NLP-Library

pdf_split.py

• Splits a PDF into smaller PDFs of arbitrary length.

run_ocr.py

• OCRs a PDF and outputs text to a file.

chapters.py

• Splits a text doc into multiple text docs based on some repeated string like "CHAPTER". Useful for making up small amounts of dev data.

doc.prep.py

• Turns a text file or directory full of text files into reduced bags of words ready for use with the https://pypi.python.org/pypi/lda package.

run_lda.py

• Run LDA using the https://pypi.python.org/pypi/lda package.