Gradient Boosting (GB)

Machine Learning with Tree-Based Models in Python

Elie Kawerk

Data Scientist

Gradient Boosted Trees

  • Sekvenční oprava chyb předchůdce.

  • Neupravuje váhy trénovacích instancí.

  • Každý prediktor je trénován na reziduálních chybách předchůdce.

  • Gradient Boosted Trees: jako základní learner se používá CART.

Machine Learning with Tree-Based Models in Python

Gradient Boosted Trees pro regresi: trénování

Trénování GBT

Machine Learning with Tree-Based Models in Python

Zmenšování (Shrinkage)

GBT – rychlost učení

Machine Learning with Tree-Based Models in Python

Gradient Boosted Trees: predikce

  • Regrese:

    • $y_{pred} = y_1 + \eta r_1 + ... + \eta r_N$
    • V sklearn: GradientBoostingRegressor.

  • Klasifikace:

    • V sklearn: GradientBoostingClassifier.
Machine Learning with Tree-Based Models in Python

Gradient Boosting v 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)
Machine Learning with Tree-Based Models in Python
# 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
Machine Learning with Tree-Based Models in Python

Pojďme si procvičit!

Machine Learning with Tree-Based Models in Python

Preparing Video For Download...