In [1]:
from pathlib import Path
import pandas as pd
import numpy as np
root=Path('../').resolve()
In [2]:
root
Out[2]:
WindowsPath('C:/Users/user/Documents/GitHub/Carkinos')
In [3]:
raw_path=root.joinpath('src','PCA_TEST.quantile_normalized.tsv')
In [4]:
sample_raw_data_df = pd.read_table(raw_path.as_posix())
In [5]:
sample_raw_data_df
Out[5]:
Unnamed: 0
GSM1687570_5500024035100021608461.G01.CEL.gz
GSM1687571_5500024034290101707049.A01.CEL.gz
GSM1687572_5500024052603032009483.A09.CEL.gz
GSM1687573_5500024035100021608461.H01.CEL.gz
GSM1687574_5500024032848101507998.D02.CEL.gz
GSM1687575_5500024030401071707289.D04.CEL.gz
GSM1687576_5500024030401071707289.C10.CEL.gz
GSM1687577_5500024052861011409506.D05.CEL.gz
GSM1687578_5500024032848101507998.E02.CEL.gz
...
GSM1688358_5500024032848101507998.G01.CEL.gz
GSM1688359_5500024031722092907496.C11.CEL.gz
GSM1688360_5500024052861011409506.E11.CEL.gz
GSM1688361_5500024035100021608461.E01.CEL.gz
GSM1688362_5500024032848101507998.H01.CEL.gz
GSM1688363_5500024052861011409506.E09.CEL.gz
GSM1688364_5500024031722092907496.B11.CEL.gz
GSM1688365_5500024052861011409506.D09.CEL.gz
GSM1688366_5500024032848101507000.H03.CEL.gz
GSM1688367_5500024035100021608461.F01.CEL.gz
0
1007_s_at
9.525619
8.718047
9.904457
9.798405
10.932997
8.973151
10.857714
10.975397
8.635765
...
9.429262
9.661919
9.589560
10.112593
8.408232
8.722528
10.710177
9.657667
9.176614
10.897960
1
1053_at
9.047948
8.616065
9.203023
8.572035
8.506107
8.229169
8.695021
8.915824
8.233599
...
8.776563
9.155915
9.336024
8.824805
8.772813
8.802262
8.678147
8.625144
8.695912
8.629976
2
117_at
7.612412
8.043859
7.603927
7.714699
7.742822
7.551629
7.504556
7.720968
7.730913
...
7.729079
11.647400
11.342093
7.850625
8.028290
8.037324
7.655276
7.888281
7.691653
7.624577
3
121_at
8.218106
8.235331
8.400500
8.405479
9.297814
8.178474
8.067798
8.176426
11.259210
...
11.123192
8.063912
8.138332
8.213297
8.035581
8.203285
8.021791
8.373332
8.081797
8.261245
4
1255_g_at
7.392744
7.395735
7.453283
7.493720
7.474639
7.436698
7.388679
7.508520
7.432427
...
7.445189
9.069289
8.621514
7.446887
7.512241
7.456834
7.453321
7.509484
7.315354
7.513548
5
1294_at
9.003722
8.375226
7.975448
7.762306
7.763070
7.981557
8.389011
8.376507
7.903314
...
8.412039
7.796222
7.722225
7.956599
8.201499
8.151006
8.215746
9.143522
8.090617
7.830512
6
1316_at
7.909244
7.878632
7.903908
7.741367
8.015132
7.772626
7.807954
7.809478
7.864759
...
8.065336
7.948937
8.050267
7.966506
8.097026
7.900293
7.847609
8.001678
8.084945
7.888374
7
1320_at
7.651478
7.708905
7.602916
7.705086
7.712262
7.723882
7.739506
7.641239
7.621617
...
7.761721
7.783990
7.627924
7.675847
7.875980
7.544660
7.588426
7.574985
7.583279
7.611891
8
1405_i_at
7.834398
7.697773
7.633690
7.601535
7.726134
7.614437
8.776613
8.449633
7.636824
...
7.801481
7.580300
7.648297
7.794772
8.369012
7.921049
7.615833
7.820004
7.807366
7.596185
9
1431_at
7.728028
7.771812
7.403523
7.667112
7.520539
7.713980
7.536457
7.460594
7.545543
...
7.672223
7.619240
7.575923
7.509735
7.758326
7.674408
7.513123
7.458537
7.479716
7.611531
10
1438_at
7.657973
7.839882
7.600658
7.751388
8.271726
7.653040
7.639229
7.651966
7.630050
...
7.703543
7.879641
7.665347
8.257526
7.835643
7.662081
7.729477
7.615180
7.752624
8.094068
11
1487_at
8.206241
7.972470
8.424972
8.281678
8.992934
8.402891
8.278146
8.351512
8.908842
...
