generated from LufsX/Experiment-LogReg
This commit is contained in:
+8
-11
@@ -16,16 +16,16 @@ import numpy as np
|
||||
id = "202210423208"
|
||||
name = "刘义天"
|
||||
|
||||
# 加载数据并添加特征交互项
|
||||
# 加载数据并添加非线性特征
|
||||
def load_data(filepath):
|
||||
"""
|
||||
从文件中加载数据并生成特征交互项。
|
||||
从文件中加载数据并生成非线性特征。
|
||||
|
||||
Args:
|
||||
- filepath (str): 数据文件路径
|
||||
|
||||
Returns:
|
||||
- X (numpy array): 包含特征交互项的特征数据
|
||||
- X (numpy array): 包含非线性特征的特征数据
|
||||
- y (numpy array): 标签数据
|
||||
"""
|
||||
# 读取数据,指定分隔符为空格,缺失值符号为 '?'
|
||||
@@ -44,15 +44,12 @@ def load_data(filepath):
|
||||
X = data[:, :-1]
|
||||
y = data[:, -1]
|
||||
|
||||
# 生成特征交互项
|
||||
n = X.shape[1]
|
||||
interaction_features = []
|
||||
for i in range(n):
|
||||
for j in range(i + 1, n):
|
||||
interaction_features.append((X[:, i] * X[:, j]).reshape(-1, 1))
|
||||
# 生成非线性特征 (平方和对数)
|
||||
square_features = X ** 2
|
||||
log_features = np.log1p(X) # 使用 log1p 避免 log(0)
|
||||
|
||||
# 将交互特征添加到原特征集
|
||||
X = np.hstack([X] + interaction_features)
|
||||
# 将非线性特征添加到原特征集
|
||||
X = np.hstack([X, square_features, log_features])
|
||||
|
||||
return X, y
|
||||
|
||||
|
||||
Reference in New Issue
Block a user