Working on CV problems.Improved speed of internal Python library by 5 times

Qodana allows you to get an overview of the project quality, set quality targets, and track progress on them. You can quickly adjust the list of checks applied for the project and include or remove directories from the analysis.

JetBrains develops tools that are used all over the world in some of the best-known companies (Google, NASA, Netflix, etc.) During this internship I've developed ML license detection tool for project and file level license detection and licenses conflicts detection.Technologies stack:- sklearn (RandomForest, TF-IDF)- xgboost / catboost- spacy- tokenization / lemmatization- gitResults:- Classification of 39 SPDX licenses with 99+% accuracy using NLP… Show more JetBrains develops tools that are used all over the world in some of the best-known companies (Google, NASA, Netflix, etc.) During this internship I've developed ML license detection tool for project and file level license detection and licenses conflicts detection.Technologies stack:- sklearn (RandomForest, TF-IDF)- xgboost / catboost- spacy- tokenization / lemmatization- gitResults:- Classification of 39 SPDX licenses with 99+% accuracy using NLP techniques.- Dimensionality reduction based on feature importance from 2 million to 1000.- Full development cycle - idea, experiments, model training, inference, testing (72% coverage). Show less