更新 function.py

function.py

@@ -1,106 +1,69 @@
-import numpy as np  
+import numpy as np
 
-"""  
+"""
-请在这里填写学号和姓名，不填写即成绩无效。  
+请在这里填写学号和姓名，不填写即成绩无效。
-"""  
+"""
-id = "202210423224"  
+id = "202210423224"
-name = "吴杨洋"  
+name = "吴杨洋"
 
 
-def sigmoid(z):  
+def sigmoid(z):
-    """  
+    return 1 / (1 + np.exp(-z))
-    Sigmoid 激活函数。  
-    """  
-    return 1 / (1 + np.exp(-z))  
 
 
-def train_logreg(X, y, learning_rate=0.01, iterations=1000):  
+def train_logreg(X, y, learning_rate=0.01, iterations=1000):
-    """  
+    m, n = X.shape
-    对率回归训练函数。  
+    weights = np.zeros(n)
-
+    for i in range(iterations):
-    Args:  
+        linear_model = np.dot(X, weights)
-    - X (numpy array): 特征数据。  
+        y_predicted = sigmoid(linear_model)
-    - y (numpy array): 标签数据。  
+        gradient = np.dot(X.T, (y_predicted - y)) / m
-    - learning_rate (float): 学习率，默认为0.01。  
+        weights -= learning_rate * gradient
-    - iterations (int): 迭代次数，默认为1000。  
+    return weights
-
-    Returns:  
-    - weights (numpy array): 训练得到的权重。  
-    """  
-    m, n = X.shape  
-    weights = np.zeros(n)  
-    for i in range(iterations):  
-        linear_model = np.dot(X, weights)  
-        y_predicted = sigmoid(linear_model)  
-        gradient = np.dot(X.T, (y_predicted - y)) / m  
-        weights -= learning_rate * gradient  
-    return weights  
 
 
-def predict_logreg(X, weights):  
+def predict_logreg(inX, weights):
-    """  
+    linear_model = np.dot(inX, weights)
-    对率回归预测函数。  
+    y_predicted = sigmoid(linear_model)
-
+    return 1 if y_predicted > 0.5 else 0
-    Args:  
-    - X (numpy array): 输入待分类的样本。  
-    - weights (numpy array): 训练得到的权重。  
-
-    Returns:  
-    - numpy array: 预测的分类标签。  
-    """  
-    linear_model = np.dot(X, weights)  
-    y_predicted = sigmoid(linear_model)  
-    return (y_predicted > 0.5).astype(int)  
 
 
-def load_data(filepath):  
+def load_data(filepath):
-    """  
+    data = np.genfromtxt(filepath, delimiter=' ', dtype=float)
-    从文件中加载数据，若不自行正确实现，则无法通过评测，不记录成绩。  
+    X = data[:, :-1]
-
+    y = data[:, -1]
-    Args:  
+    return X, y
-    - filepath (str): 数据文件路径。  
-
-    Returns:  
-    - X (np.array): 特征数据。  
-    - y (np.array): 标签数据。  
-    """  
-    # 使用 np.genfromtxt 加载数据，并且忽略文件中不能转换为 float 的行  
-    data = np.genfromtxt(filepath, delimiter=',', dtype=float, filling_values=np.nan)  
-    
-    # 删除所有包含缺失值的行  
-    data = data[~np.isnan(data).any(axis=1)]  
-    
-    # 如果数据仍然是一维的，则将其转换为二维  
-    if data.ndim == 1:  
-        data = np.array([data])  
-    
-    # 确保我们有有效的数据并且是二维的  
-    if data.shape[0] == 0:  # 如果没有数据  
-        raise ValueError("加载的数据为空，请检查输入文件。")  
-    
-    # 假设最后一列为标签  
-    X = data[:, :-1]  # 特征  
-    y = data[:, -1]   # 标签  
-    return X, y  
 
 
-if __name__ == "__main__":  
+def standardize(X):
-    # 加载训练集  
+    mean = X.mean(axis=0)
-    X_train, y_train = load_data("./data/horse-colic.data")  
+    std = X.std(axis=0)
+    return (X - mean) / std, mean, std
 
-    # 加载测试集  
-    X_test, y_test = load_data("./data/horse-colic.test")  
 
-    # 确保训练集和测试集特征数量匹配  
+def main():
-    if X_train.shape[1] != X_test.shape[1]:  
+    # 加载训练集
-        raise ValueError("训练集和测试集特征数量不匹配！")  
+    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  
+    # 标准化特征数据
-    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)  
+    X_train, mean, std = standardize(X_train)
+    X_test = (X_test - mean) / std
 
-    # 测试多个数据  
+    # 训练对率回归模型
-    y_pred = predict_logreg(X_test, weights)  
+    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
-    
+
-    # 输出部分预测结果  
+    # 测试单个数据
-    for i in range(min(10, len(y_pred))):  # 只输出前10个预测结果  
+    correct_predictions = 0
-        print(f"预测结果: {y_pred[i]}, 实际结果: {y_test[i]}")
+    for i in range(X_test.shape[0]):
+        y_pred = predict_logreg(X_test[i], weights)
+        if y_pred == y_test[i]:
+            correct_predictions += 1
+
+    accuracy = correct_predictions / X_test.shape[0]
+    print(f"Accuracy: {accuracy:.2f}")
+
+
+if __name__ == "__main__":
+    main()