https://github.com/dominodatalab/domino-intro-project-python

Code used for training
https://github.com/dominodatalab/domino-intro-project-python

Last synced: about 2 months ago
JSON representation

Code used for training

• Host: GitHub
• URL: https://github.com/dominodatalab/domino-intro-project-python
• Owner: dominodatalab
• Created: 2022-02-03T21:38:33.000Z (almost 3 years ago)
• Default Branch: main
• Last Pushed: 2022-02-07T21:33:36.000Z (almost 3 years ago)
• Last Synced: 2023-08-07T03:05:38.573Z (over 1 year ago)
• Language: Jupyter Notebook
• Size: 6.83 MB
• Stars: 0
• Watchers: 5
• Forks: 0
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
This project contains the code, data, and artifacts for the Domino Training, including the setup for the *Getting Started in Domino* Tutorial, found 

[here](https://docs.dominodatalab.com/en/4.6/get_started/index.html) for Python.

This tutorial will guide you through a common model lifecycle in Domino. 

You will start by working with data from the Balancing Mechanism Reporting Service in the UK. 

We will be exploring the Electricty Generation by Fuel Type and predicting the electricty generation in the future. 

You’ll see examples of Jupyter, Dash, pandas, and Prophet used in Domino.

Table of Contents:

* Forecast_Power_Generation.ipynb

* Scheduled_Forecast_Power_Generation.ipynb

* Forecast_Power_Generation_for_Launcher.ipynb

* forecast.ipynb

* forecast_predictor.py

* data.csv

* app.sh

Be sure to set up an environment with the following code in the Dockerfile before starting the activities:

```

RUN pip install "pystan==2.17.1.0" "plotly<4.0.0" requests dash && pip install fbprophet==0.6

RUN pip install --upgrade nbclient nbconvert

RUN pip install papermill

```

To run the model API, generate the model.pkl file by running the Forecast_Power_Generation.ipynb notebook in a Domino workspace.