generated from LufsX/Experiment-LogReg
This commit is contained in:
+21
@@ -4,6 +4,11 @@ from sklearn.preprocessing import StandardScaler
|
||||
from sklearn.model_selection import train_test_split, GridSearchCV
|
||||
from sklearn.linear_model import LogisticRegression
|
||||
|
||||
|
||||
id = "202210423130"
|
||||
name = "董秋"
|
||||
|
||||
|
||||
def load_data(filepath):
|
||||
data = []
|
||||
labels = []
|
||||
@@ -32,12 +37,24 @@ def load_data(filepath):
|
||||
|
||||
return np.array(data), np.array(labels)
|
||||
|
||||
|
||||
def preprocess_data(X):
|
||||
# 特征标准化
|
||||
scaler = StandardScaler()
|
||||
return scaler.fit_transform(X)
|
||||
|
||||
|
||||
def train_logreg(X_train, y_train):
|
||||
"""
|
||||
逻辑回归训练函数,使用网格搜索优化超参数。
|
||||
|
||||
Args:
|
||||
- X_train (numpy array): 特征数据。
|
||||
- y_train (numpy array): 标签数据。
|
||||
|
||||
Returns:
|
||||
- LogisticRegression: 训练得到的最佳模型。
|
||||
"""
|
||||
# 定义要调优的超参数范围
|
||||
param_grid = {
|
||||
'C': [0.001, 0.01, 0.1, 1, 10, 100], # 正则化参数
|
||||
@@ -56,12 +73,15 @@ def train_logreg(X_train, y_train):
|
||||
|
||||
return grid_search.best_estimator_
|
||||
|
||||
|
||||
def predict_logreg(inX, weights):
|
||||
"""
|
||||
逻辑回归预测函数。
|
||||
|
||||
Args:
|
||||
- inX (numpy array): 输入待分类的样本。
|
||||
- weights (numpy array): 训练得到的权重。
|
||||
|
||||
Returns:
|
||||
- int: 预测的分类标签。
|
||||
"""
|
||||
@@ -69,6 +89,7 @@ def predict_logreg(inX, weights):
|
||||
prediction_prob = 1 / (1 + np.exp(-z))
|
||||
return 1 if prediction_prob >= 0.5 else 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
# 加载数据集
|
||||
X, y = load_data("./data/horse-colic.data")
|
||||
|
||||
Reference in New Issue
Block a user