generated from LufsX/Experiment-LogReg
This commit is contained in:
+12
-4
@@ -91,9 +91,18 @@ def load_data(filepath):
|
||||
- X (np.array): 特征数据。
|
||||
- y (np.array): 标签数据。
|
||||
"""
|
||||
# 使用numpy的genfromtxt函数读取数据,将问号替换为NaN
|
||||
data = np.genfromtxt(filepath, delimiter=',', invalid_raise=False, filling_values=np.nan)
|
||||
|
||||
# 尝试使用numpy的genfromtxt函数读取数据,自动检测分隔符
|
||||
try:
|
||||
data = np.genfromtxt(filepath, delimiter=None, invalid_raise=False, filling_values=np.nan)
|
||||
except ValueError as e:
|
||||
print(f"Error reading file: {e}")
|
||||
return None, None
|
||||
|
||||
# 如果数据文件中只有一列,可能是分隔符没有正确识别
|
||||
if data.ndim == 1:
|
||||
print("Data file may have an incorrect delimiter or only contains one column.")
|
||||
return None, None
|
||||
|
||||
# 丢弃完全为NaN的行
|
||||
data = data[~np.isnan(data).any(axis=1)]
|
||||
|
||||
@@ -102,7 +111,6 @@ def load_data(filepath):
|
||||
y = data[:, -1]
|
||||
|
||||
return X, y
|
||||
|
||||
if __name__ == "__main__":
|
||||
# 加载训练集
|
||||
X_train, y_train = load_data("./data/horse-colic.data")
|
||||
|
||||
Reference in New Issue
Block a user