Skip to content

Python client for airt service (beta)

A python library encapsulating airt service REST API available at:

Docs

Full documentation can be found at the following link:

How to install

If you don't have the airt library already installed, please install it using pip.

pip install airt-client

How to use

Before you can use the service, you must acquire a username and password for your developer account. Please fill in the following form to get one:

The username, password, and server address can be passed explicitly while calling the authenticate method in the Client class or stored permanently in environment variables AIRT_SERVICE_USERNAME, AIRT_SERVICE_PASSWORD, and AIRT_SERVER_URL respectively.

Upon successful authentication, the airt services will be available to access.

Below is a minimal example explaining how to train a model and make predictions using airt services. The below example assumes the username, password, and server address required for authenticating the Client is stored in the environment variables AIRT_SERVICE_USERNAME, AIRT_SERVICE_PASSWORD, and AIRT_SERVER_URL respectively.

For more information, please check:

  • Tutorial with more elaborate example, and

  • API with reference documentation.

0. Authenticate

from airt.client import Client, DataSource

Client.authenticate()

1. Connect data

data_source_s3 = DataSource.s3(
    uri="s3://test-airt-service/ecommerce_behavior"
)

data_source_s3.pull().progress_bar()
print(data_source_s3.head())
100%|██████████| 1/1 [01:15<00:00, 75.27s/it]


                  event_time event_type  product_id          category_id  \
0  2019-11-01T00:00:00+00:00       view     1003461  2053013555631882655   
1  2019-11-01T00:00:00+00:00       view     5000088  2053013566100866035   
2  2019-11-01T00:00:01+00:00       view    17302664  2053013553853497655   
3  2019-11-01T00:00:01+00:00       view     3601530  2053013563810775923   
4  2019-11-01T00:00:01+00:00       view     1004775  2053013555631882655

               category_code   brand   price    user_id  \
0     electronics.smartphone  xiaomi  489.07  520088904   
1  appliances.sewing_machine  janome  293.65  530496790   
2                       None   creed   28.31  561587266   
3  appliances.kitchen.washer      lg  712.87  518085591   
4     electronics.smartphone  xiaomi  183.27  558856683

                           user_session  
0  4d3b30da-a5e4-49df-b1a8-ba5943f1dd33  
1  8e5f4f83-366c-4f70-860e-ca7417414283  
2  755422e7-9040-477b-9bd2-6a6e8fd97387  
3  3bfb58cd-7892-48cc-8020-2f17e6de6e7f  
4  313628f1-68b8-460d-84f6-cec7a8796ef2

2. Train

from datetime import timedelta

model = data_source_s3.train(
    client_column="user_id",
    target_column="event_type",
    target="*purchase",
    predict_after=timedelta(hours=3),
)
model.progress_bar()
print(model.evaluate())
100%|██████████| 5/5 [00:00<00:00, 443.94it/s]

            eval
accuracy   0.985
recall     0.962
precision  0.934

3. Predict

predictions = model.predict()
predictions.progress_bar()
print(predictions.to_pandas().head())
100%|██████████| 3/3 [00:00<00:00, 298.26it/s]

              Score
user_id            
520088904  0.979853
530496790  0.979157
561587266  0.979055
518085591  0.978915
558856683  0.977960
Back to top