff0c\u63d0\u4f9b\u4e86\u66f4\u591a\u529f\u80fd\u6765\u5904\u7406CSV\u6587\u4ef6\u3002\u8981\u8bfb\u53d6CSV\u6587\u4ef6\uff0c\u53ef\u4ee5\u4f7f\u7528pandas.read_csv<\/code>\u51fd\u6570\uff1a<\/p>\n<\/p>\n
import pandas as pd<\/p>\n
\u8bfb\u53d6CSV\u6587\u4ef6<\/strong><\/h2>\n
df = pd.read_csv('example.csv')<\/p>\n
\u663e\u793a\u6570\u636e\u6846<\/strong><\/h2>\n
print(df)<\/p>\n
<\/code><\/pre>\n<\/p>\n
Pandas\u4f1a\u5c06CSV\u6587\u4ef6\u7684\u6570\u636e\u5b58\u50a8\u5728DataFrame\u4e2d\uff0cDataFrame\u662fPandas\u7684\u6838\u5fc3\u6570\u636e\u7ed3\u6784\uff0c\u7c7b\u4f3c\u4e8e\u7535\u5b50\u8868\u683c\u6216SQL\u8868\u3002<\/p>\n<\/p>\n
2.2 \u4f7f\u7528Pandas\u5199\u5165CSV\u6587\u4ef6<\/h3>\n<\/p>\n
Pandas\u8fd8\u53ef\u4ee5\u8f7b\u677e\u5730\u5c06DataFrame\u5199\u5165CSV\u6587\u4ef6\uff0c\u4f7f\u7528to_csv<\/code>\u65b9\u6cd5\uff1a<\/p>\n<\/p>\n
import pandas as pd<\/p>\n
\u521b\u5efa\u6570\u636e\u6846<\/strong><\/h2>\n
df = pd.DataFrame({<\/p>\n
    'Name': ['Alice', 'Bob', 'Charlie'],<\/p>\n
    'Age': [30, 25, 35],<\/p>\n
    'City': ['New York', 'Los Angeles', 'Chicago']<\/p>\n
})<\/p>\n
\u5199\u5165CSV\u6587\u4ef6<\/strong><\/h2>\n
df.to_csv('output.csv', index=False)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u8fd9\u91cc\uff0cindex=False<\/code>\u53c2\u6570\u7528\u4e8e\u907f\u514d\u5c06DataFrame\u7684\u7d22\u5f15\u5199\u5165CSV\u6587\u4ef6\u3002<\/p>\n<\/p>\n
\u4e09\u3001\u5904\u7406\u7f3a\u5931\u6570\u636e<\/h2>\n<\/p>\n
\u5728\u6570\u636e\u5904\u7406\u4e2d\uff0c\u7f3a\u5931\u6570\u636e\u662f\u4e00\u4e2a\u5e38\u89c1\u95ee\u9898\u3002Pandas\u63d0\u4f9b\u4e86\u591a\u79cd\u65b9\u6cd5\u6765\u5904\u7406\u7f3a\u5931\u6570\u636e\u3002<\/p>\n<\/p>\n
3.1 \u68c0\u67e5\u7f3a\u5931\u6570\u636e<\/h3>\n<\/p>\n
\u53ef\u4ee5\u4f7f\u7528isnull<\/code>\u65b9\u6cd5\u68c0\u67e5DataFrame\u4e2d\u7684\u7f3a\u5931\u6570\u636e\uff1a<\/p>\n<\/p>\n
import pandas as pd<\/p>\n
\u8bfb\u53d6CSV\u6587\u4ef6<\/strong><\/h2>\n
df = pd.read_csv('example.csv')<\/p>\n
\u68c0\u67e5\u7f3a\u5931\u6570\u636e<\/strong><\/h2>\n
print(df.isnull())<\/p>\n
<\/code><\/pre>\n<\/p>\n
3.2 \u586b\u5145\u7f3a\u5931\u6570\u636e<\/h3>\n<\/p>\n
\u53ef\u4ee5\u4f7f\u7528fillna<\/code>\u65b9\u6cd5\u586b\u5145\u7f3a\u5931\u6570\u636e\uff1a<\/p>\n<\/p>\n
# \u586b\u5145\u7f3a\u5931\u6570\u636e<\/p>\n
df_filled = df.fillna(0)<\/p>\n
print(df_filled)<\/p>\n
<\/code><\/pre>\n<\/p>\n
3.3 \u5220\u9664\u7f3a\u5931\u6570\u636e<\/h3>\n<\/p>\n
\u8fd8\u53ef\u4ee5\u4f7f\u7528dropna<\/code>\u65b9\u6cd5\u5220\u9664\u5305\u542b\u7f3a\u5931\u6570\u636e\u7684\u884c\uff1a<\/p>\n<\/p>\n
# \u5220\u9664\u7f3a\u5931\u6570\u636e<\/p>\n
df_dropped = df.dropna()<\/p>\n
print(df_dropped)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u6570\u636e\u8fc7\u6ee4\u548c\u9009\u62e9<\/h2>\n<\/p>\n
Pandas\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u529f\u80fd\u6765\u8fc7\u6ee4\u548c\u9009\u62e9\u6570\u636e\u3002<\/p>\n<\/p>\n
4.1 \u9009\u62e9\u7279\u5b9a\u5217<\/h3>\n<\/p>\n
