bonneraj
Curious Data Scientist with five years of experience across Data Science, Machine Learning Engineering, and Data Engineering Roles.
Washington DC
Pinned Repositories
fast_api_model_serving
A repo for training a basic linear regression model and serving the saved model utilizing Docker and FastAPI.
life_expectancy_regression
A repo used to train regression models on community health data to predict average life expectancy. 2023 County Health Rankings National Data is sourced from the University of Wisconsin Population Health Institute and can be found at: https://www.countyhealthrankings.org/explore-health-rankings/rankings-data-documentation
practical-stats-ds
This notebook implements concepts laid out in 'Practical Statistics for Data Scientist - 50+ Essential Concepts Using R and Python' by Peter Bruce, Andrew Bruce, and Peter Gedeck
retail_sales_time_series
A repo containing a few exploratory notebooks for statistical (ARIMA) and supervised ML (random forest, KNN) approaches to time series analysis of monthly retail sales (sourced from St. Louis Fed). Notebooks also explore the use of MLFlow for experiment tracking, model registration, and deployment/inference.
twitter_nlp_library
A library to retrieve tweets from the Twitter API and provide various NLP scripting abilities.
bonneraj's Repositories
bonneraj/fast_api_model_serving
A repo for training a basic linear regression model and serving the saved model utilizing Docker and FastAPI.
bonneraj/life_expectancy_regression
A repo used to train regression models on community health data to predict average life expectancy. 2023 County Health Rankings National Data is sourced from the University of Wisconsin Population Health Institute and can be found at: https://www.countyhealthrankings.org/explore-health-rankings/rankings-data-documentation
bonneraj/practical-stats-ds
This notebook implements concepts laid out in 'Practical Statistics for Data Scientist - 50+ Essential Concepts Using R and Python' by Peter Bruce, Andrew Bruce, and Peter Gedeck
bonneraj/retail_sales_time_series
A repo containing a few exploratory notebooks for statistical (ARIMA) and supervised ML (random forest, KNN) approaches to time series analysis of monthly retail sales (sourced from St. Louis Fed). Notebooks also explore the use of MLFlow for experiment tracking, model registration, and deployment/inference.
bonneraj/twitter_nlp_library
A library to retrieve tweets from the Twitter API and provide various NLP scripting abilities.