8.344273
8.172797
7.982788
7.879871
8.472595
8.059953
9.227652
8.028662
8.095783
8.198551
12
1494_f_at
7.858453
7.830963
7.711877
7.809028
7.815555
7.735942
7.664429
7.825576
7.818208
...
7.844457
7.801330
7.819480
7.692542
7.922304
7.911433
7.801025
7.791079
7.718452
7.767680
13
1598_g_at
8.087957
7.959245
8.664610
7.890980
8.003252
8.358760
9.062693
9.483724
8.192223
...
10.170631
9.618505
9.566406
8.119021
7.823470
8.055860
8.487177
9.481194
8.711049
8.056754
14
160020_at
8.028948
8.007019
8.531796
8.034021
7.950786
8.030606
7.891479
8.148135
8.369209
...
7.966837
8.077760
8.133854
8.968220
7.858555
8.259718
8.591962
9.294565
8.483516
8.049743
15
1729_at
8.096292
8.180304
8.388173
8.260304
8.831569
8.349998
8.593277
8.616233
9.019362
...
8.835704
8.007914
8.141308
8.310294
8.290844
8.510494
8.542961
8.556058
8.174816
8.341683
16
177_at
7.514178
7.606598
7.693805
7.581838
7.708548
7.708384
7.597449
7.693610
7.620039
...
7.656180
7.591175
7.567320
7.698346
7.841765
7.630390
7.571643
7.708900
7.706586
7.618176
17
1773_at
7.677061
7.844826
7.771058
7.596594
7.590436
7.767117
7.812929
7.795710
7.775275
...
7.741154
7.675076
7.812365
7.961307
7.810738
7.865056
7.612419
7.775011
7.651543
7.819192
18
179_at
8.243753
8.264494
8.455341
8.109603
8.178008
8.221881
8.216369
8.128763
8.127175
...
8.079943
8.025528
8.051105
8.290394
7.986633
8.172114
8.114658
8.182000
8.141716
8.375676
19
1861_at
7.947907
8.087725
8.533923
8.077407
8.486724
8.214426
8.467074
8.454226
8.380016
...
8.391886
8.459854
8.388810
8.171772
8.105932
8.126414
8.459284
8.558124
8.431172
8.444880
20
200000_s_at
10.943962
10.554185
10.010714
10.351770
10.582500
10.918780
10.779839
11.012558
10.666718
...
10.323892
11.362956
11.045315
10.389930
10.730466
10.670736
10.434048
10.010854
11.172518
9.934250
21
200001_at
10.147493
10.029987
9.968916
10.557932
11.251398
10.456606
11.179078
11.440406
11.391664
...
11.327322
9.867762
9.967675
11.068072
10.325408
10.568185
11.879458
11.553767
11.167581
11.182587
22
200002_at
12.598934
12.884603
12.851004
12.440221
12.163264
12.102061
11.971443
11.775090
11.991532
...
12.225448
12.452044
12.234126
12.269134
12.278390
11.997784
12.361425
11.893040
12.207024
12.139081
23
200003_s_at
13.962958
13.866020
13.939309
13.421075
13.495911
13.614290
13.357725
13.273866
13.261886
...
13.665884
13.199544
13.201468
13.438959
13.736109
13.757036
13.518426
13.648311
13.487201
13.645801
24
200004_at
11.638454
11.515864
12.092778
11.388483
11.110027
11.023252
12.139457
11.722688
10.971977
...
10.811857
11.674871
11.621797
12.281479
11.026658
11.344845
11.860932
11.245582
11.229407
12.435254
25
200005_at
11.789568
11.780158
11.265116
10.932197
11.208736
11.723449
11.019480
10.959582
11.198749
...
10.613178
11.048126
10.848619
10.751546
10.975890
10.848473
10.825055
10.997519
10.427742
11.391999
26
200006_at
11.829138
11.970993
12.057994
12.046755
12.081040
12.305364
11.943838
11.873483
11.524197
...
11.690109
11.795945
11.744640
12.418210
11.275798
11.125740
11.738490
12.302239
12.460312
11.976653
27
200007_at
11.819296
11.439260
11.757965
11.494313
11.563859
11.501570
12.002326
11.871924
11.536442
...
11.674007
11.710358
11.783797
12.263241
12.122391
12.432593
11.948162
12.127104
12.066296
12.259765
28
200008_s_at
10.676458
10.690479
9.862556
8.386338
8.236503
9.655560
9.618241
8.874053
7.748188
...
