diff --git a/function.py b/function.py index 409b1ac..69b1916 100644 --- a/function.py +++ b/function.py @@ -21,11 +21,15 @@ import numpy as np """ 请在这里填写学号和姓名,不填写即成绩无效。 """ -id = "202210423xxx" -name = "test_name" +id = "202210423124" +name = "刘子豪" # 这里写自己的代码实现 +def sigmoid(z): + return 1 / (1 + np.exp(-z)) #用于将数据转化成一个0 - 1之间的概率值 + + def train_logreg(X, y, other_params="你自己设置一些其它参数"): """ 对率回归训练函数。 @@ -38,6 +42,14 @@ def train_logreg(X, y, other_params="你自己设置一些其它参数"): Returns: - numpy array: 训练得到的权重。 """ + m, n = X.shape + weights = np.zeros(n) + for _ in range(iterations): + predictions = sigmoid(np.dot(X, weights)) + errors = y - predictions + gradient = np.dot(X.T, errors) / m + weights += learning_rate * gradient + return weights def predict_logreg(inX, weights): @@ -51,6 +63,8 @@ def predict_logreg(inX, weights): Returns: - int: 预测的分类标签。 """ + probability = sigmoid(np.dot(inX, weights)) + return 1 if probability >= 0.5 else 0 # 这里也写自己的代码实现 @@ -65,6 +79,16 @@ def load_data(filepath): - np.array: 特征数据。 - np.array: 标签数据。 """ + data = [] + labels = [] + with open(filepath, 'r') as file: + for line in file: + fields = line.strip().split() + if '?' in fields: + continue # 跳过包含缺失值的行 + data.append([float(x) for x in fields[:-1]]) + labels.append(int(fields[-1])) # 假设标签在最后一列 + return np.array(data), np.array(labels) if __name__ == "__main__":