Jul 25 (edited) • General
📌 Day 7 | ETE Data Science & ML Projects
✅ Completed my second end-to-end project!
This one wasn’t just ML or data science, it involved deep software engineering + data analysis.
💬 Project: WhatsApp Chat Analyzer
→ Upload your raw .txt WhatsApp file
→ It automatically cleans & preprocesses the data
→ Converts it into a clean DataFrame (this was the most challenging part!)
→ Then flows through the full pipeline:
→ data_ingestion.py → loads and validates
pipeline.py → connects all pieces
utils.py → handles all analysis logic
app.py → Streamlit UI
🔍 Special Features & Insights
→ Works for both group and individual chats
→ You can view overall stats or filter by a specific user
→ Generates wordclouds, timelines, media stats, and more
→ Hinglish + English stopwords removed — specially designed for Indian chat patterns
→ Punctuations are filtered for cleaner analysis
→ Clean visualizations like bar charts + most active user info→ Works with any .txt file exported from WhatsApp
🔧 How to Use the App
→ Upload your .txt file
→ By default, it analyzes “Overall”
→ Change the user if needed
→ Click on “Show Analysis” to generate the stats
→ (Don’t skip that last step!)
🔗 Try the App
→ It’s open-source — feel free to clone, extend, or contribute!
🗣️ I’d love your feedback
→ Test the app using your personal or group chats
→ Let me know what you think
→ Repost and share it with your friends
3
2 comments
Zainulabidin Shaikh
1
📌 Day 7 | ETE Data Science & ML Projects
Data Innovators Exchange
skool.com/data-innovators-exchange
Your source for Data Management Professionals in the age of AI and Big Data. Comprehensive Data Engineering reviews, resources, frameworks & news.
Leaderboard (30-day)
Powered by