From 817111606bf0ef122077ed50da5d07568792727b Mon Sep 17 00:00:00 2001
From: 202210423104 <1961532386@qq.com>
Date: Sun, 3 Nov 2024 16:57:52 +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 | 21 +++------------------
 1 file changed, 3 insertions(+), 18 deletions(-)

diff --git a/function.py b/function.py
index 4211bad..a00a9fa 100644
--- a/function.py
+++ b/function.py
@@ -9,7 +9,7 @@ def load_data(filepath):
     data = []
     with open(filepath, 'r') as file:
         for line in file:
-            line_data = line.strip().split(',')
+            line_data = line.strip().split()
             if line_data:
                 try:
                     data.append([float(x) if x != '?' else np.nan for x in line_data])
@@ -31,7 +31,7 @@ def preprocess_data(X):
 
 def train_logreg(X, y):
     X_processed = preprocess_data(X)  # 预处理训练数据
-    model = RandomForestClassifier(n_estimators=113, max_depth=10, random_state=42)
+    model = RandomForestClassifier(n_estimators=200, max_depth=20, random_state=42)
     model.fit(X_processed, y)
     return model  # 返回训练好的模型
 
@@ -43,19 +43,4 @@ def predict_logreg(X, model):
     return model.predict(X_processed)[0]  # 确保 model 是训练好的模型
 
 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
-    model = train_logreg(X_train, y_train)
-
-    # 确保测试集中有数据
-    if X_test.shape[0] > 0:
-        # 预测测试集的第一个样本
-        y_pred = predict_logreg(X_test[0], model)
-        print(f"预测结果: {y_pred}, 实际结果: {y_test[0]}")
-    else:
-        print("测试集没有数据，无法进行预测。")
+    X, y = load_data("./data/horse-colic.data")