Skip to content
GitLab
Projects Groups Snippets
  • /
  • Help
    • Help
    • Support
    • Community forum
    • Submit feedback
    • Contribute to GitLab
  • Sign in
  • F Forecaster Toolbox
  • Project information
    • Project information
    • Activity
    • Labels
    • Members
  • Repository
    • Repository
    • Files
    • Commits
    • Branches
    • Tags
    • Contributors
    • Graph
    • Compare
  • Issues 0
    • Issues 0
    • List
    • Boards
    • Service Desk
    • Milestones
  • Merge requests 0
    • Merge requests 0
  • CI/CD
    • CI/CD
    • Pipelines
    • Jobs
    • Schedules
  • Deployments
    • Deployments
    • Environments
    • Releases
  • Monitor
    • Monitor
    • Incidents
  • Analytics
    • Analytics
    • Value stream
    • CI/CD
    • Repository
  • Wiki
    • Wiki
  • Snippets
    • Snippets
  • Activity
  • Graph
  • Create a new issue
  • Jobs
  • Commits
  • Issue Boards
Collapse sidebar
  • SDK4EDSDK4ED
  • Forecaster Toolbox
  • Wiki
  • usage

usage · Changes

Page history
Create usage authored Apr 28, 2020 by Dimitris Tsoukalas's avatar Dimitris Tsoukalas
Show whitespace changes
Inline Side-by-side
usage.md 0 → 100644
View page @ 10a8f921
In this example we want to predict TD Principal of the [Apache Kafka](https://github.com/apache/kafka) test project for 10 steps ahead. Apache Kafka dataset contains 150 versions, so we expect the response to contain predicted TD values for versions 151 to 160. We set the *horizon* parameter to *10* and the *regressor* parameter to *auto*, in order to allow the TD Forecaster to choose the best model based on training error minimization.
Once the server is running, open your web browser and navigate to the following URL:
http://127.0.0.1:5000/ForecasterToolbox/TDForecasting?horizon=10&project=apache_kafka_measures&regressor=auto&ground_truth=yes&test=no
The response of the submitted command is a JSON object containing the forecasted TD values of the Apache Kafka test project for versions 151 to 160 (10 steps) ahead, using the Ridge regressor, which the back-end selected as the most appropriate model for this occasion. This JSON object is illustrated below:
```json
{
"message": "The request was fulfilled.",
"results": {
"forecasts": [{
"value": 62319.09731430385,
"version": 151
},
{
"value": 62516.381787162965,
"version": 152
},
{
"value": 62690.433655431836,
"version": 153
},
{
"value": 62870.72795431035,
"version": 154
},
{
"value": 63045.263349635316,
"version": 155
},
{
"value": 63226.55220201901,
"version": 156
},
{
"value": 63422.0804451476,
"version": 157
},
{
"value": 63630.16211082426,
"version": 158
},
{
"value": 63849.70018133768,
"version": 159
},
{
"value": 64080.05189562486,
"version": 160
}
],
"parameters": {
"ground_truth": "no",
"horizon": 10,
"project": "apache_kafka_measures",
"regressor": "ridge",
"test": "no"
}
},
"status": 200
}
```
\ No newline at end of file
Clone repository
  • description
  • Home
  • installation
  • run server
  • usage