Skip to content

Commit

Permalink
Create NTD external tables for Historical API data
Browse files Browse the repository at this point in the history
  • Loading branch information
erikamov committed Sep 20, 2024
1 parent a9ff8a6 commit 0ca8e11
Show file tree
Hide file tree
Showing 4 changed files with 612 additions and 0 deletions.
Original file line number Diff line number Diff line change
@@ -0,0 +1,140 @@
operator: operators.ExternalTable
bucket: gs://calitp-ntd-api-products
source_objects:
- "fra_regulated_mode_major_security_events/historical/*.jsonl.gz"
source_format: NEWLINE_DELIMITED_JSON
use_bq_client: true
hive_options:
mode: CUSTOM
require_partition_filter: false
source_uri_prefix: "fra_regulated_mode_major_security_events/historical/{dt:DATE}/{execution_ts:TIMESTAMP}"
destination_project_dataset_table: "external_ntd__annual_reporting.historical__fra_regulated_mode_major_security_events"
prefix_bucket: false
post_hook: SELECT * FROM `{{ get_project_id() }}`.external_ntd__annual_reporting.historical__fra_regulated_mode_major_security_events LIMIT 1;
schema_fields:
- name: agency
type: STRING
- name: approximate_address
type: STRING
- name: bicyclist_fatalities
type: STRING
- name: bicyclist_injuries
type: STRING
- name: bicyclist_serious_injuries
type: STRING
- name: event_location
type: STRING
- name: event_type
type: STRING
- name: fixed_route_flag
type: STRING
- name: incident_date
type: STRING
- name: incident_description
type: STRING
- name: incident_number
type: STRING
- name: incident_time
type: STRING
- name: intentional_y_n
type: STRING
- name: mode
type: STRING
- name: ntd_id
type: NUMERIC
- name: number_of_transit_vehicles
type: STRING
- name: number_of_vehicles_involved
type: STRING
- name: occupant_of_other_vehicle
type: STRING
- name: occupant_of_other_vehicle_1
type: STRING
- name: occupant_of_other_vehicle_2
type: STRING
- name: other_fatalities
type: STRING
- name: other_injuries
type: STRING
- name: other_serious_injuries
type: STRING
- name: other_worker_fatalities
type: STRING
- name: other_worker_injuries
type: STRING
- name: other_worker_serious_injuries
type: STRING
- name: pedestrian_crossing_tracks
type: STRING
- name: pedestrian_crossing_tracks_1
type: STRING
- name: pedestrian_crossing_tracks_2
type: STRING
- name: pedestrian_in_crosswalk
type: STRING
- name: pedestrian_in_crosswalk_1
type: STRING
- name: pedestrian_in_crosswalk_2
type: STRING
- name: pedestrian_not_in_crosswalk
type: STRING
- name: pedestrian_not_in_crosswalk_1
type: STRING
- name: pedestrian_not_in_crosswalk_2
type: STRING
- name: pedestrian_walking_along
type: STRING
- name: pedestrian_walking_along_1
type: STRING
- name: pedestrian_walking_along_2
type: STRING
- name: people_waiting_or_leaving
type: STRING
- name: people_waiting_or_leaving_1
type: STRING
- name: people_waiting_or_leaving_2
type: STRING
- name: person_list
type: STRING
- name: property_damage
type: STRING
- name: rail_bus_ferry
type: STRING
- name: safety_security
type: STRING
- name: self_evacuation_y_n
type: STRING
- name: suicide_fatalities
type: STRING
- name: suicide_injuries
type: STRING
- name: suicide_serious_injuries
type: STRING
- name: total_fatalities
type: STRING
- name: total_injuries
type: STRING
- name: towed_y_n
type: STRING
- name: transit_employee_fatalities
type: STRING
- name: transit_employee_injuries
type: STRING
- name: transit_employee_serious
type: STRING
- name: transit_vehicle_operator
type: STRING
- name: transit_vehicle_operator_1
type: STRING
- name: transit_vehicle_operator_2
type: STRING
- name: transit_vehicle_rider
type: STRING
- name: transit_vehicle_rider_injuries
type: STRING
- name: transit_vehicle_rider_serious
type: STRING
- name: type_of_service
type: STRING
- name: year
type: STRING
Original file line number Diff line number Diff line change
@@ -0,0 +1,166 @@
