{"id":1048444,"date":"2024-12-31T13:51:13","date_gmt":"2024-12-31T05:51:13","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1048444.html"},"modified":"2024-12-31T13:51:17","modified_gmt":"2024-12-31T05:51:17","slug":"python%e5%a6%82%e4%bd%95%e7%94%a8pandas%e5%af%bc%e5%87%ba%e5%a4%87%e4%bb%bd%e6%96%87%e4%bb%b6","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1048444.html","title":{"rendered":"python\u5982\u4f55\u7528pandas\u5bfc\u51fa\u5907\u4efd\u6587\u4ef6"},"content":{"rendered":"

\"python\u5982\u4f55\u7528pandas\u5bfc\u51fa\u5907\u4efd\u6587\u4ef6\"<\/p>\n

\u8981\u4f7f\u7528Pandas\u5bfc\u51fa\u5907\u4efd\u6587\u4ef6\uff0c\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u51e0\u79cd\u65b9\u6cd5\uff1a\u4f7f\u7528to_csv<\/code>\u65b9\u6cd5\u5c06\u6570\u636e\u6846\u4fdd\u5b58\u4e3aCSV\u6587\u4ef6\u3001\u4f7f\u7528to_excel<\/code>\u65b9\u6cd5\u5c06\u6570\u636e\u6846\u4fdd\u5b58\u4e3aExcel\u6587\u4ef6\u3001\u4f7f\u7528to_json<\/code>\u65b9\u6cd5\u5c06\u6570\u636e\u6846\u4fdd\u5b58\u4e3aJSON\u6587\u4ef6\u3001\u4f7f\u7528to_sql<\/code>\u65b9\u6cd5\u5c06\u6570\u636e\u6846\u4fdd\u5b58\u5230\u6570\u636e\u5e93\u4e2d\u3002<\/strong> \u5176\u4e2d\uff0c\u6700\u5e38\u7528\u7684\u65b9\u6cd5\u662f\u5c06\u6570\u636e\u6846\u4fdd\u5b58\u4e3aCSV\u6587\u4ef6\u548cExcel\u6587\u4ef6\u3002\u4ee5\u4e0b\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528\u8fd9\u4e9b\u65b9\u6cd5\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u4f7f\u7528to_csv<\/code>\u65b9\u6cd5\u5bfc\u51faCSV\u6587\u4ef6<\/h3>\n<\/p>\n

to_csv<\/code>\u65b9\u6cd5\u662fPandas\u4e2d\u6700\u5e38\u7528\u7684\u5bfc\u51fa\u65b9\u6cd5\u4e4b\u4e00\uff0c\u7528\u4e8e\u5c06\u6570\u636e\u6846\u5bfc\u51fa\u4e3aCSV\u6587\u4ef6\u683c\u5f0f\u3002CSV\u683c\u5f0f\u662f\u4e00\u79cd\u5e38\u89c1\u7684\u6587\u672c\u6587\u4ef6\u683c\u5f0f\uff0c\u9002\u7528\u4e8e\u6570\u636e\u4ea4\u6362\u548c\u5907\u4efd\u3002<\/p>\n<\/p>\n

import pandas as pd<\/p>\n
\u521b\u5efa\u4e00\u4e2a\u793a\u4f8b\u6570\u636e\u6846<\/strong><\/h2>\n
data = {'Name': ['Alice', 'Bob', 'Charlie'],<\/p>\n
        'Age': [25, 30, 35],<\/p>\n
        'City': ['New York', 'Los Angeles', 'Chicago']}<\/p>\n
df = pd.DataFrame(data)<\/p>\n
\u5c06\u6570\u636e\u6846\u5bfc\u51fa\u4e3aCSV\u6587\u4ef6<\/strong><\/h2>\n
df.to_csv('backup.csv', index=False)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u4e0a\u9762\u7684\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u521b\u5efa\u4e86\u4e00\u4e2a\u793a\u4f8b\u6570\u636e\u6846\uff0c\u7136\u540e\u4f7f\u7528to_csv<\/code>\u65b9\u6cd5\u5c06\u5176\u5bfc\u51fa\u4e3a\u540d\u4e3abackup.csv<\/code>\u7684CSV\u6587\u4ef6\u3002\u53c2\u6570index=False<\/code>\u8868\u793a\u4e0d\u5bfc\u51fa\u884c\u7d22\u5f15\u3002<\/p>\n<\/p>\n
