Added files

Author: Stephen McGough

README.md

@@ -1 +1,3 @@
 # BadAI
+Data and code to go with the Blog post: The Danger of Learning the Wrong Thing
+Please see post at: 

predict.csv

@@ -0,0 +1,166 @@
+qdate,year,month,day,week,hour,min,id,owner,command,actual duration
+1263821073,2010,1,18,2,13,24,149969,4,8,934
+1263821914,2010,1,18,2,13,38,149970,4,8,24327
+1263846751,2010,1,18,2,20,32,149971,4,9,3
+1263848977,2010,1,18,2,21,9,149972,4,10,1223
+1263850223,2010,1,18,2,21,30,149973,4,10,3
+1263915682,2010,1,19,3,15,41,149975,4,11,3
+1263919050,2010,1,19,3,16,37,149976,4,11,3
+1263919345,2010,1,19,3,16,42,149977,4,11,3
+1263920377,2010,1,19,3,16,59,149978,4,11,3
+1263924242,2010,1,19,3,18,4,149979,4,11,3
+1263924728,2010,1,19,3,18,12,149980,4,11,4
+1263931520,2010,1,19,3,20,5,149981,4,11,494
+1263932284,2010,1,19,3,20,18,149982,4,11,3
+1264072945,2010,1,21,5,11,22,149986,4,11,287
+1264073258,2010,1,21,5,11,27,149987,4,11,3
+1264074453,2010,1,21,5,11,47,149988,4,11,4
+1264071357,2010,1,21,5,10,55,149985,5,11,3258
+1264075019,2010,1,21,5,11,56,149990,4,11,245
+1264074603,2010,1,21,5,11,50,149989,4,11,1585
+1264075726,2010,1,21,5,12,8,149991,4,11,476
+1264076053,2010,1,21,5,12,14,149992,5,11,3
+1264076346,2010,1,21,5,12,19,149993,4,11,219
+1264076780,2010,1,21,5,12,26,149995,4,11,438
+1264076709,2010,1,21,5,12,25,149994,5,11,786
+1264077509,2010,1,21,5,12,38,149996,5,11,3
+1264077699,2010,1,21,5,12,41,149997,5,11,624
+1264078289,2010,1,21,5,12,51,149998,5,11,144
+1264078593,2010,1,21,5,12,56,149999,5,11,659
+1264079354,2010,1,21,5,13,9,150000,5,11,3
+1264080184,2010,1,21,5,13,23,150001,5,11,4
+1264080394,2010,1,21,5,13,26,150002,5,11,3
+1264080646,2010,1,21,5,13,30,150003,5,11,498
+1264081538,2010,1,21,5,13,45,150004,5,11,49
+1264081918,2010,1,21,5,13,51,150005,5,11,52
+1264083321,2010,1,21,5,14,15,150006,5,12,8
+1264083886,2010,1,21,5,14,24,150007,5,12,7
+1264083994,2010,1,21,5,14,26,150008,5,12,7
+1264084571,2010,1,21,5,14,36,150009,5,12,7
+1264087183,2010,1,21,5,15,19,150010,5,11,39
+1264087847,2010,1,21,5,15,30,150011,5,11,48
+1264088406,2010,1,21,5,15,40,150013,5,11,22
+1264088365,2010,1,21,5,15,39,150012,5,11,68
+1264088440,2010,1,21,5,15,40,150014,5,11,883
+1264089384,2010,1,21,5,15,56,150015,5,11,49
+1264090333,2010,1,21,5,16,12,150016,5,11,453
+1264090802,2010,1,21,5,16,20,150017,5,11,57
+1264091227,2010,1,21,5,16,27,150018,5,11,57
+1264092287,2010,1,21,5,16,44,150019,5,11,30
+1264092449,2010,1,21,5,16,47,150020,5,11,29
+1264093366,2010,1,21,5,17,2,150021,5,11,26
+1264093637,2010,1,21,5,17,7,150022,5,11,25
+1264094063,2010,1,21,5,17,14,150023,5,11,21
+1264094229,2010,1,21,5,17,17,150024,5,11,30
+1264168189,2010,1,22,6,13,49,150025,4,13,147
+1264168560,2010,1,22,6,13,56,150026,4,13,211
+1264168902,2010,1,22,6,14,1,150027,4,13,505
+1264170198,2010,1,22,6,14,23,150028,4,11,26
+1264170894,2010,1,22,6,14,34,150029,4,11,30
