From 99da7c018dd5954a70876d642f35ec9c197cbf56 Mon Sep 17 00:00:00 2001
From: Wojciech Jarmosz <wojciech@jarmosz.com>
Date: Tue, 18 May 2021 23:01:50 +0200
Subject: [PATCH] Add linear regression model and results

---
 .gitignore           |    1 +
 dev-0/out.tsv        | 1000 ++++++++++++++++++++++++++++++++++++++++++
 linear_regression.py |   31 ++
 requirements.txt     |   10 +
 test-A/out.tsv       | 1000 ++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 2042 insertions(+)
 create mode 100644 dev-0/out.tsv
 create mode 100644 linear_regression.py
 create mode 100644 requirements.txt
 create mode 100644 test-A/out.tsv

diff --git a/.gitignore b/.gitignore
index 336d663..529f0d9 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,4 @@
 *~
 *.swp
 *.pyc
+env
\ No newline at end of file
diff --git a/dev-0/out.tsv b/dev-0/out.tsv
new file mode 100644
index 0000000..4399db6
--- /dev/null
+++ b/dev-0/out.tsv
@@ -0,0 +1,1000 @@
+80410
+14322
+51118
+16995
+25183
+79781
+47955
+11525
+-5348
+17010
+27481
+83471
+7797
+4808
+39068
+24877
+63737
+95380
+40459
+8421
+2497
+10570
+-9392
+59446
+-3562
+71090
+81244
+15360
+11942
+40208
+76614
+65294
+7776
+51832
+40765
+61195
+35783
+26024
+43848
+71980
+77624
+32496
+40153
+69066
+15801
+124148
+93563
+14085
+40976
+53155
+75810
+-6564
+98077
+41765
+13460
+-5587
+-2960
+27657
+72048
+24193
+64726
+-8925
+3363
+75068
+84822
+32852
+-5337
+89745
+34209
+4479
+21400
+35265
+22611
+20874
+169567
+46782
+66234
+43113
+70461
+18250
+48572
+24226
+48755
+19503
+19431
+23242
+59861
+42028
+44693
+25439
+43694
+36666
+59022
+46478
+5458
+6491
+66025
+64371
+40569
+31081
+7607
+6288
+13559
+22128
+8439
+28383
+29626
+45634
+65412
+21787
+79593
+-14498
+55480
+61808
+12042
+41735
+13844
+37718
+56878
+28461
+25692
+33897
+-20913
+33176
+67719
+78607
+-19082
+45846
+23663
+48188
+15442
+-6466
+46850
+39803
+-24799
+65169
+100049
+57881
+34365
+64864
+19021
+53339
+71521
+19386
+67976
+54040
+95037
+15784
+11930
+58565
+35678
+20935
+49646
+-35218
+75666
+-13154
+76540
+22045
+59292
+61340
+38301
+70091
+9280
+-421
+4873
+-8520
+44035
+39918
+27468
+83973
+64399
+73001
+21598
+23790
+78001
+39891
+77601
+97771
+82765
+77624
+57324
+35185
+17808
+-10907
+22751
+7463
+82252
+41402
+12474
+25441
+-10949
+43142
+46348
+64696
+4545
+55738
+43309
+60499
+24551
+38337
+102588
+98348
+-2118
+-13743
+21274
+24634
+36541
+66595
+69682
+36123
+27463
+9141
+94112
+45807
+38539
+79229
+51194
+63795
+122222
+57059
+-13502
+34886
+28541
+-7936
+40795
+28506
+2023
+42372
+42319
+55297
+8262
+46122
+28891
+48774
+-102
+6657
+74130
+51447
+15970
+63486
+40606
+26890
+24890
+50662
+38331
+16862
+15377
+45264
+32982
+14488
+56011
+26566
+50166
+75396
+15105
+88256
+34794
+84563
+36182
+23137