\u4e8c\u3001\u4f7f\u7528to_excel<\/code>\u65b9\u6cd5\u5bfc\u51faExcel\u6587\u4ef6<\/h3>\n<\/p>\n
to_excel<\/code>\u65b9\u6cd5\u7528\u4e8e\u5c06\u6570\u636e\u6846\u5bfc\u51fa\u4e3aExcel\u6587\u4ef6\u683c\u5f0f\u3002Excel\u6587\u4ef6\u683c\u5f0f\u5e38\u7528\u4e8e\u6570\u636e\u5206\u6790\u548c\u62a5\u544a\u3002<\/p>\n<\/p>\n
import pandas as pd<\/p>\n
\u521b\u5efa\u4e00\u4e2a\u793a\u4f8b\u6570\u636e\u6846<\/strong><\/h2>\n
data = {'Name': ['Alice', 'Bob', 'Charlie'],<\/p>\n
        'Age': [25, 30, 35],<\/p>\n
        'City': ['New York', 'Los Angeles', 'Chicago']}<\/p>\n
df = pd.DataFrame(data)<\/p>\n
\u5c06\u6570\u636e\u6846\u5bfc\u51fa\u4e3aExcel\u6587\u4ef6<\/strong><\/h2>\n
df.to_excel('backup.xlsx', index=False)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u4e0a\u9762\u7684\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528to_excel<\/code>\u65b9\u6cd5\u5c06\u6570\u636e\u6846\u5bfc\u51fa\u4e3a\u540d\u4e3abackup.xlsx<\/code>\u7684Excel\u6587\u4ef6\u3002\u53c2\u6570index=False<\/code>\u8868\u793a\u4e0d\u5bfc\u51fa\u884c\u7d22\u5f15\u3002<\/p>\n<\/p>\n
\u4e09\u3001\u4f7f\u7528to_json<\/code>\u65b9\u6cd5\u5bfc\u51faJSON\u6587\u4ef6<\/h3>\n<\/p>\n
to_json<\/code>\u65b9\u6cd5\u7528\u4e8e\u5c06\u6570\u636e\u6846\u5bfc\u51fa\u4e3aJSON\u6587\u4ef6\u683c\u5f0f\u3002JSON\u683c\u5f0f\u662f\u4e00\u79cd\u5e38\u89c1\u7684\u6570\u636e\u4ea4\u6362\u683c\u5f0f\uff0c\u9002\u7528\u4e8eWeb\u5e94\u7528\u7a0b\u5e8f\u548cAPI\u3002<\/p>\n<\/p>\n
import pandas as pd<\/p>\n
\u521b\u5efa\u4e00\u4e2a\u793a\u4f8b\u6570\u636e\u6846<\/strong><\/h2>\n
data = {'Name': ['Alice', 'Bob', 'Charlie'],<\/p>\n
        'Age': [25, 30, 35],<\/p>\n
        'City': ['New York', 'Los Angeles', 'Chicago']}<\/p>\n
df = pd.DataFrame(data)<\/p>\n
\u5c06\u6570\u636e\u6846\u5bfc\u51fa\u4e3aJSON\u6587\u4ef6<\/strong><\/h2>\n
df.to_json('backup.json')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u4e0a\u9762\u7684\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528to_json<\/code>\u65b9\u6cd5\u5c06\u6570\u636e\u6846\u5bfc\u51fa\u4e3a\u540d\u4e3abackup.json<\/code>\u7684JSON\u6587\u4ef6\u3002<\/p>\n<\/p>\n
\u56db\u3001\u4f7f\u7528to_sql<\/code>\u65b9\u6cd5\u5bfc\u51fa\u5230\u6570\u636e\u5e93<\/h3>\n<\/p>\n
to_sql<\/code>\u65b9\u6cd5\u7528\u4e8e\u5c06\u6570\u636e\u6846\u5bfc\u51fa\u5230\u6570\u636e\u5e93\u4e2d\u3002\u6b64\u65b9\u6cd5\u9002\u7528\u4e8e\u9700\u8981\u5c06\u6570\u636e\u5b58\u50a8\u5728\u5173\u7cfb\u6570\u636e\u5e93\u4e2d\u7684\u60c5\u51b5\u3002<\/p>\n<\/p>\n
import pandas as pd<\/p>\n
from sqlalchemy import create_engine<\/p>\n
\u521b\u5efa\u4e00\u4e2a\u793a\u4f8b\u6570\u636e\u6846<\/strong><\/h2>\n
