├── .gitignore ├── .gitmodules ├── Untitled.ipynb ├── data ├── repos.tsv └── urls ├── gitenberg-read-metadata.py ├── gitenbergScrape.py ├── gut-aus.ipynb ├── gut-aus2.ipynb ├── gut-aus3.ipynb ├── gut-rdf.ipynb ├── parseRDF.py ├── pg-add-amazon.ipynb ├── pg-add-dbpedia.ipynb ├── pg-add-goodreads-Copy1.ipynb ├── pg-add-goodreads.ipynb ├── pg-add-google-books.ipynb ├── pg-cleanup.ipynb ├── pg-collapse-volumes.ipynb ├── pg-get-corpora.ipynb ├── pg-get-filenames.ipynb ├── pg-metadata-rdf.hdf ├── pg-pr-eng-add-dbpedia.ipynb ├── pg-pr-eng-by-author.ipynb ├── pg-pr-eng-clean-text.ipynb ├── pg-pr-eng-merge-duplicates.ipynb ├── pg-vectorize.ipynb ├── pg-vectorize2.ipynb ├── pr-extract-text.ipynb ├── pr-metadata.ipynb └── pr-metadata2.ipynb /.gitignore: -------------------------------------------------------------------------------- 1 | secrets.py 2 | -------------------------------------------------------------------------------- /.gitmodules: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/.gitmodules -------------------------------------------------------------------------------- /Untitled.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/Untitled.ipynb -------------------------------------------------------------------------------- /data/repos.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/data/repos.tsv -------------------------------------------------------------------------------- /data/urls: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/data/urls -------------------------------------------------------------------------------- /gitenberg-read-metadata.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/gitenberg-read-metadata.py -------------------------------------------------------------------------------- /gitenbergScrape.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/gitenbergScrape.py -------------------------------------------------------------------------------- /gut-aus.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/gut-aus.ipynb -------------------------------------------------------------------------------- /gut-aus2.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/gut-aus2.ipynb -------------------------------------------------------------------------------- /gut-aus3.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/gut-aus3.ipynb -------------------------------------------------------------------------------- /gut-rdf.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/gut-rdf.ipynb -------------------------------------------------------------------------------- /parseRDF.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/parseRDF.py -------------------------------------------------------------------------------- /pg-add-amazon.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/pg-add-amazon.ipynb -------------------------------------------------------------------------------- /pg-add-dbpedia.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/pg-add-dbpedia.ipynb -------------------------------------------------------------------------------- /pg-add-goodreads-Copy1.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/pg-add-goodreads-Copy1.ipynb -------------------------------------------------------------------------------- /pg-add-goodreads.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/pg-add-goodreads.ipynb -------------------------------------------------------------------------------- /pg-add-google-books.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/pg-add-google-books.ipynb -------------------------------------------------------------------------------- /pg-cleanup.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/pg-cleanup.ipynb -------------------------------------------------------------------------------- /pg-collapse-volumes.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/pg-collapse-volumes.ipynb -------------------------------------------------------------------------------- /pg-get-corpora.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/pg-get-corpora.ipynb -------------------------------------------------------------------------------- /pg-get-filenames.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/pg-get-filenames.ipynb -------------------------------------------------------------------------------- /pg-metadata-rdf.hdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/pg-metadata-rdf.hdf -------------------------------------------------------------------------------- /pg-pr-eng-add-dbpedia.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/pg-pr-eng-add-dbpedia.ipynb -------------------------------------------------------------------------------- /pg-pr-eng-by-author.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/pg-pr-eng-by-author.ipynb -------------------------------------------------------------------------------- /pg-pr-eng-clean-text.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/pg-pr-eng-clean-text.ipynb -------------------------------------------------------------------------------- /pg-pr-eng-merge-duplicates.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/pg-pr-eng-merge-duplicates.ipynb -------------------------------------------------------------------------------- /pg-vectorize.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/pg-vectorize.ipynb -------------------------------------------------------------------------------- /pg-vectorize2.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/pg-vectorize2.ipynb -------------------------------------------------------------------------------- /pr-extract-text.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/pr-extract-text.ipynb -------------------------------------------------------------------------------- /pr-metadata.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/pr-metadata.ipynb -------------------------------------------------------------------------------- /pr-metadata2.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JonathanReeve/gitenberg-experiments/HEAD/pr-metadata2.ipynb --------------------------------------------------------------------------------