{"id":100307,"date":"2020-05-02T02:26:12","date_gmt":"2020-05-01T18:26:12","guid":{"rendered":"http:\/\/4563.org\/?p=100307"},"modified":"2020-05-02T02:26:12","modified_gmt":"2020-05-01T18:26:12","slug":"pandas-loc-%e6%93%8d%e4%bd%9c%e4%bc%9a%e5%86%85%e5%ad%98%e6%b3%84%e6%bc%8f%ef%bc%9f","status":"publish","type":"post","link":"http:\/\/4563.org\/?p=100307","title":{"rendered":"pandas loc \u64cd\u4f5c\u4f1a\u5185\u5b58\u6cc4\u6f0f\uff1f"},"content":{"rendered":"
\n
\n
\n

pandas loc \u64cd\u4f5c\u4f1a\u5185\u5b58\u6cc4\u6f0f\uff1f <\/h1>\n

<\/p>\n

\n
\u8cc7\u6df1\u5927\u4f6c : wuwukai007 <\/span> <\/i> 54<\/span> <\/div>\n
<\/div>\n<\/p><\/div>\n<\/p><\/div>\n<\/p><\/div>\n
<\/p>\n

df = pd.DataFrame() df \u5927\u6982\u7528\u4e86 1.5GB \u5185\u5b58 \u7136\u540e\u6211 df = df.loc[xxx] df \u5207\u7247\u4e3a\u539f\u6765\u7684 10 \u5206\u4e4b\u4e00\uff0c\u7528 sys.getsizeof(df) df \u5185\u5b58\u4e3a 100 \u591a MB\uff0c\u4f46\u662f python \u7684\u5185\u5b58\u8fd8\u662f 1.5G+, \u600e\u4e48\u4f1a\u8fd9\u6837\u5462\uff1f \u7528\u4e86 gc.collect()\u4e5f\u662f\u4e0d\u884c<\/p>\n<\/p><\/div>\n

\u5927\u4f6c\u6709\u8a71\u8aaa<\/b> (14<\/span>) <\/div>\n
<\/div>\n<\/p><\/div>\n<\/p><\/div>\n
    \n
  • \n
    \n
    \n
    \u8cc7\u6df1\u5927\u4f6c : djj510620510 <\/span> <\/div>\n
    <\/i> <\/span> <\/div>\n<\/p><\/div>\n
    \u672a\u590d\u73b0\uff1a
    import pandas
    import sys<\/p>\n

    df = pandas.DataFrame([[j for j in range(100)] for i in range(10000)])
    print(sys.getsizeof(df)) # 8000104
    df = df.loc[:100]
    print(sys.getsizeof(df)) # 80904 <\/div>\n<\/p><\/div>\n<\/li>\n

  • \n
    \n
    \n
    \u8cc7\u6df1\u5927\u4f6c : djj510620510 <\/span> <\/div>\n
    <\/i> <\/span> <\/div>\n<\/p><\/div>\n
    @djj510620510 <\/p>\n

    \u662f\u4e0d\u662f df \u91cc\u9762\u6709 list \u6216\u8005 dict \u4e4b\u7c7b\u7684\u5f15\u7528\u7c7b\u578b\uff0c <\/p><\/div>\n<\/p><\/div>\n<\/li>\n

  • \n
    \n
    \n
    \u4e3b<\/span> \u8cc7\u6df1\u5927\u4f6c : wuwukai007 <\/span> <\/div>\n
    <\/i> <\/span> <\/div>\n<\/p><\/div>\n
    @djj510620510 \u5207\u7247\u540e\u5185\u5b58\u786e\u5b9e\u662f\u5c11\u4e86
    \u4f46\u662f\u4f60\u770b python \u7684\u5185\u5b58\uff0c\u6ca1\u91ca\u653e <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
    \u4e3b<\/span> \u8cc7\u6df1\u5927\u4f6c : wuwukai007 <\/span> <\/div>\n
    <\/i> <\/span> <\/div>\n<\/p><\/div>\n
    \u5728 ipython \u91cc\u9762\uff0c\u8fd9\u6837\u64cd\u4f5c\u540e\uff0c\u5207\u7247\u540e\u7684\u5185\u5b58\u5bf9\u8c61\u5c0f\u4e86\uff0c
    \u4f46\u662f\u67e5\u770b\u5f53\u524d python \u5360\u7528\u5185\u5b58\uff0c\u8fd8\u662f \u5207\u7247\u4e4b\u524d\u7684 <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
    \u8cc7\u6df1\u5927\u4f6c : djj510620510 <\/span> <\/div>\n
    <\/i> <\/span> <\/div>\n<\/p><\/div>\n
    @wuwukai007 <\/p>\n

    \u554a\uff0c\u6211\u770b\u6f0f\u4e86\uff0c\u7684\u786e\u662f\u5185\u5b58\u8fd8\u662f\u90a3\u4e48\u591a\u3002<\/p>\n

    \u4e0d\u8fc7\u6211\u518d\u6d4b\u4e86\u4e00\u4e0b\uff0c\u5982\u679c\u628a\u5904\u7406\u653e\u5230\u51fd\u6570\u91cc\u9762\u7684\u8bdd\uff0c\u51fd\u6570\u6267\u884c\u5b8c\u4e86\uff0c\u5185\u5b58\u5c31\u4f1a\u51cf\u5c11\uff1a<\/p>\n

    In [1]: def test():
    …: df = pandas.DataFrame([[j for j in range(1000)] for _ in range(10000)])
    …: df = df.loc[:100]
    …: return df
    …:<\/p>\n

