Class BigQuerySource

sdk/python/feast/infra/offline_stores/bigquery_source.py:23–211

A BigQuerySource object defines a data source that a BigQueryOfflineStore class can use.

@typechecked
class BigQuerySource(DataSource):
    """A BigQuerySource object defines a data source that a BigQueryOfflineStore class can use."""

    def source_type(self) -> DataSourceProto.SourceType.ValueType:
        return DataSourceProto.BATCH_BIGQUERY

    def __init__(
        self,
        *,
        name: Optional[str] = None,
        timestamp_field: Optional[str] = None,
        table: Optional[str] = None,
        created_timestamp_column: Optional[str] = "",
        field_mapping: Optional[Dict[str, str]] = None,
        date_partition_column: Optional[str] = None,
        timestamp_field_type: Optional[str] = None,
        query: Optional[str] = None,
        description: Optional[str] = "",
        tags: Optional[Dict[str, str]] = None,
        owner: Optional[str] = "",
    ):
        """Create a BigQuerySource from an existing table or query.

        Args:
            name (optional): Name for the source. Defaults to the table if not specified, in which
                case the table must be specified.
            timestamp_field (optional): Event timestamp field used for point in time
                joins of feature values.
            table (optional): BigQuery table where the features are stored. At least one of 'table'
                and 'query' must be specified. When both are set, 'query' is used for reads and
                'table' is used as the write destination.
            created_timestamp_column (optional): Timestamp column when row was created, used for deduplicating rows.
            field_mapping (optional): A dictionary mapping of column names in this data source to feature names in a feature table
                or view. Only used for feature columns, not entities or timestamp columns.
            date_partition_column (optional): Timestamp column used for partitioning.
            timestamp_field_type (optional): Type of the timestamp_field column.
                Set to "DATE" when the event timestamp column is a DATE type,
                so SQL generation uses date-only comparisons instead of TIMESTAMP().
            query (optional): The query to be executed to obtain the features. When both 'table'
                and 'query' are provided, 'query' takes priority for reads.
            description (optional): A human-readable description.
            tags (optional): A dictionary of key-value pairs to store arbitrary metadata.
            owner (optional): The owner of the bigquery source, typically the email of the primary
                maintainer.
        Example:
            >>> from feast import BigQuerySource
            >>> my_bigquery_source = BigQuerySource(table="gcp_project:bq_dataset.bq_table")
        """
        if table is None and query is None:
            raise ValueError('No "table" or "query" argument provided.')

        self.bigquery_options = BigQueryOptions(table=table, query=query)

        # If no name, use the table as the default name.
        if name is None and table is None:
            raise DataSourceNoNameException()
        name = name or table
        assert name