+1264171330,2010,1,22,6,14,42,150030,4,11,16
+1264172626,2010,1,22,6,15,3,150031,4,11,26
+1264173287,2010,1,22,6,15,14,150032,4,11,25
+1264173918,2010,1,22,6,15,25,150033,4,11,25
+1264174092,2010,1,22,6,15,28,150034,4,11,4
+1264174324,2010,1,22,6,15,32,150036,4,11,14
+1264174308,2010,1,22,6,15,31,150035,4,11,1324
+1264175644,2010,1,22,6,15,54,150037,4,11,31
+1264176009,2010,1,22,6,16,0,150038,4,11,30
+1264179308,2010,1,22,6,16,55,150040,5,14,13
+1264181119,2010,1,22,6,17,25,150041,5,11,4
+1264182196,2010,1,22,6,17,43,150042,5,11,3
+1264185014,2010,1,22,6,18,30,150043,5,11,24
+1264185432,2010,1,22,6,18,37,150044,5,11,23
+1264186268,2010,1,22,6,18,51,150045,5,11,112
+1264186427,2010,1,22,6,18,53,150046,5,11,23
+1264190614,2010,1,22,6,20,3,150047,4,11,131
+1264190903,2010,1,22,6,20,8,150048,4,11,52
+1264191891,2010,1,22,6,20,24,150049,4,11,302
+1264192633,2010,1,22,6,20,37,150050,4,11,57
+1264193039,2010,1,22,6,20,43,150051,4,11,12
+1264193302,2010,1,22,6,20,48,150052,4,11,250
+1264193567,2010,1,22,6,20,52,150053,4,11,12
+1264193823,2010,1,22,6,20,57,150054,4,11,11
+1264194045,2010,1,22,6,21,0,150055,4,11,12
+1264197883,2010,1,22,6,22,4,150056,4,11,12
+1264198249,2010,1,22,6,22,10,150057,4,11,595
+1264198853,2010,1,22,6,22,20,150058,4,11,372
+1264199235,2010,1,22,6,22,27,150059,4,11,12
+1264199668,2010,1,22,6,22,34,150060,4,11,598
+1264200291,2010,1,22,6,22,44,150061,4,11,12
+1264241661,2010,1,23,7,10,14,150062,4,11,1006
+1264242781,2010,1,23,7,10,33,150063,4,11,13
+1264246188,2010,1,23,7,11,29,150064,4,11,332
+1264246598,2010,1,23,7,11,36,150065,4,11,1128
+1264247745,2010,1,23,7,11,55,150066,4,11,3
+1264270237,2010,1,23,7,18,10,150067,4,11,4
+1264270351,2010,1,23,7,18,12,150068,4,11,11
+1264270521,2010,1,23,7,18,15,150069,4,11,12
+1264271152,2010,1,23,7,18,25,150070,4,11,12
+1264274335,2010,1,23,7,19,18,150071,5,11,24
+1264274502,2010,1,23,7,19,21,150072,5,11,32
+1264274834,2010,1,23,7,19,27,150073,5,11,12
+1264285743,2010,1,23,7,22,29,150074,4,11,18
+1264424357,2010,1,25,2,12,59,150075,4,11,55
+1264430177,2010,1,25,2,14,36,150077,4,11,23
+1264430563,2010,1,25,2,14,42,150078,4,11,12
+1264430856,2010,1,25,2,14,47,150079,4,11,12
+1264431062,2010,1,25,2,14,51,150080,4,11,12
+1264431736,2010,1,25,2,15,2,150081,4,11,240
+1264432000,2010,1,25,2,15,6,150082,4,11,12
+1264432476,2010,1,25,2,15,14,150083,4,11,23
+1264432732,2010,1,25,2,15,18,150084,4,11,23
+1264433403,2010,1,25,2,15,30,150085,4,11,11
+1264433548,2010,1,25,2,15,32,150086,4,11,11
+1264433727,2010,1,25,2,15,35,150087,4,11,11
+1264434713,2010,1,25,2,15,51,150091,0,0,73
+1264434788,2010,1,25,2,15,53,150092,4,11,1469
+1264436279,2010,1,25,2,16,17,150093,4,11,24
+1264437234,2010,1,25,2,16,33,150094,4,11,24
+1264437440,2010,1,25,2,16,37,150095,4,11,23
+1264437697,2010,1,25,2,16,41,150098,4,11,23
+1264437852,2010,1,25,2,16,44,150099,4,11,23
