{"id":999107,"date":"2024-12-27T09:38:39","date_gmt":"2024-12-27T01:38:39","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/999107.html"},"modified":"2024-12-27T09:38:42","modified_gmt":"2024-12-27T01:38:42","slug":"python%e5%a6%82%e4%bd%95%e8%af%bb%e5%8f%96%e9%83%a8%e5%88%86csv","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/999107.html","title":{"rendered":"python\u5982\u4f55\u8bfb\u53d6\u90e8\u5206csv"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25074249\/c84f2d92-847d-416d-9a1b-15178f738d77.webp\" alt=\"python\u5982\u4f55\u8bfb\u53d6\u90e8\u5206csv\" \/><\/p>\n<p><p> <strong>Python\u8bfb\u53d6\u90e8\u5206CSV\u6587\u4ef6\u7684\u65b9\u6cd5\u4e3b\u8981\u5305\u62ec\uff1a\u4f7f\u7528pandas\u5e93\u7684read_csv\u65b9\u6cd5\u5e76\u7ed3\u5408nrows\u53c2\u6570\u3001\u5229\u7528skiprows\u53c2\u6570\u8df3\u8fc7\u4e0d\u9700\u8981\u7684\u884c\u3001\u901a\u8fc7chunksize\u53c2\u6570\u5206\u6279\u8bfb\u53d6\u3001\u4f7f\u7528csv\u6a21\u5757\u624b\u52a8\u8bfb\u53d6\u7279\u5b9a\u884c\u3002<\/strong>\u5176\u4e2d\uff0c<strong>pandas\u5e93\u7684read_csv\u65b9\u6cd5\u7ed3\u5408nrows\u548cskiprows\u53c2\u6570<\/strong>\u662f\u6700\u4e3a\u7b80\u4fbf\u548c\u9ad8\u6548\u7684\u65b9\u5f0f\u3002<\/p>\n<\/p>\n<p><p>Python\u63d0\u4f9b\u4e86\u591a\u79cd\u5de5\u5177\u548c\u5e93\u6765\u5904\u7406CSV\u6587\u4ef6\u3002\u5728\u5904\u7406\u5927\u578bCSV\u6587\u4ef6\u65f6\uff0c\u6709\u65f6\u53ea\u9700\u8981\u8bfb\u53d6\u90e8\u5206\u6570\u636e\u800c\u4e0d\u662f\u6574\u4e2a\u6587\u4ef6\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u5e38\u7528\u7684\u65b9\u6cd5\u548c\u6280\u5de7\uff0c\u5e2e\u52a9\u60a8\u9ad8\u6548\u5730\u8bfb\u53d6\u90e8\u5206CSV\u6587\u4ef6\u3002<\/p>\n<\/p>\n<p><p>\u4e00\u3001\u4f7f\u7528pandas\u5e93\u7684read_csv\u65b9\u6cd5  <\/p>\n<\/p>\n<p><p>pandas\u5e93\u662fPython\u4e2d\u5904\u7406\u6570\u636e\u7684\u5f3a\u5927\u5de5\u5177\u4e4b\u4e00\uff0c\u5b83\u63d0\u4f9b\u4e86\u7075\u6d3b\u7684read_csv\u51fd\u6570\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u8bfb\u53d6CSV\u6587\u4ef6\u4e2d\u7684\u90e8\u5206\u6570\u636e\u3002<\/p>\n<\/p>\n<ol>\n<li>\n<p><strong>\u4f7f\u7528nrows\u53c2\u6570\u8bfb\u53d6\u524dn\u884c<\/strong><\/p>\n<\/p>\n<p><p>\u5982\u679c\u60a8\u53ea\u9700\u8981\u8bfb\u53d6CSV\u6587\u4ef6\u7684\u524d\u51e0\u884c\uff0c\u53ef\u4ee5\u4f7f\u7528nrows\u53c2\u6570\u3002nrows\u53c2\u6570\u6307\u5b9a\u8981\u8bfb\u53d6\u7684\u884c\u6570\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import pandas as pd<\/p>\n<h2><strong>\u8bfb\u53d6CSV\u6587\u4ef6\u7684\u524d100\u884c<\/strong><\/h2>\n<p>df = pd.read_csv(&#39;data.csv&#39;, nrows=100)<\/p>\n<p>print(df)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u4f7f\u7528skiprows\u53c2\u6570\u8df3\u8fc7\u6307\u5b9a\u884c<\/strong><\/p>\n<\/p>\n<p><p>skiprows\u53c2\u6570\u53ef\u4ee5\u7528\u6765\u8df3\u8fc7CSV\u6587\u4ef6\u4e2d\u7684\u7279\u5b9a\u884c\u3002\u4f8b\u5982\uff0c\u5982\u679c\u60a8\u53ea\u60f3\u8bfb\u53d6\u6587\u4ef6\u7684\u540e\u534a\u90e8\u5206\uff0c\u53ef\u4ee5\u8df3\u8fc7\u524d\u51e0\u884c\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u8df3\u8fc7\u524d100\u884c\uff0c\u7136\u540e\u8bfb\u53d6\u5269\u4f59\u7684\u90e8\u5206<\/p>\n<p>df = pd.read_csv(&#39;data.csv&#39;, skiprows=100)<\/p>\n<p>print(df)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>skiprows\u8fd8\u53ef\u4ee5\u63a5\u53d7\u4e00\u4e2a\u5217\u8868\uff0c\u6307\u5b9a\u8981\u8df3\u8fc7\u7684\u884c\u53f7\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u8df3\u8fc7\u7b2c1, 3, 5\u884c<\/p>\n<p>df = pd.read_csv(&#39;data.csv&#39;, skiprows=[0, 2, 4])<\/p>\n<p>print(df)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u4f7f\u7528chunksize\u53c2\u6570\u5206\u6279\u8bfb\u53d6<\/strong><\/p>\n<\/p>\n<p><p>\u5f53CSV\u6587\u4ef6\u975e\u5e38\u5927\u65f6\uff0c\u53ef\u4ee5\u4f7f\u7528chunksize\u53c2\u6570\u5206\u6279\u8bfb\u53d6\u6570\u636e\u3002chunksize\u6307\u5b9a\u6bcf\u6b21\u8bfb\u53d6\u7684\u884c\u6570\uff0cread_csv\u4f1a\u8fd4\u56de\u4e00\u4e2a\u53ef\u8fed\u4ee3\u7684TextFileReader\u5bf9\u8c61\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u6bcf\u6b21\u8bfb\u53d61000\u884c<\/p>\n<p>chunk_size = 1000<\/p>\n<p>for chunk in pd.read_csv(&#39;data.csv&#39;, chunksize=chunk_size):<\/p>\n<p>    print(chunk)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u79cd\u65b9\u6cd5\u7279\u522b\u9002\u5408\u4e8e\u9700\u8981\u9010\u6b65\u5904\u7406\u5927\u6587\u4ef6\u7684\u60c5\u51b5\u3002<\/p>\n<\/p>\n<\/li>\n<\/ol>\n<p><p>\u4e8c\u3001\u4f7f\u7528csv\u6a21\u5757\u624b\u52a8\u8bfb\u53d6\u7279\u5b9a\u884c<\/p>\n<\/p>\n<p><p>Python\u5185\u7f6e\u7684csv\u6a21\u5757\u4e5f\u53ef\u4ee5\u7528\u4e8e\u8bfb\u53d6CSV\u6587\u4ef6\uff0c\u5e76\u63d0\u4f9b\u4e86\u66f4\u7cbe\u7ec6\u7684\u63a7\u5236\u3002<\/p>\n<\/p>\n<ol>\n<li>\n<p><strong>\u9010\u884c\u8bfb\u53d6<\/strong><\/p>\n<\/p>\n<p><p>\u901a\u8fc7\u9010\u884c\u8bfb\u53d6CSV\u6587\u4ef6\uff0c\u60a8\u53ef\u4ee5\u624b\u52a8\u9009\u62e9\u9700\u8981\u7684\u884c\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import csv<\/p>\n<p>with open(&#39;data.csv&#39;, newline=&#39;&#39;) as