RollingRank赚钱- Sharp-1.43
This commit is contained in:
liaozhaorun
16
.vscode/launch.json
vendored
Normal file
16
.vscode/launch.json
vendored
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
// 使用 IntelliSense 了解相关属性。
|
||||
// 悬停以查看现有属性的描述。
|
||||
// 欲了解更多信息，请访问: https://go.microsoft.com/fwlink/?linkid=830387
|
||||
"version": "0.2.0",
|
||||
"configurations": [
|
||||
{
|
||||
"name": "Python 调试程序: 当前文件",
|
||||
"type": "debugpy",
|
||||
"request": "launch",
|
||||
"program": "${file}",
|
||||
"console": "integratedTerminal",
|
||||
"cwd": "${fileDirname}"
|
||||
}
|
||||
]
|
||||
}
|
||||
7
.vscode/settings.json
vendored
Normal file
7
.vscode/settings.json
vendored
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"terminal.integrated.env.windows": {
|
||||
"PYTHONPATH": "${workspaceFolder};${env:PYTHONPATH}"
|
||||
},
|
||||
"jupyter.notebookFileRoot": "${fileDirname}",
|
||||
"python.dataScience.notebookFileRoot": "${workspaceFolder}"
|
||||
}
|
||||
@@ -1,5 +0,0 @@
|
||||
import torch
|
||||
print(torch.__version__)
|
||||
|
||||
print(torch.version.cuda)
|
||||
print(torch.backends.cudnn.version())
|
||||
File diff suppressed because one or more lines are too long
@@ -1,550 +0,0 @@
|
||||
trade_date,score,ts_code
|
||||
2022-12-29,0.5993496915237099,002033.SZ
|
||||
2022-12-30,0.5982905658824365,002095.SZ
|
||||
2023-01-03,0.43226183271936897,603882.SH
|
||||
2023-01-04,0.38835119822057007,603778.SH
|
||||
2023-01-05,0.6164292223678971,600113.SH
|
||||
2023-01-06,0.4724355189732064,002235.SZ
|
||||
2023-01-09,0.5134253220843772,002235.SZ
|
||||
2023-01-10,0.6207586842564803,605133.SH
|
||||
2023-01-11,0.5010433264248937,603613.SH
|
||||
2023-01-12,0.7015949128879678,002929.SZ
|
||||
2023-01-13,0.498544619104055,002823.SZ
|
||||
2023-01-16,0.4970324220479829,600658.SH
|
||||
2023-01-17,0.4115451783077775,000915.SZ
|
||||
2023-01-18,0.5051002083292306,002319.SZ
|
||||
2023-01-19,0.5926594478068454,002787.SZ
|
||||
2023-01-20,0.5600276908127407,002297.SZ
|
||||
2023-01-30,0.32895150606899143,002393.SZ
|
||||
2023-01-31,0.47280242914852283,601028.SH
|
||||
2023-02-01,0.7083201481019531,002253.SZ
|
||||
2023-02-02,0.41838398522919074,000534.SZ
|
||||
2023-02-03,0.4253220985948224,001266.SZ
|
||||
2023-02-06,0.6513266912105381,002806.SZ
|
||||
2023-02-07,0.47054220485721643,002995.SZ
|
||||
2023-02-08,0.46324632676699906,002748.SZ
|
||||
2023-02-09,0.6827350634512621,002354.SZ
|
||||
2023-02-10,0.4821352678819063,603300.SH
|
||||
2023-02-13,0.4217998924592719,603255.SH
|
||||
2023-02-14,0.41516502997541105,002354.SZ
|
||||
2023-02-15,0.523038598093662,000584.SZ
|
||||
2023-02-16,0.4810251131099421,603939.SH
|
||||
2023-02-17,0.46474941799229114,000983.SZ
|
||||
2023-02-20,0.6359527503415816,002229.SZ
|
||||
2023-02-21,0.2619253505063698,601212.SH
|
||||
2023-02-22,0.40658765528751784,601728.SH
|
||||
2023-02-23,0.4536434446282197,600331.SH
|
||||
2023-02-24,0.4195896415311142,002112.SZ
|
||||
2023-02-27,0.5217013872423114,002633.SZ
|
||||
2023-02-28,0.6374768326230712,603848.SH
|
||||
2023-03-01,0.2923378034053084,603528.SH
|
||||
2023-03-02,0.5800443754990299,601985.SH
|
||||
2023-03-03,0.47947515982865924,601566.SH
|
||||
2023-03-06,0.47737030446971823,600066.SH
|
||||
2023-03-07,0.3046203388776064,603722.SH
|
||||
2023-03-08,0.36582859188869005,601989.SH
|
||||
2023-03-09,0.48435052711258203,000617.SZ
|
||||
2023-03-10,0.36191241071341823,601188.SH
|
||||
2023-03-13,0.5728794198521735,600755.SH
|
||||
2023-03-14,0.4712816920394215,002796.SZ
|
||||
2023-03-15,0.54608440483593,601727.SH
|
||||
2023-03-16,0.529528195405985,002552.SZ
|
||||
2023-03-17,0.6026333408351228,601728.SH
|
||||
2023-03-20,0.6293021786167095,000032.SZ
|
||||
2023-03-21,0.4285123137413733,601138.SH
|
||||
2023-03-22,0.17692098945207105,600449.SH
|
||||
2023-03-23,0.522735444504978,603083.SH
|
||||
2023-03-24,0.3358637305583264,603236.SH
|
||||
2023-03-27,0.7491971748091738,603019.SH
|
||||
2023-03-28,0.7742172550592232,002236.SZ
|
||||
2023-03-29,0.6024815895542033,601858.SH
|
||||
2023-03-30,0.7174781312512657,000688.SZ
|
||||
2023-03-31,0.7162578431071085,002153.SZ
|
||||
2023-04-03,0.36128500062338526,600329.SH
|
||||
2023-04-04,0.38924629987793036,000975.SZ
|
||||
2023-04-06,0.5607887349405704,600839.SH
|
||||
2023-04-07,0.5264099142951268,600271.SH
|
||||
2023-04-10,0.6887949110691621,002275.SZ
|
||||
2023-04-11,-0.013340990648672061,002222.SZ
|
||||
2023-04-12,0.7012128435045554,002292.SZ
|
||||
2023-04-13,0.6712018186785565,603083.SH
|
||||
2023-04-14,0.49448523181796267,002654.SZ
|
||||
2023-04-17,0.2606690807343395,600603.SH
|
||||
2023-04-18,0.3506372217417399,600970.SH
|
||||
2023-04-19,0.4883574224012403,603019.SH
|
||||
2023-04-20,0.5145774440150311,600895.SH
|
||||
2023-04-21,0.5869040515080466,603258.SH
|
||||
2023-04-24,0.21583248767382618,603168.SH
|
||||
2023-04-25,0.5893195075497377,601595.SH
|
||||
2023-04-26,0.6971837449043878,002607.SZ
|
||||
2023-04-27,0.6749787938163464,600072.SH
|
||||
2023-04-28,0.42265788643909996,002531.SZ
|
||||
2023-05-04,0.7147352354273715,601333.SH
|
||||
2023-05-05,0.5126569134092169,601900.SH
|
||||
2023-05-08,0.6388788590952813,601801.SH
|
||||
2023-05-09,0.4628154880114463,601988.SH
|
||||
2023-05-10,0.3680072646021139,603042.SH
|
||||
2023-05-11,0.5793990274548498,000156.SZ
|
||||
2023-05-12,0.6361002944919518,600846.SH
|
||||
2023-05-15,0.5939493214011368,002749.SZ
|
||||
2023-05-16,0.7151151942359552,600137.SH
|
||||
2023-05-17,0.33308578670102396,603516.SH
|
||||
2023-05-18,0.7246909479156244,603070.SH
|
||||
2023-05-19,0.6163873089697439,603863.SH
|
||||
2023-05-22,0.46732429612549925,603685.SH
|
||||
2023-05-23,0.4012003242341679,001289.SZ
|
||||
2023-05-24,0.45583236124726323,002403.SZ
|
||||
2023-05-25,0.4179847845015258,603618.SH
|
||||
2023-05-26,0.49333506152988005,603699.SH
|
||||
2023-05-29,0.20693126993200314,000600.SZ
|
||||
2023-05-30,0.3216088340945225,002217.SZ
|
||||
2023-05-31,0.3975875358537317,603888.SH
|
||||
2023-06-01,0.6699778999036027,603888.SH
|
||||
2023-06-02,0.4766387067466558,002649.SZ
|
||||
2023-06-05,0.42010051011352373,603721.SH
|
||||
2023-06-06,0.49617555019114346,600825.SH
|
||||
2023-06-07,0.46993149983245075,000810.SZ
|
||||
2023-06-08,0.45527019920556644,600326.SH
|
||||
2023-06-09,0.3838883478919911,603685.SH
|
||||
2023-06-12,0.049849788522711665,003000.SZ
|
||||
2023-06-13,0.4463959137482046,002351.SZ
|
||||
2023-06-14,0.2724278555068798,002213.SZ
|
||||
2023-06-15,0.40225157256614297,603083.SH
|
||||
2023-06-16,0.5093788699168762,000977.SZ
|
||||
2023-06-19,0.6005876028877897,600072.SH
|
||||
2023-06-20,0.6362663028040699,605118.SH
|
||||
2023-06-21,0.6267770435866252,002865.SZ
|
||||
2023-06-26,0.4276111800347391,000539.SZ
|
||||
2023-06-27,0.45229780826455573,000539.SZ
|
||||
2023-06-28,0.439381781937665,002530.SZ
|
||||
2023-06-29,0.5405172453678457,603489.SH
|
||||
2023-06-30,0.3067701763761109,603255.SH
|
||||
2023-07-03,0.6011176016260282,002852.SZ
|
||||
2023-07-04,0.36621877921674334,600301.SH
|
||||
2023-07-05,0.43634158461187017,603118.SH
|
||||
2023-07-06,0.5027049980817844,600237.SH
|
||||
2023-07-07,0.5318395655297332,601116.SH
|
||||
2023-07-10,0.17576252976088974,002115.SZ
|
||||
2023-07-11,0.3368101850262645,605377.SH
|
||||
2023-07-12,0.2777538991748908,600851.SH
|
||||
2023-07-13,0.5815872018719028,001210.SZ
|
||||
2023-07-14,0.37666579836351755,002150.SZ
|
||||
2023-07-17,0.5207998829241304,603879.SH
|
||||
2023-07-18,0.5376239361188119,002723.SZ
|
||||
2023-07-19,0.5273840265099533,603938.SH
|
||||
2023-07-20,0.6858890521699894,002316.SZ
|
||||
2023-07-21,0.5261123602949379,003012.SZ
|
||||
2023-07-24,0.547147880532049,601966.SH
|
||||
2023-07-25,0.13788677283224893,603755.SH
|
||||
2023-07-26,0.13550085701030903,600606.SH
|
||||
2023-07-27,0.4785736932592976,002304.SZ
|
||||
2023-07-28,0.6704107966995335,000987.SZ
|
||||
2023-07-31,0.27871862372662504,000932.SZ
|
||||
2023-08-01,0.4049111188564386,002671.SZ
|
||||
2023-08-02,0.4060731245124435,000627.SZ
|
||||
2023-08-03,0.41265478848539217,600881.SH
|
||||
2023-08-04,0.21506937225407133,000514.SZ
|
||||
2023-08-07,0.6627610179095694,600743.SH
|
||||
2023-08-08,0.4355172724619028,000627.SZ
|
||||
2023-08-09,0.1816113802306989,000813.SZ
|
||||
2023-08-10,0.6154262293658468,000813.SZ
|
||||
2023-08-11,0.5367191420113877,002589.SZ
|
||||
2023-08-14,0.6326609540795168,000668.SZ
|
||||
2023-08-15,0.5320539234012944,600713.SH
|
||||
2023-08-16,0.3150745165344159,603665.SH
|
||||
2023-08-17,0.7663699019981299,001299.SZ
|
||||
2023-08-18,0.20779298609823746,603389.SH
|
||||
2023-08-21,0.5123346116515574,002006.SZ
|
||||
2023-08-22,0.5017363613028969,000006.SZ
|
||||
2023-08-23,0.18857297707037118,603220.SH
|
||||
2023-08-24,0.6937184703493717,002178.SZ
|
||||
2023-08-25,0.46923563320730854,600456.SH
|
||||
2023-08-28,0.6928686399989369,600745.SH
|
||||
2023-08-29,0.4486262249333005,603080.SH
|
||||
2023-08-30,0.36638385265763895,600257.SH
|
||||
2023-08-31,0.2620421554320702,603059.SH
|
||||
2023-09-01,0.45650430215252724,601086.SH
|
||||
2023-09-04,0.45300828900435075,603220.SH
|
||||
2023-09-05,0.33836919086447914,002178.SZ
|
||||
2023-09-06,0.3523776950519563,600702.SH
|
||||
2023-09-07,0.30264785324247073,002725.SZ
|
||||
2023-09-08,0.4374410877017653,002455.SZ
|
||||
2023-09-11,0.40357917933365633,003019.SZ
|
||||
2023-09-12,0.33552548994157866,603629.SH
|
||||
2023-09-13,0.20089687418027624,003043.SZ
|
||||
2023-09-14,0.2628097252542422,605028.SH
|
||||
2023-09-15,0.6488324013929223,600155.SH
|
||||
2023-09-18,0.3689895119626205,600706.SH
|
||||
2023-09-19,0.6361407903443482,000506.SZ
|
||||
2023-09-20,0.4920713764815601,603667.SH
|
||||
2023-09-21,0.5447514269089377,600814.SH
|
||||
2023-09-22,0.6853983507399647,002555.SZ
|
||||
2023-09-25,0.7361312667283009,600603.SH
|
||||
2023-09-26,0.6018758704099867,002401.SZ
|
||||
2023-09-27,0.584498352856423,605598.SH
|
||||
2023-09-28,0.5493103652031055,002605.SZ
|
||||
2023-10-09,0.14042322562796788,000936.SZ
|
||||
2023-10-10,0.6232596725993803,603616.SH
|
||||
2023-10-11,0.6791881628803146,603108.SH
|
||||
2023-10-12,0.4775924021857536,000700.SZ
|
||||
2023-10-13,0.4607444966146002,603863.SH
|
||||
2023-10-16,0.3605587332601004,601127.SH
|
||||
2023-10-17,0.6942097443890859,603269.SH
|
||||
2023-10-18,0.48235452929172296,603123.SH
|
||||
2023-10-19,0.500976676364544,002843.SZ
|
||||
2023-10-20,0.5980063208858518,600133.SH
|
||||
2023-10-23,0.5472315903049835,000712.SZ
|
||||
2023-10-24,0.33222159500351023,002385.SZ
|
||||
2023-10-25,0.26306038823677497,000797.SZ
|
||||
2023-10-26,0.36557105118084904,603528.SH
|
||||
2023-10-27,0.4998454678651184,002232.SZ
|
||||
2023-10-30,0.47785381969370666,603110.SH
|
||||
2023-10-31,0.29586764546156813,001319.SZ
|
||||
2023-11-01,0.21471136454108097,600792.SH
|
||||
2023-11-02,0.5475478410642985,600200.SH
|
||||
2023-11-03,0.5167221298806568,002238.SZ
|
||||
2023-11-06,0.3168057635451115,002420.SZ
|
||||
2023-11-07,-0.008519117226339919,603108.SH
|
||||
2023-11-08,0.5772228219786281,002981.SZ
|
||||
2023-11-09,0.5412574517146544,000096.SZ
|
||||
2023-11-10,0.7088352669535767,002590.SZ
|
||||
2023-11-13,0.6091298687606299,002875.SZ
|
||||
2023-11-14,0.6138540836612464,600246.SH
|
||||
2023-11-15,0.5703935902150659,600476.SH
|
||||
2023-11-16,0.6842630957277974,600506.SH
|
||||
2023-11-17,0.051723230294036034,002243.SZ
|
||||
2023-11-20,0.4372901317153261,001300.SZ
|
||||
2023-11-21,0.6329997553518004,603488.SH
|
||||
2023-11-22,0.6106038500441885,605218.SH
|
||||
2023-11-23,0.5661810065113655,002183.SZ
|
||||
2023-11-24,0.5626845716842617,001300.SZ
|
||||
2023-11-27,0.3699263484177057,600104.SH
|
||||
2023-11-28,0.28307222625592743,002919.SZ
|
||||
2023-11-29,0.6035537659610918,600605.SH
|
||||
2023-11-30,0.653341344692497,603211.SH
|
||||
2023-12-01,0.5479395522480961,002992.SZ
|
||||
2023-12-04,0.239409803949225,002561.SZ
|
||||
2023-12-05,0.5668249585663452,600692.SH
|
||||
2023-12-06,0.4780046612711487,002728.SZ
|
||||
2023-12-07,0.6151978929354516,600133.SH
|
||||
2023-12-08,0.46494086099626936,600398.SH
|
||||
2023-12-11,0.4061355033271394,603893.SH
|
||||
2023-12-12,0.454319344141846,002647.SZ
|
||||
2023-12-13,0.5056906168352251,600310.SH
|
||||
2023-12-14,0.5027794895552392,600560.SH
|
||||
2023-12-15,0.5925314880074004,002722.SZ
|
||||
2023-12-18,0.5124347230383429,600630.SH
|
||||
2023-12-19,0.5045301623066814,600159.SH
|
||||
2023-12-20,0.6247718523819663,605289.SH
|
||||
2023-12-21,-0.4803141323936112,603721.SH
|
||||
2023-12-22,0.27722679618769086,002942.SZ
|
||||
2023-12-25,0.3437093338598872,002952.SZ
|
||||
2023-12-26,0.5487536060015243,603615.SH
|
||||
2023-12-27,0.40743460382054403,603305.SH
|
||||
2023-12-28,0.6070769622657148,600630.SH
|
||||
2023-12-29,0.6582481158932626,002975.SZ
|
||||
2024-01-02,0.6624801006633897,603577.SH
|
||||
2024-01-03,0.506637896838537,600506.SH
|
||||
2024-01-04,0.5294025542238122,601801.SH
|
||||
2024-01-05,0.6101332210007661,002357.SZ
|
||||
2024-01-08,0.45447435436913936,002872.SZ
|
||||
2024-01-09,0.601915036202202,601188.SH
|
||||
2024-01-10,0.46295663419356203,001339.SZ
|
||||
2024-01-11,0.4549854971211364,603908.SH
|
||||
2024-01-12,0.36842497172059696,002140.SZ
|
||||
2024-01-15,0.43295477058318227,002868.SZ
|
||||
2024-01-16,0.34964387965090865,002779.SZ
|
||||
2024-01-17,0.6667126529120687,603800.SH
|
||||
2024-01-18,0.5436862698431507,002085.SZ
|
||||
2024-01-19,0.41105775665050137,002211.SZ
|
||||
2024-01-22,0.08992699031869929,600309.SH
|
||||
2024-01-23,0.3984935911993216,601988.SH
|
||||
2024-01-24,0.47817300180187694,003027.SZ
|
||||
2024-01-25,0.3487405928974409,601318.SH
|
||||
2024-01-26,0.3673715251392754,603122.SH
|
||||
2024-01-29,0.579027323650313,601668.SH
|
||||
2024-01-30,0.7927634486628847,601989.SH
|
||||
2024-01-31,0.7179008397683367,003816.SZ
|
||||
2024-02-01,0.6744052120546438,601186.SH
|
||||
2024-02-02,-0.09247964089462996,601319.SH
|
||||
2024-02-05,0.5804815004605282,601319.SH
|
||||
2024-02-06,0.45023793044060356,601658.SH
|
||||
2024-02-07,0.2621645071447008,603288.SH
|
||||
2024-02-08,0.27767628925434124,600036.SH
|
||||
2024-02-19,0.4365016246580571,601100.SH
|
||||
2024-02-20,0.6326656591037746,600754.SH
|
||||
2024-02-21,0.48020036053803067,000695.SZ
|
||||
2024-02-22,0.285551951897634,601398.SH
|
||||
2024-02-23,0.3176395264650533,603196.SH
|
||||
2024-02-26,-0.026515860428770643,002882.SZ
|
||||
2024-02-27,0.3072774878902384,002862.SZ
|
||||
2024-02-28,0.40650267884715247,002915.SZ
|
||||
2024-02-29,0.374012583347856,600610.SH
|
||||
2024-03-01,0.5097516871976601,600522.SH
|
||||
2024-03-04,0.45743528169930314,600498.SH
|
||||
2024-03-05,0.29520354685673805,603191.SH
|
||||
2024-03-06,0.6332834077496753,000628.SZ
|
||||
2024-03-07,0.4615916248623856,603099.SH
|
||||
2024-03-08,0.506962555062412,601918.SH
|
||||
2024-03-11,0.5961455851418274,000628.SZ
|
||||
2024-03-12,0.21785357748956846,002591.SZ
|
||||
2024-03-13,0.5203002232589222,600990.SH
|
||||
2024-03-14,0.5896398729013633,002313.SZ
|
||||
2024-03-15,0.6015442752305709,603261.SH
|
||||
2024-03-18,0.7297475381443272,001300.SZ
|
||||
2024-03-19,0.5183335586197945,002544.SZ
|
||||
2024-03-20,0.7230921381216405,600178.SH
|
||||
2024-03-21,0.7167433324190414,600818.SH
|
||||
2024-03-22,0.4761109649551903,600006.SH
|
||||
2024-03-25,0.44463988917863584,603408.SH
|
||||
2024-03-26,0.5976105195705241,600083.SH
|
||||
2024-03-27,0.2715303340494668,000020.SZ
|
||||
2024-03-28,0.5210975672972903,600577.SH
|
||||
2024-03-29,0.8590064547094538,603679.SH
|
||||
2024-04-01,0.2574204839222071,600200.SH
|
||||
2024-04-02,0.4960141109250312,603339.SH
|
||||
2024-04-03,0.576219107136073,002753.SZ
|
||||
2024-04-08,0.36707129328605576,000833.SZ
|
||||
2024-04-09,0.4840662729473024,605198.SH
|
||||
2024-04-10,0.5551658762335594,002842.SZ
|
||||
2024-04-11,0.5739287309474366,000528.SZ
|
||||
2024-04-12,0.3597546589711768,603988.SH
|
||||
2024-04-15,0.43616618245028455,600377.SH
|
||||
2024-04-16,0.5652581119540648,600566.SH
|
||||
2024-04-17,0.3107497799300893,600820.SH
|
||||
2024-04-18,0.278225553139572,600177.SH
|
||||
2024-04-19,0.5298867340143326,600761.SH
|
||||
2024-04-22,0.35277109900199877,000333.SZ
|
||||
2024-04-23,0.2717244611562532,603112.SH
|
||||
2024-04-24,0.46861984657329575,001696.SZ
|
||||
2024-04-25,0.45949404291871215,002364.SZ
|
||||
2024-04-26,0.28992311742373694,002296.SZ
|
||||
2024-04-29,0.40398504188143913,605255.SH
|
||||
2024-04-30,0.42757165709326495,002085.SZ
|
||||
2024-05-06,0.4266611853832811,000546.SZ
|
||||
2024-05-07,0.3840360967098266,601069.SH
|
||||
2024-05-08,0.4620099265747788,000698.SZ
|
||||
2024-05-09,0.2481887655386492,001205.SZ
|
||||
2024-05-10,0.6154721428668257,600645.SH
|
||||
2024-05-13,0.27657800476342925,603986.SH
|
||||
2024-05-14,0.43889305910264775,605266.SH
|
||||
2024-05-15,0.5616666330619532,002805.SZ
|
||||
2024-05-16,0.30399319047340156,002244.SZ
|
||||
