--extra_lda_stopwords

Switch

--extra_lda_stopwords FILENAME

Description

Path to a file of additional stopwords to remove before LDA topic estimation, on top of the automatically-detected ones.

Argument and Default Value

A file path. Default: None.

Details

Verified end-to-end with real Mallet: one word per line. Confirmed with a 2-word file (love, work) — DLATK printed Removed an additional 2 extra stopwords: {'work', 'love'} alongside its own automatically-detected stopword list (frequent words/punctuation).

Other Switches

Required Switches:

• --estimate_lda_topics

Optional Switches:

• --num_stopwords, --no_lda_stopping

Example Commands

Using the packaged dla_tutorial dataset (see DLATK LDA Interface):

echo -e "love\nwork" > extra_stopwords.txt
dlatkInterface.py -d dla_tutorial -t msgs -c user_id -f 'feat$1gram$msgs$user_id' \
--estimate_lda_topics --num_topics 100 --no_lda_lexicon \
--mallet_path /opt/homebrew/bin/mallet --save_lda_files ./lda_out \
--extra_lda_stopwords extra_stopwords.txt