Fitting a regression tree

regression_tree_fit.py

# Train test spliting 
from sklearn.model_selection import train_test_split

# Importing the sklearn implementation 
from sklearn.tree import DecisionTreeRegressor

# Precision metrics 
from sklearn.metrics import mean_absolute_error

# Spliting the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=0)

# Defining the hyper parameters 
hps = {
    'max_depth': 3,
    'min_samples_split': 4
}

# Loading the tree object 
tree = DecisionTreeRegressor(**hps)

# Fitting on the training data 
tree.fit(X_train, y_train)

# Predicting the test set
y_pred = tree.predict(X_test)

# Calculating the mean absolute error 
mae_train = mean_absolute_error(y_train, tree.predict(X_train)).round(2)
mae_test = mean_absolute_error(y_test, y_pred).round(2)

print(f"Mean absolute error on training set: {mae_train}")
print(f"Mean absolute error on test set: {mae_test}")