/king-county-demographic-clustering

Demographic clustering for King County as an example of how to understand similarities and differences across an administrative area.

Primary LanguagePythonApache License 2.0Apache-2.0

king-county-demographic-clustering

Deomgraphic clustering using KMeans for understanding residents

Getting Started

1 - Clone this repo.

2 - Create an environment with the requirements.

        > make env

3 - What else?

Project Organization


    ├── LICENSE
    ├── Makefile           <- Makefile with commands like `make data`
    ├── make.bat           <- Windows batch file with commands like `make data`
    ├── setup.py           <- Setup script for the library (demograpic_clustering)
    ├── .env               <- Any environment variables here - created as part of project creation, 
    │                         but NOT syncronized with git repo for project.                
    ├── README.md          <- The top-level README for developers using this project.
    ├── arcgis             <- Root location for ArcGIS Pro project created as part of
    │   │                     data science project creation.
    │   ├── king-county-demographic-clustering.aprx <- ArcGIS Pro project.    
    │   └── king-county-demographic-clustering.tbx  <- ArcGIS Pro toolbox associated with the project.
    ├── data
    │   ├── external       <- Data from third party sources.
    │   ├── interim        <- Intermediate data that has been transformed.
    │   ├── processed      <- The final, canonical data sets for modeling.
    │   └── raw            <- The original, immutable data dump.
    ├── docs               <- A default Sphinx project; see sphinx-doc.org for details
    ├── models             <- Trained and serialized models, model predictions, or model summaries
    ├── notebooks          <- Jupyter notebooks. Naming convention is a 2 digits (for ordering),
    │   │                     descriptive name. e.g.: 01_exploratory_analysis.ipynb
    │   └── notebook_template.ipynb
    ├── references         <- Data dictionaries, manuals, and all other explanatory materials.
    ├── reports            <- Generated analysis as HTML, PDF, LaTeX, etc.
    │   └── figures        <- Generated graphics and figures to be used in reporting
    ├── environment.yml    <- Requirements file for reproducing the analysis execution environment.
    │                         This includes far fewer dependencies and does not include arcpy.
    ├── environment_dev.yml<- Requirements file for reproducing the analysis deveopment environment.
    │                         This includes arcpy and everything needed to generate Sphinx docs.
    └── src                <- Source code for use in this project - all scripts, modules and code.
        └── demograpic_clustering <- Library containing the bulk of code used in this 
                                                  project. 

Project based on the cookiecutter GeoAI project template. This template, in turn, is simply an extension and light modification of the cookiecutter data science project template. #cookiecutterdatascience