Machine learning model to classify SMS messages as 'spam' or 'ham' using text preprocessing, TF-IDF vectorization, and scikit-learn classifiers.
🔍 Accuracy: 96% — overall strong classification performance
✅ Precision: 1.00 — zero false positives; no legitimate messages flagged as spam
📉 Recall: 0.72 — catches most spam but misses a few, ensuring cautious filtering
⚖️ F1 Score: 0.84 — well-balanced model with emphasis on precision
Why it matters: The model is optimized for high-precision scenarios, making it ideal for systems where false spam flags must be avoided, such as in business-critical communications.
➡️ View project: Spam Detector on GitHub →
WeatherAQI is a Jupyter Notebook project that fetches and compares real-time weather and air quality (AQI) data for different cities using APIs and data visualization.
🔧 Built with:
- Python, Jupyter Notebook
- OpenWeatherMap API
- Seaborn, Matplotlib, Pandas
- Optional: AQI API + BeautifulSoup
📊 Features:
- 🔄 Live integration with OpenWeatherMap & AQI APIs
- Auto-generated visual comparisons for multiple cities
- Includes auto-labeled bar plots with units (°C, %, AQI)
- 🗃️ Converts live CSV data to a local SQLite database (
weather_aqi.db) - 📥 Supports SQL queries for filtering and historical analysis
🔗 View Project: WeatherAQI on GitHub →
🚧
A lightweight Python tool that detects potentially suspicious credit card transactions using rule-based AML (Anti-Money Laundering) checks.
- 🚨 Flags high-value transactions and unusual activity
- 📊 Processes CSV files with clear, reviewable output
- 🔧 Easily extendable for more compliance logic or machine learning
-
💻 I'm currently working on automation for complex GRC and TPRM programs' change management and workflows with Gen AI and Python.
-
📚 I'm learning Rego (OPA) to implement policy as code for IAM risk management and map different frameworks and regulations e.g. NIST, HIPAA, PCI DSS, etc. so that it's easier for software engineers to update change management and add it to their CI/CD pipeline.
-
🙌 I'm looking to collaborate on anything related to cybersecurity.
-
💁 Ask me about GRC Compliance and TPRM program management with workflow and risk scoring methodology automation.
-
📞 How to reach me:
Language Statistics...
const cat = {
pronouns: "She" | "Her" | "Hers",
code: ["Javascript", "HTML", "CSS", "Python", "Ruby", "FEEL"],
askMeAbout: ["web dev", "tech", "app dev", "startup", "baking"],
technologies: {
webApp: ["Python App"],
frontEnd: {
js: ["React", "Context"],
python: ["FastAPI"]
css: ["material ui", "ant design", "bootstrap", "Sass", "Less"]
},
backEnd: {
js: ["node", "express"],
python: ["flask"]
},
devOps: ["AWS", "Heroku", "Docker🐳", "K8"],
databases: ["postgreSQL", "MySql", "sqlite"],
misc: ["DMN", "selenium", "postman"]
},
architecture: ["serverless architecture", "progressive web applications", "single page applications", "microservices", "event-driven", "design system pattern"],
techCommunities: {
member: "Py-Lambda",
member: "Women Techmakers",
member: "freeCodeCamp",
},
currentProject: "I am building an interactive Github Dashboard and REST APIs with Flask and Python",
funFact: "Let your code brew overnight and magic will happen the next morning"
}; 
🐱 My GitHub Data
📦 ? Used in GitHub's Storage
🏆 48 Contributions in the Year 2025
💼 Opted to Hire
📜 250 Public Repositories
🔑 0 Private Repositories
I'm an Early 🐤
🌞 Morning 269 commits █████████░░░░░░░░░░░░░░░░ 34.75 %
🌆 Daytime 443 commits ██████████████░░░░░░░░░░░ 57.24 %
🌃 Evening 62 commits ██░░░░░░░░░░░░░░░░░░░░░░░ 08.01 %
🌙 Night 0 commits ░░░░░░░░░░░░░░░░░░░░░░░░░ 00.00 %
📅 I'm Most Productive on Tuesday
Monday 68 commits ██░░░░░░░░░░░░░░░░░░░░░░░ 08.79 %
Tuesday 288 commits █████████░░░░░░░░░░░░░░░░ 37.21 %
Wednesday 54 commits ██░░░░░░░░░░░░░░░░░░░░░░░ 06.98 %
Thursday 73 commits ██░░░░░░░░░░░░░░░░░░░░░░░ 09.43 %
Friday 143 commits █████░░░░░░░░░░░░░░░░░░░░ 18.48 %
Saturday 78 commits ███░░░░░░░░░░░░░░░░░░░░░░ 10.08 %
Sunday 70 commits ██░░░░░░░░░░░░░░░░░░░░░░░ 09.04 %
📊 This Week I Spent My Time On
🕑︎ Time Zone: America/Los_Angeles
💬 Programming Languages:
Other 4 hrs 9 mins ██████████████░░░░░░░░░░░ 56.41 %
Text 2 hrs 40 mins █████████░░░░░░░░░░░░░░░░ 36.36 %
Python 31 mins ██░░░░░░░░░░░░░░░░░░░░░░░ 07.24 %
🔥 Editors:
Terminal 3 hrs 41 mins █████████████░░░░░░░░░░░░ 50.14 %
VS Code 3 hrs 40 mins ████████████░░░░░░░░░░░░░ 49.86 %
🐱💻 Projects:
PCAP 3 hrs 38 mins ████████████░░░░░░░░░░░░░ 49.37 %
endpoint-output 1 hr 58 mins ███████░░░░░░░░░░░░░░░░░░ 26.88 %
spam-detector 1 hr 39 mins ██████░░░░░░░░░░░░░░░░░░░ 22.42 %
UpdateLogList 5 mins ░░░░░░░░░░░░░░░░░░░░░░░░░ 01.33 %
💻 Operating System:
Mac 7 hrs 22 mins █████████████████████████ 100.00 %
I Mostly Code in JavaScript
JavaScript 13 repos ███████████░░░░░░░░░░░░░░ 43.33 %
HTML 4 repos ███░░░░░░░░░░░░░░░░░░░░░░ 13.33 %
TypeScript 4 repos ███░░░░░░░░░░░░░░░░░░░░░░ 13.33 %
Jupyter Notebook 3 repos ██░░░░░░░░░░░░░░░░░░░░░░░ 10.00 %
Python 2 repos ██░░░░░░░░░░░░░░░░░░░░░░░ 06.67 %
Timeline
Last Updated on 04/07/2025 19:29:40 UTC
These Readme stats are generated using Github Action awesome-readme-stats