天池大数据竞赛：降雨预测.zip

featureUpdate6:四层数据，时序波动特征，中心20*20个点特征 max_depth = 3 n_estimators=100 test pred:12.623681681623 train pred:11.573620871432695 n_estimators=150 test pred:12.317659830997428 train pred:10.720445544796865 n_estimators=180 test pred:12.208551919586299 train pred:10.286177731502873 n_estimators=200 test pred:12.145938939596897 train pred:9.990710964429967 n_estimators=300 test pred:11.956212055111502 train pred:8.877026045679548 # featureUpdate6 learning_rate=0.2 n_estimators=100 test pred:12.403705478463547 train pred:9.964415337003672 n_estimators=150 test pred:12.211558197477899 train pred:8.820394682794719 n_estimators=180 test pred:12.134433143248971 train pred:8.272877542770784 n_estimators=200 test pred:12.099284451670718 train pred:7.955848401303026 n_estimators=300 test pred:11.868172598526131 train pred:6.596863362624191 # featureUpdate2 learning_rate=0.2 n_estimators=100 test pred:12.70641711939246 train pred:10.431358393102265 n_estimators=150 test pred:12.459133188146383 train pred:9.097374177122942 n_estimators=180 test pred:12.371916719027164 train pred:8.465162521131331 n_estimators=200 test pred:12.318136914944857 train pred:8.090355076936463 n_estimators=300 test pred:12.183165433923184 train pred:6.503274517322605 # random forest 20 test pred:12.104646685260995 train pred:4.690074445038159 #featureUpdate7 n_estimators=100 test pred:12.511569266405072 train pred:11.468932697550247 #featureUpdate8 n_estimators=100 test pred:12.598992289426565 train pred:11.52581011319261 n_estimators=150 test pred:12.372631817875744 train pred:10.73342254237062 n_estimators=180 test pred:12.245633177402098 train pred:10.295530853961504 n_estimators=200 test pred:12.203993002151494 train pred:10.01964103101855 n_estimators=300 test pred:11.955014968315712 train pred:8.896421731556167 11.0121736589 # feature_update_train7 max = 2 n_estimators=85 learning_rate=0.1 test pred:13.145149877814049 train pred:13.043230214878472 n_estimators=90 learning_rate=0.1 test pred:13.11939406310709 train pred:12.9966327341424 n_estimators=100 learning_rate=0.1 test pred:13.065093535271114 train pred:12.894628182113141 n_estimators=120 learning_rate=0.1 test pred:12.996149018972739 train pred:12.63867189456957 #featureUpdate9 max =2 n_estimators=90 learning_rate=0.1 test pred:13.113375581148345 train pred:12.997301441807453 n_estimators=100 learning_rate=0.1 test pred:13.063530048223345 train pred:12.906313042863461 n_estimators=120 learning_rate=0.1 test pred:12.998649518223969 train pred:12.655903549975468 # feature_update_train7 max = 2 80 learning_rate=0.1 test pred:13.154279394817765 train pred:13.163041065271548 # feature_update_train9 max = 2 n_estimators=60 learning_rate=0.1 test pred:13.284394579922454 train pred:13.450612394192735 n_estimators=50 learning_rate=0.1 test pred:13.351583503255181 train pred:13.6749400911764 n_estimators=40 learning_rate=0.1 test pred:13.495396256673521 train pred:13.9056013769743 # feature_update_train9 max = 3 n_estimators=40 learning_rate=0.1 test pred:13.00302623825569 train pred:12.948496769442505 n_estimators=36 learning_rate=0.1 test pred:13.052810680081569 train pred:13.067498235937808 n_estimators=30 learning_rate=0.1 test pred:13.159532377700373 train pred:13.296807942161482 n_estimators=20 learning_rate=0.1 test pred:13.4241057072059 train pred:13.844570380205843 n_estimators=10 learning_rate=0.1 test pred:13.930656800771468 train pred:14.58340923946873 #featureUpdate10_2 n_estimators=50 test pred:13.381558185397957 train pred:13.637190443866292 n_estimators=60 test pred:13.268645827169548 train pred:13.408712900830752 n_estimators=70 test pred:13.17660440527657 train pred:13.256819740521971 n_estimators=80 test pred:13.095511516784121 train pred:13.09926500685547 n_estimators=100 test pred:12.962584924444837 train pred:12.848624720657144 #featureUpdate10_3 n_estimators=50 max_depth=2 test pred:13.28625313790449 score 13.6 train pred:13.625511265589333 n_estimators=60 max_depth=2 test pred:13.165629560197472 train pred:13.396882279747524 n_estimators=70 max_depth=2 test pred:13.064558161833299 train pred:13.241448676505621 n_estimators=80 max_depth=2 test pred:13.00309265025689 train pred:13.071901631692475 n_estimators=90 max_depth=2 test pred:12.955022540783034 train pred:12.944752629141579 n_estimators=100 max_depth=2 test pred:12.902901751730457 train pred:12.845060491232283 #featureUpdate10_4 n_estimators=50 test pred:13.332917824364422 train pred:13.596363229445517 n_estimators=60 test pred:13.213487528079883 train pred:13.396176165439513 n_estimators=70 test pred:13.10819335098783 train pred:13.232742431772904 n_estimators=80 test pred:13.028332928142436 train pred:13.05872852961913 n_estimators=100 test pred:12.86919017601814 train pred:12.791915988739184 #featureUpdate9_copy (17770, 3261) max_depth=3 estimators=150 velify: 12.5334900921 train: 11.3776224998 estimators=200 velify: 11.550748202 train: 10.1344264144 max_depth=4 estimators=150 velify: 10.1836276086 train: 8.34158042085 estimators=200 velify: 9.37591981994 train: 7.20248574924 (12331, 3261) [1109 1648 6771 ..., 603 8275 1578] max_depth=3 estimators=150 velify: 10.6453847159 train: 11.2729932001 estimators=200 velify: 9.9414817475 train: 10.389250062 max_depth=4 estimators=150 velify: 8.75527324868 train: 8.97797705027 estimators=200 velify: 7.86024826823 train: 7.88008217996