MetaOD
MetaOD copied to clipboard
yzhao062
Automating Outlier Detection via Meta-Learning (Code, API, and Contribution Instructions)
Variations of MetaOD are used as baselines (MetaOD_C and MetaOD_F) on the paper. Could it be possible to open-source their code? It would really help us understanding them. Also, is...
The definition of the `sigmoid_derivate` function (core.py:26) is missing `a*`. Although it doesn’t make a huge difference, since `a` is normally set to 1.
It seems like we cannot fit ndarray smaller than shape(-1,3). e.g. if we want to fit in some array of shape(-1,2):  And it will call a function in gen_meta_features,...
Hi, the paper reproducibility branch gives me an error, any idea how to tackle this? https://github.com/yzhao062/MetaOD/tree/master/paper_reproducibility
In the Example code: To generate sample data X_train, y_train, X_test, y_test = \ generate_data(n_train=1000, n_test=100, n_features=3, contamination=0.5, random_state=42) Here, the `generate_data` function was used improperly. Should be: X_train, X_test,...
Hello, I want to use MetaOD with my dataset, but when I run this code: `selected_models = select_model(X_train, n_selection=100)` but I have the next error: This is my dataset details:
On somewhat sparse data, this function ends up dividing by zero. Should there be a check for this?
