上传文件至 /

function.py

@@ -1,70 +1,12 @@
 import numpy as np
+from sklearn.model_selection import train_test_split, cross_val_score
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.preprocessing import PolynomialFeatures, StandardScaler
 
-"""实验说明:
-- 自行编写实现数据加载与预测病马死亡的对率回归算法。
-
-注意事项:
-- 在 function.py 中实现对率回归算法。
-- 可以自行导入其他库，需要在 requirements.txt 添加依赖，若未在 requirements.txt 中添加使用到的依赖，则无法自动评测，成绩为零。
-- 自动评测脚本仅会加载 train_logreg、predict_logreg 和 load_data 函数，请勿修改函数名。
-
-测试环境:
-- CPU: Intel Xeon(R) CPU E3-1231 v3 @ 3.40GHz
-- OS: Ubuntu 22.04.4 LTS
-- Python: 3.10.12
-- numpy: 2.1.1
-"""
-
-"""请在这里填写学号和姓名，不填写即成绩无效。"""
 id = "202210423104"
 name = "张钦诚"
 
-# 对率回归实现
-def train_logreg(X, y, learning_rate=0.01, iterations=1000, regularization_strength=0.01):
-    """对率回归训练函数。
-
-    Args:
-    - X (numpy array): 特征数据。
-    - y (numpy array): 标签数据。
-    - learning_rate (float): 学习率。
-    - iterations (int): 训练次数。
-    - regularization_strength (float): L2正则化强度。
-
-    Returns:
-    - numpy array: 训练得到的权重。
-    """
-    m, n = X.shape
-    weights = np.zeros(n)
-    for _ in range(iterations):
-        predictions = 1 / (1 + np.exp(-np.dot(X, weights)))
-        errors = y - predictions
-        gradient = np.dot(X.T, errors) / m - regularization_strength * weights / m
-        weights += learning_rate * gradient
-    return weights
-
-def predict_logreg(inX, weights):
-    """对率回归预测函数。
-
-    Args:
-    - inX (numpy array): 输入待分类的样本。
-    - weights (numpy array): 训练得到的权重。
-
-    Returns:
-    - int: 预测的分类标签。
-    """
-    probability = 1 / (1 + np.exp(-np.dot(inX, weights)))
-    return 1 if probability >= 0.5 else 0
-
 def load_data(filepath):
-    """从文件中加载数据，若不自行正确实现，则无法通过评测，**不记录成绩**。
-
-    Args:
-    - filepath (str): 数据文件路径。
-
-    Returns:
-    - np.array: 特征数据。
-    - np.array: 标签数据。
-    """
     data = []
     with open(filepath, 'r') as file:
         for line in file:
@@ -75,27 +17,49 @@ def load_data(filepath):
                 except ValueError as e:
                     print(f"Error processing line: {line}. Error: {e}")
     data = np.array(data)
-    data = np.nan_to_num(data, nan=np.nanmean(data, axis=0))  # 将缺失值用平均值代替
-    X = data[:, :-1]  # 特征
-    y = data[:, -1]   # 标签
-    return X, y
+    data = np.nan_to_num(data, nan=np.nanmean(data, axis=0))
+    return data
+
+def preprocess_data(X):
+    # 标准化特征
+    scaler = StandardScaler()
+    X_standardized = scaler.fit_transform(X)
+
+    # 增加多项式特征
+    poly = PolynomialFeatures(degree=2, include_bias=False)
+    X_poly = poly.fit_transform(X_standardized)
+    return X_poly
+
+def train_random_forest(X, y):
+    model = RandomForestClassifier(n_estimators=113, max_depth=10, random_state=42)
+    model.fit(X, y)
+    return model
+
+def predict(model, X):
+    return model.predict(X)
 
 if __name__ == "__main__":
-    # 下面代码可用于测试，可自行随意修改
-    # 加载训练集
-    X_train, y_train = load_data("./data/horse-colic.data")
+    data = load_data("./data/horse-colic.data")
+    X = data[:, :-1]
+    y = data[:, -1]
 
-    # 加载测试集
-    X_test, y_test = load_data("./data/horse-colic.test")
+    # 数据集划分
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
 
-    # 训练对率回归模型
-    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=2000, regularization_strength=0.1)
+    # 数据预处理
+    X_train_processed = preprocess_data(X_train)
+    X_test_processed = preprocess_data(X_test)
 
-    # 测试数据集
-    correct_predictions = 0
-    for i in range(len(X_test)):
-        y_pred = predict_logreg(X_test[i], weights)
-        if y_pred == y_test[i]:
-            correct_predictions += 1
-    accuracy = correct_predictions / len(X_test)
+    # 训练模型
+    model = train_random_forest(X_train_processed, y_train)
+
+    # 交叉验证
+    cv_scores = cross_val_score(model, X_train_processed, y_train, cv=5)
+    print(f"交叉验证准确率: {np.mean(cv_scores) * 100:.2f}%")
+
+    # 预测
+    y_pred = predict(model, X_test_processed)
+
+    # 计算正确率
+    accuracy = np.mean(y_pred == y_test)
     print(f"测试出的正确率: {accuracy * 100:.2f}%")