Three notebooks to jump start a data science project
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
data
notebooks
.gitattributes
LICENSE
README.md
mean_depth_vs_time.png

README.md

subsurface_hackathon_2017

Three notebooks to jump start a data science project

This repository is associated with a post on my blog.


The three Jupyter notebooks that you will find here were originally written during the Subsurface Hackathon that took place in Paris in June 2017. Martin Bentley and I were in a team that tried to exploit the free availability of groundwater data from the Geological Survey of the Netherlands.

The notebooks provide some examples written in Python for tackling this project, but I think the code is pretty generic and can be used for a large range of other data science projects, especially in geology or geophysics.

mean_depth_vs_time

While much more is certainly possible to achieve with this dataset, I hope this work can help anyone who wants to start a data science project using open data, Python, the pandas library, and Jupyter notebooks.

Requirements

  • Python 3.5
  • pandas 0.20
  • matplotlib 2.0
  • numpy 1.12
  • Scipy 0.19
  • ipywidgets 6.0

Note that the notebooks might certainly work with slightly different configurations - nothing here is cutting edge.