7.779491
8.238553
8.077361
9.726048
8.215377
8.102943
8.383057
7.727232
7.818090
10.854761
29
200009_at
12.241562
12.123915
11.613592
11.436513
12.077685
11.656556
11.656313
11.804873
11.717407
...
11.635394
11.511827
11.450963
11.001656
11.963714
11.745106
11.711815
10.430322
10.139406
12.053892
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
22247
AFFX-PheX-3_at
7.587780
7.739597
7.637001
7.572844
7.566232
7.626215
7.597273
7.609240
7.693653
...
7.636286
7.581094
7.677399
7.564076
7.684905
7.730319
7.591921
7.646766
7.617262
7.655340
22248
AFFX-PheX-5_at
7.615105
7.584478
7.455959
7.645467
7.560949
7.619625
7.598112
7.582925
7.627934
...
7.525731
7.579176
7.570382
7.418292
7.732098
7.588400
7.546730
7.637900
7.641483
7.602141
22249
AFFX-PheX-M_at
7.500879
7.558350
7.423706
7.425247
7.467854
7.400606
7.364192
7.400171
7.531035
...
7.510141
7.385669
7.557117
7.408859
7.686879
7.642765
7.437861
7.544820
7.509462
7.375522
22250
AFFX-r2-Bs-dap-3_at
7.415058
7.538497
7.444206
7.537508
7.526306
7.475735
7.457193
7.489438
7.510553
...
7.641837
7.473934
7.497987
7.439749
7.762372
7.470218
7.395558
7.626874
7.440026
7.339268
22251
AFFX-r2-Bs-dap-5_at
7.510356
7.599167
7.576703
7.430549
7.595861
7.407454
7.450202
7.493626
7.640243
...
7.489692
7.520011
7.573883
7.419995
7.758236
7.611355
7.547459
7.573749
7.517581
7.443672
22252
AFFX-r2-Bs-dap-M_at
7.428785
7.492951
7.480116
7.301982
7.369849
7.324410
7.369699
7.345805
7.429821
...
7.307410
7.394087
7.483675
7.442209
7.438441
7.523250
7.365466
7.517269
7.419273
7.410981
22253
AFFX-r2-Bs-lys-3_at
7.541610
7.804846
7.405789
7.458813
7.653536
7.562071
7.451183
7.573437
7.857587
...
7.581681
7.649899
7.749900
7.500011
7.735787
7.835627
7.567267
7.681973
7.696307
7.495174
22254
AFFX-r2-Bs-lys-5_at
7.424384
7.714397
7.318250
7.494257
7.518036
7.493577
7.360679
7.566592
7.668429
...
7.515631
7.450158
7.508255
7.357867
7.726456
7.789662
7.445381
7.663948
7.512095
7.388519
22255
AFFX-r2-Bs-lys-M_at
7.598653
7.533525
7.550970
7.556028
7.639852
7.378454
7.558760
7.513993
7.536908
...
7.759471
7.566438
7.647331
7.538462
8.024200
7.592782
7.435744
7.452174
7.626060
7.519610
22256
AFFX-r2-Bs-phe-3_at
7.588818
7.700379
7.608957
7.617782
7.668815
7.544640
7.420475
7.465998
7.587814
...
7.579117
7.570955
7.700903
7.527279
7.805261
7.738460
7.566220
7.714249
7.558661
7.564291
22257
AFFX-r2-Bs-phe-5_at
7.626531
7.575690
7.474051
7.700783
7.609364
7.330687
7.302846
7.577040
7.630244
...
7.705097
7.578413
7.756379
7.508484
7.899927
7.602541
7.482776
7.755496
7.608196
7.514778
22258
AFFX-r2-Bs-phe-M_at
7.491488
7.581517
7.428292
7.495536
7.631848
7.480835
7.453392
7.509254
7.501456
...
7.597136
7.554519
7.478137
7.444631
7.700423
7.555826
7.438705
7.460913
7.608836
7.501917
22259
AFFX-r2-Bs-thr-3_s_at
7.576096
7.616859
7.621567
7.633570
7.607185
7.675595
7.595108
7.778257
7.824489
...
7.665649
7.608371
7.698390
7.623490
7.792992
7.790727
7.587139
7.693699
7.539833
7.562464
22260
AFFX-r2-Bs-thr-5_s_at
7.728724
7.708178
7.608102
7.591521
7.683940
7.517711
7.579549
7.641952
7.686149
...
7.659568
7.594628
7.740366
7.635615
7.985159
7.910271
7.584600
7.754253
7.666207
7.649350
22261
AFFX-r2-Bs-thr-M_s_at
7.586706
7.730064
7.519281
7.657503
7.557744
7.527900
7.502069
7.569939
7.534255
...
