diff --git a/function.py b/function.py index 9fdaf87..cd966ee 100644 --- a/function.py +++ b/function.py @@ -85,7 +85,13 @@ def load_data(filepath): for line in lines: parts = line.strip().split(',') label = int(parts[-1]) - features.append([float(x) for x in parts[:-1]]) + feature_list = [] + for x in parts[:-1]: + if x == '?': + feature_list.append(0) # 用0代替缺失值 + else: + feature_list.append(float(x)) + features.append(feature_list) labels.append(label) return np.array(features), np.array(labels) @@ -99,14 +105,4 @@ if __name__ == "__main__": # 预测 predictions = [predict_logreg(X_train[i], weights) for i in range(X_train.shape[0])] # 打印预测结果 - print(predictions) - - # 加载测试集 - X_test, y_test = load_data("./data/horse-colic.test") - - # 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 - y_pred = predict_logreg(X_test[11], weights) - print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}") + print(predictions) \ No newline at end of file