2024-05-17,0.39283219107712214,600376.SH
|
||||
2024-05-20,0.29090758221269003,002975.SZ
|
||||
2024-05-21,0.5606517618909638,002074.SZ
|
||||
2024-05-22,0.7621495610963794,600675.SH
|
||||
2024-05-23,0.46402194151059933,603062.SH
|
||||
2024-05-24,0.43546631287178944,001201.SZ
|
||||
2024-05-27,0.40113230199193795,002737.SZ
|
||||
2024-05-28,0.18649522050725045,600000.SH
|
||||
2024-05-29,0.4642902384655265,000958.SZ
|
||||
2024-05-30,0.33734597168313746,002016.SZ
|
||||
2024-05-31,0.6197774925920987,603598.SH
|
||||
2024-06-03,0.5431165555013201,601020.SH
|
||||
2024-06-04,0.31316944674769853,002913.SZ
|
||||
2024-06-05,0.6035291959051149,002149.SZ
|
||||
2024-06-06,0.2540892303993234,603665.SH
|
||||
2024-06-07,0.47842845250564225,601398.SH
|
||||
2024-06-11,0.3146902368949125,600683.SH
|
||||
2024-06-12,0.6432549051280668,600123.SH
|
||||
2024-06-13,0.23800231645439224,002408.SZ
|
||||
2024-06-14,0.15226813323151922,002856.SZ
|
||||
2024-06-17,0.47565645731093625,002709.SZ
|
||||
2024-06-18,0.44932612957892926,600601.SH
|
||||
2024-06-19,0.39542884763678066,600269.SH
|
||||
2024-06-20,0.327102036042336,600686.SH
|
||||
2024-06-21,0.3833796567203426,600094.SH
|
||||
2024-06-24,0.5982665645963915,002943.SZ
|
||||
2024-06-25,0.20899979538875846,601988.SH
|
||||
2024-06-26,0.6901592527781292,000863.SZ
|
||||
2024-06-27,0.6221234326649174,600216.SH
|
||||
2024-06-28,0.5252595668594158,601668.SH
|
||||
2024-07-01,0.6450838481295202,003816.SZ
|
||||
2024-07-02,0.4650441286452329,600556.SH
|
||||
2024-07-03,0.2570346528746614,600310.SH
|
||||
2024-07-04,0.5072867070953532,601288.SH
|
||||
2024-07-05,0.40509078780149366,000820.SZ
|
||||
2024-07-08,0.6794583459324044,002384.SZ
|
||||
2024-07-09,0.558963551001815,000679.SZ
|
||||
2024-07-10,0.3347949941192904,000813.SZ
|
||||
2024-07-11,0.5471614704740059,002947.SZ
|
||||
2024-07-12,0.606586425153978,002947.SZ
|
||||
2024-07-15,0.491428038903955,002920.SZ
|
||||
2024-07-16,0.3520867128567497,002829.SZ
|
||||
2024-07-17,0.4368484139541634,002114.SZ
|
||||
2024-07-18,0.5711362079713318,601818.SH
|
||||
2024-07-19,0.570553006364647,601816.SH
|
||||
2024-07-22,0.5446790556747791,600085.SH
|
||||
2024-07-23,0.4576036360785198,600216.SH
|
||||
2024-07-24,0.4684923603589487,605117.SH
|
||||
2024-07-25,0.36326756116546477,600686.SH
|
||||
2024-07-26,0.7417069213473678,002202.SZ
|
||||
2024-07-29,0.8486578272435568,600611.SH
|
||||
2024-07-30,0.4642324976741237,600079.SH
|
||||
2024-07-31,0.45181776568715054,600012.SH
|
||||
2024-08-01,0.427232828082015,603261.SH
|
||||
2024-08-02,0.5973908054488837,600611.SH
|
||||
2024-08-05,0.3621832514143976,001215.SZ
|
||||
2024-08-06,0.6152880440422925,000521.SZ
|
||||
2024-08-07,0.41444619068423183,002652.SZ
|
||||
2024-08-08,0.6478614590135714,603863.SH
|
||||
2024-08-09,0.5930494234277425,002792.SZ
|
||||
2024-08-12,0.25873562692266217,002737.SZ
|
||||
2024-08-13,0.5729850282121722,603900.SH
|
||||
2024-08-14,0.2865185974792763,001223.SZ
|
||||
2024-08-15,0.5834369717958423,002792.SZ
|
||||
2024-08-16,0.5710851526661445,603966.SH
|
||||
2024-08-19,0.4036113851301617,600843.SH
|
||||
2024-08-20,0.14065947878455815,601328.SH
|
||||
2024-08-21,0.3457278358065422,601288.SH
|
||||
2024-08-22,0.45521959430168984,002717.SZ
|
||||
2024-08-23,0.6962370369795378,601398.SH
|
||||
2024-08-26,0.6840685708080309,601658.SH
|
||||
2024-08-27,0.6143024097340646,002957.SZ
|
||||
2024-08-28,0.6139291482796375,601298.SH
|
||||
2024-08-29,0.1337266871366976,600352.SH
|
||||
2024-08-30,0.3951676679126667,600599.SH
|
||||
2024-09-02,0.4684921271140201,600671.SH
|
||||
2024-09-03,0.4078753152276658,002717.SZ
|
||||
2024-09-04,0.3067002855286549,603989.SH
|
||||
2024-09-05,0.4342289124879712,600406.SH
|
||||
2024-09-06,0.6808950214517175,600561.SH
|
||||
2024-09-09,0.43976049446893795,603338.SH
|
||||
2024-09-10,0.5149110083057741,601096.SH
|
||||
2024-09-11,0.6734113595487885,600007.SH
|
||||
2024-09-12,0.7683594358215743,000628.SZ
|
||||
2024-09-13,0.45977943135802823,002640.SZ
|
||||
2024-09-18,0.3647308972416072,600482.SH
|
||||
2024-09-19,0.2813665788012203,600053.SH
|
||||
2024-09-20,0.46565889001722827,605086.SH
|
||||
2024-09-23,0.44690986217371853,600048.SH
|
||||
2024-09-24,0.5632940959647639,002803.SZ
|
||||
2024-09-25,0.5767833157235442,002622.SZ
|
||||
2024-09-26,0.4016590689510123,600739.SH
|
||||
2024-09-27,0.5587044842683202,002311.SZ
|
||||
2024-09-30,0.43872813516535136,002667.SZ
|
||||
2024-10-08,0.21652184419342826,001298.SZ
|
||||
2024-10-09,0.24193695906773188,600809.SH
|
||||
2024-10-10,0.21177605015643433,601858.SH
|
||||
2024-10-11,0.23008772929050933,600764.SH
|
||||
2024-10-14,0.30580248320188735,601398.SH
|
||||
2024-10-15,0.3298408339375664,001367.SZ
|
||||
2024-10-16,0.3660842238302505,000617.SZ
|
||||
2024-10-17,0.5018187879115691,600837.SH
|
||||
2024-10-18,0.22539525121316248,000514.SZ
|
||||
2024-10-21,0.5550755061413811,600418.SH
|
||||
2024-10-22,0.6054618626426457,002488.SZ
|
||||
2024-10-23,0.7102335664067001,002529.SZ
|
||||
2024-10-24,0.4202034910245759,601929.SH
|
||||
2024-10-25,0.37200409737852075,600438.SH
|
||||
2024-10-28,0.20058072722568346,600653.SH
|
||||
2024-10-29,0.66492012749881,002628.SZ
|
||||
2024-10-30,0.6114912867512079,600353.SH
|
||||
2024-10-31,0.6222592653415162,002693.SZ
|
||||
2024-11-01,0.6491176289083889,600843.SH
|
||||
2024-11-04,0.32739829303036627,002178.SZ
|
||||
2024-11-05,0.759688936684659,600363.SH
|
||||
2024-11-06,0.7002870933948189,603955.SH
|
||||
2024-11-07,0.6233511178174305,002146.SZ
|
||||
2024-11-08,0.42009301025642376,002542.SZ
|
||||
2024-11-11,0.5565950654983003,002146.SZ
|
||||
2024-11-12,0.5162774812844746,002208.SZ
|
||||
2024-11-13,0.18855339088498282,002436.SZ
|
||||
2024-11-14,0.33502003120522583,002331.SZ
|
||||
2024-11-15,0.3444118110953233,605117.SH
|
||||
2024-11-18,0.2375219448592142,605108.SH
|
||||
2024-11-19,0.36795547875739953,002806.SZ
|
||||
2024-11-20,0.6197454506964482,603529.SH
|
||||
2024-11-21,0.5892913531640508,603015.SH
|
||||
2024-11-22,0.4899996166040043,002175.SZ
|
||||
2024-11-25,0.053452906549405044,600279.SH
|
||||
2024-11-26,0.4865888640770184,002759.SZ
|
||||
2024-11-27,0.6359984075734232,002820.SZ
|
||||
2024-11-28,0.5845277604948084,603660.SH
|
||||
2024-11-29,0.47680425412521155,001368.SZ
|
||||
2024-12-02,0.6219213214295504,002640.SZ
|
||||
2024-12-03,0.3803484646619281,002682.SZ
|
||||
2024-12-04,0.5021729841555644,600825.SH
|
||||
2024-12-05,0.4523940690895692,002607.SZ
|
||||
2024-12-06,0.4670859538386592,002607.SZ
|
||||
2024-12-09,0.3701075272107646,000882.SZ
|
||||
2024-12-10,0.5343702375509868,603536.SH
|
||||
2024-12-11,0.355506285480863,002177.SZ
|
||||
2024-12-12,0.6322659533895655,002076.SZ
|
||||
2024-12-13,0.2290905336564884,002042.SZ
|
||||
2024-12-16,0.562049425347173,000892.SZ
|
||||
2024-12-17,0.44457814702247433,002227.SZ
|
||||
2024-12-18,0.548681923527933,002339.SZ
|
||||
2024-12-19,0.4216722859146472,603042.SH
|
||||
2024-12-20,0.5352746358597549,000681.SZ
|
||||
2024-12-23,0.4216281498853076,601985.SH
|
||||
2024-12-24,0.35525757086955895,002364.SZ
|
||||
2024-12-25,0.4646707077082279,600000.SH
|
||||
2024-12-26,0.6180913472078771,603988.SH
|
||||
2024-12-27,0.41709449819514827,600865.SH
|
||||
2024-12-30,0.2849460219241718,000703.SZ
|
||||
2024-12-31,0.5260981389670845,000759.SZ
|
||||
2025-01-02,0.3401356086119528,603119.SH
|
||||
2025-01-03,0.509584346569425,605218.SH
|
||||
2025-01-06,0.448801551657659,002218.SZ
|
||||
2025-01-07,0.3353427306743042,002946.SZ
|
||||
2025-01-08,0.45256872671906395,002187.SZ
|
||||
2025-01-09,0.24080883076721746,002713.SZ
|
||||
2025-01-10,0.3586572514416752,600605.SH
|
||||
2025-01-13,0.39270667594047576,603291.SH
|
||||
2025-01-14,0.45992646415377564,600292.SH
|
||||
2025-01-15,0.6283116743234524,002917.SZ
|
||||
2025-01-16,0.42470390001857816,002529.SZ
|
||||
2025-01-17,0.6132519800275194,603306.SH
|
||||
2025-01-20,0.5185912224767291,002175.SZ
|
||||
2025-01-21,0.6196849792216136,603686.SH
|
||||
2025-01-22,0.4402928705741018,603912.SH
|
||||
2025-01-23,0.1991054141392674,000573.SZ
|
||||
2025-01-24,0.5744429678225592,002629.SZ
|
||||
2025-01-27,0.6708520363113031,603803.SH
|
||||
2025-02-05,0.5225638923392779,002629.SZ
|
||||
2025-02-06,0.7204347328958394,002779.SZ
|
||||
2025-02-07,0.5784909103136393,002137.SZ
|
||||
2025-02-10,0.4616488838492335,603958.SH
|
||||
2025-02-11,0.3299565974394537,002691.SZ
|
||||
2025-02-12,0.531256628487983,600602.SH
|
||||
2025-02-13,0.3697957752701452,002369.SZ
|
||||
2025-02-14,0.34205785645354486,002401.SZ
|
||||
2025-02-17,0.6382159196768067,605488.SH
|
||||
2025-02-18,0.454465198035325,600183.SH
|
||||
2025-02-19,0.4626953105114797,603286.SH
|
||||
2025-02-20,0.5335048642887046,603319.SH
|
||||
2025-02-21,0.6624046002142201,605488.SH
|
||||
2025-02-24,0.6104076951455467,603319.SH
|
||||
2025-02-25,0.7143736802604856,000096.SZ
|
||||
2025-02-26,0.7304919691471087,002335.SZ
|
||||
2025-02-27,0.5489810788910849,600622.SH
|
||||
2025-02-28,0.5090242119766623,603037.SH
|
||||
2025-03-03,0.4566864089278842,603278.SH
|
||||
2025-03-04,0.42810543306501575,603823.SH
|
||||
2025-03-05,0.6007593312117221,002725.SZ
|
||||
2025-03-06,0.4659316168581486,003033.SZ
|
||||
2025-03-07,0.5126705833678915,603108.SH
|
||||
2025-03-10,0.6053442608509896,600416.SH
|
||||
2025-03-11,0.4270764095716286,002755.SZ
|
||||
2025-03-12,0.6309604913581539,002802.SZ
|
||||
2025-03-13,0.4074738089247502,000570.SZ
|
||||
2025-03-14,0.7959726877406155,002342.SZ
|
||||
2025-03-17,0.45598110409066034,600101.SH
|
||||
2025-03-18,0.4044499886067394,600610.SH
|
||||
2025-03-19,0.5597196066632053,603757.SH
|
||||
2025-03-20,0.6572997838613929,002227.SZ
|
||||
2025-03-21,0.3434871219772223,000815.SZ
|
||||
2025-03-24,0.48052908404470174,605336.SH
|
||||
2025-03-25,0.4770085150157279,600243.SH
|
||||
2025-03-26,0.660278423238859,001256.SZ
|
||||
2025-03-27,0.3297001064267294,600491.SH
|
||||
2025-03-28,0.5576338314263632,603949.SH
|
||||
2025-03-31,0.2710726347586525,002132.SZ
|
||||
2025-04-01,0.4716112567435462,600095.SH
|
||||
2025-04-02,0.8038165991136271,002639.SZ
|
||||
2025-04-03,0.7280761776931406,600215.SH
|
||||
2025-04-07,0.3907944194714457,600844.SH
|
||||
2025-04-08,0.44531097808775816,002306.SZ
|
||||
2025-04-09,0.6994155866649565,600180.SH
|
||||
|
0
main/__init__.py
Normal file
0
main/__init__.py
Normal file
BIN
main/__pycache__/__init__.cpython-310.pyc
Normal file
BIN
main/__pycache__/__init__.cpython-310.pyc
Normal file
Binary file not shown.
BIN
main/__pycache__/__init__.cpython-311.pyc
Normal file
BIN
main/__pycache__/__init__.cpython-311.pyc
Normal file
Binary file not shown.
1926
main/data/ths_index.ipynb
Normal file
1926
main/data/ths_index.ipynb
Normal file
File diff suppressed because one or more lines are too long
0
main/factor/__init__.py
Normal file
0
main/factor/__init__.py
Normal file
BIN
main/factor/__pycache__/__init__.cpython-310.pyc
Normal file
BIN
main/factor/__pycache__/__init__.cpython-310.pyc
Normal file
Binary file not shown.
BIN
main/factor/__pycache__/__init__.cpython-311.pyc
Normal file
BIN
main/factor/__pycache__/__init__.cpython-311.pyc
Normal file
Binary file not shown.
BIN
main/factor/__pycache__/factor.cpython-310.pyc
Normal file
BIN
main/factor/__pycache__/factor.cpython-310.pyc
Normal file
Binary file not shown.
BIN
main/factor/__pycache__/factor.cpython-311.pyc
Normal file
BIN
main/factor/__pycache__/factor.cpython-311.pyc
Normal file
Binary file not shown.
BIN
main/factor/__pycache__/operator.cpython-311.pyc
Normal file
BIN
main/factor/__pycache__/operator.cpython-311.pyc
Normal file
Binary file not shown.
1532
main/factor/factor.py
Normal file
1532
main/factor/factor.py
Normal file
File diff suppressed because it is too large
Load Diff
1028
main/factor/generate_factor.ipynb
Normal file
1028
main/factor/generate_factor.ipynb
Normal file
File diff suppressed because it is too large
Load Diff
7
main/factor/operators.py
Normal file
7
main/factor/operators.py
Normal file
@@ -0,0 +1,7 @@
|
||||
|
||||
|
||||
from main.utils.utils import read_and_merge_h5_data, merge_with_industry_data
|
||||
|
||||
|
||||
import sys
|
||||
print(sys.path)
|
||||
222
main/factor/save_factor.py
Normal file
222
main/factor/save_factor.py
Normal file
@@ -0,0 +1,222 @@
|
||||
from tqdm import tqdm
|
||||
|
||||
from main.factor.factor import get_rolling_factor, get_simple_factor
|
||||
from main.utils.utils import read_and_merge_h5_data
|
||||
import pandas as pd
|
||||
|
||||
|
||||
def create_factor_table_clickhouse(clickhouse_host: str, clickhouse_port: int,
|
||||
clickhouse_user: str, clickhouse_password: str,
|
||||
clickhouse_database: str, table_name: str = 'factor_data'):
|
||||
"""
|
||||
在 ClickHouse 中创建 factor_data 表，考虑读取速度。
|
||||
"""
|
||||
try:
|
||||
print('create factor table')
|
||||
client = Client(host=clickhouse_host, port=clickhouse_port, user=clickhouse_user,
|
||||
password=clickhouse_password, database=clickhouse_database)
|
||||
|
||||
create_table_query = f"""
|
||||
CREATE TABLE IF NOT EXISTS {table_name}
|
||||
(
|
||||
date Date,
|
||||
asset_id String,
|
||||
factor_name String,
|
||||
factor_value Float64
|
||||
)
|
||||
ENGINE = MergeTree()
|
||||
PARTITION BY toYYYYMM(date)
|
||||
ORDER BY (date, asset_id, factor_name)
|
||||
"""
|
||||
|
||||
client.execute(create_table_query)
|
||||
print(f"成功在 ClickHouse 数据库 '{clickhouse_database}' 中创建表 '{table_name}'!")
|
||||
|
||||
except Exception as e:
|
||||
print(f"创建 ClickHouse 表发生错误: {e}")
|
||||
finally:
|
||||
if 'client' in locals() and client.connection:
|
||||
client.disconnect()
|
||||
|
||||
|
||||
def write_features_to_clickhouse(df: pd.DataFrame, feature_columns: list,
|
||||
clickhouse_host: str, clickhouse_port: int,
|
||||
clickhouse_user: str, clickhouse_password: str,
|
||||
clickhouse_database: str, table_name: str = 'stock_factor',
|
||||
batch_size: int = 5000): # 设置批次大小
|
||||
"""
|
||||
将 DataFrame 中指定的特征列分批写入 ClickHouse 的宽表，动态添加列。
|
||||
"""
|
||||
try:
|
||||
client = Client(host=clickhouse_host, port=clickhouse_port, user=clickhouse_user,
|
||||
password=clickhouse_password, database=clickhouse_database)
|
||||
|
||||
if 'ts_code' not in df.columns or 'trade_date' not in df.columns:
|
||||
raise ValueError("DataFrame 必须包含 'ts_code' 和 'trade_date' 列。")
|
||||
|
||||
existing_columns = set()
|
||||
columns_query = f"DESCRIBE TABLE {table_name}"
|
||||
columns_result = client.execute(columns_query)
|
||||
for col in columns_result:
|
||||
existing_columns.add(col[0])
|
||||
|
||||
for factor_name in feature_columns:
|
||||
if factor_name not in existing_columns:
|
||||
if factor_name not in df.columns:
|
||||
print(f"警告: 特征 '{factor_name}' 不存在于 DataFrame 中，将跳过添加列。")
|
||||
continue
|
||||
|
||||
factor_series = df[factor_name]
|
||||
factor_dtype = factor_series.dtype
|
||||
|
||||
clickhouse_dtype = None
|
||||
if pd.api.types.is_float_dtype(factor_dtype):
|
||||
clickhouse_dtype = 'Float64'
|
||||
elif pd.api.types.is_integer_dtype(factor_dtype):
|
||||
clickhouse_dtype = 'Int64'
|
||||
elif factor_dtype == 'object':
|
||||
print(f"警告: 特征 '{factor_name}' 的数据类型为 object，将跳过添加列。")
|
||||
continue
|
||||
else:
|
||||
clickhouse_dtype = 'Float64'
|
||||
|
||||
if clickhouse_dtype:
|
||||
add_column_query = f"ALTER TABLE {table_name} ADD COLUMN IF NOT EXISTS {factor_name} {clickhouse_dtype}"
|
||||
client.execute(add_column_query)
|
||||
print(f"在表 '{table_name}' 中添加了新列: {factor_name} ({clickhouse_dtype})")
|
||||
existing_columns.add(factor_name)
|
||||
|
||||
insert_columns_order = ['date', 'asset_id'] + [col for col in feature_columns if
|
||||
col in existing_columns and col in df.columns]
|
||||
|
||||
# 分批处理 DataFrame
|
||||
num_rows = len(df)
|
||||
for i in tqdm(range(0, num_rows, batch_size), desc="写入批次"):
|
||||
batch_df = df[i:i + batch_size]
|
||||
data_to_insert_batch = []
|
||||
for row in batch_df.itertuples(index=False):
|
||||
insert_row = [getattr(row, 'trade_date'), getattr(row, 'ts_code')]
|
||||
for factor in feature_columns:
|
||||
if factor in existing_columns and factor in df.columns:
|
||||
try:
|
||||
insert_row.append(getattr(row, factor))
|
||||
except AttributeError:
|
||||
insert_row.append(None)
|
||||
data_to_insert_batch.append(tuple(insert_row))
|
||||
write_batch_to_clickhouse(client, table_name, data_to_insert_batch, insert_columns_order)
|
||||
|
||||
except Exception as e:
|
||||
print(f"写入 ClickHouse 发生错误: {e}")
|
||||
finally:
|
||||
if 'client' in locals() and client.connection:
|
||||
client.disconnect()
|
||||
|
||||
|
||||
def write_batch_to_clickhouse(client, table_name, data_to_insert, columns_order):
|
||||
"""将一个批次的数据写入 ClickHouse"""
|
||||
if data_to_insert:
|
||||
insert_query_final = f"INSERT INTO {table_name} ({', '.join(columns_order)}) VALUES"
|
||||
try:
|
||||
client.execute(insert_query_final, data_to_insert)
|
||||
print(f"成功写入 {len(data_to_insert)} 条数据到 ClickHouse 表 '{table_name}'!")
