mofax
mofax copied to clipboard
bioFAM
Work with trained factor models in Python
When running `mfx.plot_weights()` I've tried the following codes but all output plots with all factors `mfx.plot_weights(m, factor=2, n_features=2)` `mfx.plot_weights(m, factor='Factor2', n_features=2)`
Hi, When using the function mfx.plot_r2_barplot() with group_label, I get the following error message: File ~/miniconda3/envs/scanpy/lib/python3.9/site-packages/mofax/plot_variance.py:237, in plot_r2_barplot(model, factors, view, groups_df, group_label, x, y, groupby, xtic klabels_size, linewidth, stacked, **kwargs)...
Removes the warning from pandas triggered by using append() to extend the r2 dataframe by replacing each call to r2_df.append() with a call to pd.concat()
Added per_factor=True to the get_r2 call on the plot_r2 function, allowing to use a group_label without running into errors. Otherwise the r2 dataframe is generated per view and group only,...
Hi I am using mofax to interpret some MEFISTO analyses and tried to plot the factors. When inspecting the plots I realised that they don't match my training setup. Upon...
Title says it all. Should also be fixed here: https://github.com/scverse/muon-tutorials/blame/2457af8b9155678dd9ec31f06672af0e3bb75c5b/CLL.ipynb#L675
This PR makes sure that the metadata is checked for each view individually. If this is not the case, then a view without metadata is assumed to have metadat as...
We packaged this tool for [GNU Guix](https://guix.gnu.org/), the reproducible package manager, but encountered a failure in the TestMofaModelMethods.test_get_methods test case when running the tests for the mofax project. The test...
Is there any way to provide custom names/labels as string for the factors? Either via the `hdf5` format or after loading the model on `mofax`.