csvfile:<\/p>\n<p>    csvreader = csv.reader(csvfile)<\/p>\n<p>    for i, row in enumerate(csvreader):<\/p>\n<p>        if i &gt;= 10 and i &lt; 20:  # \u8bfb\u53d6\u7b2c10\u5230\u7b2c19\u884c<\/p>\n<p>            print(row)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u4f7f\u7528DictReader<\/strong><\/p>\n<\/p>\n<p><p>csv\u6a21\u5757\u8fd8\u63d0\u4f9b\u4e86DictReader\u7c7b\uff0c\u5c06CSV\u6587\u4ef6\u4e2d\u7684\u6bcf\u4e00\u884c\u8f6c\u6362\u4e3a\u5b57\u5178\uff0c\u952e\u4e3a\u5217\u540d\u3002\u8fd9\u5bf9\u4e8e\u5904\u7406\u5e26\u6709\u6807\u9898\u7684CSV\u6587\u4ef6\u975e\u5e38\u65b9\u4fbf\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">with open(&#39;data.csv&#39;, newline=&#39;&#39;) as csvfile:<\/p>\n<p>    csvreader = csv.DictReader(csvfile)<\/p>\n<p>    for i, row in enumerate(csvreader):<\/p>\n<p>        if i &gt;= 10 and i &lt; 20:<\/p>\n<p>            print(row)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<\/li>\n<\/ol>\n<p><p>\u4e09\u3001\u4f7f\u7528dask\u5e93\u5904\u7406\u5927\u578bCSV\u6587\u4ef6<\/p>\n<\/p>\n<p><p>\u5bf9\u4e8e\u975e\u5e38\u5927\u7684CSV\u6587\u4ef6\uff0cdask\u5e93\u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u5de5\u5177\u3002dask\u662f\u4e00\u4e2a\u5e76\u884c\u8ba1\u7b97\u5e93\uff0c\u80fd\u591f\u5904\u7406\u6bd4\u5185\u5b58\u8fd8\u5927\u7684\u6570\u636e\u96c6\u3002<\/p>\n<\/p>\n<ol>\n<li>\n<p><strong>\u8bfb\u53d6\u5927\u6587\u4ef6<\/strong><\/p>\n<\/p>\n<p><p>dask.dataframe\u7684read_csv\u51fd\u6570\u4e0epandas\u7684read_csv\u7c7b\u4f3c\uff0c\u4f46\u5b83\u8fd4\u56de\u7684\u662f\u4e00\u4e2a\u5ef6\u8fdf\u8ba1\u7b97\u7684Dask DataFrame\u5bf9\u8c61\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import dask.dataframe as dd<\/p>\n<h2><strong>\u8bfb\u53d6CSV\u6587\u4ef6<\/strong><\/h2>\n<p>df = dd.read_csv(&#39;large_data.csv&#39;)<\/p>\n<h2><strong>\u8fdb\u884c\u8ba1\u7b97\u5e76\u8f6c\u6362\u4e3apandas DataFrame<\/strong><\/h2>\n<p>result = df.compute()<\/p>\n<p>print(result)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u6307\u5b9a\u8bfb\u53d6\u7684\u884c\u548c\u5217<\/strong><\/p>\n<\/p>\n<p><p>dask\u4e5f\u652f\u6301\u7c7b\u4f3cpandas\u7684skiprows\u548cusecols\u53c2\u6570\uff0c\u5141\u8bb8\u60a8\u9009\u62e9\u8981\u8bfb\u53d6\u7684\u7279\u5b9a\u884c\u548c\u5217\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">df = dd.read_csv(&#39;large_data.csv&#39;, skiprows=100, usecols=[&#39;column1&#39;, &#39;column2&#39;])<\/p>\n<p>result = df.compute()<\/p>\n<p>print(result)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<\/li>\n<\/ol>\n<p><p>\u56db\u3001\u603b\u7ed3\u4e0e\u4f18\u5316\u5efa\u8bae<\/p>\n<\/p>\n<p><p>\u5728\u5904\u7406CSV\u6587\u4ef6\u65f6\uff0c\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\u53d6\u51b3\u4e8e\u6587\u4ef6\u7684\u5927\u5c0f\u548c\u5177\u4f53\u9700\u6c42\u3002\u5bf9\u4e8e\u5c0f\u578b\u5230\u4e2d\u578b\u6587\u4ef6\uff0cpandas\u5e93\u63d0\u4f9b\u4e86\u7b80\u4fbf\u4e14\u9ad8\u6548\u7684\u8bfb\u53d6\u65b9\u5f0f\uff1b\u800c\u5bf9\u4e8e\u5927\u578b\u6587\u4ef6\uff0cdask\u5e93\u548c\u5206\u6279\u8bfb\u53d6\u7b56\u7565\u53ef\u4ee5\u6709\u6548\u964d\u4f4e\u5185\u5b58\u538b\u529b\u3002\u6b64\u5916\uff0c\u4f7f\u7528csv\u6a21\u5757\u53ef\u4ee5\u5b9e\u73b0\u66f4\u4f4e\u7ea7\u522b\u7684\u63a7\u5236\uff0c\u4f46\u53ef\u80fd\u9700\u8981\u66f4\u591a\u7684\u7f16\u7801\u5de5\u4f5c\u3002<\/p>\n<\/p>\n<p><p>\u4e3a\u4e86\u63d0\u9ad8CSV\u6587\u4ef6\u8bfb\u53d6\u7684\u6548\u7387\uff0c\u53ef\u4ee5\u8003\u8651\u4ee5\u4e0b\u51e0\u70b9\uff1a<\/p>\n<\/p>\n<ul>\n<li><strong>\u4f18\u5316\u6570\u636e\u5b58\u50a8\u683c\u5f0f<\/strong>\uff1a\u5c06CSV\u6587\u4ef6\u8f6c\u6362\u4e3a\u66f4\u9ad8\u6548\u7684\u4e8c\u8fdb\u5236\u683c\u5f0f\uff08\u5982Parquet\u6216Feather\uff09\u53ef\u4ee5\u663e\u8457\u63d0\u9ad8\u8bfb\u53d6\u901f\u5ea6\u3002<\/li>\n<li><strong>\u4f7f\u7528\u7d22\u5f15<\/strong>\uff1a\u5982\u679cCSV\u6587\u4ef6\u662f\u6309\u67d0\u4e2a\u5b57\u6bb5\u6392\u5e8f\u7684\uff0c\u60a8\u53ef\u4ee5\u5148\u8bfb\u53d6\u7d22\u5f15\u4ee5\u5feb\u901f\u67e5\u627e\u6240\u9700\u6570\u636e\u3002<\/li>\n<li><strong>\u5206\u533a\u5b58\u50a8<\/strong>\uff1a\u5c06\u5927\u578bCSV\u6587\u4ef6\u62c6\u5206\u4e3a\u66f4\u5c0f\u7684\u5206\u533a\u6587\u4ef6\uff0c\u53ef\u4ee5\u51cf\u5c11\u8bfb\u53d6\u7279\u5b9a\u6570\u636e\u65f6\u7684I\/O\u5f00\u9500\u3002<\/li>\n<\/ul>\n<p><p>\u901a\u8fc7\u7075\u6d3b\u4f7f\u7528\u4e0a\u8ff0\u65b9\u6cd5\uff0c\u60a8\u53ef\u4ee5\u9ad8\u6548\u5730\u8bfb\u53d6\u548c\u5904\u7406CSV\u6587\u4ef6\u4e2d\u7684\u90e8\u5206\u6570\u636e\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u8bfb\u53d6CSV\u6587\u4ef6\u7684\u7279\u5b9a\u884c\u6216\u5217\uff1f<\/strong><br \/>Python\u63d0\u4f9b\u4e86\u591a\u79cd\u5e93\u6765\u8bfb\u53d6CSV\u6587\u4ef6\uff0c\u5176\u4e2dPandas\u662f\u6700\u5e38\u7528\u7684\u5e93\u4e4b\u4e00\u3002\u901a\u8fc7\u4f7f\u7528Pandas\u7684<code>read_csv()<\/code>\u51fd\u6570\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u9009\u62e9\u7279\u5b9a\u7684\u884c\u6216\u5217\u3002\u4f8b\u5982\uff0c\u4f7f\u7528<code>usecols<\/code>\u53c2\u6570\u53ef\u4ee5\