In [2]:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
import seaborn as sns
In [3]:
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
from sklearn.datasets import samples_generator
from sklearn import svm
from sklearn.pipeline import Pipeline
from sklearn.pipeline import FeatureUnion
from sklearn.cross_validation import StratifiedKFold, permutation_test_score
In [4]:
from utils.sax import SAX
from utils.SAXTransformer import SAXTransformer
In [16]:
X = []
y = []
with open('data/synthetic_control_TRAIN.txt') as infile:
for i in infile:
instance = []
for j in i.split():
instance.append(float(j))
X.append(np.array(instance[1:]))
y.append(instance[0])
X = np.array(X)
y = np.array(y)
In [22]:
df = pd.DataFrame(X)
df
Out[22]:
0
1
2
3
4
5
6
7
8
9
...
50
51
52
53
54
55
56
57
58
59
0
-0.376936
1.224864
0.343874
0.328454
-0.337609
1.026514
-1.330996
-0.657800
1.446077
-0.846397
...
0.370712
-1.568165
1.021863
-1.429748
1.356966
1.372781
0.663558
0.918346
-1.311742
-1.197146
1
0.644406
0.413269
-0.862278
-1.497386
-0.421458
-0.214215
-1.292131
0.956898
-1.216140
-0.588536
...
1.317268
-0.802528
-1.121287
0.989319
-1.109687
0.219856
0.630034
1.398140
0.085742
0.024997
2
-0.978667
-0.406232
0.822429
-1.408242
-1.676734
-0.490632
1.404598
1.168600
-1.703254
0.972810
...
-0.828783
-0.762884
1.382972
-0.869103
1.277252
-0.198967
0.966809
0.666129
0.106996
0.082715
3
-0.236537
-0.098175
0.367092
1.366860
0.498281
-0.300223
1.715634
0.902108
-0.218132
-1.430721
...
0.068904
-1.499604
0.406744
1.289153
-1.119731
-0.995985
1.651135
-1.187098
0.025463
-0.841518
4
1.490735
1.325243
1.626829
-0.317056
-1.098990
-0.022213
0.596980
1.667339
-0.206153
-1.376627
...
0.815065
1.029995
-1.496161
-1.167442
1.484208
-0.373020
-0.843281
-0.209794
0.137724
0.716542
5
1.643316
1.764011
0.437756
0.199310
-1.567616
-0.719117
-1.094189
1.033176
-1.377166
-0.948905
...
0.282082
-1.368681
0.097894
-0.425231
0.575449
-0.912021
1.317424
-0.397265
0.209267
-0.045311
6
1.184702
0.788449
-1.742959
-0.963561
-1.267327
1.133356
0.206078
-0.428372
-0.979484
-1.488956
...
0.704026
-0.037163
1.557496
1.070896
-1.713899
-1.275625
0.184349
-0.764247
0.628312
0.754082
7
-1.523098
0.995921
1.696381
-0.253934
-0.196881
0.858227
0.145158
-1.449185
-1.416422
1.316850
...
0.430313
-0.853009
0.795066
1.647490
-0.632845
1.486350
-1.046602
0.699480
1.236125
-0.976517
8
-1.370494
-0.695313
-0.844815
-1.359326
1.522725
-1.155992
-0.086756
0.800240
-1.057486
0.173543
...
-0.287343
-0.401065
-1.717156
1.299328
0.313944
0.601898
-1.723981
0.708323
0.067532
1.184749
9
-0.824564
0.541666
0.320328
-0.362941
-0.948632
0.852671
-1.555186
0.311272
1.752519
1.540855
...
-0.865549
-1.610791
-0.019699
-1.305691
0.449620
0.588895
-0.319360
-0.527314
1.650272
-0.828984
10
-1.175847
1.214149
-1.311968
-1.577644
-0.826284
-1.297805
-1.309377
0.095824
-1.278990
0.037524
...
1.654224
-0.358090
-0.764421
-1.489635
1.250041
1.827444
0.699256
1.010865
0.677968
-0.851046
11
0.512565
0.419255
1.208409
1.028563
1.303379
-0.178350
-0.508625
-1.423431
0.227785
1.537814
...
0.431064
1.562407
1.503152
1.425921
0.135266
1.163599
-1.290609
0.919781
-1.090731
-0.199938
12
-0.275532
0.796881
1.130192
1.536720
0.444744
-0.056489
-2.124858
-0.310393
0.640376
0.868848
...
