Calories Estimator

• 

  Project UI

Inspiration

Exercise. Working out.

What it does

It is a calorie burn estimator that uses a machine learning model to estimate a user's calorie burn after a workout. After entering your gender, activity, BMI,and the highest BPM you had during the activity, the model can estimate the number of calories you burnt in 30 minutes.

How we built it

I created and deployed this web application using streamlit for the UI in python.

The machine learning model was done in Google Colab using a multiple regression model. I used the Lifesnaps Fitbit dataset from Kaggle. This dataset was created with data from fitbit users. To create the model, I first preprocessed the dataset by removing unnecessary information and null values. Then I trained the model and downloaded it to a python project folder. Using streamlit, the input from the user is passed to the downloaded model, which generates an estimated value of calorie burnt.

Challenges we ran into

This was my first time using machine learning for an unprocessed data so I spent majority of my time understanding the dataset and how to use it to accomplish the goal of the project, and preprocessing the data

Accomplishments that we're proud of

• Creating a machine learning model
• Using streamlit for the first time
• Deploying the app

What we learned

How to create a machine learning model and use it in a full stack application

What's next for Calories Estimator

• Revise the model with a better dataset that can provide more accurate values
• Include data for more activities like yoga, running etc

Built With

• colab
• dataset
• github
• machine-learning
• python
• regression
• streamlit