更新 function.py

function.py

@@ -24,67 +24,83 @@ import numpy as np
 id = "202210423222"
 name = "邓龙树"
 
+# user_code.py
+
 import numpy as np
 
-def load_data(filepath):
+def sigmoid(z):
+    """计算sigmoid函数"""
+    return 1 / (1 + np.exp(-z))
+
+def train_logreg(X, y, learning_rate=0.01, iterations=1000):
     """
-    从文件中加载数据。
+    对率回归训练函数。
 
     Args:
-    - filepath (str): 数据文件路径。
-
+    - X (numpy array): 特征数据。
+    - y (numpy array): 标签数据。
+    - learning_rate (float): 学习率，默认值为0.01。
+    - iterations (int): 迭代次数，默认值为1000。
+    
     Returns:
-    - np.array: 特征数据。
-    - np.array: 标签数据。
+    - weights (numpy array): 训练得到的权重。
     """
-    # 读取每一行作为字符串
+    # 初始化权重
+    weights = np.zeros(X.shape[1])
+    
+    # 训练模型
+    for _ in range(iterations):
+        z = np.dot(X, weights)
+        predictions = sigmoid(z)
+        # 计算梯度
+        gradient = np.dot(X.T, (predictions - y)) / y.size
+        # 更新权重
+        weights -= learning_rate * gradient
+    
+    return weights
+
+def predict_logreg(X, weights):
+    """使用训练好的权重预测标签"""
+    z = np.dot(X, weights)
+    predictions = sigmoid(z)
+    return np.where(predictions >= 0.5, 1, 0)
+
+def load_data(filepath):
+    """从文件中加载数据，处理不规则列数问题"""
     with open(filepath, 'r') as file:
         lines = file.readlines()
-
-    # 分割每一行并填充缺失的列
-    max_cols = 0
-    rows = []
+    
+    max_columns = 0
+    data = []
+    
     for line in lines:
-        # 分割每一行
-        cols = line.strip().split(' ')
-        # 记录最大列数
-        max_cols = max(max_cols, len(cols))
-        rows.append(cols)
-
-    # 将所有行填充到相同的列数
-    for row in rows:
-        while len(row) < max_cols:
-            row.append('nan')
-
-    # 转换为numpy数组
-    data = np.array(rows, dtype=float)
-
-    # 用np.nan替换字符串'nan'
-    data[data == 'nan'] = np.nan
-
-    X = data[:, :-1]  # 假设最后一列是标签
-    y = data[:, -1]
-    return X, y
-
+        parts = line.strip().split()
+        max_columns = max(max_columns, len(parts))
+        data.append(parts)
+    
+    # 填充缺失的列
+    for i in range(len(data)):
+        if len(data[i]) < max_columns:
+            data[i].extend(['nan'] * (max_columns - len(data[i])))
+    
+    # 转换成numpy数组，处理缺失值
+    data_array = np.array(data, dtype=float)
+    data_array[np.isnan(data_array)] = np.nanmean(data_array, axis=0)
+    
+    return data_array[:, :-1], data_array[:, -1]
 
+# 主逻辑
 if __name__ == "__main__":
-    # 加载训练集
-    X_train, y_train = load_data("./data/horse-colic.data")
+    # 加载数据
+    X, y = load_data('path_to_data_file.txt')
 
-    # 加载测试集
-    X_test, y_test = load_data("./data/horse-colic.test")
+    # 训练模型
+    weights = train_logreg(X, y)
 
-    # 处理缺失值，例如用列的均值替代
-    X_train = np.nan_to_num(X_train, nan=np.nanmean(X_train, axis=0))
-    X_test = np.nan_to_num(X_test, nan=np.nanmean(X_train, axis=0))  # 用训练集的均值替代测试集
+    # 加载测试数据并预测
+    X_test, y_test = load_data('path_to_test_data_file.txt')
+    predictions = predict_logreg(X_test, weights)
 
-    # 确保标签为浮点型
-    y_train = y_train.astype(float)
-    y_test = y_test.astype(float)
-
-    # 训练对率回归模型
-    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
-
-    # 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]}")
+    # 打印预测结果和实际结果
+    for i in range(min(10, len(y_test))):  # 打印前10个结果或全部结果，取决于测试数据量
+        print(f"预测结果: {predictions[i]}, 实际结果: {y_test[i]}")