operator: operators.ExternalTable
bucket: gs://calitp-ntd-api-products
source_objects:
- "major_safety_events/historical/*.jsonl.gz"
source_format: NEWLINE_DELIMITED_JSON
use_bq_client: true
hive_options:
mode: CUSTOM
require_partition_filter: false
source_uri_prefix: "major_safety_events/historical/{dt:DATE}/{execution_ts:TIMESTAMP}"
destination_project_dataset_table: "external_ntd__annual_reporting.historical__major_safety_events"
prefix_bucket: false
post_hook: SELECT * FROM `{{ get_project_id() }}`.external_ntd__annual_reporting.historical__major_safety_events LIMIT 1;
schema_fields:
# - name: :@computed_region_8fe2_rd7y
# type: STRING
# - name: :@computed_region_m2nu_4dib
# type: STRING
- name: _5_digit_ntd_id
type: STRING
- name: agency
type: STRING
- name: approximate_address
type: STRING
- name: assault_homicide_person_type_desc
type: STRING
- name: assault_homicide_transit_worker_flag
type: STRING
- name: assault_homicide_type_desc
type: STRING
- name: bicyclist_fatalities
type: STRING
- name: bicyclist_injuries
type: STRING
- name: bicyclist_serious_injuries
type: STRING
- name: event_category
type: STRING
- name: event_type
type: STRING
- name: event_type_group
type: STRING
- name: fixed_route_flag
type: STRING
- name: incident_date
type: STRING
- name: incident_description
type: STRING
- name: incident_number
type: STRING
- name: incident_time
type: STRING
- name: intentional_y_n
type: STRING
- name: latitude
type: STRING
- name: latlon
type: STRING
- name: life_safety_y_n
type: STRING
- name: location_type
type: STRING
- name: longitude
type: STRING
- name: mode
type: STRING
- name: mode_name
type: STRING
- name: number_of_transit_vehicles
type: STRING
- name: number_of_vehicles_involved
type: STRING
- name: occupant_of_other_vehicle
type: STRING
- name: occupant_of_other_vehicle_1
type: STRING
- name: occupant_of_other_vehicle_2
type: STRING
- name: other_fatalities
type: STRING
- name: other_injuries
type: STRING
- name: other_serious_injuries
type: STRING
- name: other_worker_fatalities
type: STRING
- name: other_worker_injuries
type: STRING
- name: other_worker_serious_injuries
type: STRING
- name: pederstiran_in_crosswalk
type: STRING
- name: pederstiran_in_crosswalk_1
type: STRING
- name: pedestrian_crossing_tracks
type: STRING
- name: pedestrian_crossing_tracks_1
type: STRING
- name: pedestrian_crossing_tracks_2
type: STRING
- name: pedestrian_in_crosswalk
type: STRING
- name: pedestrian_not_in_crosswalk
type: STRING
- name: pedestrian_not_in_crosswalk_1
type: STRING
- name: pedestrian_not_in_crosswalk_2
type: STRING
- name: pedestrian_walking_along
type: STRING
- name: pedestrian_walking_along_1
type: STRING
- name: pedestrian_walking_along_2
type: STRING
- name: people_waiting_or_leaving
type: STRING
- name: people_waiting_or_leaving_1
type: STRING
- name: people_waiting_or_leaving_2
type: STRING
- name: person_list
type: STRING
- name: rail_bus_ferry
type: STRING
- name: safety_security
type: STRING
- name: self_evacuation_y_n
type: STRING
- name: suicide_fatalities
type: STRING
- name: suicide_injuries
type: STRING
- name: suicide_serious_injuries
type: STRING
- name: total_fatalities
type: STRING
- name: total_injuries
type: STRING
- name: total_serious_injuries
type: STRING
- name: towed_y_n
type: STRING
- name: transit_employee_fatalities
type: STRING
- name: transit_employee_injuries
type: STRING
- name: transit_employee_serious
type: STRING
- name: transit_vehicle_operator
type: STRING
- name: transit_vehicle_operator_1
type: STRING
- name: transit_vehicle_operator_2
type: STRING
- name: transit_vehicle_rider
type: STRING
- name: transit_vehicle_rider_injuries
type: STRING
- name: transit_vehicle_rider_serious
type: STRING
- name: type_of_service
type: STRING
- name: uace_code
type: STRING
- name: year
type: STRING
Loading

0 comments on commit 0ca8e11

Please sign in to comment.