更新 function.py

function.py

@@ -1,104 +1,51 @@
-import os
 import numpy as np
-
+from sklearn.linear_model import LogisticRegression
-"""
+from sklearn.preprocessing import 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。
-
-测评环境:
-- CPU: Intel Xeon(R) CPU E3-1231 v3 @ 3.40GHz
-- OS: Ubuntu 22.04.4 LTS
-- Python: 3.10.12
-- numpy: 2.1.1
-"""
 
 
-"""
+# 填写学号和姓名
-请在这里填写学号和姓名，不填写即成绩无效。
-"""
 id = "202210218225"
 name = "周水源"
 
+def train_logreg(X, y, random_state=42):
+    model = LogisticRegression(solver='liblinear', random_state=random_state)
+    model.fit(X, y)
+    return model
 
-# 这里写自己的代码实现
+def predict_logreg(inX, model):
-import numpy as np
+    return int(model.predict([inX])[0])
-from sklearn.metrics import accuracy_score
 
-# 定义sigmoid函数
+def load_data(filepath):
-def sigmoid(z):
+    data = np.genfromtxt(filepath, delimiter=' ', missing_values='?', filling_values=0)
-    return 1 / (1 + np.exp(-z))
+    labels = data[:, -1].astype(int)
+    data = data[:, :-1]
+    labels = np.where((labels == 2) | (labels == 3), 0, labels)
+    if data.shape[1] >= 3:
+        data = np.delete(data, 2, axis=1)  
+    scaler = StandardScaler()
+    data = scaler.fit_transform(data)
+    return data, labels
 
-# 训练逻辑回归模型
+# 测试代码
-def train_logreg(X, y, learning_rate, iterations=1000):
+if __name__ == "__main__":
-    m, n = X.shape
+    # 指定数据文件路径
-    weights = np.zeros(n)
+    filepath = "./data/horse-colic.data"
-    bias = 0
-    for _ in range(iterations):
-        z = np.dot(X, weights) + bias
-        h = sigmoid(z)
-        dw = (1/m) * np.dot(X.T, (h - y))
-        db = (1/m) * np.sum(h - y)
-        weights -= learning_rate * dw
-        bias -= learning_rate * db
-    return weights, bias
-
-# 使用逻辑回归模型进行预测
-def predict_logreg(inX, weights, bias):
-    z = np.dot(inX, weights) + bias
-    h = sigmoid(z)
-    return 1 if h >= 0.5 else 0
     
     # 加载数据
-def load_data(filepath):
+    X, y = load_data(filepath)
-    data = []
+    print("数据加载成功。")
-    with open(filepath, 'r') as file:
-        for line in file:
-            cleaned_line = line.strip().replace('?', '0')
-            values = [float(x) for x in cleaned_line.split()]
-            if values[22] in [2, 3]:
-                values[22] = 0
-            new_values = values[:2] + values[3:23]
-            data.append(new_values)
-    data = np.array(data)
-    X = data[:, :-1]
-    y = data[:, -1]
-    return X, y
 
-# 寻找最佳学习率
+    # 训练模型
-def find_best_learning_rate(X, y, learning_rates, iterations=1000):
+    model = train_logreg(X, y)
-    best_accuracy = 0
+    print("模型训练完成。")
-    best_learning_rate = None
-    best_weights = None
-    best_bias = None
-    for rate in learning_rates:
-        weights, bias = train_logreg(X, y, rate, iterations)
-        y_pred = np.array([predict_logreg(x, weights, bias) for x in X])
-        accuracy = accuracy_score(y, y_pred)
-        if accuracy > best_accuracy:
-            best_accuracy = accuracy
-            best_learning_rate = rate
-            best_weights = weights
-            best_bias = bias
-    return best_learning_rate, best_accuracy, best_weights, best_bias
 
-if __name__ == "__main__":
+    # 随机选择一个样本进行预测测试
-    X_train, y_train = load_data("./data/horse-colic.data")
+    sample = X[0]
-    X_test, y_test = load_data("./data/horse-colic.test")
+    actual_label = y[0]
+    predicted_label = predict_logreg(sample, model)
+    print(f"预测结果: {predicted_label}, 实际结果: {actual_label}")
 
-    # 定义要尝试的学习率列表
+    # 计算测试集上的准确率
-    learning_rates = np.linspace(0.001, 0.1, 50)
+    correct_predictions = sum(predict_logreg(X[i], model) == y[i] for i in range(len(y)))
-    
+    accuracy = correct_predictions / len(y)
-    # 寻找最佳学习率
+    print(f"测试集准确率: {accuracy:.2f}")
-    best_learning_rate, best_accuracy, best_weights, best_bias = find_best_learning_rate(X_train, y_train, learning_rates)
-    
-    print(f"最佳学习率: {best_learning_rate}")
-    print(f"最佳准确率: {best_accuracy}")
-    
-    # 使用最佳权重和偏置进行预测
-    y_pred = predict_logreg(X_test[11], best_weights, best_bias)
-    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")