generated from LufsX/Experiment-LogReg
This commit is contained in:
+68
-84
@@ -1,99 +1,83 @@
|
||||
# function.py
|
||||
import os
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
|
||||
from sklearn.preprocessing import MinMaxScaler
|
||||
from sklearn.model_selection import train_test_split
|
||||
"""
|
||||
实验说明:
|
||||
- 自行编写实现数据加载与预测病马死亡的对率回归算法。
|
||||
注意事项:
|
||||
- 在 function.py 中实现对率回归算法。
|
||||
- 可以自行导入其他库,需要在 requirements.txt 添加依赖,若未在 requirements.txt 中添加使用到的依赖,则无法自动评测,成绩为零。
|
||||
- 自动评测脚本仅会加载 train_logreg、predict_logreg 和 load_data 函数,请勿修改函数名。
|
||||
测评环境:
|
||||
- CPU: Intel Xeon(R) CPU E3-1231 v3 @ 3.40GHz
|
||||
- OS: Ubuntu 22.04.4 LTS
|
||||
- Python: 3.10.12
|
||||
- numpy: 2.1.1
|
||||
"""
|
||||
# Sigmoid 函数
|
||||
def sigmoid(z):
|
||||
return 1 / (1 + np.exp(-z))
|
||||
"""
|
||||
请在这里填写学号和姓名,不填写即成绩无效。
|
||||
"""
|
||||
id = "202210423223"
|
||||
name = "李顺潮"
|
||||
|
||||
def load_data(filepath):
|
||||
"""从文件中加载数据,处理不规则的字段数量和缺失值"""
|
||||
data = []
|
||||
with open(filepath, 'r') as f:
|
||||
for line in f:
|
||||
fields = line.strip().split()
|
||||
# 处理不规则的字段数量,这里选择忽略多余的字段
|
||||
if len(fields) > 28:
|
||||
fields = fields[:28]
|
||||
# 替换 '?' 为 NaN
|
||||
fields = [np.nan if x == '?' else x for x in fields]
|
||||
data.append(fields)
|
||||
|
||||
# 使用 pandas 创建 DataFrame
|
||||
df = pd.DataFrame(data)
|
||||
# 删除包含 NaN 的行
|
||||
df.dropna(inplace=True)
|
||||
# 转换为数值类型
|
||||
df = df.astype(float)
|
||||
|
||||
X = df.iloc[:, :-1].values
|
||||
y = df.iloc[:, -1].values
|
||||
return X, y
|
||||
except pd.errors.ParserError as e:
|
||||
print(f"数据加载错误: {e}")
|
||||
return None
|
||||
except Exception as e:
|
||||
print(f"发生未知错误: {e}")
|
||||
return None
|
||||
|
||||
def sigmoid(z):
|
||||
"""
|
||||
Sigmoid 函数,用于对率回归的激活函数。
|
||||
|
||||
Args:
|
||||
- z (numpy array): 输入值。
|
||||
|
||||
Returns:
|
||||
- numpy array: Sigmoid 函数输出。
|
||||
"""
|
||||
return 1 / (1 + np.exp(-z))
|
||||
|
||||
def train_logreg(X, y, other_params=None):
|
||||
"""
|
||||
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**。
|
||||
|
||||
Returns:
|
||||
- numpy array: 训练得到的权重。
|
||||
"""
|
||||
# 对率回归训练函数
|
||||
def train_logreg(X, y, learning_rate=0.01, iterations=1000):
|
||||
X = np.hstack((np.ones((X.shape[0], 1)), X)) # 在特征前添加一列全为1的列
|
||||
m, n = X.shape
|
||||
weights = np.zeros(n) # 初始化权重
|
||||
learning_rate = 0.01
|
||||
num_iterations = 1000
|
||||
weights = np.zeros(n)
|
||||
|
||||
for _ in range(num_iterations):
|
||||
for _ in range(iterations):
|
||||
z = np.dot(X, weights)
|
||||
predictions = sigmoid(z)
|
||||
# 计算梯度
|
||||
gradient = np.dot(X.T, (predictions.astype(float) - y.astype(float))) / m
|
||||
# 更新权重
|
||||
predictions = 1 / (1 + np.exp(-z))
|
||||
gradient = np.dot(X.T, (predictions - y)) / m
|
||||
weights -= learning_rate * gradient
|
||||
|
||||
return weights
|
||||
|
||||
# 对率回归预测函数
|
||||
# 对率回归预测函数,支持多类分类
|
||||
def predict_logreg(inX, weights):
|
||||
"""
|
||||
对率回归预测函数。
|
||||
inX = np.insert(inX, 0, 1) # 在特征前添加1作为偏置项
|
||||
prob = 1 / (1 + np.exp(-np.dot(inX, weights)))
|
||||
|
||||
Args:
|
||||
- inX (numpy array): 输入待分类的样本。
|
||||
- weights (numpy array): 训练得到的权重。
|
||||
if prob < 0.5:
|
||||
return 0
|
||||
elif prob >= 0.5 and prob < 1.0:
|
||||
return 1
|
||||
else:
|
||||
return 2 # 确保返回3个类别中的一个
|
||||
|
||||
Returns:
|
||||
- int: 预测的分类标签。
|
||||
"""
|
||||
z = np.dot(inX, weights)
|
||||
probability = sigmoid(z)
|
||||
return 1 if probability >= 0.5 else 0
|
||||
# 从文件中加载数据
|
||||
def load_data(filepath):
|
||||
data = pd.read_csv(filepath, header=None, na_values='?', delim_whitespace=True)
|
||||
data.fillna(0, inplace=True)
|
||||
X = data.iloc[:, :-1].to_numpy() # 特征
|
||||
y = data.iloc[:, -1].to_numpy() # 标签
|
||||
return X, y
|
||||
# 准确率计算函数
|
||||
def calculate_accuracy(X, y, weights):
|
||||
predictions = np.array([predict_logreg(x, weights) for x in X])
|
||||
accuracy = np.mean(predictions == y)
|
||||
return accuracy
|
||||
|
||||
if __name__ == "__main__":
|
||||
# 加载训练集
|
||||
X_train, y_train = load_data("./data/horse-colic.data")
|
||||
# 训练模型
|
||||
weights = train_logreg(X_train, y_train)
|
||||
# 测试预测
|
||||
sample_index = 0 # 选择一个样本进行测试
|
||||
y_pred = predict_logreg(X_train[sample_index], weights)
|
||||
print(f"预测结果: {y_pred}, 实际结果: {y_train[sample_index]}")
|
||||
if __name__ == "__main__":
|
||||
# 加载训练集和测试集
|
||||
X_train, y_train = load_data("E:\\Edge站内文件下载\\病马数据集\\horse-colic.data")
|
||||
X_test, y_test = load_data( "E:\\Edge站内文件下载\\病马数据集\\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]}")
|
||||
|
||||
|
||||
# 计算并输出模型的准确率
|
||||
accuracy = calculate_accuracy(X_test, y_test, weights)
|
||||
print(f"模型的准确率: {accuracy:.4f}")
|
||||
Reference in New Issue
Block a user