Quick Start#


Install ads using pip (shown below) or OCI Conda Packs (see Installation)

python3 -m pip install "oracle_ads[forecast]"


Initialize your forecast through the ads cli command:

ads operator init -t forecast --output my-forecast

Input Data#

Within the forecast folder created above there will be a forecast.yaml file. This file should be updated to contain the details about your data and forecast. Prophet’s Yosemite Temperature dataset is provided as an example below:

cd my-forecast
vi forecast.yaml
kind: operator
type: forecast
version: v1
        name: ds
        url: https://raw.githubusercontent.com/facebook/prophet/main/examples/example_yosemite_temps.csv
    horizon: 3
    model: auto
    target_column: y

There are many more options in this YAML file.


Now run the forecast locally:

ads operator run -f forecast.yaml


If not specified in the YAML, all results will be placed in a new folder called results. Performance is summarized in the report.html file, and the full forecast is available in the forecast.csv file.

open results/report.html