更新 function.py

function.py

@@ -1,5 +1,8 @@
 # function.py
 import numpy as np
+from sklearn.linear_model import LogisticRegression
+from sklearn.preprocessing import StandardScaler
+from sklearn.model_selection import train_test_split
 
 """
 实验说明:
@@ -25,6 +28,9 @@ id = "202210423204"
 name = "陈垣豪"
 
 
+
+
+
 def load_data(filepath):
     """加载数据并处理缺失值."""
     data = np.genfromtxt(filepath, delimiter=' ', dtype=float, missing_values='?', filling_values=np.nan)
@@ -35,41 +41,32 @@ def load_data(filepath):
     y = data[:, -1]
     return X, y
 
-def train_logreg(X, y, learning_rate=0.01, iterations=1000):
+def train_logreg(X, y):
-    """训练逻辑回归模型，使用随机梯度下降."""
+    """训练逻辑回归模型，使用scikit-learn."""
-    n_samples, n_features = X.shape
+    scaler = StandardScaler()
-    weights = np.zeros(n_features + 1)  # 增加一位用于偏置
+    X_scaled = scaler.fit_transform(X)  # 标准化特征
-    X = np.c_[X, np.ones((n_samples, 1))]  # 增加偏置项
+    model = LogisticRegression()
+    model.fit(X_scaled, y)
+    return model, scaler
 
-    for _ in range(iterations):
+def predict_logreg(model, scaler, inX):
-        random_index = np.random.randint(n_samples)
+    """使用训练好的模型预测结果."""
-        X_i = X[random_index]
+    inX_scaled = scaler.transform(inX.reshape(1, -1))  # 标准化输入数据
-        y_i = y[random_index]
+    return model.predict(inX_scaled)[0]
-
-        linear_model = np.dot(X_i, weights)
-        dw = (linear_model - y_i) * X_i
-        weights -= learning_rate * dw
-
-    return weights
-
-def predict_logreg(inX, weights):
-    """使用线性模型预测结果."""
-    inX = np.append(inX, 1)  # 增加偏置项
-    linear_model = np.dot(inX, weights)
-    return 1.0 if linear_model >= 0 else 2.0
 
 if __name__ == "__main__":
     # 示例：加载数据并训练模型
     X_train, y_train = load_data("./data/horse-colic.data")
-    weights = train_logreg(X_train, y_train, learning_rate=0.001, iterations=5000)
+    model, scaler = train_logreg(X_train, y_train)
 
     # 测试单个数据
     X_test, y_test = load_data("./data/horse-colic.test")
-    y_pred = predict_logreg(X_test[11], weights)
+    y_pred = predict_logreg(model, scaler, X_test[11])
     
     print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
 
 
+
     # 训练逻辑回归模型
     weights = train_logreg(X_train, y_train, learning_rate=0.001, iterations=5000)