From d427c23869b90500f3ffc40f9b4784b2b9261e06 Mon Sep 17 00:00:00 2001
From: wzy <675163717@qq.com>
Date: Thu, 31 Oct 2024 20:26:11 +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 | 51 +++++++++++++++------------------------------------
 1 file changed, 15 insertions(+), 36 deletions(-)

diff --git a/function.py b/function.py
index 8d51b11..4b5f68a 100644
--- a/function.py
+++ b/function.py
@@ -1,7 +1,7 @@
 # function.py
 import numpy as np
 import random
-import pandas as pd
+from sklearn.preprocessing import StandardScaler
 
 """
 实验说明:
@@ -28,8 +28,8 @@ name = "万子玉"
 
 
 # 这里写自己的代码实现
-def sigmoid(inx):
-    return 1 / (1 + np.exp(-inx))
+def sigmoid(z):
+    return 1 / (1 + np.exp(-z))
 
 def train_logreg(X, y, learning_rate=0.001, iterations=500, batch_size=16, initial_weights=None):
     X = np.insert(X, 0, 1, axis=1)  # 添加偏置项
@@ -56,6 +56,7 @@ def train_logreg(X, y, learning_rate=0.001, iterations=500, batch_size=16, initi
             weights -= learning_rate * gradient
         
     return weights
+
     """
     对率回归训练函数。
 
@@ -92,16 +93,13 @@ def evaluate_model(X_val, y_val, weights):
     return accuracy
 
 def split_train_val(X, y, val_size=0.2):
-    # 确保数据是随机打乱的
     shuffled_indices = list(range(X.shape[0]))
     random.shuffle(shuffled_indices)
     X_shuffled = X[shuffled_indices]
     y_shuffled = y[shuffled_indices]
     
-    # 计算验证集的大小
     val_count = int(X.shape[0] * val_size)
     
-    # 分割数据集
     X_val = X_shuffled[:val_count]
     y_val = y_shuffled[:val_count]
     X_train = X_shuffled[val_count:]
@@ -110,16 +108,17 @@ def split_train_val(X, y, val_size=0.2):
     return X_train, X_val, y_train, y_val
 
 
+
 # 这里也写自己的代码实现
 def load_data(filepath):
     with open(filepath, 'r') as file:
         lines = file.readlines()
     
-    data = [line.strip().split() for line in lines]
+    data = [line.strip().split() for line in lines if line.strip().split()[-1].isdigit()]
     data = [list(map(lambda x: float(x) if x != '?' else np.nan, row)) for row in data]
     
     # 移除类别标签缺失的样本
-    data = [row for row in data if row[-1] != np.nan]
+    data = [row for row in data if not np.isnan(row[-1])]
 
     # 使用“0”填充缺失值
     for row in data:
@@ -129,34 +128,20 @@ def load_data(filepath):
     
     # 合并特征23的值2和3为0
     for row in data:
-        if row[22] == 2 or row == 3:  # 假设特征23是第23个元素
+        if row[22] == 2 or row[22] == 3:  # 假设特征23是第23个元素
             row[22] = 0
     
     # 移除不需要的特征
-    # 假设特征从0开始编号，那么我们需要移除特征3和特征24~28
     data = [row[:2] + row[3:23] + row[28:] for row in data]
     
     # 分离特征和标签
-    X = [row[:-1] for row in data]  # 特征现在是从0到21，然后是23到27
+    X = [row[:-1] for row in data]
     y = [row[-1] for row in data]
     
-    return np.array(X), np.array(y)
+    scaler = StandardScaler()
+    X = scaler.fit_transform(X)
     
-    data = pd.read_csv(filepath, header=None, delimiter=' ')
-    return data
-
-# 标准化函数
-def regularize(xMat):
-    inMat = xMat.copy()
-    inMeans = np.mean(inMat, axis=0)
-    inVar = np.std(inMat, axis=0)
-    inMat = (inMat - inMeans) / inVar
-    return inMat
-
-def classify(inx, weights):
-    p = sigmoid(np.dot(inx, weights))
-    return 1 if p >= 0.5 else 0
-
+    return np.array(X), np.array(y)
     """
     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**。
 
@@ -169,16 +154,10 @@ def classify(inx, weights):
     """
 
 if __name__ == "__main__":
-    # 以下代码可用于测试，可自行随意修改
-    # 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)
-    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
+    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
\ No newline at end of file