From e55373177475eac3e8d985af260daa14964920ae 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 21:13:01 +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 | 120 +++++++++++++++++++++++++++++-----------------------
 1 file changed, 67 insertions(+), 53 deletions(-)

diff --git a/function.py b/function.py
index 5466123..50dab40 100644
--- a/function.py
+++ b/function.py
@@ -1,65 +1,79 @@
-import numpy as np  
+import numpy as np
 
-# 学号和姓名  
-id = "202210423224"  
-name = "吴杨洋"  
+id = "202210423224"
+name = "吴杨洋"
 
-def sigmoid(z):  
-    return 1 / (1 + np.exp(-z))  
+def sigmoid(z):
+    return 1 / (1 + np.exp(-z))
 
-def train_logreg(X, y, num_iter=1000, learning_rate=0.01, lambda_reg=0.01):  
-    m, n = X.shape  
-    weights = np.zeros(n)  
-    
-    for _ in range(num_iter):  
-        z = np.dot(X, weights)  
-        h = sigmoid(z)  
-        error = y - h  
-        
-        # 添加正则化项  
-        gradient = np.dot(X.T, error) / m + lambda_reg * weights / m  
-        weights += learning_rate * gradient  
-        
-    return weights  
+def train_logreg(X, y, numIter=1000, learning_rate=0.01, lambda_reg=0.01):
+    m, n = X.shape
+    weights = np.zeros(n)
+    val_X, val_y = X[:int(0.2*m)], y[:int(0.2*m)]  # Split 20% of data for validation
+    for i in range(numIter):
+        z = np.dot(X, weights)
+        h = sigmoid(z)
+        gradient = np.dot(X.T, (h - y)) / m
+        reg_term = lambda_reg * weights
+        gradient += reg_term / m
+        weights -= learning_rate * gradient
+        # Early stopping
+        if i % 100 == 0:  # Check every 100 iterations
+            val_z = np.dot(val_X, weights)
+            val_h = sigmoid(val_z)
+            val_error = val_h - val_y
+            if np.mean(np.abs(val_error)) < 0.01:  # If the validation error is small enough
+                break
+    return weights
 
-def predict_logreg(X, weights):  
-    probabilities = sigmoid(np.dot(X, weights))  
-    return (probabilities >= 0.5).astype(int)  
+def predict_logreg(inX, weights):
+    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=',', dtype=str, filling_values=np.nan)  
-    # 处理缺失值，转换数据类型  
-    data = np.where(data == '?', np.nan, data).astype(np.float)  
-    data = data[~np.isnan(data).any(axis=1)]  # 删除含有NaN的行  
+def load_data(filepath):
+    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
 
-    # 特征与标签分离  
-    X = np.delete(data, [22, 24, 25, 26, -1], axis=1)  # 删除不需要的列  
-    y = np.array([1 if row[22] in ['2', '3'] else 0 for row in data])  # 生成标签  
-    X = np.insert(X, 0, 1, axis=1)  # 添加偏置项  
+def standardize(X):
+    mean = X.mean(axis=0)
+    std = X.std(axis=0)
+    return (X - mean) / std, mean, std
 
-    return X, y  
+def main():
+    X_train, y_train = load_data("./data/horse-colic.data")
+    X_test, y_test = load_data("./data/horse-colic.test")
 
-def standardize(X):  
-    mean = X.mean(axis=0)  
-    std = X.std(axis=0)  
-    return (X - mean) / std, mean, std  
+    X_train, mean, std = standardize(X_train)
+    X_test = (X_test - mean) / std
 
-def main():  
-    # 加载训练集和测试集  
-    X_train, y_train = load_data("./data/horse-colic.data")  
-    X_test, y_test = load_data("./data/horse-colic.test")  
+    weights = train_logreg(X_train, y_train, numIter=1000, learning_rate=0.01, lambda_reg=0.1)
 
-    # 数据标准化  
-    X_train, mean, std = standardize(X_train)  
-    X_test = (X_test - mean) / std  
+    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}")
 
-    # 训练对率回归模型  
-    weights = train_logreg(X_train, y_train, num_iter=1000, learning_rate=0.01, lambda_reg=0.1)  
-
-    # 测试模型  
-    y_pred_test = predict_logreg(X_test, weights)  
-    accuracy_test = np.mean(y_pred_test == y_test)  
-    print(f"Test Accuracy: {accuracy_test:.2f}")  
-
-if __name__ == "__main__":  
+if __name__ == "__main__":
     main()
\ No newline at end of file