/
pipeline.yaml
83 lines (77 loc) · 3.12 KB
/
pipeline.yaml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
# Copyright 2021 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
---
resources:
- type: bigquery_table
table_id: usa_1910_current
description: |-
The table contains the number of applicants for a Social Security card by year of birth and sex. The number of such applicants is restricted to U.S. births where the year of birth, sex, State of birth (50 States and District of Columbia) are known, and where the given name is at least 2 characters long.
source: http://www.ssa.gov/OACT/babynames/limits.html
dag:
initialize:
dag_id: "usa_1910_current"
default_args:
owner: "Google"
depends_on_past: False
start_date: '2021-06-17'
max_active_runs: 1
schedule_interval: "@monthly"
catchup: False
default_view: graph
tasks:
- operator: "BashOperator"
description: "Task to copy `namesbystate.zip` from Social Security Administration to GCS"
args:
task_id: "download_and_process_source_zip_file"
bash_command: |
mkdir -p $data_dir/{{ ds }}
curl -o $data_dir/{{ ds }}/namesbystate.zip -L $zip_source_url
unzip $data_dir/{{ ds }}/namesbystate.zip -d $data_dir/{{ ds }}
cat $data_dir/{{ ds }}/*.TXT >> $data_dir/{{ ds }}/data.csv
env:
zip_source_url: "https://www.ssa.gov/OACT/babynames/state/namesbystate.zip"
data_dir: "/home/airflow/gcs/data/usa_names/usa_1910_current"
- operator: "GoogleCloudStorageToBigQueryOperator"
description: "Task to load the data from Airflow data folder to BigQuery"
args:
task_id: "load_csv_file_to_bq_table"
bucket: "{{ var.json.shared.composer_bucket }}"
source_objects: ["data/usa_names/usa_1910_current/{{ ds }}/data.csv"]
source_format: "CSV"
destination_project_dataset_table: "usa_names.usa_1910_current"
skip_leading_rows: 0
write_disposition: "WRITE_TRUNCATE"
schema_fields:
- name: state
type: STRING
description: 2-digit state code
mode: NULLABLE
- name: gender
type: STRING
description: Sex (M=male or F=female)
mode: NULLABLE
- name: year
type: INTEGER
description: 4-digit year of birth
mode: NULLABLE
- name: name
type: STRING
description: Given name of a person at birth
mode: NULLABLE
- name: number
type: INTEGER
description: Number of occurrences of the name
mode: NULLABLE
graph_paths:
- "download_and_process_source_zip_file >> load_csv_file_to_bq_table"