<Kaggle > Learn- Intro to Machine Learning (Random Forest)

Random Forest

• A deep tree with lots of leaves might overfit and a shallow tree with few leaves might underfit.

→ Random Forest is an example of models that can lead to better performances.

 

• Random Forest uses many trees, and it makes a prediction by averaging the predictions of each component tree.
• One of the best features of these methods is that they generally work reasonably even without tunings like parameter tunings.

from sklearn.ensemble import RandomFroestRegressor
from sklearn.metrics import mean_absolute_error

forest_model = RandomForestRegressor(random_state=1)
forest_model.fit(train_X, train_y)
melb_preds = forest_model.predict(val_X)
print(mean_absolute_error(val_y, melb_preds))