The project is the last output of the sharpen.ipynb file. Open the project in a jupyter notebook, making sure to have the specified data files present. These are the folder 7td, the folder "765 text data" renamed. The folder "example_data_set_1" from the project https://youngjookim.github.io/sdr/. And the files "atush_v0","atush_v1","ipums_v0", and "ipums_v1", where the v1's are just the v0's with at least the rows with string data deleted.

ALTERNATIVELY! The project can be viewed at https://colab.research.google.com/drive/1mwK-e_A2gzwI1lE5MBSQDzVjbq4DYFN3#scrollTo=bfb03011. In which case you should have the appropriate files in your root google drive folder. Just run all cells (it will take a few minutes)...

The following libraries were used:

keras.datasets numpy umap-learn seaborn matplotlib sklearn pandas ipywidgets IPython.display

Note! umap should be installed with: pip install umap-learn