|
||||
except Exception as e:
|
||||
print(f"写入 ClickHouse 批次数据发生错误: {e}")
|
||||
|
||||
|
||||
# -------------------- 使用示例 --------------------
|
||||
if __name__ == "__main__":
|
||||
# 示例 DataFrame
|
||||
|
||||
print('daily data')
|
||||
df = read_and_merge_h5_data('../../data/daily_data.h5', key='daily_data',
|
||||
columns=['ts_code', 'trade_date', 'open', 'close', 'high', 'low', 'vol', 'pct_chg'],
|
||||
df=None)
|
||||
|
||||
print('daily basic')
|
||||
df = read_and_merge_h5_data('../../data/daily_basic.h5', key='daily_basic',
|
||||
columns=['ts_code', 'trade_date', 'turnover_rate', 'pe_ttm', 'circ_mv', 'volume_ratio',
|
||||
'is_st'], df=df, join='inner')
|
||||
df = df[df['trade_date'] >= '2021-01-01']
|
||||
|
||||
print('stk limit')
|
||||
df = read_and_merge_h5_data('../../data/stk_limit.h5', key='stk_limit',
|
||||
columns=['ts_code', 'trade_date', 'pre_close', 'up_limit', 'down_limit'],
|
||||
df=df)
|
||||
print('money flow')
|
||||
df = read_and_merge_h5_data('../../data/money_flow.h5', key='money_flow',
|
||||
columns=['ts_code', 'trade_date', 'buy_sm_vol', 'sell_sm_vol', 'buy_lg_vol',
|
||||
'sell_lg_vol',
|
||||
'buy_elg_vol', 'sell_elg_vol', 'net_mf_vol'],
|
||||
df=df)
|
||||
print('cyq perf')
|
||||
df = read_and_merge_h5_data('../../data/cyq_perf.h5', key='cyq_perf',
|
||||
columns=['ts_code', 'trade_date', 'his_low', 'his_high', 'cost_5pct', 'cost_15pct',
|
||||
'cost_50pct',
|
||||
'cost_85pct', 'cost_95pct', 'weight_avg', 'winner_rate'],
|
||||
df=df)
|
||||
print(df.info())
|
||||
|
||||
origin_columns = df.columns.tolist()
|
||||
origin_columns = [col for col in origin_columns if 'cyq' not in col]
|
||||
print(origin_columns)
|
||||
|
||||
|
||||
def filter_data(df):
|
||||
# df = df.groupby('trade_date').apply(lambda x: x.nlargest(1000, 'act_factor1'))
|
||||
df = df[~df['is_st']]
|
||||
df = df[~df['ts_code'].str.endswith('BJ')]
|
||||
df = df[~df['ts_code'].str.startswith('30')]
|
||||
df = df[~df['ts_code'].str.startswith('68')]
|
||||
df = df[~df['ts_code'].str.startswith('8')]
|
||||
df = df[df['trade_date'] >= '20180101']
|
||||
if 'in_date' in df.columns:
|
||||
df = df.drop(columns=['in_date'])
|
||||
df = df.reset_index(drop=True)
|
||||
return df
|
||||
|
||||
|
||||
df = filter_data(df)
|
||||
df, _ = get_rolling_factor(df)
|
||||
df, _ = get_simple_factor(df)
|
||||
# df['test'] = 1
|
||||
# df['test2'] = 2
|
||||
# df = df.merge(industry_df, on=['l2_code', 'trade_date'], how='left')
|
||||
df = df.rename(columns={'l2_code': 'cat_l2_code'})
|
||||
# df = df.merge(index_data, on='trade_date', how='left')
|
||||
|
||||
print(df.info())
|
||||
|
||||
feature_columns = [col for col in df.columns if col in df.columns]
|
||||
feature_columns = [col for col in feature_columns if col not in ['trade_date',
|
||||
'ts_code',
|
||||
'label']]
|
||||
feature_columns = [col for col in feature_columns if 'future' not in col]
|
||||
feature_columns = [col for col in feature_columns if 'label' not in col]
|
||||
feature_columns = [col for col in feature_columns if 'score' not in col]
|
||||
feature_columns = [col for col in feature_columns if 'gen' not in col]
|
||||
feature_columns = [col for col in feature_columns if 'is_st' not in col]
|
||||
# feature_columns = [col for col in feature_columns if 'pe_ttm' not in col]
|
||||
# feature_columns = [col for col in feature_columns if 'volatility' not in col]
|
||||
# feature_columns = [col for col in feature_columns if 'circ_mv' not in col]
|
||||
feature_columns = [col for col in feature_columns if 'cat_l2_code' not in col]
|
||||
feature_columns = [col for col in feature_columns if col not in origin_columns]
|
||||
feature_columns = [col for col in feature_columns if not col.startswith('_')]
|
||||
|
||||
print(feature_columns)
|
||||
|
||||
# 替换为您的 ClickHouse 连接信息
|
||||
clickhouse_host = '127.0.0.1'
|
||||
clickhouse_port = 9000
|
||||
clickhouse_user = 'default'
|
||||
clickhouse_password = 'clickhouse520102'
|
||||
clickhouse_database = 'stock_data'
|
||||
|
||||
# create_factor_table_clickhouse(clickhouse_host, clickhouse_port,
|
||||
# clickhouse_user, clickhouse_password,
|
||||
# clickhouse_database)
|
||||
|
||||
write_features_to_clickhouse(
|
||||
df[[col for col in df.columns if col in ['ts_code', 'trade_date'] or col in feature_columns]], feature_columns,
|
||||
clickhouse_host, clickhouse_port,
|
||||
clickhouse_user, clickhouse_password,
|
||||
clickhouse_database)
|
||||
4
main/test.py
Normal file
4
main/test.py
Normal file
@@ -0,0 +1,4 @@
|
||||
import sys
|
||||
print(sys.path)
|
||||
|
||||
from main.utils.utils import read_and_merge_h5_data, merge_with_industry_data
|
||||
2179
main/train/AnalyzeData.ipynb
Normal file
2179
main/train/AnalyzeData.ipynb
Normal file
File diff suppressed because it is too large
Load Diff
@@ -36,7 +36,7 @@
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"from utils.utils import read_and_merge_h5_data\n",
|
||||
"from code.utils.utils import read_and_merge_h5_data\n",
|
||||
"\n",
|
||||
"print('daily data')\n",
|
||||
"df = read_and_merge_h5_data('../../data/daily_data.h5', key='daily_data',\n",
|
||||
@@ -75,7 +75,7 @@
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from utils.utils import read_and_merge_h5_data\n",
|
||||
"from code.utils.utils import read_and_merge_h5_data\n",
|
||||
"\n",
|
||||
"print('daily data')\n",
|
||||
"df = read_and_merge_h5_data('../../data/daily_data.h5', key='daily_data',\n",
|
||||
@@ -172,7 +172,7 @@
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"from utils.utils import read_and_merge_h5_data\n",
|
||||
"from code.utils.utils import read_and_merge_h5_data\n",
|
||||
"\n",
|
||||
"print('daily data')\n",
|
||||
"df = read_and_merge_h5_data('../../data/daily_data.h5', key='daily_data',\n",
|
||||
@@ -26,7 +26,7 @@
|
||||
"scrolled": true
|
||||
},
|
||||
"source": [
|
||||
"from utils.utils import read_and_merge_h5_data\n",
|
||||
"from code.utils.utils import read_and_merge_h5_data\n",
|
||||
"\n",
|
||||
"print('daily data')\n",
|
||||
"df = read_and_merge_h5_data('../../data/daily_data.h5', key='daily_data',\n",
|
||||
@@ -510,7 +510,7 @@
|
||||
"scrolled": true
|
||||
},
|
||||
"source": [
|
||||
"from utils.factor import get_act_factor\n",
|
||||
"from code.utils.factor import get_act_factor\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def read_industry_data(h5_filename):\n",
|
||||
@@ -620,9 +620,6 @@
|
||||
},
|
||||
"source": [
|
||||
"from scipy.stats import ks_2samp, wasserstein_distance\n",
|
||||
"from sklearn.metrics import roc_auc_score\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"from sklearn.preprocessing import StandardScaler\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def remove_shifted_features(train_data, test_data, feature_columns, ks_threshold=0.1, wasserstein_threshold=0.15,\n",
|
||||
@@ -786,7 +783,6 @@
|
||||
"\n",
|
||||
"\n",
|
||||
"import pandas as pd\n",
|
||||
"from sklearn.preprocessing import StandardScaler\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def cross_sectional_standardization(df, features):\n",
|
||||
@@ -36,7 +36,7 @@
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"from utils.utils import read_and_merge_h5_data\n",
|
||||
"from code.utils.utils import read_and_merge_h5_data\n",
|
||||
"\n",
|
||||
"print('daily data')\n",
|
||||
"df = read_and_merge_h5_data('../../data/daily_data.h5', key='daily_data',\n",
|
||||
@@ -35,7 +35,7 @@
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"from utils.utils import read_and_merge_h5_data_polars\n",
|
||||
"from code.utils.utils import read_and_merge_h5_data_polars\n",
|
||||
"\n",
|
||||
"print('daily data')\n",
|
||||
"df = read_and_merge_h5_data_polars('../../data/daily_data.h5', key='daily_data',\n",
|
||||
@@ -721,13 +721,7 @@
|
||||
"import lightgbm as lgb\n",
|
||||
"import numpy as np\n",
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"import optuna\n",
|
||||
"from sklearn.model_selection import KFold\n",
|
||||
"from sklearn.metrics import mean_absolute_error\n",
|
||||
"import os\n",
|
||||
"import json\n",
|
||||
"import pickle\n",
|
||||
"import hashlib\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def train_light_model(train_data_df, test_data_df, params, feature_columns, callbacks, evals,\n",
|
||||
" print_feature_importance=True, num_boost_round=100,\n",
|
||||
1984
main/train/Rank.ipynb
Normal file
1984
main/train/Rank.ipynb
Normal file
File diff suppressed because one or more lines are too long
@@ -27,7 +27,7 @@
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"from utils.utils import read_and_merge_h5_data\n",
|
||||
"from code.utils.utils import read_and_merge_h5_data\n",
|
||||
"\n",
|
||||
"print('daily data')\n",
|
||||
"df = read_and_merge_h5_data('../../data/daily_data.h5', key='daily_data',\n",
|
||||
@@ -502,7 +502,7 @@
|
||||
"id": "a735bc02ceb4d872",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"from utils.factor import get_act_factor\n",
|
||||
"from code.utils.factor import get_act_factor\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def read_industry_data(h5_filename):\n",
|
||||
@@ -612,9 +612,6 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"from scipy.stats import ks_2samp, wasserstein_distance\n",
|
||||
"from sklearn.metrics import roc_auc_score\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"from sklearn.preprocessing import StandardScaler\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def remove_shifted_features(train_data, test_data, feature_columns, ks_threshold=0.05, wasserstein_threshold=0.1,\n",
|
||||
@@ -769,8 +766,6 @@
|
||||
" or 'act' in col or 'af' in col]\n",
|
||||
" return remaining_features\n",
|
||||
"\n",
|
||||
"import pandas as pd\n",
|
||||
"from sklearn.preprocessing import StandardScaler\n",
|
||||
"\n",
|
||||
"def cross_sectional_standardization(df, features):\n",
|
||||
" df_sorted = df.sort_values(by='trade_date') # 按时间排序\n",
|
||||
4641
main/train/RollingRank.ipynb
Normal file
4641
main/train/RollingRank.ipynb
Normal file
File diff suppressed because it is too large
Load Diff
918
main/train/RollingRank.txt
Normal file
918
main/train/RollingRank.txt
Normal file
@@ -0,0 +1,918 @@
|
||||
#!/usr/bin/env python
|
||||
# coding: utf-8
|
||||
|
||||
# In[1]:
|
||||
|
||||
|
||||
# %load_ext autoreload
|
||||
# %autoreload 2
|
||||
|
||||
import pandas as pd
|
||||
import warnings
|
||||
|
||||
warnings.filterwarnings("ignore")
|
||||
|
||||
pd.set_option('display.max_columns', None)
|
||||
|
||||
|
||||
# In[2]:
|
||||
|
||||
|
||||
from utils.utils import read_and_merge_h5_data
|
||||
|
||||
print('daily data')
|
||||
df = read_and_merge_h5_data('../../data/daily_data.h5', key='daily_data',
|
||||
columns=['ts_code', 'trade_date', 'open', 'close', 'high', 'low', 'vol', 'pct_chg'],
|
||||
df=None)
|
||||
|
||||
print('daily basic')
|
||||
df = read_and_merge_h5_data('../../data/daily_basic.h5', key='daily_basic',
|
||||
columns=['ts_code', 'trade_date', 'turnover_rate', 'pe_ttm', 'circ_mv', 'volume_ratio',
|
||||
'is_st'], df=df, join='inner')
|
||||
|
||||
print('stk limit')
|
||||
df = read_and_merge_h5_data('../../data/stk_limit.h5', key='stk_limit',
|
||||
columns=['ts_code', 'trade_date', 'pre_close', 'up_limit', 'down_limit'],
|
||||
df=df)
|
||||
print('money flow')
|
||||
df = read_and_merge_h5_data('../../data/money_flow.h5', key='money_flow',
|
||||
columns=['ts_code', 'trade_date', 'buy_sm_vol', 'sell_sm_vol', 'buy_lg_vol', 'sell_lg_vol',
|
||||
'buy_elg_vol', 'sell_elg_vol', 'net_mf_vol'],
|
||||
df=df)
|
||||
print('cyq perf')
|
||||
df = read_and_merge_h5_data('../../data/cyq_perf.h5', key='cyq_perf',
|
||||
columns=['ts_code', 'trade_date', 'his_low', 'his_high', 'cost_5pct', 'cost_15pct',
|
||||
'cost_50pct',
|
||||
'cost_85pct', 'cost_95pct', 'weight_avg', 'winner_rate'],
|
||||
df=df)
|
||||
print(df.info())
|
||||
|
||||
|
||||
# In[3]:
|
||||
|
||||
|
||||
print('industry')
|
||||
industry_df = read_and_merge_h5_data('../../data/industry_data.h5', key='industry_data',
|
||||
columns=['ts_code', 'l2_code', 'in_date'],
|
||||
df=None, on=['ts_code'], join='left')
|
||||
|
||||
|
||||
def merge_with_industry_data(df, industry_df):
|
||||
# 确保日期字段是 datetime 类型
|
||||
df['trade_date'] = pd.to_datetime(df['trade_date'])
|
||||
industry_df['in_date'] = pd.to_datetime(industry_df['in_date'])
|
||||
|
||||
# 对 industry_df 按 ts_code 和 in_date 排序
|
||||
industry_df_sorted = industry_df.sort_values(['in_date', 'ts_code'])
|
||||
|
||||
# 对原始 df 按 ts_code 和 trade_date 排序
|
||||
df_sorted = df.sort_values(['trade_date', 'ts_code'])
|
||||
|
||||
# 使用 merge_asof 进行向后合并
|
||||
merged = pd.merge_asof(
|
||||
df_sorted,
|
||||
industry_df_sorted,
|
||||
by='ts_code', # 按 ts_code 分组
|
||||
left_on='trade_date',
|
||||
right_on='in_date',
|
||||
direction='backward'
|
||||
)
|
||||
|
||||
# 获取每个 ts_code 的最早 in_date 记录
|
||||
min_in_date_per_ts = (industry_df_sorted
|
||||
.groupby('ts_code')
|
||||
.first()
|
||||
.reset_index()[['ts_code', 'l2_code']])
|
||||
|
||||
# 填充未匹配到的记录（trade_date 早于所有 in_date 的情况）
|
||||
merged['l2_code'] = merged['l2_code'].fillna(
|
||||
merged['ts_code'].map(min_in_date_per_ts.set_index('ts_code')['l2_code'])
|
||||
)
|
||||
|
||||
# 保留需要的列并重置索引
|
||||
result = merged.reset_index(drop=True)
|
||||
return result
|
||||
|
||||
|
||||
# 使用示例
|
||||
df = merge_with_industry_data(df, industry_df)
|
||||
# print(mdf[mdf['ts_code'] == '600751.SH'][['ts_code', 'trade_date', 'l2_code']])
|
||||
|
||||
|
||||
# In[4]:
|
||||
|
||||
|
||||
def calculate_indicators(df):
|
||||
"""
|
||||
计算四个指标：当日涨跌幅、5日移动平均、RSI、MACD。
|
||||
"""
|
||||
df = df.sort_values('trade_date')
|
||||
df['daily_return'] = (df['close'] - df['pre_close']) / df['pre_close'] * 100
|
||||
# df['5_day_ma'] = df['close'].rolling(window=5).mean()
|
||||
delta = df['close'].diff()
|
||||
gain = delta.where(delta > 0, 0)
|
||||
loss = -delta.where(delta < 0, 0)
|
||||
avg_gain = gain.rolling(window=14).mean()
|
||||
avg_loss = loss.rolling(window=14).mean()
|
||||
rs = avg_gain / avg_loss
|
||||
df['RSI'] = 100 - (100 / (1 + rs))
|
||||
|
||||
# 计算MACD
|
||||
ema12 = df['close'].ewm(span=12, adjust=False).mean()
|
||||
ema26 = df['close'].ewm(span=26, adjust=False).mean()
|
||||
df['MACD'] = ema12 - ema26
|
||||
df['Signal_line'] = df['MACD'].ewm(span=9, adjust=False).mean()
|
||||
df['MACD_hist'] = df['MACD'] - df['Signal_line']
|
||||
|
||||
# 4. 情绪因子1：市场上涨比例（Up Ratio）
|
||||
df['up_ratio'] = df['daily_return'].apply(lambda x: 1 if x > 0 else 0)
|
||||
df['up_ratio_20d'] = df['up_ratio'].rolling(window=20).mean() # 过去20天上涨比例
|
||||
|
||||
# 5. 情绪因子2：成交量变化率（Volume Change Rate）
|
||||
df['volume_mean'] = df['vol'].rolling(window=20).mean() # 过去20天的平均成交量
|
||||
df['volume_change_rate'] = (df['vol'] - df['volume_mean']) / df['volume_mean'] * 100 # 成交量变化率
|
||||
|
||||
# 6. 情绪因子3：波动率（Volatility）
|
||||
df['volatility'] = df['daily_return'].rolling(window=20).std() # 过去20天的日收益率标准差
|
||||
|
||||
# 7. 情绪因子4：成交额变化率（Amount Change Rate）
|
||||
df['amount_mean'] = df['amount'].rolling(window=20).mean() # 过去20天的平均成交额
|
||||
df['amount_change_rate'] = (df['amount'] - df['amount_mean']) / df['amount_mean'] * 100 # 成交额变化率
|
||||
|
||||
return df
|
||||
|
||||
|
||||
def generate_index_indicators(h5_filename):
|
||||
df = pd.read_hdf(h5_filename, key='index_data')
|
||||
df['trade_date'] = pd.to_datetime(df['trade_date'], format='%Y%m%d')
|
||||
df = df.sort_values('trade_date')
|
||||
|
||||
# 计算每个ts_code的相关指标
|
||||
df_indicators = []
|
||||
for ts_code in df['ts_code'].unique():
|
||||
df_index = df[df['ts_code'] == ts_code].copy()
|
||||
df_index = calculate_indicators(df_index)
|
||||
df_indicators.append(df_index)
|
||||
|
||||
# 合并所有指数的结果
|
||||
df_all_indicators = pd.concat(df_indicators, ignore_index=True)
|
||||
|
||||
# 保留trade_date列，并将同一天的数据按ts_code合并成一行
|
||||
df_final = df_all_indicators.pivot_table(
|
||||
index='trade_date',
|
||||
columns='ts_code',
|
||||
values=['daily_return', 'RSI', 'MACD', 'Signal_line',
|
||||
'MACD_hist', 'up_ratio_20d', 'volume_change_rate', 'volatility',
|
||||
'amount_change_rate', 'amount_mean'],
|
||||
aggfunc='last'
|
||||
)
|
||||
|
||||
df_final.columns = [f"{col[1]}_{col[0]}" for col in df_final.columns]
|
||||
df_final = df_final.reset_index()
|
||||
|
||||
return df_final
|
||||
|
||||
|
||||
# 使用函数
|
||||
h5_filename = '../../data/index_data.h5'
|
||||
index_data = generate_index_indicators(h5_filename)
|
||||
index_data = index_data.dropna()
|
||||
|
||||
|
||||
|
||||
# In[6]:
|
||||
|
||||
|
||||
from utils.factor import get_act_factor
|
||||
|
||||
|
||||
def read_industry_data(h5_filename):
|
||||
# 读取 H5 文件中所有的行业数据
|
||||
industry_data = pd.read_hdf(h5_filename, key='sw_daily', columns=[
|
||||
'ts_code', 'trade_date', 'open', 'close', 'high', 'low', 'pe', 'pb', 'vol'
|
||||
]) # 假设 H5 文件的键是 'industry_data'
|
||||
industry_data = industry_data.sort_values(by=['ts_code', 'trade_date'])
|
||||
industry_data = industry_data.reindex()
|
||||
industry_data['trade_date'] = pd.to_datetime(industry_data['trade_date'], format='%Y%m%d')
|
||||
|
||||
grouped = industry_data.groupby('ts_code', group_keys=False)
|
||||
industry_data['obv'] = grouped.apply(
|
||||
lambda x: pd.Series(talib.OBV(x['close'].values, x['vol'].values), index=x.index)
|
||||
)
|
||||
industry_data['return_5'] = grouped['close'].apply(lambda x: x / x.shift(5) - 1)
|
||||
industry_data['return_20'] = grouped['close'].apply(lambda x: x / x.shift(20) - 1)
|
||||
|
||||
industry_data = get_act_factor(industry_data, cat=False)
|
||||
industry_data = industry_data.sort_values(by=['trade_date', 'ts_code'])
|
||||
|
||||
# # 计算每天每个 ts_code 的因子和当天所有 ts_code 的中位数的偏差
|
||||
# factor_columns = ['obv', 'return_5', 'return_20', 'act_factor1', 'act_factor2', 'act_factor3', 'act_factor4'] # 因子列
|
||||
#
|
||||
# for factor in factor_columns:
|
||||
# if factor in industry_data.columns:
|
||||
# # 计算每天每个 ts_code 的因子值与当天所有 ts_code 的中位数的偏差
|
||||
# industry_data[f'{factor}_deviation'] = industry_data.groupby('trade_date')[factor].transform(
|
||||
# lambda x: x - x.mean())
|
||||
|
||||
industry_data['return_5_percentile'] = industry_data.groupby('trade_date')['return_5'].transform(
|
||||
lambda x: x.rank(pct=True))
|
||||
industry_data['return_20_percentile'] = industry_data.groupby('trade_date')['return_20'].transform(
|
||||
lambda x: x.rank(pct=True))
|
||||
industry_data = industry_data.drop(columns=['open', 'close', 'high', 'low', 'pe', 'pb', 'vol'])
|
||||
|
||||
industry_data = industry_data.rename(
|
||||
columns={col: f'industry_{col}' for col in industry_data.columns if col not in ['ts_code', 'trade_date']})
|
||||
|
||||
industry_data = industry_data.rename(columns={'ts_code': 'cat_l2_code'})
|
||||
return industry_data
|
||||
|
||||
|
||||
industry_df = read_industry_data('../../data/sw_daily.h5')
|
||||
|
||||
|
||||
# In[7]:
|
||||
|
||||
|
||||
origin_columns = df.columns.tolist()
|
||||
origin_columns = [col for col in origin_columns if
|
||||
col not in ['turnover_rate', 'pe_ttm', 'volume_ratio', 'vol', 'pct_chg', 'l2_code', 'winner_rate']]
|
||||
origin_columns = [col for col in origin_columns if col not in index_data.columns]
|
||||
origin_columns = [col for col in origin_columns if 'cyq' not in col]
|
||||
print(origin_columns)
|
||||
|
||||
|
||||
# In[8]:
|
||||
|
||||
|
||||
def filter_data(df):
|
||||
# df = df.groupby('trade_date').apply(lambda x: x.nlargest(1000, 'act_factor1'))
|
||||
df = df[~df['is_st']]
|
||||
df = df[~df['ts_code'].str.endswith('BJ')]
|
||||
df = df[~df['ts_code'].str.startswith('30')]
|
||||
df = df[~df['ts_code'].str.startswith('68')]
|
||||
df = df[~df['ts_code'].str.startswith('8')]
|
||||
df = df[df['trade_date'] >= '20180101']
|
||||
df = df.drop(columns=['in_date'])
|
||||
df = df.reset_index(drop=True)
|
||||
return df
|
||||
|
||||
|
||||
df = filter_data(df)
|
||||
# df = get_technical_factor(df)
|
||||
# df = get_act_factor(df)
|
||||
# df = get_money_flow_factor(df)
|
||||
# df = get_alpha_factor(df)
|
||||
# df = get_limit_factor(df)
|
||||
# df = get_cyp_perf_factor(df)
|
||||
# df = get_mv_factors(df)
|
||||
df, _ = get_rolling_factor(df)
|
||||
df, _ = get_simple_factor(df)
|
||||
# df = df.merge(industry_df, on=['l2_code', 'trade_date'], how='left')
|
||||
df = df.rename(columns={'l2_code': 'cat_l2_code'})
|
||||
# df = df.merge(index_data, on='trade_date', how='left')
|
||||
|
||||
print(df.info())
|
||||
|
||||
|
||||
# In[9]:
|
||||
|
||||
|
||||
def create_deviation_within_dates(df, feature_columns):
|
||||
groupby_col = 'cat_l2_code' # 使用 trade_date 进行分组
|
||||
new_columns = {}
|
||||
ret_feature_columns = feature_columns[:]
|
||||
|
||||
# 自动选择所有数值型特征
|
||||
num_features = [col for col in feature_columns if 'cat' not in col and 'index' not in col]
|
||||
|
||||
# num_features = ['vol', 'pct_chg', 'turnover_rate', 'volume_ratio', 'cat_vol_spike', 'obv', 'maobv_6', 'return_5', 'return_10', 'return_20', 'std_return_5', 'std_return_15', 'std_return_90', 'std_return_90_2', 'act_factor1', 'act_factor2', 'act_factor3', 'act_factor4', 'act_factor5', 'act_factor6', 'rank_act_factor1', 'rank_act_factor2', 'rank_act_factor3', 'active_buy_volume_large', 'active_buy_volume_big', 'active_buy_volume_small', 'alpha_022', 'alpha_003', 'alpha_007', 'alpha_013']
|
||||
num_features = [col for col in num_features if 'cat' not in col and 'industry' not in col]
|
||||
num_features = [col for col in num_features if 'limit' not in col]
|
||||
num_features = [col for col in num_features if 'cyq' not in col]
|
||||
|
||||
# 遍历所有数值型特征
|
||||
for feature in num_features:
|
||||
if feature == 'trade_date': # 不需要对 'trade_date' 计算偏差
|
||||
continue
|
||||
|
||||
# grouped_mean = df.groupby(['trade_date'])[feature].transform('mean')
|
||||
# deviation_col_name = f'deviation_mean_{feature}'
|
||||
# new_columns[deviation_col_name] = df[feature] - grouped_mean
|
||||
# ret_feature_columns.append(deviation_col_name)
|
||||
|
||||
grouped_mean = df.groupby(['trade_date', groupby_col])[feature].transform('mean')
|
||||
deviation_col_name = f'deviation_mean_{feature}'
|
||||
new_columns[deviation_col_name] = df[feature] - grouped_mean
|
||||
ret_feature_columns.append(deviation_col_name)
|
||||
|
||||
# 将新计算的偏差特征与原始 DataFrame 合并
|
||||
df = pd.concat([df, pd.DataFrame(new_columns)], axis=1)
|
||||
|
||||
# for feature in ['obv', 'return_20', 'act_factor1', 'act_factor2', 'act_factor3', 'act_factor4']:
|
||||
# df[f'deviation_industry_{feature}'] = df[feature] - df[f'industry_{feature}']
|
||||
|
||||
return df, ret_feature_columns
|
||||
|
||||
|
||||
# In[10]:
|
||||
|
||||
|
||||
import pandas as pd
|
||||
|
||||
from scipy.stats import ks_2samp, wasserstein_distance
|
||||
from sklearn.metrics import roc_auc_score
|
||||
from sklearn.model_selection import train_test_split
|
||||
from sklearn.preprocessing import StandardScaler
|
||||
|
||||
|
||||
def remove_shifted_features(train_data, feature_columns, ks_threshold=0.05, wasserstein_threshold=0.1, size=0.8):
|
||||
dropped_features = []
|
||||
|
||||
all_dates = train_data['trade_date'].unique() # 获取所有唯一的 trade_date
|
||||
split_date = all_dates[int(len(all_dates) * size)] # 划分点为倒数第 validation_days 天
|
||||
train_data_split = train_data[train_data['trade_date'] < split_date] # 训练集
|
||||
val_data_split = train_data[train_data['trade_date'] >= split_date] # 验证集
|
||||
|
||||
# **统计数据漂移**
|
||||
numeric_columns = train_data_split.select_dtypes(include=['float64', 'int64']).columns
|
||||
numeric_columns = [col for col in numeric_columns if col in feature_columns]
|
||||
for feature in numeric_columns:
|
||||
ks_stat, p_value = ks_2samp(train_data_split[feature], val_data_split[feature])
|
||||
wasserstein_dist = wasserstein_distance(train_data_split[feature], val_data_split[feature])
|
||||
|
||||
if p_value < ks_threshold or wasserstein_dist > wasserstein_threshold:
|
||||
dropped_features.append(feature)
|
||||
|
||||
print(f"检测到 {len(dropped_features)} 个可能漂移的特征: {dropped_features}")
|
||||
|
||||
# **应用阈值进行最终筛选**
|
||||
filtered_features = [f for f in feature_columns if f not in dropped_features]
|
||||
|
||||
return filtered_features, dropped_features
|
||||
|
||||
|
||||
def remove_outliers_label_percentile(label: pd.Series, lower_percentile: float = 0.01, upper_percentile: float = 0.99,
|
||||
log=True):
|
||||
if not (0 <= lower_percentile < upper_percentile <= 1):
|
||||
raise ValueError("Percentile values must satisfy 0 <= lower_percentile < upper_percentile <= 1.")
|
||||
|
||||
# Calculate lower and upper bounds based on percentiles
|
||||
lower_bound = label.quantile(lower_percentile)
|
||||
upper_bound = label.quantile(upper_percentile)
|
||||
|
||||
# Filter out values outside the bounds
|
||||
filtered_label = label[(label >= lower_bound) & (label <= upper_bound)]
|
||||
|
||||
# Print the number of removed outliers
|
||||
if log:
|
||||
print(f"Removed {len(label) - len(filtered_label)} outliers.")