7.508732
7.479604
7.536840
7.606430
7.901393
7.671241
7.452707
7.548825
7.389860
7.605472
22262
AFFX-r2-Ec-bioB-3_at
10.184430
9.529309
8.619244
10.147914
8.838657
8.555512
8.452804
8.597299
8.768882
...
9.190201
8.810104
8.790299
9.860041
9.168162
9.268455
8.586246
9.029980
8.885536
10.091491
22263
AFFX-r2-Ec-bioB-5_at
9.998544
9.456845
8.516449
9.808780
8.703090
8.361782
8.357288
8.425705
8.778259
...
9.107011
8.799799
8.807281
9.658986
9.130400
9.104295
8.460702
8.724103
8.768013
9.928022
22264
AFFX-r2-Ec-bioB-M_at
9.886580
9.316752
8.414869
9.810127
8.594883
8.288756
8.271467
8.283263
8.720208
...
8.906124
8.707507
8.462430
9.729706
8.889075
9.032003
8.428403
8.866616
8.680978
10.030972
22265
AFFX-r2-Ec-bioC-3_at
9.496804
10.373924
9.122523
9.469340
9.079933
8.593055
8.660188
8.902277
9.101185
...
9.508558
9.213596
9.361792
9.247763
9.475856
9.678426
8.899431
9.424195
9.112191
9.572530
22266
AFFX-r2-Ec-bioC-5_at
9.791266
10.589859
9.408320
9.824942
9.469546
8.960363
9.020998
9.076730
9.407147
...
9.819895
9.604219
9.799778
9.653474
9.793151
10.135800
9.191924
9.603816
9.369659
10.024467
22267
AFFX-r2-Ec-bioD-3_at
12.953441
12.664495
10.985948
12.976145
11.643625
11.059735
11.240215
10.678759
11.696586
...
12.190513
12.099303
11.631617
13.011969
12.132080
11.715813
11.564594
11.437572
11.593778
13.032810
22268
AFFX-r2-Ec-bioD-5_at
12.661458
12.620283
10.741545
12.682194
11.454273
10.980560
10.843183
10.394221
11.313661
...
11.888910
12.019156
11.254002
12.499611
11.828679
11.341177
11.334232
11.093700
11.469527
12.721535
22269
AFFX-r2-P1-cre-3_at
14.346964
14.126229
13.314945
14.450152
13.692042
13.304899
13.486599
12.848590
13.609245
...
13.908696
13.938217
13.516265
14.690593
13.816831
13.493863
13.490274
13.326792
13.702848
14.523304
22270
AFFX-r2-P1-cre-5_at
14.085980
13.808825
13.040669
14.181299
13.383539
12.818351
12.867753
12.499426
13.264427
...
13.662149
13.547378
13.314796
14.407109
13.565362
13.300146
12.954981
13.003925
13.351522
14.308021
22271
AFFX-ThrX-3_at
7.642534
7.676568
7.645716
7.607399
7.644112
7.667333
7.561026
7.579219
7.733833
...
7.692174
7.644974
7.750016
7.645419
7.866301
7.810828
7.567872
7.703038
7.648424
7.679152
22272
AFFX-ThrX-5_at
7.631033
7.542400
7.455327
7.540580
7.566635
7.543538
7.455010
7.436875
7.456654
...
7.611665
7.523678
7.454592
7.464096
7.792424
7.527578
7.494294
7.534673
7.519013
7.507123
22273
AFFX-ThrX-M_at
7.501928
7.610702
7.495555
7.614399
7.472724
7.444107
7.438042
7.424471
7.599155
...
7.550857
7.478097
7.575058
7.438450
7.684441
7.549105
7.424649
7.584892
7.525257
7.490484
22274
AFFX-TrpnX-3_at
7.513615
7.633015
7.515081
7.546858
7.547228
7.525382
7.396986
7.511896
7.630086
...
7.598619
7.590259
7.718625
7.468810
7.863286
7.591056
7.523585
7.703311
7.504957
7.483636
22275
AFFX-TrpnX-5_at
7.567607
7.427258
7.534118
7.453376
7.448552
7.526502
7.432864
7.508867
7.492580
...
7.532869
7.484638
7.444738
7.487153
7.535606
7.609732
7.415789
7.611814
7.523121
7.502138
22276
AFFX-TrpnX-M_at
7.561439
7.654442
7.551581
7.494555
7.597676
7.508101
7.503649
7.559667
7.629655
...
7.596008
7.595698
7.743632
7.567720
8.060336
7.605666
7.532778
7.542190
7.611075
7.470764
22277 rows × 799 columns
In [6]:
sample_raw_data_df.shape
Out[6]:
(22277, 799)
In [ ]:
Content source: LeeYiFang/Carkinos
Similar notebooks: