{"id":1107752,"date":"2025-01-08T16:53:02","date_gmt":"2025-01-08T08:53:02","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1107752.html"},"modified":"2025-01-08T16:53:05","modified_gmt":"2025-01-08T08:53:05","slug":"python%e5%a6%82%e4%bd%95%e5%b0%86%e4%b8%a4%e4%b8%aacsv%e5%90%88%e5%b9%b6","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1107752.html","title":{"rendered":"python\u5982\u4f55\u5c06\u4e24\u4e2acsv\u5408\u5e76"},"content":{"rendered":"

\"python\u5982\u4f55\u5c06\u4e24\u4e2acsv\u5408\u5e76\"<\/p>\n

Python\u5c06\u4e24\u4e2aCSV\u6587\u4ef6\u5408\u5e76\u7684\u65b9\u6cd5\u6709\u591a\u79cd\uff0c\u53ef\u4ee5\u4f7f\u7528pandas\u5e93\u8fdb\u884c\u6570\u636e\u5904\u7406\u3001\u7ed3\u5408\u76f8\u540c\u5217\u540d\u3001\u6309\u884c\u5408\u5e76\u7b49\u65b9\u5f0f\u3002<\/strong>\u9996\u5148\u9700\u8981\u786e\u4fdd\u4e24\u4e2aCSV\u6587\u4ef6\u7684\u7ed3\u6784\u548c\u6570\u636e\u7c7b\u578b\u517c\u5bb9\uff0c\u7136\u540e\u53ef\u4ee5\u4f7f\u7528pandas\u5e93\u7684\u5404\u79cd\u65b9\u6cd5\u6765\u5408\u5e76\u6570\u636e\u3002\u63a5\u4e0b\u6765\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u8fd9\u4e9b\u65b9\u6cd5\uff0c\u5e76\u63d0\u4f9b\u4ee3\u7801\u793a\u4f8b\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u4f7f\u7528pandas\u8bfb\u53d6CSV\u6587\u4ef6<\/h3>\n<\/p>\n

\u5728\u5408\u5e76CSV\u6587\u4ef6\u4e4b\u524d\uff0c\u6211\u4eec\u9700\u8981\u5148\u7528pandas\u8bfb\u53d6CSV\u6587\u4ef6\uff0cpandas\u662f\u4e00\u4e2a\u975e\u5e38\u5f3a\u5927\u7684\u6570\u636e\u5904\u7406\u5e93\uff0c\u80fd\u591f\u65b9\u4fbf\u5730\u8bfb\u53d6\u3001\u64cd\u4f5c\u548c\u4fdd\u5b58\u6570\u636e\u3002<\/p>\n<\/p>\n

import pandas as pd<\/p>\n
\u8bfb\u53d6CSV\u6587\u4ef6<\/strong><\/h2>\n
df1 = pd.read_csv('file1.csv')<\/p>\n
df2 = pd.read_csv('file2.csv')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u6309\u884c\u5408\u5e76\uff08\u7eb5\u5411\u5408\u5e76\uff09<\/h3>\n<\/p>\n
\u5982\u679c\u4e24\u4e2aCSV\u6587\u4ef6\u5177\u6709\u76f8\u540c\u7684\u5217\u540d\uff0c\u53ef\u4ee5\u4f7f\u7528concat<\/code>\u51fd\u6570\u5c06\u4e24\u4e2aDataFrame\u6309\u884c\u5408\u5e76\u3002<\/p>\n<\/p>\n
# \u6309\u884c\u5408\u5e76<\/p>\n
df_combined = pd.concat([df1, df2], ignore_index=True)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u8fd9\u91cc\u7684ignore_index=True<\/code>\u53c2\u6570\u786e\u4fdd\u5408\u5e76\u540e\u7684DataFrame\u7d22\u5f15\u91cd\u65b0\u6392\u5217\u3002<\/p>\n<\/p>\n
\u4e09\u3001\u6309\u5217\u5408\u5e76\uff08\u6a2a\u5411\u5408\u5e76\uff09<\/h3>\n<\/p>\n
