mbatchkarov

critical_difference

repeval2016

A critique of word similarity as a method for evaluating distributional semantic models

learning_rust

Plovdiv

Project Plovdiv is a simple network epidemiology simulator and can be used to teach basic graph theory.

poppee

Pet pee tracker

pydata_berlin_2017

Slides for my talk on gold standard data labelling at PyData Berlin 2017

spacy-docker

Spacy in a docker image, again

thesisgenerator

BoV work in progress.

dc_evaluation

Evaluation of distributional models through document classification

amazon-transcribe-streaming-sdk

The Amazon Transcribe Streaming SDK is an async Python SDK for converting audio into text via Amazon Transcribe.

conf2017slides

datefinder

Find dates inside text using Python and get back datetime objects

dateparser

python parser for human readable dates

dotfiles

dsf_london_2019

Slides for my talk at London DataSci Festival

JsonWeb

Quickly add JSON (de)serialization to your python objects

k8s-sqs-autoscaler

Kubernetes pod autoscaler based on queue size in AWS SQS

LSH

Locality Sensitive Hashing using MinHash in Python/Cython to detect near duplicate text documents

mbatchkarov.github.io

My Github page

meteor

Meteor, the JavaScript App Platform

ms-bot

pick-mongo-primary

Get MongoDB Shell command to PRIMARY from the Mongo URL

productner

Algorithms to categorize products and do named entity recognition on words in product descriptions

psql_connector

A simple UI for connecting to a remote Postgres table via an ssh tunnel and copying data locally

pycharm-settings

relearning_c

sanic

Async Python 3.5+ web server that's written to go fast

spaCy

💫 Industrial-strength Natural Language Processing (NLP) with Python and Cython

textacy

higher-level NLP built on Spacy

vscode-meteorhelper

MeteorJS Helper for Visual Studio Code