+68839
+11294
+22905
+17544
+75223
+28147
+12
+98265
+3732
+20634
+-10490
+25096
+19875
+20927
+70814
+19296
+19249
+149444
+23283
+26375
+122204
+63495
+14787
+17157
+77788
+32937
+82248
+11154
+35952
+59363
+28749
+73774
+42269
+2696
+30354
+38458
+46926
+31848
+31601
+56576
+25729
+13615
+4902
+37858
+15536
+37136
+9413
+54018
+40874
+12366
+6817
+-21553
+27806
+-17378
+71710
+90435
+4267
+29824
+49562
+29217
+47518
+53054
+28060
+19025
+59713
+79927
+21649
+47733
+64419
+33803
+30548
+66436
+7680
+36104
+-5147
+44328
+44973
+33280
+54027
+67065
+132570
+88117
+46440
+69546
+15081
+65688
+16567
+5943
+55711
+43232
+59470
+16812
+49663
+34348
+53332
+67288
+11415
+7962
+56206
+23327
+98506
+44871
+2484
+52022
+55957
+81238
+179270
+70149
+57143
+12422
+33106
+35108
+-20534
+72847
+84523
+44394
+26109
+51094
+79257
+39524
+-14438
+42003
+37555
+53926
+-32
+29253
+21862
+-13394
+28171
+2672
+51003
+72873
+49982
+26045
+10293
+66290
+25307
+71946
+43336
+36044
+52764
+41238
+89361
+62552
+54602
+27821
+1612
+22972
+81753
+83102
+46789
+8493
+22436
+238622
+101140
+123755
+114931
+11719
+46603
+50958
+46409
+69552
+69213
+81237
+62003
+50624
+53645
+-24318
+56315
+44665
+42636
+76503
+59921
+30071
+8114
+75733
+22129
+43575
+29719
+68659
+33170
+60713
+26725
+69984
+64399
+115713
+45056
+99399
+67277
+67991
+65185
+31389
+7921
+21118
+28048
+50302
+12870
+65919
+54141
+34348
+78663
+17170
+28591
+26298
+11788
+40712
+14642
+85698
+46264
+40513
+28665
+19272
+80029
+73494
+25307
+55617
+31379
+23615
+16500
+62209
+-25892
+47405
+24823
+24354
+18844
+28898
+55693
+51212
+36608
+29213
+47261
+51349
+81238
+26208
+20776
+38692
+64426
+44767
+80125
+1418
+65533
+30339
+38348
+29159
+62853
+62396
+67651
+9777
+90185
+33725
+-28633
+106887
+76779
+22186
+196426
+53668
+20215
+49520
+37178
+-27344
+24311
+54037
+107725
+18712
+27476
+95891
+-10095
+95183
+74380
+69729
+61291
+29958
+98517
+15345
+82047
+13459
+71781
+3895
+68185
+45746
+76472
+70358
+31463
+-522
+13655
+6540
+48452
+21200
+69121
+72862
+53251
+57619
+13720
+30357
+20070
+6026
+18511
+-9642
+5139
+55271
+138658
+87248
+4984
+42858
+42955
+-25442
+57774
+20973
+-1709
+2837
+75662
+38286
+95919
+66880
+85506
+57042
+50228
+91832
+31367
+66899
+-3156
+59106
+-18113
+61856
+73403
+15847
+9605
+39437
+67353
+20024
+1248
+25698
+75565
+16789
+49241
+65301
+68921
+129748
+53420
+5720
+28892
+72123
+45560
+64241
+17410
+35750
+14783
+-45085
+26248
+59500
+48483
+19907
+80
+58338
+46505
+44274
+27615
+23818
+55055
+43443
+201641
+18485
+-16156
+58552
+41653
+17495
+41891
+51666
+12237
+73580
+-628
+134770
+91510
+127
+27778
+1182
+31943
+675
+69719
+27013
+42141
+-5269
+23093
+26278
+36395
+23286
+51525
+36019
+61173
+57702
+57628
+24984
+28703
+44814
+63992
