Command Line Examples.txt

# twitter_user_grabber.py (search):
python twitter_user_grabber.py search -c "Newport Beach" -s California -r 100mi -f ../Output/twitter_geo_searches/test_cliques -z ../twitter_dev_accounts

# get_community_tweets:
python get_community_tweets.py -f ../Output/twitter_geo_searches/filename.json -c ../twitter_dev_accounts -o ../Output/dnld_tweets/ -n 25

# create the corpus/dict from wiki dump with lemmatization
python create_LDA_model.py wiki -w ../Output/model_and_corpus/simplewiki-latest-pages-articles.xml.bz2 -c ../Output/model_and_corpus/test_corpus -m

# create the lda model from the corpus and dictionary (num topics is set to 50 and num passes is 5)
python create_LDA_model.py lda -c ../Output/model_and_corpus/wiki_corpus.mm -d ../Output/model_and_corpus/wiki_corpus.dict -n 50 -p 5 -l ../Output/model_and_corpus/lda_model

# create ldaVis html file from the model
python create_LDA_model.py ldavis -c ../Output/model_and_corpus/wiki_corpus.mm -d ../Output/model_and_corpus/wiki_corpus.dict -l ../Output/model_and_corpus/lda_model.model

# uses the tweets of each user to get document vectors from the lda model and puts the vectors in files/folders for each community
python tweets_on_LDA.py -t ../Output/twitter_geo_searches/test_cliques.json -p clique -w ../Output/graphs_and_data/ -l ../Output/model_and_corpus/lda_model.model -d ../Output/model_and_corpus/wiki_corpus.dict -u ../Output/dnld_tweets/

# plots the data from the result of running tweets_on_LDA.py
python plot_distances.py indiv -w ../Output/graphs_and_data/ -i