Skip to content
View scmlewis's full-sized avatar

Block or report scmlewis

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
scmlewis/README.md

Data Analyst → AI-assisted Builder

Solving real problems with Python, data, and AI coding tools.

Portfolio


Stuff I use

Python Jupyter SQL

Core data stack

Pandas NumPy SciPy Statsmodels NetworkX

Machine learning & modeling

scikit-learn TensorFlow Keras PyTorch

Visualization & storytelling

Matplotlib Seaborn Plotly Dash Streamlit

Big data & scaling

Dask PySpark


Featured Projects

Project What it does
train.eta Real-time arrival dashboard for Hong Kong MTR, Light Rail, and MTR Bus — live transit data at your fingertips.
gridify Habit tracker that turns consistency into a game. Grid-based streaks, XP rewards, and level-ups keep you coming back.
ds_assistant Streamlit-powered data science sidekick — drop in any dataset and get automated EDA, visualizations, and insights in seconds.
thermapace VDOT pace calculator that factors in real-time weather — temperature, humidity, and wind degradation modeling for runners.
See all 27 projects

My Projects

AI & Machine Learning

Project Description
eatwise_ai AI-powered nutrition coach that analyzes meals, tracks macros, and helps you eat smarter — built with NLP and food data APIs
semantic_search_app_food Natural language search engine for nutrition databases — ask questions like "high protein low carb snacks" and get instant results
ds_assistant Streamlit-powered data science sidekick that automates EDA, generates visualizations, and surfaces hidden insights from any dataset
PulseLens Customer feedback analyzer using zero-shot classification to extract sentiment and key themes — no labeled data needed

Data Analytics, Predictive Analytics & ML Models

Project Description
Medical-Insurance-Premium-Prediction Statistical modeling with Python and statsmodels to forecast insurance premiums based on age, BMI, smoking status, and more
Telco-Customer-Churn-Prediction Predictive model that identifies at-risk telecom customers before they leave — feature engineering meets business retention strategy
House_Price_Prediction Regression model for estimating residential property values using market features, location data, and housing attributes
obesity_prediction ML pipeline that predicts obesity risk levels from health and lifestyle metrics — explores which factors matter most
Customer-Segmentation-Project K-means clustering deep dive that segments customers by behavior and spending patterns for targeted marketing insights
Google-DA-Capstone-Cyclistic-Case-Study Google Data Analytics capstone analyzing 12 months of bike-share data to uncover seasonal trends and rider behavior
karate_club_network_analysis Graph theory exploration of Zachary's Karate Club — visualizing community detection and network centrality with NetworkX

Web Applications

Project Description
modern-weather-forecast-lab Sleek weather dashboard with animated forecasts, interactive maps, and multi-day outlooks — built with modern web APIs
linkshrink URL shortener with built-in analytics — track clicks, referrers, and geographic data on every link you share
pulsedrift Calm-inducing mindfulness timer with guided breathing exercises, ambient soundscapes, and session tracking
pdf_processing Web app that extracts, parses, and transforms PDF documents — batch process, merge, and convert files in-browser
Chromatique Color palette generator and harmony analyzer for designers — discover complementary, analogous, and triadic color schemes
gaming-hub Gaming platform aggregator and community dashboard — consolidate your gaming life in one place
lottery_tool Interactive probability analyzer for lottery numbers — frequency analysis, hot/cold numbers, and statistical breakdowns
portfoiliolab Python toolkit for portfolio optimization — Sharpe ratio analysis, efficient frontier visualization, and risk assessment
train.eta Real-time arrival dashboard for Hong Kong MTR, Light Rail, and MTR Bus — never miss your train again
hk_school_finder PWA for parents to discover kindergartens, primary, and secondary schools across Hong Kong with filters and maps
hk_a-e_waiting_time Live waiting time tracker for Hong Kong A&E departments — helps you decide which hospital to head to
qrtist Beautifully designed QR code generator PWA — customize colors, add logos, and download in multiple formats
litlist_hub Reading list manager PWA for tracking books, progress, and notes — your personal digital bookshelf
gridify Habit tracker that turns consistency into a game — grid-based streaks, XP rewards, and level-ups keep you motivated
thermapace VDOT pace calculator that factors in real-time weather — temperature, humidity, and wind degradation modeling for runners
travel-split Expense splitter for group trips — log shared costs, settle debts, and keep travel budgets transparent

Let's chat!

Always down to talk data, analytics, cool datasets, or just life in general.
Drop me a message anytime I don't bite (unless it's pizza).

Portfolio

Thanks for stopping by!

Popular repositories Loading

  1. Medical-Insurance-Premium-Prediction Medical-Insurance-Premium-Prediction Public

    Statistical model forecasting insurance premiums using Python and statsmodels

    Jupyter Notebook

  2. Telco-Customer-Churn-Prediction Telco-Customer-Churn-Prediction Public

    Predictive analytics model identifying at-risk telecom customers for churn prevention

    Jupyter Notebook

  3. Customer-Segmentation-Project Customer-Segmentation-Project Public

    K-means clustering analysis for customer segmentation and marketing insights

    Jupyter Notebook

  4. House_Price_Prediction House_Price_Prediction Public

    Regression model for predicting residential property values using market features

    Python

  5. Google-DA-Capstone-Cyclistic-Case-Study Google-DA-Capstone-Cyclistic-Case-Study Public

    Google Data Analytics capstone analyzing bike-share usage patterns for Cyclistic

  6. semantic_search_app_food semantic_search_app_food Public

    Semantic search engine with intent detection for querying nutrition databases

    Python