Y label Error.

[xunmzii]

When I tried openFE, the error I got as below.
ofe = openfe() features = ofe.fit(data=X_train_feature, label=Y_train.ravel(), n_jobs=1) D:\miniconda3\lib\site-packages\sklearn\preprocessing\_label.py:133: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel(). y = column_or_1d(y, warn=True)
I guess the source code of OpenFE has not the corresponding processing about label data.

[ZhangTP1996]

When I tried openFE, the error I get as below. ofe = openfe() features = ofe.fit(data=X_train_feature, label=Y_train.ravel(), n_jobs=1) D:\miniconda3\lib\site-packages\sklearn\preprocessing\_label.py:133: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel(). y = column_or_1d(y, warn=True) I guess the source code of OpenFE have not the corresponding processing about label data.

OpenFE accepts label in a pd.DataFrame with one column. We will try to make OpenFE compatible with different input types.

[ZhangTP1996]

When I tried openFE, the error I get as below. ofe = openfe() features = ofe.fit(data=X_train_feature, label=Y_train.ravel(), n_jobs=1) D:\miniconda3\lib\site-packages\sklearn\preprocessing\_label.py:133: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel(). y = column_or_1d(y, warn=True) I guess the source code of OpenFE have not the corresponding processing about label data.

And please make sure that data and label have the same index.

[kkangliu]

As the data URL is not available, I manually downloaded the dataset from the link as below:
https://www.kaggle.com/datasets/camnugent/california-housing-prices

Then I encountered the same issue when I tried to run the provided example.py. Fortunately, I found that it can be solved by simply adding the following code after the definition of these variables into the self._evaluate() and the self.stage2_select() functions of the openfe/openfe.py:

# avoid dataframe bug
train_y = np.array(train_y)[:, 0]
train_init = np.array(train_init)[:, 0]
val_y = np.array(val_y)[:, 0]
val_init = np.array(val_init)[:, 0]

[xunmzii]

When I tried openFE, the error I get as below. ofe = openfe() features = ofe.fit(data=X_train_feature, label=Y_train.ravel(), n_jobs=1) D:\miniconda3\lib\site-packages\sklearn\preprocessing\_label.py:133: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel(). y = column_or_1d(y, warn=True) I guess the source code of OpenFE have not the corresponding processing about label data.

OpenFE accepts label in a pd.DataFrame with one column. We will try to make OpenFE compatible with different input types.

I really appreciate that and thanks a lot for your attention！

[leonleeann]

I encountered the same warnning, when I was trying to solve a classification problem instead of a regression one.
If I write a piece of experiment code that mimic the example 'IEEE', there's no such warnning.
But tons of such warnnings always appear when I passed task='classification' to openfe.fit().
It looks like that the fit() is expecting a 2D DataFrame on the parameter label, but when we do a 'classification' job, some codes inside fit() is expecting a 1D label
(我也遇到同样的问题，做回归任务不会，只有分类任务的时候，会出现大量的类似警告。就是传递task='classification'给openfe.fit()的时候。看起来openfe.fit()内部似乎有点自相矛盾：一方面它希望参数label是一个二维的DataFrame，另一方面在它内部，当做分类的时候，又希望该参数是一维的？希望这个信息有点用).

BTW, all examples in this repository are for regression instead of classification.