更新 function.py

function.py

@@ -32,10 +32,9 @@ from sklearn.preprocessing import StandardScaler
 def sigmoid(intX):
     return 1.0 / (1 + np.exp(-intX))
 
-
 def train_logreg(X, y, numIter=150):
     m, n = X.shape
-    weights = np.ones(n)
+    weights = np.zeros(n)  # 初始化权重为0而不是1
     for j in range(numIter):
         dataIndex = list(range(m))
         for i in range(m):
@@ -43,11 +42,10 @@ def train_logreg(X, y, numIter=150):
             randIndex = int(np.random.uniform(0, len(dataIndex)))
             h = sigmoid(np.dot(X[randIndex], weights))
             error = y[randIndex] - h
-            weights = weights + np.dot(alpha * error, X[randIndex])
+            weights = weights + alpha * error * X[randIndex]
             del(dataIndex[randIndex])
     return weights
 
-
 def predict_logreg(X, weights):
     predictions = []
     for x in X:
@@ -55,7 +53,6 @@ def predict_logreg(X, weights):
         predictions.append(1 if prob > 0.5 else 0)
     return predictions
 
-
 def load_data(filepath):
     data = []
     labels = []
@@ -70,29 +67,19 @@ def load_data(filepath):
     data = np.array(data)
     labels = np.array(labels)
     target_variable = labels
-    target_variable[(target_variable == 2) | (target_variable == 3)] = 0
+    target_variable[np.logical_or(target_variable == 2, target_variable == 3)] = 0
     data = np.delete(data, [2] + list(range(23, 28)), axis=1)
     scaler = StandardScaler()
     data = scaler.fit_transform(data)
     return data, target_variable
 
-
 def accuracy(X, y, weights):
     predictions = predict_logreg(X, weights)
     return np.mean(predictions == y)
 
-
-    # 以下代码可用于测试，可自行随意修改
 if __name__ == '__main__':
-    # 加载训练集
-    X_train, y_train = load_data("./data/horse-colic.data")
-
-    # 加载测试集
-    X_test, y_test = load_data("./data/horse-colic.test")
-
-    # 训练对率回归模型
-    weights = train_logreg(X_train, y_train)
-
-    # 测试单个数据
-    y_pred = predict_logreg(X_test[11], weights)
-    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
+    X_train, y_train = load_data("./horse-colic.data")
+    X_test, y_test = load_data("./horse-colic.test")
+    final_weights = train_logreg(X_train, y_train)
+    final_accuracy = accuracy(X_test, y_test, final_weights)
+    print(f"最终测试集的准确率: {final_accuracy:.4f}")