Set up TruEra workspace, split data and add data collection

setup_truera_airbnb.py

import truera
#set up TruEra workspace
from truera.client.truera_workspace import TrueraWorkspace
from truera.client.truera_authentication import BasicAuthentication
auth = BasicAuthentication(USERNAME, PASSWORD)
tru = TrueraWorkspace(CONNECTION_STRING, auth, verify_cert = False)
tru.set_environment("remote")
tru.set_project("airbnb_sf_price", score_type="regression")
 
#create data collection or schema
tru.add_data_collection(data_collection_name = "sf_data_collection_v1",
                       pre_to_post_feature_map = feature_map_data,
                       provide_transform_with_model=True)
#add data splits to collection
tru.add_data_split("train", pre_data = X_train, label_data=y_train, split_type="train")
tru.add_data_split("test", pre_data = X_test, label_data=y_test, split_type="test")