Sagar Mishra
Software Engineer
Mumbai, Maharashtra, India
Summary
🤩
RockstarSagar Mishra is a software engineer based in Mumbai with six years of experience focused on machine learning and data engineering. As a core developer on sktime, he has improved dataset loading, added regression support via @targetlabel for .ts files, integrated TapNet models, and strengthened test coverage and documentation—work that directly benefits time-series ML practitioners. He combines practical engineering (refactors, default parameters, datatype fixes) with model integration, showing a balance of software craftsmanship and applied ML. Colleagues can rely on him to untangle messy data pipelines and make open-source tooling more robust and user-friendly.
6 years of coding experience
Stackoverflow
295reputation
4kreached
4answers
5questions
Github Skills (23)
python10
scikit10
machine-learning10
keras10
tensorflow10
scikit-learn10
data-science9
data-engineering9
ml9
mle9
mask-rcnn9
faster-rcnn9
time-series8
anomaly-detection7
classify7
Programming languages (9)
Github contributions (5)
sktime/sktime
Jul 2022 - Jan 2023
A unified framework for machine learning with time series
Role in this project:
Data Scientist & ML Engineer
Data Scientist & ML EngineerContributions:89 reviews, 19 commits, 55 PRs in 5 months
Contributions summary:Sagar primarily refactored and enhanced dataset loading functionalities within the `sktime` library, a framework for machine learning with time series. Their work involved streamlining the loading process, introducing default parameters for flexibility, and addressing data type conversion issues. Additionally, the user added support for the `@targetlabel` identifier in `.ts` files, enabling regression tasks and added a test for regression data by incorporating a dataset for death rate prediction. They also integrated TapNet models for both classification and regression tasks, along with fixing typos and improving documentation.
forecastingtime-series-analysistime-series-regressiondata-sciencedeep-learning
achieveordie/sktime
Jul 2022 - Feb 2023
A unified framework for machine learning with time series
Contributions:84 pushes, 26 branches in 6 months
deep-learningtime-seriesmachine-learning
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.