更新 function.py

function.py

@@ -2,7 +2,7 @@
 import numpy as np
 import pandas as pd
 from sklearn.impute import SimpleImputer
-from sklearn.preprocessing import MinMaxScaler
+from sklearn.preprocessing import StandardScaler
 from sklearn.model_selection import train_test_split
 from sklearn.metrics import accuracy_score, classification_report
 
@@ -44,11 +44,11 @@ def compute_gradient(X_batch, y_batch, weights, lambda_reg):
     return gradient
 
 # train_logreg函数，用于训练逻辑回归模型
-def train_logreg(X, y, learning_rate=0.001, iterations=10000, batch_size=64, lambda_reg=0.1):
+def train_logreg(X, y, learning_rate=0.01, iterations=1000, batch_size=64, lambda_reg=0.1):
     m, n = X.shape
-    weights = np.random.randn(n) * np.sqrt(2. / n)  # He初始化
+    weights = np.zeros(n)
-    best_weights = weights.copy()
     best_accuracy = 0
+    best_weights = weights.copy()
 
     for i in range(iterations):
         indices = np.random.permutation(m)
@@ -61,22 +61,23 @@ def train_logreg(X, y, learning_rate=0.001, iterations=10000, batch_size=64, lam
             gradient = compute_gradient(X_batch, y_batch, weights, lambda_reg)
             weights -= learning_rate * gradient
 
+        # 计算训练集准确率
         accuracy = accuracy_score(y, predict_logreg(X, weights))
         if accuracy > best_accuracy:
             best_accuracy = accuracy
             best_weights = weights.copy()
 
-        if i % 1000 == 0:  # 每1000次迭代调整学习率
+        # 动态调整学习率
-            if best_accuracy > 0.95:  # 如果达到高准确率，则减小学习率
+        if i % 100 == 0 and accuracy > 0.95:  # 达到高准确率时减小学习率
-                learning_rate *= 0.9
+            learning_rate *= 0.9
 
     return best_weights
 
 # predict_logreg函数，用于使用训练好的权重进行预测
-def predict_logreg(X, weights):
+def predict_logreg(inX, weights):
-    z = np.dot(X, weights)
+    linear_output = np.dot(inX, weights)
-    h = sigmoid(z)
+    probability = sigmoid(linear_output)
-    return np.where(h >= 0.5, 1, 0)
+    return np.where(probability > 0.5, 1, 0)
 
 # preprocess_data函数，用于预处理数据
 def preprocess_data(X, y):
@@ -107,22 +108,24 @@ def load_data(filepath):
 def main():
     X, y = load_data("./data/horse-colic.data")
     if X is not None:
-        # 分割数据集为训练集和验证集
+        # 分割数据集为训练集和测试集
-        X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)
+        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
         
-        # 数据归一化
+        # 特征缩放
-        scaler = MinMaxScaler()
+        scaler = StandardScaler()
         X_train = scaler.fit_transform(X_train)
-        X_val = scaler.transform(X_val)
+        X_test = scaler.transform(X_test)
         
         # 训练模型
-        weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=5000, batch_size=64, lambda_reg=0.1)
+        weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000, batch_size=64, lambda_reg=0.1)
         
-        # 验证模型
+        # 预测测试集
-        y_pred = predict_logreg(X_val, weights)
+        y_pred = predict_logreg(X_test, weights)
-        val_accuracy = accuracy_score(y_val, y_pred)
+        
-        print(f"验证集的准确率: {val_accuracy:.4f}")
+        # 计算准确率
-        print(classification_report(y_val, y_pred))
+        accuracy = accuracy_score(y_test, y_pred)
+        print(f"准确率: {accuracy}")
+        print(classification_report(y_test, y_pred))
 
 if __name__ == "__main__":
     main()