\u5982\u679c\u4e24\u4e2aCSV\u6587\u4ef6\u5177\u6709\u76f8\u540c\u7684\u884c\u7d22\u5f15\uff0c\u53ef\u4ee5\u4f7f\u7528concat<\/code>\u51fd\u6570\u5c06\u4e24\u4e2aDataFrame\u6309\u5217\u5408\u5e76\u3002<\/p>\n<\/p>\n
# \u6309\u5217\u5408\u5e76<\/p>\n
df_combined = pd.concat([df1, df2], axis=1)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u57fa\u4e8e\u67d0\u4e00\u5217\u5408\u5e76\uff08\u7c7b\u4f3cSQL\u7684JOIN\u64cd\u4f5c\uff09<\/h3>\n<\/p>\n
\u5982\u679c\u4e24\u4e2aCSV\u6587\u4ef6\u5177\u6709\u67d0\u4e00\u5217\u76f8\u540c\uff0c\u53ef\u4ee5\u4f7f\u7528merge<\/code>\u51fd\u6570\u8fdb\u884c\u5408\u5e76\uff0c\u7c7b\u4f3c\u4e8eSQL\u4e2d\u7684JOIN\u64cd\u4f5c\u3002<\/p>\n<\/p>\n
# \u57fa\u4e8e\u67d0\u4e00\u5217\u5408\u5e76<\/p>\n
df_combined = pd.merge(df1, df2, on='key_column')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u5904\u7406\u5408\u5e76\u540e\u7684\u6570\u636e<\/h3>\n<\/p>\n
\u5408\u5e76\u540e\u7684\u6570\u636e\u53ef\u80fd\u9700\u8981\u8fdb\u4e00\u6b65\u5904\u7406\uff0c\u5982\u53bb\u9664\u91cd\u590d\u503c\u3001\u5904\u7406\u7f3a\u5931\u503c\u7b49\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u5e38\u7528\u7684\u6570\u636e\u5904\u7406\u65b9\u6cd5\uff1a<\/p>\n<\/p>\n
\u53bb\u9664\u91cd\u590d\u503c<\/h4>\n<\/p>\n
# \u53bb\u9664\u91cd\u590d\u503c<\/p>\n
df_combined.drop_duplicates(inplace=True)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5904\u7406\u7f3a\u5931\u503c<\/h4>\n<\/p>\n
# \u586b\u5145\u7f3a\u5931\u503c<\/p>\n
df_combined.fillna(value={'column_name': 'default_value'}, inplace=True)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516d\u3001\u4fdd\u5b58\u5408\u5e76\u540e\u7684\u6570\u636e<\/h3>\n<\/p>\n
\u6700\u540e\uff0c\u5c06\u5408\u5e76\u540e\u7684DataFrame\u4fdd\u5b58\u4e3a\u65b0\u7684CSV\u6587\u4ef6\u3002<\/p>\n<\/p>\n
# \u4fdd\u5b58\u5408\u5e76\u540e\u7684\u6570\u636e<\/p>\n
df_combined.to_csv('combined_file.csv', index=False)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e03\u3001\u793a\u4f8b\u4ee3\u7801\u6574\u5408<\/h3>\n<\/p>\n
\u4ee5\u4e0b\u662f\u5b8c\u6574\u7684\u793a\u4f8b\u4ee3\u7801\uff0c\u5c06\u6240\u6709\u6b65\u9aa4\u6574\u5408\u5728\u4e00\u8d77\uff1a<\/p>\n<\/p>\n
import pandas as pd<\/p>\n
\u8bfb\u53d6CSV\u6587\u4ef6<\/strong><\/h2>\n
df1 = pd.read_csv('file1.csv')<\/p>\n
df2 = pd.read_csv('file2.csv')<\/p>\n
\u6309\u884c\u5408\u5e76<\/strong><\/h2>\n
df_combined = pd.concat([df1, df2], ignore_index=True)<\/p>\n
\u53bb\u9664\u91cd\u590d\u503c<\/strong><\/h2>\n
df_combined.drop_duplicates(inplace=True)<\/p>\n
\u586b\u5145\u7f3a\u5931\u503c<\/strong><\/h2>\n
df_combined.fillna(value={'column_name': 'default_value'}, inplace=True)<\/p>\n
