Quick Start¶
Install¶
Install ads using pip (shown below) or OCI Conda Packs (see Installation)
python3 -m pip install "oracle_ads[anomaly]"
Initialize¶
Initialize your anomaly detection job through the ads cli command:
ads operator init -t anomaly
Input Data¶
Within the anomaly
folder created above there will be a anomaly.yaml
file. This file should be updated to contain the details about your data and anomaly. Prophet’s Yosemite Temperature dataset is provided as an example below:
cd anomaly
vi anomaly.yaml
kind: operator
type: anomaly
version: v1
spec:
datetime_column:
name: timestamp
target_category_columns:
- series_id
input_data:
url: https://raw.githubusercontent.com/oracle/accelerated-data-science/refs/heads/main/ads/opctl/operator/common/data/synthetic.csv
model: autots
target_column: target
There are many more options in this YAML file.
Run¶
Now run the anomaly detection job locally:
ads operator run -f anomaly.yaml
Results¶
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.
open results/report.html