Rupen's Projects
Based on Hierarchical Temporal Memory algorithm for intelligent storage system
Nonparametric timeseries classification for Twitter trending topic detection (MEng thesis)
Config files for my GitHub profile.
Sparse Additive Generative Model of Text
Tweets Sentiment Analyzer
A collection of command line utilities
Java API for Natural Language Generation. Originally developed at the University of Aberdeen's Department of Computing Science. This git repo is the official SimpleNLG version.
The simplest way to extract text from PDFs in Python
Generates SQLAlchemy models and downloads and imports data from geonames.org dumps.
An Evaluation of the Brazilian Portuguese LIWC dictionary for Sentiment Analysis
Extractive graph-based text summarizer
Module for automatic summarization of text documents and HTML pages.
#TacoTrucksOnEveryCorner - Map of taco trucks throughout United States
Automatically exported from code.google.com/p/templatemaker
higher-level NLP built on Spacy
An easy-to-use Python wrapper for the Open311 API.
Topological Anomaly Detection (TAD) per Gartley and Basener 2009
simulation code of "Space- and Time- Invariant Trajectory Clustering via Deep Representation Learning"
transforest
Unsupervised machine learning methods to detect and classify anomalies in streaming data. We apply this to the viral event, TwitchPlaysPokemon, and attempt to identify trolls in a live IRC chat.
Simple Python module to watch Twitter user pages or search-results.
Naive Bayes Spam Classifier written in Python
Capture Twitter stream data using Python and Tweepy.
extracts geolocation data from twitter user locations and tweets
Python scripts for geocoding tweets and for downloading images embedded in tweets.
John Langford's original release of Vowpal Wabbit -- a fast online learning algorithm
Use of Naiive Bayes Text Classification and Mutual Information Feature selection to predict from what major city region a twitter user is tweeting
A Pythonic wrapper for the Wikipedia API