Skip to content

pparashar073/FocusFlow

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🧠 FocusFlow — AI Focus Score Predictor

A machine learning web app that predicts your daily focus score based on your sleep, screen time, meals and mood — and gives you a personalised AI productivity tip.

Python Streamlit Scikit-learn Groq

🔗 Live Demo


🌟 Features

  • 📊 Focus Score Prediction — ML model predicts your focus score (0–100) based on daily habits
  • 🟢🟡🔴 Colour-coded Results — High / Medium / Low focus with a progress bar
  • 💡 AI Productivity Tips — Personalised tip generated by LLaMA 3.3 via Groq API
  • 🎚️ Simple Sliders — Just move 4 sliders and get your result instantly
  • 🤖 Linear Regression Model — Trained on a custom dataset of daily habits vs focus scores

🖥️ Screenshots

Move the sliders → Click Predict → Get your focus score and AI tip instantly

image image

🚀 How to Run Locally

1. Clone the repo

git clone https://github.com/pparashar073/FocusFlow.git
cd FocusFlow

2. Install dependencies

pip install streamlit scikit-learn pandas joblib groq python-dotenv

3. Get a free Groq API key

4. Create a .env file

GROQ_API_KEY=your_groq_api_key_here

5. Run the app

streamlit run app.py

🛠️ Tech Stack

Tech Purpose
Python Core language
Scikit-learn Linear Regression model training
Pandas Data handling
Joblib Model saving and loading
Streamlit Web UI framework
Groq API AI inference engine
LLaMA 3.3 70B Productivity tip generation

📋 How It Works

  1. A Linear Regression model is trained on a dataset of daily habits (sleep, screen time, meals, mood) vs focus scores
  2. User inputs their daily stats using sliders
  3. The trained model predicts a focus score out of 100
  4. The score is displayed with a colour-coded label and progress bar
  5. LLaMA 3.3 via Groq generates a personalised productivity tip based on the user's inputs and score

📁 Project Structure

FocusFlow/
  ├── app.py           # Main Streamlit app
  ├── train_model.py   # Model training script
  ├── data.csv         # Training dataset
  ├── requirements.txt # Dependencies
  └── .env             # API key (not committed)

👨‍💻 Built By

Paras Parashar — B.Tech CS/AI Student
GitHub · LinkedIn


FocusFlow v1.0 — Know your focus. Improve your day. 🧠

About

AI-powered focus score predictor using Machine Learning and LLaMA 3.3

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages