generated from LufsX/Experiment-LogReg
This commit is contained in:
+17
-5
@@ -85,12 +85,24 @@ def load_data(filepath):
|
||||
- np.array: 特征数据。
|
||||
- np.array: 标签数据。
|
||||
"""
|
||||
data = np.loadtxt(filepath, delimiter=',')
|
||||
X = data[:, :-1]
|
||||
y = data[:, -1]
|
||||
# 读取数据,假设数据是用空格分隔的,并且最后一列是标签
|
||||
data = []
|
||||
with open(filepath, 'r') as file:
|
||||
for line in file:
|
||||
# 分割行,并去除任何可能的空白字符
|
||||
parts = [part.strip() for part in line.split()]
|
||||
# 将缺失值'?'替换为0(或者你可以选择其他适当的处理方式)
|
||||
features = [float(part) if part != '?' else 0 for part in parts[:-1]]
|
||||
# 将标签从2转换为1(如果原始标签是1和2的话)
|
||||
label = int(parts[-1]) - 1 # 假设原始标签是1和2,转换为0和1
|
||||
data.append(features + [label])
|
||||
|
||||
# 将标签转换为0和1)假设原始标签为1和2)
|
||||
y = np.where(y == 1, 0, 1)
|
||||
# 将数据转换为numpy数组
|
||||
data_array = np.array(data)
|
||||
|
||||
# 分离特征和标签
|
||||
X = data_array[:, :-1] # 所有行,除了最后一列
|
||||
y = data_array[:, -1] # 所有行的最后一列
|
||||
|
||||
return X, y
|
||||
|
||||
|
||||
Reference in New Issue
Block a user