Python中的随机森林算法与实战

import numpy as np
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.ensemble import RandomForestClassifier

class IrisRandomForest:
    def __init__(self, n_estimators=100, max_depth=None, random_state=42):
        """初始化随机森林分类器"""
        self.n_estimators = n_estimators
        self.max_depth = max_depth
        self.random_state = random_state
        self.model = RandomForestClassifier(
            n_estimators=self.n_estimators, 
            max_depth=self.max_depth, 
            random_state=self.random_state
        )

    def load_data(self):
        """加载Iris数据集并拆分为训练集和测试集"""
        iris = load_iris()
        X_train, X_test, y_train, y_test = train_test_split(
            iris.data, iris.target, test_size=0.3, random_state=self.random_state
        )
        return X_train, X_test, y_train, y_test

    def train(self, X_train, y_train):
        """训练模型"""
        self.model.fit(X_train, y_train)

    def evaluate(self, X_test, y_test):
        """评估模型性能"""
        predictions = self.model.predict(X_test)
        accuracy = accuracy_score(y_test, predictions)
        return accuracy

if __name__ == "__main__":
    rf_classifier = IrisRandomForest(n_estimators=100, max_depth=5)
    X_train, X_test, y_train, y_test = rf_classifier.load_data()
    rf_classifier.train(X_train, y_train)
    accuracy = rf_classifier.evaluate(X_test, y_test)
    print(f"分类模型的准确率: {accuracy:.2f}")

from sklearn.datasets import fetch_california_housing
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_squared_error

class HousingPricePredictor:
    def __init__(self, n_estimators=100, max_depth=None, random_state=42):
        """初始化随机森林回归模型"""
        self.n_estimators = n_estimators
        self.max_depth = max_depth
        self.random_state = random_state
        self.model = RandomForestRegressor(
            n_estimators=self.n_estimators, 
            max_depth=self.max_depth, 
            random_state=self.random_state
        )

    def load_data(self):
        """加载房价数据并拆分为训练集和测试集"""
        data = fetch_california_housing()
        X_train, X_test, y_train, y_test = train_test_split(
            data.data, data.target, test_size=0.3, random_state=self.random_state
        )
        return X_train, X_test, y_train, y_test

    def train(self, X_train, y_train):
        """训练模型"""
        self.model.fit(X_train, y_train)

    def evaluate(self, X_test, y_test):
        """评估模型性能"""
        predictions = self.model.predict(X_test)
        mse = mean_squared_error(y_test, predictions)
        return mse

if __name__ == "__main__":
    predictor = HousingPricePredictor(n_estimators=100, max_depth=10)
    X_train, X_test, y_train, y_test = predictor.load_data()
    predictor.train(X_train, y_train)
    mse = predictor.evaluate(X_test, y_test)
    print(f"回归模型的均方误差: {mse:.2f}")