data = {'Name': ['Alice', 'Bob', 'Charlie'],<\/p>\n
        'Age': [25, 30, 35],<\/p>\n
        'City': ['New York', 'Los Angeles', 'Chicago']}<\/p>\n
df = pd.DataFrame(data)<\/p>\n
\u521b\u5efa\u6570\u636e\u5e93\u8fde\u63a5<\/strong><\/h2>\n
engine = create_engine('sqlite:\/\/\/backup.db')<\/p>\n
\u5c06\u6570\u636e\u6846\u5bfc\u51fa\u5230\u6570\u636e\u5e93<\/strong><\/h2>\n
df.to_sql('backup_table', engine, index=False, if_exists='replace')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u4e0a\u9762\u7684\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528to_sql<\/code>\u65b9\u6cd5\u5c06\u6570\u636e\u6846\u5bfc\u51fa\u5230SQLite\u6570\u636e\u5e93\u4e2d\uff0c\u5e76\u5c06\u5176\u5b58\u50a8\u5728\u540d\u4e3abackup_table<\/code>\u7684\u8868\u4e2d\u3002\u53c2\u6570if_exists='replace'<\/code>\u8868\u793a\u5982\u679c\u8868\u5df2\u5b58\u5728\uff0c\u5219\u66ff\u6362\u8868\u3002<\/p>\n<\/p>\n
\u4e94\u3001\u5bfc\u51fa\u5927\u6570\u636e\u96c6\u65f6\u7684\u6ce8\u610f\u4e8b\u9879<\/h3>\n<\/p>\n
\u5f53\u5904\u7406\u5927\u6570\u636e\u96c6\u65f6\uff0c\u53ef\u80fd\u9700\u8981\u8003\u8651\u5185\u5b58\u548c\u6027\u80fd\u95ee\u9898\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u5efa\u8bae\uff1a<\/p>\n<\/p>\n
    \n
  1. \u5206\u5757\u5bfc\u51fa<\/strong>\uff1a\u5bf9\u4e8e\u975e\u5e38\u5927\u7684\u6570\u636e\u96c6\uff0c\u53ef\u4ee5\u4f7f\u7528\u5206\u5757\u5bfc\u51fa\u7684\u65b9\u6cd5\uff0c\u4ee5\u907f\u514d\u5185\u5b58\u6ea2\u51fa\u3002<\/li>\n<\/ol>\n
    chunk_size = 1000  # \u6bcf\u6b21\u5bfc\u51fa1000\u884c<\/p>\n
    for i in range(0, len(df), chunk_size):<\/p>\n
        df.iloc[i:i+chunk_size].to_csv(f'backup_part_{i\/\/chunk_size}.csv', index=False)<\/p>\n
    <\/code><\/pre>\n<\/p>\n
      \n
    1. \u538b\u7f29\u6587\u4ef6<\/strong>\uff1a\u5728\u5bfc\u51fa\u65f6\uff0c\u53ef\u4ee5\u4f7f\u7528\u538b\u7f29\u9009\u9879\uff0c\u4ee5\u51cf\u5c11\u6587\u4ef6\u5927\u5c0f\u3002<\/li>\n<\/ol>\n
      df.to_csv('backup.csv.gz', index=False, compression='gzip')<\/p>\n
      <\/code><\/pre>\n<\/p>\n
        \n
      1. \u4f18\u5316\u6570\u636e\u7c7b\u578b<\/strong>\uff1a\u5728\u5bfc\u51fa\u524d\uff0c\u53ef\u4ee5\u4f18\u5316\u6570\u636e\u7c7b\u578b\uff0c\u4ee5\u51cf\u5c11\u5185\u5b58\u4f7f\u7528\u3002<\/li>\n<\/ol>\n
        df['Age'] = df['Age'].astype('int32')<\/p>\n
        <\/code><\/pre>\n<\/p>\n
        \u516d\u3001\u5bfc\u51fa\u65f6\u7684\u5176\u4ed6\u9009\u9879<\/h3>\n<\/p>\n
        Pandas\u63d0\u4f9b\u4e86\u8bb8\u591a\u9009\u9879\uff0c\u4ee5\u4fbf\u5728\u5bfc\u51fa\u65f6\u8fdb\u884c\u66f4\u591a\u7684\u63a7\u5236\u3002\u4f8b\u5982\uff1a<\/p>\n<\/p>\n
          \n
