问如何正确应用随机森林？

EN

def classification_model(model, data, predictors, outcome):
    # Fit the model:
    model.fit(data[predictors], data[outcome])

    # Make predictions on training set:
    predictions = model.predict(data[predictors])

    # Print accuracy
    accuracy = metrics.accuracy_score(predictions, data[outcome])
    print("Accuracy : %s" % "{0:.3%}".format(accuracy))

    # Perform k-fold cross-validation with 5 folds
    kf = KFold(data.shape[0], n_folds=5)
    error = []
    for train, test in kf:
        # Filter training data
        train_predictors = (data[predictors].iloc[train, :])

        # The target we're using to train the algorithm.
        train_target = data[outcome].iloc[train]

        # Training the algorithm using the predictors and target.
        model.fit(train_predictors, train_target)

        # Record error from each cross-validation run
        error.append(model.score(data[predictors].iloc[test, :], data[outcome].iloc[test]))

    print("Cross-Validation Score : %s" % "{0:.3%}".format(np.mean(error)))

    # Fit the model again so that it can be refered outside the function:
    model.fit(data[predictors], data[outcome])



outcome_var = 'Sold'
model = RandomForestClassifier(n_estimators=20)
predictor_var = train.drop('Sold', axis=1).columns.values
classification_model(model,train,predictor_var,outcome_var)

#Create a series with feature importances:
featimp = pd.Series(model.feature_importances_, index=predictor_var).sort_values(ascending=False)
print(featimp)

outcome_var = 'Sold'
model = RandomForestClassifier(n_estimators=20, max_depth=20, oob_score = True)
predictor_var = ['fet1','fet2','fet3','fet4']
classification_model(model,train,predictor_var,outcome_var)