generated from LufsX/Experiment-LogReg
This commit is contained in:
+43
-6
@@ -23,23 +23,37 @@ import numpy as np
|
||||
姓名请直接**填写中文**
|
||||
例如: name = "张三"
|
||||
"""
|
||||
id = "202210423xxx"
|
||||
name = "test_name"
|
||||
id = "202210423629"
|
||||
name = "Tanjunfeng"
|
||||
|
||||
|
||||
# 这里写自己的代码实现
|
||||
def train_logreg(X, y, other_params="你自己设置一些其它参数"):
|
||||
|
||||
# 这里写自己的代码实现
|
||||
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。
|
||||
- other_params (str): 其它参数,可选设置。若需设置其它参数,必须设置其默认值,否则将**无法通过**自动评测,**成绩为零**。
|
||||
- learning_rate (float): 学习率,默认0.01。
|
||||
- iterations (int): 迭代次数,默认1000。
|
||||
|
||||
Returns:
|
||||
- numpy array: 训练得到的权重。
|
||||
"""
|
||||
m, n = X.shape
|
||||
X = np.hstack((np.ones((m, 1)), X)) # 添加偏置项
|
||||
weights = np.zeros(n + 1)
|
||||
|
||||
for _ in range(iterations):
|
||||
z = np.dot(X, weights)
|
||||
h = 1 / (1 + np.exp(-z))
|
||||
gradient = np.dot(X.T, (h - y)) / m # 计算梯度
|
||||
weights -= learning_rate * gradient # 更新权重
|
||||
|
||||
return weights
|
||||
|
||||
|
||||
def predict_logreg(inX, weights):
|
||||
@@ -53,6 +67,10 @@ def predict_logreg(inX, weights):
|
||||
Returns:
|
||||
- int: 预测的分类标签。
|
||||
"""
|
||||
inX = np.insert(inX, 0, 1) # 添加偏置项
|
||||
z = np.dot(inX, weights)
|
||||
h = 1 / (1 + np.exp(-z))
|
||||
return int(h >= 0.5)
|
||||
|
||||
|
||||
# 这里也写自己的代码实现
|
||||
@@ -61,12 +79,25 @@ 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:
|
||||
- directory (str): 数据文件路径。
|
||||
- filepath (str): 数据文件路径。
|
||||
|
||||
Returns:
|
||||
- np.array: 特征数据。
|
||||
- np.array: 标签数据。
|
||||
"""
|
||||
data = []
|
||||
with open(filepath, 'r') as file:
|
||||
for line in file:
|
||||
line = line.strip().split()
|
||||
if '?' in line:
|
||||
continue # 跳过包含缺失值的行
|
||||
data.append([float(x) for x in line])
|
||||
data = np.array(data)
|
||||
X = data[:, :-1]
|
||||
y = data[:, -1]
|
||||
# 将标签转换为二分类1: 存活,0: 死亡或安乐死
|
||||
y = np.where(y == 1, 0, 1)
|
||||
return X, y
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
@@ -78,8 +109,14 @@ if __name__ == "__main__":
|
||||
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)
|
||||
weights = train_logreg(X_train, y_train, learning_rate=0.001, iterations=5000)
|
||||
|
||||
# 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]}")
|
||||
|
||||
# 可选:计算测试集上的准确率
|
||||
correct = sum(predict_logreg(X_test[i], weights) == y_test[i] for i in range(len(X_test)))
|
||||
accuracy = correct / len(X_test)
|
||||
print(f"模型在测试集上的准确率: {accuracy * 100:.2f}%")
|
||||
|
||||
|
||||
Reference in New Issue
Block a user