444

function.py

@@ -42,7 +42,6 @@ def load_data(filepath):
         del data[26]
         del data[25]
         del data[24]
-        del data[23]
         del data[22]
         del data[2]
         for i in data_25:
@@ -53,12 +52,9 @@ def load_data(filepath):
     y_train = np.array([1 if y[j] == '2' or y[j] == '3' else 0 for j in range(data_number)])
     X = np.array(data_list)
     X_train = np.insert(X, 0, 1, axis=1)  # 添加偏置项
-    scaler = StandardScaler()
-    X= scaler.fit_transform(X)
-
     return X_train, y_train
 
-def train_logreg(X, y, numIter=1500, learning_rate=0.05, batch_size=64, lambda_reg=0.01):
+def train_logreg(X, y, numIter=1000, learning_rate=0.06, batch_size=128, lambda_reg=0.01):
     m, n = X.shape
     weights = np.zeros(n)
     for j in range(numIter):
@@ -71,10 +67,9 @@ def train_logreg(X, y, numIter=1500, learning_rate=0.05, batch_size=64, lambda_r
             h = 1 / (1 + np.exp(-z))
             error = batch_y - h
             gradient = np.dot(batch_X.T, error) / len(batch_y)
-            # L1正则化项
-            l1_reg_term = np.sign(weights)
-            # 更新权重，加入L1正则化
-            weights -= learning_rate * (gradient + lambda_reg * l1_reg_term)
+            reg_term = 2 * lambda_reg * weights
+            gradient -= reg_term / len(batch_y)
+            weights += learning_rate * gradient
     return weights
 
 def predict_logreg(inX, weights):
@@ -108,3 +103,38 @@ if __name__ == "__main__":
     accuracy_test = accuracy_score(y_test, y_pred_test)
     print(f"Test Accuracy: {accuracy_test}")
 
+    # 随机森林模型
+    param_grid = {
+        'n_estimators': [100, 200, 300],
+        'max_depth': [5, 10, 15],
+        'learning_rate': [0.01, 0.05, 0.1]
+    }
+    rf = RandomForestClassifier()
+    grid_search = GridSearchCV(estimator=rf, param_grid=param_grid, cv=5, scoring='accuracy')
+    grid_search.fit(X_train, y_train)
+    best_rf = grid_search.best_estimator_
+    print("Best parameters:", grid_search.best_params_)
+    print("Best accuracy:", grid_search.best_score_)
+
+    # 集成学习 - 投票分类器
+    log_clf = LogisticRegression()
+    rnd_clf = RandomForestClassifier(n_estimators=100, random_state=42)
+    voting_clf = VotingClassifier(estimators=[('lr', log_clf), ('rf', rnd_clf)], voting='soft')
+    voting_clf.fit(X_train, y_train)
+    y_pred = voting_clf.predict(X_test)
+    print("Voting classifier accuracy:", accuracy_score(y_test, y_pred))
+
+    # 梯度提升机模型
+    gb_clf = GradientBoostingClassifier()
+    gb_clf.fit(X_train, y_train)
+    y_pred = gb_clf.predict(X_test)
+    print("Gradient Boosting classifier accuracy:", accuracy_score(y_test, y_pred))
+
+    # 使用K折交叉验证评估模型性能
+    scores = cross_val_score(gb_clf, X_train, y_train, cv=5, scoring='accuracy')
+    print("Cross-validation scores:", scores)
+    print("Average cross-validation score:", np.mean(scores))
+
+    # 使用F1分数评估模型性能
+    f1 = f1_score(y_test, y_pred)
+    print("F1 Score:", f1)