gvyshnya
A Data Scientist & Software Dev with blended industrial experience in software development, IT, DevOps, operation and project management, and C-level roles
Kyiv, Ukraine - Warsaw, Poland
Pinned Repositories
BirdCallClassification
The repo contains various materials created as a part of Cornell Birdcall Identification project
COVID19
This is the home of my public efforts in data analytics, research and data science/software development dedicated to various aspects of COVID-19 impact analysis
CreditRiskPrediction
The notebook with materials related to credit risk prediction competition (https://inclass.kaggle.com/c/adatelemz-si-platformok-2016-2-gyakorlat/)
dataproc-pyspark-etl
This repo provides the end-to-end case study on how to build effective Big Data-scale ETL solutions in Google Cloud Platform, using PySpark/Dataproc and Airflow/Composer
DVC_R_Ensemble
Materials of a case study to build a DVC-based ML pipeline for an R project with ensemble prediction
kaggle-2021-survey
This repo collects the various research artifacts and final-quality notebooks with the research on Kaggle 2021 Survey results.
malimg
This repo contains the artifacts of ML experiments to detect / classify various malware attacks based on the classical MalImg Dataset
state-of-data-science-and-ml-2020
This repo contains the notebooks with the comprehansive EDA and data-driven insights from the data collected in Kaggle's 2020 survey of 'State of Data Science and Machine Learning 2020'.
WPPF
An early prototype of a time-series forecasting app predicting wind power production
gvyshnya's Repositories
gvyshnya/DVC_R_Ensemble
Materials of a case study to build a DVC-based ML pipeline for an R project with ensemble prediction
gvyshnya/WPPF
An early prototype of a time-series forecasting app predicting wind power production
gvyshnya/BirdCallClassification
The repo contains various materials created as a part of Cornell Birdcall Identification project
gvyshnya/COVID19
This is the home of my public efforts in data analytics, research and data science/software development dedicated to various aspects of COVID-19 impact analysis
gvyshnya/CreditRiskPrediction
The notebook with materials related to credit risk prediction competition (https://inclass.kaggle.com/c/adatelemz-si-platformok-2016-2-gyakorlat/)
gvyshnya/ShowOfHands2016
This is the notebook with various submission scripts used to tackle the Kaggle competition per https://inclass.kaggle.com/c/can-we-predict-voting-outcomes
gvyshnya/AdvancedHousePricingProblem
This repo is dedicated to various experiments and research with the data of 'House Prices: Advanced Regression Techniques' problem
gvyshnya/RuTextNormal
This is the repo with Python code of models developed in Google Russian Text normalization competiontion (https://www.kaggle.com/c/text-normalization-challenge-russian-language/)
gvyshnya/Spacial_Data_Analysis
The repo contains materials of a project to deliver data mining and data visiualization/analytics based on geospacial data of telecom infrastructure and customer locations of a large national telecom operator
gvyshnya/state-of-data-science-and-ml-2020
This repo contains the notebooks with the comprehansive EDA and data-driven insights from the data collected in Kaggle's 2020 survey of 'State of Data Science and Machine Learning 2020'.
gvyshnya/tab-mar-21
This repo will contain various EDA and ML experiments for Kaggle's March 2021 Tabular Playground competition.
gvyshnya/WTTSF_Python
Materials of project per the competition of https://www.kaggle.com/c/web-traffic-time-series-forecasting/
gvyshnya/dataproc-pyspark-etl
This repo provides the end-to-end case study on how to build effective Big Data-scale ETL solutions in Google Cloud Platform, using PySpark/Dataproc and Airflow/Composer
gvyshnya/kaggle-2021-survey
This repo collects the various research artifacts and final-quality notebooks with the research on Kaggle 2021 Survey results.
gvyshnya/malimg
This repo contains the artifacts of ML experiments to detect / classify various malware attacks based on the classical MalImg Dataset
gvyshnya/CMS-Detect-Sleep-States
Materials and experiments with the dataset for 'Child Mind Institute - Detect Sleep States' competition
gvyshnya/dvc
Make your data science projects reproducible and shareable. https://dataversioncontrol.com
gvyshnya/erpnext
ERP made Simple
gvyshnya/exodus
The repo with Data Analytics artifacts to track the international corporate exodus from russia amid the war in Ukraine
gvyshnya/frappe
Full Stack Web Framework in Python & JS. Used to build ERPNext
gvyshnya/FrappeClient-PHP
PHP Wrapper for ERPNext API
gvyshnya/HousePricePrediction1
The repo demonstrates an end-to-end ML pipeline to predict UK house prices based on the historic sales data for 1995-2015
gvyshnya/kaggle-rossman-store-sales
Solution for Kaggle Rossmann Store Sales Competition
gvyshnya/KerasBinClass1
This repo contains a Keras-based neural network solution to tackle a binary classification problem
gvyshnya/ml-gcp-deployment
This repo is dedicated to the reference implementation of an ML solution as well as packaging and deploying it as a Web-based Google Cloud Platform's cloud functoion
gvyshnya/MoA
This repo contains the materials for the 'Mechanisms of Action' competition at Kaggle
gvyshnya/reactJSNewsMiniSite
News mini-site implemented in React JS (with mini-server implemented in node.js)
gvyshnya/tab-dec-21
This repo contains the materials and artifacts related to the experiments with the dataset of Kaggle's Dec 2021 Tabular Playground Competition.
gvyshnya/tab-feb-2021
Various AutoML and ML Experiments on Kaggle's Feb 2021 Tabular Contest Dataset
gvyshnya/tab-jan-2021
Various AutoML and ML Experiments on Kaggle's Jan 2021 Tabular Contest Dataset