Merge pull request #35 from google-research/test_699375108

Correct the performance test so that the CSV data loader in both PNU and PU configurations works properly.

spade_anomaly_detection/data_loader.py

@@ -90,8 +90,10 @@ def load_dataframe(
       'thyroid_labeled',
       'covertype_pu_labeled',
       'drug_train_pu_labeled',
-      'covertype_pnu_10000',
       'covertype_pnu_100000',
+      'covertype_pnu_train',
+      'covertype_pu_train',
+      'covertype_test',
   ]:
     raise ValueError(f'Unknown dataset_name: {dataset_name}')
 

spade_anomaly_detection/example_data/covertype_pnu_10000.csv

@@ -1,4 +1,4 @@
-0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52
+0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,label
 0.8279139569784891,0.6861111111111111,0.36363636363636365,0.4051539012168933,0.5581395348837209,0.4263032176478853,0.6377952755905512,0.984251968503937,0.8622047244094488,0.10065523490868535,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,-1.0
 0.3676838419209604,0.4138888888888889,0.16666666666666669,0.17680744452397995,0.2868217054263566,0.2263594211043979,0.9212598425196851,0.9448818897637795,0.5314960629921259,0.2396486825595985,0.0,0.0,1.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,-1.0
 0.6703351675837917,0.5416666666666667,0.21212121212121213,0.0,0.2235142118863049,0.3918786005339328,0.8543307086614174,0.9881889763779528,0.6496062992125984,0.355778614247874,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,-1.0