From aadc69da6e5fd0c56e6858b457ea5ad753512acb Mon Sep 17 00:00:00 2001
From: 202210423104 <1961532386@qq.com>
Date: Sun, 3 Nov 2024 16:20:18 +0800
Subject: [PATCH] =?UTF-8?q?=E4=B8=8A=E4=BC=A0=E6=96=87=E4=BB=B6=E8=87=B3?=
 =?UTF-8?q?=20/?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 function.py | 30 ++++++++++++++++++++++++------
 1 file changed, 24 insertions(+), 6 deletions(-)

diff --git a/function.py b/function.py
index 0e76974..185680b 100644
--- a/function.py
+++ b/function.py
@@ -1,6 +1,7 @@
 import numpy as np
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.preprocessing import PolynomialFeatures, StandardScaler
+from sklearn.model_selection import train_test_split, cross_val_score
 
 id = "202210423104"
 name = "张钦诚"
@@ -35,12 +36,29 @@ def train_logreg(X, y):
     model.fit(X_processed, y)
     return model  # 返回训练好的模型
 
-def predict_logreg(X, model):
-    # 确保输入数据是一个 numpy 数组
-    if len(X.shape) == 1:
-        X = X.reshape(1, -1)  # 保持输入数据的形状为 (1, n)，符合模型的输入要求
-    X_processed = preprocess_data(X)  # 预处理测试数据
-    return model.predict(X_processed)[0]  # 确保 model 是训练好的模型
+def predict_logreg(model, X):
+    X_processed = preprocess_data(X.reshape(1, -1))  # 预处理单个测试样本
+    return model.predict(X_processed)[0]  # 预测并返回结果
 
 if __name__ == "__main__":
+    # 加载数据
     X, y = load_data("./data/horse-colic.data")
+
+    # 划分数据集
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+    # 训练模型
+    model = train_logreg(X_train, y_train)
+
+    # 预测
+    y_pred = []
+    for sample in X_test:
+        y_pred.append(predict_logreg(model, sample))
+
+    # 计算准确率
+    accuracy = np.mean(y_pred == y_test)
+    print(f"测试出的正确率: {accuracy * 100:.2f}%")
+
+    # 交叉验证
+    cv_scores = cross_val_score(model, preprocess_data(X_train), y_train, cv=5)
+    print(f"交叉验证准确率: {np.mean(cv_scores) * 100:.2f}%")