airt-client 2022.5.0

airt client

Python client for airt service 2022.5.0

A python library encapsulating airt service REST API available at:

• https://api.airt.ai/

Docs

For full documentation, Please follow the below link:

• https://docs.airt.ai/

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

To access the airt service, you must create a developer account. Please fill out the signup form below to get one:

• https://bit.ly/3hbXQLY

Upon successful verification, you will receive the username/password for the developer account in an email.

Finally, you need an application token to access all the APIs in airt service. Please call the Client.get_token method with the username/password to get one.

You can either pass the username, password, and server address as parameters to the Client.get_token method or store the same in the AIRT_SERVICE_USERNAME, AIRT_SERVICE_PASSWORD, and AIRT_SERVER_URL environment variables.

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

For more information, please check:

• Tutorial with more elaborate example, and

• API with reference documentation.

Below is a minimal example explaining how to train a model and make predictions using airt services.

!!! info

In the below example, the username, password, and server address are stored in **AIRT_SERVICE_USERNAME**, **AIRT_SERVICE_PASSWORD**, and **AIRT_SERVER_URL** environment variables.

0. Get token

from airt.client import Client, DataSource, DataBlob

Client.get_token()

1. Connect data

# In this case, the input data is a CSV file strored in an AWS S3 bucket.

# Pulling the data into airt server
data_blob = DataBlob.from_s3(
    uri="s3://test-airt-service/ecommerce_behavior_csv"
)
data_blob.progress_bar()

# Preprocessing the data
data_source = data_blob.from_csv(
    index_column="user_id",
    sort_by="event_time"
)
data_source.progress_bar()

print(data_source.head())

100%|██████████| 1/1 [00:35<00:00, 35.34s/it]
100%|██████████| 1/1 [00:30<00:00, 30.30s/it]

                          event_time event_type  product_id  \
user_id                                                       
10300217   2019-11-06 06:51:52+00:00       view    26300219   
253299396  2019-11-05 21:25:44+00:00       view     2400724   
253299396  2019-11-05 21:27:43+00:00       view     2400724   
272811580  2019-11-05 19:38:48+00:00       view     3601406   
272811580  2019-11-05 19:40:21+00:00       view     3601406   
288929779  2019-11-06 05:39:21+00:00       view    15200134   
288929779  2019-11-06 05:39:34+00:00       view    15200134   
310768124  2019-11-05 20:25:52+00:00       view     1005106   
315309190  2019-11-05 23:13:43+00:00       view    31501222   
339186405  2019-11-06 07:00:32+00:00       view     1005115   

                   category_id              category_code  \
user_id                                                     
10300217   2053013563424899933                       None   
253299396  2053013563743667055    appliances.kitchen.hood   
253299396  2053013563743667055    appliances.kitchen.hood   
272811580  2053013563810775923  appliances.kitchen.washer   
272811580  2053013563810775923  appliances.kitchen.washer   
288929779  2053013553484398879                       None   
288929779  2053013553484398879                       None   
310768124  2053013555631882655     electronics.smartphone   
315309190  2053013558031024687                       None   
339186405  2053013555631882655     electronics.smartphone   

                               brand    price  \
user_id                                         
10300217                     sokolov    40.54   
253299396                      bosch   246.85   
253299396                      bosch   246.85   
272811580                       beko   195.60   
272811580                       beko   195.60   
288929779                      racer    55.86   
288929779                      racer    55.86   
310768124                      apple  1422.31   
315309190  dobrusskijfarforovyjzavod   115.18   
339186405                      apple   915.69   

                                   user_session  
user_id                                          
10300217   d1fdcbf1-bb1f-434b-8f1a-4b77f29a84a0  
253299396  b097b84d-cfb8-432c-9ab0-a841bb4d727f  
253299396  b097b84d-cfb8-432c-9ab0-a841bb4d727f  
272811580  d18427ab-8f2b-44f7-860d-a26b9510a70b  
272811580  d18427ab-8f2b-44f7-860d-a26b9510a70b  
288929779  fc582087-72f8-428a-b65a-c2f45d74dc27  
288929779  fc582087-72f8-428a-b65a-c2f45d74dc27  
310768124  79d8406f-4aa3-412c-8605-8be1031e63d6  
315309190  e3d5a1a4-f8fd-4ac3-acb7-af6ccd1e3fa9  
339186405  15197c7e-aba0-43b4-9f3a-a815e31ade40  

2. Train

from datetime import timedelta

model = data_source.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, 134.71it/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 [00:10<00:00,  3.37s/it]

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