generated from LufsX/Experiment-LogReg
This commit is contained in:
+51
-89
@@ -1,133 +1,95 @@
|
||||
import numpy as np
|
||||
from sklearn.linear_model import LogisticRegression
|
||||
from sklearn.metrics import accuracy_score
|
||||
from sklearn.impute import SimpleImputer
|
||||
|
||||
id = "202210423213"
|
||||
name = "熊浩燃"
|
||||
|
||||
|
||||
def sigmoid(z):
|
||||
"""计算Sigmoid函数值"""
|
||||
return 1 / (1 + np.exp(-z))
|
||||
|
||||
|
||||
def train_logreg(X, y, learning_rate=0.01, iterations=1000, initial_weights=None):
|
||||
"""
|
||||
对率回归训练函数，支持暴力搜索超参数。
|
||||
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
|
||||
"""
|
||||
|
||||
id = "202210423xxx" # 请填写学号
|
||||
name = "test_name" # 请填写姓名
|
||||
|
||||
|
||||
def train_logreg(X, y, max_iter=1000, C=1.0):
|
||||
"""
|
||||
对率回归训练函数，使用sklearn的LogisticRegression。
|
||||
|
||||
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): 梯度下降迭代次数，默认为1000。
|
||||
- initial_weights (numpy array): 预设初始权重，可选。
|
||||
- max_iter (int): 最大迭代次数。
|
||||
- C (float): 正则化强度。
|
||||
|
||||
Returns:
|
||||
- numpy array: 训练得到的权重。
|
||||
- sklearn LogisticRegression: 训练好的模型。
|
||||
"""
|
||||
# 初始化权重
|
||||
weights = initial_weights if initial_weights is not None else np.zeros(X.shape[1])
|
||||
|
||||
# 梯度下降
|
||||
for i in range(iterations):
|
||||
predictions = sigmoid(np.dot(X, weights))
|
||||
errors = y - predictions
|
||||
weights += learning_rate * np.dot(X.T, errors)
|
||||
|
||||
return weights
|
||||
# 使用sklearn的LogisticRegression模型
|
||||
model = LogisticRegression(max_iter=max_iter, C=C)
|
||||
model.fit(X, y)
|
||||
return model
|
||||
|
||||
|
||||
def predict_logreg(inX, weights):
|
||||
def predict_logreg(inX, model):
|
||||
"""
|
||||
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。
|
||||
- model (LogisticRegression): 训练得到的LogisticRegression模型。
|
||||
|
||||
Returns:
|
||||
- int: 预测的分类标签。
|
||||
"""
|
||||
probability = sigmoid(np.dot(inX, weights))
|
||||
return 1 if probability >= 0.5 else 0
|
||||
return int(model.predict(inX.reshape(1, -1))[0])
|
||||
|
||||
|
||||
def load_data(filepath):
|
||||
"""
|
||||
从文件中加载数据并填充缺失值。确保每列的缺失值被正确填充为该列的均值。
|
||||
从文件中加载数据并填充缺失值。
|
||||
|
||||
Args:
|
||||
- filepath (str): 数据文件路径。
|
||||
|
||||
Returns:
|
||||
- np.array: 特征数据。
|
||||
- np.array: 填充缺失值后的特征数据。
|
||||
- np.array: 标签数据。
|
||||
"""
|
||||
# 加载数据，处理缺失值（使用 nan 表示缺失数据）
|
||||
data = np.genfromtxt(filepath, delimiter=",", dtype=float, missing_values="?", filling_values=np.nan)
|
||||
# 加载数据
|
||||
data = np.loadtxt(filepath, delimiter=",", dtype=float)
|
||||
|
||||
# 特征和标签分离
|
||||
X = data[:, :-1]
|
||||
y = data[:, -1]
|
||||
# 分割特征和标签
|
||||
X = data[:, :-1] # 特征
|
||||
y = data[:, -1] # 标签
|
||||
|
||||
# 对每列特征数据进行缺失值填充
|
||||
col_means = np.nanmean(X, axis=0)
|
||||
inds = np.where(np.isnan(X))
|
||||
X[inds] = np.take(col_means, inds[1])
|
||||
# 填充缺失值，使用列的平均值
|
||||
imputer = SimpleImputer(strategy="mean")
|
||||
X = imputer.fit_transform(X)
|
||||
|
||||
return X, y
|
||||
|
||||
|
||||
def brute_force_search(X_train, y_train, X_val, y_val, learning_rates, iterations_list):
|
||||
"""
|
||||
通过暴力搜索选择最佳的学习率和迭代次数。
|
||||
|
||||
Args:
|
||||
- X_train, y_train: 训练集特征和标签。
|
||||
- X_val, y_val: 验证集特征和标签。
|
||||
- learning_rates (list of floats): 学习率列表。
|
||||
- iterations_list (list of ints): 迭代次数列表。
|
||||
|
||||
Returns:
|
||||
- tuple: 最佳学习率，最佳迭代次数，最佳权重。
|
||||
"""
|
||||
best_acc = 0
|
||||
best_params = (0, 0)
|
||||
best_weights = None
|
||||
|
||||
for lr in learning_rates:
|
||||
for iters in iterations_list:
|
||||
weights = train_logreg(X_train, y_train, learning_rate=lr, iterations=iters)
|
||||
y_pred = [predict_logreg(x, weights) for x in X_val]
|
||||
acc = accuracy_score(y_val, y_pred)
|
||||
|
||||
if acc > best_acc:
|
||||
best_acc = acc
|
||||
best_params = (lr, iters)
|
||||
best_weights = weights
|
||||
|
||||
print(f"最佳学习率: {best_params[0]}, 最佳迭代次数: {best_params[1]}, 验证集准确率: {best_acc}")
|
||||
return best_params[0], best_params[1], best_weights
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
# 加载训练集和测试集
|
||||
# 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")
|
||||
|
||||
# 使用暴力搜索找到最佳的超参数组合
|
||||
learning_rates = [0.001, 0.01, 0.1]
|
||||
iterations_list = [500, 1000, 1500]
|
||||
best_lr, best_iters, best_weights = brute_force_search(X_train, y_train, X_test, y_test, learning_rates, iterations_list)
|
||||
# 训练对率回归模型
|
||||
model = train_logreg(X_train, y_train, max_iter=1000, C=1.0)
|
||||
|
||||
# 使用 sklearn 进行对比
|
||||
sklearn_model = LogisticRegression(max_iter=best_iters, solver='lbfgs')
|
||||
sklearn_model.fit(X_train, y_train)
|
||||
y_pred_sklearn = sklearn_model.predict(X_test)
|
||||
sklearn_acc = accuracy_score(y_test, y_pred_sklearn)
|
||||
print(f"Sklearn Logistic Regression 准确率: {sklearn_acc}")
|
||||
|
||||
# 测试对率回归预测
|
||||
y_pred_custom = [predict_logreg(x, best_weights) for x in X_test]
|
||||
custom_acc = accuracy_score(y_test, y_pred_custom)
|
||||
print(f"自实现 Logistic Regression 准确率: {custom_acc}")
|
||||
# 测试单个数据
|
||||
y_pred = predict_logreg(X_test[11], model)
|
||||
print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
|
||||
|
||||
Reference in New Issue
Block a user