sklearn中随机森林的使用

1、数据准备与《sklearn中决策树的使用》中相同，这里不再累述、

2、使用步骤

from sklearn.ensemble import RandomForestClassifier
model_RR=RandomForestClassifier()
model_RR.fit(X_train,y_train)

y_prob = model_RR.predict_proba(X_test)[:,1] # This will give you positive class prediction probabilities  
y_pred = np.where(y_prob > 0.5, 1, 0) # This will threshold the probabilities to give class predictions.
model_RR.score(X_test, y_pred)

print('The AUC of default Random Forest is', roc_auc_score(y_test,y_pred))

from sklearn.ensemble import RandomForestClassifier

model_RR=RandomForestClassifier()

tuned_parameters = {'min_samples_leaf': range(1,10,2), 'n_estimators' : range(1,10,2)}

from sklearn.model_selection import GridSearchCV
RR = GridSearchCV(model_RR, tuned_parameters,cv=10)

RR.fit(X_train,y_train)

print(RR.grid_scores_)

print(RR.best_score_)

print(RR.best_params_)

y_prob = RR.predict_proba(X_test)[:,1] # This will give you positive class prediction probabilities  
y_pred = np.where(y_prob > 0.5, 1, 0) # This will threshold the probabilities to give class predictions.
RR.score(X_test, y_pred)

auc_roc=roc_auc_score(y_test,y_pred)
auc_roc