u6307\u5b9a\u60f3\u8981\u8bfb\u53d6\u7684\u5217\uff0c\u4f7f\u7528<code>skiprows<\/code>\u53c2\u6570\u53ef\u4ee5\u8df3\u8fc7\u4e0d\u9700\u8981\u7684\u884c\u3002\u8fd9\u6837\u53ef\u4ee5\u6709\u6548\u51cf\u5c11\u5185\u5b58\u4f7f\u7528\u5e76\u52a0\u5feb\u8bfb\u53d6\u901f\u5ea6\u3002<\/p>\n<p><strong>\u5728Python\u4e2d\uff0c\u5982\u4f55\u4f7f\u7528\u6761\u4ef6\u8fc7\u6ee4\u6765\u8bfb\u53d6CSV\u6587\u4ef6\u4e2d\u7684\u6570\u636e\uff1f<\/strong><br \/>\u5728\u8bfb\u53d6CSV\u6587\u4ef6\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528Pandas\u7684DataFrame\u8fdb\u884c\u6761\u4ef6\u8fc7\u6ee4\u3002\u4f8b\u5982\uff0c\u901a\u8fc7\u5e03\u5c14\u7d22\u5f15\u53ef\u4ee5\u8f7b\u677e\u7b5b\u9009\u51fa\u7b26\u5408\u7279\u5b9a\u6761\u4ef6\u7684\u884c\u3002\u8fd9\u79cd\u65b9\u6cd5\u975e\u5e38\u9002\u5408\u5904\u7406\u5927\u6570\u636e\u96c6\uff0c\u5e2e\u52a9\u7528\u6237\u5feb\u901f\u83b7\u53d6\u6240\u9700\u7684\u6570\u636e\u5b50\u96c6\u3002<\/p>\n<p><strong>\u662f\u5426\u53ef\u4ee5\u7528Python\u6309\u7279\u5b9a\u6761\u4ef6\u5206\u5757\u8bfb\u53d6CSV\u6587\u4ef6\uff1f<\/strong><br \/>\u662f\u7684\uff0cPython\u652f\u6301\u6309\u5757\u8bfb\u53d6CSV\u6587\u4ef6\uff0c\u53ef\u4ee5\u4f7f\u7528Pandas\u7684<code>chunksize<\/code>\u53c2\u6570\u3002\u8fd9\u79cd\u65b9\u5f0f\u9002\u5408\u5904\u7406\u5927\u578b\u6587\u4ef6\uff0c\u5141\u8bb8\u7528\u6237\u5206\u6279\u8bfb\u53d6\u6570\u636e\uff0c\u6bcf\u6b21\u53ea\u5904\u7406\u4e00\u4e2a\u5757\uff0c\u4ece\u800c\u51cf\u5c11\u5185\u5b58\u5360\u7528\u3002\u8fd9\u5bf9\u4e8e\u9700\u8981\u9010\u6b65\u5904\u7406\u6570\u636e\u7684\u573a\u666f\u5c24\u5176\u6709\u7528\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u8bfb\u53d6\u90e8\u5206CSV\u6587\u4ef6\u7684\u65b9\u6cd5\u4e3b\u8981\u5305\u62ec\uff1a\u4f7f\u7528pandas\u5e93\u7684read_csv\u65b9\u6cd5\u5e76\u7ed3\u5408nrows\u53c2\u6570\u3001\u5229 [&hellip;]","protected":false},"author":3,"featured_media":999115,"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\/999107"}],"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=999107"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/999107\/revisions"}],"predecessor-version":[{"id":999117,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/999107\/revisions\/999117"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/999115"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=999107"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=999107"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=999107"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}