{"id":997000,"date":"2024-12-27T09:19:45","date_gmt":"2024-12-27T01:19:45","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/997000.html"},"modified":"2024-12-27T09:19:47","modified_gmt":"2024-12-27T01:19:47","slug":"python%e5%a6%82%e4%bd%95%e6%89%b9%e6%ac%a1%e8%af%bb%e6%95%b0%e6%8d%ae","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/997000.html","title":{"rendered":"python\u5982\u4f55\u6279\u6b21\u8bfb\u6570\u636e"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25073011\/3fbe877e-2997-4f98-9683-da11c65edd2b.webp\" alt=\"python\u5982\u4f55\u6279\u6b21\u8bfb\u6570\u636e\" \/><\/p>\n<p><p> <strong>Python\u6279\u6b21\u8bfb\u53d6\u6570\u636e\u7684\u5e38\u7528\u65b9\u6cd5\u5305\u62ec\u4f7f\u7528\u751f\u6210\u5668\u3001Pandas\u5e93\u7684<code>read_csv<\/code>\u65b9\u6cd5\u3001NumPy\u7684<code>loadtxt<\/code>\u65b9\u6cd5\u3001\u4ee5\u53ca\u9010\u884c\u8bfb\u53d6\u6587\u4ef6\u3002\u751f\u6210\u5668\u53ef\u4ee5\u5e2e\u52a9\u8282\u7701\u5185\u5b58\u3001Pandas\u7684<code>read_csv<\/code>\u65b9\u6cd5\u53ef\u4ee5\u65b9\u4fbf\u5730\u5904\u7406\u5927\u89c4\u6a21\u6570\u636e\u3001NumPy\u7684<code>loadtxt<\/code>\u65b9\u6cd5\u9002\u7528\u4e8e\u6570\u503c\u8ba1\u7b97\u3001\u9010\u884c\u8bfb\u53d6\u6587\u4ef6\u5219\u662f\u6700\u57fa\u7840\u7684\u65b9\u6cd5\u3002\u4ee5\u4e0b\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u751f\u6210\u5668\u7684\u4f7f\u7528\u3002<\/strong><\/p>\n<\/p>\n<p><p>\u751f\u6210\u5668\u662f\u4e00\u79cd\u7279\u6b8a\u7684\u8fed\u4ee3\u5668\uff0c\u4f7f\u7528\u751f\u6210\u5668\u53ef\u4ee5\u9010\u6b65\u83b7\u53d6\u6570\u636e\u800c\u4e0d\u9700\u8981\u4e00\u6b21\u6027\u52a0\u8f7d\u6240\u6709\u6570\u636e\u5230\u5185\u5b58\u4e2d\u3002\u8fd9\u6837\u53ef\u4ee5\u6781\u5927\u5730\u8282\u7701\u5185\u5b58\u8d44\u6e90\u5e76\u63d0\u9ad8\u6570\u636e\u5904\u7406\u7684\u6548\u7387\u3002\u4f7f\u7528\u751f\u6210\u5668\u8bfb\u53d6\u6570\u636e\u65f6\uff0c\u53ef\u4ee5\u5c06\u6570\u636e\u5206\u6279\u6b21\u8bfb\u5165\u5e76\u5904\u7406\u3002\u4f8b\u5982\u5728\u5904\u7406\u5927\u89c4\u6a21\u6587\u672c\u6587\u4ef6\u65f6\uff0c\u53ef\u4ee5\u901a\u8fc7\u751f\u6210\u5668\u6bcf\u6b21\u8bfb\u53d6\u56fa\u5b9a\u884c\u6570\u7684\u6570\u636e\u5757\uff0c\u7136\u540e\u9010\u5757\u8fdb\u884c\u5904\u7406\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u4f7f\u7528\u751f\u6210\u5668\u6279\u6b21\u8bfb\u53d6\u6570\u636e<\/h3>\n<\/p>\n<p><p>\u751f\u6210\u5668\u662fPython\u4e2d\u5904\u7406\u5927\u6570\u636e\u96c6\u7684\u4e00\u79cd\u6709\u6548\u5de5\u5177\u3002\u901a\u8fc7\u4f7f\u7528\u751f\u6210\u5668\uff0c\u53ef\u4ee5\u5728\u4e0d\u5360\u