mirror of
https://github.com/datahub-project/datahub.git
synced 2025-11-11 17:03:33 +00:00
50 lines
1.5 KiB
Python
50 lines
1.5 KiB
Python
import os
|
|
|
|
import datahub.emitter.mce_builder as builder
|
|
import datahub.metadata.schema_classes as models
|
|
from datahub.emitter.mcp import MetadataChangeProposalWrapper
|
|
from datahub.emitter.rest_emitter import DatahubRestEmitter
|
|
|
|
# Create an emitter to DataHub over REST
|
|
gms_server = os.getenv("DATAHUB_GMS_URL", "http://localhost:8080")
|
|
token = os.getenv("DATAHUB_GMS_TOKEN")
|
|
emitter = DatahubRestEmitter(gms_server=gms_server, token=token)
|
|
|
|
feature_table_urn = builder.make_ml_feature_table_urn(
|
|
feature_table_name="users_feature_table", platform="feast"
|
|
)
|
|
|
|
feature_urns = [
|
|
builder.make_ml_feature_urn(
|
|
feature_name="user_signup_date", feature_table_name="users_feature_table"
|
|
),
|
|
builder.make_ml_feature_urn(
|
|
feature_name="user_last_active_date", feature_table_name="users_feature_table"
|
|
),
|
|
]
|
|
|
|
primary_key_urns = [
|
|
builder.make_ml_primary_key_urn(
|
|
feature_table_name="users_feature_table",
|
|
primary_key_name="user_id",
|
|
)
|
|
]
|
|
|
|
feature_table_properties = models.MLFeatureTablePropertiesClass(
|
|
description="Test description",
|
|
# link your features to a feature table
|
|
mlFeatures=feature_urns,
|
|
# link your primary keys to the feature table
|
|
mlPrimaryKeys=primary_key_urns,
|
|
)
|
|
|
|
# MCP creation
|
|
metadata_change_proposal = MetadataChangeProposalWrapper(
|
|
entityUrn=feature_table_urn,
|
|
aspect=feature_table_properties,
|
|
)
|
|
|
|
# Emit metadata!
|
|
emitter.emit_mcp(metadata_change_proposal)
|
|
print(f"Created ML feature table: {feature_table_urn}")
|