def q_2_6():
data, test_data, feature_names, class_names = load_titanic_data()
data = preprocess_titanic(data, True)
perm = np.random.RandomState(seed=20).permutation((data.shape[0]))
data = data[perm]
data, valid = data[:800], data[800:]
type_map, categories_map = gen_maps(data)
classifier = DecisionTree(type_map, categories_map, feature_names,
class_names)
classifier.fit(data, 3, 10)
print(classifier)
def test_gini_impurity_2(self):
X = np.array([1, 4, 2, 6])
y = np.array([1, 0, 1, 0])
thresh = 3
gini = DecisionTree.gini_impurity(X, y, thresh)
G_above = 0
G_under = 0
self.assertEqual(gini, 0.5 * G_above + 0.5 * G_under)
def test_information_gain(self):
X = np.array([1, 4, 2, 6])
y = np.array([1, 0, 0, 1])
thresh = 3
gain = DecisionTree.information_gain(X, y, thresh)
H_y = -0.5 * np.log(0.5) * 2
H_above = -0.5 * np.log(0.5) * 2
H_under = -0.5 * np.log(0.5) * 2
self.assertEqual(gain, H_y - 0.5 * H_above - 0.5 * H_under)
def kaggle():
data, test_data, feature_names, class_names = load_titanic_data()
data = preprocess_titanic(data, True)
test = preprocess_titanic(test_data, False)
type_map, categories_map = gen_maps(data)
classifier = DecisionTree(type_map, categories_map)
classifier.fit(data, 4, 10)
predictions = classifier.predict(test)
pred_train = classifier.predict(data)
actual = extract_column(data, 9)
print(error_rate(pred_train, actual))
results_to_csv(predictions.flatten())
"""
def q_2_4():
print("******RUNNING TITANIC DATA SET*****")
data, test_data, feature_names, class_names = load_titanic_data()
data = preprocess_titanic(data, True)
perm = np.random.RandomState(seed=20).permutation((data.shape[0]))
data = data[perm]
data, valid = data[:800], data[800:]
idy = data.shape[1] - 1
type_map, categories_map = gen_maps(data)
classifier = DecisionTree(type_map, categories_map)
classifier.fit(data, 4, 10)
train_predictions = classifier.predict(data)
train_actual = extract_column(data, idy)
valid_predictions = classifier.predict(valid)
valid_actual = extract_column(valid, idy)
print("Decision Tree training Accuracies: ",
error_rate(train_predictions, train_actual))
print("Decision Tree Validation Accuracies: ",
error_rate(valid_predictions, valid_actual))
classifier = RandomForest(300, 300, 2, type_map, categories_map, 20)
classifier.fit(data, 10, 10)
train_predictions = classifier.predict(data)
train_actual = extract_column(data, idy)
valid_predictions = classifier.predict(valid)
valid_actual = extract_column(valid, idy)
print("Random Forest training Accuracies: ",
error_rate(train_predictions, train_actual))
print("Random Forest Validation Accuracies: ",
error_rate(valid_predictions, valid_actual))