generated from LufsX/Experiment-LogReg
This commit is contained in:
+3
-13
@@ -1,5 +1,4 @@
|
|||||||
import numpy as np
|
import numpy as np
|
||||||
import pandas as pd
|
|
||||||
|
|
||||||
"""
|
"""
|
||||||
实验说明:
|
实验说明:
|
||||||
@@ -73,18 +72,9 @@ def load_data(filepath):
|
|||||||
- np.array: 特征数据。
|
- np.array: 特征数据。
|
||||||
- np.array: 标签数据。
|
- np.array: 标签数据。
|
||||||
"""
|
"""
|
||||||
# 使用pandas读取数据,假设逗号为分隔符
|
data = np.genfromtxt(filepath, delimiter=',', dtype=float, filling_values=0)
|
||||||
data = pd.read_csv(filepath, header=None)
|
X = data[:, :-1]
|
||||||
|
y = data[:, -1].astype(int) # 将标签列转换为整数类型
|
||||||
# 将所有非数值列转换为数值型,非数值的转换为NaN,然后填充NaN为0
|
|
||||||
for col in data.columns:
|
|
||||||
if data[col].dtype == 'object':
|
|
||||||
data[col] = pd.to_numeric(data[col], errors='coerce').fillna(0)
|
|
||||||
|
|
||||||
# 将数据转换为numpy数组
|
|
||||||
X = data.iloc[:, :-1].values
|
|
||||||
y = data.iloc[:, -1].values
|
|
||||||
|
|
||||||
return X, y
|
return X, y
|
||||||
|
|
||||||
if __name__ == "__main__":
|
if __name__ == "__main__":
|
||||||
|
|||||||
Reference in New Issue
Block a user