Streaming Live Events

You can stream production data to Fiddler as an alternative to batch publishing. Streaming offers lower latency, which is beneficial for high-velocity or near real-time models.

When to Use Streaming vs. Batch Publishing

• Use streaming when low latency is a priority and you're working with individual events or small batches

• Use batch publishing for large datasets or when you need to track longer-running processes with Job objects

Stream Individual Inference Events

To stream a single inference event:

project = fdl.Project.from_name(name='your_project_name')
model = fdl.Model.from_name(name='your_model_name', project_id=project.id)

# A single event must still be passed as an array.
model.publish([
    {
        'customer_id': 1234,
        'timestamp': 1710428785,
        'CreditScore': 650,
        'Geography': 'France',
        'Gender': 'Female',
        'Age': 45,
        'Tenure': 2,
        'Balance': 10000.0,
        'NumOfProducts': 1,
        'HasCrCard': 'Yes',
        'isActiveMember': 'Yes',
        'EstimatedSalary': 120000,
        'probability_churned': 0.105,
        'churn': 1
    }
])

Stream Small Batches of Events

For better efficiency, you can stream multiple events at once:

# For multiple events, where `my_events` is a list of Python dictionaries
model.publish(my_events)

🚧 Note

Convert a pandas DataFrame to a list of event dictionaries using the to_dict function.

my_events = my_df.to_dict(orient='records')

For batches larger than 5,000 events, prefer batch publishing over streaming.