def setUp(self):
"""
Setup internal parameters used multiple times.
"""
# Create decision with tree with a gain ratio
# Create decision tree with leaf pure termination criteria
dt_1 = DT.ClassificationDecisionTree(
split_type='gain_ratio',
terminate='pure',
)
dt_2 = DT.ClassificationDecisionTree(
split_type='gini',
terminate='pure',
)
# Make simple input data
self.x_data_1 = np.array([[1, 1], [2, 1], [3, 1], [4, 1], [5, 1],
[6, 2], [7, 2], [8, 2], [9, 2], [10, 2]])
self.y_data_1 = np.array([0, 1, 1, 0, 1, 0, 1, 1, 0, 1])
# Train the data
dt_1.fit(self.x_data_1, self.y_data_1)
dt_2.fit(self.x_data_1, self.y_data_1)
# Get the result object
self.result_tree_1 = dt_1.get_tree()
self.result_tree_2 = dt_2.get_tree()
def setUp(self):
"""
Setup internal parameters used multiple times.
"""
# Create decision with leaf size as 1
self.leaf_terminate_1 = 1
self.dt_1 = DT.ClassificationDecisionTree(
split_type='gini',
terminate='leaf',
leaf_terminate=self.leaf_terminate_1)
# Create decision tree with leaf size as 2
self.leaf_terminate_2 = 2
self.dt_2 = DT.ClassificationDecisionTree(
split_type='gini',
terminate='leaf',
leaf_terminate=self.leaf_terminate_2)
# Create decision tree with leaf pure termination criteria
self.dt_3_pure = DT.ClassificationDecisionTree(
split_type='gini',
terminate='pure',
)
# Make simple input data
self.x_data_1 = np.array([[1, 4], [6, 7], [1, 4], [2, 3], [4, 5],
[1, 5], [3, 6], [1, 4], [3, 1], [8, 9]])
self.y_data_1 = np.array([0, 1, 1, 0, 1, 0, 1, 1, 0, 1])
# Train the data
self.dt_1.fit(self.x_data_1, self.y_data_1)
self.dt_2.fit(self.x_data_1, self.y_data_1)
self.dt_3_pure.fit(self.x_data_1, self.y_data_1)
def setUp(self):
"""
Setup internal parameters used multiple times.
"""
# Create decision with tree with a gain ratio
self.dt_w_prune = DT.ClassificationDecisionTree(
split_type='gain_ratio', terminate='pure', prune=True)
self.dt_wo_prune = DT.ClassificationDecisionTree(
split_type='gain_ratio', terminate='pure', prune=False)
# Make simple input data
x_data_1 = np.array([[1]] * 2 + [[2]] * 3)
y_data_1 = np.array([0, 1, 0, 1, 1])
# Train the data
self.dt_w_prune.fit(x_data_1, y_data_1)
self.dt_wo_prune.fit(x_data_1, y_data_1)
def __get_tree(self, x, y):
"""
Create a decision tree based upon self._num_trees.
:param x: The x data to fit to (input)
:paray y: The y data to fit to (target)
:return: A new CDT
"""
dt = DT.ClassificationDecisionTree(self._split_type,
self._terminate,
self._leaf_terminate,
prune=False)
dt.fit(x, y)
return dt
def test_data_intake_classification(self):
"""
Test the classification can intake the data in different formats and predict same result.
"""
# Setup y data
y_data_train = np.array([0, 1, 1, 0, 1, 0, 1, 1, 0, 1])
y_data_true = np.array([1, 0, 1])
y_series_train = pd.Series(y_data_train)
y_matrix_train = np.asmatrix(y_data_train)
# Classification tree
class_tree = DT.ClassificationDecisionTree(split_type='gini',
terminate='leaf',
leaf_terminate=1)
# Test different inputs and assertions
class_tree.fit(self.x_df_train, y_series_train)
self.assertEqual(list(class_tree.predict(self.x_df_test)),
list(y_data_true))
class_tree.fit(self.x_matrix_train, y_matrix_train)
self.assertEqual(list(class_tree.predict(self.x_matrix_test)),
list(y_data_true))
