Skip to content

Latest commit

 

History

History
14 lines (12 loc) · 522 Bytes

README.md

File metadata and controls

14 lines (12 loc) · 522 Bytes

fachinfo_ai

Doing NLTK and AI on Swiss Fachinfos with Python. Parsing all the important words from all FIs in Switzerland.

Requirements:

  • List of stopwords in folder input (filename: stopwords.txt)
  • Amiko sqlite DB in folder dbs (filename: amiko_db_full_idx_de.db)

Output:

  • Frequency csv file in folder output (filename: frequency.csv)
  • Auto-generated stopwords file in folder output (filename: auto_stopwords.csv)

Requirements

  • pip install nltk
  • python 3.5.2
  • nltk.download('stopwords','punkt')