|
||||
return filtered_label
|
||||
|
||||
|
||||
def calculate_risk_adjusted_target(df, days=5):
|
||||
df = df.sort_values(by=['ts_code', 'trade_date'])
|
||||
|
||||
df['future_close'] = df.groupby('ts_code')['close'].shift(-days)
|
||||
df['future_open'] = df.groupby('ts_code')['open'].shift(-1)
|
||||
df['future_return'] = (df['future_close'] - df['future_open']) / df['future_open']
|
||||
|
||||
df['future_volatility'] = df.groupby('ts_code')['future_return'].rolling(days, min_periods=1).std().reset_index(
|
||||
level=0, drop=True)
|
||||
sharpe_ratio = df['future_return'] * df['future_volatility']
|
||||
sharpe_ratio.replace([np.inf, -np.inf], np.nan, inplace=True)
|
||||
|
||||
return sharpe_ratio
|
||||
|
||||
|
||||
def calculate_score(df, days=5, lambda_param=1.0):
|
||||
def calculate_max_drawdown(prices):
|
||||
peak = prices.iloc[0] # 初始化峰值
|
||||
max_drawdown = 0 # 初始化最大回撤
|
||||
|
||||
for price in prices:
|
||||
if price > peak:
|
||||
peak = price # 更新峰值
|
||||
else:
|
||||
drawdown = (peak - price) / peak # 计算当前回撤
|
||||
max_drawdown = max(max_drawdown, drawdown) # 更新最大回撤
|
||||
|
||||
return max_drawdown
|
||||
|
||||
def compute_stock_score(stock_df):
|
||||
stock_df = stock_df.sort_values(by=['trade_date'])
|
||||
future_return = stock_df['future_return']
|
||||
# 使用已有的 pct_chg 字段计算波动率
|
||||
volatility = stock_df['pct_chg'].rolling(days).std().shift(-days)
|
||||
max_drawdown = stock_df['close'].rolling(days).apply(calculate_max_drawdown, raw=False).shift(-days)
|
||||
score = future_return - lambda_param * max_drawdown
|
||||
return score
|
||||
|
||||
# # 确保 DataFrame 按照股票代码和交易日期排序
|
||||
# df = df.sort_values(by=['ts_code', 'trade_date'])
|
||||
|
||||
# 对每个股票分别计算 score
|
||||
df['score'] = df.groupby('ts_code').apply(compute_stock_score).reset_index(level=0, drop=True)
|
||||
|
||||
return df['score']
|
||||
|
||||
|
||||
def remove_highly_correlated_features(df, feature_columns, threshold=0.9):
|
||||
numeric_features = df[feature_columns].select_dtypes(include=[np.number]).columns.tolist()
|
||||
if not numeric_features:
|
||||
raise ValueError("No numeric features found in the provided data.")
|
||||
|
||||
corr_matrix = df[numeric_features].corr().abs()
|
||||
upper = corr_matrix.where(np.triu(np.ones(corr_matrix.shape), k=1).astype(bool))
|
||||
to_drop = [column for column in upper.columns if any(upper[column] > threshold)]
|
||||
remaining_features = [col for col in feature_columns if col not in to_drop
|
||||
or 'act' in col or 'af' in col]
|
||||
return remaining_features
|
||||
|
||||
|
||||
import pandas as pd
|
||||
from sklearn.preprocessing import StandardScaler
|
||||
|
||||
|
||||
def cross_sectional_standardization(df, features):
|
||||
df_sorted = df.sort_values(by='trade_date') # 按时间排序
|
||||
df_standardized = df_sorted.copy()
|
||||
|
||||
for date in df_sorted['trade_date'].unique():
|
||||
# 获取当前时间点的数据
|
||||
current_data = df_standardized[df_standardized['trade_date'] == date]
|
||||
|
||||
# 只对指定特征进行标准化
|
||||
scaler = StandardScaler()
|
||||
standardized_values = scaler.fit_transform(current_data[features])
|
||||
|
||||
# 将标准化结果重新赋值回去
|
||||
df_standardized.loc[df_standardized['trade_date'] == date, features] = standardized_values
|
||||
|
||||
return df_standardized
|
||||
|
||||
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
import statsmodels.api as sm
|
||||
|
||||
from concurrent.futures import ProcessPoolExecutor
|
||||
|
||||
|
||||
def neutralize_manual(df, features, industry_col, mkt_cap_col):
|
||||
""" 手动实现简单回归以提升速度 """
|
||||
|
||||
for col in features:
|
||||
residuals = []
|
||||
for _, group in df.groupby(industry_col):
|
||||
if len(group) > 1:
|
||||
x = np.log(group[mkt_cap_col]) # 市值对数
|
||||
y = group[col] # 因子值
|
||||
beta = np.cov(y, x)[0, 1] / np.var(x) # 计算斜率
|
||||
alpha = np.mean(y) - beta * np.mean(x) # 计算截距
|
||||
resid = y - (alpha + beta * x) # 计算残差
|
||||
residuals.extend(resid)
|
||||
else:
|
||||
residuals.extend(group[col]) # 样本不足时保留原值
|
||||
|
||||
df[col] = residuals
|
||||
|
||||
return df
|
||||
|
||||
|
||||
import gc
|
||||
|
||||
gc.collect()
|
||||
|
||||
|
||||
def mad_filter(df, features, n=3):
|
||||
for col in features:
|
||||
median = df[col].median()
|
||||
mad = np.median(np.abs(df[col] - median))
|
||||
upper = median + n * mad
|
||||
lower = median - n * mad
|
||||
df[col] = np.clip(df[col], lower, upper) # 截断极值
|
||||
return df
|
||||
|
||||
|
||||
def percentile_filter(df, features, lower_percentile=0.01, upper_percentile=0.99):
|
||||
for col in features:
|
||||
# 按日期分组计算上下百分位数
|
||||
lower_bound = df.groupby('trade_date')[col].transform(
|
||||
lambda x: x.quantile(lower_percentile)
|
||||
)
|
||||
upper_bound = df.groupby('trade_date')[col].transform(
|
||||
lambda x: x.quantile(upper_percentile)
|
||||
)
|
||||
# 截断超出范围的值
|
||||
df[col] = np.clip(df[col], lower_bound, upper_bound)
|
||||
return df
|
||||
|
||||
|
||||
from scipy.stats import iqr
|
||||
|
||||
|
||||
def iqr_filter(df, features):
|
||||
for col in features:
|
||||
df[col] = df.groupby('trade_date')[col].transform(
|
||||
lambda x: (x - x.median()) / iqr(x) if iqr(x) != 0 else x
|
||||
)
|
||||
return df
|
||||
|
||||
|
||||
def quantile_filter(df, features, lower_quantile=0.01, upper_quantile=0.99, window=60):
|
||||
df = df.copy()
|
||||
for col in features:
|
||||
# 计算 rolling 统计量，需要按日期进行 groupby
|
||||
rolling_lower = df.groupby('trade_date')[col].transform(
|
||||
lambda x: x.rolling(window=min(len(x), window)).quantile(lower_quantile))
|
||||
rolling_upper = df.groupby('trade_date')[col].transform(
|
||||
lambda x: x.rolling(window=min(len(x), window)).quantile(upper_quantile))
|
||||
|
||||
# 对数据进行裁剪
|
||||
df[col] = np.clip(df[col], rolling_lower, rolling_upper)
|
||||
|
||||
return df
|
||||
|
||||
|
||||
# In[11]:
|
||||
|
||||
|
||||
# print(test_data.head()[['act_factor1', 'act_factor2', 'ts_code', 'trade_date']])
|
||||
|
||||
|
||||
# In[12]:
|
||||
|
||||
|
||||
from sklearn.preprocessing import StandardScaler
|
||||
import lightgbm as lgb
|
||||
import matplotlib.pyplot as plt
|
||||
from sklearn.decomposition import PCA
|
||||
|
||||
|
||||
def train_light_model(train_data_df, params, feature_columns, callbacks, evals,
|
||||
print_feature_importance=True, num_boost_round=100,
|
||||
validation_days=180, use_pca=False, split_date=None): # 新增参数：validation_days
|
||||
# 确保数据按时间排序
|
||||
train_data_df = train_data_df.sort_values(by='trade_date')
|
||||
|
||||
numeric_columns = train_data_df.select_dtypes(include=['float64', 'int64']).columns
|
||||
numeric_columns = [col for col in numeric_columns if col in feature_columns]
|
||||
# X_train.loc[:, numeric_columns] = scaler.fit_transform(X_train[numeric_columns])
|
||||
# X_val.loc[:, numeric_columns] = scaler.transform(X_val[numeric_columns])
|
||||
# train_data_df = cross_sectional_standardization(train_data_df, numeric_columns)
|
||||
|
||||
# 去除标签为空的样本
|
||||
train_data_df = train_data_df.dropna(subset=['label'])
|
||||
print('原始训练集大小: ', len(train_data_df))
|
||||
|
||||
# 按时间顺序划分训练集和验证集
|
||||
if split_date is None:
|
||||
all_dates = train_data_df['trade_date'].unique() # 获取所有唯一的 trade_date
|
||||
split_date = all_dates[-validation_days] # 划分点为倒数第 validation_days 天
|
||||
train_data_split = train_data_df[train_data_df['trade_date'] < split_date] # 训练集
|
||||
val_data_split = train_data_df[train_data_df['trade_date'] >= split_date] # 验证集
|
||||
|
||||
# 打印划分结果
|
||||
print(f"划分后的训练集大小: {len(train_data_split)}, 验证集大小: {len(val_data_split)}")
|
||||
|
||||
# 提取特征和标签
|
||||
X_train = train_data_split[feature_columns]
|
||||
y_train = train_data_split['label']
|
||||
|
||||
X_val = val_data_split[feature_columns]
|
||||
y_val = val_data_split['label']
|
||||
|
||||
# 标准化数值特征
|
||||
scaler = StandardScaler()
|
||||
|
||||
# 计算每个 trade_date 内的样本数（LTR 需要 group 信息）
|
||||
train_groups = train_data_split.groupby('trade_date').size().tolist()
|
||||
val_groups = val_data_split.groupby('trade_date').size().tolist()
|
||||
|
||||
# 处理类别特征
|
||||
categorical_feature = [col for col in feature_columns if 'cat' in col]
|
||||
|
||||
pca = None
|
||||
if use_pca:
|
||||
pca = PCA(n_components=0.95) # 或指定 n_components=固定值（如 10）
|
||||
numeric_features = [col for col in feature_columns if col not in categorical_feature]
|
||||
numeric_pca = pca.fit_transform(X_train[numeric_features])
|
||||
X_train = pd.concat([pd.DataFrame(numeric_pca, index=X_train.index), X_train[categorical_feature]], axis=1)
|
||||
|
||||
numeric_pca = pca.transform(X_val[numeric_features])
|
||||
X_val = pd.concat([pd.DataFrame(numeric_pca, index=X_val.index), X_val[categorical_feature]], axis=1)
|
||||
|
||||
# 计算权重（基于时间）
|
||||
# trade_date = train_data_split['trade_date'] # 交易日期
|
||||
# weights = (trade_date - trade_date.min()).dt.days / (trade_date.max() - trade_date.min()).days + 1
|
||||
# weights = train_data_split.groupby('trade_date')['std_return_5'].transform(
|
||||
# lambda x: x / x.mean()
|
||||
# )
|
||||
ud = sorted(train_data_split["trade_date"].unique().tolist())
|
||||
date_weights = {date: weight * weight for date, weight in zip(ud, np.linspace(1, 10, len(ud)))}
|
||||
params['weight'] = train_data_split["trade_date"].map(date_weights).tolist()
|
||||
|
||||
train_dataset = lgb.Dataset(
|
||||
X_train, label=y_train, group=train_groups,
|
||||
categorical_feature=categorical_feature
|
||||
)
|
||||
|
||||
# weights = val_data_split.groupby('trade_date')['std_return_5'].transform(
|
||||
# lambda x: x / x.mean()
|
||||
# )
|
||||
val_dataset = lgb.Dataset(
|
||||
X_val, label=y_val, group=val_groups,
|
||||
categorical_feature=categorical_feature
|
||||
)
|
||||
|
||||
# 训练模型
|
||||
model = lgb.train(
|
||||
params, train_dataset, num_boost_round=num_boost_round,
|
||||
valid_sets=[train_dataset, val_dataset], valid_names=['train', 'valid'],
|
||||
callbacks=callbacks
|
||||
)
|
||||
|
||||
# 打印特征重要性（如果需要）
|
||||
if print_feature_importance:
|
||||
lgb.plot_metric(evals)
|
||||
lgb.plot_importance(model, importance_type='split', max_num_features=20)
|
||||
plt.show()
|
||||
|
||||
return model, scaler, pca
|
||||
|
||||
|
||||
# In[13]:
|
||||
|
||||
|
||||
days = 2
|
||||
df = df.sort_values(by=['ts_code', 'trade_date'])
|
||||
# df['future_return'] = df.groupby('ts_code', group_keys=False)['close'].apply(lambda x: x.shift(-days) / x - 1)
|
||||
df['future_return'] = (df.groupby('ts_code')['close'].shift(-days) - df.groupby('ts_code')['open'].shift(-1)) / \
|
||||
df.groupby('ts_code')['open'].shift(-1)
|
||||
df['future_volatility'] = (
|
||||
df.groupby('ts_code')['pct_chg']
|
||||
.transform(lambda x: x.rolling(days).std().shift(-days))
|
||||
)
|
||||
df['future_score'] = calculate_score(df, days=2, lambda_param=0.3)
|
||||
df['label'] = df.groupby('trade_date', group_keys=False)['future_score'].transform(
|
||||
lambda x: pd.qcut(x, q=20, labels=False, duplicates='drop')
|
||||
)
|
||||
# df['future_score'] = (
|
||||
# 0.7 * df['future_return']
|
||||
# * 0.3 * df['future_volatility']
|
||||
# )
|
||||
|
||||
|
||||
# In[30]:
|
||||
|
||||
|
||||
def select_pre_zt_stocks_dynamic(
|
||||
stock_df,
|
||||
):
|
||||
stock_df = stock_df.groupby('trade_date', group_keys=False).apply(
|
||||
lambda x: x.nlargest(1000, 'return_20')
|
||||
)
|
||||
return stock_df
|
||||
|
||||
|
||||
pdf = select_pre_zt_stocks_dynamic(df)
|
||||
filter_index = pdf['future_return'].between(pdf['future_return'].quantile(0.01), pdf['future_return'].quantile(0.99))
|
||||
|
||||
# filter_index = pdf['future_volatility'].between(pdf['future_volatility'].quantile(0.01),
|
||||
# pdf['future_volatility'].quantile(0.99)) | filter_index
|
||||
|
||||
|
||||
# In[ ]:
|
||||
|
||||
|
||||
pdf = pdf.merge(industry_df, on=['cat_l2_code', 'trade_date'], how='left')
|
||||
pdf = pdf.sort_values(['trade_date'])
|
||||
pdf = pdf.replace([np.inf, -np.inf], np.nan)
|
||||
|
||||
|
||||
feature_columns = [col for col in pdf.columns if col in pdf.columns]
|
||||
feature_columns = [col for col in feature_columns if col not in ['trade_date',
|
||||
'ts_code',
|
||||
'label']]
|
||||
feature_columns = [col for col in feature_columns if 'future' not in col]
|
||||
feature_columns = [col for col in feature_columns if 'label' not in col]
|
||||
feature_columns = [col for col in feature_columns if 'score' not in col]
|
||||
feature_columns = [col for col in feature_columns if 'gen' not in col]
|
||||
feature_columns = [col for col in feature_columns if 'cat_l2_code' not in col]
|
||||
feature_columns = [col for col in feature_columns if col not in origin_columns]
|
||||
feature_columns = [col for col in feature_columns if not col.startswith('_')]
|
||||
|
||||
numeric_columns = pdf.select_dtypes(include=['float64', 'int64']).columns
|
||||
numeric_columns = [col for col in numeric_columns if col in feature_columns]
|
||||
|
||||
# feature_columns, _ = remove_shifted_features(pdf, feature_columns, size=0.8)
|
||||
|
||||
pdf = quantile_filter(pdf, numeric_columns)
|
||||
|
||||
pdf = cross_sectional_standardization(pdf, numeric_columns)
|
||||
|
||||
|
||||
# print('去极值')
|
||||
# train_data = quantile_filter(train_data, numeric_columns) # 去极值
|
||||
# # print('中性化')
|
||||
# # train_data = neutralize_manual(train_data, numeric_columns, industry_col='cat_l2_code', mkt_cap_col='log(circ_mv)') # 中性化
|
||||
# print('去极值')
|
||||
# test_data = quantile_filter(test_data, numeric_columns) # 去极值
|
||||
|
||||
feature_columns = remove_highly_correlated_features(pdf,
|
||||
feature_columns)
|
||||
print(len(pdf))
|
||||
|
||||
|
||||
# In[123]:
|
||||
|
||||
|
||||
# print('train data size: ', len(train_data))
|
||||
|
||||
label_gain = list(range(len(df['label'].unique())))
|
||||
label_gain = [gain * gain for gain in label_gain]
|
||||
light_params = {
|
||||
'label_gain': label_gain,
|
||||
'objective': 'lambdarank',
|
||||
'metric': 'ndcg',
|
||||
'learning_rate': 0.03,
|
||||
'num_leaves': 32,
|
||||
# 'min_data_in_leaf': 128,
|
||||
'max_depth': 8,
|
||||
'max_bin': 32,
|
||||
'feature_fraction': 0.7,
|
||||
# 'bagging_fraction': 0.7,
|
||||
'bagging_freq': 5,
|
||||
'lambda_l1': 0.1,
|
||||
'lambda_l2': 0.1,
|
||||
'boosting': 'gbdt',
|
||||
'verbosity': -1,
|
||||
'extra_trees': True,
|
||||
'max_position': 5,
|
||||
'ndcg_at': 1,
|
||||
'quant_train_renew_leaf': True,
|
||||
'lambdarank_truncation_level': 3,
|
||||
# 'lambdarank_position_bias_regularization': 1,
|
||||
'seed': 7
|
||||
}
|
||||
evals = {}
|
||||
|
||||
gc.collect()
|
||||
|
||||
|
||||
# In[128]:
|
||||
|
||||
|
||||
gc.collect()
|
||||
|
||||
|
||||
def rolling_train_predict(df, train_days, test_days, feature_columns_origin, days=5, use_pca=False, validation_days=60,
|
||||
filter_index=None):
|
||||
# 1. 按照交易日期排序
|
||||
unique_dates = df[df['trade_date'] >= '2020-01-01']['trade_date'].unique().tolist()
|
||||
unique_dates = sorted(unique_dates)
|
||||
n = len(unique_dates)
|
||||
|
||||
# 2. 计算需要跳过的天数，使后续窗口对齐
|
||||
extra_days = (n - train_days) % test_days
|
||||
start_index = extra_days # 从此索引开始滚动
|
||||
|
||||
predictions_list = []
|
||||
|
||||
for start in range(start_index, n - train_days - test_days + 1, test_days):
|
||||
|
||||
train_dates = unique_dates[start: start + train_days]
|
||||
test_dates = unique_dates[start + train_days: start + train_days + test_days]
|
||||
|
||||
# 根据日期筛选数据
|
||||
train_data = df[filter_index & df['trade_date'].isin(train_dates)]
|
||||
test_data = df[df['trade_date'].isin(test_dates)]
|
||||
|
||||
train_data = train_data.sort_values('trade_date')
|
||||
test_data = test_data.sort_values('trade_date')
|
||||
|
||||
# feature_columns, _ = remove_shifted_features(train_data, feature_columns_origin, size=0.8)
|
||||
|
||||
train_data = train_data.dropna(subset=feature_columns)
|
||||
train_data = train_data.dropna(subset=['label'])
|
||||
train_data = train_data.reset_index(drop=True)
|
||||
|
||||
# print(test_data.tail())
|
||||
test_data = test_data.dropna(subset=feature_columns)
|
||||
# test_data = test_data.dropna(subset=['label'])
|
||||
test_data = test_data.reset_index(drop=True)
|
||||
|
||||
# print(len(train_data))
|
||||
print(f"最小日期: {train_data['trade_date'].min().strftime('%Y-%m-%d')}")
|
||||
print(f"最大日期: {train_data['trade_date'].max().strftime('%Y-%m-%d')}")
|
||||
# print(len(test_data))
|
||||
print(f"最小日期: {test_data['trade_date'].min().strftime('%Y-%m-%d')}")
|
||||
print(f"最大日期: {test_data['trade_date'].max().strftime('%Y-%m-%d')}")
|
||||
|
||||
cat_columns = [col for col in df.columns if col.startswith('cat')]
|
||||
for col in cat_columns:
|
||||
train_data[col] = train_data[col].astype('category')
|
||||
test_data[col] = test_data[col].astype('category')
|
||||
|
||||
label_gain = list(range(len(train_data['label'].unique())))
|
||||
label_gain = [(gain + 1) * (gain + 1) for gain in label_gain]
|
||||
light_params['label_gain'] = label_gain
|
||||
|
||||
# ud = train_data["trade_date"].unique()
|
||||
# date_weights = {date: weight for date, weight in zip(ud, np.linspace(1, 2, len(unique_dates)))}
|
||||
# light_params['weight'] = train_data["trade_date"].map(date_weights).tolist()
|
||||
|
||||
# print(f'feature_columns: {feature_columns}')
|
||||
# feature_contri = [2 if feat.startswith('act_factor') else 1 for feat in feature_columns]
|
||||
# light_params['feature_contri'] = feature_contri
|
||||
model, _, _ = train_light_model(train_data.dropna(subset=['label']),
|
||||
light_params, feature_columns,
|
||||
[lgb.log_evaluation(period=100),
|
||||
lgb.callback.record_evaluation(evals),
|
||||
lgb.early_stopping(100, first_metric_only=True)
|
||||
], evals,
|
||||
num_boost_round=3000, validation_days=validation_days,
|
||||
print_feature_importance=False, use_pca=False)
|
||||
|
||||
score_df = test_data.copy()
|
||||
score_df['score'] = model.predict(score_df[feature_columns])
|
||||
score_df = score_df.loc[score_df.groupby('trade_date')['score'].idxmax()]
|
||||
score_df = score_df[['trade_date', 'score', 'ts_code']]
|
||||
predictions_list.append(score_df)
|
||||
|
||||
# m = 5
|
||||
# all_data = []
|
||||
# for i, trade_date in enumerate(sorted(score_df['trade_date'].unique().tolist())):
|
||||
# # 提取当前日期的数据
|
||||
# current_data = score_df[score_df['trade_date'] == trade_date]
|
||||
# all_data.append(current_data)
|
||||
#
|
||||
# numeric_columns = [col for col in feature_columns if col in current_data.select_dtypes(include=['float64', 'int64']).columns]
|
||||
# current_data = cross_sectional_standardization(current_data, numeric_columns)
|
||||
# current_data['score'] = model.predict(current_data[feature_columns])
|
||||
# daily_top_score = current_data.loc[[current_data['score'].idxmax()]]
|
||||
# predictions_list.append(daily_top_score[['trade_date', 'score', 'ts_code']])
|
||||
#
|
||||
# if i % m == 0:
|
||||
# train_data_split = pd.concat(all_data)
|
||||
# train_data_split = train_data_split.dropna(subset=['label'])
|
||||
#
|
||||
# X_train = train_data_split[feature_columns]
|
||||
# y_train = train_data_split['label']
|
||||
#
|
||||
# train_groups = train_data_split.groupby('trade_date').size().tolist()
|
||||
# categorical_feature = [col for col in feature_columns if 'cat' in col]
|
||||
#
|
||||
# train_dataset = lgb.Dataset(
|
||||
# X_train, label=y_train, group=train_groups,
|
||||
# categorical_feature=categorical_feature
|
||||
# )
|
||||
#
|
||||
# model = lgb.train(
|
||||
# light_params, train_dataset, num_boost_round=36,
|
||||
# init_model=model
|
||||
# )
|
||||
# all_data = []
|
||||
|
||||
final_predictions = pd.concat(predictions_list, ignore_index=True)
|
||||
return final_predictions
|
||||
|
||||
|
||||
# In[129]:
|
||||
|
||||
|
||||
gc.collect()
|
||||
|
||||
print(df[df['ts_code'] == '000001.SZ'].tail(1)[['act_factor1', 'act_factor2']])
|
||||
print('finish')
|
||||
# qdf = qdf[qdf['trade_date'] >= '2022-01-01']
|
||||
|
||||
final_predictions = rolling_train_predict(pdf[pdf['trade_date'] >= '2020-01-01'], 500, 20, feature_columns,
|
||||
days=days, validation_days=60, filter_index=filter_index)
|
||||
final_predictions.to_csv('predictions_test.tsv', index=False)
|
||||
|
||||
|
||||
# In[126]:
|
||||
|
||||
|
||||
print(df[df['ts_code'] == '000001.SZ'].tail(1)[['act_factor1', 'act_factor2']])
|
||||
print('finish')
|
||||
|
||||
|
||||
# In[29]:
|
||||
|
||||
|
||||
train_data = pdf[filter_index & (pdf['trade_date'] == '2023-01-03')]
|
||||
train_data = train_data.dropna(subset=['label'])
|
||||
train_data = train_data.reset_index(drop=True)
|
||||
print(len(train_data))
|
||||
|
||||
|
||||
# In[34]:
|
||||
|
||||
|
||||
# filter_index = pdf['future_return'].between(pdf['future_return'].quantile(0.01), pdf['future_return'].quantile(0.99))
|
||||
|
||||
train_data = pdf[filter_index & (pdf['trade_date'] == '2023-01-03')]
|
||||
print(len(train_data))
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -37,7 +37,7 @@
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"from utils.utils import read_and_merge_h5_data\n",
|
||||
"from code.utils.utils import read_and_merge_h5_data\n",