\u53ef\u4ee5\u4f7f\u7528\u5217\u540d\u9009\u62e9\u7279\u5b9a\u7684\u5217\uff1a<\/p>\n<\/p>\n
# \u9009\u62e9\u7279\u5b9a\u5217<\/p>\n
names = df['Name']<\/p>\n
print(names)<\/p>\n
<\/code><\/pre>\n<\/p>\n
4.2 \u8fc7\u6ee4\u6570\u636e<\/h3>\n<\/p>\n
\u53ef\u4ee5\u6839\u636e\u6761\u4ef6\u8fc7\u6ee4\u6570\u636e\uff1a<\/p>\n<\/p>\n
# \u8fc7\u6ee4\u5e74\u9f84\u5927\u4e8e30\u7684\u6570\u636e<\/p>\n
filtered_data = df[df['Age'] > 30]<\/p>\n
print(filtered_data)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u6570\u636e\u5206\u7ec4\u548c\u805a\u5408<\/h2>\n<\/p>\n
Pandas\u5141\u8bb8\u5bf9\u6570\u636e\u8fdb\u884c\u5206\u7ec4\u548c\u805a\u5408\u5206\u6790\u3002<\/p>\n<\/p>\n
5.1 \u6570\u636e\u5206\u7ec4<\/h3>\n<\/p>\n
\u53ef\u4ee5\u4f7f\u7528groupby<\/code>\u65b9\u6cd5\u5bf9\u6570\u636e\u8fdb\u884c\u5206\u7ec4\uff1a<\/p>\n<\/p>\n
# \u6309\u57ce\u5e02\u5206\u7ec4<\/p>\n
grouped = df.groupby('City')<\/p>\n
\u6253\u5370\u6bcf\u4e2a\u7ec4\u7684\u5927\u5c0f<\/strong><\/h2>\n
print(grouped.size())<\/p>\n
<\/code><\/pre>\n<\/p>\n
5.2 \u6570\u636e\u805a\u5408<\/h3>\n<\/p>\n
\u53ef\u4ee5\u4f7f\u7528\u805a\u5408\u51fd\u6570\u5bf9\u5206\u7ec4\u6570\u636e\u8fdb\u884c\u805a\u5408\uff1a<\/p>\n<\/p>\n
# \u8ba1\u7b97\u6bcf\u4e2a\u57ce\u5e02\u7684\u5e73\u5747\u5e74\u9f84<\/p>\n
mean_age = grouped['Age'].mean()<\/p>\n
print(mean_age)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516d\u3001\u6570\u636e\u53ef\u89c6\u5316<\/h2>\n<\/p>\n
\u867d\u7136Pandas\u672c\u8eab\u4e0d\u662f\u4e00\u4e2a\u6570\u636e\u53ef\u89c6\u5316\u5e93\uff0c\u4f46\u5b83\u53ef\u4ee5\u5f88\u65b9\u4fbf\u5730\u4e0eMatplotlib\u7ed3\u5408\u4f7f\u7528\u3002<\/p>\n<\/p>\n
6.1 \u4f7f\u7528Matplotlib\u8fdb\u884c\u53ef\u89c6\u5316<\/h3>\n<\/p>\n
import matplotlib.pyplot as plt<\/p>\n
\u7ed8\u5236\u67f1\u72b6\u56fe<\/strong><\/h2>\n
df['Age'].plot(kind='bar')<\/p>\n
plt.show()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u60a8\u53ef\u4ee5\u4f7f\u7528Python\u9ad8\u6548\u5730\u5904\u7406CSV\u6587\u4ef6\u3002\u4ece\u7b80\u5355\u7684\u8bfb\u53d6\u548c\u5199\u5165\uff0c\u5230\u590d\u6742\u7684\u6570\u636e\u5206\u6790\u548c\u53ef\u89c6\u5316\uff0cPython\u548c\u5b83\u7684\u5e93\u63d0\u4f9b\u4e86\u5f3a\u5927\u7684\u5de5\u5177\u6765\u6ee1\u8db3\u5404\u79cd\u9700\u6c42\u3002\u65e0\u8bba\u662f\u521d\u5b66\u8005\u8fd8\u662f\u7ecf\u9a8c\u4e30\u5bcc\u7684\u6570\u636e\u79d1\u5b66\u5bb6\uff0c\u90fd\u53ef\u4ee5\u4ece\u4e2d\u53d7\u76ca\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u5728Python\u4e2d\u8bfb\u53d6CSV\u6587\u4ef6\uff1f<\/strong>
\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528\u5185\u7f6e\u7684csv<\/code>\u6a21\u5757\u6765\u8bfb\u53d6CSV\u6587\u4ef6\u3002\u9996\u5148\uff0c\u60a8\u9700\u8981\u5bfc\u5165\u8be5\u6a21\u5757\uff0c\u7136\u540e\u4f7f\u7528csv.reader()<\/code>\u51fd\u6570\u6253\u5f00\u6587\u4ef6\u5e76\u9010\u884c\u8bfb\u53d6\u6570\u636e\u3002\u4f8b\u5982\uff1a<\/p>\n
