Random Forest with RandomSearch

Question

Im trying to create a Random Forest model with RandomSearch but am getting an error pertaining to Invalid parameter learning_rate

Here's the error,

ValueError: Invalid parameter learning_rate for estimator RandomForestClassifier(max_depth=1100, n_estimators=300). 
Check the list of available parameters with `estimator.get_params().keys()`.

Code:

from sklearn.model_selection import RandomizedSearchCV
model = RandomForestClassifier()
param_vals = {'max_depth': [200, 500, 800, 1100], 'n_estimators': [100, 200, 300, 400],
              'learning_rate': [0.001, 0.01, 0.1, 1, 10]}
random_rf = RandomizedSearchCV(estimator=model, param_distributions=param_vals,
                              n_iter=10, scoring='accuracy', cv=5,
                              refit=True, n_jobs=-1)
random_rf.fit(X_train,y_train)
rf_prediction = random_rf.predict(X_test)

rf_predprobability = random_rf.predict_proba(X_test)

#Random search execute
print("accuracy score:")
print(accuracy_score(y_test, rf_prediction))
print("Accuracy on training set: {:.2f}".format(random_rf.score(X_train, y_train))) 
print("Accuracy on test set: {:.2f}".format(random_rf.score(X_test, y_test)))

I can't figure out why the error is showing. Can anyone tell me why I am getting this error?

Answer 1

The error means that RandomForestClassifier does not take learning_rate as parameter. Removing 'learning_rate': [0.001, 0.01, 0.1, 1, 10] from the param_vals variable will fix the issue.