上传文件至 /

function.py

@@ -6,6 +6,7 @@ from sklearn.preprocessing import PolynomialFeatures, StandardScaler
 id = "202210423104"
 name = "张钦诚"
 
+
 def load_data(filepath):
     data = []
     with open(filepath, 'r') as file:
@@ -18,7 +19,12 @@ def load_data(filepath):
                     print(f"Error processing line: {line}. Error: {e}")
     data = np.array(data)
     data = np.nan_to_num(data, nan=np.nanmean(data, axis=0))
-    return data
+
+    # 将最后一列作为标签，其他列作为特征
+    X = data[:, :-1]
+    y = data[:, -1]
+    return X, y
+
 
 def preprocess_data(X):
     # 标准化特征
@@ -30,18 +36,19 @@ def preprocess_data(X):
     X_poly = poly.fit_transform(X_standardized)
     return X_poly
 
+
 def train_logreg(X, y):
     model = RandomForestClassifier(n_estimators=113, max_depth=10, random_state=42)
     model.fit(X, y)
     return model
 
+
 def predict_logreg(model, X):
     return model.predict(X)
 
+
 if __name__ == "__main__":
-    data = load_data("./data/horse-colic.data")
-    X = data[:, :-1]
-    y = data[:, -1]
+    X, y = load_data("./data/horse-colic.data")
 
     # 数据集划分
     X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)