codeformuenster/datadive-on-time-series

Name: datadive-on-time-series

Owner: codeformuenster

Description: Code (python, scikit-learn) zum DataScience Münster Wettbewerb: Besucherzahlen vorhersagen mit Machine Learning

Created: 2016-10-30 15:03:00.0

Updated: 2016-11-13 14:43:27.0

Pushed: 2016-11-13 14:46:49.0

Homepage:

Size: 5

Language: Jupyter Notebook

GitHub Committers

UserMost Recent Commit# Commits

Other Committers

UserEmailMost Recent Commit# Commits

README

Contribution to the Münster Datadive On Time Series Competition

About the repository content

This is the jupyter notebook code that we used to place 4th in the DataScience Münster Meetup DataDive Hackathon in 10/2016. The goal of the Kaggle Competition was to predict visitors of the Nettebad in Osnabrück. Sadly the dataset license does not match our license, so there is no input data here, just the prediction code.

Requirements

Python (tested with 2.7 and 3.5), jupyter notebook, scikit-learn and pandas.

This work is supported by the National Institutes of Health's National Center for Advancing Translational Sciences, Grant Number U24TR002306. This work is solely the responsibility of the creators and does not necessarily represent the official views of the National Institutes of Health.