|
||||
"\n",
|
||||
"print('daily data')\n",
|
||||
"df = read_and_merge_h5_data('../../data/daily_data.h5', key='daily_data',\n",
|
||||
@@ -587,7 +587,7 @@
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"from utils.factor import get_act_factor\n",
|
||||
"from code.utils.factor import get_act_factor\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def read_industry_data(h5_filename):\n",
|
||||
@@ -1205,10 +1205,6 @@
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"import torch\n",
|
||||
"import torch.nn as nn\n",
|
||||
"import torch.optim as optim\n",
|
||||
"from torch.utils.data import DataLoader, Dataset\n",
|
||||
"from sklearn.metrics import accuracy_score\n",
|
||||
"\n",
|
||||
"num_heads = 4 # Transformer头数\n",
|
||||
"transformer_input_dim = 64\n",
|
||||
@@ -1243,8 +1239,6 @@
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"from tqdm import tqdm\n",
|
||||
"import torch\n",
|
||||
"import torch.nn as nn\n",
|
||||
"import torch.optim as optim\n",
|
||||
"from sklearn.preprocessing import LabelEncoder, StandardScaler\n",
|
||||
"from sklearn.metrics import accuracy_score\n",
|
||||
@@ -44,7 +44,7 @@
|
||||
},
|
||||
"source": [
|
||||
"\n",
|
||||
"from utils.utils import read_and_merge_h5_data\n",
|
||||
"from code.utils.utils import read_and_merge_h5_data\n",
|
||||
"\n",
|
||||
"print('daily data')\n",
|
||||
"df = read_and_merge_h5_data('../../data/daily_data.h5', key='daily_data',\n",
|
||||
@@ -33,7 +33,7 @@
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"from utils.utils import read_and_merge_h5_data\n",
|
||||
"from code.utils.utils import read_and_merge_h5_data\n",
|
||||
"\n",
|
||||
"print('daily data')\n",
|
||||
"df = read_and_merge_h5_data('../../data/daily_data.h5', key='daily_data',\n",
|
||||
@@ -33,7 +33,7 @@
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"from utils.utils import read_and_merge_h5_data\n",
|
||||
"from code.utils.utils import read_and_merge_h5_data\n",
|
||||
"\n",
|
||||
"print('daily data')\n",
|
||||
"df = read_and_merge_h5_data('../../data/daily_data.h5', key='daily_data',\n",
|
||||
@@ -592,7 +592,7 @@
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"from utils.factor import get_act_factor\n",
|
||||
"from code.utils.factor import get_act_factor\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def read_industry_data(h5_filename):\n",
|
||||
@@ -735,9 +735,6 @@
|
||||
},
|
||||
"source": [
|
||||
"from scipy.stats import ks_2samp, wasserstein_distance\n",
|
||||
"from sklearn.metrics import roc_auc_score\n",
|
||||
"from sklearn.model_selection import train_test_split\n",
|
||||
"from sklearn.preprocessing import StandardScaler\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def remove_shifted_features(train_data, test_data, feature_columns, ks_threshold=0.1, wasserstein_threshold=0.15,\n",
|
||||
@@ -902,7 +899,6 @@
|
||||
"\n",
|
||||
"\n",
|
||||
"import pandas as pd\n",
|
||||
"from sklearn.preprocessing import StandardScaler\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def cross_sectional_standardization(df, features):\n",
|
||||
@@ -41,7 +41,7 @@
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"from utils.utils import read_and_merge_h5_data\n",
|
||||
"from code.utils.utils import read_and_merge_h5_data\n",
|
||||
"\n",
|
||||
"print('daily data')\n",
|
||||
"df = read_and_merge_h5_data('../../data/daily_data.h5', key='daily_data',\n",
|
||||
@@ -36,7 +36,7 @@
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"from utils.utils import read_and_merge_h5_data\n",
|
||||
"from code.utils.utils import read_and_merge_h5_data\n",
|
||||
"\n",
|
||||
"print('daily data')\n",
|
||||
"df = read_and_merge_h5_data('../../data/daily_data.h5', key='daily_data',\n",
|
||||
@@ -142,8 +142,7 @@
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"import pandas as pd\n",
|
||||
"import numpy as np\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def calculate_indicators(df):\n",
|
||||
@@ -791,15 +790,11 @@
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"from sklearn.linear_model import SGDRegressor\n",
|
||||
"from sklearn.preprocessing import StandardScaler, OneHotEncoder\n",
|
||||
"from sklearn.compose import ColumnTransformer\n",
|
||||
"from sklearn.pipeline import Pipeline\n",
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"\n",
|
||||
"import numpy as np\n",
|
||||
"\n",
|
||||
"import pandas as pd\n",
|
||||
"from sklearn.linear_model import SGDRegressor, LinearRegression\n",
|
||||
"from sklearn.linear_model import LinearRegression\n",
|
||||
"from sklearn.preprocessing import StandardScaler, OneHotEncoder\n",
|
||||
"\n",
|
||||
"\n",
|
||||
@@ -1304,7 +1299,6 @@
|
||||
},
|
||||
"source": [
|
||||
"import joblib\n",
|
||||
"import lightgbm as lgb\n",
|
||||
"import pandas as pd\n",
|
||||
"\n",
|
||||
"\n",
|
||||
@@ -12,7 +12,7 @@
|
||||
"%load_ext autoreload\n",
|
||||
"%autoreload 2\n",
|
||||
"\n",
|
||||
"from utils.utils import read_and_merge_h5_data"
|
||||
"from code.utils.utils import read_and_merge_h5_data"
|
||||
],
|
||||
"id": "79a7758178bafdd3",
|
||||
"outputs": [],
|
||||
@@ -12,7 +12,7 @@
|
||||
"%load_ext autoreload\n",
|
||||
"%autoreload 2\n",
|
||||
"\n",
|
||||
"from utils.utils import read_and_merge_h5_data\n"
|
||||
"from code.utils.utils import read_and_merge_h5_data\n"
|
||||
],
|
||||
"id": "79a7758178bafdd3",
|
||||
"outputs": [
|
||||
0
main/train/__init__.py
Normal file
0
main/train/__init__.py
Normal file
565
main/train/predictions_test.tsv
Normal file
565
main/train/predictions_test.tsv
Normal file
@@ -0,0 +1,565 @@
|
||||
trade_date,score,ts_code
|
||||
2022-12-08,0.27431420966080605,600778.SH
|
||||
2022-12-09,0.6150539465999814,002995.SZ
|
||||
2022-12-12,0.32582588516973016,001219.SZ
|
||||
2022-12-13,0.449772253615743,603183.SH
|
||||
2022-12-14,0.6769511128551923,001219.SZ
|
||||
2022-12-15,0.5930979713048357,001219.SZ
|
||||
2022-12-16,0.43211109874606424,603183.SH
|
||||
2022-12-19,0.5066203384263489,000892.SZ
|
||||
2022-12-20,0.2882618462700443,000691.SZ
|
||||
2022-12-21,0.40494380930765467,001219.SZ
|
||||
2022-12-22,0.7379517535413331,002762.SZ
|
||||
2022-12-23,0.5775898117404806,002566.SZ
|
||||
2022-12-26,0.3292293609625978,002719.SZ
|
||||
2022-12-27,0.580738686242899,000679.SZ
|
||||
2022-12-28,0.5180122078878033,605289.SH
|
||||
2022-12-29,0.643325626734685,002103.SZ
|
||||
2022-12-30,0.5378362015974298,603209.SH
|
||||
2023-01-03,0.36814451293952416,000985.SZ
|
||||
2023-01-04,0.4506419163930136,605133.SH
|
||||
2023-01-05,-0.08745711573292192,605167.SH
|
||||
2023-01-06,0.3958417326952953,605289.SH
|
||||
2023-01-09,0.16620697664167175,600778.SH
|
||||
2023-01-10,0.25992110313636035,000985.SZ
|
||||
2023-01-11,0.5095437644681087,002771.SZ
|
||||
2023-01-12,0.4397750442288285,605258.SH
|
||||
2023-01-13,0.6102622318789971,003043.SZ
|
||||
2023-01-16,0.31204276505440004,002808.SZ
|
||||
2023-01-17,0.4972787924897241,002975.SZ
|
||||
2023-01-18,0.026553404105244968,002975.SZ
|
||||
2023-01-19,0.29558268580158115,603860.SH
|
||||
2023-01-20,0.2510349420297213,002849.SZ
|
||||
2023-01-30,0.21942028551157527,003039.SZ
|
||||
2023-01-31,0.3575069234093295,605081.SH
|
||||
2023-02-01,0.4427957172082794,002893.SZ
|
||||
2023-02-02,0.6212207641739337,600817.SH
|
||||
2023-02-03,0.6202750689624308,002993.SZ
|
||||
2023-02-06,0.20845430964837489,000010.SZ
|
||||
2023-02-07,0.3667829939094325,600593.SH
|
||||
2023-02-08,0.32215761217132205,000820.SZ
|
||||
2023-02-09,0.1516026707537734,002021.SZ
|
||||
2023-02-10,0.5453734923733047,003016.SZ
|
||||
2023-02-13,0.7491169288183265,003037.SZ
|
||||
2023-02-14,0.32476512974212635,002828.SZ
|
||||
2023-02-15,0.6984519009806621,605128.SH
|
||||
2023-02-16,0.2078494458450699,605378.SH
|
||||
2023-02-17,0.20087261579967608,000668.SZ
|
||||
2023-02-20,0.6724819126277912,002715.SZ
|
||||
2023-02-21,0.7209181859866042,605028.SH
|
||||
2023-02-22,0.42474501256326314,002900.SZ
|
||||
2023-02-23,0.43124729325039124,001236.SZ
|
||||
2023-02-24,0.6008854884810912,603102.SH
|
||||
2023-02-27,0.5702542696831331,605259.SH
|
||||
2023-02-28,0.24318268223778186,002857.SZ
|
||||
2023-03-01,0.5388577927345274,603950.SH
|
||||
2023-03-02,0.6815724852841429,001236.SZ
|
||||
2023-03-03,0.6064483180272962,002098.SZ
|
||||
2023-03-06,0.5180664638865109,605178.SH
|
||||
2023-03-07,0.7291442722387731,001339.SZ
|
||||
2023-03-08,0.3240206100047592,603268.SH
|
||||
2023-03-09,0.5619204909224714,603030.SH
|
||||
2023-03-10,0.6055962888677536,003027.SZ
|
||||
2023-03-13,0.10471064296768949,605296.SH
|
||||
2023-03-14,0.5148688231123284,603176.SH
|
||||
2023-03-15,0.41425644779572274,605287.SH
|
||||
2023-03-16,0.3858205191834723,605303.SH
|
||||
2023-03-17,0.38210649704563177,002899.SZ
|
||||
2023-03-20,0.20755090351337924,002778.SZ
|
||||
2023-03-21,0.2184477420463366,603155.SH
|
||||
2023-03-22,0.07842488490864312,002836.SZ
|
||||
2023-03-23,0.26327386834675565,002899.SZ
|
||||
2023-03-24,0.21281930224537013,605086.SH
|
||||
2023-03-27,0.19455767073518335,603729.SH
|
||||
2023-03-28,0.18440479662298903,603324.SH
|
||||
2023-03-29,0.5577394899737692,002995.SZ
|
||||
2023-03-30,0.28537485170922117,603679.SH
|
||||
2023-03-31,0.30705863202777134,603615.SH
|
||||
2023-04-03,0.43719928717137047,603321.SH
|
||||
2023-04-04,0.7949399014212187,603139.SH
|
||||
2023-04-06,0.5079656399994698,002715.SZ
|
||||
2023-04-07,0.701235747536229,605299.SH
|
||||
2023-04-10,0.5142089175897191,001316.SZ
|
||||
2023-04-11,0.6097058153625001,002835.SZ
|
||||
2023-04-12,0.42821688099056865,003043.SZ
|
||||
2023-04-13,0.6086458195457266,605296.SH
|
||||
2023-04-14,0.40520429106061684,001316.SZ
|
||||
2023-04-17,0.7332476184295339,002862.SZ
|
||||
2023-04-18,0.24978196798538302,600768.SH
|
||||
2023-04-19,0.5235224445388739,603657.SH
|
||||
2023-04-20,0.5073410973887871,000702.SZ
|
||||
2023-04-21,0.25827344858110657,002848.SZ
|
||||
2023-04-24,0.441433820804789,603685.SH
|
||||
2023-04-25,0.45710917638850534,603230.SH
|
||||
2023-04-26,0.28288056233393655,002725.SZ
|
||||
2023-04-27,0.13616135413238703,002972.SZ
|
||||
2023-04-28,0.26068199992734814,603178.SH
|
||||
2023-05-04,0.5654404518697154,600107.SH
|
||||
2023-05-05,0.26758125911217795,603021.SH
|
||||
2023-05-08,0.23558429168600836,002778.SZ
|
||||
2023-05-09,0.2707962779077066,603213.SH
|
||||
2023-05-10,0.33701828135159717,600778.SH
|
||||
2023-05-11,0.5467076847749692,603958.SH
|
||||
2023-05-12,0.6956005090125644,603958.SH
|
||||
2023-05-15,0.28587355864974423,000679.SZ
|
||||
2023-05-16,0.6092507418432053,600796.SH
|
||||
2023-05-17,0.4723632871528185,002633.SZ
|
||||
2023-05-18,0.44171920333992315,605089.SH
|
||||
2023-05-19,0.15743942037394715,001317.SZ
|
||||
2023-05-22,0.47338926108587503,603151.SH
|
||||
2023-05-23,0.7537765588258426,603721.SH
|
||||
2023-05-24,0.35894033254239865,003007.SZ
|
||||
2023-05-25,0.6230303733419829,003005.SZ
|
||||
2023-05-26,0.5243725213664181,003005.SZ
|
||||
2023-05-29,0.5460639613578377,001288.SZ
|
||||
2023-05-30,-0.14324964018444036,605151.SH
|
||||
2023-05-31,0.1321851497388741,003041.SZ
|
||||
2023-06-01,0.488265280236323,603170.SH
|
||||
2023-06-02,0.2725329302903607,002875.SZ
|
||||
2023-06-05,0.4445215836414108,001316.SZ
|
||||
2023-06-06,0.233866225393599,600753.SH
|
||||
2023-06-07,0.1512953839015877,603097.SH
|
||||
2023-06-08,0.5303933339784708,002780.SZ
|
||||
2023-06-09,0.595474766855165,002893.SZ
|
||||
2023-06-12,0.7044220035173576,002820.SZ
|
||||
2023-06-13,0.46792362066084003,002702.SZ
|
||||
2023-06-14,0.5917956764629129,000880.SZ
|
||||
2023-06-15,0.3231002542961875,002981.SZ
|
||||
2023-06-16,0.3426911954075076,600847.SH
|
||||
2023-06-19,-0.02150391139369695,603132.SH
|
||||
2023-06-20,0.6704208966606625,002949.SZ
|
||||
2023-06-21,0.7415606269689047,002806.SZ
|
||||
2023-06-26,0.2389199769543643,600847.SH
|
||||
2023-06-27,0.2003853580878301,605169.SH
|
||||
2023-06-28,0.46623595119888966,605218.SH
|
||||
2023-06-29,0.5589108980336046,603958.SH
|
||||
2023-06-30,0.6290675381060588,603286.SH
|
||||
2023-07-03,0.30433310431106353,600778.SH
|
||||
2023-07-04,0.41651276650561014,002513.SZ
|
||||
2023-07-05,0.3473548650199746,603132.SH
|
||||
2023-07-06,0.40969750497772167,002591.SZ
|
||||
2023-07-07,0.2430362735691786,001231.SZ
|
||||
2023-07-10,0.4983750803303532,001267.SZ
|
||||
2023-07-11,0.733386176985722,002551.SZ
|
||||
2023-07-12,0.7936049551065578,000004.SZ
|
||||
2023-07-13,0.40916765144188155,000638.SZ
|
||||
2023-07-14,0.21996055437116258,605580.SH
|
||||
2023-07-17,0.22071234127281886,605369.SH
|
||||
2023-07-18,0.32992331418284704,002802.SZ
|
||||
2023-07-19,0.3337178034533016,001222.SZ
|
||||
2023-07-20,0.44391528952121656,600234.SH
|
||||
2023-07-21,0.5703993630872055,600448.SH
|
||||
2023-07-24,0.13840705878806345,002753.SZ
|
||||
2023-07-25,0.14047801960398054,002377.SZ
|
||||
2023-07-26,0.44664932418756537,003032.SZ
|
||||
2023-07-27,0.5452266508240136,603838.SH
|
||||
2023-07-28,0.6501197606840003,002397.SZ
|
||||
2023-07-31,0.8161881604231447,002397.SZ
|
||||
2023-08-01,0.8054314713785248,002397.SZ
|
||||
2023-08-02,0.5699471212343736,600119.SH
|
||||
2023-08-03,0.3961899673469923,002787.SZ
|
||||
2023-08-04,0.747143154431229,600082.SH
|
||||
2023-08-07,0.5542807418220157,605162.SH
|
||||
2023-08-08,0.4660499541690493,605369.SH
|
||||
2023-08-09,0.1846960748819621,605060.SH
|
||||
2023-08-10,0.6657079567366654,003020.SZ
|
||||
2023-08-11,0.657079341742516,000953.SZ
|
||||
2023-08-14,0.42201036027484534,002495.SZ
|
||||
2023-08-15,0.4783974585467736,002495.SZ
|
||||
2023-08-16,0.5756999736912221,003030.SZ
|
||||
2023-08-17,0.7578964013923504,002052.SZ
|
||||
2023-08-18,0.004897979672684783,603151.SH
|
||||
2023-08-21,0.11103177103375994,605339.SH
|
||||
2023-08-22,0.5482563310657345,603021.SH
|
||||
2023-08-23,0.7223546665888397,000669.SZ
|
||||
2023-08-24,0.750140979575826,600235.SH
|
||||
2023-08-25,0.34893747282432125,001318.SZ
|
||||
2023-08-28,0.17097259367409923,603329.SH
|
||||
2023-08-29,0.290639411928478,001267.SZ
|
||||
2023-08-30,0.07811174210597455,603021.SH
|
||||
2023-08-31,0.2910924076064356,603838.SH
|
||||
2023-09-01,0.6435370857973789,002696.SZ
|
||||
2023-09-04,0.04554737468797225,605259.SH
|
||||
2023-09-05,0.18999529865866976,001231.SZ
|
||||
2023-09-06,0.47343827547785233,002982.SZ
|
||||
2023-09-07,0.5685183560937441,001231.SZ
|
||||
2023-09-08,0.4682919982486746,003025.SZ
|
||||
2023-09-11,0.511414318533627,002535.SZ
|
||||
2023-09-12,0.34217637355801866,003020.SZ
|
||||
2023-09-13,0.4524964916922371,001269.SZ
|
||||
2023-09-14,0.6440683894231696,002856.SZ
|
||||
2023-09-15,0.6265975964127983,001269.SZ
|
||||
2023-09-18,0.6451154901817582,002857.SZ
|
||||
2023-09-19,0.41416994363886955,605151.SH
|
||||
2023-09-20,0.4097659657161061,600615.SH
|
||||
2023-09-21,0.3308468663518861,603616.SH
|
||||
2023-09-22,0.7278118492027132,600608.SH
|
||||
2023-09-25,0.3087058065638187,002963.SZ
|
||||
2023-09-26,0.44957535540535354,000638.SZ
|
||||
2023-09-27,0.6529354742977974,000609.SZ
|
||||
2023-09-28,0.5608546287364546,605080.SH
|
||||
2023-10-09,0.2684689324603092,000004.SZ
|
||||
2023-10-10,0.7514903867910352,001337.SZ
|
||||
2023-10-11,0.6833204831817536,000010.SZ
|
||||
2023-10-12,0.6849345854259707,001288.SZ
|
||||
2023-10-13,0.45213040270359944,001223.SZ
|
||||
2023-10-16,0.44367713319364266,001311.SZ
|
||||
2023-10-17,0.4358062265247695,001266.SZ
|
||||
2023-10-18,0.7896227965981543,002535.SZ
|
||||
2023-10-19,0.8091287635227896,000609.SZ
|
||||
2023-10-20,0.7497841605463051,000705.SZ
|
||||
2023-10-23,0.5162013866354915,600615.SH
|
||||
2023-10-24,0.5346626404470584,000554.SZ
|
||||
2023-10-25,0.31017050910898813,002836.SZ
|
||||
2023-10-26,0.41928742617604475,002798.SZ
|
||||
2023-10-27,0.6206681321070086,600791.SH
|
||||
2023-10-30,0.2809249638133884,600697.SH
|
||||
2023-10-31,0.41380204486883465,605299.SH
|
||||
2023-11-01,0.3913649017002345,002952.SZ
|
||||
2023-11-02,0.25190883932779223,603272.SH
|
||||
2023-11-03,0.25483193696737405,600697.SH
|
||||
2023-11-06,0.6843951349633363,603900.SH
|
||||
2023-11-07,0.6794539224187386,002005.SZ
|
||||
2023-11-08,0.2787637201989255,605337.SH
|
||||
2023-11-09,0.43869442213023335,603307.SH
|
||||
2023-11-10,0.2901012944614997,002615.SZ
|
||||
2023-11-13,0.48928158926409887,003020.SZ
|
||||
2023-11-14,0.46232236500040824,603268.SH
|
||||
2023-11-15,0.6895995906987776,000010.SZ
|
||||
2023-11-16,0.45286066066734804,001298.SZ
|
||||
2023-11-17,0.7301876489705413,000010.SZ
|
||||
2023-11-20,0.7343688038104235,000004.SZ
|
||||
2023-11-21,0.23914531702237296,600361.SH
|
||||
2023-11-22,0.6007850824537518,002735.SZ
|
||||
2023-11-23,0.6504458118708949,603655.SH
|
||||
2023-11-24,0.46094310596129545,002842.SZ
|
||||
2023-11-27,0.6273014444813882,603729.SH
|
||||
2023-11-28,0.44076850931480105,002188.SZ
|
||||
2023-11-29,0.2215431212240851,605598.SH
|
||||
2023-11-30,0.47752407474308556,002247.SZ
|
||||
2023-12-01,0.5451043441108514,603045.SH
|
||||
2023-12-04,0.37633081988016603,603183.SH
|
||||
2023-12-05,0.7161351255511346,000929.SZ
|
||||
2023-12-06,0.467262040140511,002848.SZ
|
||||
2023-12-07,0.39095280707015256,600883.SH
|
||||
2023-12-08,0.4253618928722024,001373.SZ
|
||||
2023-12-11,0.2828511933586843,002753.SZ
|
||||
2023-12-12,0.5178019880022604,600099.SH
|
||||
2023-12-13,0.5539680447662736,000702.SZ
|
||||
2023-12-14,0.7341038153763678,000609.SZ
|
||||
2023-12-15,0.5186263801346903,002495.SZ
|
||||
2023-12-18,0.45857609424669377,002835.SZ
|
||||
2023-12-19,0.4688848440159626,000004.SZ
|
||||
2023-12-20,0.528943977776945,002571.SZ
|
||||
2023-12-21,0.22718655814787117,000020.SZ
|
||||
2023-12-22,0.5928968748610841,002052.SZ
|
||||
2023-12-25,0.3483050510250432,001201.SZ
|
||||
2023-12-26,0.32710963694268524,600778.SH
|
||||
2023-12-27,0.8023420246227895,603061.SH
|
||||
2023-12-28,0.6117050022740004,001223.SZ
|
||||
2023-12-29,0.30978967753335185,600791.SH
|
||||
2024-01-02,0.7213136293380755,001339.SZ
|
||||
2024-01-03,0.27966735262244463,603255.SH
|
||||
2024-01-04,0.4113020595403535,002569.SZ
|
||||
2024-01-05,0.5862299814842546,002397.SZ
|
||||
2024-01-08,0.2751799131522872,002207.SZ
|
||||
2024-01-09,0.3983758716199103,600462.SH
|
||||
2024-01-10,0.27583418641572577,002381.SZ
|
||||
2024-01-11,0.5163369671207251,001308.SZ
|
||||
2024-01-12,0.1869457075250673,001333.SZ
|
||||
2024-01-15,0.38890973684559677,600778.SH
|
||||
2024-01-16,0.628350379976437,002973.SZ
|
||||
2024-01-17,0.567643592779436,001259.SZ
|
||||
2024-01-18,0.45358303557672786,605003.SH
|
||||
2024-01-19,0.17143291074790643,605003.SH
|
||||
2024-01-22,0.38033202178552034,600137.SH
|
||||
2024-01-23,0.2682996358307573,603307.SH
|
||||
2024-01-24,0.09762885957278981,002200.SZ
|
||||
2024-01-25,0.2791248936457759,600322.SH
|
||||
2024-01-26,0.6698373552722515,001300.SZ
|
||||
2024-01-29,0.3453399213641141,001212.SZ
|
||||
2024-01-30,0.2018197040316142,000609.SZ
|
||||
2024-01-31,0.13839592742162668,002862.SZ
|
||||
2024-02-01,0.304731410465905,002397.SZ
|
||||
2024-02-02,0.4968354158495188,600791.SH
|
||||
2024-02-05,0.6076128945914563,002883.SZ
|
||||
2024-02-06,0.27529438199416406,001313.SZ
|
||||
2024-02-07,0.7032777773473656,601279.SH
|
||||
2024-02-08,0.5124649392628607,001339.SZ
|
||||
2024-02-19,0.47259882754683735,600608.SH
|
||||
2024-02-20,-0.14666017874686663,605289.SH
|
||||
2024-02-21,0.658199830069353,001317.SZ
|
||||
2024-02-22,-0.03512517816725689,603895.SH
|
||||
2024-02-23,0.49070407040956543,603286.SH
|
||||
2024-02-26,0.5874761268473985,603192.SH
|
||||
2024-02-27,0.6988377838547319,002856.SZ
|
||||
2024-02-28,0.2914956876374956,002513.SZ
|
||||
2024-02-29,0.39780267057003393,002760.SZ
|
||||
2024-03-01,0.270122240597905,000908.SZ
|
||||
2024-03-04,0.6403053454891889,000622.SZ
|
||||
2024-03-05,0.7898552633062592,002848.SZ
|
||||
2024-03-06,0.3809277227308279,002888.SZ
|
||||
2024-03-07,0.853455303753637,002199.SZ
|
||||
2024-03-08,0.2596463171676263,603206.SH
|
||||
2024-03-11,0.7555631824344116,002888.SZ
|
||||
2024-03-12,0.22682284013007994,001298.SZ
|
||||
2024-03-13,0.5422854277369126,001298.SZ
|
||||
2024-03-14,0.45779191251005164,600444.SH
|
||||
2024-03-15,0.6383376746111096,603023.SH
|
||||
2024-03-18,0.3201696636960583,001217.SZ
|
||||
2024-03-19,0.5996501433774017,001300.SZ
|
||||
2024-03-20,0.679915283803281,603273.SH
|
||||
2024-03-21,0.33698105904573383,000820.SZ
|
||||
2024-03-22,0.5218294653991029,002272.SZ
|
||||
2024-03-25,0.6420731490646061,002272.SZ
|
||||
2024-03-26,0.2833072190123176,000985.SZ
|
||||
2024-03-27,0.47781267803027716,002094.SZ
|
||||
2024-03-28,0.3495920493283059,001368.SZ
|
||||
2024-03-29,0.6814619283051855,605167.SH
|
||||
2024-04-01,0.13340757834476227,002787.SZ
|
||||
2024-04-02,0.6485933245807073,002629.SZ
|
||||
2024-04-03,0.5005374249650347,600889.SH
|
||||
2024-04-08,0.3458211793083884,002998.SZ
|
||||
2024-04-09,0.4543106999676991,603268.SH
|
||||
2024-04-10,0.3782795993313912,600289.SH
|
||||
2024-04-11,0.5682306510607521,002999.SZ
|
||||
2024-04-12,0.7563586796123376,001333.SZ
|
||||
2024-04-15,0.6820371060072895,605259.SH