7528\u5927\u91cf\u5185\u5b58\u7684\u60c5\u51b5\u4e0b\u8bfb\u53d6\u548c\u5904\u7406\u6570\u636e\u3002<\/p>\n<\/p>\n<p><h4>1. \u521b\u5efa\u751f\u6210\u5668\u51fd\u6570<\/h4>\n<\/p>\n<p><p>\u751f\u6210\u5668\u51fd\u6570\u4f7f\u7528<code>yield<\/code>\u5173\u952e\u5b57\u6765\u8fd4\u56de\u6570\u636e\uff0c\u8fd9\u4e0e\u666e\u901a\u51fd\u6570\u4e0d\u540c\uff0c\u666e\u901a\u51fd\u6570\u4f7f\u7528<code>return<\/code>\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">def batch_read(file_path, batch_size):<\/p>\n<p>    with open(file_path, &#39;r&#39;) as file:<\/p>\n<p>        batch = []<\/p>\n<p>        for line in file:<\/p>\n<p>            batch.append(line.strip())<\/p>\n<p>            if len(batch) == batch_size:<\/p>\n<p>                yield batch<\/p>\n<p>                batch = []<\/p>\n<p>        if batch:<\/p>\n<p>            yield batch<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c<code>batch_read<\/code>\u51fd\u6570\u9010\u884c\u8bfb\u53d6\u6587\u4ef6\uff0c\u6bcf\u6b21\u8bfb\u53d6<code>batch_size<\/code>\u884c\u6570\u636e\u540e\uff0c\u901a\u8fc7<code>yield<\/code>\u8fd4\u56de\u4e00\u4e2a\u6279\u6b21\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<p><h4>2. \u4f7f\u7528\u751f\u6210\u5668\u8bfb\u53d6\u6570\u636e<\/h4>\n<\/p>\n<p><p>\u53ef\u4ee5\u901a\u8fc7\u5faa\u73af\u6765\u83b7\u53d6\u751f\u6210\u5668\u8fd4\u56de\u7684\u6570\u636e\u6279\u6b21\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">for batch in batch_read(&#39;large_file.txt&#39;, 100):<\/p>\n<p>    process_data(batch)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u8fc7\u7a0b\u4e2d\uff0c<code>process_data<\/code>\u662f\u4e00\u4e2a\u5904\u7406\u6570\u636e\u7684\u51fd\u6570\uff0c\u6bcf\u6b21\u5904\u7406\u4e00\u4e2a\u6570\u636e\u6279\u6b21\u3002<\/p>\n<\/p>\n<p><h3>\u4e8c\u3001\u4f7f\u7528Pandas\u7684<code>read_csv<\/code>\u65b9\u6cd5<\/h3>\n<\/p>\n<p><p>Pandas\u5e93\u63d0\u4f9b\u4e86\u5f3a\u5927\u7684\u6570\u636e\u8bfb\u53d6\u548c\u5904\u7406\u80fd\u529b\uff0c\u5c24\u5176\u9002\u5408\u7528\u4e8e\u5904\u7406CSV\u6587\u4ef6\u3002<code>read_csv<\/code>\u65b9\u6cd5\u652f\u6301\u5206\u5757\u8bfb\u53d6\u6570\u636e\u3002<\/p>\n<\/p>\n<p><h4>1. \u4f7f\u7528<code>chunksize<\/code>\u53c2\u6570<\/h4>\n<\/p>\n<p><p><code>read_csv<\/code>\u65b9\u6cd5\u7684<code>chunksize<\/code>\u53c2\u6570\u5141\u8bb8\u6309\u5757\u8bfb\u53d6CSV\u6587\u4ef6\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import pandas as pd<\/p>\n<p>chunk_size = 1000<\/p>\n<p>for chunk in pd.read_csv(&#39;large_file.csv&#39;, chunksize=chunk_size):<\/p>\n<p>    