Adding pipeline.py

dev-0/expected.tsv

@@ -0,0 +1,462 @@
+373000
+299000
+365000
+369000
+483791
+430000
+312000
+397000
+302672
+325000
+302800
+300495
+375038
+437131
+373761
+337567
+359320
+326407
+294819
+266000
+355720.5
+288000
+239000
+385000
+349000
+804500
+520000
+315441
+339000
+429000
+325000
+269000
+420000
+400000
+420000
+385000
+617232
+399000
+328338
+596232
+339000
+293000
+289000
+330000
+499000
+419000
+219598
+341670
+351259
+319000
+211426
+309000
+299000
+349000
+508000
+270000
+333750
+724120
+485000
+274000
+242775
+415125
+269000
+535000
+497000
+357124
+830000
+675000
+399000
+550000
+245000
+219598
+365000
+435000
+254231
+359000
+485000
+469758
+382740
+499000
+279000
+283080
+298200
+339000
+239900
+341145
+310000
+369000
+327000
+259000
+1308456
+434358
+449000
+293000
+203000
+273000
+175000
+368938
+299000
+415000
+333000
+345000
+350000
+297987
+290696.04
+293571
+459000
+355000
+269000
+345000
+300000
+1156756
+242943.1
+486600
+305370
+318240
+340000
+316000
+300500
+335000
+227000
+399000
+1100000
+389000
+370000
+659000
+249000
+555000
+315205
+349000
+385000
+397005
+469000
+490000
+316900
+254500
+280000
+294588
+275000
+369000
+857514
+560000
+310000
+596232
+459000
+238000
+440000
+499000
+327104
+650000
+235000
+338200
+412000
+329000
+609631
+309000
+250000
+469000
+311122
+450000
+299000
+499000
+330400
+295000
+315500
+254500
+467700
+393750
+530000
+270000
+297987
+360400
+337567
+380000
+568600
+322010
+490824
+269548
+361745
+359371
+579900
+340000
+199000
+255000
+255000
+245000
+303204
+290000
+349000
+360000
+350000
+469064
+280000
+417000
+318032
+579000
+320000
+382060
+379000
+420000
+250000
+211500
+254280
+383000
+355696
+249000
+359000
+429000
+605000
+325949
+340000
+420000
+579215
+304900
+380000
+229000
+325000
+675000
+409000
+355000
+388447.5
+345015
+199000
+320292
+300841
+313000
+566999
+275000
+359371
+253000
+262000
+230000
+299000
+399000
+453040
+479000
+312000
+1100000
+308196
+355000
+336842
+248100
+352894
+242000
+330000
+315000
+299900
+454000
+325000
+499900
+369000
+429000
+244500
+661650
+357475
+321165
+330000
+404900
+1240000
+696000
+295000
+295000
+417000
+242300
+285000
+980000
+229000
+259786
+447496.2
+239617.2
+260000
+387000
+799000
+238638
+354944
+521683
+506600
+506363
+299000
+844990
+213000
+324900
+261000
+349000
+480000
+283000
+430000
+259786
+339000
+299000
+530000
+396683
+329000
+420863
+299000
+276458
+350286
+515000
+341670
+369000
+322000
+761976.07
+389000
+459999
+429000
+425000
+286000
+270000
+561636.5
+550625
+324836
+221976
+699000
+579000
+514000
+282000
+345000
+534508
+299000
+545000
+250000
+379000
+269000
+299000
+329000
+249976
+430000
+303086
+303000
+238400
+339000
+241500
+1100000
+399000
+530000
+972000
+359000
+250000
+329460
+239000
+490110
+468120
+378157
+285000
+235850
+499000
+235850
+365428
+670000
+320000
+279000
+388000
+324990
+570000
+348796
+287144
+272000
+267877
+255062
+650000
+364000
+530000
+570000
+284000
+339000
+435000
+280000
+1300000
+365428
+295000
+360000
+205000
+319000
+736450
+453040
+280500
+299000
+330000
+337110
+520000
+395000
+595000
+375000
+358575
+588000
+1025455
+245000
+238500
+1167400
+249000
+441000
+239000
+455000
+640000
+344250
+400000
+485000
+543617
+276000
+428400
+360315
+595000
+595000
+535000
+534600
+330000
+627810
+439000
+304945
+699000
+712164
+250000
+449000
+284859
+595350
+259000
+590000
+355000
+389000
+429000
+649000
+297987
+159761
+505505
+336676
+272764
+343876
+336290.5
+308035
+335226.5
+532317
+525937.5
+397720
+702150
+592020
+671488
+593000
+399000
+1800000
+288728
+393211
+789325
+453040
+345015
+519745
+400920
+2318580
+469728
+247154
+328828.5
+260927.5
+482729
+257328.5
+305923.5
+529623
+641395.58
+669606.91
+655544.02
+471397.97
+309958
+699000
+850000