+25751
+59102
+90941
+91019
+43865
+54575
+2787
+47255
+27165
+37769
+41292
+19038
+17499
+12015
+90985
+51847
+34356
+9818
+90416
+28048
+36281
+33291
+81097
+32205
+47623
+-34890
+40158
+19170
+119529
+76608
+52509
+67067
+32530
+39479
+-5972
+12381
+13931
+11493
+55250
+48871
+3333
+-15323
+96171
+-468
+72417
+211
+34486
+97899
+43675
+25304
+52378
+61404
+99580
+35457
+-14177
+16163
+-27059
+23126
+54194
+8252
+37064
+-9206
+61546
+129410
+50148
+62257
+983
+43179
+59715
+-2148
+-1092
+56671
+15205
+23850
+-766
+30596
+81036
+106151
+17925
+2842
+84794
+1098
+29001
+21878
+5639
+27765
+23041
+94404
+64512
+720
+50187
+53391
+45518
+57871
+17855
+61013
+-28439
+46730
+76814
+5511
+71709
+45335
+-11533
+-40403
+33312
+14093
+16659
+27512
+110034
+30124
+47260
+30592
+34368
+-32654
+44842
+-23410
+38028
+35564
+39112
+55143
+10586
+-23469
+21379
+43556
+19513
+23776
+40001
+-58294
+63741
+50496
+8120
+74076
+60869
+28961
+14874
+61446
+8438
+-5477
+38317
+174650
+-14201
+22005
+81696
+64399
+20911
+-10685
+10042
+63661
+17100
+25686
+4737
+30614
+38752
+59122
+74645
+-4639
+61789
+76892
+7394
+40876
+28525
+16776
+8696
+80303
+59715
+37858
+30856
+6658
+39325
+27287
+69719
+48219
+-4182
+59713
+93795
+24446
+50100
+54485
+76728
+6107
+46668
+60593
+17087
+-7661
+49759
+24212
+41361
+66560
+41808
+6305
+40368
+34129
+67245
+22086
+24401
+31996
+34786
+30608
+58746
+64334
+60408
+13117
+51525
+23556
+-4981
+22126
+16591
+-7523
+45399
+23377
+-13211
+23421
+23634
+32799
+17677
+72048
+52073
+37792
+38817
+11275
+99581
+45846
+128465
+64386
+76435
+37323
+28341
+63242
+19627
+41980
+82435
+47098
+53037
+98027
+11989
+4968
+28018
+1472
+26655
+41332
+-52729
+40133
+-14910
+61455
+82387
+53407
+30966
+81238
+52
+28730
+42977
+-13967
+19111
+46297
+91251
+62018
+118893
+96772
+63100
+24200
+-13270
+29973
+19163
+27931
+30727
+91974
+81320
+2595
+31789
+74920
+79736
+99063
+37220
+16711
+16850
+61040
+45796
+30905
+58921
+17107
+40176
+68556
+82918
+62729
+58316
+-6056
+-12741
+31002
+90231
+43549
+73982
+65229
+-11211
+8557
+89478
+31576
+38469
+11570
+-4165
+36045
+66443
+71639
+22160
+22254
+22366
+6022
+62019
+41278
+85489
+70189
+21879
+22904
+73886
+76768
+7964
+57887
+75408
+49944
+43781
+50167
+38184
+1121
+77624
+26161
+7938
+47213
+78635
+77433
+6209
+8927
+16241
+69194
+79801
+70350
+41169
+36762
+8160
+47339
+48839
+-25660
+19654
+73326
+75456
+44299
+120124
diff --git a/linear_regression.py b/linear_regression.py
new file mode 100644
index 0000000..d493fae
--- /dev/null
+++ b/linear_regression.py
@@ -0,0 +1,31 @@
+from sklearn.linear_model import LinearRegression
+import pandas as pd
+
+def prepare_data(file, type):
+    data = pd.read_csv(file, header=None, sep="\t")
+    for c in data.select_dtypes(include=object).columns.values:
+        data[c] = data[c].astype("category").cat.codes
+    if type == 'train':
+        data = pd.get_dummies(data, columns=[4])
+    else:
+        data = pd.get_dummies(data, columns=[3])
+    return data
+
+data = prepare_data("./train/train.tsv", "train")
+
+data = data.loc[(data[0] > 1000)]
+
+price = data.iloc[:,0]
+training_data = data.iloc[:,1:]
+
+clf = LinearRegression().fit(training_data, price)
+
+with open('dev-0/out.tsv', 'w') as writer:
+    dev_data = prepare_data('dev-0/in.tsv', "dev")
+    for result in clf.predict(dev_data.iloc[:,0:]):
+        writer.write(str(int(result)) + '\n')
+
+with open('test-A/out.tsv', 'w') as writer:
+    test_data = prepare_data('test-A/in.tsv', "test")
+    for result in clf.predict(test_data.iloc[:,0:]):
+        writer.write(str(int(result)) + '\n')
\ No newline at end of file
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..f9a4c95
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,10 @@
+joblib==1.0.1
+numpy==1.20.3
+pandas==1.2.4
+python-dateutil==2.8.1
+pytz==2021.1
+scikit-learn==0.24.2
+scipy==1.6.3
+six==1.16.0
+sklearn==0.0
+threadpoolctl==2.1.0
diff --git a/test-A/out.tsv b/test-A/out.tsv
new file mode 100644
index 0000000..93d8b27
--- /dev/null
+++ b/test-A/out.tsv
@@ -0,0 +1,1000 @@
+26157
+27555
+13839
+-7723
+-2132
+22592
+41965
+21547
+120156
+51129
+-27560
+46371
+-3668
+32466
+-23123
+-5269
+47201
+68436
+37206
+17003
+61732
+20411
+-3724
+45983
+7150
+27237
+39819
+38463
+78053
+30008
+43817
+23655
+25128
+12421
+72325
+15805
+55162
+47654
+72747
+38991
+11697
+53460
+38874
+71281
+67499
+35575
+40226
+10662
+29661
+44138
+42675
+87889
+14490
+49094
+-1763
+34218
+67701
+34208
+73689
+99661
+23059
+81924
+67268
+29432
+63425
+71133
+-3853
+-978
+44000
+81238
+53093
+95380
+31177
+79768
+48517
+21858
+24450
+17196
+88506
+31612
+19482
+47269
+65524
+48210
+43307
+78086
+88489
+20038
+35191
+50234
+15561
+62633
+76465
+48705
+22613
+76030
+23887
+11668
+67611
+41702
+77788
+57900
+8214
+30129
+34157
+70957
+58284
+5291
+46665
+20990
+28506
+1925
+61815
+19099
+7208
+81123
+2818
+79020
+-7896
+48039
+23722
+14970
+37107
+224
+16541
+18839
+31427
+5520
+63404
+45993
+24309
+19179
+37698
+9569
+112758
+76679
+31155
+49091
+55517
+33534
+38937
+30515
+45686
+-19052
+35561
+25420
+123830
+47183
+35459
+12563
+62677
+76453
+75774
+31115
+-5560
+121094
+47701
+28410
+43728
+26770
+24155
+19504
+58638
+-7486
+63361
+47134
+27843
+69077
+46770
+64541
+62897
+3607
+27120
+56489
+59865
+17821
+38529
+62631
+83365
+66107
+47816
+52731
+25664
+98277
+55243
+75066
+36756
+40612
+96333
+24386
+27036
+13394
+5366
+21006
+19207
+12880
+57655
+46860
+11835
+43584
+99972
+29394
+23885
+60417
+79448
+67219
+21799
+12514