    In [2]:<\/p>\n

    In [2]: import pandas<\/p>\n

    In [3]: a = test() <\/p><\/div>\n<\/p><\/div>\n<\/li>\n

  • \n
    \n
    \n
    \u8cc7\u6df1\u5927\u4f6c : Kelan <\/span> <\/div>\n
    <\/i> <\/span> <\/div>\n<\/p><\/div>\n
    python \u5c31\u6709\u8fd9\u79cd\u95ee\u9898\uff0c\u5982\u679c\u8fd0\u7b97\u8fc7\u7a0b\u5bf9\u5185\u5b58\u5f88\u7d27\u5f20\u7684\u8bdd\uff0c\u5efa\u8bae\u5f00\u5b50\u8fdb\u7a0b\uff0c\u7528\u5b8c\u9500\u6bc1 <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
    \u8cc7\u6df1\u5927\u4f6c : zk8802 <\/span> <\/div>\n
    <\/i> <\/span> <\/div>\n<\/p><\/div>\n
    IPython \u7684 In \u4e0e Out \u662f\u4e0d\u662f\u4fdd\u6301\u4e86\u5207\u7247\u4e4b\u524d\u7684\u6570\u7ec4\u7684\u5f15\u7528\uff1f\u8bd5\u8bd5 IPython.display.clear_output() <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
    \u8cc7\u6df1\u5927\u4f6c : jyyx <\/span> <\/div>\n
    <\/i> <\/span> <\/div>\n<\/p><\/div>\n
    \u7528 ipython \u4f60\u53ef\u4ee5\u770b\u4e0b globals()\u91cc\u9762\u8fd8\u6709\u539f\u6765\u7684\u53d8\u91cf <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
    \u4e3b<\/span> \u8cc7\u6df1\u5927\u4f6c : wuwukai007 <\/span> <\/div>\n
    <\/i> <\/span> <\/div>\n<\/p><\/div>\n
    @Kelan @djj510620510 @zk8802
    \u7528\u4e86\u4e00\u4e2a\u66f2\u7ebf\u7684\u65b9\u6cd5\uff0c
    df2 = df.loc[:100].copy()
    del df
    \u4f46\u662f\u6709\u4e00\u4e2a\u95ee\u9898\uff0c\u5982\u679c\u5207\u7247\u7684\u6570\u636e\u4e5f\u662f\u5f88\u591a\u7684\u8bdd\u6bd4\u5982\u6e90\u6570\u636e 1.5G \u5207\u4e00\u822c\uff0c
    \u8fd9\u6837\u66f2\u7ebf\u505a\u8fd8\u662f\u4f1a\u4e34\u65f6\u589e\u52a0 800MB \u7684\u5185\u5b58\u3002\u3002\u3002\u3002 <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
    \u4e3b<\/span> \u8cc7\u6df1\u5927\u4f6c : wuwukai007 <\/span> <\/div>\n
    <\/i> <\/span> <\/div>\n<\/p><\/div>\n
    @jyyx @zk8802
    \u4e0d\u662f ipython \u7684\u95ee\u9898\uff0c\u6211\u5728\u811a\u672c\u91cc\u8dd1\u53d1\u73b0\u8fd9\u4e2a\u95ee\u9898\u624d\u5728 ipython \u91cc\u9762\u6d4b\u8bd5\u7684 <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
    \u8cc7\u6df1\u5927\u4f6c : zk8802 <\/span> <\/div>\n
    <\/i> <\/span> <\/div>\n<\/p><\/div>\n
    \u8bd5\u8bd5\u5f3a\u5236 garbage collection:
    import gc; gc.collect() <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
    \u8cc7\u6df1\u5927\u4f6c : cheng6563 <\/span> <\/div>\n
    <\/i> <\/span> <\/div>\n<\/p><\/div>\n
    \u4e0d\u61c2 python\uff0c\u4f1a\u4e0d\u4f1a\u662f gc \u56de\u6536\u5185\u5b58\u540e\u4e0d\u4f1a\u5b9e\u65f6\u628a\u5185\u5b58\u8fd8\u7ed9\u64cd\u4f5c\u7cfb\u7edf\u3002 <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
    \u8cc7\u6df1\u5927\u4f6c : TPOB <\/span> <\/div>\n
    <\/i> <\/span> <\/div>\n<\/p><\/div>\n
    \u6211\u4e4b\u524d\u4e5f\u9047\u5230\u8fc7\u7c7b\u4f3c\u7684\u60c5\u51b5\uff0c\u540e\u6765\u50cf\u4e0a\u8bf4\u7684\u7528\u5b50\u8fdb\u7a0b\u4e86 <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n
    \n
    \n
    \u8cc7\u6df1\u5927\u4f6c : jyyx <\/span> <\/div>\n
    <\/i> <\/span> <\/div>\n<\/p><\/div>\n
    \u6211\u8bd5\u4e86\u4e0b\u7684\u786e\u7528\u5207\u7247\u4f1a\u6709\u95ee\u9898
    df = df.loc[xxx, :] \u8fd9\u6837\u5199\u4f1a\u6709\u95ee\u9898
    \u53ef\u4ee5\u8bd5\u4e0b\u6539\u6210 df.drop(xxxx, inplace=True) <\/div>\n<\/p><\/div>\n<\/li>\n
  • \n","protected":false},"excerpt":{"rendered":"

    pandas loc \u64cd\u4f5c\u4f1a\u5185\u5b58\u6cc4…<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[],"tags":[],"_links":{"self":[{"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/posts\/100307"}],"collection":[{"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=100307"}],"version-history":[{"count":0,"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/posts\/100307\/revisions"}],"wp:attachment":[{"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=100307"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=100307"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=100307"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}