asifkhan2017 Goto Github PK

1styearhomework

awesome-community-detection

A curated list of community detection research papers with implementations.

belief_propagation_community_detection

Python implementation of the community detection algorithm based on belief propagation proposed in https://www.pnas.org/content/111/51/18144

bert

TensorFlow code and pre-trained models for BERT

biolink-model

Schema and generated objects for biolink data model and upper ontology

capstone-project

Build user communities from their posted content on Twitter using clustering and topic detection methods.

charm

Parsing and testing Juju charms

chinese_sentiment_analysis

Tutorial for Chinese Sentiment analysis with hotel review data

communitydetection

Implements of community detection algorithms

crowdsourcing

dgp

Rethinking Knowledge Graph Propagation for Zero-Shot Learning, in CVPR 2019

elecbert

Improving Sentiment Analysis in Election-Based Conversations on Twitter with ElecBERT Language Model

generativessl

Deep generative model for labels for semi-supervised learning

identifying-influential-users

Tested and analyzed 9 algorithms for identifying influential spreaders in social networks

jwescoder-corpusoptima_operationalcode

Contains fully operational working code for creating large, biomedically pertinent semantic spaces based on "clean corpora" scraped from public databases, in particular abstracts from the National Library of Medicine's Pubmed biomedical literature database. The resulting semantic space has multiple uses esp. training Latent Semantic Analysis (LSA) and Latent Dirichlet Allocation (LDA) models in text-mining modules and packages such as Gensim and scikit-learn. The CorpusOptima system allows for comprehensive, systematic, and efficient scraping of exclusively abstract text -- without XML header, author/location data, or other ancillary text -- from all abstracts in a given chronological stretch (month-by-month in the primary version), conveniently organized to store all the scraped text from a given month or year of Pubmed abstracts in a local file or database entry. For incorporation into Gensim, scikit-learn or other modules implementing LSA and other document comparison tools, the "corpora" (semantic spaces) are available in two forms, each corresponding to a saved simplejson text file in the primary version of the code: 1. a large list of comma-separated strings with each string -- representing a separate document -- corresponding to text from a single scraped abstract (akin to the "documents" variable in Radim Rehurek's first Gensim tutorial -- https://radimrehurek.com/gensim/tut1.html ) 2. a nested list with the external list containing numerous lists of single-word tokens, each internal list representing the stemmed, lowercased, depunctuated, stopworded tokenization of each abstract, and thus with each internal list again corresponding to a distinct document (akin to the "texts" variable in Radim Rehurek's first Gensim tutorial -- https://radimrehurek.com/gensim/tut1.html ). The basic code module first uploaded maxes out at 100,000 abstracts per scrape (the maximum allowed under the NLM eutils API); a looped variant allows for scraping > 100,000 abstracts up to the total catalogued for a given month or year. I have used this code to scrape NLM Pubmed abstracts on a month-by-month and year-by-year basis dating back to 1911, one of the first years when abstracts in general were systematically catalogued for biomedical publications, with the full semantic space (complete corpus) of biomedical abstracts -- housing tens of millions of documents in total -- being stored in public Dropbox and Google Drive directories (each file corresponding to one month's or one year’s worth of saved corpora) as well as a database under construction.

machine-learning-templates

Templates for regression ,classification,NLP etc.

ncbi_bert

NCBI BERT, pre-trained on PubMed abstracts and clinical notes (MIMIC-III).

networks

Social network anlaysis

networkx-tutorial

Twitter Network Analysis with NetworkX

online-social-network-analysis

Empirical Analysis of Predictive Algorithms for Collaborative Filtering, constructing a Social Network using Twitter Data, Community Detection and Link Prediction using Facebook ‘Like’ Data, Categorizing Movie Reviews based on Sentiment Analysis, Content-based Recommendation Algorithm using Python, Pandas, Numpy and scikit-learn.

pytorch-biggraph

Software used for generating embeddings from large-scale graph-structured data.

scrapper

Facebook, Blog, Twitter, and Instagram Scrapper

socialnetworkanalysis

Empirical Analysis of Predictive Algorithms for Collaborative Filtering, constructing a Social Network using Twitter Data, Community Detection and Link Prediction using Facebook ‘Like’ Data, Categorizing Movie Reviews based on Sentiment Analysis, Content-based Recommendation Algorithm using Python, Pandas, Numpy and scikit-learn.

tridnr

Tri-Party Deep Network Representation

zero-shot-action-recognition-with-two-stream-gcn

I Know the Relationships: Zero-Shot Action Recognition via Two-Stream Graph Convolutional Networks and Knowledge Graphs