一文彻底搞懂机器学习 - 随机森林（Random Forest） 原创

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


# 加载数据集
data = load_iris()
# 只选择前两个特征
X = data.data[:, :2]
y = data.target


# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)


# 初始化随机森林分类器
clf = RandomForestClassifier(n_estimators=100, random_state=42)


# 训练模型
clf.fit(X_train, y_train)


# 预测
y_pred = clf.predict(X_test)


# 计算准确率
accuracy = accuracy_score(y_test, y_pred)
print(f'Accuracy: {accuracy:.2f}')


# 可视化决策边界（近似）
h = .02  # 网格中的步长
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
                     np.arange(y_min, y_max, h))
Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)


plt.contourf(xx, yy, Z, alpha=0.8)
# 绘制训练样本点
scatter = plt.scatter(X[:, 0], X[:, 1], c=y, edgecolors='k', marker='o')
plt.legend(*scatter.legend_elements(), title="Classes")
plt.xlabel('Feature 1')
plt.ylabel('Feature 2')
plt.title('Random Forest Classification Decision Boundary (Approximation using 2 features)')
plt.show()

import numpy as np
import matplotlib.pyplot as plt
from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_diabetes
from sklearn.metrics import mean_squared_error


# 加载数据集
data = load_diabetes()
X, y = data.data, data.target


# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)


# 初始化随机森林回归器
reg = RandomForestRegressor(n_estimators=100, random_state=42)


# 训练模型
reg.fit(X_train, y_train)


# 预测
y_pred = reg.predict(X_test)


# 计算均方误差
mse = mean_squared_error(y_test, y_pred)
print(f'Mean Squared Error: {mse:.2f}')


# 可视化回归结果
plt.scatter(y_test, y_pred, edgecolors=(0, 0, 0))
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'k--', lw=4)
plt.xlabel('Actual Values')
plt.ylabel('Predicted Values')
plt.title('Random Forest Regression: Actual vs Predicted')
plt.show()

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_iris
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score


# 加载数据集
iris = load_iris()
X, y = iris.data, iris.target


# 为了可视化，我们只选择两个特征
feature_indices = [0, 1]  # 选择前两个特征（花萼长度和花萼宽度）
X_vis = X[:, feature_indices]


# 分割数据集为训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X_vis, y, test_size=0.3, random_state=42)


# 定义随机森林类
class RandomForest:
    def __init__(self, n_estimators=100, max_depth=None, min_samples_split=2, random_state=42):
        self.n_estimators = n_estimators
        self.max_depth = max_depth
        self.min_samples_split = min_samples_split
        self.random_state = random_state
        self.trees = []
        np.random.seed(random_state)


    def fit(self, X, y):
        for _ in range(self.n_estimators):
            # 自助抽样（Bootstrap Sampling）
            indices = np.random.choice(X.shape[0], X.shape[0], replace=True)
            X_sample, y_sample = X[indices], y[indices]


            # 训练决策树
            tree = DecisionTreeClassifier(max_depth=self.max_depth, min_samples_split=self.min_samples_split, random_state=self.random_state)
            tree.fit(X_sample, y_sample)
            self.trees.append(tree)


    def predict(self, X):
        # 对每个样本，收集所有树的预测结果
        tree_preds = np.array([tree.predict(X) for tree in self.trees])


        # 对于分类任务，采用多数投票机制
        majority_votes = np.apply_along_axis(lambda x: np.bincount(x).argmax(), axis=0, arr=tree_preds)
        return majority_votes


# 初始化并训练随机森林
rf = RandomForest(n_estimators=100, max_depth=None, min_samples_split=2, random_state=42)
rf.fit(X_train, y_train)


# 预测测试集
y_pred = rf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print(f'Accuracy: {accuracy:.2f}')


# 可视化决策边界（仅适用于二维数据）
x_min, x_max = X_vis[:, 0].min() - 1, X_vis[:, 0].max() + 1
y_min, y_max = X_vis[:, 1].min() - 1, X_vis[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.01),
                     np.arange(y_min, y_max, 0.01))


# 对网格中的每个点进行预测
Z = rf.predict(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)


# 绘制决策边界和测试数据点
plt.contourf(xx, yy, Z, alpha=0.3)
plt.scatter(X_test[:, 0], X_test[:, 1], c=y_test, edgecolors='k', marker='o', cmap=plt.cm.Paired)
plt.xlabel(iris.feature_names[feature_indices[0]])
plt.ylabel(iris.feature_names[feature_indices[1]])
plt.title('Random Forest Decision Boundaries (2 features)')
plt.show()