-1.545083
0.648490
-0.569492
1.089558
0.338879
0.974360
-0.328416
0.997804
1.288814
-0.033751
13
0.935475
0.889252
-0.857636
-1.034085
-1.185071
-1.283998
0.357616
0.420726
-1.355498
-0.658464
...
0.298163
1.571469
-0.147964
1.070757
0.529925
1.121605
-1.474081
-0.516459
1.292328
-1.496991
14
1.163575
-0.544958
0.682241
-0.745874
0.248983
-1.367687
0.027031
-1.469814
0.789101
0.421428
...
0.731715
0.036373
1.293886
1.185023
0.368585
1.555270
-1.348082
1.402431
-1.853915
-0.919273
15
-0.864947
1.454779
-0.821804
-1.578166
-0.820126
0.966642
-0.503750
1.014549
-0.021405
-0.131429
...
-1.235969
-0.206754
0.760426
-0.020512
0.329047
0.296567
0.836048
-1.181214
-1.600035
1.357774
16
1.373763
-1.275270
0.655254
-0.069390
-1.308730
1.251184
0.882781
-1.099739
0.709878
1.564404
...
1.543240
-1.086674
0.372572
-0.804177
1.453642
0.667443
-0.676526
-1.154151
1.541779
-0.700399
17
-1.260423
1.466464
-0.547978
-1.683989
0.990511
0.212970
0.727742
-0.033511
-1.111252
0.218769
...
1.326672
-0.894517
0.640421
1.546876
0.231922
1.239961
1.527314
-1.119299
-0.589238
-0.088951
18
-1.343327
0.190683
-0.915430
0.493999
0.052807
1.324177
-1.484093
-0.455041
0.660807
0.218277
...
0.178940
-0.936452
1.045564
1.464061
1.755298
-1.615915
0.408206
1.285509
-1.354735
0.812160
19
-0.711199
-1.293888
1.394605
0.263612
0.683074
-1.536496
1.019617
0.450990
1.713260
1.232247
...
-0.147558
-0.269877
-0.143934
-0.849377
0.170459
1.407274
0.975027
1.497324
1.236393
-0.592272
20
0.998438
0.010591
0.051387
1.232272
1.247846
-0.366884
0.103733
0.901161
-0.262413
0.849449
...
0.543340
0.471367
-1.542476
-1.160563
0.307879
-0.358559
0.457998
-0.349656
1.207160
-1.436103
21
0.530381
-0.668505
0.555085
1.175591
0.247205
-0.392256
1.260225
-1.432780
0.772346
0.151074
...
0.101165
-1.578260
0.873666
-1.011229
0.415767
-1.132477
-1.438175
-0.733359
-1.360674
-1.170151
22
1.209642
1.358040
1.727919
-1.284312
-0.357169
1.692404
-0.509908
-0.110882
-1.318321
0.768647
...
0.938406
-0.156383
-1.352244
1.511936
1.012590
0.514083
-1.383070
-0.902421
-1.495952
-1.446313
23
0.724569
0.992426
-1.090382
0.102660
-0.681565
-1.208842
-1.919883
0.843060
0.112178
1.492692
...
0.354477
-0.968584
-0.313173
0.265840
0.064739
0.154859
-1.562369
0.156559
0.727412
1.121116
24
-0.268848
1.911734
-1.148335
-0.298710
-1.132138
0.203322
0.917081
1.633279
1.941566
0.067112
...
-1.162782
-1.042675
0.140033
1.706168
-0.530793
-0.059873
0.644379
-1.280824
1.248132
2.047663
25
-1.484351
-0.785003
0.182506
-1.291101
0.444604
0.249626
0.215305
-0.551545
0.206168
-0.840497
...
-0.285933
-1.176452
1.741829
1.646566
-1.149451
-1.108482
0.827004
-0.351530
0.937027
-1.145058
26
-1.269741
-1.043208
0.945561
-0.077906
-0.104779
-1.453267
1.518538
0.487803
0.196732
0.982711
...
-0.639738
0.294109
0.892575
-0.512858
-1.502267
1.455085
-1.286689
1.254258
0.301484
-0.384705
27
-1.345260
-1.192002
0.441649
1.251280
0.040124
-0.707149
1.088061
1.010849
-0.303295
-1.568245
...
0.240246
-1.267612
-1.022462
-1.806230
-0.961823
0.722273
-0.302013
-1.524819
0.428600
-0.288878
28
1.799137
-0.550966
0.897647
-0.519890
0.216201
-1.506052
-0.138867
0.787497
0.123578
-0.330094
...
