From f5aa7b86c768b0684c8fc9a287c8f7a4f41552b4 Mon Sep 17 00:00:00 2001
From: zhangchenghong <1598349064@qq.com>
Date: Thu, 7 Nov 2024 17:03:55 +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 | 61 ++++++++++++++++-------------------------------------
 1 file changed, 18 insertions(+), 43 deletions(-)

diff --git a/function.py b/function.py
index c1ef21e..cde8fce 100644
--- a/function.py
+++ b/function.py
@@ -31,18 +31,7 @@ import numpy as np
 def sigmoid(z):
     return 1 / (1 + np.exp(-z))
 
-def train_logreg(X, y, learning_rate=0.005, iterations=1000):
-    """
-    对率回归训练函数。
-
-    Args:
-    - X (numpy array): 特征数据。
-    - y (numpy array): 标签数据。
-    - other_params (str): 其它参数，可选设置。若需设置其它参数，必须设置其默认值，否则将**无法通过**自动评测，**成绩为零**。
-
-    Returns:
-    - numpy array: 训练得到的权重。
-    """
+def train_logreg(X, y, learning_rate, iterations):
     m, n = X.shape
     weights = np.zeros(n)
     bias = 0
@@ -56,38 +45,16 @@ def train_logreg(X, y, learning_rate=0.005, iterations=1000):
     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)
     h = sigmoid(z)
     return 1 if h >= 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:
-    - directory (str): 数据文件路径。
-
-    Returns:
-    - np.array: 特征数据。
-    - np.array: 标签数据。
-    """
     data = []
     with open(filepath, 'r') as file:
         for line in file:
-            # 清理无效数据
             cleaned_line = line.strip().replace('?', '0')
             values = [float(x) for x in cleaned_line.split()]
-            # 处理目标变量
             if values[22] in [2, 3]:
                 values[22] = 0
             new_values = values[:2] + values[3:23]
@@ -98,15 +65,23 @@ def load_data(filepath):
     return X, y
 
 if __name__ == "__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")
-
-    # 训练对率回归模型
-    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
-
-    # 测试单个数据
-    y_pred = predict_logreg(X_test[11], weights)
+    best_learning_rate = None
+    best_accuracy = 0
+    learning_rates = [0.001, 0.002, 0.003, 0.004, 0.005, 0.006, 0.007, 0.008, 0.009, 0.01]
+    iterations = 1000
+    for lr in learning_rates:
+        weights = train_logreg(X_train, y_train, learning_rate=lr, iterations=iterations)
+        correct_count = 0
+        for i in range(len(X_test)):
+            y_pred = predict_logreg(X_test[i], weights)
+            if y_pred == y_test[i]:
+                correct_count += 1
+        accuracy = correct_count / len(X_test)
+        if accuracy > best_accuracy:
+            best_accuracy = accuracy
+            best_learning_rate = lr
+    best_weights = train_logreg(X_train, y_train, learning_rate=best_learning_rate, iterations=iterations)
+    y_pred = predict_logreg(X_test[11], best_weights)
     print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
\ No newline at end of file