        1. \u81ea\u5b9a\u4e49\u5206\u9694\u7b26<\/strong>\uff1a\u5728\u5bfc\u51faCSV\u6587\u4ef6\u65f6\uff0c\u53ef\u4ee5\u6307\u5b9a\u81ea\u5b9a\u4e49\u7684\u5206\u9694\u7b26\u3002<\/li>\n<\/ol>\n
          df.to_csv('backup.tsv', index=False, sep='\\t')<\/p>\n
          <\/code><\/pre>\n<\/p>\n
            \n
          1. \u5904\u7406\u7f3a\u5931\u503c<\/strong>\uff1a\u5728\u5bfc\u51fa\u65f6\uff0c\u53ef\u4ee5\u6307\u5b9a\u5982\u4f55\u5904\u7406\u7f3a\u5931\u503c\u3002<\/li>\n<\/ol>\n
            df.to_csv('backup.csv', index=False, na_rep='NA')<\/p>\n
            <\/code><\/pre>\n<\/p>\n
              \n
            1. \u5bfc\u51fa\u7279\u5b9a\u5217<\/strong>\uff1a\u53ef\u4ee5\u9009\u62e9\u53ea\u5bfc\u51fa\u7279\u5b9a\u7684\u5217\u3002<\/li>\n<\/ol>\n
              df.to_csv('backup.csv', columns=['Name', 'Age'], index=False)<\/p>\n
              <\/code><\/pre>\n<\/p>\n
              \u4e03\u3001\u5bfc\u51fa\u540e\u7684\u6570\u636e\u9a8c\u8bc1<\/h3>\n<\/p>\n
              \u5728\u5bfc\u51fa\u6570\u636e\u540e\uff0c\u5efa\u8bae\u8fdb\u884c\u6570\u636e\u9a8c\u8bc1\uff0c\u4ee5\u786e\u4fdd\u5bfc\u51fa\u7684\u6570\u636e\u4e0e\u539f\u59cb\u6570\u636e\u4e00\u81f4\u3002\u4f8b\u5982\uff0c\u53ef\u4ee5\u91cd\u65b0\u8bfb\u53d6\u5bfc\u51fa\u7684\u6587\u4ef6\uff0c\u5e76\u4e0e\u539f\u59cb\u6570\u636e\u6846\u8fdb\u884c\u6bd4\u8f83\u3002<\/p>\n<\/p>\n
              df_exported = pd.read_csv('backup.csv')<\/p>\n
              assert df.equals(df_exported)<\/p>\n
              <\/code><\/pre>\n<\/p>\n
              \u901a\u8fc7\u4ee5\u4e0a\u65b9\u6cd5\uff0c\u53ef\u4ee5\u6709\u6548\u5730\u4f7f\u7528Pandas\u5bfc\u51fa\u6570\u636e\u6846\uff0c\u5e76\u786e\u4fdd\u6570\u636e\u7684\u5b8c\u6574\u6027\u548c\u4e00\u81f4\u6027\u3002\u65e0\u8bba\u662f\u5907\u4efd\u6570\u636e\uff0c\u8fd8\u662f\u8fdb\u884c\u6570\u636e\u4ea4\u6362\uff0c\u8fd9\u4e9b\u65b9\u6cd5\u90fd\u80fd\u6ee1\u8db3\u5927\u591a\u6570\u9700\u6c42\u3002<\/p>\n<\/p>\n
              \u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
               \u5728\u4f7f\u7528Pandas\u5bfc\u51fa\u5907\u4efd\u6587\u4ef6\u65f6\uff0c\u652f\u6301\u54ea\u4e9b\u6587\u4ef6\u683c\u5f0f\uff1f<\/strong>
              Pandas\u652f\u6301\u591a\u79cd\u6587\u4ef6\u683c\u5f0f\u7684\u5bfc\u51fa\uff0c\u5305\u62ecCSV\u3001Excel\u3001JSON\u3001HTML\u7b49\u3002\u4f7f\u7528DataFrame.to_csv()<\/code>\u53ef\u4ee5\u5c06\u6570\u636e\u5bfc\u51fa\u4e3aCSV\u6587\u4ef6\uff0c\u4f7f\u7528DataFrame.to_excel()<\/code>\u53ef\u4ee5\u5bfc\u51fa\u4e3aExcel\u6587\u4ef6\uff0c\u4f7f\u7528DataFrame.to_json()<\/code>\u5219\u53ef\u4ee5\u5bfc\u51fa\u4e3aJSON\u683c\u5f0f\u3002\u8fd9\u4e9b\u683c\u5f0f\u5404\u6709\u7279\u70b9\uff0c\u53ef\u4ee5\u6839\u636e\u6570\u636e\u7684\u4f7f\u7528\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u5bfc\u51fa\u683c\u5f0f\u3002<\/p>\n
