From 130bec1f67d06915c804b9e5a7d87641e617ed3d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=90=B4=E6=9D=A8=E6=B4=8B?= <2445091977@qq.com>
Date: Sat, 2 Nov 2024 21:28:08 +0800
Subject: [PATCH] =?UTF-8?q?=E6=9B=B4=E6=96=B0=20function.py?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 function.py | 111 ++++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 90 insertions(+), 21 deletions(-)

diff --git a/function.py b/function.py
index f8da889..f189af5 100644
--- a/function.py
+++ b/function.py
@@ -12,31 +12,100 @@ def sigmoid(z):
     Sigmoid 激活函数。
     """
     return 1 / (1 + np.exp(-z))
-def train_logreg(X, y, random_state=42):
-    model = LogisticRegression(solver='liblinear', random_state=random_state)
-    model.fit(X, y)
-    return model
 
 
-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):
-    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
+    """
+    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。
 
-    # 去掉不相关特征
-    data = np.delete(data, [2] + list(range(23, 28)), axis=1)
+    Args:
+    - filepath (str): 数据文件路径。
 
-    # 数据标准化
-    scaler = StandardScaler()
-    data = scaler.fit_transform(data)
-    return data, labels
\ No newline at end of file
+    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)
+    X_train = np.insert(X, 0, 1, axis=1)  # 添加偏置项
+    return X_train, y_train
+
+
+def standardize(X):
+    mean = X.mean(axis=0)
+    std = X.std(axis=0)
+    return (X - mean) / std, mean, std
+
+
+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")
+
+    # 标准化特征数据
+    X_train, mean, std = standardize(X_train)
+    X_test = (X_test - mean) / std
+
+    # 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()
\ No newline at end of file