更新 function.py

function.py

@@ -1,5 +1,6 @@
 import numpy as np
-
+from sklearn.preprocessing import StandardScaler
+from sklearn.linear_model import LogisticRegression
 
 """
 实验说明:
@@ -32,43 +33,30 @@ def load_data(filepath):
     
     # 将缺失值填充为每列的平均值
     for i in range(X.shape[1]):
-        X[:, i] = np.where(np.isnan(X[:, i]), np.mean(X[:, i]), X[:, i])
+        X[:, i] = np.where(np.isnan(X[:, i]), np.nanmean(X[:, i]), X[:, i])
     
     return X, y.astype(int)
 
-def scale_features(X):
-    mean = np.mean(X, axis=0)
-    std = np.std(X, axis=0)
-    std[std == 0] = 1
-    scaled_X = (X - mean) / std
-    return scaled_X
+def train_logreg(X, y):
+    scaler = StandardScaler()
+    X_scaled = scaler.fit_transform(X)
     
-def train_logreg(X, y, learning_rate=0.01, iterations=1000, lambda_reg=0.01):
-    m, n = X.shape
-    weights = np.zeros(n)
-    for _ in range(iterations):
-        for i in range(m):
-            x_i = X[i]
-            y_i = y[i]
-            prediction = 1 / (1 + np.exp(-np.dot(x_i, weights)))
-            gradient = x_i * (prediction - y_i)
-            weights -= learning_rate * (gradient + lambda_reg * weights)
-    return weights
+    model = LogisticRegression(solver='liblinear')
+    model.fit(X_scaled, y)
     
-def predict_logreg(inX, weights):
-    prediction = 1 / (1 + np.exp(-np.dot(inX, weights)))
-    return 1 if prediction > 0.5 else 0
+    return model
+
+def predict_logreg(model, inX):
+    prediction = model.predict(inX)
+    return prediction
 
 if __name__ == "__main__":
     X_train, y_train = load_data("./data/horse-colic.data")
     X_test, y_test = load_data("./data/horse-colic.test")
     
-    X_train_scaled = scale_features(X_train)
-    X_test_scaled = scale_features(X_test)
-    
-    weights = train_logreg(X_train_scaled, y_train, learning_rate=0.01, iterations=1000)
+    model = train_logreg(X_train, y_train)
     
     # 测试模型
-    y_pred = [predict_logreg(x, weights) for x in X_test_scaled]
+    y_pred = predict_logreg(model, X_test)
     accuracy = np.mean(y_pred == y_test)
     print(f"Accuracy: {accuracy}")