import csv\n\nwith open('yourfile.csv', mode='r') as file:\n    csv_reader = csv.reader(file)\n    for row in csv_reader:\n        print(row)\n<\/code><\/pre>\n
\u8fd9\u79cd\u65b9\u5f0f\u4f1a\u5c06\u6bcf\u4e00\u884c\u6570\u636e\u4f5c\u4e3a\u5217\u8868\u8fd4\u56de\uff0c\u4f7f\u5f97\u60a8\u53ef\u4ee5\u65b9\u4fbf\u5730\u8bbf\u95ee\u6bcf\u4e2a\u5b57\u6bb5\u3002<\/p>\n
\u5982\u4f55\u5728Python\u4e2d\u5199\u5165CSV\u6587\u4ef6\uff1f<\/strong>
\u8981\u5c06\u6570\u636e\u5199\u5165CSV\u6587\u4ef6\uff0c\u60a8\u540c\u6837\u53ef\u4ee5\u4f7f\u7528csv<\/code>\u6a21\u5757\u3002\u4f7f\u7528csv.writer()<\/code>\u51fd\u6570\u53ef\u4ee5\u5c06\u6570\u636e\u9010\u884c\u5199\u5165\u6587\u4ef6\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u793a\u4f8b\uff1a<\/p>\n
import csv\n\ndata = [['Name', 'Age', 'City'],\n        ['Alice', 30, 'New York'],\n        ['Bob', 25, 'Los Angeles']]\n\nwith open('output.csv', mode='w', newline='') as file:\n    csv_writer = csv.writer(file)\n    csv_writer.writerows(data)\n<\/code><\/pre>\n
\u8fd9\u6bb5\u4ee3\u7801\u5c06\u521b\u5efa\u4e00\u4e2a\u65b0\u7684CSV\u6587\u4ef6\uff0c\u5e76\u5c06\u7ed9\u5b9a\u7684\u6570\u636e\u5199\u5165\u5176\u4e2d\u3002<\/p>\n
\u5982\u4f55\u5904\u7406CSV\u6587\u4ef6\u4e2d\u7684\u7f3a\u5931\u503c\uff1f<\/strong>
\u5904\u7406CSV\u6587\u4ef6\u4e2d\u7684\u7f3a\u5931\u503c\u53ef\u4ee5\u901a\u8fc7\u591a\u79cd\u65b9\u5f0f\u8fdb\u884c\u3002\u5728\u8bfb\u53d6CSV\u6587\u4ef6\u65f6\uff0c\u53ef\u4ee5\u4f7f\u7528pandas<\/code>\u5e93\uff0c\u5b83\u63d0\u4f9b\u4e86\u66f4\u5f3a\u5927\u7684\u6570\u636e\u5904\u7406\u529f\u80fd\u3002\u4ee5\u4e0b\u662f\u5982\u4f55\u4f7f\u7528pandas<\/code>\u5904\u7406\u7f3a\u5931\u503c\u7684\u793a\u4f8b\uff1a<\/p>\n
import pandas as pd\n\ndf = pd.read_csv('yourfile.csv')\ndf.fillna('N\/A', inplace=True)  # \u5c06\u7f3a\u5931\u503c\u66ff\u6362\u4e3a'N\/A'\nprint(df)\n<\/code><\/pre>\n
\u4f7f\u7528pandas<\/code>\u53ef\u4ee5\u8f7b\u677e\u5730\u586b\u5145\u6216\u5220\u9664\u7f3a\u5931\u503c\uff0c\u5e76\u8fdb\u884c\u66f4\u590d\u6742\u7684\u6570\u636e\u5206\u6790\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5728Python\u4e2d\u5904\u7406CSV\u6587\u4ef6\u662f\u4e00\u9879\u5e38\u89c1\u7684\u4efb\u52a1\uff0c\u5c24\u5176\u662f\u5728\u6570\u636e\u5206\u6790\u548c\u6570\u636e\u5904\u7406\u9886\u57df\u3002Python\u63d0\u4f9b\u4e86\u591a\u4e2a\u5e93\u6765\u5904\u7406 […]","protected":false},"author":3,"featured_media":1005007,"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\/1005001"}],"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=1005001"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1005001\/revisions"}],"predecessor-version":[{"id":1005010,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1005001\/revisions\/1005010"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1005007"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1005001"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1005001"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1005001"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}