更新 function.py

function.py

@@ -1,106 +1,28 @@
-import numpy as np
-from sklearn.preprocessing import StandardScaler
+def train_logreg(X, y, random_state=42):
+    model = LogisticRegression(solver='liblinear', random_state=random_state)
+    model.fit(X, y)
+    return model
 
-"""
-请在这里填写学号和姓名，不填写即成绩无效。
-"""
-id = "202210423224"
-name = "吴杨洋"
 
-def sigmoid(z):
-    """
-    Sigmoid 激活函数。
-    """
-    return 1 / (1 + np.exp(-z))
+def predict_logreg(inX, model):
+    return int(model.predict([inX])[0])
 
-def train_logreg(X, y, numIter=1000, learning_rate=0.01, lambda_reg=0.01):
-    m, n = X.shape
-    weights = np.zeros(n)
-    for j in range(numIter):
-        for i in range(m):
-            z = np.dot(X[i], weights)
-            h = sigmoid(z)
-            error = y[i] - h
-            gradient = X[i] * error
-            reg_term = lambda_reg * weights
-            gradient += reg_term
-            weights += learning_rate * gradient
-    return weights
-
-def predict_logreg(inX, weights):
-    """
-    对率回归预测函数。
-
-    Args:
-    - inX (numpy array): 输入待分类的样本。
-    - weights (numpy array): 训练得到的权重。
-
-    Returns:
-    - int: 预测的分类标签。
-    """
-    z = np.dot(inX, weights)
-    prob = sigmoid(z)
-    return 1 if prob >= 0.5 else 0
 
 def load_data(filepath):
-    """
-    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。
-
-    Args:
-    - filepath (str): 数据文件路径。
-
-    Returns:
-    - X (np.array): 特征数据。
-    - y (np.array): 标签数据。
-    """
-    file = open(filepath)
-    fr = file.readlines()
-    data_list = []
-    y = []
-    for data in fr:
-        data = data.strip()
-        data = data.split(' ')
-        data_25 = data[24]
-        y.append(data[22])
-        del data[-1]
-        del data[26]
-        del data[25]
-        del data[24]
-        del data[22]
-        del data[2]
-        for i in data_25:
-            data.append(i)
-        data = [0 if data_elem == '?' else float(data_elem) for data_elem in data]
-        data_list.append(data)
-    data_number = len(y)
-    y_train = np.array([1 if y[j] == '2' or y[j] == '3' else 0 for j in range(data_number)])
-    X = np.array(data_list)
-    return X, y_train  # 不在这里添加偏置项
-
-def 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")
-
-    # 创建标准化器实例
+    data = np.genfromtxt(filepath, delimiter=' ', missing_values='?', filling_values=0)
+    labels = data[:, -1].astype(int)
+    data = data[:, :-1]
+    labels = np.where((labels == 2) | (labels == 3), 0, labels)
+    if data.shape[1] >= 3:
+        data = np.delete(data, 2, axis=1)
     scaler = StandardScaler()
+    data = scaler.fit_transform(data)
+    return data, labels
 
-    # 标准化特征数据
-    X_train = scaler.fit_transform(X_train)
-    X_test = scaler.transform(X_test)
+    # 去掉不相关特征
+    data = np.delete(data, [2] + list(range(23, 28)), axis=1)
 
-    # 添加偏置项
-    X_train = np.insert(X_train, 0, 1, axis=1)  # 训练集
-    X_test = np.insert(X_test, 0, 1, axis=1)  # 测试集
-
-    # 训练对率回归模型
-    weights = train_logreg(X_train, y_train, numIter=1000, learning_rate=0.01, lambda_reg=0.1)
-
-    # 测试单个数据
-    y_pred_test = [predict_logreg(x, weights) for x in X_test]
-    accuracy_test = np.mean(y_pred_test == y_test)
-    print(f"Test Accuracy: {accuracy_test:.2f}")
-
-if __name__ == "__main__":
-    main()
+    # 数据标准化
+    scaler = StandardScaler()
+    data = scaler.fit_transform(data)
+    return data, labels