generated from LufsX/Experiment-LogReg
This commit is contained in:
+47
-15
@@ -1,4 +1,3 @@
|
||||
# function.py
|
||||
import numpy as np
|
||||
|
||||
"""
|
||||
@@ -17,58 +16,90 @@ import numpy as np
|
||||
- numpy: 2.1.1
|
||||
"""
|
||||
|
||||
|
||||
"""
|
||||
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 = "202210423118" # 请填写你的学号
|
||||
name = "刘国庆" # 请填写你的姓名
|
||||
|
||||
|
||||
# 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"):
|
||||
# Sigmoid函数
|
||||
def sigmoid(z):
|
||||
return 1 / (1 + np.exp(-z))
|
||||
|
||||
|
||||
# 对率回归训练函数
|
||||
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, 默认值为0.01。
|
||||
- iterations (int): 迭代次数, 默认值为1000。
|
||||
|
||||
Returns:
|
||||
- numpy array: 训练得到的权重。
|
||||
- float: 训练得到的偏置。
|
||||
"""
|
||||
n_samples, n_features = X.shape
|
||||
weights = np.zeros(n_features)
|
||||
bias = 0
|
||||
|
||||
# 梯度下降法
|
||||
for i in range(iterations):
|
||||
linear_model = np.dot(X, weights) + bias
|
||||
y_pred = sigmoid(linear_model)
|
||||
|
||||
# 计算梯度
|
||||
dw = (1 / n_samples) * np.dot(X.T, (y_pred - y))
|
||||
db = (1 / n_samples) * np.sum(y_pred - y)
|
||||
|
||||
# 更新权重和偏置
|
||||
weights -= learning_rate * dw
|
||||
bias -= learning_rate * db
|
||||
|
||||
return weights, bias
|
||||
|
||||
|
||||
def predict_logreg(inX, weights):
|
||||
# 对率回归预测函数
|
||||
def predict_logreg(inX, weights, bias):
|
||||
"""
|
||||
对率回归预测函数。
|
||||
|
||||
Args:
|
||||
- inX (numpy array): 输入待分类的样本。
|
||||
- weights (numpy array): 训练得到的权重。
|
||||
- bias (float): 训练得到的偏置。
|
||||
|
||||
Returns:
|
||||
- int: 预测的分类标签。
|
||||
- int: 预测的分类标签 (0 或 1)。
|
||||
"""
|
||||
linear_model = np.dot(inX, weights) + bias
|
||||
y_pred = sigmoid(linear_model)
|
||||
return 1 if y_pred >= 0.5 else 0
|
||||
|
||||
|
||||
# 这里也写自己的代码实现
|
||||
# 数据加载函数
|
||||
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**。
|
||||
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 = np.loadtxt(filepath, delimiter=' ', dtype=float)
|
||||
X = data[:, :-1] # 所有列(除了最后一列)是特征
|
||||
y = data[:, -1] # 最后一列是标签
|
||||
return X, y
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
# 以下代码可用于测试,可自行随意修改
|
||||
# 加载训练集
|
||||
X_train, y_train = load_data("./data/horse-colic.data")
|
||||
|
||||
@@ -76,8 +107,9 @@ 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, bias = 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)
|
||||
y_pred = predict_logreg(X_test[11], weights, bias)
|
||||
print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
|
||||
|
||||
|
||||
Reference in New Issue
Block a user