Skip to content

Commit

Permalink
Add READEME instructions
Browse files Browse the repository at this point in the history
  • Loading branch information
mdietrichstein committed Mar 16, 2018
1 parent 322f5f5 commit 8db77e0
Showing 1 changed file with 44 additions and 0 deletions.
44 changes: 44 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,44 @@
# Correlating Alcohol Consumption and UFO Sightings in the USA

The code in this repository explores the connection between the alcohol consumption per capita and the number of ufo sightings in the USA.


## Data Sources

* [NUFORC](http://www.nuforc.org/) UFO Sightings, downloaded from [Github](https://github.com/planetsig/ufo-reports)
* [OECD Alcohol Consumption per Capita in the USA](https://data.oecd.org/healthrisk/alcohol-consumption.htm) via the OECD Data Portal

## Running the code

To run the code in this repository you will need to have access to a machine running `python` (at least version `3.5`) and pip.

Run `pip install -r requirements.txt` to install the required dependencies.

Once the dependencies have been installed, start the jupyter notebook server via `jupyter notebook` and open `http://localhost:8888`.

In the `notebooks` folder you'll find the following notebooks:

**01_data-preprocessing.ipynb**

Running this notebook generates a dataset consisting of the number of ufo sightings and the alcohol consumption in the usa per year by preprocessing and accumulating the data provided by the datasources mentioned above.

The resulting dataset is located at `data/processed/ufo_alcohol.csv`

**02_visualization.ipynb**

This notebook takes the data generated by running `01_data-preprocessing.ipynb` as input and generates a plot to visualize correlations between the data points.

The resulting plot is stored at `reports/figures/correlation.png`


### Docker

Run `docker build .` to create a docker image of this repository. The resulting image exposes the jupyter notebook on port `8888`.

Boot a docker container via `docker run -i -p 8888:8888 <IMAGE_ID>` to start a jupyter instance. The resulting console output will show the url you can open in your browser to take a look at the code, e.g.

```
Copy/paste this URL into your browser when you connect for the first time,
to login with a token:
http://0.0.0.0:8888/?token=<SOME_TOKEN>
```

0 comments on commit 8db77e0

Please sign in to comment.