Skip to content

A demonstration of bike sharing rental predictions using a simple neural network. This project is a part of udacity's Deep Learning Specilization Nanodegree.

Notifications You must be signed in to change notification settings

Priya4607/Bike-Sharing-Demand-Predictions

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Bike sharing demand predictions

A demonstration of bike sharing rental predictions using a simple neural network. It is classic regression modelling problem.

This problem may yield better results using other machine learning algorithms, however the intention behind the project is to familiarize onself with the basics of building neural network.

The dataset is from UCI Machine Learning Database.

Table of Contents

Setup

Requires python 3.0+ version.

To install the dependencies,

sudo apt-get --no-install-recommends install -y python3-pip
pip install -U pip

Clone the project,

git clone https://github.com/Priya4607/Bike-Sharing-Demand-Predictions.git
cd Bike-Sharing-Demand-Predictions
pip install -r requirements.txt

Usage

To run the notebook start a local jupyter server from the project folder,

jupyter notebook

Inference

As you can see that the predictions are pretty spot-on for most of the days, except during holiday season. Owing to the fact that the data is available for only past two years, the network sees only two such points which doesn't help much in making a good prediction.

Acknowledgements

This project is a part of my udacity's Deep Learning Specialization Nanodegree.

About

A demonstration of bike sharing rental predictions using a simple neural network. This project is a part of udacity's Deep Learning Specilization Nanodegree.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published