随机森林API之泰坦尼克号案例

DecisionTreeClassifier()

RandomForestClassifier(max_depth=6, random_state=22)

param_grid = {
    'n_estimators': [40, 50, 60, 70],  # 树的数量
    'max_depth': [2, 4, 6, 8, 10]      # 最大深度
}

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
from sklearn.feature_extraction import DictVectorizer

# 1. 加载数据
def load_data():
    """加载数据"""
    data = pd.read_csv('data/train.csv')
    print(f"数据形状: {data.shape}")
    return data

# 2. 数据预处理
def preprocess_data(data):
    """数据预处理"""
    # 2.1 提取特征和标签
    X = data[['Pclass', 'Age', 'Sex']]
    y = data['Survived']
    
    # 2.2 缺失值填充（Age列用平均值）
    X = X.copy()
    X['Age'] = X['Age'].fillna(X['Age'].mean())
    
    # 2.3 One-Hot编码（Sex列）
    X_dict = X.to_dict(orient='records')
    transfer = DictVectorizer(sparse=False)
    X_new = transfer.fit_transform(X_dict)
    
    print(f"特征形状: {X_new.shape}")
    print(f"特征名称: {transfer.get_feature_names_out()}")
    
    return X_new, y, transfer

# 3. 划分数据集
def split_data(X, y):
    """划分训练集和测试集"""
    X_train, X_test, y_train, y_test = train_test_split(
        X, y, test_size=0.2, random_state=22
    )
    print(f"训练集: {X_train.shape}")
    print(f"测试集: {X_test.shape}")
    return X_train, X_test, y_train, y_test

# 4. 单一决策树
def train_decision_tree(X_train, X_test, y_train, y_test):
    """单一决策树"""
    print("\n=== 单一决策树 ===")
    dt = DecisionTreeClassifier(random_state=22)
    dt.fit(X_train, y_train)
    
    y_pred = dt.predict(X_test)
    acc = accuracy_score(y_test, y_pred)
    print(f"准确率: {acc:.4f}")
    return dt, acc

# 5. 随机森林
def train_random_forest(X_train, X_test, y_train, y_test):
    """随机森林"""
    print("\n=== 随机森林 ===")
    rf = RandomForestClassifier(
        max_depth=6,
        random_state=22
    )
    rf.fit(X_train, y_train)
    
    y_pred = rf.predict(X_test)
    acc = accuracy_score(y_test, y_pred)
    print(f"准确率: {acc:.4f}")
    return rf, acc

# 6. 网格搜索调参
def grid_search(X_train, X_test, y_train, y_test):
    """网格搜索调参"""
    print("\n=== 网格搜索调参 ===")
    rf = RandomForestClassifier(random_state=22)
    
    # 参数列表
    param_grid = {
        'n_estimators': [40, 50, 60, 70],
        'max_depth': [2, 4, 6, 8, 10]
    }
    
    # 网格搜索
    grid_search = GridSearchCV(
        rf,
        param_grid,
        cv=3,  # 3折交叉验证
        n_jobs=-1  # 使用所有CPU
    )
    
    grid_search.fit(X_train, y_train)
    
    # 最优参数
    print(f"最优参数: {grid_search.best_params_}")
    print(f"最优得分: {grid_search.best_score_:.4f}")
    
    # 最优模型评估
    best_model = grid_search.best_estimator_
    y_pred = best_model.predict(X_test)
    acc = accuracy_score(y_test, y_pred)
    print(f"测试集准确率: {acc:.4f}")
    
    return best_model, acc

# 7. 主函数
def main():
    """主函数"""
    print("=" * 50)
    print("随机森林 - 泰坦尼克号案例")
    print("=" * 50)
    
    # 1. 加载数据
    data = load_data()
    
    # 2. 数据预处理
    X, y, transfer = preprocess_data(data)
    
    # 3. 划分数据集
    X_train, X_test, y_train, y_test = split_data(X, y)
    
    # 4. 单一决策树
    dt, dt_acc = train_decision_tree(X_train, X_test, y_train, y_test)
    
    # 5. 随机森林
    rf, rf_acc = train_random_forest(X_train, X_test, y_train, y_test)
    
    # 6. 网格搜索调参
    best_model, best_acc = grid_search(X_train, X_test, y_train, y_test)
    
    # 7. 对比
    print("\n=== 对比 ===")
    print(f"单一决策树: {dt_acc:.4f}")
    print(f"随机森林: {rf_acc:.4f}")
    print(f"网格搜索后: {best_acc:.4f}")
    
    # 8. 预测新样本
    print("\n=== 预测新样本 ===")
    samples = [
        {'Pclass': 3, 'Age': 25.0, 'Sex': 'male'},
        {'Pclass': 1, 'Age': 30.0, 'Sex': 'female'},
        {'Pclass': 2, 'Age': 35.0, 'Sex': 'male'}
    ]
    
    X_new = transfer.transform(samples)
    predictions = best_model.predict(X_new)
    
    for sample, pred in zip(samples, predictions):
        status = '存活' if pred == 1 else '未存活'
        print(f"{sample}: {status}")

if __name__ == '__main__':
    main()