上传文件至 /

function.py

@@ -1,5 +1,4 @@
 import numpy as np
-from sklearn.model_selection import train_test_split, cross_val_score
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.preprocessing import PolynomialFeatures, StandardScaler
 
@@ -19,17 +18,14 @@ def load_data(filepath):
     data = np.array(data)
     data = np.nan_to_num(data, nan=np.nanmean(data, axis=0))
 
-    # 将最后一列作为标签，其他列作为特征
-    X = data[:, :-1]
-    y = data[:, -1]
+    # 这里需要根据具体数据格式调整
+    X = data[:, :-1]  # 特征
+    y = data[:, -1]   # 标签
     return X, y
 
 def preprocess_data(X):
-    # 标准化特征
     scaler = StandardScaler()
     X_standardized = scaler.fit_transform(X)
-
-    # 增加多项式特征
     poly = PolynomialFeatures(degree=2, include_bias=False)
     X_poly = poly.fit_transform(X_standardized)
     return X_poly
@@ -40,28 +36,9 @@ def train_logreg(X, y):
     return model
 
 def predict_logreg(model, X):
-    return model.predict(X)
+    # X 应该是一个单独的样本，确保它的形状是 (1, n_features)
+    return model.predict(X.reshape(1, -1))[0]
 
 if __name__ == "__main__":
     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)
-
-    # 数据预处理
-    X_train_processed = preprocess_data(X_train)
-    X_test_processed = preprocess_data(X_test)
-
-    # 训练模型
-    model = train_logreg(X_train_processed, y_train)
-
-    # 交叉验证
-    cv_scores = cross_val_score(model, X_train_processed, y_train, cv=5)
-    print(f"交叉验证准确率: {np.mean(cv_scores) * 100:.2f}%")
-
-    # 预测
-    y_pred = predict_logreg(model, X_test_processed)
-
-    # 计算正确率
-    accuracy = np.mean(y_pred == y_test)
-    print(f"测试出的正确率: {accuracy * 100:.2f}%")
+    # 这里可能需要确保调用和处理的逻辑符合你的数据处理需求