Example of bauplan_import_plan.yamlΒΆ

plan_state:
  plan_id: to-be-filled
  branch_name: vlad.hello_bauplan
  table_identifier:
  - bauplan
  - vlad_green_taxi_table
  table_replace: false
schema_info:
  conflicts: []
  detected_schemas:
  - column_name: VendorID
    src_datatypes:
    - datatype: int
    dst_datatype:
    - datatype: int
  - column_name: lpep_pickup_datetime
    src_datatypes:
    - datatype: timestamp
      unit: us
    dst_datatype:
    - datatype: timestamp
      unit: us
      timezone: UTC
  - column_name: lpep_dropoff_datetime
    src_datatypes:
    - datatype: timestamp
      unit: us
    dst_datatype:
    - datatype: timestamp
      unit: us
      timezone: UTC
  - column_name: store_and_fwd_flag
    src_datatypes:
    - datatype: string
    dst_datatype:
    - datatype: string
  - column_name: RatecodeID
    src_datatypes:
    - datatype: long
    dst_datatype:
    - datatype: long
  - column_name: PULocationID
    src_datatypes:
    - datatype: int
    dst_datatype:
    - datatype: int
  - column_name: DOLocationID
    src_datatypes:
    - datatype: int
    dst_datatype:
    - datatype: int
  - column_name: passenger_count
    src_datatypes:
    - datatype: long
    dst_datatype:
    - datatype: long
  - column_name: trip_distance
    src_datatypes:
    - datatype: double
    dst_datatype:
    - datatype: double
  - column_name: fare_amount
    src_datatypes:
    - datatype: double
    dst_datatype:
    - datatype: double
  - column_name: extra
    src_datatypes:
    - datatype: double
    dst_datatype:
    - datatype: double
  - column_name: mta_tax
    src_datatypes:
    - datatype: double
    dst_datatype:
    - datatype: double
  - column_name: tip_amount
    src_datatypes:
    - datatype: double
    dst_datatype:
    - datatype: double
  - column_name: tolls_amount
    src_datatypes:
    - datatype: double
    dst_datatype:
    - datatype: double
  - column_name: ehail_fee
    src_datatypes:
    - datatype: double
    dst_datatype:
    - datatype: double
  - column_name: improvement_surcharge
    src_datatypes:
    - datatype: double
    dst_datatype:
    - datatype: double
  - column_name: total_amount
    src_datatypes:
    - datatype: double
    dst_datatype:
    - datatype: double
  - column_name: payment_type
    src_datatypes:
    - datatype: long
    dst_datatype:
    - datatype: long
  - column_name: trip_type
    src_datatypes:
    - datatype: long
    dst_datatype:
    - datatype: long
  - column_name: congestion_surcharge
    src_datatypes:
    - datatype: double
    dst_datatype:
    - datatype: double
  partitions: []
plan_metadata:
  cloud_provider_info:
    provider: s3
    bucket_region: us-east-1
internal_scan_summary:
- column_to_type:
    VendorID:
      datatype: int
    lpep_pickup_datetime:
      datatype: timestamp
      unit: us
    lpep_dropoff_datetime:
      datatype: timestamp
      unit: us
    store_and_fwd_flag:
      datatype: string
    RatecodeID:
      datatype: long
    PULocationID:
      datatype: int
    DOLocationID:
      datatype: int
    passenger_count:
      datatype: long
    trip_distance:
      datatype: double
    fare_amount:
      datatype: double
    extra:
      datatype: double
    mta_tax:
      datatype: double
    tip_amount:
      datatype: double
    tolls_amount:
      datatype: double
    ehail_fee:
      datatype: double
    improvement_surcharge:
      datatype: double
    total_amount:
      datatype: double
    payment_type:
      datatype: long
    trip_type:
      datatype: long
    congestion_surcharge:
      datatype: double
  path: s3://alpha-hello-bauplan/green-taxi/green_tripdata_2023-02.parquet
plan_schema_version: 0.3.0