4544444

function.py

@@ -1,10 +1,6 @@
 import numpy as np
-from sklearn.model_selection import train_test_split, GridSearchCV, cross_val_score
 from sklearn.preprocessing import StandardScaler
-from sklearn.metrics import accuracy_score, roc_auc_score, f1_score
-from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier, VotingClassifier
 from sklearn.linear_model import LogisticRegression
-from sklearn.svm import SVC
 
 """
 实验说明:
@@ -29,117 +25,45 @@ id = "202210423221"
 name = "廖子豪"
 
 def load_data(filepath):
-    file = open(filepath)
+    # 使用 numpy 的 genfromtxt 函数加载数据，自动处理缺失值
-    fr = file.readlines()
+    data = np.genfromtxt(filepath, delimiter=' ', missing_values='?', filling_values=0)
-    data_list = []
+    labels = data[:, -1].astype(int)
-    y = []
+    features = data[:, :-1]
-    for data in fr:
-        data = data.strip()
-        data = data.split(' ')
-        data_25 = data[24]
-        y.append(data[22])
-        del data[-1]
-        del data[26]
-        del data[25]
-        del data[24]
-        del data[22]
-        del data[2]
-        for i in data_25:
-            data.append(i)
-        data = [0 if data_elem == '?' else float(data_elem) for data_elem in data]
-        data_list.append(data)
-    data_number = len(y)
-    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
-    return X_train, y_train
     
-def train_logreg(X, y, numIter=1000, learning_rate=0.06, batch_size=128, lambda_reg=0.01, penalty='l2'):
+    # 将标签转换为二分类问题
-    m, n = X.shape
+    labels = np.where((labels == 2) | (labels == 3), 1, 0)
-    weights = np.zeros(n)
-    for j in range(numIter):
-        dataIndex = np.random.permutation(m)
-        for i in range(0, m, batch_size):
-            end = min(i + batch_size, m)
-            batch_X = X[dataIndex[i:end]]
-            batch_y = y[dataIndex[i:end]]
-            z = np.dot(batch_X, weights)
-            h = 1 / (1 + np.exp(-z))
-            error = batch_y - h
-            gradient = np.dot(batch_X.T, error) / len(batch_y)
-            if penalty == 'l1':
-                reg_term = lambda_reg * np.sign(weights)
-            elif penalty == 'l2':
-                reg_term = 2 * lambda_reg * weights
-            else:
-                raise ValueError("Unsupported penalty type. Use 'l1' or 'l2'.")
-            gradient -= reg_term / len(batch_y)
-            weights -= learning_rate * gradient
-    return weights
     
-def predict_logreg(inX, weights):
+    # 删除不相关特征（如果需要）
-    z = np.dot(inX, weights)
+    # features = np.delete(features, [2] + list(range(23, 28)), axis=1)
-    prob = 1 / (1 + np.exp(-z))
-    return 1 if prob >= 0.5 else 0
     
+    # 数据标准化
+    scaler = StandardScaler()
+    features = scaler.fit_transform(features)
+    
+    return features, labels
+
+def train_logreg(X, y, random_state=42):
+    # 创建逻辑回归模型，使用liblinear求解器
+    model = LogisticRegression(solver='liblinear', random_state=random_state)
+    model.fit(X, y)
+    return model
+
+def predict_logreg(inX, model):
+    # 使用模型进行预测
+    return int(model.predict([inX])[0])
+
+# 示例使用
 if __name__ == "__main__":
+    # 加载训练数据和测试数据
     X_train, y_train = load_data("./data/horse-colic.data")
     X_test, y_test = load_data("./data/horse-colic.test")
 
-    scaler = StandardScaler()
+    # 训练模型
-    X_train = scaler.fit_transform(X_train)
+    model = train_logreg(X_train, y_train, random_state=42)
-    X_test = scaler.transform(X_test)
 
-    X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.2, random_state=42)
+    # 进行预测
+    y_pred = [predict_logreg(x, model) for x in X_test]
 
-    best_weights = None
+    # 计算准确率
-    best_auc = 0
+    accuracy = np.mean(y_pred == y_test)
-    for iter in range(1, 1001):
+    print(f"Test Accuracy: {accuracy:.2f}")
-        weights = train_logreg(X_train, y_train, numIter=iter, learning_rate=0.01, lambda_reg=0.1, penalty='l2')
-        y_pred = [predict_logreg(x, weights) for x in X_val]
-        auc = roc_auc_score(y_val, y_pred)
-        if auc > best_auc:
-            best_auc = auc
-            best_weights = weights
-        if iter > 10 and auc == best_auc:
-            break
-
-    y_pred_test = [predict_logreg(x, best_weights) for x in X_test]
-    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)