Skip to content

edisonwang03/seoul-bike-sharing-demand

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 

Repository files navigation

Seoul Bike-Sharing Demand Model

Seoul Bike Sharing Demand Prediction

This project uses machine learning to predict the number of bikes rented per hour in the Seoul Bike Sharing System.

Data

The data used for this project is from the UCI Machine Learning Repository. It contains 8760 observations, each of which represents the number of bikes rented per hour in Seoul, South Korea. The data also includes weather information (temperature, rainfall, etc.) as well as date information (time of day, functioning days, etc.). The link is as follows: https://archive.ics.uci.edu/dataset/560/seoul+bike+sharing+demand

Libraries

The following libraries were used in this project:

  • NumPy and pandas were used to represent and manipulate the data
  • Seaborn and MatPlotLib were used to visualize the data
  • scikit-learn was used to transform the data (encoding text categories, standardize & scale, etc.), create pipelines, and test different models

Results

The best model that I found was a random forest regressor. It has a root mean squared error of 233.76.

image

Future Work

Some possible future work for this project includes:

  • Using more data to train the model
  • Trying other machine learning algorithms
  • Improving the data preprocessing steps

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published