[go: nahoru, domu]
Skip to content
View GrigoriiTarasov's full-sized avatar
190 followers · 178 following

Achievements

Achievement: Pull Sharkx2Achievement: YOLOAchievement: Quickdraw

Achievements

Achievement: Pull Sharkx2Achievement: YOLOAchievement: Quickdraw

Highlights

Block or Report

Block or report GrigoriiTarasov

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
GrigoriiTarasov/README.md

Hi there 👋 I'm Grigorii Tarasov

I'm an Experienced Machine Learning engineer, Python developer who started from Data Scientist job.

1. Detailed info

Careerpath, publications, certificates, skills and technologies are mostly listed at Linkedin

2. Sample projects

While most of my projects are closed-source, I'm happy to share some solo projects that higlights skills and stack.

(status) type, Link Scope Technologies Used Focus of implementation
(Ongoing) Handbook with code
Leaks-in-ML-DS-prevention		 Experiment design, metric choice,
pipeline rules to prevent leaks in ML/DS systems.
Quick fixes where possible.		 Markdown
ML experiment design		 Experiment design
consultations
(Completed) API service
Face-Age-Detection-app		 Detects a single face and predicts age.
Finetuned on UTKFace dataset.
Returns JSON with bounds coordinates,
age, and confidence		 Conda docker
DVC Fastapi
github actions
MlFlow Pytest tensorflow 		CI, conteinerization
code quality
flexebility of model ML updates
(In process) MLE project
Optiver-Trading-at-the-Close-retrain-monitoring		 Monitored time series prediction pipeline with
intensive feature engineering including Linear Regression and
best proven model of boosting family		 Catboost Optuna Polars Feature engineering,
Boosting model,
Monitoring, time series,
metric decay automated prevention

3. Contacts

Pinned Loading

  1. Leaks-in-ML-DS-prevention Leaks-in-ML-DS-prevention Public

    Ongoing handbook with practice-orientated examples, quick-fixes, symptoms, tests for leaks during data preparation and model development

    Python 12

  2. Face-Age-Detection-app Face-Age-Detection-app Public

    CLI app to detect face and predict age tuned on UTKFace with docker and Continuous Integration

    Jupyter Notebook 8 2

  3. Time-Series-Library Time-Series-Library Public

    Forked from thuml/Time-Series-Library

    Fork to fix FEDformer script bug

    Python 2

  4. Optiver-Trading-at-the-Close-retrain-monitoring Optiver-Trading-at-the-Close-retrain-monitoring Public

    300 features selection, CatBoost, NannyML to monitor concept drift, auto-retrain, daily load h5 trick

    Jupyter Notebook 4

  5. st-annotated-text st-annotated-text Public

    Forked from tvst/st-annotated-text

    Fixed newlines error

    Python 4