更新 function.py

function.py

@@ -1,6 +1,7 @@
 import numpy as np
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.preprocessing import PolynomialFeatures, StandardScaler
+from sklearn.metrics import accuracy_score, f1_score
 
 id = "202210423104"
 name = "张钦诚"
@@ -11,29 +12,48 @@ 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 = np.array(data)
     data = np.nan_to_num(data, nan=np.nanmean(data, axis=0))
-    X = data[:, :-1]
+
-    y = data[:, -1]
+    X = data[:, :-1]  # 特征
+    y = data[:, -1]   # 标签
     return X, y
 
-def preprocess_data(X):
+def preprocess_data(X, scaler=None, poly=None):
+    if scaler is None:
         scaler = StandardScaler()
         X_standardized = scaler.fit_transform(X)
+    else:
+        X_standardized = scaler.transform(X)
+    
+    if poly is None:
         poly = PolynomialFeatures(degree=2, include_bias=False)
         X_poly = poly.fit_transform(X_standardized)
-    return X_poly
+    else:
+        X_poly = poly.transform(X_standardized)
+        
+    return X_poly, scaler, poly
 
 def train_logreg(X, y):
-    X_processed = preprocess_data(X)  # 预处理训练数据
+    X_processed, scaler, poly = 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
+    return model, scaler, poly  # 返回训练好的模型及预处理器
 
-def predict_logreg(model, X):
+def predict_logreg(model, X, scaler, poly):
-    X_processed = preprocess_data(X)  # 预处理测试数据
+    # 确保输入数据是一个 numpy 数组
-    return model.predict(X_processed)[0]  # 返回预测结果
+    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, scaler, poly)  # 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__":
     X, y = load_data("./data/horse-colic.data")
+    model, scaler, poly = train_logreg(X, y)  # 训练模型
+    y_pred = [predict_logreg(model, sample, scaler, poly) for sample in X]  # 预测
+    print(f"Accuracy: {accuracy_score(y, y_pred):.2f}")
+    print(f"F1 Score: {f1_score(y, y_pred, average='weighted'):.2f}")