0.513252
1.555841
-0.674315
-0.880460
0.503201
-1.669129
-0.514164
0.816919
-0.917961
-0.755838
29
0.075424
0.002187
-1.539788
1.238665
-1.498312
1.241067
0.092778
-1.128174
1.377143
-1.526472
...
-1.130493
1.004604
0.710894
-0.391308
0.854092
-0.573362
0.199686
-0.199322
-0.282081
-1.429087
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
270
0.693533
0.336936
0.314176
-0.054203
0.845034
-0.138991
0.138383
1.081019
1.320044
1.901741
...
-1.354448
-1.030520
0.462426
-1.612217
-0.925170
0.542433
0.633322
0.328062
-1.028760
-0.291640
271
1.553505
1.447669
1.691212
1.348695
1.450091
1.002545
0.500227
1.854059
1.330638
1.452158
...
-0.456903
-0.027280
-0.531971
-0.934373
-0.439200
-0.278053
-0.552549
-0.345169
0.112665
0.012664
272
0.060546
0.947275
1.767715
0.557307
1.320836
1.257246
0.254468
1.542317
0.140770
1.337181
...
-1.847822
-1.591464
0.156827
0.283388
-1.654209
-1.351658
-1.062135
-0.446831
-0.889093
-0.257052
273
0.331645
1.354371
1.080032
0.557326
0.397578
1.194133
0.517856
1.343859
0.322843
0.355059
...
-0.421454
-0.668045
-1.015987
-1.255607
-0.662398
-0.933582
-0.652651
-1.078898
-1.483230
-1.308082
274
0.853049
0.380466
1.110460
0.454124
1.147169
0.444658
0.567308
1.455448
0.436779
1.412526
...
-0.959834
-0.544383
-1.083618
-0.819071
-0.436422
-0.515447
-0.494534
-1.356151
-0.713871
-0.580091
275
1.587592
0.937045
0.203236
1.330903
1.585494
0.528824
-0.308439
-0.248508
-0.360857
1.138359
...
-0.322301
-1.599115
-0.613637
-1.071497
-0.953105
-0.080944
0.156378
-1.750969
-0.514595
0.002102
276
0.474543
1.463514
0.664824
1.390514
1.586898
1.165709
0.668478
0.596785
0.434861
0.392211
...
-1.186097
-0.759535
-1.181447
-0.469702
-1.380300
-1.634880
-0.843466
-0.861880
-0.827305
-1.401607
277
1.812364
0.983723
1.158263
1.523850
1.514194
1.396586
1.473005
1.345374
0.729658
0.943108
...
0.034319
-0.224128
-1.314849
-0.294508
-0.851381
-0.650263
-0.594511
-0.118455
-0.792505
-0.456715
278
0.424390
0.496525
0.489231
1.390912
1.230207
1.171173
2.182840
2.245100
0.763918
1.272395
...
-1.278360
-0.738251
-1.127924
-1.344115
-0.226350
-1.475481
-0.558172
0.125024
-0.298360
0.194382
279
0.337007
1.734533
1.681828
0.494425
0.385980
1.165555
1.581474
1.150102
0.309171
1.151102
...
-0.210597
-0.148189
-2.056933
-1.149592
-1.308248
-0.398786
-1.243092
-0.647703
-0.620918
-1.285517
280
-0.508647
0.203090
-0.301114
1.097649
0.589860
1.049308
-0.025958
0.346135
0.655993
1.526098
...
-1.980461
-0.204118
-0.602978
-2.353553
-1.391410
-0.353786
-1.373363
-0.211309
-0.545701
-0.202903
281
1.300421
1.282511
0.501704
0.403188
0.936324
0.788908
0.986904
0.810403
0.327012
0.561521
...
-1.603539
-1.018826
-0.440809
-0.952545
-1.579890
-1.259458
-0.964192
-0.284063
-1.109410
-0.925963
282
0.876021
0.964189
0.980474
1.163220
1.094635
0.734070
0.268186
0.346197
1.231877
0.593070
...
-1.351913
-1.114362
-1.104122
-1.449476
-1.891623
-0.797485
-1.315502
-1.068086
-1.892658
-1.611132
283
0.118799
0.889472
0.709761
1.101568
0.758967
0.412104
1.440211
0.850789
0.776578
1.083117
...
-1.310849
-1.144690
-0.750860
-1.523696
-1.266173
-0.240687
-0.915632
-1.155849
-1.569021
-1.468318
284
0.987800
1.755330
1.273615
1.695207
1.367180
0.858529
1.893642
1.952042
0.429874
1.887508
...
