From 670cf4e4e3e365b9f3f90b1d2d199662439c54a9 Mon Sep 17 00:00:00 2001
From: 202210423104 <1961532386@qq.com>
Date: Sun, 3 Nov 2024 16:32:07 +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 | 44 +++++++++++++++-----------------------------
 1 file changed, 15 insertions(+), 29 deletions(-)

diff --git a/function.py b/function.py
index a0d5613..0e417d3 100644
--- a/function.py
+++ b/function.py
@@ -1,6 +1,6 @@
 import numpy as np
-from sklearn.model_selection import train_test_split, cross_val_score
 from sklearn.ensemble import RandomForestClassifier
+from sklearn.model_selection import train_test_split, cross_val_score
 from sklearn.preprocessing import PolynomialFeatures, StandardScaler
 
 id = "202210423104"
@@ -12,15 +12,11 @@ def load_data(filepath):
         for line in file:
             line_data = line.strip().split()
             if line_data:
-                try:
-                    data.append([float(x) if x != '?' else np.nan for x in line_data])
-                except ValueError as e:
-                    print(f"Error processing line: {line}. Error: {e}")
+                data.append([float(x) if x != '?' else np.nan for x in line_data])
     data = np.array(data)
     data = np.nan_to_num(data, nan=np.nanmean(data, axis=0))
-
-    X = data[:, :-1]  # 特征
-    y = data[:, -1]   # 标签
+    X = data[:, :-1]
+    y = data[:, -1]
     return X, y
 
 def preprocess_data(X):
@@ -31,32 +27,22 @@ def preprocess_data(X):
     return X_poly
 
 def train_logreg(X, y):
-    model = RandomForestClassifier(n_estimators=113, max_depth=10, random_state=42)
-    X_processed = preprocess_data(X)  # 预处理训练数据
+    X_processed = preprocess_data(X)
+    model = RandomForestClassifier(n_estimators=200, max_depth=15, random_state=42)  # 改变参数
     model.fit(X_processed, y)
-    return model  # 返回训练好的模型
+    return model
 
 def predict_logreg(model, X):
-    X_processed = preprocess_data(X)  # 预处理输入数据
-    return model.predict(X_processed)  # 返回预测结果
+    if len(X.shape) == 1:
+        X = X.reshape(1, -1)
+    X_processed = preprocess_data(X)
+    return model.predict(X_processed)[0]
 
 if __name__ == "__main__":
     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 = predict_logreg(model, X_test)  # 调用预测函数
-
-    # 计算准确率
-    accuracy = np.mean(y_pred == y_test)
-    print(f"测试出的正确率: {accuracy * 100:.2f}%")
-
+    model = train_logreg(X, y)
+    
     # 交叉验证
-    X_train_processed = preprocess_data(X_train)  # 预处理训练数据
-    cv_scores = cross_val_score(model, X_train_processed, y_train, cv=5)
+    X_processed = preprocess_data(X)
+    cv_scores = cross_val_score(model, X_processed, y, cv=5)
     print(f"交叉验证准确率: {np.mean(cv_scores) * 100:.2f}%")