# sajal2692/data-science-portfolio

Portfolio of data science projects completed by me for academic, self learning, and hobby purposes.

Repository: https://github.com/sajal2692/data-science-portfolio
Canonical: https://ross.abutalabs.com/products/data-science-portfolio
Homepage: https://sajalsharma.com
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: data-science, portfolio, python, pandas, scikit-learn, machine-learning, nlp, pytorch
Last push: 2026-07-07T03:52:39+00:00

## Health v2 (maintenance only)
Score: 73/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 91, release rhythm 35, longevity 100
- inputs: {"age_days": 3649, "days_push": 57, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1305, forks 455 (observed 2026-08-28T04:04:17.463439+00:00)

## What it is
A portfolio of data science and machine learning projects presented as Jupyter notebooks, covering supervised/unsupervised learning, reinforcement learning, deep learning with PyTorch, and NLP. Originally built around 2016 for academic and self-learning purposes and refreshed in 2026 to run on a current Python stack.

## Use cases
- learn data science fundamentals through worked examples
- find reference notebooks for machine learning projects
- build my own data science portfolio
- see examples of scikit-learn and pandas workflows
- learn NLP classification with notebooks
- study a CNN digit recognition example in PyTorch
- find beginner machine learning project ideas

## When to choose
- you are a beginner or early-career learner wanting runnable end-to-end ML notebooks
- you want examples spanning classic ML, NLP, and a PyTorch CNN
- you need inspiration or structure for your own data science portfolio

## When to avoid
- you need production-grade, maintained software or libraries
- you want modern LLM/agent engineering work rather than classic data science
- you need a curated course with instruction rather than self-contained notebooks

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, nlp, data-science, deep-learning, data-visualization
- domain: data-science, machine-learning, tutorials, education
- platform: python, cross-platform
- tags: jupyter-notebooks, portfolio, scikit-learn, pytorch, pandas, self-learning, example-projects, natural-language-processing

## Member repositories
- sajal2692/data-science-portfolio (main) score 73

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:17.463439+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:51:04.234280+00:00, confidence not recorded.
  - readme: https://github.com/sajal2692/data-science-portfolio (fetched 2026-08-28T04:04:17.463439+00:00, sha 0fd8c19b34d4)
  - homepage: https://sajalsharma.com (fetched 2026-08-29T12:09:01.175846+00:00, sha e5b6449301ab)
  - site_page: https://sajalsharma.com/about (fetched 2026-08-29T12:09:01.185491+00:00, sha 4f3dfc72c4ca)
- Data as of 2026-08-30T08:39:29.467469+00:00.