notebook.community

Edit and run 





In [1]:



    


import pandas as pd
import numpy as np



    











In [62]:



    


pwd



    


















    
Out[62]:








u'/Users/ganthony/Documents/notebooks/neon/luna16'

















In [63]:



    


df = pd.read_csv('/Users/ganthony/Desktop/predictions9.csv')
df_perfect = pd.read_csv('/Users/ganthony/Documents/evaluationScript/exampleFiles/submission/perfect_submission.csv')



    











In [69]:



    


df_perfect['seriesuid'].loc[13]



    


















    
Out[69]:








'1.3.6.1.4.1.14519.5.2.1.6279.6001.100225287222365663678666836860'

















In [70]:



    


df_perfect.loc[13]



    


















    
Out[70]:








seriesuid      1.3.6.1.4.1.14519.5.2.1.6279.6001.100225287222...
coordX                                                   104.165
coordY                                                  -211.686
coordZ                                                  -227.011
probability                                                    1
Name: 13, dtype: object

















In [80]:



    


df_perfect2 = df_perfect[(df_perfect['seriesuid'] == df['filename'].loc[0])]



    











In [83]:



    


sum(df['filename']==df['filename'].loc[0])



    


















    
Out[83]:








620

















In [81]:



    


df_perfect2



    


















    
Out[81]:











  
    

      
      seriesuid
      coordX
      coordY
      coordZ
      probability
    

  
  
    

      6453
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      -32.557644
      -22.198961
      -215.086481
      0
    

    

      6454
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      92.870000
      16.110000
      -115.810000
      0
    

    

      6455
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      123.491069
      2.980240
      -202.344555
      0
    

    

      6456
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      109.618624
      11.210602
      -127.961579
      0
    

    

      6457
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      59.014300
      15.181310
      -120.080000
      0
    

    

      6458
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      -38.144943
      44.809336
      -276.644144
      0
    

    

      6459
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      -53.284858
      56.858563
      -275.995790
      0
    

    

      6460
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      84.818961
      89.958424
      -174.631405
      0
    

    

      6461
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      -66.562991
      -22.192829
      -177.408871
      0
    

    

      6462
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      100.774655
      -35.013297
      -205.862048
      0
    

    

      6463
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      -28.487734
      -42.213851
      -204.433520
      0
    

    

      6464
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      63.307771
      -3.913908
      -176.632596
      0
    

    

      6465
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      92.442792
      9.261215
      -193.238013
      0
    

    

      6466
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      131.024804
      -68.340102
      -281.485567
      0
    

    

      6467
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      69.592766
      77.164999
      -177.933202
      0
    

    

      6468
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      66.791114
      40.123599
      -187.369461
      0
    

    

      6469
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      114.673472
      37.329904
      -225.713208
      0
    

    

      6470
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      91.318395
      -13.583161
      -163.389057
      0
    

    

      6471
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      87.358201
      -60.743964
      -192.043773
      0
    

    

      6472
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      -44.178623
      51.949368
      -207.204274
      0
    

    

      6473
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      110.933594
      99.446233
      -271.401250
      0
    

    

      6474
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      -66.324328
      -16.590934
      -162.147446
      0
    

    

      6475
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      73.045470
      51.385564
      -141.354717
      0
    

    

      6476
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      -26.377982
      2.239656
      -170.508120
      0
    

    

      6477
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      79.378169
      -1.015675
      -203.566480
      0
    

    

      6478
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      80.062767
      8.502244
      -254.565990
      0
    

    

      6479
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      90.744387
      27.071561
      -95.875218
      0
    

    

      6480
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      -46.086500
      -29.814700
      -232.276000
      0
    

    

      6481
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      -77.548028
      76.477255
      -283.398305
      0
    

    

      6482
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      -55.801403
      49.090214
      -231.027300
      0
    

    

      ...
      ...
      ...
      ...
      ...
      ...
    

