Template
103 lines
3.0 KiB
Python
103 lines
3.0 KiB
Python
import numpy as np
|
||
|
||
"""
|
||
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"
|
||
|
||
|
||
def sigmoid(z):
|
||
"""
|
||
Sigmoid 激活函数。
|
||
"""
|
||
return 1 / (1 + np.exp(-z))
|
||
|
||
|
||
def train_logreg(X, y, learning_rate=0.01, iterations=1000):
|
||
"""
|
||
对率回归训练函数。
|
||
|
||
Args:
|
||
- X (numpy array): 特征数据。
|
||
- y (numpy array): 标签数据。
|
||
- learning_rate (float): 学习率，默认为0.01。
|
||
- iterations (int): 迭代次数，默认为1000。
|
||
|
||
Returns:
|
||
- weights (numpy array): 训练得到的权重。
|
||
"""
|
||
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
|
||
return weights
|
||
|
||
|
||
def predict_logreg(X, weights):
|
||
"""
|
||
对率回归预测函数。
|
||
|
||
Args:
|
||
- X (numpy array): 输入待分类的样本。
|
||
- weights (numpy array): 训练得到的权重。
|
||
|
||
Returns:
|
||
- numpy array: 预测的分类标签。
|
||
"""
|
||
linear_model = np.dot(X, weights)
|
||
y_predicted = sigmoid(linear_model)
|
||
return (y_predicted > 0.5).astype(int)
|
||
|
||
|
||
def load_data(filepath):
|
||
"""
|
||
从文件中加载数据，若不自行正确实现，则无法通过评测，不记录成绩。
|
||
|
||
Args:
|
||
- filepath (str): 数据文件路径。
|
||
|
||
Returns:
|
||
- X (np.array): 特征数据。
|
||
- y (np.array): 标签数据。
|
||
"""
|
||
# 使用 np.genfromtxt 加载数据，并且忽略文件中不能转换为 float 的行
|
||
# 更新分隔符为逗号，根据实际格式来修改，通常csv用','，txt文件则可能用'\t'或者' '来分隔
|
||
data = np.genfromtxt(filepath, delimiter=',', dtype=float, filling_values=np.nan)
|
||
|
||
# 删除所有包含缺失值的行
|
||
data = data[~np.isnan(data).any(axis=1)]
|
||
|
||
# 确保数据的正确性: 不同于训练集的标签列
|
||
if data.ndim == 1:
|
||
data = np.array([data])
|
||
|
||
# 假设最后一列为标签
|
||
X = data[:, :-1] # 特征
|
||
y = data[:, -1] # 标签
|
||
return X, y
|
||
|
||
|
||
if __name__ == "__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")
|
||
|
||
# 确保训练集和测试集特征数量匹配
|
||
if X_train.shape[1] != X_test.shape[1]:
|
||
raise ValueError("训练集和测试集特征数量不匹配！")
|
||
|
||
# 训练对率回归模型
|
||
weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
|
||
|
||
# 测试多个数据
|
||
y_pred = predict_logreg(X_test, weights)
|
||
|
||
# 输出部分预测结果
|
||
for i in range(min(10, len(y_pred))): # 只输出前10个预测结果
|
||
print(f"预测结果: {y_pred[i]}, 实际结果: {y_test[i]}") |