+1264438260,2010,1,25,2,16,51,150100,4,11,23
+1264438814,2010,1,25,2,17,0,150101,4,11,24
+1264496826,2010,1,26,3,9,7,150102,4,11,7209
+1264504331,2010,1,26,3,11,12,150103,4,11,4
+1264504534,2010,1,26,3,11,15,150104,4,11,45
+1264510270,2010,1,26,3,12,51,150105,4,11,12
+1264511336,2010,1,26,3,13,8,150106,4,11,11
+1264511983,2010,1,26,3,13,19,150107,4,11,188
+1264512181,2010,1,26,3,13,23,150108,4,11,667
+1264512860,2010,1,26,3,13,34,150109,4,11,150
+1264513025,2010,1,26,3,13,37,150110,4,11,11
+1264513512,2010,1,26,3,13,45,150111,4,11,11
+1264514553,2010,1,26,3,14,2,150112,4,11,56
+1264434713,2010,1,25,2,15,51,150088,0,0,80944
+1264434713,2010,1,25,2,15,51,150089,0,0,80951
+1264434713,2010,1,25,2,15,51,150090,0,0,80953
+1264515879,2010,1,26,3,14,24,150114,4,12,8
+1264515522,2010,1,26,3,14,18,150113,4,11,12
+1264516127,2010,1,26,3,14,28,150115,4,11,12
+1264516500,2010,1,26,3,14,35,150116,4,12,741
+1264517033,2010,1,26,3,14,43,150117,4,11,214
+1264517257,2010,1,26,3,14,47,150118,4,11,11
+1264517646,2010,1,26,3,14,54,150119,4,11,12
+1264520243,2010,1,26,3,15,37,150120,4,11,12
+1264520321,2010,1,26,3,15,38,150121,4,11,11
+1264520322,2010,1,26,3,15,38,150122,4,11,13
+1264520353,2010,1,26,3,15,39,150123,4,11,11
+1264520402,2010,1,26,3,15,40,150124,4,11,11
+1264520404,2010,1,26,3,15,40,150125,4,11,11
+1264680495,2010,1,28,5,12,8,150126,4,11,62
+1264680741,2010,1,28,5,12,12,150127,4,11,12
+1264681306,2010,1,28,5,12,21,150128,4,11,11
+1264693114,2010,1,28,5,15,38,150130,5,11,24
+1264701032,2010,1,28,5,17,50,150131,0,0,1
+1264701193,2010,1,28,5,17,53,150132,0,0,135
+1264701341,2010,1,28,5,17,55,150133,0,0,21
+1264701381,2010,1,28,5,17,56,150134,0,0,679
+1264763189,2010,1,29,6,11,6,150135,4,11,58
+1264768732,2010,1,29,6,12,38,150136,4,11,58
+1264770383,2010,1,29,6,13,6,150138,4,11,74
+1264770091,2010,1,29,6,13,1,150137,4,11,57
+1264771865,2010,1,29,6,13,31,150139,4,11,252703
+1264771904,2010,1,29,6,13,31,150140,4,11,252667
+1264692165,2010,1,28,5,15,22,150129,5,11,543754

rfCode.py

@@ -0,0 +1,33 @@
+import pandas as pd
+from sklearn.model_selection import train_test_split
+
+data=pd.read_csv("train.csv")
+print (data.columns)
+del data['year']
+
+X_train, X_test, y_train, y_test = train_test_split(data, data.loc[: ,'actual duration'], test_size=0.3, random_state=123456)
+
+del X_train['actual duration']
+del X_test['actual duration']
+
+from sklearn.ensemble import RandomForestRegressor
+
+rf = RandomForestRegressor(n_estimators=50, random_state=123456, n_jobs=-1)
+rf.fit(X_train, y_train)
+
+r2s = rf.score(X_test, y_test)
+
+print ('R^2 from test set = ', r2s)
+
+print (rf.feature_importances_)
+
+predict=pd.read_csv("predict.csv")
+
+predict_label = predict.loc[: ,'actual duration']
+
+del predict['year']
+del predict['actual duration']
+
+score = rf.score(predict, predict_label)
+
+print ('R^2 from predicion set = ', score)