DS

ML for stalkering social networks

tweets_extraction.ipynb - parsing tweets using Twitter API
input.py & fromfile.py scraping vk groups, the first reads domens from command line
networking_for_introverts.py - parsing geolocated photos from vk anf instagram (may be useful in case you want to find profiles in social networks of someone you met at an event)
clean.py - preprocessing text data from vk for k-means
prepare_text.ipynb - tokenization, lemmatization, removing stop words, vectirization (tf-idf) for BigARTM
topic_modeling.ipynb - extracting topics using ML model ARTM
k-means.ipynb - text clastering for comparison
vw_classifier.ipynb - segmentation of auditory using VowpalWabbit Classifier based on stochastic gradient descent and hyperopt with python wrapper for VW lib

Name		Name	Last commit message	Last commit date
Latest commit History 22 Commits
README.md		README.md
clean.py		clean.py
example_for_vw.json		example_for_vw.json
fromfile.py		fromfile.py
input.py		input.py
k-means.ipynb		k-means.ipynb
networking_for_introverts.py		networking_for_introverts.py
prepare_text.ipynb		prepare_text.ipynb
support_data.ipynb		support_data.ipynb
swrussian.txt		swrussian.txt
topic_modeling.ipynb		topic_modeling.ipynb
tweets_extractor.ipynb		tweets_extractor.ipynb
vw_classifier.ipynb		vw_classifier.ipynb
yandex_log.txt		yandex_log.txt

Provide feedback