train_test_split = int(0.7*len(iris_data))
X = X_data.iloc[:train_test_split, :]
X_test = X_data.iloc[train_test_split:, :]
y = y_data.iloc[:train_test_split]
y_test = y_data.iloc[train_test_split:]
# Training and Testing
for criteria in ['information_gain', 'gini_index']:
tree = DecisionTree(criterion=criteria, max_depth=3)
# Build Decision Tree
tree.fit(X, y)
#Predict
y_hat = tree.predict(X)
y_test_hat = tree.predict(X_test)
tree.plot()
print('Criteria :', criteria)
print('Train Accuracy: ', accuracy(y_hat, y))
print('Test Accuracy: ', accuracy(y_test_hat, y_test))
# Precesion and Recall for each class
for cls in y.unique():
print("Class =",cls)
print('Precision: ', precision(y_test_hat, y_test, cls))
print('Recall: ', recall(y_test_hat, y_test, cls))
####################################################################################
# 5 fold cross-validation
acc = 0
for i in range(5):
# 70:30 train test split
train_test_split = int(0.7*data.shape[0])
X = data.iloc[:train_test_split, :-1]
X_test = data.iloc[train_test_split:, :-1]
y = data.iloc[:train_test_split, -1]
y_test = data.iloc[train_test_split:, -1]
maxdepth = 4
# Building Decesion Tree based on my model
criteria = 'information_gain'
mytree = DecisionTree(criterion=criteria, max_depth=maxdepth) #Split based on Inf. Gain
mytree.fit(X, y)
mytree.plot()
print("My Model")
y_hat = mytree.predict(X)
print("Train Scores:")
print('\tRMSE: ', rmse(y_hat, y))
print('\tMAE: ', mae(y_hat, y))
y_test_hat = mytree.predict(X_test)
print("Test Scores:")
print('\tRMSE: ', rmse(y_test_hat, y_test))
print('\tMAE: ', mae(y_test_hat, y_test))
###################################################################################
# Building Decesion Tree based on sklearn