diff --git a/function.py b/function.py index ca396fa..85c93ae 100644 --- a/function.py +++ b/function.py @@ -1,69 +1,140 @@ +# function.py 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: +- 自行编写实现数据加载与预测病马死亡的对率回归算法。 + +注意事项: +- 在 function.py 中实现对率回归算法。 +- 可以自行导入其他库，需要在 requirements.txt 添加依赖，若未在 requirements.txt 中添加使用到的依赖，则无法自动评测，成绩为零。 +- 自动评测脚本仅会加载 train_logreg、predict_logreg 和 load_data 函数，请勿修改函数名。 + +测评环境: +- CPU: Intel Xeon(R) CPU E3-1231 v3 @ 3.40GHz +- OS: Ubuntu 22.04.4 LTS +- Python: 3.10.12 +- numpy: 2.1.1 +""" + """ 请在这里填写学号和姓名，不填写即成绩无效。 """ -id = "202210423224" -name = "吴杨洋" +id = "202210423221" +name = "廖子豪" +def load_data(filepath): + file = open(filepath) + fr = file.readlines() + data_list = [] + y = [] + 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 sigmoid(z): - return 1 / (1 + np.exp(-z)) - - -def train_logreg(X, y, learning_rate=0.01, iterations=1000): +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 i in range(iterations): - linear_model = np.dot(X, weights) - y_predicted = sigmoid(linear_model) - gradient = np.dot(X.T, (y_predicted - y)) / m - weights -= learning_rate * gradient + 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) + reg_term = 2 * lambda_reg * weights + gradient -= reg_term / len(batch_y) + weights += learning_rate * gradient return weights - def predict_logreg(inX, weights): - linear_model = np.dot(inX, weights) - y_predicted = sigmoid(linear_model) - return 1 if y_predicted > 0.5 else 0 - - -def load_data(filepath): - data = np.genfromtxt(filepath, delimiter=' ', dtype=float) - X = data[:, :-1] - y = data[:, -1] - return X, y - - -def standardize(X): - mean = X.mean(axis=0) - std = X.std(axis=0) - return (X - mean) / std, mean, std - - -def main(): - # 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") - - # 标准化特征数据 - X_train, mean, std = standardize(X_train) - X_test = (X_test - mean) / std - - # 训练对率回归模型 - weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000) - - # 测试单个数据 - correct_predictions = 0 - for i in range(X_test.shape[0]): - y_pred = predict_logreg(X_test[i], weights) - if y_pred == y_test[i]: - correct_predictions += 1 - - accuracy = correct_predictions / X_test.shape[0] - print(f"Accuracy: {accuracy:.2f}") - + z = np.dot(inX, weights) + prob = 1 / (1 + np.exp(-z)) + return 1 if prob >= 0.5 else 0 if __name__ == "__main__": - main() \ No newline at end of file + X_train, y_train = load_data("./data/horse-colic.data") + X_test, y_test = load_data("./data/horse-colic.test") + + scaler = StandardScaler() + X_train = scaler.fit_transform(X_train) + 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) + + best_weights = None + best_auc = 0 + for iter in range(1, 1001): + weights = train_logreg(X_train, y_train, numIter=iter, learning_rate=0.01, lambda_reg=0.1) + 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) \ No newline at end of file