dev-0/out.tsv

@@ -0,0 +1,106 @@
+438785.2913972244
+439057.23099919874
+386274.2118016632
+386722.31769914605
+366094.3344721196
+516777.10211508814
+468621.88667045534
+349948.5366470157
+444966.9443439897
+349657.9314571674
+281814.65768045397
+380230.24610083
+533761.0395582682
+284298.6286792335
+302760.82473539945
+294494.6957395293
+303626.5505932587
+584528.6660046072
+784700.0575206266
+752671.6754240954
+516071.1433928942
+416107.9319851352
+381330.4301660287
+588211.6199853121
+480981.67140597175
+484859.78185138875
+311068.7302960584
+315949.9297491256
+257801.58826774202
+142550.63848562422
+362860.87012622226
+388171.5324259206
+478092.2326986545
+328405.01758869365
+380134.098031612
+381587.1579842053
+288324.8145994118
+432696.6726767714
+318130.32826012623
+435187.4588356118
+424704.3103526968
+354259.9454763391
+390066.9031165759
+352230.25542972225
+262434.35465128557
+286093.8046546493
+278652.1534394977
+305132.6744196697
+379476.8952788627
+523803.4038821715
+472164.2783154694
+557197.9049793513
+385707.6208490075
+249770.74994324776
+447297.85237721645
+473926.4254470614
+551525.0612915668
+455249.75394877745
+277287.1035815221
+377954.25547762506
+265071.3019075517
+390541.15477277193
+340022.347779955
+331980.58217403764
+247821.5699980029
+335310.7744164435
+426980.41512499726
+424797.4845629018
+505361.1298279477
+460097.1617031188
+284709.2873732758
+335647.83233635745
+270052.19102661626
+290966.45832854987
+279396.1721889902
+323414.4972144816
+727959.0986630493
+390603.4021630825
+340741.933773114
+264762.50193169154
+403417.3623101625
+392590.4807311653
+387039.147268873
+276373.95325510646
+298303.8143283458
+779346.0980894796
+290662.80052611313
+353715.6417229106
+303551.4737648836
+668522.8530199206
+398220.6541869035
+339215.5191208159
+394305.8946513819
+355238.0213504333
+310163.81687300355
+348995.790840848
+65517.75407795762
+306231.0218035679
+325183.35496851837
+652223.7740641477
+251438.3009618289
+488597.6679408548
+653295.0728505378
+704240.8981666869
+387418.8114984069
+649756.6035774458

pipeline.py

@@ -0,0 +1,21 @@
+import csv
+import model_training as mt
+import pandas as pd
+import price_evaluation as pe
+
+def eval(filename_in, filename_out):
+    data_eval = pd.read_table(filename_in, delimiter='\t', header=None)
+    data_eval.rename(columns={0: 'stan', 1: 'czynsz', 2: 'x3', 3: 'cenazam', 4: 'link', 5: 'pietro', 6: 'x7', 7: 'metraz', 8: 'rynek', 9: 'liczba pokoi', 10: 'budynek', 11: 'x12', 12: 'x13', 13: 'x14', 14: 'x15', 15: 'x16', 16: 'x17', 17: 'x18', 18: 'x19', 19: 'x20', 20: 'x21', 21: 'x22', 22: 'x23', 23: 'x24', 24: 'x25'}, inplace=True)
+
+    data_eval.drop(['x3','cenazam','link','pietro','budynek','x7','x12','x13','x14','x15','x16','x17','x18','x19','x20','x21','x22','x23','x24','x25'], inplace=True, axis=1)
+    data_eval['czynsz'] = data_eval['czynsz'].str.extract('(\d+)')
+    data_eval['stan'] = data_eval['stan'].map({'do zamieszkania': 2, 'do remontu': 1, 'do wykończenia': 2})
+    data_eval['rynek'] = data_eval['rynek'].map({'wtórny': 0, 'pierwotny': 1})
+    data_eval.dropna(inplace=True)
+    data_eval = data_eval[['stan', 'czynsz', 'liczba pokoi', 'metraz', 'rynek']]
+
+    out = mt.model.predict(data_eval)
+    pd.DataFrame(out).to_csv(filename_out, sep='\t', index=False, header=False)
+
+eval('dev-0/in.tsv', 'dev-0/out.tsv')
+eval('test-A/in.tsv', 'test-A/out.tsv')

test-A/out.tsv

@@ -0,0 +1,101 @@
+355128.4427831349
+334338.4901026813
+529063.9425151651
+455553.4766766229
+297897.73747289146
+355097.23031301657
+593121.4404591958
+224053.5741490908
+500224.3245957352
+309386.0591294997
+362595.45714443433
+297020.13034301443
+392628.7523117415
+390740.85354551824
+417512.4555268084
+255871.19009756995
+303906.69154232735
+430706.6866501465
+388055.513946502
+199553.12140648713
+324437.34934717487
+287716.39837987634
+326783.354171627
+344969.65422220883
+439943.4301322885
+365651.3739072073
+473541.93998109805
+397190.011401333
+339491.08093359147
+361314.0333504934
+906943.1251904051
+379487.3807523678
+330066.353096911
+746684.0270939263
+409639.6845630782
+310685.77511363453
+267903.0399920683
+390741.63975717244
+321296.753898358
+329296.9204894126
+259589.79429047485
+383509.25625372084
+605335.0230421544
+453360.8062374862
+275612.1870547221
+328711.75370610604
+409551.6896071418
+161409.09137445962
+481964.7347708574
+308140.44034038077
+211810.63872246095
+199931.02910046442
+470081.37468967284
+293605.6384494368
+410235.8627761756
+473525.4554782605
+766906.700454194
+304833.8161031428
+291768.67322025984
+246247.99513514055
+228514.897144243
+328736.21085431206
+292199.0189778785
+1774178.7986119075
+371416.8287964024
+331230.87479559705
+334673.1883525122
+380762.55288023036
+472908.3991528695
+1402111.6523221093
+430163.1097101653
+253050.0648098148
+777659.7566094768
+264887.0264718806
+538378.2928022667
+437593.33760668256
+485300.95596167
+586242.5075015154
+514807.9896312915
+510207.3597893864
+353014.32668722013
+462445.0163546961
+271161.07258611044
+325183.35496851837
+338231.7490905717
+365688.57318596356
+335687.09607300966
+258097.40319777536
+589911.7328044499
+332230.7078283557
+469659.0989816049
+242480.32092807116
+430706.6866501465
+330888.9738887339
+695028.778686561
+309179.47218438284
+314151.65667571756
+473926.4254470614
+363344.6070129465
+198848.53877465893
+393844.61698660883