\u4fdd\u5b58\u5408\u5e76\u540e\u7684\u6570\u636e<\/strong><\/h2>\n
df_combined.to_csv('combined_file.csv', index=False)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516b\u3001\u6ce8\u610f\u4e8b\u9879<\/h3>\n<\/p>\n
    \n
  1. \u6570\u636e\u7c7b\u578b\u517c\u5bb9\u6027<\/strong>\uff1a\u5408\u5e76\u524d\u786e\u4fdd\u4e24\u4e2aCSV\u6587\u4ef6\u7684\u5217\u6570\u636e\u7c7b\u578b\u517c\u5bb9\uff0c\u5426\u5219\u53ef\u80fd\u4f1a\u51fa\u73b0\u6570\u636e\u7c7b\u578b\u9519\u8bef\u3002<\/li>\n
  2. \u7f3a\u5931\u503c\u5904\u7406<\/strong>\uff1a\u5408\u5e76\u540e\u7684DataFrame\u53ef\u80fd\u5305\u542b\u7f3a\u5931\u503c\uff0c\u9700\u8981\u6839\u636e\u5b9e\u9645\u60c5\u51b5\u8fdb\u884c\u5904\u7406\u3002<\/li>\n
  3. \u5217\u540d\u4e00\u81f4\u6027<\/strong>\uff1a\u6309\u884c\u5408\u5e76\u65f6\uff0c\u786e\u4fdd\u4e24\u4e2aCSV\u6587\u4ef6\u7684\u5217\u540d\u4e00\u81f4\uff1b\u6309\u5217\u5408\u5e76\u65f6\uff0c\u786e\u4fdd\u884c\u7d22\u5f15\u4e00\u81f4\u3002<\/li>\n
  4. \u6027\u80fd\u4f18\u5316<\/strong>\uff1a\u5bf9\u4e8e\u975e\u5e38\u5927\u7684CSV\u6587\u4ef6\uff0c\u5408\u5e76\u64cd\u4f5c\u53ef\u80fd\u4f1a\u6d88\u8017\u5927\u91cf\u5185\u5b58\uff0c\u53ef\u4ee5\u8003\u8651\u9010\u884c\u8bfb\u53d6\u548c\u5199\u5165\uff0c\u6216\u8005\u4f7f\u7528Dask\u5e93\u5904\u7406\u5927\u6570\u636e\u96c6\u3002<\/li>\n<\/ol>\n
    \u901a\u8fc7\u4ee5\u4e0a\u65b9\u6cd5\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u4f7f\u7528Python\u5408\u5e76\u4e24\u4e2aCSV\u6587\u4ef6\uff0c\u5e76\u8fdb\u884c\u8fdb\u4e00\u6b65\u7684\u6570\u636e\u5904\u7406\u548c\u5206\u6790\u3002\u5e0c\u671b\u8fd9\u4e9b\u65b9\u6cd5\u5bf9\u60a8\u6709\u6240\u5e2e\u52a9\uff01<\/p>\n<\/p>\n
    \u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
     \u5982\u4f55\u5728Python\u4e2d\u8bfb\u53d6CSV\u6587\u4ef6\u5e76\u8fdb\u884c\u5408\u5e76\uff1f<\/strong>
    \u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528pandas\u5e93\u6765\u8bfb\u53d6\u548c\u5408\u5e76CSV\u6587\u4ef6\u3002\u9996\u5148\uff0c\u786e\u4fdd\u4f60\u5df2\u7ecf\u5b89\u88c5\u4e86pandas\u5e93\u3002\u63a5\u7740\uff0c\u4f7f\u7528pd.read_csv()<\/code>\u51fd\u6570\u8bfb\u53d6\u4e24\u4e2aCSV\u6587\u4ef6\uff0c\u7136\u540e\u4f7f\u7528pd.concat()<\/code>\u6216pd.merge()<\/code>\u51fd\u6570\u6765\u5408\u5e76\u5b83\u4eec\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u57fa\u672c\u793a\u4f8b\uff1a  <\/p>\n
