更新 function.py

function.py

@@ -1,8 +1,6 @@
 # function.py
 import numpy as np
 from sklearn.preprocessing import StandardScaler
-from sklearn.model_selection import GridSearchCV
-from sklearn.base import BaseEstimator, ClassifierMixin
 
 """
 实验说明:
@@ -30,7 +28,7 @@ name = "程悦"
 def sigmoid(z):
     return 1.0 / (1 + np.exp(-z))
 
-def train_logreg(X, y, learning_rate=0.01, iterations=1000, regularization='l2', lambda_=0.01):
+def train_logreg(X, y, learning_rate=0.01, iterations=100):
     """
     对率回归训练函数。
 
@@ -47,12 +45,6 @@ def train_logreg(X, y, learning_rate=0.01, iterations=1000, regularization='l2',
         z = np.dot(X, weights)
         h = sigmoid(z)
         gradient = np.dot(X.T, (h - y)) / m
-        # 正则化
-        if regularization == 'l2':
-            gradient += lambda_ * weights / m
-        elif regularization == 'l1':
-            gradient += lambda_ * np.sign(weights) / m
-
         weights -= learning_rate * gradient
     return weights
 
@@ -109,47 +101,18 @@ def load_data(filepath):
     
     return data, target_variable
 
-class CustomLogisticRegression(BaseEstimator, ClassifierMixin):
-    def __init__(self, learning_rate=0.01, iterations=1000, regularization='l2', lambda_=0.01):
-        self.learning_rate = learning_rate
-        self.iterations = iterations
-        self.regularization = regularization
-        self.lambda_ = lambda_
-        self.weights = None
-
-    def fit(self, X, y):
-        self.weights = train_logreg(X, y, self.learning_rate, self.iterations,
-                                    self.regularization, self.lambda_)
-
-    def predict(self, X):
-        return np.array([predict_logreg(x, self.weights) for x in X])
-
 if __name__ == "__main__":
-    # 加载训练集和测试集
+    # 以下代码可用于测试，可自行随意修改
+    # 加载训练集
     X_train, y_train = load_data("./data/horse-colic.data")
+
+    # 加载测试集
     X_test, y_test = load_data("./data/horse-colic.test")
 
-# 定义网格搜索的参数范围
+    # 训练对率回归模型
-    param_grid = {
+    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000, re
-        'learning_rate': [0.001, 0.01, 0.1],
+    ='l1')
-        'iterations': [100, 500, 1000],
-        'regularization': ['l1', 'l2'],
-        'lambda_': [0.01, 0.1, 1.0]
-    }
-
-    # 创建逻辑回归模型
-    model = CustomLogisticRegression()
-
-    # 网格搜索
-    grid_search = GridSearchCV(model, param_grid, cv=5)
-    grid_search.fit(X_train, y_train)
-
-    # 使用最佳模型进行预测
-    best_model = grid_search.best_estimator_
-    y_pred = best_model.predict(X_test)
 
     # 测试单个数据
-    single_prediction = best_model.predict([X_test[11]])
+    y_pred = predict_logreg(X_test[11], weights)
-    print(f"最佳参数组合: {grid_search.best_params_}")
+    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
-    print(f"最佳准确率: {grid_search.best_score_}")
-    print(f"预测结果: {single_prediction[0]}, 实际结果: {y_test[11]}")