process_chunk(chunk)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p><code>chunksize<\/code>\u53c2\u6570\u6307\u5b9a\u6bcf\u6b21\u8bfb\u53d6\u7684\u884c\u6570\uff0c\u8fd4\u56de\u7684<code>chunk<\/code>\u662f\u4e00\u4e2aDataFrame\u5bf9\u8c61\uff0c\u53ef\u4ee5\u76f4\u63a5\u8fdb\u884cPandas\u64cd\u4f5c\u3002<\/p>\n<\/p>\n<p><h4>2. \u5904\u7406\u6570\u636e\u5757<\/h4>\n<\/p>\n<p><p>\u5728\u5faa\u73af\u4e2d\uff0c\u53ef\u4ee5\u5bf9\u6bcf\u4e2a\u6570\u636e\u5757\u8fdb\u884c\u5904\u7406\uff0c\u4f8b\u5982\u8ba1\u7b97\u7edf\u8ba1\u4fe1\u606f\u3001\u6570\u636e\u6e05\u6d17\u7b49\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">def process_chunk(chunk):<\/p>\n<p>    # \u8fdb\u884c\u6570\u636e\u5904\u7406<\/p>\n<p>    print(chunk.describe())<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u4f7f\u7528NumPy\u7684<code>loadtxt<\/code>\u65b9\u6cd5<\/h3>\n<\/p>\n<p><p>NumPy\u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u6570\u503c\u8ba1\u7b97\u5e93\uff0c\u9002\u7528\u4e8e\u5904\u7406\u6570\u503c\u578b\u6570\u636e\u3002<code>loadtxt<\/code>\u65b9\u6cd5\u53ef\u4ee5\u7528\u6765\u8bfb\u53d6\u6587\u672c\u6587\u4ef6\u4e2d\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<p><h4>1. \u8bfb\u53d6\u6570\u636e<\/h4>\n<\/p>\n<p><p><code>loadtxt<\/code>\u65b9\u6cd5\u53ef\u4ee5\u901a\u8fc7<code>max_rows<\/code>\u53c2\u6570\u6765\u63a7\u5236\u6bcf\u6b21\u8bfb\u53d6\u7684\u6570\u636e\u884c\u6570\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import numpy as np<\/p>\n<p>def batch_load(file_path, batch_size):<\/p>\n<p>    with open(file_path, &#39;r&#39;) as file:<\/p>\n<p>        while True:<\/p>\n<p>            data = np.loadtxt(file, max_rows=batch_size)<\/p>\n<p>            if data.size == 0:<\/p>\n<p>                break<\/p>\n<p>            yield data<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2. \u4f7f\u7528\u751f\u6210\u5668<\/h4>\n<\/p>\n<p><p>\u901a\u8fc7\u751f\u6210\u5668\u9010\u6279\u5904\u7406\u6570\u636e\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">for data_batch in batch_load(&#39;large_data.txt&#39;, 100):<\/p>\n<p>    process_data_batch(data_batch)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u56db\u3001\u9010\u884c\u8bfb\u53d6\u6587\u4ef6<\/h3>\n<\/p>\n<p><p>\u9010\u884c\u8bfb\u53d6\u662f\u6700\u57fa\u7840\u7684\u6570\u636e\u8bfb\u53d6\u65b9\u5f0f\uff0c\u9002\u7528\u4e8e\u7b80\u5355\u7684\u6587\u672c\u5904\u7406\u4efb\u52a1\u3002<\/p>\n<\/p>\n<p><h4>1. \u6253\u5f00\u6587\u4ef6\u9010\u884c\u8bfb\u53d6<\/h4>\n<\/p>\n<p><pre><code class=\"language-python\">def process_line(line):<\/p>\n<p>    # \u5904\u7406\u6bcf\u884c\u6570\u636e<\/p>\n<p>    print(line)<\/p>\n<p>with open(&#39;large_file.txt&#39;, &#39;r&#39;) as file:<\/p>\n<p>    for line in file:<\/p>\n<p>        process_line(line.strip())<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2. \u4f7f\u7528<code>readlines<\/code>\u65b9\u6cd5<\/h4>\n<\/p>\n<p><p><code>readlines<\/code>\u65b9\u6cd5\u53ef\u4ee5\u4e00\u6b21\u8bfb\u53d6\u6240\u6709\u884c\uff0c\u4f46\u5728\u5927\u6587\u4ef6\u4e2d\u4e0d\u63a8\u8350\u4f7f\u7528\uff0c\u56e0\u4e3a\u5b83\u4f1a\u5360\u7528\u5927\u91cf\u5185\u5b58\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">with open(&#39;large_file.txt&#39;, &#39;r&#39;) as file:<\/p>\n<p>    lines = file.readlines()<\/p>\n<p>    for line in lines:<\/p>\n<p>        process_line(line.strip())<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u7ed3\u5408\u4f7f\u7528\u4ee5\u4e0a\u65b9\u6cd5\uff0cPython\u53ef\u4ee5\u9ad8\u6548\u5730\u6279\u6b21\u8bfb\u53d6\u548c\u5904\u7406\u5927\u89c4\u6a21\u6570\u636e\u96c6\u3002\u5728\u9009\u62e9\u65b9\u6cd5\u65f6\uff0c\u9700\u8981\u6839\u636e\u5177\u4f53\u7684\u5e94\u7528\u573a\u666f\u3001\u6570\u636e\u89c4\u6a21\u4ee5\u53ca\u5185\u5b58\u9650\u5236\u6765\u51b3\u5b9a\u6700\u5408\u9002\u7684\u65b9\u6848\u3002\u4f7f\u7528\u751f\u6210\u5668\u548cPandas\u7684<code>chunksize<\/code>\u529f\u80fd\u662f\u5e94\u5bf9\u5927\u6570\u636e\u7684\u5e38\u7528\u7b56\u7565\uff0c\u65e2\u53ef\u4ee5\u8282\u7701\u5185\u5b58\uff0c\u53c8\u80fd\u4fdd\u6301\u4ee3\u7801\u7684\u7b80\u6d01\u548c\u9ad8\u6548\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u5728Python\u4e2d\u9ad8\u6548\u5730\u8bfb\u53d6\u5927\u578b\u6570\u636e\u6587\u4ef6\uff1f<\/strong><br \/>\u5728\u5904\u7406\u5927\u578b\u6570\u636e\u6587\u4ef6\u65f6\uff0c\u53ef\u4ee5\u4f7f\u7528<code>pandas<\/code>\u5e93\u7684<code>read_csv<\/code>\u51fd\u6570\uff0c\u7ed3\u5408<code>chunksize<\/code>\u53c2\u6570\uff0c\u8fd9\u6837\u53ef\u4ee5\u4e00\u6b21\u8bfb\u53d6\u4e00\u5b9a\u91cf\u7684\u6570\u636e\uff0c\u907f\u514d\u5185\u5b58\u6ea2\u51fa\u3002\u793a\u4f8b\u4ee3\u7801\u5982\u4e0b\uff1a  <\/p>\n<pre><code class=\"language-python\">import pandas as pd\n\nfor chunk in pd.read_csv(&#39;large_file.csv&#39;, chunksize=1000):\n    # \u5bf9\u6bcf\u4e2a\u6570\u636e\u5757\u8fdb\u884c\u5904\u7406\n    process_data(chunk)\n<\/code><\/pre>\n<p>\u8fd9\u79cd\u65b9\u6cd5\u53ef\u4ee5\u4f7f\u6570\u636e\u5904\u7406\u66f4\u4e3a\u9ad8\u6548\uff0c\u540c\u65f6\u4e5f\u4fbf\u4e8e\u9010\u6b65\u5206\u6790\u6570\u636e\u3002<\/p>\n<p><strong>Python\u652f\u6301\u54ea\u4e9b\u6570\u636e\u683c\u5f0f\u7684\u6279\u91cf\u8bfb\u53d6\uff1f<\/strong><br \/>Python\u652f\u6301\u591a\u79cd\u6570\u636e\u683c\u5f0f\u7684\u6279\u91cf\u8bfb\u53d6\uff0c\u5305\u62ecCSV\u3001Excel\u3001JSON\u3001SQL\u6570\u636e\u5e93\u7b49\u3002\u4f7f\u7528<code>pandas<\/code>\u5e93\uff0c\u53ef\u4ee5\u8f7b\u677e\u5730\u8bfb\u53d6\u8fd9\u4e9b\u683c\u5f0f\u7684\u6570\u636e\u3002\u4f8b\u5982\uff0c<code>pd.read_excel()<\/code>\u7528\u4e8e\u8bfb\u53d6Excel\u6587\u4ef6\uff0c<code>pd.read_json()<\/code>\u7528\u4e8e\u8bfb\u53d6JSON\u6587\u4ef6\u3002\u6839\u636e\u5177\u4f53\u7684\u6570\u636e\u683c\u5f0f\u9009\u62e9\u5408\u9002\u7684\u8bfb\u53d6\u51fd\u6570\u5373\u53ef\u3002<\/p>\n<p><strong>\u5982\u4f55\u63d0\u9ad8Python\u6279\u91cf\u8bfb\u53d6\u6570\u636e\u7684\u901f\u5ea6\uff1f<\/strong><br \/>\u63d0\u9ad8\u6570\u636e\u8bfb\u53d6\u901f\u5ea6\u53ef\u4ee5\u901a\u8fc7\u51e0\u79cd\u65b9\u5f0f\u5b9e\u73b0\uff1a  <\/p>\n<ol>\n<li>\u4f7f\u7528<code>dask<\/code>\u5e93\uff0c\u5b83\u53ef\u4ee5\u5904\u7406\u5927\u89c4\u6a21\u6570\u636e\u5e76\u652f\u6301\u5e76\u884c\u8ba1\u7b97\u3002<\/li>\n<li>\u5728\u8bfb\u53d6CSV\u6587\u4ef6\u65f6\uff0c\u5408\u7406\u8bbe\u7f6e<code>dtype<\/code>\u53c2\u6570\uff0c\u4ee5\u51cf\u5c11\u81ea\u52a8\u63a8\u65ad\u6570\u636e\u7c7b\u578b\u6240\u9700\u7684\u65f6\u95f4\u3002<\/li>\n<li>\u4f7f\u7528<code>pyarrow<\/code>\u5e93\u6765\u52a0\u901fParquet\u548cFeather\u683c\u5f0f\u7684\u6570\u636e\u8bfb\u53d6\uff0c\u8fd9\u4e9b\u683c\u5f0f\u901a\u5e38\u6bd4CSV\u6587\u4ef6\u66f4\u5feb\u4e14\u5360\u7528\u66f4\u5c11\u7a7a\u95f4\u3002<br \/>\u91c7\u7528\u8fd9\u4e9b\u65b9\u6cd5\u53ef\u4ee5\u663e\u8457\u63d0\u9ad8\u6570\u636e\u8bfb\u53d6\u7684\u6548\u7387\u3002<\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"Python\u6279\u6b21\u8bfb\u53d6\u6570\u636e\u7684\u5e38\u7528\u65b9\u6cd5\u5305\u62ec\u4f7f\u7528\u751f\u6210\u5668\u3001Pandas\u5e93\u7684read_csv\u65b9\u6cd5\u3001NumPy\u7684loadt [&hellip;]","protected":false},"author":3,"featured_media":997007,"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\/997000"}],"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=997000"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/997000\/revisions"}],"predecessor-version":[{"id":997011,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/997000\/revisions\/997011"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/997007"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=997000"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=997000"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=997000"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}