feat: Onboard USA names dataset (#96)

* feat: create usa_names dataset and pipeline * generate terraform * add impersonating account * add BQ descriptions * decrease cadence of pipeline run * use `cat` in bash operator to combine TXT files * fixed YAML lint errors * generated DAG file Co-authored-by: Adler Santos <adlersantos@google.com>
GoogleCloudPlatform · Jul 21, 2021 · eb28f0f · eb28f0f
1 parent 0f0eb2b
commit eb28f0f
Show file tree

Hide file tree

Showing 7 changed files with 318 additions and 0 deletions.
diff --git a/datasets/usa_names/_terraform/provider.tf b/datasets/usa_names/_terraform/provider.tf
@@ -0,0 +1,28 @@
+/**
+ * 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.
+ */
+
+
+provider "google" {
+  project                     = var.project_id
+  impersonate_service_account = var.impersonating_acct
+  region                      = var.region
+}
+
+data "google_client_openid_userinfo" "me" {}
+
+output "impersonating-account" {
+  value = data.google_client_openid_userinfo.me.email
+}
diff --git a/datasets/usa_names/_terraform/usa_1910_current_pipeline.tf b/datasets/usa_names/_terraform/usa_1910_current_pipeline.tf
@@ -0,0 +1,39 @@
+/**
+ * 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.
+ */
+
+
+resource "google_bigquery_table" "usa_1910_current" {
+  project    = var.project_id
+  dataset_id = "usa_names"
+  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.\n\nsource: http://www.ssa.gov/OACT/babynames/limits.html"
+
+
+
+
+  depends_on = [
+    google_bigquery_dataset.usa_names
+  ]
+}
+
+output "bigquery_table-usa_1910_current-table_id" {
+  value = google_bigquery_table.usa_1910_current.table_id
+}
+
+output "bigquery_table-usa_1910_current-id" {
+  value = google_bigquery_table.usa_1910_current.id
+}
diff --git a/datasets/usa_names/_terraform/usa_names_dataset.tf b/datasets/usa_names/_terraform/usa_names_dataset.tf
@@ -0,0 +1,26 @@
+/**
+ * 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.
+ */
+
+
+resource "google_bigquery_dataset" "usa_names" {
+  dataset_id  = "usa_names"
+  project     = var.project_id
+  description = "This public dataset was created by the Social Security Administration and contains all names from Social Security card applications for births that occurred in the United States after 1879. Note that many people born before 1937 never applied for a Social Security card, so their names are not included in this data. For others who did apply, records may not show the place of birth, and again their names are not included in the data.\n\nAll data are from a 100% sample of records on Social Security card applications as of the end of February 2015.  To safeguard privacy, the Social Security Administration restricts names to those with at least 5 occurrences."
+}
+
+output "bigquery_dataset-usa_names-dataset_id" {
+  value = google_bigquery_dataset.usa_names.dataset_id
+}
diff --git a/datasets/usa_names/_terraform/variables.tf b/datasets/usa_names/_terraform/variables.tf
@@ -0,0 +1,23 @@
+/**
+ * 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.
+ */
+
+
+variable "project_id" {}
+variable "bucket_name_prefix" {}
+variable "impersonating_acct" {}
+variable "region" {}
+variable "env" {}
+
diff --git a/datasets/usa_names/dataset.yaml b/datasets/usa_names/dataset.yaml
@@ -0,0 +1,30 @@
+# 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.
+
+dataset:
+  name: usa_names
+
+  friendly_name: ~
+  description: ~
+  update_frequency: ~
+  dataset_sources: ~
+  terms_of_use: ~
+
+resources:
+  - type: bigquery_dataset
+    dataset_id: usa_names
+    description: |-
+      This public dataset was created by the Social Security Administration and contains all names from Social Security card applications for births that occurred in the United States after 1879. Note that many people born before 1937 never applied for a Social Security card, so their names are not included in this data. For others who did apply, records may not show the place of birth, and again their names are not included in the data.
+
+      All data are from a 100% sample of records on Social Security card applications as of the end of February 2015.  To safeguard privacy, the Social Security Administration restricts names to those with at least 5 occurrences.
diff --git a/datasets/usa_names/usa_1910_current/pipeline.yaml b/datasets/usa_names/usa_1910_current/pipeline.yaml
@@ -0,0 +1,83 @@
+# 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"
diff --git a/datasets/usa_names/usa_1910_current/usa_1910_current_dag.py b/datasets/usa_names/usa_1910_current/usa_1910_current_dag.py
@@ -0,0 +1,89 @@
+# 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.
+
+
+from airflow import DAG
+from airflow.contrib.operators import gcs_to_bq
+from airflow.operators import bash_operator
+
+default_args = {
+    "owner": "Google",
+    "depends_on_past": False,
+    "start_date": "2021-06-17",
+}
+
+
+with DAG(
+    dag_id="usa_names.usa_1910_current",
+    default_args=default_args,
+    max_active_runs=1,
+    schedule_interval="@monthly",
+    catchup=False,
+    default_view="graph",
+) as dag:
+
+    # Task to copy `namesbystate.zip` from Social Security Administration to GCS
+    download_and_process_source_zip_file = bash_operator.BashOperator(
+        task_id="download_and_process_source_zip_file",
+        bash_command="mkdir -p $data_dir/{{ ds }}\ncurl -o $data_dir/{{ ds }}/namesbystate.zip -L $zip_source_url\nunzip $data_dir/{{ ds }}/namesbystate.zip -d $data_dir/{{ ds }}\ncat $data_dir/{{ ds }}/*.TXT \u003e\u003e $data_dir/{{ ds }}/data.csv\n",
+        env={
+            "zip_source_url": "https://www.ssa.gov/OACT/babynames/state/namesbystate.zip",
+            "data_dir": "/home/airflow/gcs/data/usa_names/usa_1910_current",
+        },
+    )
+
+    # Task to load the data from Airflow data folder to BigQuery
+    load_csv_file_to_bq_table = gcs_to_bq.GoogleCloudStorageToBigQueryOperator(
+        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",
+            },
+        ],
+    )
+
+    download_and_process_source_zip_file >> load_csv_file_to_bq_table