From 255174f444cc7b9b30ff63a5cf7d55831d562ad9 Mon Sep 17 00:00:00 2001
From: 77 <3298722099@qq.com>
Date: Fri, 1 Nov 2024 21:17:06 +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 | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/function.py b/function.py
index 8644ca5..e1269ff 100644
--- a/function.py
+++ b/function.py
@@ -1,9 +1,9 @@
+# function.py
 import numpy as np
 import pandas as pd
 from sklearn.impute import SimpleImputer
 from sklearn.preprocessing import StandardScaler
 
-
 """
 实验说明:
 - 自行编写实现数据加载与预测病马死亡的对率回归算法。
@@ -28,12 +28,10 @@ id = "202210423201"
 name = "陈瑞琪祥"
 
 
-
-# Sigmoid 函数
+# 这里写自己的代码实现
 def sigmoid(x):
     return 1 / (1 + np.exp(-x))
 
-# 逻辑回归训练函数
 def train_logreg(X, y, learning_rate=0.01, iterations=1000, regularization=0.01):
     m, n = X.shape
     weights = np.zeros(n)
@@ -44,13 +42,11 @@ def train_logreg(X, y, learning_rate=0.01, iterations=1000, regularization=0.01)
         weights -= learning_rate * gradient
     return weights
 
-# 逻辑回归预测函数
 def predict_logreg(inX, weights):
     linear_output = np.dot(inX, weights)
     probability = sigmoid(linear_output)
     return 1 if probability > 0.5 else 0
 
-# 数据预处理函数
 def preprocess_data(X, y):
     # 合并目标变量的类别
     y[y == 2] = 0
@@ -62,42 +58,53 @@ def preprocess_data(X, y):
 
     return X, y
 
-# 加载数据函数
 def load_data(filepath):
+    # 使用Pandas读取数据，可以更好地处理缺失值和字符串
     try:
         data = pd.read_csv(filepath, header=None, sep=r'\s+', on_bad_lines='skip')
     except pd.errors.ParserError as e:
         print(f"Error parsing file: {e}")
         return None, None
 
+    # 将'?'替换为np.nan
     data.replace('?', np.nan, inplace=True)
+
+    # 使用SimpleImputer填充缺失值
     imputer = SimpleImputer(missing_values=np.nan, strategy='constant', fill_value=0)
     data.iloc[:, :-1] = imputer.fit_transform(data.iloc[:, :-1])
 
+    # 将所有列转换为数值类型
     for col in data.columns[:-1]:
         data[col] = pd.to_numeric(data[col], errors='coerce')
 
     X = data.iloc[:, :-1].values
     y = data.iloc[:, -1].values.astype(int)
 
+    # 预处理数据
     X, y = preprocess_data(X, y)
+
     return X, y
 
-# 主函数
 def main():
     X_train, y_train = load_data("D:/data/horse/horse-colic.data")
     X_test, y_test = load_data("D:/data/horse/horse-colic.test")
 
     if X_train is not None and X_test is not None:
+        # 特征缩放
         scaler = StandardScaler()
         X_train = scaler.fit_transform(X_train)
         X_test = scaler.transform(X_test)
 
+        # 训练模型
         weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000, regularization=0.1)
+
+        # 预测测试集
         y_pred = [predict_logreg(x, weights) for x in X_test]
 
+        # 计算准确率
         accuracy = np.mean(y_pred == y_test)
         print(f"准确率: {accuracy}")
 
 if __name__ == "__main__":
     main()
+