    import pandas as pd\n\n# \u8bfb\u53d6CSV\u6587\u4ef6\ndf1 = pd.read_csv('file1.csv')\ndf2 = pd.read_csv('file2.csv')\n\n# \u5408\u5e76\u6570\u636e\nmerged_df = pd.concat([df1, df2])\n# \u6216\u8005\u4f7f\u7528 pd.merge() \u8fdb\u884c\u66f4\u590d\u6742\u7684\u5408\u5e76\n# merged_df = pd.merge(df1, df2, on='common_column')\n\n# \u4fdd\u5b58\u5408\u5e76\u540e\u7684\u6570\u636e\nmerged_df.to_csv('merged_file.csv', index=False)\n<\/code><\/pre>\n
    \u5408\u5e76CSV\u6587\u4ef6\u65f6\uff0c\u5982\u4f55\u5904\u7406\u91cd\u590d\u6570\u636e\uff1f<\/strong>
    \u5728\u5408\u5e76CSV\u6587\u4ef6\u65f6\uff0c\u53ef\u80fd\u4f1a\u51fa\u73b0\u91cd\u590d\u7684\u6570\u636e\u3002\u53ef\u4ee5\u4f7f\u7528pandas\u4e2d\u7684drop_duplicates()<\/code>\u51fd\u6570\u6765\u53bb\u9664\u91cd\u590d\u884c\u3002\u5728\u5408\u5e76\u4e4b\u540e\uff0c\u8c03\u7528merged_df.drop_duplicates(inplace=True)<\/code>\u5c06\u5220\u9664\u6240\u6709\u91cd\u590d\u8bb0\u5f55\uff0c\u786e\u4fdd\u6700\u7ec8\u6570\u636e\u96c6\u7684\u552f\u4e00\u6027\u3002<\/p>\n
    CSV\u5408\u5e76\u540e\u5982\u4f55\u8fdb\u884c\u6570\u636e\u6e05\u6d17\uff1f<\/strong>
    \u5408\u5e76CSV\u6587\u4ef6\u540e\uff0c\u6570\u636e\u6e05\u6d17\u662f\u4e00\u4e2a\u91cd\u8981\u7684\u6b65\u9aa4\u3002\u4f7f\u7528pandas\u53ef\u4ee5\u5f88\u65b9\u4fbf\u5730\u6267\u884c\u6570\u636e\u6e05\u6d17\u64cd\u4f5c\uff0c\u4f8b\u5982\u586b\u8865\u7f3a\u5931\u503c\u3001\u4fee\u6539\u6570\u636e\u7c7b\u578b\u548c\u5220\u9664\u4e0d\u5fc5\u8981\u7684\u5217\u3002\u4f60\u53ef\u4ee5\u4f7f\u7528merged_df.fillna(value)<\/code>\u586b\u5145\u7f3a\u5931\u503c\uff0c\u6216\u8005\u4f7f\u7528merged_df.drop(columns=['unnecessary_column'])<\/code>\u6765\u5220\u9664\u7279\u5b9a\u7684\u5217\uff0c\u4ee5\u786e\u4fdd\u6570\u636e\u7684\u6574\u6d01\u548c\u4e00\u81f4\u6027\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u5c06\u4e24\u4e2aCSV\u6587\u4ef6\u5408\u5e76\u7684\u65b9\u6cd5\u6709\u591a\u79cd\uff0c\u53ef\u4ee5\u4f7f\u7528pandas\u5e93\u8fdb\u884c\u6570\u636e\u5904\u7406\u3001\u7ed3\u5408\u76f8\u540c\u5217\u540d\u3001\u6309\u884c\u5408\u5e76\u7b49\u65b9\u5f0f […]","protected":false},"author":3,"featured_media":1107761,"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\/1107752"}],"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=1107752"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1107752\/revisions"}],"predecessor-version":[{"id":1107763,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1107752\/revisions\/1107763"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1107761"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1107752"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1107752"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1107752"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}