Shreyan Sen

Rising Codementor

US$12.00

For every 15 mins

First 15 mins free for your first session

ABOUT ME

Data Scientist + Mindfulness Instructor

If you are an aspiring or new data scientist, I can help you:

master practical fundamentals
build a dream portfolio to prove your skills
code from a place of confidence, clarity, and ease

My training method is project-based and skills-based, and you learn by doing. First, we develop a project plan based on your interests, or you choose from a portfolio of suggested projects. We meet once a week to have an accountability check-in, pair code, or explore mindful coding practices. Since each person has different goals and background, each path is unique. We work together to discover yours.

English

Pacific Time (US & Canada) (-08:00)

Joined October 2024

EXPERTISE

6 years experience

6 years experience

6 years experience

6 years experience

6 years experience

REVIEWS FROM CLIENTS

Shreyan's profile has been carefully vetted and approved as a Codementor. Connect with Shreyan now, and leave a review for them once you're done!

SOCIAL PRESENCE

GitHub

shreyansen.github.io

youtube_transcription_desktop_app

Simple python script to download youtube transcripts, but with a pyqt GUI and runnable by executable (using PyInstaller)

Python

EMPLOYMENTS

Data Scientist

Aclima

2020-04-01-2023-10-01

● Developed a NumPy stochastic simulation engine to detect and visualize statistical aberrations in our environmental data products, gene...

● Developed a NumPy stochastic simulation engine to detect and visualize statistical aberrations in our environmental data products, generating consensus for deep shift in modeling approaches ● Built core algorithms as lead developer for anomaly detection product, using Hidden Markov Models to identify and temporally characterize urban natural gas leaks from sparse sensor data ● Led development of hypothesis testing frameworks and uncertainty intervals for air quality comparisons, enhancing decision-making for spatial analysis in urban planning ● Collaborated with executives, product managers, and environmental scientists to deliver innovative data products, integrating sensor-derived and imputed data into actionable insights

Python

SQL

Git

Python

SQL

Git

Terminal

Statistics

Simulation

Anomaly Detection

Data Scientist

Orbital Insight

2018-07-01-2020-04-01

● Created geospatial algorithms for foot traffic inference based on cell phone geolocation data ● Built near real-time predictive models ...

● Created geospatial algorithms for foot traffic inference based on cell phone geolocation data ● Built near real-time predictive models for key product outputs in a multi-day data ingestion pipeline, using bootstrap analysis to forecast accurate values ahead of complete data delivery ● Spearheaded development of a $700,000 contract’s algorithm and Dockerized data pipeline, utilizing Spark and in-house parallelized approaches to process vast volumes of geolocation data

Python

Terminal

Statistics

Python

Terminal

Statistics

Apache Spark

Geospatial Data Analysis

PROJECTS

Travel By BookView Project

2024

Travel By Book was born while traveling. I was sitting in a cafe in Penang, reading Tan Twan Eng's The House of Doors. The book is set in...

Travel By Book was born while traveling. I was sitting in a cafe in Penang, reading Tan Twan Eng's The House of Doors. The book is set in Penang and tells the story of my favorite author's own time in Penang. Tan is a Penang local, and his book's rich descriptions of Penang's history, society, and architecture opened my eyes to what was around me. Wouldn't it be nice, I thought, to be able to do this anywhere? Of course, the best way is to do exactly what I did. Go to a local bookstore, make friends with the shopkeeper, and ask for the local treatment. But, what's your second best option? I thought it would be nice to have a database of books that have some connection to places. But how would I get the right books, and how would I assess where they are set? Chasing this question, I built an app that used LLMs to parse hundreds of wikipedia articles, create a database, and display the results

Python

Web Scraping

Streamlit

Python

Web Scraping

Streamlit

Large Language Models