|
||||
2024-04-16,0.20646370209051096,603177.SH
|
||||
2024-04-17,0.397823887165538,001367.SZ
|
||||
2024-04-18,0.5284023840181794,001288.SZ
|
||||
2024-04-19,0.5531779115633008,603137.SH
|
||||
2024-04-22,0.5285690780224108,603270.SH
|
||||
2024-04-23,0.4948891344668796,605003.SH
|
||||
2024-04-24,0.18745324505195465,002899.SZ
|
||||
2024-04-25,0.5561527695473475,605287.SH
|
||||
2024-04-26,0.3910800271321991,603813.SH
|
||||
2024-04-29,0.22800522777162466,600083.SH
|
||||
2024-04-30,0.47575239303431954,603991.SH
|
||||
2024-05-06,0.24135147235517762,603991.SH
|
||||
2024-05-07,0.6505337985284155,603955.SH
|
||||
2024-05-08,-0.008011195615733824,000820.SZ
|
||||
2024-05-09,0.3612607813981246,002848.SZ
|
||||
2024-05-10,0.5729784871026853,002295.SZ
|
||||
2024-05-13,0.42642459942636673,001228.SZ
|
||||
2024-05-14,0.616654660412696,603150.SH
|
||||
2024-05-15,0.14069160886717613,000995.SZ
|
||||
2024-05-16,0.2893164763341796,002893.SZ
|
||||
2024-05-17,0.26559138928183623,000593.SZ
|
||||
2024-05-20,0.6202830453921107,605318.SH
|
||||
2024-05-21,0.5962739970033031,002231.SZ
|
||||
2024-05-22,0.24212148187955357,600408.SH
|
||||
2024-05-23,0.5866973439001457,000056.SZ
|
||||
2024-05-24,0.4950026505575876,002620.SZ
|
||||
2024-05-27,0.2716568170957144,001367.SZ
|
||||
2024-05-28,0.614584069552624,603062.SH
|
||||
2024-05-29,0.5190445551469995,605567.SH
|
||||
2024-05-30,0.5650446836882232,001299.SZ
|
||||
2024-05-31,0.05127480727491687,002811.SZ
|
||||
2024-06-03,0.34948424376750514,603276.SH
|
||||
2024-06-04,0.2962107247005024,605365.SH
|
||||
2024-06-05,0.4265710639424621,600793.SH
|
||||
2024-06-06,0.2352508879607737,603193.SH
|
||||
2024-06-07,0.48735816467729426,001306.SZ
|
||||
2024-06-11,0.46798640763968125,002569.SZ
|
||||
2024-06-12,0.47153387530090407,001215.SZ
|
||||
2024-06-13,0.5520110912359264,603280.SH
|
||||
2024-06-14,0.19454715507705864,605598.SH
|
||||
2024-06-17,0.0963230849661045,002888.SZ
|
||||
2024-06-18,-0.07804798333558113,002615.SZ
|
||||
2024-06-19,0.610634439198648,002848.SZ
|
||||
2024-06-20,0.528548137823535,002888.SZ
|
||||
2024-06-21,0.5548914160403448,603097.SH
|
||||
2024-06-24,0.39920928373259934,001336.SZ
|
||||
2024-06-25,0.3187385965144802,603255.SH
|
||||
2024-06-26,0.32449821843842575,002582.SZ
|
||||
2024-06-27,0.5820092583390628,001387.SZ
|
||||
2024-06-28,0.3390536217231177,600493.SH
|
||||
2024-07-01,0.6778726275046811,002875.SZ
|
||||
2024-07-02,0.20520989636689582,605255.SH
|
||||
2024-07-03,0.5743008555845837,002495.SZ
|
||||
2024-07-04,0.9067074210889693,002247.SZ
|
||||
2024-07-05,0.7460402549612926,002094.SZ
|
||||
2024-07-08,0.6484051297498691,002012.SZ
|
||||
2024-07-09,0.4656464752321579,000056.SZ
|
||||
2024-07-10,0.5651250099764935,600421.SH
|
||||
2024-07-11,0.3919914680384934,000010.SZ
|
||||
2024-07-12,0.6138163480575665,002861.SZ
|
||||
2024-07-15,0.7779874584252403,605318.SH
|
||||
2024-07-16,0.4480483662651257,001217.SZ
|
||||
2024-07-17,0.4172203427639832,002094.SZ
|
||||
2024-07-18,0.7704811874850669,600561.SH
|
||||
2024-07-19,0.47075926007399854,002883.SZ
|
||||
2024-07-22,0.7111332900169166,002094.SZ
|
||||
2024-07-23,0.2511920883015322,002094.SZ
|
||||
2024-07-24,0.4172115642303865,000017.SZ
|
||||
2024-07-25,0.3128542596085397,002485.SZ
|
||||
2024-07-26,0.7143056769547913,002800.SZ
|
||||
2024-07-29,0.7348554188058531,001212.SZ
|
||||
2024-07-30,0.6544735763131749,600678.SH
|
||||
2024-07-31,0.33170353517328943,000619.SZ
|
||||
2024-08-01,0.5622688198785722,603021.SH
|
||||
2024-08-02,0.553901968970459,600355.SH
|
||||
2024-08-05,0.7203888768112711,002652.SZ
|
||||
2024-08-06,0.06845913509306308,002388.SZ
|
||||
2024-08-07,0.32607442357451333,002647.SZ
|
||||
2024-08-08,0.16487864247139689,600538.SH
|
||||
2024-08-09,0.541184606366378,603657.SH
|
||||
2024-08-12,0.26199426116748675,605180.SH
|
||||
2024-08-13,0.3717346916082516,600281.SH
|
||||
2024-08-14,0.6248284781260683,603151.SH
|
||||
2024-08-15,0.4701587394310862,001288.SZ
|
||||
2024-08-16,0.4980961856837102,600538.SH
|
||||
2024-08-19,0.6280757532182177,002622.SZ
|
||||
2024-08-20,0.4216952108346084,002094.SZ
|
||||
2024-08-21,0.8872335373988718,001317.SZ
|
||||
2024-08-22,0.5745604057145399,000056.SZ
|
||||
2024-08-23,0.505744305740485,603122.SH
|
||||
2024-08-26,0.8419619283484038,002072.SZ
|
||||
2024-08-27,0.6810091806857562,002084.SZ
|
||||
2024-08-28,0.6875657067302675,002072.SZ
|
||||
2024-08-29,0.44229937751556,600692.SH
|
||||
2024-08-30,0.5551556278148088,605100.SH
|
||||
2024-09-02,0.6992787682915002,000004.SZ
|
||||
2024-09-03,0.29976910325882256,001218.SZ
|
||||
2024-09-04,0.6768429298090569,002717.SZ
|
||||
2024-09-05,0.6206771676543172,002622.SZ
|
||||
2024-09-06,0.7271087976454396,002861.SZ
|
||||
2024-09-09,0.5051345343079485,002199.SZ
|
||||
2024-09-10,0.606941618095118,600533.SH
|
||||
2024-09-11,0.44563057902498,000632.SZ
|
||||
2024-09-12,0.544127097473236,600889.SH
|
||||
2024-09-13,0.8023872948409544,000702.SZ
|
||||
2024-09-18,0.27102315041971126,002729.SZ
|
||||
2024-09-19,0.8222201895966966,002629.SZ
|
||||
2024-09-20,0.7270786760641249,001296.SZ
|
||||
2024-09-23,0.6662260924500418,603778.SH
|
||||
2024-09-24,0.45201298931080247,600322.SH
|
||||
2024-09-25,0.7020112241768041,000573.SZ
|
||||
2024-09-26,0.9042164267563502,600322.SH
|
||||
2024-09-27,0.6660782992616279,600156.SH
|
||||
2024-09-30,0.6863709879538685,600156.SH
|
||||
2024-10-08,0.6127578713627717,600791.SH
|
||||
2024-10-09,0.42399006878436024,002486.SZ
|
||||
2024-10-10,0.19353810507130897,001379.SZ
|
||||
2024-10-11,0.32072111647856577,001306.SZ
|
||||
2024-10-14,0.3485052899457631,605169.SH
|
||||
2024-10-15,0.23682051553226138,603130.SH
|
||||
2024-10-16,0.06953864745342996,000695.SZ
|
||||
2024-10-17,0.6514983088909282,600599.SH
|
||||
2024-10-18,0.4389209760325074,002977.SZ
|
||||
2024-10-21,0.7197768607464181,603261.SH
|
||||
2024-10-22,0.6635882450692222,002806.SZ
|
||||
2024-10-23,0.45400588695990063,603172.SH
|
||||
2024-10-24,0.38830884380759845,600107.SH
|
||||
2024-10-25,0.8934238346702872,600243.SH
|
||||
2024-10-28,0.2797309154889543,600539.SH
|
||||
2024-10-29,0.2969987104969114,600768.SH
|
||||
2024-10-30,0.40287164661797453,002551.SZ
|
||||
2024-10-31,0.3564256188428194,002086.SZ
|
||||
2024-11-01,0.6321036634810505,002551.SZ
|
||||
2024-11-04,0.5456367520507691,603682.SH
|
||||
2024-11-05,0.4395577653608702,600802.SH
|
||||
2024-11-06,0.6650198272206568,600243.SH
|
||||
2024-11-07,0.43235770657243566,000430.SZ
|
||||
2024-11-08,0.5643849119436214,002076.SZ
|
||||
2024-11-11,0.7137448249635079,000007.SZ
|
||||
2024-11-12,0.5201716819040841,000679.SZ
|
||||
2024-11-13,0.6337096887315559,603214.SH
|
||||
2024-11-14,0.4979383369165651,603201.SH
|
||||
2024-11-15,0.45240021627553617,603201.SH
|
||||
2024-11-18,0.22669552732089976,605177.SH
|
||||
2024-11-19,0.38573714473203297,603331.SH
|
||||
2024-11-20,0.2979426663257885,001378.SZ
|
||||
2024-11-21,0.42041152689995204,002980.SZ
|
||||
2024-11-22,0.4998877526755884,003003.SZ
|
||||
2024-11-25,0.3166022033285757,002381.SZ
|
||||
2024-11-26,0.5105217556899093,001300.SZ
|
||||
2024-11-27,0.4581772650911419,603183.SH
|
||||
2024-11-28,0.2582863137914294,600302.SH
|
||||
2024-11-29,0.6516611156931627,600202.SH
|
||||
2024-12-02,0.6264742314126309,603021.SH
|
||||
2024-12-03,0.17876631396560913,605287.SH
|
||||
2024-12-04,0.571815529773696,603637.SH
|
||||
2024-12-05,0.5009836942607793,002615.SZ
|
||||
2024-12-06,0.5935816089479097,002615.SZ
|
||||
2024-12-09,0.2732740647491455,000880.SZ
|
||||
2024-12-10,0.8403246240655503,002211.SZ
|
||||
2024-12-11,0.6063814254598854,000952.SZ
|
||||
2024-12-12,0.65530104057359,002213.SZ
|
||||
2024-12-13,0.4326422618589393,002193.SZ
|
||||
2024-12-16,0.6951945851895344,002582.SZ
|
||||
2024-12-17,0.4367668554492269,002846.SZ
|
||||
2024-12-18,0.6034186500026795,600844.SH
|
||||
2024-12-19,0.6478095239545749,000695.SZ
|
||||
2024-12-20,0.12678291780050743,002687.SZ
|
||||
2024-12-23,0.0005977226174160126,603176.SH
|
||||
2024-12-24,0.6931664421535906,000790.SZ
|
||||
2024-12-25,0.9280754228431425,000004.SZ
|
||||
2024-12-26,0.5025149234980124,603082.SH
|
||||
2024-12-27,0.5619791111821815,603325.SH
|
||||
2024-12-30,0.5970375646444621,603291.SH
|
||||
2024-12-31,0.6210268787938896,603798.SH
|
||||
2025-01-02,0.5150847228562943,603255.SH
|
||||
2025-01-03,0.3936455223882481,001238.SZ
|
||||
2025-01-06,0.42512989288467096,001256.SZ
|
||||
2025-01-07,0.20046282642128765,002763.SZ
|
||||
2025-01-08,0.3594789763099251,603137.SH
|
||||
2025-01-09,0.17148562512671917,603150.SH
|
||||
2025-01-10,0.8141461510449396,603909.SH
|
||||
2025-01-13,0.7278259334554208,002365.SZ
|
||||
2025-01-14,0.5332116728293693,000955.SZ
|
||||
2025-01-15,0.26395540555061114,001223.SZ
|
||||
2025-01-16,0.20321325349056088,603637.SH
|
||||
2025-01-17,0.5155710238940482,000586.SZ
|
||||
2025-01-20,0.7692783436325927,002072.SZ
|
||||
2025-01-21,0.3743531875901297,601798.SH
|
||||
2025-01-22,0.5609509357408301,603059.SH
|
||||
2025-01-23,0.20207700522454125,001378.SZ
|
||||
2025-01-24,0.3138610824997807,002760.SZ
|
||||
2025-01-27,0.3887191549307029,603192.SH
|
||||
2025-02-05,0.5131470103792286,600599.SH
|
||||
2025-02-06,0.42133133196663924,603255.SH
|
||||
2025-02-07,0.2981033776962701,605003.SH
|
||||
2025-02-10,0.78495727017451,600225.SH
|
||||
2025-02-11,0.9081192688195034,600225.SH
|
||||
2025-02-12,0.8027995368952746,600225.SH
|
||||
2025-02-13,0.6500142590724168,603789.SH
|
||||
2025-02-14,0.7725392087365835,002058.SZ
|
||||
2025-02-17,0.49255867173448825,600228.SH
|
||||
2025-02-18,0.5576519868864848,600243.SH
|
||||
2025-02-19,0.2592919075461544,002496.SZ
|
||||
2025-02-20,0.421298468924212,002848.SZ
|
||||
2025-02-21,0.29697775540100313,001316.SZ
|
||||
2025-02-24,0.7638868267339545,603211.SH
|
||||
2025-02-25,0.5526784340520452,003028.SZ
|
||||
2025-02-26,0.5065861650146529,603716.SH
|
||||
2025-02-27,0.7407038446632749,603211.SH
|
||||
2025-02-28,0.4668521688585335,003043.SZ
|
||||
2025-03-03,0.2680721667617631,600753.SH
|
||||
2025-03-04,0.34955816615272756,002977.SZ
|
||||
2025-03-05,0.7482244194415444,603057.SH
|
||||
2025-03-06,0.6305254140888802,603280.SH
|
||||
2025-03-07,0.19351037427994797,600241.SH
|
||||
2025-03-10,0.38766031239447357,603325.SH
|
||||
2025-03-11,0.4303913500153944,002872.SZ
|
||||
2025-03-12,0.18459289202598228,002898.SZ
|
||||
2025-03-13,0.8576596052682522,001319.SZ
|
||||
2025-03-14,0.6230146680130096,000757.SZ
|
||||
2025-03-17,0.7328875682123387,603843.SH
|
||||
2025-03-18,0.47499472013228067,000669.SZ
|
||||
2025-03-19,0.3268919044509167,002305.SZ
|
||||
2025-03-20,0.4569272632462979,600356.SH
|
||||
2025-03-21,0.07591851931376978,000586.SZ
|
||||
2025-03-24,0.49072061900133407,603335.SH
|
||||
2025-03-25,0.4306632631450777,603381.SH
|
||||
2025-03-26,0.46006642069249487,001299.SZ
|
||||
2025-03-27,0.41362062710862235,002394.SZ
|
||||
2025-03-28,0.564157006795436,001332.SZ
|
||||
2025-03-31,0.5981134959932276,001238.SZ
|
||||
2025-04-01,0.6363729449100586,603102.SH
|
||||
2025-04-02,0.2865246522723796,002872.SZ
|
||||
2025-04-03,0.29802040504689753,000633.SZ
|
||||
2025-04-07,0.554762051627518,002872.SZ
|
||||
2025-04-08,0.34687738661031947,603682.SH
|
||||
2025-04-09,0.13896921728258024,001331.SZ
|
||||
|
14
main/train/test.py
Normal file
14
main/train/test.py
Normal file
@@ -0,0 +1,14 @@
|
||||
from operator import index
|
||||
|
||||
import tushare as ts
|
||||
import pandas as pd
|
||||
import time
|
||||
|
||||
ts.set_token('3a0741c702ee7e5e5f2bf1f0846bafaafe4e320833240b2a7e4a685f')
|
||||
pro = ts.pro_api()
|
||||
|
||||
df = pro.index_member_all(ts_code='603579.SH')
|
||||
print(df)
|
||||
|
||||
df = pro.sw_daily(trade_date='20250305', fields='ts_code,name,open,close,vol,pe,pb')
|
||||
print(df[df['ts_code'] == '851171.SI'])
|
||||
565
main/train/test1.tsv
Normal file
565
main/train/test1.tsv
Normal file
@@ -0,0 +1,565 @@
|
||||
trade_date,score,ts_code
|
||||
2022-12-08,1.2708337806641494,603816.SH
|
||||
2022-12-09,1.4207120834806832,603567.SH
|
||||
2022-12-12,1.0198883623815167,002305.SZ
|
||||
2022-12-13,1.7022732146012465,002910.SZ
|
||||
2022-12-14,0.4115956442621504,600493.SH
|
||||
2022-12-15,1.2308250306434583,601858.SH
|
||||
2022-12-16,0.5214964254452716,601677.SH
|
||||
2022-12-19,1.5635207796349075,000721.SZ
|
||||
2022-12-20,0.9950031675966513,002314.SZ
|
||||
2022-12-21,1.867139344678808,603238.SH
|
||||
2022-12-22,0.11397346668733664,002095.SZ
|
||||
2022-12-23,0.7020503260530933,600706.SH
|
||||
2022-12-26,1.064077090528082,002707.SZ
|
||||
2022-12-27,0.5487905008977592,000978.SZ
|
||||
2022-12-28,0.9795388321537417,600225.SH
|
||||
2022-12-29,0.6402559056339422,600056.SH
|
||||
2022-12-30,0.9466308655445547,002357.SZ
|
||||
2023-01-03,0.6849950582517478,002031.SZ
|
||||
2023-01-04,0.8958700703884613,003010.SZ
|
||||
2023-01-05,0.9901544872773684,002357.SZ
|
||||
2023-01-06,0.7029762528454185,000929.SZ
|
||||
2023-01-09,1.2070723183050875,002279.SZ
|
||||
2023-01-10,0.28632510343867906,002933.SZ
|
||||
2023-01-11,0.7059503351778397,002576.SZ
|
||||
2023-01-12,1.700028635026902,002576.SZ
|
||||
2023-01-13,1.4228228373146723,002043.SZ
|
||||
2023-01-16,0.24930703006686591,600958.SH
|
||||
2023-01-17,1.0616927130654037,603882.SH
|
||||
2023-01-18,0.6166412038694548,000739.SZ
|
||||
2023-01-19,0.5967697229641841,603806.SH
|
||||
2023-01-20,0.8290879039003781,600705.SH
|
||||
2023-01-30,1.0826864888349266,000972.SZ
|
||||
2023-01-31,1.7476350470413293,605133.SH
|
||||
2023-02-01,1.0698795326344217,002297.SZ
|
||||
2023-02-02,1.168956058233029,002762.SZ
|
||||
2023-02-03,0.6068761459217956,002474.SZ
|
||||
2023-02-06,1.3603267774479497,002855.SZ
|
||||
2023-02-07,1.3722562072579707,002167.SZ
|
||||
2023-02-08,1.444800461687164,002117.SZ
|
||||
2023-02-09,0.6478721098934555,600501.SH
|
||||
2023-02-10,1.7330712792214502,002122.SZ
|
||||
2023-02-13,1.0751336841418047,603711.SH
|
||||
2023-02-14,0.858121706097957,002354.SZ
|
||||
2023-02-15,1.0628443879922715,600817.SH
|
||||
2023-02-16,1.0941227999628862,002660.SZ
|
||||
2023-02-17,0.5452970336991657,002792.SZ
|
||||
2023-02-20,0.7452925786277558,600817.SH
|
||||
2023-02-21,1.2263444506836183,601360.SH
|
||||
2023-02-22,0.8498400500947443,002882.SZ
|
||||
2023-02-23,1.3778772059701936,002942.SZ
|
||||
2023-02-24,0.8116211264751758,002942.SZ
|
||||
2023-02-27,1.369491951000112,600118.SH
|
||||
2023-02-28,1.7437044662527195,600325.SH
|
||||
2023-03-01,0.6172338223208104,002350.SZ
|
||||
2023-03-02,0.9753294078191806,002261.SZ
|
||||
2023-03-03,0.9460072368251595,605389.SH
|
||||
2023-03-06,0.7661730237898733,000977.SZ
|
||||
2023-03-07,1.5306012129925908,601728.SH
|
||||
2023-03-08,1.7347243229852956,603042.SH
|
||||
2023-03-09,1.7785688963407722,601698.SH
|
||||
2023-03-10,1.794639030708944,002808.SZ
|
||||
2023-03-13,2.2765957078169055,601728.SH
|
||||
2023-03-14,1.5770232731123273,002236.SZ
|
||||
2023-03-15,1.9886076279595977,601698.SH
|
||||
2023-03-16,1.7538871949426555,601138.SH
|
||||
2023-03-17,1.2850616649676168,000506.SZ
|
||||
2023-03-20,0.6617355633181617,601117.SH
|
||||
2023-03-21,1.2834165832572753,600633.SH
|
||||
2023-03-22,1.286625601927238,002803.SZ
|
||||
2023-03-23,1.2442366849499193,601138.SH
|
||||
2023-03-24,1.7385288121049993,601138.SH
|
||||
2023-03-27,0.5271836596864287,600633.SH
|
||||
2023-03-28,0.9233261884964775,000890.SZ
|
||||
2023-03-29,1.0388156797328032,600633.SH
|
||||
2023-03-30,0.880222808466912,600975.SH
|
||||
2023-03-31,1.7723670660012394,002153.SZ
|
||||
2023-04-03,1.4447814388081068,600633.SH
|
||||
2023-04-04,0.9805981968002965,000988.SZ
|
||||
2023-04-06,1.2735568908129031,002558.SZ
|
||||
2023-04-07,0.5977729773368881,002222.SZ
|
||||
2023-04-10,0.36120306701232185,000032.SZ
|
||||
2023-04-11,2.0134197062348904,603258.SH
|
||||
2023-04-12,0.6807091195842823,603888.SH
|
||||
2023-04-13,1.5510435282176684,600415.SH
|
||||
2023-04-14,1.6158618609191548,603258.SH
|
||||
2023-04-17,0.5935406330588169,603918.SH
|
||||
2023-04-18,1.438798944751228,603258.SH
|
||||
2023-04-19,0.4851330354034662,002975.SZ
|
||||
2023-04-20,0.17004215747506052,600415.SH
|
||||
2023-04-21,1.3733089702528274,601595.SH
|
||||
2023-04-24,2.3249160418531685,603258.SH
|
||||
2023-04-25,2.4887955829326054,601858.SH
|
||||
2023-04-26,1.9420082198135482,601019.SH
|
||||
2023-04-27,2.3040109178691113,601811.SH
|
||||
2023-04-28,1.0754625899722956,601811.SH
|
||||
2023-05-04,1.6688121146522907,601336.SH
|
||||
2023-05-05,1.1037723664352612,601989.SH
|
||||
2023-05-08,1.6994199603704685,601288.SH
|
||||
2023-05-09,1.2636377329259567,002354.SZ
|
||||
2023-05-10,1.2628967915122853,601949.SH
|
||||
2023-05-11,0.8020741700988911,603083.SH
|
||||
2023-05-12,0.22312816960298115,600629.SH
|
||||
2023-05-15,0.7341052846591558,002229.SZ
|
||||
2023-05-16,0.6350705971737554,603268.SH
|
||||
2023-05-17,1.0396627856239795,603958.SH
|
||||
2023-05-18,1.4091099521269763,601858.SH
|
||||
2023-05-19,0.6341161328902458,600239.SH
|
||||
2023-05-22,0.4664478043150085,603798.SH
|
||||
2023-05-23,0.3950180406443093,002864.SZ
|
||||
2023-05-24,0.9532057286987137,002366.SZ
|
||||
2023-05-25,0.661525047825837,605011.SH
|
||||
2023-05-26,0.873646794491419,600088.SH
|
||||
2023-05-29,1.0161343809163572,600636.SH
|
||||
2023-05-30,1.8522924730896868,603918.SH
|
||||
2023-05-31,0.14065827549083917,002315.SZ
|
||||
2023-06-01,1.0647192154325815,002229.SZ
|
||||
2023-06-02,1.0897714474656055,605028.SH
|
||||
2023-06-05,0.818149194152834,002995.SZ
|
||||
2023-06-06,1.1559913886165554,002229.SZ
|
||||
2023-06-07,0.9730919792856488,603933.SH
|
||||
2023-06-08,1.1740853193005574,003010.SZ
|
||||
2023-06-09,0.7055820145524615,002395.SZ
|
||||
2023-06-12,0.8768369889703852,000977.SZ
|
||||
2023-06-13,0.5333934871843615,600839.SH
|
||||
2023-06-14,1.1828705214010444,002229.SZ
|
||||
2023-06-15,1.9054644381740913,600602.SH
|
||||
2023-06-16,1.6671793256997451,002920.SZ
|
||||
2023-06-19,0.4424093682681172,002194.SZ
|
||||
2023-06-20,0.7166566485622967,600100.SH
|
||||
2023-06-21,1.185368125310508,600592.SH
|
||||
2023-06-26,0.49477817284107434,605016.SH
|
||||
2023-06-27,0.6467017315354233,002865.SZ
|
||||
2023-06-28,1.4462997720570885,600310.SH
|
||||
2023-06-29,0.9079748876905797,000809.SZ
|
||||
2023-06-30,1.1417365323043627,002920.SZ
|
||||
2023-07-03,1.0292231512798002,600105.SH
|
||||
2023-07-04,0.9764499369108617,002355.SZ
|
||||
2023-07-05,1.1950967963313073,603489.SH
|
||||
2023-07-06,0.8067305519266362,603809.SH
|
||||
2023-07-07,-0.11113958569144997,603786.SH
|
||||
2023-07-10,1.4365223354022805,002835.SZ
|
||||
2023-07-11,0.9055036034028278,603767.SH
|
||||
2023-07-12,0.662603535490377,002265.SZ
|
||||
2023-07-13,0.6580169744401991,605005.SH
|
||||
2023-07-14,0.7806145283148259,002284.SZ
|
||||
2023-07-17,0.8928179964563782,002616.SZ
|
||||
2023-07-18,1.0102033286200784,603709.SH
|
||||
2023-07-19,0.28926601683884473,603429.SH
|
||||
2023-07-20,1.0778442223423874,603709.SH
|
||||
2023-07-21,0.49418969039024113,000068.SZ
|
||||
2023-07-24,1.152792861172028,002172.SZ
|
||||
2023-07-25,-0.48175589465657037,000656.SZ
|
||||
2023-07-26,0.9348834119551785,000608.SZ
|
||||
2023-07-27,1.5360069738010982,600231.SH
|
||||
2023-07-28,1.5514157372959714,600782.SH
|
||||
2023-07-31,0.31996521869248884,000750.SZ
|
||||
2023-08-01,0.5474246928163892,601860.SH
|
||||
2023-08-02,1.277218052964389,600162.SH
|
||||
2023-08-03,0.784739789704388,002400.SZ
|
||||
2023-08-04,1.5311245596423297,002310.SZ
|
||||
2023-08-07,1.3664999923727883,002377.SZ
|
||||
2023-08-08,0.6775719496805408,000004.SZ
|
||||
2023-08-09,1.0473202246778897,003005.SZ
|
||||
2023-08-10,0.7095500932241833,600610.SH
|
||||
2023-08-11,0.9061227536071346,000656.SZ
|
||||
2023-08-14,1.712926297349448,600272.SH
|
||||
2023-08-15,0.7173624078005385,000656.SZ
|
||||
2023-08-16,1.0612842867590515,600155.SH
|
||||
2023-08-17,-0.11242980180119416,002898.SZ
|
||||
2023-08-18,0.7958378602153298,002221.SZ
|
||||
2023-08-21,1.2818341414622505,000006.SZ
|
||||
2023-08-22,1.4925485997390293,000006.SZ
|
||||
2023-08-23,1.0205726179128791,002178.SZ
|
||||
2023-08-24,0.5123818439671383,603000.SH
|
||||
2023-08-25,1.1561261254770698,600684.SH
|
||||
2023-08-28,1.0243035845865234,600602.SH
|
||||
2023-08-29,0.48711445602297804,002279.SZ
|
||||
2023-08-30,1.5892134655969756,002279.SZ
|
||||
2023-08-31,0.8832038176770832,002235.SZ
|
||||
2023-09-01,0.7778267621876187,002527.SZ
|
||||
2023-09-04,0.9715794190221472,000766.SZ
|
||||
2023-09-05,0.6363690681522609,000701.SZ
|
||||
2023-09-06,1.1626954331771984,603078.SH
|
||||
2023-09-07,0.8950438021027404,601001.SH
|
||||
2023-09-08,0.4907685411177441,603722.SH
|
||||
2023-09-11,1.4880263364860575,000851.SZ
|
||||
2023-09-12,0.7192761393042792,603329.SH
|
||||
2023-09-13,0.7091837012523252,000158.SZ
|
||||
2023-09-14,0.7548676419597591,601699.SH
|
||||
2023-09-15,0.9847401608369946,600257.SH
|
||||
2023-09-18,1.7523740102808545,600814.SH
|
||||
2023-09-19,0.9311114338734422,000536.SZ
|
||||
2023-09-20,1.5094699709720083,002902.SZ
|
||||
2023-09-21,1.10032325281936,603890.SH
|
