def test_predict(self):
ch = hmc.load_shades_class_hierachy()
X, y = hmc.load_shades_data()
dt = hmc.DecisionTreeHierarchicalClassifier(ch)
dt = dt.fit(X, y)
predictions = dt.predict(X)
# One prediction for each observation
self.assertEqual(len(predictions), len(X))
def test_predict(self):
ch = hmc.load_shades_class_hierachy()
X, y = hmc.load_shades_data()
dt = hmc.DecisionTreeHierarchicalClassifier(ch)
dt = dt.fit(X, y)
predictions = dt.predict(X)
# One prediction for each observation
self.assertEqual(len(predictions), len(X))
def setUp(self):
self.ch = hmc.load_shades_class_hierachy()
self.X, self.y = hmc.load_shades_data()
self.X_train, self.X_test, self.y_train, self.y_test = train_test_split(
self.X, self.y, test_size=0.50, random_state=0)
self.dt = hmc.DecisionTreeHierarchicalClassifier(self.ch)
self.dt_nonh = tree.DecisionTreeClassifier()
self.dt = self.dt.fit(self.X_train, self.y_train)
self.dt_nonh = self.dt_nonh.fit(self.X_train, self.y_train)
self.y_pred = self.dt.predict(self.X_test)
self.y_pred_nonh = self.dt_nonh.predict(self.X_test)
def setUp(self):
self.ch = hmc.load_shades_class_hierachy()
self.X, self.y = hmc.load_shades_data()
self.X_train, self.X_test, self.y_train, self.y_test = train_test_split(
self.X, self.y, test_size=0.50, random_state=0)
self.dt = hmc.DecisionTreeHierarchicalClassifier(self.ch)
self.dt_nonh = tree.DecisionTreeClassifier()
self.dt = self.dt.fit(self.X_train, self.y_train)
self.dt_nonh = self.dt_nonh.fit(self.X_train, self.y_train)
self.y_pred = self.dt.predict(self.X_test)
self.y_pred_nonh = self.dt_nonh.predict(self.X_test)
def test_fit(self):
ch = hmc.load_shades_class_hierachy()
X, y = hmc.load_shades_data()
dt = hmc.DecisionTreeHierarchicalClassifier(ch)
dt = dt.fit(X, y)
trees_fit = True
for stage in dt.stages:
if 'tree' not in stage.keys():
trees_fit = False
# After the fit each stage should have a tree
self.assertEqual(trees_fit, True)
def test_fit(self):
ch = hmc.load_shades_class_hierachy()
X, y = hmc.load_shades_data()
dt = hmc.DecisionTreeHierarchicalClassifier(ch)
dt = dt.fit(X, y)
trees_fit = True
for stage in dt.stages:
if 'tree' not in stage.keys():
trees_fit = False
# After the fit each stage should have a tree
self.assertEqual(trees_fit, True)
def test_score(self):
ch = hmc.load_shades_class_hierachy()
X, y = hmc.load_shades_data()
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.50, random_state=0)
dt = hmc.DecisionTreeHierarchicalClassifier(ch)
dt_nonh = tree.DecisionTreeClassifier()
dt = dt.fit(X_train, y_train)
dt_nonh = dt_nonh.fit(X_train, y_train)
accuracy = dt.score(X_test, y_test)
accuracy_nonh = dt_nonh.score(X_test, y_test)
# Hierachical classification should be at least as accurate as traditional classification
self.assertTrue(accuracy >= accuracy_nonh)
def test_score(self):
ch = hmc.load_shades_class_hierachy()
X, y = hmc.load_shades_data()
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.50,
random_state=0)
dt = hmc.DecisionTreeHierarchicalClassifier(ch)
dt_nonh = tree.DecisionTreeClassifier()
dt = dt.fit(X_train, y_train)
dt_nonh = dt_nonh.fit(X_train, y_train)
accuracy = dt.score(X_test, y_test)
accuracy_nonh = dt_nonh.score(X_test, y_test)
# Hierachical classification should be at least as accurate as traditional classification
self.assertTrue(accuracy >= accuracy_nonh)
def test_predict_stages(self):
ch = hmc.load_shades_class_hierachy()
X, y = hmc.load_shades_data()
dt = hmc.DecisionTreeHierarchicalClassifier(ch)
dt = dt.fit(X, y)
def row_is_hierarchical(row):
is_hierarchical = True
for field in range(1, len(row)):
if row[field - 1] not in [ch._get_children(row[field]), row[field - 1]]:
is_hierarchical = False
return is_hierarchical
stage_predictions = dt._predict_stages(X)
stage_predictions['Hierarchical'] = stage_predictions.apply(
lambda row: row_is_hierarchical(row), axis=1)
# Each stage of classification should descend from the previous class
self.assertEqual(len(stage_predictions[stage_predictions['Hierarchical'] != True]), 0)
def test_predict_stages(self):
ch = hmc.load_shades_class_hierachy()
X, y = hmc.load_shades_data()
dt = hmc.DecisionTreeHierarchicalClassifier(ch)
dt = dt.fit(X, y)
def row_is_hierarchical(row):
is_hierarchical = True
for field in range(1, len(row)):
if row[field - 1] not in [
ch._get_children(row[field]), row[field - 1]
]:
is_hierarchical = False
return is_hierarchical
stage_predictions = dt._predict_stages(X)
stage_predictions['Hierarchical'] = stage_predictions.apply(
lambda row: row_is_hierarchical(row), axis=1)
# Each stage of classification should descend from the previous class
self.assertEqual(
len(stage_predictions[stage_predictions['Hierarchical'] != True]),
0)
def test_score_before_fit(self):
ch = hmc.load_shades_class_hierachy()
X, y = hmc.load_shades_data()
dt = hmc.DecisionTreeHierarchicalClassifier(ch)
# Scoring without fitting should raise exception
self.assertRaises(ClassifierNotFitError, dt.score, X, y)
def test_score_before_fit(self):
ch = hmc.load_shades_class_hierachy()
X, y = hmc.load_shades_data()
dt = hmc.DecisionTreeHierarchicalClassifier(ch)
# Scoring without fitting should raise exception
self.assertRaises(ClassifierNotFitError, dt.score, X, y)