Machine Learning with Tree-Based Models in Python__Bagging and Random Forests.py

# -*- coding: utf-8 -*-
"""
Created on Fri Aug  2 18:10:32 2019

@author: z
"""

#####Bagging and Random Forests
### Import DecisionTreeClassifier
from sklearn.tree import DecisionTreeClassifier

# Import BaggingClassifier
from sklearn.ensemble import BaggingClassifier

# Instantiate dt
dt = DecisionTreeClassifier(random_state=1)

# Instantiate bc
bc = BaggingClassifier(base_estimator=dt, n_estimators=50, random_state=1)



###Evaluate Bagging performance
# Fit bc to the training set
bc.fit(X_train, y_train)

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

# Evaluate acc_test
acc_test = accuracy_score(y_pred, y_test)
print('Test set accuracy of bc: {:.2f}'.format(acc_test)) 



###Out of Bag Evaluation：Prepare the ground
# Import DecisionTreeClassifier
from sklearn.tree import DecisionTreeClassifier

# Import BaggingClassifier
from sklearn.ensemble import BaggingClassifier

# Instantiate dt
dt = DecisionTreeClassifier(min_samples_leaf=8, random_state=1)

# Instantiate bc
bc = BaggingClassifier(base_estimator=dt, 
            n_estimators=50,
            oob_score=True,
            random_state=1)



###OOB Score vs Test Set Score
# Fit bc to the training set 
bc.fit(X_train, y_train)

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

# Evaluate test set accuracy
acc_test = accuracy_score(y_pred, y_test)

# Evaluate OOB accuracy
acc_oob = bc.oob_score_

# Print acc_test and acc_oob
print('Test set accuracy: {:.3f}, OOB accuracy: {:.3f}'.format(acc_test, acc_oob))




###Random Forests (RF)：Train an RF regressor
# Import RandomForestRegressor
from sklearn.ensemble import RandomForestRegressor

# Instantiate rf
rf = RandomForestRegressor(n_estimators=25,
            random_state=2)
            
# Fit rf to the training set    
rf.fit(X_train, y_train) 



###Evaluate the RF regressor
# Import mean_squared_error as MSE
from sklearn.metrics import mean_squared_error as MSE

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

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

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



###Visualizing features importances
# Create a pd.Series of features importances
importances = pd.Series(data=rf.feature_importances_,
                        index= X_train.columns)

# Sort importances
importances_sorted = importances.sort_values()

# Draw a horizontal barplot of importances_sorted
importances_sorted.plot(kind='barh', color='lightgreen')
plt.title('Features Importances')
plt.show()



###