From 02e212bb5358bf0187beab669a7a51ad40e40dc1 Mon Sep 17 00:00:00 2001
From: zhangchenghong <1598349064@qq.com>
Date: Sat, 2 Nov 2024 14:22:12 +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 | 31 +++++++++++++++++++++++++------
 1 file changed, 25 insertions(+), 6 deletions(-)

diff --git a/function.py b/function.py
index 66bf6ad..fefc3f3 100644
--- a/function.py
+++ b/function.py
@@ -29,13 +29,13 @@ name = "章程鸿"
 import numpy as np
 import pandas as pd
 from sklearn.preprocessing import StandardScaler
-from sklearn.model_selection import train_test_split
+from sklearn.model_selection import train_test_split, KFold
 
 def sigmoid(z):
     """Sigmoid 激活函数。"""
     return 1 / (1 + np.exp(-z))
 
-def train_logreg(X, y, learning_rate=0.01, iterations=1000, lambda_reg=0.01, batch_size=32):
+def train_logreg(X, y, learning_rate=0.1, iterations=2000, lambda_reg=0.01, batch_size=32):
     """逻辑回归训练函数，随机初始化权重，并在每次迭代前打乱数据。"""
     m, n = X.shape
     weights = np.random.randn(n) * 0.01  # 随机初始化权重，取较小值
@@ -61,7 +61,8 @@ def train_logreg(X, y, learning_rate=0.01, iterations=1000, lambda_reg=0.01, bat
             weights -= learning_rate * gradient
 
         # 动态调整学习率，逐渐减小
-        learning_rate *= 0.99
+        if i % 100 == 0:  # 每100次迭代输出一次学习率
+            print(f"Iteration {i}, Learning Rate: {learning_rate}")
 
     return weights
 
@@ -117,9 +118,27 @@ if __name__ == "__main__":
     # 使用 train_test_split 打乱并随机抽取数据
     X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
 
-    # 训练逻辑回归模型，设置 batch_size
-    batch_size = 32
-    weights = train_logreg(X_train, y_train, learning_rate=0.1, iterations=1000, lambda_reg=0.01, batch_size=batch_size)
+    # K折交叉验证
+    k = 5
+    kf = KFold(n_splits=k, shuffle=True, random_state=42)
+    accuracies = []
+
+    for train_index, val_index in kf.split(X_train):
+        X_train_kf, X_val_kf = X_train[train_index], X_train[val_index]
+        y_train_kf, y_val_kf = y_train[train_index], y_train[val_index]
+
+        # 训练逻辑回归模型，设置 batch size
+        batch_size = 32
+        weights = train_logreg(X_train_kf, y_train_kf, learning_rate=0.1, iterations=2000, lambda_reg=0.01, batch_size=batch_size)
+
+        # 验证模型
+        val_predictions = [predict_logreg(X_val_kf[i], weights) for i in range(len(X_val_kf))]
+        accuracy = np.mean(val_predictions == y_val_kf)
+        accuracies.append(accuracy)
+
+    # 输出交叉验证的准确率和平均准确率
+    print(f"K折交叉验证得分: {accuracies}")
+    print(f"平均准确率: {np.mean(accuracies)}")
 
     # 测试单个数据
     y_pred = predict_logreg(X_test[11], weights)