||||
2023-09-22,0.5455145772639567,001268.SZ
|
||||
2023-09-25,1.5392432178391338,600895.SH
|
||||
2023-09-26,1.139513204589203,002642.SZ
|
||||
2023-09-27,1.0155696225867201,002827.SZ
|
||||
2023-09-28,0.7631131516304462,001298.SZ
|
||||
2023-10-09,1.3121583124085132,002513.SZ
|
||||
2023-10-10,1.192726847273738,600895.SH
|
||||
2023-10-11,1.378300878017007,600895.SH
|
||||
2023-10-12,1.3374848728915072,000010.SZ
|
||||
2023-10-13,1.247352917522287,000536.SZ
|
||||
2023-10-16,1.0205919288199263,002456.SZ
|
||||
2023-10-17,1.8124967402525871,601127.SH
|
||||
2023-10-18,1.6545503123646252,002456.SZ
|
||||
2023-10-19,1.403565591711023,603009.SH
|
||||
2023-10-20,1.479674671497312,002176.SZ
|
||||
2023-10-23,1.1364881895480998,002337.SZ
|
||||
2023-10-24,1.603597993080332,002122.SZ
|
||||
2023-10-25,1.2135837368610372,603123.SH
|
||||
2023-10-26,1.0507834567170797,002671.SZ
|
||||
2023-10-27,1.2313059730365872,603266.SH
|
||||
2023-10-30,1.4721372697796935,603353.SH
|
||||
2023-10-31,0.8329626816487755,600599.SH
|
||||
2023-11-01,0.7167096735509632,603186.SH
|
||||
2023-11-02,1.2802635893255563,601633.SH
|
||||
2023-11-03,1.2590421473918265,002640.SZ
|
||||
2023-11-06,0.7531355226612281,003040.SZ
|
||||
2023-11-07,0.6577034595225779,603768.SH
|
||||
2023-11-08,1.8511623446368441,002889.SZ
|
||||
2023-11-09,1.4717991539794943,603266.SH
|
||||
2023-11-10,0.46890167407485095,002584.SZ
|
||||
2023-11-13,1.1394805956388967,603220.SH
|
||||
2023-11-14,1.0217982309018654,603883.SH
|
||||
2023-11-15,0.6661740992600602,600106.SH
|
||||
2023-11-16,1.3719183134079516,002584.SZ
|
||||
2023-11-17,1.5131093025579179,603266.SH
|
||||
2023-11-20,1.6229596862404188,002103.SZ
|
||||
2023-11-21,0.9595377845746105,002291.SZ
|
||||
2023-11-22,1.1541727944363123,600506.SH
|
||||
2023-11-23,0.6172428975445288,000029.SZ
|
||||
2023-11-24,0.3581002329377547,000710.SZ
|
||||
2023-11-27,1.0865084227106108,002691.SZ
|
||||
2023-11-28,0.36551005528336356,603721.SH
|
||||
2023-11-29,0.6325689777455243,600780.SH
|
||||
2023-11-30,0.9673540111120547,600148.SH
|
||||
2023-12-01,1.6031005266953247,002238.SZ
|
||||
2023-12-04,0.3139675086881397,601156.SH
|
||||
2023-12-05,0.4471787298728605,002238.SZ
|
||||
2023-12-06,1.519722809770461,600128.SH
|
||||
2023-12-07,0.9306959636346697,601599.SH
|
||||
2023-12-08,1.11955592447384,600678.SH
|
||||
2023-12-11,0.920549654717692,600981.SH
|
||||
2023-12-12,1.1192972102468268,603999.SH
|
||||
2023-12-13,1.059999047897406,601595.SH
|
||||
2023-12-14,1.3135891954923238,605577.SH
|
||||
2023-12-15,1.0121314183460337,603358.SH
|
||||
2023-12-18,1.2923561000198138,601595.SH
|
||||
2023-12-19,0.4727877781694898,002856.SZ
|
||||
2023-12-20,-0.01336745195249621,002937.SZ
|
||||
2023-12-21,0.9432845860894691,603825.SH
|
||||
2023-12-22,1.5927408932377043,603167.SH
|
||||
2023-12-25,1.1489781197830256,001314.SZ
|
||||
2023-12-26,2.075405615830143,605117.SH
|
||||
2023-12-27,1.1634401553385165,002952.SZ
|
||||
2023-12-28,1.9276471606617283,600610.SH
|
||||
2023-12-29,1.1664703290672742,600621.SH
|
||||
2024-01-02,1.4036288516782467,603396.SH
|
||||
2024-01-03,0.6064916104024441,603052.SH
|
||||
2024-01-04,0.27194078032727403,000810.SZ
|
||||
2024-01-05,0.7248236406349026,002884.SZ
|
||||
2024-01-08,1.917000409535365,600983.SH
|
||||
2024-01-09,1.3670026723187405,601225.SH
|
||||
2024-01-10,0.6428111801429847,002419.SZ
|
||||
2024-01-11,0.8603468507895841,603097.SH
|
||||
2024-01-12,0.8616154280062541,001269.SZ
|
||||
2024-01-15,1.6162131927011785,002140.SZ
|
||||
2024-01-16,1.6278064283944136,605366.SH
|
||||
2024-01-17,1.2234956634332685,603556.SH
|
||||
2024-01-18,0.2930411130350266,601865.SH
|
||||
2024-01-19,0.5463003069500746,002033.SZ
|
||||
2024-01-22,1.4568410090998594,600438.SH
|
||||
2024-01-23,0.4796543547584619,002056.SZ
|
||||
2024-01-24,1.1933657317735877,000921.SZ
|
||||
2024-01-25,1.1196073236619992,000070.SZ
|
||||
2024-01-26,0.22116166302548493,601225.SH
|
||||
2024-01-29,1.0247482544629951,000717.SZ
|
||||
2024-01-30,1.0239528607343813,000651.SZ
|
||||
2024-01-31,1.371059822546121,600188.SH
|
||||
2024-02-01,0.9952706097104108,601288.SH
|
||||
2024-02-02,1.1495734266360917,601658.SH
|
||||
2024-02-05,0.29949274220153294,600018.SH
|
||||
2024-02-06,1.299845239071017,600004.SH
|
||||
2024-02-07,1.000836675958177,600350.SH
|
||||
2024-02-08,0.6401652900537433,600131.SH
|
||||
2024-02-19,0.08475967168317824,002749.SZ
|
||||
2024-02-20,0.5804821425310229,002085.SZ
|
||||
2024-02-21,0.5362126107341831,600053.SH
|
||||
2024-02-22,1.206204153162725,600639.SH
|
||||
2024-02-23,1.6848572441872742,603958.SH
|
||||
2024-02-26,-0.22984388407558198,000017.SZ
|
||||
2024-02-27,-0.02096017812243845,603011.SH
|
||||
2024-02-28,1.1590591855669556,603933.SH
|
||||
2024-02-29,0.1819266114797644,002085.SZ
|
||||
2024-03-01,0.6727454630028324,600571.SH
|
||||
2024-03-04,1.113038537485005,601058.SH
|
||||
2024-03-05,0.8578265704409984,600160.SH
|
||||
2024-03-06,1.0085170866918751,600331.SH
|
||||
2024-03-07,1.0605223005794961,603220.SH
|
||||
2024-03-08,0.9054891550652612,601001.SH
|
||||
2024-03-11,1.3538575989659345,002085.SZ
|
||||
2024-03-12,0.9889456011580702,603580.SH
|
||||
2024-03-13,1.212835645663162,603499.SH
|
||||
2024-03-14,0.648581745020845,603773.SH
|
||||
2024-03-15,1.2772879612108654,002902.SZ
|
||||
2024-03-18,0.8179927345023094,002591.SZ
|
||||
2024-03-19,1.6214555790374034,000908.SZ
|
||||
2024-03-20,2.2115174455952333,603580.SH
|
||||
2024-03-21,1.545209963736103,603499.SH
|
||||
2024-03-22,0.6838446792203144,605180.SH
|
||||
2024-03-25,0.31578511420724414,603985.SH
|
||||
2024-03-26,1.781904626165001,605198.SH
|
||||
2024-03-27,-0.16938824239950148,603006.SH
|
||||
2024-03-28,0.9649663433118687,002739.SZ
|
||||
2024-03-29,0.3320943922901912,603499.SH
|
||||
2024-04-01,0.9952388185722638,603878.SH
|
||||
2024-04-02,0.9364155422135148,000603.SZ
|
||||
2024-04-03,0.7982619216871609,603878.SH
|
||||
2024-04-08,1.358471943036704,605198.SH
|
||||
2024-04-09,0.18053926667744466,002574.SZ
|
||||
2024-04-10,1.3153422390391303,000528.SZ
|
||||
2024-04-11,1.3657881440950266,002716.SZ
|
||||
2024-04-12,1.5676274828749224,000975.SZ
|
||||
2024-04-15,-0.13567914644119722,000157.SZ
|
||||
2024-04-16,0.93425932274213,600690.SH
|
||||
2024-04-17,1.327024106545604,001696.SZ
|
||||
2024-04-18,1.8296222086183656,600210.SH
|
||||
2024-04-19,0.578844593874061,002716.SZ
|
||||
2024-04-22,1.0676680912492613,603050.SH
|
||||
2024-04-23,1.5669359888338785,002167.SZ
|
||||
2024-04-24,0.7255550236691839,603017.SH
|
||||
2024-04-25,1.997033122105935,000737.SZ
|
||||
2024-04-26,1.1631716891035941,001696.SZ
|
||||
2024-04-29,0.5416930775042976,002715.SZ
|
||||
2024-04-30,0.4865144780512015,002167.SZ
|
||||
2024-05-06,1.6985755115133785,002125.SZ
|
||||
2024-05-07,1.5949401523876496,600789.SH
|
||||
2024-05-08,0.978355142201031,605177.SH
|
||||
2024-05-09,0.1605421067543249,603018.SH
|
||||
2024-05-10,0.6676316772066117,002264.SZ
|
||||
2024-05-13,0.733933392442504,603222.SH
|
||||
2024-05-14,0.5547173325807716,603025.SH
|
||||
2024-05-15,1.3155422143795996,000913.SZ
|
||||
2024-05-16,1.4221204991742524,001696.SZ
|
||||
2024-05-17,1.1562985723597323,600383.SH
|
||||
2024-05-20,0.4695922603130449,002264.SZ
|
||||
2024-05-21,1.8689264604736717,000002.SZ
|
||||
2024-05-22,1.3121218875647056,600843.SH
|
||||
2024-05-23,0.7664908704814034,002225.SZ
|
||||
2024-05-24,0.7589930057344444,600530.SH
|
||||
2024-05-27,1.19159766228358,601919.SH
|
||||
2024-05-28,1.0019105122452157,600726.SH
|
||||
2024-05-29,0.4881622770453212,601019.SH
|
||||
2024-05-30,1.4287668616222775,002938.SZ
|
||||
2024-05-31,1.0528834774374836,601019.SH
|
||||
2024-06-03,0.7762962067944593,603530.SH
|
||||
2024-06-04,1.7857240618535462,601117.SH
|
||||
2024-06-05,1.3040177518621878,603530.SH
|
||||
2024-06-06,1.0260169367235976,600900.SH
|
||||
2024-06-07,0.8588448524419576,603172.SH
|
||||
2024-06-11,1.1812779982242239,600584.SH
|
||||
2024-06-12,1.3882505145638304,003026.SZ
|
||||
2024-06-13,1.4302228321179788,001339.SZ
|
||||
2024-06-14,0.9306175962728962,002889.SZ
|
||||
2024-06-17,0.6869594774433183,600530.SH
|
||||
2024-06-18,1.1904711061862112,001298.SZ
|
||||
2024-06-19,1.697703035579816,605258.SH
|
||||
2024-06-20,0.8952978126779231,600733.SH
|
||||
2024-06-21,1.6755370442001838,001298.SZ
|
||||
2024-06-24,0.7658870375300119,002252.SZ
|
||||
2024-06-25,0.5860602429129975,002485.SZ
|
||||
2024-06-26,0.3448818899550934,003031.SZ
|
||||
2024-06-27,0.5265851943756428,000793.SZ
|
||||
2024-06-28,1.9979062957915383,603838.SH
|
||||
2024-07-01,1.0825164001234038,002485.SZ
|
||||
2024-07-02,0.9075039211419761,601985.SH
|
||||
2024-07-03,1.409183048681464,600025.SH
|
||||
2024-07-04,0.904029442040085,600025.SH
|
||||
2024-07-05,1.0426545217304006,001286.SZ
|
||||
2024-07-08,1.698642218338944,600584.SH
|
||||
2024-07-09,0.6470181687793882,002463.SZ
|
||||
2024-07-10,2.06122700428312,002947.SZ
|
||||
2024-07-11,0.7410903122804028,600601.SH
|
||||
2024-07-12,1.340083218079972,600686.SH
|
||||
2024-07-15,1.5618937384484992,600733.SH
|
||||
2024-07-16,1.758580945058497,600733.SH
|
||||
2024-07-17,1.5157121004090266,000625.SZ
|
||||
2024-07-18,0.3083377315759717,603898.SH
|
||||
2024-07-19,0.8944208661047769,000078.SZ
|
||||
2024-07-22,1.0429143541686636,002829.SZ
|
||||
2024-07-23,0.8234894660266799,002005.SZ
|
||||
2024-07-24,1.0749929990189133,600626.SH
|
||||
2024-07-25,1.880220214501819,600611.SH
|
||||
2024-07-26,1.8509059338376548,600650.SH
|
||||
2024-07-29,2.076506303850798,600817.SH
|
||||
2024-07-30,2.1084511316806602,000712.SZ
|
||||
2024-07-31,1.638115197432452,000421.SZ
|
||||
2024-08-01,1.040980502901104,600811.SH
|
||||
2024-08-02,1.7885572982299731,001696.SZ
|
||||
2024-08-05,0.9537751859233105,001379.SZ
|
||||
2024-08-06,0.3092017392193045,002461.SZ
|
||||
2024-08-07,1.466643911628964,002488.SZ
|
||||
2024-08-08,0.7882843739164674,603863.SH
|
||||
2024-08-09,0.23494689741035102,603488.SH
|
||||
2024-08-12,2.131668395298663,002488.SZ
|
||||
2024-08-13,2.0937880721661606,603978.SH
|
||||
2024-08-14,1.131943220068558,002232.SZ
|
||||
2024-08-15,0.5873737710201326,002611.SZ
|
||||
2024-08-16,1.199835048451392,000062.SZ
|
||||
2024-08-19,1.1805751411608383,600811.SH
|
||||
2024-08-20,1.5503271129180245,600661.SH
|
||||
2024-08-21,0.578554281440386,000880.SZ
|
||||
2024-08-22,1.2853820450612699,600105.SH
|
||||
2024-08-23,0.6423692277445572,002403.SZ
|
||||
2024-08-26,0.9239367963781929,002986.SZ
|
||||
2024-08-27,0.46409556994532736,605183.SH
|
||||
2024-08-28,1.0631407155165504,002647.SZ
|
||||
2024-08-29,1.1245501698512903,603639.SH
|
||||
2024-08-30,0.6361599235773499,002246.SZ
|
||||
2024-09-02,1.2492364629991852,002072.SZ
|
||||
2024-09-03,1.1926755374832714,002199.SZ
|
||||
2024-09-04,1.6204729565651932,600599.SH
|
||||
2024-09-05,1.0957778793973632,002595.SZ
|
||||
2024-09-06,1.6168023970816094,002005.SZ
|
||||
2024-09-09,0.8605482386029011,002456.SZ
|
||||
2024-09-10,1.3546410789459808,002717.SZ
|
||||
2024-09-11,0.5980254226205031,603196.SH
|
||||
2024-09-12,0.9187303745519808,002640.SZ
|
||||
2024-09-13,0.6801121207893971,600358.SH
|
||||
2024-09-18,1.079264299860147,600550.SH
|
||||
2024-09-19,1.9477947178464494,002786.SZ
|
||||
2024-09-20,1.1194340099294373,002123.SZ
|
||||
2024-09-23,1.6714675557693415,002453.SZ
|
||||
2024-09-24,1.3675826070587052,002453.SZ
|
||||
2024-09-25,0.7076301816428471,000627.SZ
|
||||
2024-09-26,0.8882412710980511,603398.SH
|
||||
2024-09-27,0.7521975260737696,000002.SZ
|
||||
2024-09-30,0.7230331038260748,600570.SH
|
||||
2024-10-08,1.0593517928482987,600550.SH
|
||||
2024-10-09,1.0220239311477122,000560.SZ
|
||||
2024-10-10,1.234368197028218,600606.SH
|
||||
2024-10-11,0.8664109594444052,000750.SZ
|
||||
2024-10-14,1.8450296800922745,603822.SH
|
||||
2024-10-15,1.8353472785641625,002583.SZ
|
||||
2024-10-16,0.9543901161454763,000536.SZ
|
||||
2024-10-17,1.0015738096430133,600619.SH
|
||||
2024-10-18,1.2591757462030437,600622.SH
|
||||
2024-10-21,1.364327760137209,002583.SZ
|
||||
2024-10-22,2.0756244365506276,002685.SZ
|
||||
2024-10-23,0.38458758527962894,000004.SZ
|
||||
2024-10-24,1.5124132416681377,002094.SZ
|
||||
2024-10-25,1.4347033681199353,600839.SH
|
||||
2024-10-28,1.5745059258009038,001696.SZ
|
||||
2024-10-29,1.8529251428567266,002628.SZ
|
||||
2024-10-30,1.7713369405635928,002717.SZ
|
||||
2024-10-31,1.1151492405672683,001696.SZ
|
||||
2024-11-01,0.7164870376829126,600246.SH
|
||||
2024-11-04,1.769839917258226,002384.SZ
|
||||
2024-11-05,1.092728971983151,600212.SH
|
||||
2024-11-06,0.6671879019120053,603336.SH
|
||||
2024-11-07,0.5602821558966659,002416.SZ
|
||||
2024-11-08,1.1858491806130256,001696.SZ
|
||||
2024-11-11,1.3270787455846025,002456.SZ
|
||||
2024-11-12,1.4104327679900899,603398.SH
|
||||
2024-11-13,1.2197272384042277,600839.SH
|
||||
2024-11-14,0.6314176029145626,603697.SH
|
||||
2024-11-15,-0.13737144527610326,603268.SH
|
||||
2024-11-18,0.7120357386859574,000605.SZ
|
||||
2024-11-19,0.42252100937945863,002469.SZ
|
||||
2024-11-20,1.007664521961136,600619.SH
|
||||
2024-11-21,0.9709988043471746,002694.SZ
|
||||
2024-11-22,-0.01837433439991007,000415.SZ
|
||||
2024-11-25,0.7354373323734968,000973.SZ
|
||||
2024-11-26,1.4832316580516,002348.SZ
|
||||
2024-11-27,1.0092630330488712,002899.SZ
|
||||
2024-11-28,1.6528548440755675,600327.SH
|
||||
2024-11-29,1.5310967942763765,003010.SZ
|
||||
2024-12-02,0.9985829805322318,000981.SZ
|
||||
2024-12-03,1.1009990341574898,600628.SH
|
||||
2024-12-04,1.4406720428536548,000679.SZ
|
||||
2024-12-05,1.5166810165916147,002640.SZ
|
||||
2024-12-06,1.5480151614841313,003021.SZ
|
||||
2024-12-09,0.7658546815142482,600593.SH
|
||||
2024-12-10,1.6164052159572586,000981.SZ
|
||||
2024-12-11,1.0871733525157767,000882.SZ
|
||||
2024-12-12,1.3618111397645727,002265.SZ
|
||||
2024-12-13,1.1378238320491278,605006.SH
|
||||
2024-12-16,0.5942319336561258,603533.SH
|
||||
2024-12-17,0.8922367248452927,600503.SH
|
||||
2024-12-18,0.29961260322010785,600796.SH
|
||||
2024-12-19,0.5126832965650956,002031.SZ
|
||||
2024-12-20,0.4049032161823233,600172.SH
|
||||
2024-12-23,0.378293448285725,600172.SH
|
||||
2024-12-24,0.7270156370860105,600673.SH
|
||||
2024-12-25,0.8938311286037234,603610.SH
|
||||
2024-12-26,0.8824820051198142,603893.SH
|
||||
2024-12-27,1.3362649834557183,002068.SZ
|
||||
2024-12-30,0.35138947858631225,600183.SH
|
||||
2024-12-31,1.1948708599448123,600506.SH
|
||||
2025-01-02,1.4558889081434663,002730.SZ
|
||||
2025-01-03,0.7128978848132725,600707.SH
|
||||
2025-01-06,0.7650844601290192,600803.SH
|
||||
2025-01-07,1.0635380792047187,600405.SH
|
||||
2025-01-08,0.7951289392847068,002837.SZ
|
||||
2025-01-09,1.0252099583039425,603306.SH
|
||||
2025-01-10,0.30155175957668673,002916.SZ
|
||||
2025-01-13,0.9708056750766493,603986.SH
|
||||
2025-01-14,0.7870312186305877,000063.SZ
|
||||
2025-01-15,1.6878038525240218,002917.SZ
|
||||
2025-01-16,0.8478674953917144,002449.SZ
|
||||
2025-01-17,1.0235316084839805,600693.SH
|
||||
2025-01-20,0.8827244215589688,002730.SZ
|
||||
2025-01-21,0.9142145000698546,002379.SZ
|
||||
2025-01-22,1.632439883586815,603228.SH
|
||||
2025-01-23,0.5950475737248152,603121.SH
|
||||
2025-01-24,1.512800316493977,000880.SZ
|
||||
2025-01-27,0.280247948525134,002532.SZ
|
||||
2025-02-05,0.7525772298409897,600722.SH
|
||||
2025-02-06,-0.059951823103750426,601869.SH
|
||||
2025-02-07,0.45215019046862537,000977.SZ
|
||||
2025-02-10,1.2658737579405763,003007.SZ
|
||||
2025-02-11,1.0408324160127955,603106.SH
|
||||
2025-02-12,1.6119030499830551,000856.SZ
|
||||
2025-02-13,1.59310517514652,002929.SZ
|
||||
2025-02-14,1.5077797651403821,002410.SZ
|
||||
2025-02-17,1.3860825096123015,002044.SZ
|
||||
2025-02-18,1.1270921559091267,002779.SZ
|
||||
2025-02-19,1.187211682113541,603286.SH
|
||||
2025-02-20,1.2669618354736996,605488.SH
|
||||
2025-02-21,1.025703816755235,600588.SH
|
||||
2025-02-24,1.5648046166656084,600602.SH
|
||||
2025-02-25,0.8745657353291226,002896.SZ
|
||||
2025-02-26,0.9230669528117501,000032.SZ
|
||||
2025-02-27,0.9367812438709472,603200.SH
|
||||
2025-02-28,1.0306691811926367,002276.SZ
|
||||
2025-03-03,0.6479828536311146,002044.SZ
|
||||
2025-03-04,0.9022328614595625,001306.SZ
|
||||
2025-03-05,0.13297506000529996,002036.SZ
|
||||
2025-03-06,1.0473094549911606,001309.SZ
|
||||
2025-03-07,0.8908293616489041,002580.SZ
|
||||
2025-03-10,0.9714032058498194,600126.SH
|
||||
2025-03-11,1.5066583997940508,000678.SZ
|
||||
2025-03-12,1.2822828774552384,603059.SH
|
||||
2025-03-13,1.1088751386616387,003038.SZ
|
||||
2025-03-14,1.2806594439606795,002713.SZ
|
||||
2025-03-17,0.9239379376977839,001256.SZ
|
||||
2025-03-18,1.155518645532713,600610.SH
|
||||
2025-03-19,1.566452580640379,605008.SH
|
||||
2025-03-20,1.6658038834776503,603949.SH
|
||||
2025-03-21,0.3002046262826852,603112.SH
|
||||
2025-03-24,0.969025415982965,001256.SZ
|
||||
2025-03-25,1.0089862742297053,002300.SZ
|
||||
2025-03-26,0.9563316876479583,600468.SH
|
||||
2025-03-27,0.7596417124134163,000633.SZ
|
||||
2025-03-28,0.8823950983342874,000006.SZ
|
||||
2025-03-31,1.5478113985550597,002851.SZ
|
||||
2025-04-01,0.5961759062409911,002847.SZ
|
||||
2025-04-02,0.1297394192678443,002093.SZ
|
||||
2025-04-03,1.6113567681708816,603353.SH
|
||||
2025-04-07,1.6243924524047828,601008.SH
|
||||
2025-04-08,1.5465757662622548,600598.SH
|
||||
2025-04-09,1.2262057864670963,601952.SH
|
||||
|
72
main/train/test2.tsv
Normal file
72
main/train/test2.tsv
Normal file
@@ -0,0 +1,72 @@
|
||||
trade_date,score,ts_code
|
||||
2024-12-09,1.1968650846005326,600593.SH
|
||||
2024-12-10,0.21490252296809745,002611.SZ
|
||||
2024-12-11,0.5721914798956016,002321.SZ
|
||||
2024-12-12,0.6509338263544048,600628.SH
|
||||
2024-12-13,2.1288113028385376,600628.SH
|
||||
2024-12-16,1.378346480524284,002086.SZ
|
||||
2024-12-17,1.45986967550941,002741.SZ
|
||||
2024-12-18,1.3436778254529067,600579.SH
|
||||
2024-12-19,0.41218776805787716,600796.SH
|
||||
2024-12-20,1.0840917563770454,603421.SH
|
||||
2024-12-23,1.00141172278312,600889.SH
|
||||
2024-12-24,1.0354156548919864,600725.SH
|
||||
2024-12-25,0.9562524807100355,600066.SH
|
||||
2024-12-26,1.1279048294352958,002916.SZ
|
||||
2024-12-27,0.6532174116474766,002068.SZ
|
||||
2024-12-30,-0.1308794790538431,002918.SZ
|
||||
2024-12-31,0.7160474599127873,600857.SH
|
||||
2025-01-02,1.5067649520721882,002449.SZ
|
||||
2025-01-03,0.9282246137432282,603379.SH
|
||||
2025-01-06,0.6797051204009213,603893.SH
|
||||
2025-01-07,0.9376184079476354,603236.SH
|
||||
2025-01-08,0.9064516934700023,603308.SH
|
||||
2025-01-09,0.9314493554789942,000880.SZ
|
||||
2025-01-10,0.5025761501709369,600584.SH
|
||||
2025-01-13,0.7483210862212708,000063.SZ
|
||||
2025-01-14,1.2632673941368837,000063.SZ
|
||||
2025-01-15,1.8580661802761587,002917.SZ
|
||||
2025-01-16,1.1918089652002073,600693.SH
|
||||
2025-01-17,0.8288939941365315,600693.SH
|
||||
2025-01-20,0.677726091977902,002577.SZ
|
||||
2025-01-21,1.8336548268410158,603893.SH
|
||||
2025-01-22,1.0395051538956546,000573.SZ
|
||||
2025-01-23,0.4308220427423068,003021.SZ
|
||||
2025-01-24,1.8057941775723685,002862.SZ
|
||||
2025-01-27,1.216662909774701,002779.SZ
|
||||
2025-02-05,0.8484867753831473,603990.SH
|
||||
2025-02-06,0.5038824073142949,001380.SZ
|
||||
2025-02-07,0.7672133571524726,002031.SZ
|
||||
2025-02-10,0.5417223016033719,000681.SZ
|
||||
2025-02-11,0.9399374716518157,000034.SZ
|
||||
2025-02-12,1.8742056631297925,000856.SZ
|
||||
2025-02-13,1.4837670146272484,600633.SH
|
||||
2025-02-14,1.2043600916692372,605488.SH
|
||||
2025-02-17,1.1259104542173328,603918.SH
|
||||
2025-02-18,1.1806931791732853,600126.SH
|
||||
2025-02-19,1.020437698817749,603956.SH
|
||||
2025-02-20,0.5818349669113919,003021.SZ
|
||||
2025-02-21,1.0941497070930342,603950.SH
|
||||
2025-02-24,1.867258980329339,600602.SH
|
||||
2025-02-25,0.8646726218943293,002691.SZ
|
||||
2025-02-26,1.2878484406363957,002245.SZ
|
||||
2025-02-27,1.3013902577988068,600173.SH
|
||||
2025-02-28,0.7804376426721501,603040.SH
|
||||
2025-03-03,0.45593268249434266,002345.SZ
|
||||
2025-03-04,0.9265705061587579,600589.SH
|
||||
2025-03-05,0.766962270753268,002575.SZ
|
||||
2025-03-06,0.7030260458187082,601100.SH
|
||||
2025-03-07,0.924011193171594,002896.SZ
|
||||
2025-03-10,1.0811487252993004,600126.SH
|
||||
2025-03-11,1.272392599656189,002896.SZ
|
||||
2025-03-12,1.0905437448562905,002276.SZ
|
||||
2025-03-13,1.0688995313878895,003038.SZ
|
||||
2025-03-14,1.2418913857438587,001256.SZ
|
||||
2025-03-17,1.004550155323,001256.SZ
|
||||
2025-03-18,0.7517848278576412,600403.SH
|
||||
2025-03-19,1.5106246878723002,605008.SH
|
||||
2025-03-20,1.1509811695536982,600610.SH
|
||||
2025-03-21,0.6033998331536018,603196.SH
|
||||
2025-03-24,0.3456173948047773,002345.SZ
|
||||
2025-03-25,1.470314131581159,600320.SH
|
||||
2025-03-26,0.745243100558546,603325.SH
|
||||
|
0
main/utils/__init__.py
Normal file
0
main/utils/__init__.py
Normal file
BIN
main/utils/__pycache__/__init__.cpython-310.pyc
Normal file
BIN
main/utils/__pycache__/__init__.cpython-310.pyc
Normal file
Binary file not shown.
