更新 function.py

function.py

@@ -1,8 +1,5 @@
-# function.py
+import os
 import numpy as np
-import pandas as pd
-from sklearn.preprocessing import StandardScaler
-from sklearn.model_selection import train_test_split, KFold
 
 """
 实验说明:
@@ -24,111 +21,84 @@ from sklearn.model_selection import train_test_split, KFold
 """
 请在这里填写学号和姓名，不填写即成绩无效。
 """
-id = "202210423209"
+id = "202210218225"
-name = "万子玉"
+name = "周水源"
+
 
 # 这里写自己的代码实现
+import numpy as np
+from sklearn.metrics import accuracy_score
+
+# 定义sigmoid函数
 def sigmoid(z):
-    return 1.0 / (1 + np.exp(-z))
+    return 1 / (1 + np.exp(-z))
 
-def compute_gradient(X_batch, y_batch, weights, lambda_reg):
+# 训练逻辑回归模型
-    z = np.dot(X_batch, weights)
+def train_logreg(X, y, learning_rate, iterations=1000):
-    h = sigmoid(z)
-    gradient = np.dot(X_batch.T, (h - y_batch)) / len(y_batch)
-    gradient += (lambda_reg / len(y_batch)) * weights  # L2正则化
-    return gradient
-
-def train_logreg(X, y, learning_rate=0.001, iterations=10000, 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()
+    bias = 0
-    best_accuracy = 0
-
     for _ in range(iterations):
-        indices = np.random.permutation(m)
+        z = np.dot(X, weights) + bias
-        X_shuffled = X[indices]
-        y_shuffled = y[indices]
-
-        for j in range(0, m, batch_size):
-            X_batch = X_shuffled[j:j + batch_size]
-            y_batch = y_shuffled[j:j + batch_size]
-            gradient = compute_gradient(X_batch, y_batch, weights, lambda_reg)
-            weights -= learning_rate * gradient
-
-        # 计算训练集准确率
-        train_accuracy = accuracy(X, y, weights)
-        if train_accuracy > best_accuracy:
-            best_accuracy = train_accuracy
-            best_weights = weights.copy()
-
-        # 动态调整学习率
-        if _ % 100 == 0 and train_accuracy > 0.95:  # 达到高准确率时减小学习率
-            learning_rate *= 0.9
-
-    return best_weights
-
-def predict_logreg(X, weights):
-    z = np.dot(X, weights)
         h = sigmoid(z)
-    return np.where(h >= 0.5, 1, 0)
+        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):
-    data, labels = [], []
+    data = []
-    with open(filepath, 'r') as f:
+    with open(filepath, 'r') as file:
-        for line in f:
+        for line in file:
-            line = line.strip().split()
+            cleaned_line = line.strip().replace('?', '0')
-            if len(line) >= 1 and line[-1].isdigit():
+            values = [float(x) for x in cleaned_line.split()]
-                line_data = [0 if x == '?' else float(x) for x in line[:-1]]
+            if values[22] in [2, 3]:
-                data.append(line_data)
+                values[22] = 0
-                labels.append(int(line[-1]))
+            new_values = values[:2] + values[3:23]
-
+            data.append(new_values)
     data = np.array(data)
-    labels = np.array(labels)
+    X = data[:, :-1]
+    y = data[:, -1]
+    return X, y
 
-    # 检查特征数量
+# 寻找最佳学习率
-    num_features = data.shape[1]
+def find_best_learning_rate(X, y, learning_rates, iterations=1000):
+    best_accuracy = 0
+    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
 
-	    # 特征选择:去掉特征3和特征24~28，确保索引有效
-    indices_to_delete = [2]  # 特征3
-    if num_features > 24:  # 确保特征数量足够
-	        indices_to_delete += list(range(24, 27))  # 特征24到27
-
-    # 删除特征
-    data = np.delete(data, indices_to_delete, axis=1)
-
-	    # 将标签二分类化，特征23取值2和3合并为0，其余为1
-    target_variable = np.where((labels == 2) | (labels == 3), 0, 1)
-
-    return data, target_variable
-
-def accuracy(X, y, weights):
-    predictions = predict_logreg(X, weights)
-    return np.mean(predictions == y)
-
-# 其余代码保持不变
 if __name__ == "__main__":
-    # 加载数据
+    X_train, y_train = load_data("./data/horse-colic.data")
-    X, y = load_data("./data/horse-colic.data")
-    
-    # 拆分训练集和验证集
-    X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)
-
-    # 数据归一化
-    scaler = MinMaxScaler()
-    X_train = scaler.fit_transform(X_train)
-    X_val = scaler.transform(X_val)
-
-    # 训练模型
-    final_weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=5000, batch_size=64, lambda_reg=0.1)
-
-    # 验证模型
-    val_accuracy = accuracy(X_val, y_val, final_weights)
-    print(f"验证集的准确率: {val_accuracy:.4f}")
-
-    # 加载测试集
     X_test, y_test = load_data("./data/horse-colic.test")
-    X_test = scaler.transform(X_test)
     
-    # 测试模型
+    # 定义要尝试的学习率列表
-    final_test_accuracy = accuracy(X_test, y_test, final_weights)
+    learning_rates = np.linspace(0.001, 0.1, 50)
-    print(f"最终测试集的准确率: {final_test_accuracy:.4f}")
+    
+    # 寻找最佳学习率
+    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]}")