GithubHelp home page GithubHelp logo

fagan2888 / mixed-migration-forecasting Goto Github PK

View Code? Open in Web Editor NEW

This project forked from ibm/mixed-migration-forecasting

0.0 1.0 0.0 16.28 MB

Forecasting mixed migration for the Danish Refugee Council.

Python 73.70% Jupyter Notebook 23.89% PowerShell 0.40% Batchfile 0.37% Roff 1.64%

mixed-migration-forecasting's Introduction

mm4sight

Asset with the Danish Refugee Council for the mixed migration and displacement forecasting project.

Setting up

To get started, clone this repository.

$ git clone [email protected]:IBM/mixed-migration-forecasting.git

Then setup a python environment. If you use the Anaconda distribution (recommended), create a python virtual environment using conda. This way your project specific dependencies are isolated.

$ conda create -n mm4sight python=3.6
$ source activate mm4sight
(mm4sight) $ pip install -r requirements.txt

Here source activate mm4isght activates the virtual environment (source deactivate will deactivate it). pip install directives will install packages for the virtual environment.

Fetch the data artifacts. TBD

Running

The code is in three parts.

Data Transformation (optional): Scripts related to data manipulation. Data transformations are run based on the configuration.json file that has a source file along with a transformer class for each source. All transformer implementations are within the transformer folder. The entire transformation script can be run by activating your python virtual environment and running the wrapper script so.

$ source activate mm4sight
(mm4sight) $ python executor.py

This standardizes the data and populates the processed folder. A base set of processed data is available. So this step is only needed when new data sources or features are added.

Models: The models specification is available as a module in this repository. To recreate the model objects, run

(mm4sight) $ python model/trainer.py

Few additional helper scripts that may be of use.

  1. evaluation.py runs the evaluations reported in the paper.
  2. gridsearch.py determines grid search parameters for a country level model.
  3. test_prediction.py to see how the scoring API can be invoked and how scenarios can be defined.
  4. paper-plots.py shows some of the error analysis and plots used in the paper.

Deployment: We use a cloud foundry build pack which can be deployed to IBM Cloud.

mixed-migration-forecasting's People

Contributors

boschwartz avatar rahulnair23 avatar rahulnair23ibm avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.