+37605
+19681
+26600
+-14099
+26207
+42601
+34882
+4233
+56440
+29914
+42100
+15453
+27577
+14802
+74971
+9739
+-6315
+9063
+-10818
+59384
+16567
+54198
+-30600
+4345
+56583
+65478
+44693
+9937
+49627
+27474
+59981
+55790
+-23894
+32
+63945
+-9471
+21802
+30547
+54008
+121514
+47162
+39780
+21843
+43274
+70887
+60514
+61548
+74010
+19763
+41001
+81238
+91125
+27973
+87394
+71466
+3667
+58424
+34671
+31899
+48323
+13453
+68494
+28685
+9248
+39959
+72744
+-532
+6915
+17191
+21962
+83615
+50265
+45312
+21648
+56160
+48565
+36947
+42799
+59476
+81238
+4012
+44416
+36859
+43175
+38331
+25577
+48358
+14630
+50426
+49833
+30907
+46560
+87913
+38001
+112525
+73527
+96053
+63643
+44557
+5154
+82538
+29695
+40316
+-2423
+57901
+55451
+14322
+67062
+28220
+-10083
+40697
+45502
+71969
+43354
+91899
+20544
+17288
+93326
+36070
+24981
+54216
+12316
+-36320
+6205
+55352
+71630
+61423
+35576
+27676
+-7290
+73952
+67252
+60472
+46756
+43176
+124857
+81237
+13482
+15681
+26855
+90344
+42752
+64486
+58386
+80193
+5823
+42965
+29058
+44023
+15335
+40526
+52759
+63534
+11379
+14186
+29165
+-5593
+41506
+67255
+38671
+33926
+59047
+57643
+133258
+31542
+24377
+27867
+48249
+58072
+64481
+1575
+17983
+83291
+22481
+44068
+41123
+26400
+27283
+31880
+8264
+2883
+2620
+4201
+34848
+51199
+20470
+34984
+46669
+38739
+60054
+61270
+37059
+79620
+-4871
+47808
+51852
+22639
+-2661
+32209
+10269
+21671
+44447
+54275
+56781
+64073
+69465
+60396
+50127
+2077
+71988
+81653
+24549
+55252
+31575
+69984
+11105
+58077
+31304
+37552
+61890
+97787
+42272
+38115
+16657
+64399
+-1520
+9131
+33000
+33325
+95424
+64199
+28941
+98076
+74910
+27279
+-7177
+23718
+61120
+20009
+34104
+48181
+43513
+-24747
+25322
+-31250
+27822
+15957
+67352
+-9593
+26473
+100283
+29137
+24351
+6251
+25062
+18957
+38248
+6951
+42234
+54052
+-17437
+-33904
+47641
+12286
+78013
+37687
+58400
+-1374
+54503
+46338
+17288
+53230
+486
+78394
+127873
+82289
+10167
+95078
+42260
+55249
+46808
+45410
+-16126
+32788
+28384
+24131
+59051
+37314
+33313
+67005
+79122
+53128
+31603
+78265
+9591
+58998
+8250
+19901
+60016
+39667
+-48229
+53592
+72478
+-10315
+84537
+59935
+46142
+133819
+29406
+95380
+19592
+55575
+69200
+42167
+42040
+26086
+108261
+-13012
+7897
+-12719
+-3263
+38898
+18630
+49622
+-28938
+53955
+37477
+29384
+14420
+98948
+81951
+61535
+58485
+44686
+26691
+81238
+53884
+6530
+36330
+33326
+118469
+60044
+41527
+64916
+41138
+98669
+36356
+76617
+54644
+41816
+68261
+26222
+-20607
+30937
+-17384
+16010
+94973
+74272
+69583
+17574
+53768
+75832
+87276
+56541
+9343
+49924
+90831
+28802
+95081
+59652
+-846
+86172
+13267
+8345
+50634
+40776
+-6612
+104233
+29502
+31430
+92401
+-4825
+123329
+8435
+80227
+52901
+174633
+-12376
+-1784
+24111
+35422
+53118
+30384
+14127
+4252
