https://github.com/codeslash21/predicting_bike_sharing_pattern
Predicting bike sharing pattern for a ride sharing company for making efficient business policies.
https://github.com/codeslash21/predicting_bike_sharing_pattern
deep-learning neural-network
Last synced: about 1 year ago
JSON representation
Predicting bike sharing pattern for a ride sharing company for making efficient business policies.
- Host: GitHub
- URL: https://github.com/codeslash21/predicting_bike_sharing_pattern
- Owner: codeslash21
- License: mit
- Created: 2020-06-05T21:04:22.000Z (about 6 years ago)
- Default Branch: master
- Last Pushed: 2020-06-05T21:38:41.000Z (about 6 years ago)
- Last Synced: 2025-02-15T15:51:34.001Z (over 1 year ago)
- Topics: deep-learning, neural-network
- Language: Jupyter Notebook
- Homepage:
- Size: 632 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Predicting_Bike_Sharing_Pattern
In this project, we'll build a neural network from scratch to predict bike-sharing rides.
Imagine yourself owning a bike sharing company like [Cycle Hop](https://cyclehop.com). You want to protect how many bikes you need because if you have too few you're losing money from potential riders. If you have too many you're wasting money on bikes that are just sitting around. So you need to predict from historical data how many bikes you'll need in the near future.
A good way to do this is with a neural network which is exactly what you'll do. In this notebook, you'll implement a neural network and train it on historical data to make predictions. After training the network and viewing its performance as it's being trained, you'll compare your networks predictions with actual data. If you build your network right you should find the network does a really good job, for the most part. Right! It's time for you to get started on your project.
The data comes from the [UCI Machine Learning Database](https://archive.ics.uci.edu/ml/datasets/Bike+Sharing+Dataset).
## Getting Started:
For this project you have to download `anaconda` or `miniconda`. Then follow the below instructions -
1. Download the project materials from our GitHub repository. You can get download the repository with `git clone https://github.com/codeslash21/Predicting_Bike_Sharing_Pattern.git`.
2. cd into the `Predicting_Bike_Sharing_Pattern` directory.
3. Create a new conda environment:
```
conda create --name deep-learning python=3
```
4. Enter your new environment:
- Mac/Linux: `>> source activate deep-learning`
- Windows: `>> activate deep-learning`
5. Ensure you have `numpy`, `matplotlib`, `pandas`, and `jupyter notebook` installed by doing the following:
```
conda install numpy matplotlib pandas jupyter notebook
```
6. Run the following command to open up jupyter notebook:
```
jupyter notebook
```
7. In your browser, open `Your_first_neural_network.ipynb`.