{"id":3254,"date":"2023-07-18T11:09:02","date_gmt":"2023-07-18T11:09:02","guid":{"rendered":"https:\/\/statorials.org\/cn\/%e6%af%8f%e5%91%a8%e6%9c%89%e4%b8%80%e7%be%a4%e7%86%8a%e7%8c%ab\/"},"modified":"2023-07-18T11:09:02","modified_gmt":"2023-07-18T11:09:02","slug":"%e6%af%8f%e5%91%a8%e6%9c%89%e4%b8%80%e7%be%a4%e7%86%8a%e7%8c%ab","status":"publish","type":"post","link":"https:\/\/statorials.org\/cn\/%e6%af%8f%e5%91%a8%e6%9c%89%e4%b8%80%e7%be%a4%e7%86%8a%e7%8c%ab\/","title":{"rendered":"\u5982\u4f55\u5728 pandas dataframe \u4e2d\u6309\u5468\u5206\u7ec4\uff08\u4e3e\u4f8b\uff09"},"content":{"rendered":"

<\/p>\n

\n

\u60a8\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u57fa\u672c\u8bed\u6cd5\u5728 pandas DataFrame \u4e2d\u6309\u5468\u5bf9\u884c\u8fdb\u884c\u5206\u7ec4\uff1a<\/span><\/p>\n

 #convert date column to datetime and subtract one week<\/span>\ndf[' date<\/span> '] = pd. to_datetime<\/span> (df[' date<\/span> ']) - pd. to_timedelta<\/span> (7, unit=' d<\/span> ')\n\n#calculate sum of values, grouped by week\n<\/span>df. groupby<\/span> ([pd. Group<\/span> (key=' date<\/span> ', freq=' W<\/span> ')])[' values<\/span> ']. sum<\/span> ()\n<\/strong><\/pre>\n
\u8fd9\u4e2a\u7279\u5b9a\u7684\u516c\u5f0f\u6309\u5468\u5bf9\u65e5\u671f<\/strong>\u5217\u4e2d\u7684\u884c\u8fdb\u884c\u5206\u7ec4\uff0c\u5e76\u8ba1\u7b97 DataFrame \u4e2d\u503c\u5217\u7684\u503c\u7684<\/strong>\u603b\u548c\u3002<\/span><\/p>\n
\u4ee5\u4e0b\u793a\u4f8b\u5c55\u793a\u4e86\u5982\u4f55\u5728\u5b9e\u8df5\u4e2d\u4f7f\u7528\u6b64\u8bed\u6cd5\u3002<\/span><\/p>\n
\u793a\u4f8b\uff1a\u5982\u4f55\u5728 Pandas \u4e2d\u6309\u5468\u5206\u7ec4<\/strong><\/span><\/h2>\n
\u5047\u8bbe\u6211\u4eec\u6709\u4ee5\u4e0b pandas DataFrame\uff0c\u5b83\u663e\u793a\u4e86\u4e00\u5bb6\u516c\u53f8\u5728\u4e0d\u540c\u65e5\u671f\u7684\u9500\u552e\u989d\uff1a<\/span><\/p>\n
 import<\/span> pandas as<\/span> pd\n\n#createDataFrame<\/span>\ndf = pd. DataFrame<\/span> ({' date<\/span> ': pd. date_range<\/span> (start='1\/5\/2022', freq='D', periods=15),\n                   ' sales<\/span> ': [6, 8, 9, 5, 4, 8, 8, 3, 5, 9, 8, 3, 4, 7, 7]})\n\n#view DataFrame\nprint<\/span><\/span> (df)\n\n         dirty date\n0 2022-01-05 6\n1 2022-01-06 8\n2 2022-01-07 9\n3 2022-01-08 5\n4 2022-01-09 4\n5 2022-01-10 8\n6 2022-01-11 8\n7 2022-01-12 3\n8 2022-01-13 5\n9 2022-01-14 9\n10 2022-01-15 8\n11 2022-01-16 3\n12 2022-01-17 4\n13 2022-01-18 7\n14 2022-01-19 7\n<\/strong><\/span><\/pre>\n
\u76f8\u5173\uff1a<\/strong>\u5982\u4f55\u5728 Pandas \u4e2d\u521b\u5efa\u65e5\u671f\u8303\u56f4<\/a><\/span><\/p>\n
\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u8bed\u6cd5\u6765\u8ba1\u7b97\u6309\u5468\u5206\u7ec4\u7684\u9500\u552e\u989d\u603b\u548c\uff1a<\/span><\/p>\n
 #convert date column to datetime and subtract one week<\/span>\ndf[' date<\/span> '] = pd. to_datetime<\/span> (df[' date<\/span> ']) - pd. to_timedelta<\/span> (7, unit=' d<\/span> ')\n\n#calculate sum of values, grouped by week\n<\/span>df. groupby<\/span> ([pd. Group<\/span> (key=' date<\/span> ', freq=' W<\/span> ')])[' sales<\/span> ']. sum<\/span> ()\n\ndate\n2022-01-02 32\n2022-01-09 44\n2022-01-16 18\nFreq: W-SUN, Name: sales, dtype: int64\n<\/strong><\/pre>\n
\u4ee5\u4e0b\u662f\u5982\u4f55\u89e3\u91ca\u7ed3\u679c\uff1a<\/span><\/p>\n