Cell2cell

New features
- Implemented in-house GSEA using gseapy. Associated code is located in
`cell2cell.datasets.gsea_data` and `cell2cell.external.gseapy`.
- Implemented a function to obtain a dataframe of lr pairs by cell pairs from a tensor decomposition
result, so it can be use to make a plot. It can compute a communication score that is by factor or
across all factors. See function `cell2cell.analysis.tensor_downstream.get_lr_by_cell_pairs()`.

Feature updates
- Added the axis names to the dataframe generated with cell2cell.analysis.tensor_downstream.get_joint_loadings(),
which correspond to the `dim1` and `dim2` parameters.
- Added the axis labels (`cm.ax_heatmap.set_xlabel()` & (`cm.ax_heatmap.set_ylabel()`) using the dataframe axis names
passed to cell2cell.plotting.factor_plot.loading_clustermap()

What's Changed
* Minor update to examples & docs by earmingol in https://github.com/earmingol/cell2cell/pull/23
* Updates for v0.6.5 by earmingol in https://github.com/earmingol/cell2cell/pull/24


**Full Changelog**: https://github.com/earmingol/cell2cell/compare/v0.6.4...v0.6.5

New features
- Added a the cell2cell.io.read_data.load_tensor() function to directly load a previously
exported interaction_tensor variable generated with Tensor-cell2cell.
- Added a new dataset from a COVID-19 study. Available in cell2cell.datasets.anndata.balf_covid().
- Added functions to create and explore directories in cell2cell.io.directories.
- Added cell2cell.io.read_data.load_tables_from_directory() to load all tables or dataframes with the same
extension that are located in such directory.

Feature updates
- Modified sparsity_fraction() and missing_fraction() methods of cell2cell.tensor.tensor.BaseTensor to return
the item in the tensorly tensor object.
- Added progress bar to cell2cell.tensor.external_scores.dataframes_to_tensor().
- Added the option to specify the backend when running cell2cell.analysis.tensor_pipelines.run_tensor_cell2cell_pipeline().

Fixed Bugs
- Implemented a way to manage duplicated instances of a LR comm score in cell2cell.tensor.external_scores.dataframes_to_tensor().
It can be controled through the parameter dup_aggregation.

What's Changed
* Code restructuring by earmingol in https://github.com/earmingol/cell2cell/pull/3
* Added core pipeline by earmingol in https://github.com/earmingol/cell2cell/pull/4
* Code reorganization by earmingol in https://github.com/earmingol/cell2cell/pull/5
* v0.5.10 by earmingol in https://github.com/earmingol/cell2cell/pull/8
* New version - v0.5.11 by earmingol in https://github.com/earmingol/cell2cell/pull/11
* Updates for v0.6.0 by earmingol in https://github.com/earmingol/cell2cell/pull/12
* Updates for v0.6.1 by earmingol in https://github.com/earmingol/cell2cell/pull/15
* Updates for v0.6.2 by earmingol in https://github.com/earmingol/cell2cell/pull/17
* Updates for v0.6.3 by earmingol in https://github.com/earmingol/cell2cell/pull/18
* Quick rebase by earmingol in https://github.com/earmingol/cell2cell/pull/20
* Updates for v0.6.4 by earmingol in https://github.com/earmingol/cell2cell/pull/21

New Contributors
* earmingol made their first contribution in https://github.com/earmingol/cell2cell/pull/3

**Full Changelog**: https://github.com/earmingol/cell2cell/commits/v0.6.4