tw.endpoints.anomaly_detection.build_model

tw.endpoints.anomaly_detection.build_model(configuration=dict,dataset=pandas.DataFrame)

Submit a model-building job.
POST ``/anomaly-detection/build-model``

Parameters

configuration : dict

Model configuration payload.

dataset : pandas.DataFrame

Historical training data serialised as CSV and sent as a multipart file.

Returns

dict

API response containing at least ``"id"`` (the new job identifier).

Example Configuration

CODE

anomaly_detection_build_model_configuration = {
    'normal_behavior':{
        'target_column':'str',
        'holiday_column:':'str',
        'target_offsets':'combined',
        'allow_offsets':True,
        'offset_limit': 0,
        'normalization':True,
        'max_feature_count':20,
        'transformations': [
            'exponential_moving_average',
            'rest_of_week',
            'periodic',
            'intercept',
            'piecewise_linear',
            'time_offsets',
            'polynomial',
            'identity',
            'simple_moving_average',
            'month',
            'trend',
            'day_of_week',
            'fourier',
            'public_holidays',
            'one_hot_encoding'
        ],    
        'daily_cycle':True,
        'confidence_level':90,
        'categorical_columns':[
            'str'
        ],
        'data_alignment': [
            {
                'column_name': 'string',
                'timestamp': 'yyyy-mm-dd hh:mm:ssZ'
            }
        ],
    },
    'detection_layers': [
        {
            'residuals_transformation':{
                'type':'residuals'
            },
            'sensitivity':0.3
        },
        {
            'residuals_transformation':{
                'type':'residuals_change',
                'window_length':2
            },
            'sensitivity':0.3
        },
        {
            'residuals_transformation':{
                'type':'moving_average',
                'window_length':1
            },
            'sensitivity':0.3
        },
        {
            'residuals_transformation':{
                'type':'moving_average_change',
                'window_lengths':[
                    2,
                    1
                ]
            },
            'sensitivity':0.3
        },
        {
            'residuals_transformation':{
                'type':'standard_deviation',
                'window_length':1
            },
            'sensitivity':0.3
        },
        {
            'residuals_transformation':{
                'type':'standard_deviation_change',
                'window_lengths':[
                    2,
                    1
                ]
            },
            'sensitivity':0.3
        },
    ]
}

Example Usage

CODE

anomaly_detection_build_model_response = tw.endpoints.anomaly_detection.build_model(
    configuration = anomaly_detection_build_model_configuration,
    dataset = dataset
)

Example Output

CODE

anomaly_detection_build_model_id = anomaly_detection_build_model_response['id']