-0.895954
-0.344551
-0.265248
-0.764402
-0.084556
0.049666
-0.953662
-0.685843
-0.980175
0.177196
285
1.640048
0.457685
1.027842
1.288748
1.811037
1.271028
1.520211
0.475453
1.195247
1.099978
...
-0.262813
-1.342934
-0.208529
-0.574657
-0.901820
-0.727449
-0.113487
-0.795331
-0.846138
-0.712835
286
1.820585
0.923731
1.211736
1.525482
0.779063
1.075045
1.779380
0.799778
1.503837
1.843649
...
-0.463621
-0.024226
-0.964194
-0.968628
-0.262861
-0.012003
-0.798584
-0.652119
-0.354202
-0.112791
287
0.709331
1.032259
0.824723
1.955907
0.711254
0.634161
0.374651
0.634748
1.757492
0.475327
...
-0.026973
-0.092635
-0.562431
-0.493084
-0.319240
-1.516282
-1.325764
-0.320870
-0.668209
-0.090779
288
1.898080
1.011445
1.585312
0.721400
1.718678
1.590322
0.159375
0.740917
2.084904
1.758202
...
-0.268304
-0.634834
-0.354100
-1.103825
-1.174945
-1.066292
-1.194092
-0.042007
-0.758534
-0.652242
289
-0.134751
1.689514
0.525538
1.579188
1.491051
-0.181860
0.784123
1.527880
-0.234634
1.042581
...
0.142457
-0.272966
-0.529035
-0.427089
-1.725244
-0.035646
-1.455619
-0.333721
-1.376729
-0.274504
290
0.947571
1.045224
1.280352
1.166374
1.593510
1.001718
0.667217
1.600279
0.507579
0.704017
...
-0.058286
-0.220046
-1.188638
-0.838060
-0.496977
-0.858304
-0.439810
-0.864453
-1.381173
-1.223394
291
0.899774
0.511203
-0.064804
1.195401
0.898803
0.092994
1.062571
0.788133
1.203837
0.007135
...
-0.496199
-0.864591
-1.671988
-1.678260
-0.661987
-1.258554
-0.267578
-0.783258
-1.265154
-1.078360
292
1.466291
1.401358
0.890413
0.637260
0.540565
0.999387
0.860492
0.906255
0.428833
1.784884
...
-0.146449
-0.435276
-1.208402
-1.386830
0.056563
-0.490119
-0.889240
-0.467283
-1.328606
-1.207029
293
1.213886
1.005379
0.524086
0.516285
0.949565
1.463143
0.909321
1.295207
0.938458
1.243282
...
-0.249001
-0.722244
-1.198085
-1.481894
-1.031969
-1.479087
-1.263724
-1.248447
-1.215835
-0.297171
294
1.511380
1.105290
1.110977
0.920534
0.940863
0.063350
0.051428
1.705281
0.604451
1.417216
...
-1.045283
-0.688617
-1.509790
-0.486498
-0.564905
-1.907605
-0.557404
-0.482625
-0.221068
-1.265369
295
0.805841
0.137184
1.039280
0.175289
0.875453
0.508280
1.272193
0.107335
0.652739
1.153325
...
-0.976683
-0.849044
-1.513174
-0.636618
-1.004551
-1.107356
-0.761440
-1.223342
-1.309249
-1.273690
296
0.417909
1.544827
1.693856
1.115731
0.954563
0.625996
0.746136
1.096354
1.213999
0.819162
...
-1.465301
-0.418516
-1.150362
-0.445236
-0.359302
-1.197046
-0.079914
-0.054488
-0.751970
-0.954400
297
0.965901
0.640161
0.480857
0.462761
0.800787
0.507464
0.629943
0.361362
1.270979
0.429349
...
-1.422507
-1.498756
-1.234976
-1.537108
-0.481013
-1.469285
-1.371460
-0.683358
-1.195676
-0.803644
298
0.354971
0.109652
0.238897
0.910018
0.198167
0.360869
0.728878
1.268917
0.372435
0.752898
...
-0.655457
-1.586054
-0.925246
-0.757277
-1.570425
-1.262181
-0.518927
-1.625361
-1.765371
-1.675383
299
0.646617
0.613516
1.126664
0.979204
0.919017
1.617676
1.707450
1.409003
2.098429
0.755410
...
0.018942
-1.022475
-0.522985
-0.875489
-0.818226
-1.444264
-0.956029
-0.023957
-0.833347
-0.261178
300 rows × 60 columns
In [ ]:
Content source: tarmstro/mvbop
Similar notebooks: