MC3-Project-1-Test-Cases-spr2016
Jump to navigation
Jump to search
These test cases rely on a set of orders files, provided here: File:Mc3p1 data spr2016.zip
learning_test_cases = [ LearningTestCase( description="Test Case 01", group='KNNLearner', inputs=dict( train_file=os.path.join('Data', 'ripple.csv'), test_file=os.path.join('Data', 'testcase01.csv') ), outputs=dict( rmse=6.08094194449e-17, corr=1.0 ) ), LearningTestCase( description="Test Case 01 - Noisy, 4 features", group='KNNLearner', inputs=dict( train_file=os.path.join('Data', 'ripple_noisy.csv'), test_file=os.path.join('Data', 'testcase01_noisy.csv') ), outputs=dict( rmse=0.568574577879, corr=0.61379073821 ) ), LearningTestCase( description="Test Case 03", group='KNNLearner', inputs=dict( train_file=os.path.join('Data', 'ripple.csv'), test_file=os.path.join('Data', 'testcase03.csv') ), outputs=dict( rmse=2.85197162452e-12, corr=1.0 ) ), LearningTestCase( description="Test Case 04", group='KNNLearner', inputs=dict( train_file=os.path.join('Data', 'best4KNN.csv'), test_file=os.path.join('Data', 'testcase04.csv') ), outputs=dict( rmse=0.00240027433274, corr=0.999999987071 ) ), LearningTestCase( description="Test Case 05", group='KNNLearner', inputs=dict( train_file=os.path.join('Data', 'ripple.csv'), test_file=os.path.join('Data', 'testcase05.csv') ), outputs=dict( rmse=0.359438468147, corr=0.838279931481 ) ), LearningTestCase( description="Test Case 06", group='KNNLearner', inputs=dict( train_file=os.path.join('Data', '3_groups.csv'), test_file=os.path.join('Data', 'testcase06.csv'), kwargs={'k': 10} ), outputs=dict( rmse=35.1015004428, corr=-0.208568812714 ) ), LearningTestCase( description="Test Case 07", group='KNNLearner', inputs=dict( train_file=os.path.join('Data', 'ripple.csv'), test_file=os.path.join('Data', 'testcase07.csv') ), outputs=dict( rmse=0.918312680526, corr=-0.119588294412 ) ), LearningTestCase( description="Test Case 08", group='KNNLearner', inputs=dict( train_file=os.path.join('Data', 'ripple.csv'), test_file=os.path.join('Data', 'testcase08.csv') ), outputs=dict( rmse=0.0904271221715, corr=0.988993695858 ) ), LearningTestCase( description="Test Case 09", group='KNNLearner', inputs=dict( train_file=os.path.join('Data', 'simple.csv'), test_file=os.path.join('Data', 'testcase09.csv'), kwargs={'k': 1} ), outputs=dict( rmse=0.0, corr=1.0 ) ), LearningTestCase( description="Test Case 10", group='KNNLearner', inputs=dict( train_file=os.path.join('Data', 'ripple.csv'), test_file=os.path.join('Data', 'testcase10.csv') ), outputs=dict( rmse=1.78531847475, corr=-0.789236317359 ) ), LearningTestCase( description="Test Case 01 - Bagging", group='BagLearner', inputs=dict( train_file=os.path.join('Data', 'ripple.csv'), test_file=os.path.join('Data', 'testcase01.csv') ), outputs=dict( rmse=0.102347955217, corr=0.991328696155 ) ), LearningTestCase( description="Test Case 02 - Bagging", group='BagLearner', inputs=dict( train_file=os.path.join('Data', 'simple.csv'), test_file=os.path.join('Data', 'testcase02.csv') ), outputs=dict( rmse=0.0894427191, corr=0.99966144456 ) ), LearningTestCase( description="Test Case 03 - Bagging", group='BagLearner', inputs=dict( train_file=os.path.join('Data', 'ripple.csv'), test_file=os.path.join('Data', 'testcase03.csv') ), outputs=dict( rmse=1.78531847475, corr=-0.789236317359 ) ), LearningTestCase( description="Test Case 04 - Bagging", group='BagLearner', inputs=dict( train_file=os.path.join('Data', 'best4KNN.csv'), test_file=os.path.join('Data', 'testcase04.csv') ), outputs=dict( rmse=0.0301204201819, corr=0.999997608631 ) ), LearningTestCase( description="Test Case 05 - Bagging", group='BagLearner', inputs=dict( train_file=os.path.join('Data', 'ripple.csv'), test_file=os.path.join('Data', 'testcase05.csv') ), outputs=dict( rmse=0.323579476488, corr=0.867361902312 ) ), LearningTestCase( description="Test Case 06 - Bagging", group='BagLearner', inputs=dict( train_file=os.path.join('Data', '3_groups.csv'), test_file=os.path.join('Data', 'testcase06.csv'), kwargs={'kwargs': {'k': 1}, 'bags': 20, 'boost': False} ), outputs=dict( rmse=35.1014280336, corr=-0.230388246034 ) ), LearningTestCase( description="Test Case 07 - Bagging", group='BagLearner', inputs=dict( train_file=os.path.join('Data', 'ripple.csv'), test_file=os.path.join('Data', 'testcase07.csv'), kwargs={'kwargs': {'k': 3}, 'bags': 20, 'boost': False} ), outputs=dict( rmse=0.912956660467, corr=-0.112955082143 ) ), LearningTestCase( description="Test Case 08 - Bagging", group='BagLearner', inputs=dict( train_file=os.path.join('Data', 'ripple.csv'), test_file=os.path.join('Data', 'testcase08.csv'), kwargs={'kwargs': {'k': 3}, 'bags': 20, 'boost': False} ), outputs=dict( rmse=0.141072888643, corr=0.971258408243 ) ), LearningTestCase( description="Test Case 09 - Bagging", group='BagLearner', inputs=dict( train_file=os.path.join('Data', 'simple.csv'), test_file=os.path.join('Data', 'testcase09.csv'), kwargs={'kwargs': {'k': 1}, 'bags': 20, 'boost': False} ), outputs=dict( rmse=0.0235702260396, corr=0.999957755088 ) ), LearningTestCase( description="Test Case 10 - Bagging, 5 bags", group='BagLearner', inputs=dict( train_file=os.path.join('Data', 'ripple.csv'), test_file=os.path.join('Data', 'testcase10.csv'), kwargs={'kwargs': {'k': 3}, 'bags': 5, 'boost': False} ), outputs=dict( rmse=1.79642483731, corr=-0.73463819703 ) ) ]