BIN
main/utils/__pycache__/__init__.cpython-311.pyc
Normal file
BIN
main/utils/__pycache__/__init__.cpython-311.pyc
Normal file
Binary file not shown.
BIN
main/utils/__pycache__/factor.cpython-311.pyc
Normal file
BIN
main/utils/__pycache__/factor.cpython-311.pyc
Normal file
Binary file not shown.
BIN
main/utils/__pycache__/factor_processor.cpython-311.pyc
Normal file
BIN
main/utils/__pycache__/factor_processor.cpython-311.pyc
Normal file
Binary file not shown.
BIN
main/utils/__pycache__/utils.cpython-310.pyc
Normal file
BIN
main/utils/__pycache__/utils.cpython-310.pyc
Normal file
Binary file not shown.
BIN
main/utils/__pycache__/utils.cpython-311.pyc
Normal file
BIN
main/utils/__pycache__/utils.cpython-311.pyc
Normal file
Binary file not shown.
@@ -2,6 +2,7 @@ import numpy as np
|
||||
import talib
|
||||
import pandas as pd
|
||||
|
||||
|
||||
def get_technical_factor(df):
|
||||
# 按股票和日期排序
|
||||
df = df.sort_values(by=['ts_code', 'trade_date'])
|
||||
@@ -735,4 +736,45 @@ def generate_index_indicators(h5_filename):
|
||||
df_final.columns = [f"{col[1]}_{col[0]}" for col in df_final.columns]
|
||||
df_final = df_final.reset_index()
|
||||
|
||||
return df_final
|
||||
return df_final
|
||||
|
||||
|
||||
def read_industry_data(h5_filename):
|
||||
# 读取 H5 文件中所有的行业数据
|
||||
industry_data = pd.read_hdf(h5_filename, key='sw_daily', columns=[
|
||||
'ts_code', 'trade_date', 'open', 'close', 'high', 'low', 'pe', 'pb', 'vol'
|
||||
]) # 假设 H5 文件的键是 'industry_data'
|
||||
industry_data = industry_data.sort_values(by=['ts_code', 'trade_date'])
|
||||
industry_data = industry_data.reindex()
|
||||
industry_data['trade_date'] = pd.to_datetime(industry_data['trade_date'], format='%Y%m%d')
|
||||
|
||||
grouped = industry_data.groupby('ts_code', group_keys=False)
|
||||
industry_data['obv'] = grouped.apply(
|
||||
lambda x: pd.Series(talib.OBV(x['close'].values, x['vol'].values), index=x.index)
|
||||
)
|
||||
industry_data['return_5'] = grouped['close'].apply(lambda x: x / x.shift(5) - 1)
|
||||
industry_data['return_20'] = grouped['close'].apply(lambda x: x / x.shift(20) - 1)
|
||||
|
||||
industry_data = get_act_factor(industry_data, cat=False)
|
||||
industry_data = industry_data.sort_values(by=['trade_date', 'ts_code'])
|
||||
|
||||
# # 计算每天每个 ts_code 的因子和当天所有 ts_code 的中位数的偏差
|
||||
# factor_columns = ['obv', 'return_5', 'return_20', 'act_factor1', 'act_factor2', 'act_factor3', 'act_factor4'] # 因子列
|
||||
#
|
||||
# for factor in factor_columns:
|
||||
# if factor in industry_data.columns:
|
||||
# # 计算每天每个 ts_code 的因子值与当天所有 ts_code 的中位数的偏差
|
||||
# industry_data[f'{factor}_deviation'] = industry_data.groupby('trade_date')[factor].transform(
|
||||
# lambda x: x - x.mean())
|
||||
|
||||
industry_data['return_5_percentile'] = industry_data.groupby('trade_date')['return_5'].transform(
|
||||
lambda x: x.rank(pct=True))
|
||||
industry_data['return_20_percentile'] = industry_data.groupby('trade_date')['return_20'].transform(
|
||||
lambda x: x.rank(pct=True))
|
||||
industry_data = industry_data.drop(columns=['open', 'close', 'high', 'low', 'pe', 'pb', 'vol'])
|
||||
|
||||
industry_data = industry_data.rename(
|
||||
columns={col: f'industry_{col}' for col in industry_data.columns if col not in ['ts_code', 'trade_date']})
|
||||
|
||||
industry_data = industry_data.rename(columns={'ts_code': 'cat_l2_code'})
|
||||
return industry_data
|
||||
233
main/utils/factor_processor.py
Normal file
233
main/utils/factor_processor.py
Normal file
@@ -0,0 +1,233 @@
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
|
||||
from scipy.stats import ks_2samp
|
||||
from sklearn.preprocessing import StandardScaler
|
||||
|
||||
|
||||
def remove_shifted_features(train_data, feature_columns, ks_threshold=0.05, wasserstein_threshold=0.1, size=0.8,
|
||||
log=True, val_data=None):
|
||||
dropped_features = []
|
||||
|
||||
if val_data is None:
|
||||
all_dates = sorted(train_data['trade_date'].unique().tolist()) # 获取所有唯一的 trade_date
|
||||
split_date = all_dates[int(len(all_dates) * size)] # 划分点为倒数第 validation_days 天
|
||||
train_data_split = train_data[train_data['trade_date'] < split_date] # 训练集
|
||||
val_data_split = train_data[train_data['trade_date'] >= split_date] # 验证集
|
||||
else:
|
||||
train_data_split = train_data
|
||||
val_data_split = val_data
|
||||
|
||||
# **统计数据漂移**
|
||||
numeric_columns = train_data_split.select_dtypes(include=['float64', 'int64']).columns
|
||||
numeric_columns = [col for col in numeric_columns if col in feature_columns]
|
||||
for feature in numeric_columns:
|
||||
ks_stat, p_value = ks_2samp(train_data_split[feature], val_data_split[feature])
|
||||
# wasserstein_dist = wasserstein_distance(train_data_split[feature], val_data_split[feature])
|
||||
|
||||
# if p_value < ks_threshold or wasserstein_dist > wasserstein_threshold:
|
||||
if p_value < ks_threshold:
|
||||
dropped_features.append(feature)
|
||||
if log:
|
||||
print(f"检测到 {len(dropped_features)} 个可能漂移的特征: {dropped_features}")
|
||||
|
||||
# **应用阈值进行最终筛选**
|
||||
filtered_features = [f for f in feature_columns if f not in dropped_features]
|
||||
|
||||
return filtered_features, dropped_features
|
||||
|
||||
|
||||
def remove_outliers_label_percentile(label: pd.Series, lower_percentile: float = 0.01, upper_percentile: float = 0.99,
|
||||
log=True):
|
||||
if not (0 <= lower_percentile < upper_percentile <= 1):
|
||||
raise ValueError("Percentile values must satisfy 0 <= lower_percentile < upper_percentile <= 1.")
|
||||
|
||||
# Calculate lower and upper bounds based on percentiles
|
||||
lower_bound = label.quantile(lower_percentile)
|
||||
upper_bound = label.quantile(upper_percentile)
|
||||
|
||||
# Filter out values outside the bounds
|
||||
filtered_label = label[(label >= lower_bound) & (label <= upper_bound)]
|
||||
|
||||
# Print the number of removed outliers
|
||||
if log:
|
||||
print(f"Removed {len(label) - len(filtered_label)} outliers.")
|
||||
return filtered_label
|
||||
|
||||
|
||||
def calculate_risk_adjusted_target(df, days=5):
|
||||
df = df.sort_values(by=['ts_code', 'trade_date'])
|
||||
|
||||
df['future_close'] = df.groupby('ts_code')['close'].shift(-days)
|
||||
df['future_open'] = df.groupby('ts_code')['open'].shift(-1)
|
||||
df['future_return'] = (df['future_close'] - df['future_open']) / df['future_open']
|
||||
|
||||
df['future_volatility'] = df.groupby('ts_code')['future_return'].rolling(days, min_periods=1).std().reset_index(
|
||||
level=0, drop=True)
|
||||
sharpe_ratio = df['future_return'] * df['future_volatility']
|
||||
sharpe_ratio.replace([np.inf, -np.inf], np.nan, inplace=True)
|
||||
|
||||
return sharpe_ratio
|
||||
|
||||
|
||||
def calculate_score(df, days=5, lambda_param=1.0):
|
||||
def calculate_max_drawdown(prices):
|
||||
peak = prices.iloc[0] # 初始化峰值
|
||||
max_drawdown = 0 # 初始化最大回撤
|
||||
|
||||
for price in prices:
|
||||
if price > peak:
|
||||
peak = price # 更新峰值
|
||||
else:
|
||||
drawdown = (peak - price) / peak # 计算当前回撤
|
||||
max_drawdown = max(max_drawdown, drawdown) # 更新最大回撤
|
||||
|
||||
return max_drawdown
|
||||
|
||||
def compute_stock_score(stock_df):
|
||||
stock_df = stock_df.sort_values(by=['trade_date'])
|
||||
future_return = stock_df['future_return']
|
||||
# 使用已有的 pct_chg 字段计算波动率
|
||||
volatility = stock_df['pct_chg'].rolling(days).std().shift(-days)
|
||||
max_drawdown = stock_df['close'].rolling(days).apply(calculate_max_drawdown, raw=False).shift(-days)
|
||||
score = future_return - lambda_param * max_drawdown
|
||||
return score
|
||||
|
||||
# # 确保 DataFrame 按照股票代码和交易日期排序
|
||||
# df = df.sort_values(by=['ts_code', 'trade_date'])
|
||||
|
||||
# 对每个股票分别计算 score
|
||||
df['score'] = df.groupby('ts_code').apply(compute_stock_score).reset_index(level=0, drop=True)
|
||||
|
||||
return df['score']
|
||||
|
||||
|
||||
def remove_highly_correlated_features(df, feature_columns, threshold=0.9):
|
||||
numeric_features = df[feature_columns].select_dtypes(include=[np.number]).columns.tolist()
|
||||
if not numeric_features:
|
||||
raise ValueError("No numeric features found in the provided data.")
|
||||
|
||||
corr_matrix = df[numeric_features].corr().abs()
|
||||
upper = corr_matrix.where(np.triu(np.ones(corr_matrix.shape), k=1).astype(bool))
|
||||
to_drop = [column for column in upper.columns if any(upper[column] > threshold)]
|
||||
remaining_features = [col for col in feature_columns if col not in to_drop
|
||||
or 'act' in col or 'af' in col]
|
||||
return remaining_features
|
||||
|
||||
|
||||
def cross_sectional_standardization(df, features):
|
||||
df_sorted = df.sort_values(by='trade_date') # 按时间排序
|
||||
df_standardized = df_sorted.copy()
|
||||
|
||||
for date in df_sorted['trade_date'].unique():
|
||||
# 获取当前时间点的数据
|
||||
current_data = df_standardized[df_standardized['trade_date'] == date]
|
||||
|
||||
# 只对指定特征进行标准化
|
||||
scaler = StandardScaler()
|
||||
standardized_values = scaler.fit_transform(current_data[features])
|
||||
|
||||
# 将标准化结果重新赋值回去
|
||||
df_standardized.loc[df_standardized['trade_date'] == date, features] = standardized_values
|
||||
|
||||
return df_standardized
|
||||
|
||||
|
||||
def neutralize_manual(df, features, industry_col, mkt_cap_col):
|
||||
""" 手动实现简单回归以提升速度 """
|
||||
|
||||
for col in features:
|
||||
residuals = []
|
||||
for _, group in df.groupby(industry_col):
|
||||
if len(group) > 1:
|
||||
x = np.log(group[mkt_cap_col]) # 市值对数
|
||||
y = group[col] # 因子值
|
||||
beta = np.cov(y, x)[0, 1] / np.var(x) # 计算斜率
|
||||
alpha = np.mean(y) - beta * np.mean(x) # 计算截距
|
||||
resid = y - (alpha + beta * x) # 计算残差
|
||||
residuals.extend(resid)
|
||||
else:
|
||||
residuals.extend(group[col]) # 样本不足时保留原值
|
||||
|
||||
df[col] = residuals
|
||||
|
||||
return df
|
||||
|
||||
|
||||
def mad_filter(df, features, n=3):
|
||||
for col in features:
|
||||
median = df[col].median()
|
||||
mad = np.median(np.abs(df[col] - median))
|
||||
upper = median + n * mad
|
||||
lower = median - n * mad
|
||||
df[col] = np.clip(df[col], lower, upper) # 截断极值
|
||||
return df
|
||||
|
||||
|
||||
def percentile_filter(df, features, lower_percentile=0.01, upper_percentile=0.99):
|
||||
for col in features:
|
||||
# 按日期分组计算上下百分位数
|
||||
lower_bound = df.groupby('trade_date')[col].transform(
|
||||
lambda x: x.quantile(lower_percentile)
|
||||
)
|
||||
upper_bound = df.groupby('trade_date')[col].transform(
|
||||
lambda x: x.quantile(upper_percentile)
|
||||
)
|
||||
# 截断超出范围的值
|
||||
df[col] = np.clip(df[col], lower_bound, upper_bound)
|
||||
return df
|
||||
|
||||
|
||||
from scipy.stats import iqr
|
||||
|
||||
|
||||
def iqr_filter(df, features):
|
||||
for col in features:
|
||||
df[col] = df.groupby('trade_date')[col].transform(
|
||||
lambda x: (x - x.median()) / iqr(x) if iqr(x) != 0 else x
|
||||
)
|
||||
return df
|
||||
|
||||
|
||||
def quantile_filter(df, features, lower_quantile=0.01, upper_quantile=0.99, window=60):
|
||||
df = df.copy()
|
||||
for col in features:
|
||||
# 计算 rolling 统计量，需要按日期进行 groupby
|
||||
rolling_lower = df.groupby('trade_date')[col].transform(
|
||||
lambda x: x.rolling(window=min(len(x), window)).quantile(lower_quantile))
|
||||
rolling_upper = df.groupby('trade_date')[col].transform(
|
||||
lambda x: x.rolling(window=min(len(x), window)).quantile(upper_quantile))
|
||||
|
||||
# 对数据进行裁剪
|
||||
df[col] = np.clip(df[col], rolling_lower, rolling_upper)
|
||||
|
||||
return df
|
||||
|
||||
|
||||
def time_series_quantile_filter(df, features, lower_quantile=0.01, upper_quantile=0.99, window=60):
|
||||
df = df.copy()
|
||||
# 确保按股票和时间排序
|
||||
df = df.sort_values(['ts_code', 'trade_date'])
|
||||
grouped = df.groupby('ts_code')
|
||||
for col in features:
|
||||
# 对每个股票的时间序列计算滚动分位数
|
||||
rolling_lower = grouped[col].rolling(window=window, min_periods=window // 2).quantile(lower_quantile)
|
||||
rolling_upper = grouped[col].rolling(window=window, min_periods=window // 2).quantile(upper_quantile)
|
||||
# rolling结果带有多重索引，需要对齐
|
||||
rolling_lower = rolling_lower.reset_index(level=0, drop=True)
|
||||
rolling_upper = rolling_upper.reset_index(level=0, drop=True)
|
||||
# 应用 clip
|
||||
df[col] = np.clip(df[col], rolling_lower, rolling_upper)
|
||||
return df
|
||||
|
||||
|
||||
def cross_sectional_quantile_filter(df, features, lower_quantile=0.01, upper_quantile=0.99):
|
||||
df = df.copy()
|
||||
grouped = df.groupby('trade_date')
|
||||
for col in features:
|
||||
# 计算每日截面的分位数边界
|
||||
lower_bound = grouped[col].transform(lambda x: x.quantile(lower_quantile))
|
||||
upper_bound = grouped[col].transform(lambda x: x.quantile(upper_quantile))
|
||||
# 应用 clip
|
||||
df[col] = np.clip(df[col], lower_bound, upper_bound)
|
||||
return df
|
||||
@@ -42,6 +42,43 @@ def read_and_merge_h5_data(h5_filename, key, columns, df=None, join='left', on=[
|
||||
return merged_df
|
||||
|
||||
|
||||
def merge_with_industry_data(df, industry_df):
|
||||
# 确保日期字段是 datetime 类型
|
||||
df['trade_date'] = pd.to_datetime(df['trade_date'])
|
||||
industry_df['in_date'] = pd.to_datetime(industry_df['in_date'])
|
||||
|
||||
# 对 industry_df 按 ts_code 和 in_date 排序
|
||||
industry_df_sorted = industry_df.sort_values(['in_date', 'ts_code'])
|
||||
|
||||
# 对原始 df 按 ts_code 和 trade_date 排序
|
||||
df_sorted = df.sort_values(['trade_date', 'ts_code'])
|
||||
|
||||
# 使用 merge_asof 进行向后合并
|
||||
merged = pd.merge_asof(
|
||||
df_sorted,
|
||||
industry_df_sorted,
|
||||
by='ts_code', # 按 ts_code 分组
|
||||
left_on='trade_date',
|
||||
right_on='in_date',
|
||||
direction='backward'
|
||||
)
|
||||
|
||||
# 获取每个 ts_code 的最早 in_date 记录
|
||||
min_in_date_per_ts = (industry_df_sorted
|
||||
.groupby('ts_code')
|
||||
.first()
|
||||
.reset_index()[['ts_code', 'l2_code']])
|
||||
|
||||
# 填充未匹配到的记录（trade_date 早于所有 in_date 的情况）
|
||||
merged['l2_code'] = merged['l2_code'].fillna(
|
||||
merged['ts_code'].map(min_in_date_per_ts.set_index('ts_code')['l2_code'])
|
||||
)
|
||||
|
||||
# 保留需要的列并重置索引
|
||||
result = merged.reset_index(drop=True)
|
||||
return result
|
||||
|
||||
|
||||
def calculate_risk_adjusted_return(df, days=1, method='ratio', lambda_=0.5, eps=1e-8):
|
||||
"""
|
||||
计算单只股票的风险调整收益。
|
||||
@@ -81,7 +118,6 @@ def calculate_risk_adjusted_return(df, days=1, method='ratio', lambda_=0.5, eps=
|
||||
|
||||
return df
|
||||
|
||||
|
||||
# import polars as pl
|
||||
#
|
||||
# def read_and_merge_h5_data_polars(h5_filename, key, columns, df=None, join='left', on=['ts_code', 'trade_date']):
|
||||
@@ -116,5 +152,3 @@ def calculate_risk_adjusted_return(df, days=1, method='ratio', lambda_=0.5, eps=
|
||||
# merged_df = data
|
||||
#
|
||||
# return merged_df
|
||||
|
||||
|
||||
Reference in New Issue
Block a user