# Next line commented out because we only want to run this once
# nohup python src/load_kiva_loans_to_mongodb.py

!python src/convert_mongodb_to_blei_ldac.py --dataDir data/topicmodelling\
                                            --corpusBaseName kiva \
                                            --stopwordFile=data/topicmodelling/kiva_stopwords.tsv \
                                            --startYear 1990 \
                                            --maxNrDocs 800000 \
                                            --filterBelow 10 \
                                            --filterAbove 0.5 \
                                            --filterKeepN 1000

!python src/model_topics.py --dataDir data/topicmodelling \
                            --modelDir data/topicmodelling \
                            --corpusBaseName kiva \
                            --nrTopics 64 \
                            --nrWords 8

!python src/infer_document_topic_distributions.py --modelDir data/topicmodelling \
                                                  --modelBaseName kiva \
                                                  --maxNrDocs 250000

!python src/build_topic_hierarchy.py --modelDir data/topicmodelling \
                                     --modelBaseName kiva \
                                     --nrClusters 16 \
                                     --nrWords 7