+1905
+43320
+13633
+32675
+35474
+62550
+9492
+61724
+53586
+57490
+94823
+-192
+58331
+10350
+13036
+-9313
+22827
+61722
+33452
+25708
+95246
+12593
+44264
+17523
+-21595
+38841
+76353
+38050
+-8720
+66142
+33652
+58888
+55087
+59482
+34972
+56055
+34698
+89678
+34203
+61957
+42487
+35134
+114412
+24876
+27597
+25859
+-14144
+116170
+7362
+65799
+66825
+51588
+106242
+-11795
+84523
+88562
+10622
+87652
+2668
+59319
+12856
+-65273
+5699
+20373
+41976
+144260
+41191
+-939
+63034
+-11475
+-8104
+39925
+39870
+81099
+74770
+55308
+32149
+34452
+20416
+82976
+19949
+-8354
+44715
+5426
+84949
+41155
+5136
+14676
+25558
+5881
+28692
+35496
+-12888
+3855
+11207
+3677
+81314
+50219
+7996
+83291
+7701
+-31061
+44683
+63980
+79555
+68537
+54798
+4192
+34235
+26029
+93291
+36026
+28953
+55684
+77624
+3263
+15390
+28566
+84591
+91217
+16804
+99062
+804
+73136
+95065
+68013
+4994
+35331
+100000
+28989
+73433
+72101
+8976
+38024
+54719
+39657
+39235
+40541
+67626
+35178
+81238
+39272
+31913
+19418
+9131
+53715
+16274
+32611
+39733
+113
+37020
+11051
+77727
+67752
+59029
+30228
+87904
+11589
+57182
+71190
+76277
+-36829
+42809
+98348
+1606
+50356
+58335
+125075
+41879
+7889
+3220
+71874
+27029
+17900
+87600
+31874
+26040
+593
+66371
+60274
+123307
+50468
+17444
+36644
+47640
+52093
+68192
+-11749
+22351
+46657
+53998
+21320
+27140
+9988
+108767
+18267
+65241
+129
+79782
+23521
+32022
+60327
+6162
+47731
+-10829
+45003
+74654
+25891
+112012
+38036
+46255
+30360
+6797
+83972
+28403
+37603
+50750
+5295
+3355
+61253
+5411
+19855
+116350
+44794
+39736
+8919
+12933
+36932
+-29950
+49221
+72052
+15283
+70806
+43608
+49518
+12379
+17368
+22799
+25469
+65518
+29658
+1010
+23651
+37719
+27389
+30180
+47865
+20981
+50767
+42195
+98405
+22920
+36313
+98076
+-23934
+31942
+59241
+76892
+81871
+22164
+22139
+17048
+23449
+24947
+-12693
+23743
+37921
+67884
+33002
+67948
+34255
+24304
+63677
+4282
+7040
+36154
+19857
+-3987
+83314
+11799
+42680
+9573
+-19696
+-14051
+24258
+-8475
+30137
+98005
+46304
+28414
+6523
+71874
+7095
+68800
+14519
+34115
+31970
+23839
+30257
+63037
+93454
+23393
+73220
+99501
+23202
+78104
+36660
+5278
+1476
+88894
+55601
+40861
+30066
+34636
+-20347
+13416
+14405
+28438
+9079
+-31217
+39519
+31140
+77879
+12157
+35511
+76590
+39063
+28840
+59110
+-23582
+8196
+16509
+66125
+36164
+9309
+44559
+-3212
+69984
+-21415
+38093
+45547
+-4138
+72007
+59098
+693
+46614
+30746
+4744
+31361
+68437
+80791
+-2744
+61970
+10487
+-12135
+37871
+29038
+16652
+7386
+62262
+38400
+14708
+68423
+117840
+82172
+50390
+40514
+44305
+34840
+125953
+19791
+13764
+46250
+55925
+-37100
+46828
+38377
+-11985
+57277
+10123
+1773
+28618
+8588
+16419
+84190
+84518
+25975
+15978
+70830
+70351
+32368
+151715
+4085
+76015
+59633
+48906
+88482