From a9fb7b5eaa36d421478d083fe085c15c59dac143 Mon Sep 17 00:00:00 2001
From: wzy <675163717@qq.com>
Date: Sat, 26 Oct 2024 12:20:04 +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 | 36 ++++++++++++++++++++++++++++++------
 1 file changed, 30 insertions(+), 6 deletions(-)

diff --git a/function.py b/function.py
index e58ee0c..4388d14 100644
--- a/function.py
+++ b/function.py
@@ -1,6 +1,6 @@
 # function.py
 import numpy as np
-from sklearn.model_selection import train_test_split
+import random
 
 """
 实验说明:
@@ -68,10 +68,12 @@ def train_logreg(X, y, learning_rate=0.001, iterations=1000, batch_size=32, init
     """
 
 
-def evaluate_model(X_val, y_val, weights):
-    predictions = np.array([predict_logreg(x, weights) for x in X_val])
-    accuracy = np.mean(predictions == y_val)
-    return accuracy
+def predict_logreg(inX, weights):
+    inX = np.insert(inX, 0, 1)  # 添加偏置项
+    z = np.dot(inX, weights)
+    h = sigmoid(z)
+    return 1 if h >= 0.5 else 0
+
 
     """
     对率回归预测函数。
@@ -83,6 +85,28 @@ def evaluate_model(X_val, y_val, weights):
     Returns:
     - int: 预测的分类标签。
     """
+def evaluate_model(X_val, y_val, weights):
+    predictions = np.array([predict_logreg(x, weights) for x in X_val])
+    accuracy = np.mean(predictions == y_val)
+    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:]
+    y_train = y_shuffled[val_count:]
+    
+    return X_train, X_val, y_train, y_val
 
 
 # 这里也写自己的代码实现
@@ -119,7 +143,7 @@ def load_data(filepath):
 if __name__ == "__main__":
     # 加载数据并分割为训练集和验证集
     X, y = load_data("./data/horse-colic.data")
-    X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)
+    X_train, X_val, y_train, y_val = split_train_val(X, y)
 
     # 模型调优参数
     learning_rates = [0.01, 0.001, 0.0001]