Gradient Boosting (GB)

Machine Learning dengan Model Berbasis Pohon di Python

Elie Kawerk

Data Scientist

Gradient Boosted Trees

Koreksi berurutan atas galat model sebelumnya.
Tidak menyesuaikan bobot instance latih.
Tiap prediktor dilatih dengan residual pendahulunya sebagai label.
Gradient Boosted Trees: CART dipakai sebagai learner dasar.

Gradient Boosted Trees untuk Regresi: Pelatihan

Pelatihan GBT

Shrinkage

Laju belajar GBT

Gradient Boosted Trees: Prediksi

Regresi:
- $y_{pred} = y_1 + \eta r_1 + ... + \eta r_N$
- Di sklearn: GradientBoostingRegressor.
Klasifikasi:
- Di sklearn: GradientBoostingClassifier.

Gradient Boosting di sklearn (dataset auto)

# Import models and utility functions
from sklearn.ensemble import GradientBoostingRegressor
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error as MSE

# Set seed for reproducibility
SEED = 1

# Split dataset into 70% train and 30% test
X_train, X_test, y_train, y_test = train_test_split(X,y, 
                                                    test_size=0.3, 
                                                    random_state=SEED)

# Instantiate a GradientBoostingRegressor 'gbt'
gbt = GradientBoostingRegressor(n_estimators=300, max_depth=1, random_state=SEED)


# Fit 'gbt' to the training set
gbt.fit(X_train, y_train)

# Predict the test set labels
y_pred = gbt.predict(X_test)

# Evaluate the test set RMSE
rmse_test = MSE(y_test, y_pred)**(1/2)

# Print the test set RMSE
print('Test set RMSE: {:.2f}'.format(rmse_test))

Test set RMSE: 4.01

Ayo berlatih!

Machine Learning dengan Model Berbasis Pohon di Python