def test_fit(self):
tbl = self.table
params = dtree_defaults.copy()
params.update(
dict(target='Cylinders',
nominals=['Make', 'Model'],
inputs=['Make', 'Model', 'Horsepower']))
dtree = DecisionTree(target='Cylinders',
nominals=['Make', 'Model'],
inputs=['Make', 'Model', 'Horsepower'])
model = dtree.fit(tbl)
self.assertEqual(model.__class__.__name__, 'DecisionTreeModel')
self.assertEqual(model.data.__class__.__name__, 'CASTable')
self.assertEqual(model.params, params)
self.assertEqual(model.diagnostics.__class__.__name__, 'CASResults')
self.assertEqual(sorted(model.diagnostics.keys()),
['ModelInfo', 'OutputCasTables'])
# Have nominals set automatically
dtree = DecisionTree(target='Cylinders',
nominals=[],
inputs=['Make', 'Model', 'Horsepower'])
model = dtree.fit(tbl)
self.assertEqual(model.params['nominals'], [])
def test_unload_model(self):
dtree = DecisionTree(target='Cylinders', inputs=['MSRP', 'Horsepower'])
model = dtree.fit(self.table)
self.assertEqual(model.data.table.tableexists().exists, 1)
with ResourceManager() as mgr:
mgr.track_model(model)
self.assertEqual(model.data.table.tableexists().exists, 0)
def test_unload(self):
dtree = DecisionTree(target='Cylinders',
nominals=['Make', 'Model'],
inputs=['Make', 'Model', 'Horsepower'])
model = dtree.fit(self.table)
self.assertEqual(model.data.table.tableexists().exists, 1)
model.unload()
self.assertEqual(model.data.table.tableexists().exists, 0)
def test_fit(self):
tbl = self.table
params = dtree_defaults.copy()
params.update(dict(target='Origin', nominals=nominals, inputs=inputs))
dtree = DecisionTree(target='Origin', nominals=nominals, inputs=inputs)
model = dtree.fit(tbl)
self.assertEqual(model.__class__.__name__, 'DecisionTreeModel')
self.assertEqual(model.data.__class__.__name__, 'CASTable')
self.assertEqual(model.params, params)
self.assertEqual(model.diagnostics.__class__.__name__, 'CASResults')
self.assertEqual(sorted(model.diagnostics.keys()), ['ModelInfo', 'OutputCasTables'])
def test_params(self):
tbl = self.table
# Check defaults
dtree = DecisionTree()
self.assertEqual(dtree.params.to_dict(), dtree_defaults)
# Check constructor parameters
params = dtree_defaults.copy()
params.update(
dict(prune=True,
target='Cylinders',
nominals=['Make', 'Model'],
inputs=['Make', 'Model', 'Horsepower']))
dtree = DecisionTree(prune=True,
target='Cylinders',
nominals=['Make', 'Model'],
inputs=['Make', 'Model', 'Horsepower'])
self.assertEqual(dtree.params.to_dict(), params)
model = dtree.fit(tbl)
self.assertEqual(model.__class__.__name__, 'DecisionTreeModel')
self.assertEqual(model.params, params)
# Check constructor parameter error
with self.assertRaises(ValueError):
DecisionTree(prune=True,
criterion='foo',
target='Cylinders',
nominals=['Make', 'Model'],
inputs=['Make', 'Model', 'Horsepower'])
with self.assertRaises(TypeError):
DecisionTree(foo='bar')
# Check fit parameter overrides
params = dtree_defaults.copy()
params.update(
dict(max_depth=7,
leaf_size=5,
target='Cylinders',
nominals=['Make', 'Model'],
inputs=['Make', 'Model', 'Horsepower']))
model = dtree.fit(tbl, prune=False, max_depth=7)
self.assertEqual(model.__class__.__name__, 'DecisionTreeModel')
self.assertEqual(model.params, params)
# Check parameter overrides error
with self.assertRaises(TypeError):
dtree.fit(tbl, prune='foo', max_depth=7)
with self.assertRaises(KeyError):
dtree.fit(tbl, foo='bar')
def test_score(self):
tbl = self.table
params = dtree_defaults.copy()
params.update(
dict(target='Cylinders',
nominals=['Make', 'Model'],
inputs=['Make', 'Model', 'Horsepower']))
dtree = DecisionTree(target='Cylinders',
nominals=['Make', 'Model'],
inputs=['Make', 'Model', 'Horsepower'])
model = dtree.fit(tbl)
score = model.score(tbl)
self.assertTrue(isinstance(score, pd.Series))
self.assertAlmostEqual(score.loc['MeanSquaredError'], 0.4423817642)
self.assertEqual(score.loc['NObsUsed'], 426)
self.assertEqual(score.loc['NObsRead'], 428)
def test_regression_score(self):
tbl = self.table
params = dtree_defaults.copy()
params.update(dict(target='MSRP', nominals=nominals, inputs=inputs))
dtree = DecisionTree(target='MSRP', nominals=nominals, inputs=inputs)
model = dtree.fit(tbl)
score = model.score(tbl)
self.assertTrue(isinstance(score, pd.Series))
self.assertEqual(score.loc['Target'], 'MSRP')
self.assertEqual(score.loc['Level'], 'INTERVAL')
self.assertEqual(score.loc['NBins'], 100)
self.assertEqual(score.loc['NObsUsed'], 428)
self.assertTrue(isinstance(score.loc['AverageSquaredError'], float))
self.assertTrue(isinstance(score.loc['AverageAbsoluteError'], float))
self.assertTrue(isinstance(score.loc['AverageSquaredLogarithmicError'], float))
self.assertTrue(isinstance(score.loc['RootAverageSquaredError'], float))
self.assertTrue(isinstance(score.loc['RootAverageAbsoluteError'], float))
self.assertTrue(isinstance(score.loc['RootAverageSquaredLogarithmicError'], float))
def test_classification_score(self):
tbl = self.table
params = dtree_defaults.copy()
params.update(dict(target='Origin', nominals=nominals, inputs=inputs))
dtree = DecisionTree(target='Origin', nominals=nominals, inputs=inputs)
model = dtree.fit(tbl)
score = model.score(tbl)
self.assertTrue(isinstance(score, pd.Series))
self.assertEqual(score.loc['Target'], 'Origin')
self.assertEqual(score.loc['Level'], 'CLASS')
self.assertEqual(score.loc['Event'], 'USA')
self.assertEqual(score.loc['NBins'], 100)
self.assertEqual(score.loc['NObsUsed'], 428)
self.assertTrue(isinstance(score.loc['AreaUnderROCCurve'], float))
self.assertTrue(isinstance(score.loc['CRCut'], float))
self.assertTrue(isinstance(score.loc['KS'], float))
self.assertTrue(isinstance(score.loc['KSCutOff'], float))
self.assertTrue(isinstance(score.loc['MisClassificationRate'], float))
def test_unload(self):
dtree = DecisionTree(target='Origin', nominals=nominals, inputs=inputs)
model = dtree.fit(self.table)
self.assertEqual(model.data.table.tableexists().exists, 1)
model.unload()
self.assertEqual(model.data.table.tableexists().exists, 0)