    

      6785
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      -6.014112
      55.058761
      -175.747872
      0
    

    

      6786
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      57.162758
      39.078119
      -314.366265
      0
    

    

      6787
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      106.635337
      45.651078
      -197.855556
      0
    

    

      6788
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      -92.751398
      22.623912
      -182.015663
      0
    

    

      6789
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      -9.440754
      10.685435
      -86.286962
      0
    

    

      6790
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      76.024588
      85.649073
      -194.346392
      0
    

    

      6791
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      102.271172
      -6.130424
      -134.563298
      0
    

    

      6792
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      81.848811
      35.204611
      -226.174755
      0
    

    

      6793
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      58.975839
      13.996170
      -195.903392
      0
    

    

      6794
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      84.322029
      45.677255
      -104.455368
      0
    

    

      6795
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      -93.362000
      -4.844120
      -185.180000
      0
    

    

      6796
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      58.621968
      -1.640901
      -106.367456
      0
    

    

      6797
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      83.469201
      41.444611
      -144.193853
      0
    

    

      6798
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      -21.144297
      18.893719
      -209.373544
      0
    

    

      6799
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      -39.644124
      99.785421
      -259.259091
      0
    

    

      6800
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      129.534181
      45.608767
      -158.374577
      0
    

    

      6801
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      -31.601893
      -14.779938
      -94.371540
      0
    

    

      6802
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      107.733082
      18.411353
      -296.253261
      0
    

    

      6803
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      72.378037
      53.502247
      -211.853684
      0
    

    

      6804
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      -34.198125
      20.248542
      -161.368021
      0
    

    

      6805
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      45.125724
      16.920182
      -90.430496
      0
    

    

      6806
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      59.940000
      79.170000
      -288.930000
      0
    

    

      6807
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      64.840000
      11.910000
      -103.140000
      0
    

    

      6808
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      95.670000
      -73.560000
      -260.780000
      0
    

    

      6809
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      87.960000
      2.800000
      -293.860000
      0
    

    

      6810
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      -12.220000
      19.620000
      -258.670000
      0
    

    

      6811
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      -33.240000
      -7.700000
      -213.630000
      0
    

    

      6812
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      79.550000
      77.770000
      -301.600000
      0
    

    

      6813
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      106.880000
      3.500000
      -193.920000
      0
    

    

      6814
      1.3.6.1.4.1.14519.5.2.1.6279.6001.102681962408...
      97.070000
      -63.050000
      -213.630000
      0
    

  



362 rows × 5 columns



















In [ ]:



    






    











In [16]:



    


sum(df['pred'] == df['target']) / float(df.shape[0])



    


















    
Out[16]:








0.98506375710067395

















In [35]:



    


from sklearn.metrics import confusion_matrix, classification_report



    











In [51]:



    


[[tn, fp], [fn, tp]] = confusion_matrix(df['target'], df['pred'], labels=[0, 1])
print classification_report(df['target'], df['pred'], target_names=['Class 0', 'Class 1'])



    


















    






             precision    recall  f1-score   support

    Class 0       1.00      0.99      0.99     75379
    Class 1       0.10      0.85      0.18       142

avg / total       1.00      0.99      0.99     75521


















In [44]:



    


true_negative = sum((df['target']==0) & (df['pred'] == 0))
print true_negative



    


















    






74273

















In [45]:



    


false_negative = sum((df['target']==1) & (df['pred'] == 0))
print false_negative



    


















    






22

















In [46]:



    


true_positive = sum((df['target']==1) & (df['pred'] == 1))
print true_positive



    


















    






120

















In [47]:



    


false_positive = sum((df['target']==0) & (df['pred'] == 1))
print false_positive



    


















    






1106

















In [58]:



    


df2 = df[df['filename']==df['filename'][0]]



    











In [60]:



    


df2[df2['x']==105.0557924]



    


















    
Out[60]:











  
    

      
      filename
      x
      y
      z
      prob
      pred
      target
    

  
  
  




















In [ ]:

Content source: mas-dse-greina/neon

Similar notebooks:

notebook.community | gallery | about