def test_set_params(self):
tbl = self.table
mean_imp = Imputer(Imputer.MEAN)
mode_imp = Imputer(Imputer.MODE)
dtree = DecisionTree(target='Origin', nominals=nominals, inputs=inputs)
pipe = Pipeline([mean_imp, mode_imp, dtree])
out = pipe.fit(tbl).score(tbl)
self.assertEqual(out.loc['Target'], 'Origin')
# Set extra parameters on Pipeline (not on estimator)
pipe.set_params({dtree.target: 'MSRP'})
self.assertEqual(dtree.target, 'Origin')
out = pipe.fit(tbl).score(tbl)
self.assertEqual(out.loc['Target'], 'MSRP')
# Set parameters during fit
pipe = Pipeline([mean_imp, mode_imp, dtree])
out = pipe.fit(tbl).score(tbl)
self.assertEqual(out.loc['Target'], 'Origin')
out = pipe.fit(tbl, {dtree.target: 'MSRP'}).score(tbl)
self.assertEqual(out.loc['Target'], 'MSRP')
def test_basic(self):
tbl = self.table
mean_imp = Imputer(Imputer.MEAN)
mode_imp = Imputer(Imputer.MODE)
dtree = DecisionTree(target='Origin', nominals=nominals, inputs=inputs)
pipe = Pipeline([mean_imp, mode_imp, dtree])
model = pipe.fit(tbl)
self.assertEqual(model.__class__.__name__, 'PipelineModel')
self.assertEqual(len(model.stages), 3)
self.assertTrue(model[0] is mean_imp)
self.assertTrue(model[1] is mode_imp)
self.assertEqual(model[2].__class__.__name__, 'DecisionTreeModel')
out = model.score(tbl)
self.assertEqual(
set(list(out.index)),
set([
'Target', 'Level', 'Var', 'NBins', 'NObsUsed', 'TargetCount',
'TargetMiss', 'PredCount', 'PredMiss', 'Event', 'EventCount',
'NonEventCount', 'EventMiss', 'AreaUnderROCCurve', 'CRCut',
'ClassificationCutOff', 'KS', 'KSCutOff',
'MisClassificationRate'
]))
# Bad item type
with self.assertRaises(TypeError):
Pipeline([mean_imp, mode_imp, 'foo', dtree])
def test_regression_score(self):
tbl = self.table
mean_imp = Imputer(Imputer.MEAN)
mode_imp = Imputer(Imputer.MODE)
dtree = DecisionTree(target='MSRP', nominals=nominals, inputs=inputs)
pipe = Pipeline([mean_imp, mode_imp, dtree])
model = pipe.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_multiple_estimators(self):
tbl = self.table
mean_imp = Imputer(Imputer.MEAN)
mode_imp = Imputer(Imputer.MODE)
dtree1 = DecisionTree(target='Origin',
nominals=nominals,
inputs=inputs)
dtree2 = DecisionTree(target='Origin',
nominals=nominals,
inputs=inputs)
pipe = Pipeline([mean_imp, mode_imp, dtree1, dtree2])
model = pipe.fit(tbl)
self.assertEqual(model.__class__.__name__, 'PipelineModel')
self.assertEqual(len(model.stages), 4)
self.assertTrue(model[0] is mean_imp)
self.assertTrue(model[1] is mode_imp)
self.assertEqual(model[2].__class__.__name__, 'DecisionTreeModel')
self.assertEqual(model[3].__class__.__name__, 'DecisionTreeModel')
out = model.score(tbl)
self.assertEqual(set(list(out.index)),
set(['DecisionTree', 'DecisionTree1']))
def test_unload(self):
mean_imp = Imputer(Imputer.MEAN)
mode_imp = Imputer(Imputer.MODE)
dtree = DecisionTree(target='MSRP', nominals=nominals, inputs=inputs)
pipe = Pipeline([mean_imp, mode_imp, dtree])
model = pipe.fit(self.table)
self.assertEqual(model[-1].data.table.tableexists().exists, 1)
model.unload()
self.assertEqual(model[-1].data.table.tableexists().exists, 0)
def test_model_transform(self):
tbl = self.table
mode_imp = Imputer(Imputer.MODE)
dtree = DecisionTree(target='Origin', nominals=nominals, inputs=inputs)
pipe = Pipeline([mode_imp, dtree])
self.assertEqual(tbl.nmiss().max(), 2)
model = pipe.fit(tbl)
out = model.transform(tbl)
self.assertEqual(out.__class__.__name__, 'CASTable')
self.assertEqual(tbl.nmiss().max(), 2)
self.assertEqual(out.nmiss().max(), 0)
def test_classification_score(self):
tbl = self.table
mean_imp = Imputer(Imputer.MEAN)
mode_imp = Imputer(Imputer.MODE)
dtree = DecisionTree(target='Origin', nominals=nominals, inputs=inputs)
pipe = Pipeline([mean_imp, mode_imp, dtree])
model = pipe.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))