              \u5982\u4f55\u786e\u4fdd\u5bfc\u51fa\u7684\u5907\u4efd\u6587\u4ef6\u5305\u542b\u5b8c\u6574\u7684\u6570\u636e\u548c\u5143\u6570\u636e\uff1f<\/strong>
              \u5728\u5bfc\u51fa\u5907\u4efd\u6587\u4ef6\u65f6\uff0c\u53ef\u4ee5\u4f7f\u7528DataFrame.to_csv()<\/code>\u7684\u53c2\u6570\u6765\u786e\u4fdd\u6570\u636e\u7684\u5b8c\u6574\u6027\u3002\u4f8b\u5982\uff0c\u901a\u8fc7\u8bbe\u7f6eindex=True<\/code>\u53ef\u4ee5\u5c06\u884c\u7d22\u5f15\u5305\u542b\u5728\u5bfc\u51fa\u7684\u6587\u4ef6\u4e2d\u3002\u6b64\u5916\uff0c\u53ef\u4ee5\u4f7f\u7528DataFrame.info()<\/code>\u6765\u67e5\u770b\u6570\u636e\u7684\u7c7b\u578b\u548c\u7f3a\u5931\u503c\uff0c\u786e\u4fdd\u5bfc\u51fa\u524d\u6570\u636e\u7684\u5b8c\u6574\u6027\u548c\u51c6\u786e\u6027\u3002<\/p>\n
              \u5bfc\u51fa\u5907\u4efd\u6587\u4ef6\u65f6\uff0c\u5982\u4f55\u5904\u7406\u7279\u6b8a\u5b57\u7b26\u6216\u7f16\u7801\u95ee\u9898\uff1f<\/strong>
              \u5904\u7406\u7279\u6b8a\u5b57\u7b26\u6216\u7f16\u7801\u95ee\u9898\u65f6\uff0c\u53ef\u4ee5\u5728\u4f7f\u7528to_csv()<\/code>\u6216to_excel()<\/code>\u65f6\u6307\u5b9aencoding<\/code>\u53c2\u6570\u3002\u4f8b\u5982\uff0c\u82e5\u6570\u636e\u4e2d\u5305\u542b\u4e2d\u6587\u5b57\u7b26\uff0c\u53ef\u4ee5\u5c06\u7f16\u7801\u8bbe\u7f6e\u4e3a'utf-8'<\/code>\u6216'utf-8-sig'<\/code>\u3002\u6b64\u5916\uff0cquoting<\/code>\u53c2\u6570\u53ef\u4ee5\u5e2e\u52a9\u5904\u7406\u5305\u542b\u9017\u53f7\u7684\u5b57\u7b26\u4e32\uff0c\u786e\u4fdd\u6570\u636e\u5728\u5bfc\u51fa\u65f6\u4e0d\u4f1a\u88ab\u9519\u8bef\u89e3\u6790\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u8981\u4f7f\u7528Pandas\u5bfc\u51fa\u5907\u4efd\u6587\u4ef6\uff0c\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u51e0\u79cd\u65b9\u6cd5\uff1a\u4f7f\u7528to_csv\u65b9\u6cd5\u5c06\u6570\u636e\u6846\u4fdd\u5b58\u4e3aCSV\u6587\u4ef6\u3001\u4f7f\u7528to_ […]","protected":false},"author":3,"featured_media":1048453,"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\/1048444"}],"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=1048444"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1048444\/revisions"}],"predecessor-version":[{"id":1048455,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1048444\/revisions\/1048455"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1048453"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1048444"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1048444"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1048444"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}