上传文件至 /

function.py

@@ -1,53 +1,46 @@
 import numpy as np
-
-"""
-实验说明:
-- 自行编写实现数据加载与预测病马死亡的对率回归算法。
-
-注意事项:
-- 在 function.py 中实现对率回归算法。
-- 可以自行导入其他库，需要在 requirements.txt 添加依赖，若未在 requirements.txt 中添加使用到的依赖，则无法自动评测，成绩为零。
-- 自动评测脚本仅会加载 train_logreg、predict_logreg 和 load_data 函数，请勿修改函数名。
-
-测评环境:
-- CPU: Intel Xeon(R) CPU E3-1231 v3 @ 3.40GHz
-- OS: Ubuntu 22.04.4 LTS
-- Python: 3.10.12
-- numpy: 2.1.1
-"""
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.preprocessing import PolynomialFeatures, StandardScaler
 
 id = "202210423104"
 name = "张钦诚"
 
-
-# 训练对率回归模型
-def train_logreg(X, y, learning_rate=0.01, iterations=1000):
-    weights = np.zeros(X.shape[1])
-
-    for _ in range(iterations):
-        predictions = 1 / (1 + np.exp(-np.dot(X, weights)))
-        errors = y - predictions
-        gradient = np.dot(X.T, errors)
-        weights += learning_rate * gradient
-
-    return weights
-
-
-# 预测函数
-def predict_logreg(inX, weights):
-    prob = 1 / (1 + np.exp(-np.dot(inX, weights)))
-    return 1 if prob >= 0.5 else 0
-
-
-# 数据加载函数
 def load_data(filepath):
-    data = np.genfromtxt(filepath, delimiter=',', dtype=float, filling_values=np.nan)  # 根据实际分隔符调整
-    data = data[~np.isnan(data).any(axis=1)]
+    data = []
+    with open(filepath, 'r') as file:
+        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 = 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
     return X, y
 
+def preprocess_data(X):
+    scaler = StandardScaler()
+    X_standardized = scaler.fit_transform(X)
+    poly = PolynomialFeatures(degree=2, include_bias=False)
+    X_poly = poly.fit_transform(X_standardized)
+    return X_poly
+
+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.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
 
 if __name__ == "__main__":
     # 加载训练集
@@ -56,14 +49,13 @@ if __name__ == "__main__":
     # 加载测试集
     X_test, y_test = load_data("./data/horse-colic.test")
 
-    # 输出数据形状以便调试
-    print(f"X_train shape: {X_train.shape}, y_train shape: {y_train.shape}")
-    print(f"X_test shape: {X_test.shape}, y_test shape: {y_test.shape}")
+    # 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:
-        weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
-        index_to_test = 0 if X_test.shape[0] == 1 else 11
-        y_pred = predict_logreg(X_test[index_to_test], weights)
-        print(f"预测结果: {y_pred}, 实际结果: {y_test[index_to_test]}")
+        # 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。")