🤖 ML Task Submission
👤 Name: Shrisha
📧 Contact: shrisha337@gmail.com
Phone No: 8765656336
WhatsApp No: 9455461928
Branch: Computer Science [CS]
Year: 2nd yr
🎯 Task: Teen Smartphone Usage Analysis
🔗 Repository:
https://github.com/shrisha337-beep/Smartphone-Usage-Analysis
📓 Notebook:
https://colab.research.google.com/drive/184txnIfBJq-a3ruXG0jWxGGRghxuvL4v#scrollTo=ss_L7-mbvlro
🛠️ Tech Stack:
- Python 3.
- Libraries: [pandas, matplotlib, seaborn, plotly, scikit-learn, scipy]
- Environment: [Google Colab]
📊 Analysis Completed:
- ✅ Data cleaning and preprocessing
- ✅ Usage patterns analysis
- ✅ Academic performance correlation
- ✅ Sleep impact analysis
- ✅ Mental health indicators
- ✅ [Additional analyses]
🎁 Bonus Features:
Interactive Visuals
Instead of boring static graphs, I’ve added Plotly charts so you can zoom, hover, and actually explore the data. It makes the patterns a lot easier (and way more fun) to understand.
Digging Deeper
I didn’t just stop at screen time averages — I explored age, gender, app categories, daily/weekly patterns, and even sleep habits. Basically, I asked the “what’s really going on here?” questions instead of scratching the surface.
Professional Storytelling
The notebook isn’t just random code and plots. It’s structured like a proper report — with clear sections, key findings, recommendations, and ideas for future research. It feels more like a data story than just an assignment.
Clean Deliverables
All the important charts are saved as images, the dataset is cleaned and ready, and everything sits neatly in the GitHub repo. So it’s easy for anyone else to follow along or build on top of this work.
Room for Machine Learning (optional bonus)
I’ve set up the project in a way that makes it easy to plug in a predictive model — for example, predicting if a teen falls into a “high usage” category based on demographics and habits. This wasn’t required, but it’s a natural next step.
🤖 ML Task Submission
👤 Name: Shrisha
📧 Contact: shrisha337@gmail.com
Phone No: 8765656336
WhatsApp No: 9455461928
Branch: Computer Science [CS]
Year: 2nd yr
🎯 Task: Teen Smartphone Usage Analysis
🔗 Repository:
https://github.com/shrisha337-beep/Smartphone-Usage-Analysis
📓 Notebook:
https://colab.research.google.com/drive/184txnIfBJq-a3ruXG0jWxGGRghxuvL4v#scrollTo=ss_L7-mbvlro
🛠️ Tech Stack:
📊 Analysis Completed:
🎁 Bonus Features:
Interactive Visuals
Instead of boring static graphs, I’ve added Plotly charts so you can zoom, hover, and actually explore the data. It makes the patterns a lot easier (and way more fun) to understand.
Digging Deeper
I didn’t just stop at screen time averages — I explored age, gender, app categories, daily/weekly patterns, and even sleep habits. Basically, I asked the “what’s really going on here?” questions instead of scratching the surface.
Professional Storytelling
The notebook isn’t just random code and plots. It’s structured like a proper report — with clear sections, key findings, recommendations, and ideas for future research. It feels more like a data story than just an assignment.
Clean Deliverables
All the important charts are saved as images, the dataset is cleaned and ready, and everything sits neatly in the GitHub repo. So it’s easy for anyone else to follow along or build on top of this work.
Room for Machine Learning (optional bonus)
I’ve set up the project in a way that makes it easy to plug in a predictive model — for example, predicting if a teen falls into a “high usage” category based on demographics and habits. This wasn’t required, but it’s a natural next step.