michael-eble / pdf-analysis-word-extraction-word-frequencies Goto Github PK
View Code? Open in Web Editor NEWPDF Analysis: Extracting words and their word frequencies from PDF files; Preparation of text data for performing topic analysis on annual reports of German car manufacturers - e.g. Volkswagen, Porsche and Audi. Please note that words are only being extracted, stemming is not being applied. In order to improve this, use nltk.stem.snowball.SnowballStemmer('german'), for example.
License: MIT License