| name: anomaly_detection | |
| enabled: true | |
| required: false | |
| description: >- | |
| anomaly_detection function identifies anomalies from an input DataFrame of | |
| time series. It will add a new column "Is_Anomaly", where each entry will be marked with "True" if the value is an anomaly or "False" otherwise. | |
| For example, result_df, description = anomaly_detection(df, "datetime", "value"). | |
| parameters: | |
| - name: df | |
| type: DataFrame | |
| required: true | |
| description: >- | |
| the input data from which we can identify the anomalies with the 3-sigma | |
| algorithm. | |
| - name: time_col_name | |
| type: str | |
| required: true | |
| description: name of the column that contains the datetime | |
| - name: value_col_name | |
| type: str | |
| required: true | |
| description: name of the column that contains the numeric values. | |
| returns: | |
| - name: df | |
| type: DataFrame | |
| description: >- | |
| This DataFrame extends the input DataFrame with a newly-added column | |
| "Is_Anomaly" containing the anomaly detection result. | |
| - name: description | |
| type: str | |
| description: This is a string describing the anomaly detection results. | |