feat: Onboard BLS dataset

datasets/bls/_images/run_csv_transform_kub/Dockerfile

@@ -0,0 +1,43 @@
+# 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.
+
+# The base image for this build
+FROM python:3.8
+
+# Allow statements and log messages to appear in Cloud logs
+ENV PYTHONUNBUFFERED True
+
+RUN apt-get -y update && apt-get install -y apt-transport-https ca-certificates gnupg &&\
+    echo "deb https://packages.cloud.google.com/apt cloud-sdk main" | tee -a /etc/apt/sources.list.d/google-cloud-sdk.list &&\
+    curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | apt-key add - &&\
+    apt-get -y update && apt-get install -y google-cloud-sdk
+
+
+# Copy the requirements file into the image
+COPY requirements.txt ./
+
+# Install the packages specified in the requirements file
+RUN python3 -m pip install --no-cache-dir -r requirements.txt
+
+# The WORKDIR instruction sets the working directory for any RUN, CMD,
+# ENTRYPOINT, COPY and ADD instructions that follow it in the Dockerfile.
+# If the WORKDIR doesn’t exist, it will be created even if it’s not used in
+# any subsequent Dockerfile instruction
+WORKDIR /custom
+
+# Copy the specific data processing script/s in the image under /custom/*
+COPY ./csv_transform.py .
+
+# Command to run the data processing script when the container is run
+CMD ["python3", "csv_transform.py"]

datasets/bls/_images/run_csv_transform_kub/csv_transform.py

@@ -0,0 +1,148 @@
+# 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.
+
+import datetime
+import json
+import logging
+import os
+import pathlib
+import re
+import subprocess
+import typing
+
+import pandas as pd
+from google.cloud import storage
+
+
+def main(
+    source_url: typing.List[str],
+    source_file: typing.List[pathlib.Path],
+    target_file: pathlib.Path,
+    target_gcs_bucket: str,
+    target_gcs_path: str,
+    headers: typing.List[str],
+    pipeline_name: str,
+    joining_key: str,
+    columns: typing.List[str],
+) -> None:
+
+    logging.info(
+        f"BLS {pipeline_name} process started at "
+        + str(datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S"))
+    )
+
+    logging.info("Creating 'files' folder")
+    pathlib.Path("./files").mkdir(parents=True, exist_ok=True)
+
+    logging.info("Downloading file...")
+    download_file(source_url, source_file)
+
+    logging.info("Reading the file(s)....")
+    df = read_files(source_file, joining_key)
+
+    logging.info("Transform: Removing whitespace from headers names...")
+    df.columns = df.columns.str.strip()
+
+    logging.info("Transform: Trim Whitespaces...")
+    tream_white_spaces(df, columns)
+
+    if pipeline_name == "unemployment_cps":
+        logging.info("Transform: Replacing values...")
+        df["value"] = df["value"].apply(reg_exp_tranformation, args=(r"^(\-)$", ""))
+
+    logging.info("Transform: Reordering headers..")
+    df = df[headers]
+
+    logging.info(f"Saving to output file.. {target_file}")
+    try:
+        save_to_new_file(df, file_path=str(target_file))
+    except Exception as e:
+        logging.error(f"Error saving output file: {e}.")
+    logging.info("..Done!")
+
+    logging.info(
+        f"Uploading output file to.. gs://{target_gcs_bucket}/{target_gcs_path}"
+    )
+    upload_file_to_gcs(target_file, target_gcs_bucket, target_gcs_path)
+
+    logging.info(
+        f"BLS {pipeline_name} process completed at "
+        + str(datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S"))
+    )
+
+
+def save_to_new_file(df: pd.DataFrame, file_path: pathlib.Path) -> None:
+    df.to_csv(file_path, index=False)
+
+
+def download_file(
+    source_url: typing.List[str], source_file: typing.List[pathlib.Path]
+) -> None:
+    for url, file in zip(source_url, source_file):
+        logging.info(f"Downloading file from {url} ...")
+        subprocess.check_call(["gsutil", "cp", f"{url}", f"{file}"])
+
+
+def read_files(
+    source_file: typing.List[pathlib.Path], joining_key: str
+) -> pd.DataFrame:
+    if len(source_file) > 1:
+        if source_file[0][-3:] == "csv":
+            df1 = pd.read_csv(source_file[0])
+        else:
+            df1 = pd.read_csv(source_file[0], sep="\t")
+        if source_file[1][-3:] == "csv":
+            df2 = pd.read_csv(source_file[1])
+        else:
+            df2 = pd.read_csv(source_file[1], sep="\t")
+        df = pd.merge(df1, df2, how="left", on=joining_key)
+    else:
+        if source_file[0][-3:] == "csv":
+            df = pd.read_csv(source_file[0])
+        else:
+            df = pd.read_csv(source_file[0], sep="\t")
+    return df
+
+
+def tream_white_spaces(df: pd.DataFrame, columns: typing.List[str]) -> None:
+    for col in columns:
+        df[col] = df[col].astype(str).str.strip()
+
+
+def reg_exp_tranformation(str_value: str, search_pattern: str, replace_val: str) -> str:
+    str_value = re.sub(search_pattern, replace_val, str_value)
+    return str_value
+
+
+def upload_file_to_gcs(file_path: pathlib.Path, gcs_bucket: str, gcs_path: str) -> None:
+    storage_client = storage.Client()
+    bucket = storage_client.bucket(gcs_bucket)
+    blob = bucket.blob(gcs_path)
+    blob.upload_from_filename(file_path)
+
+
+if __name__ == "__main__":
+    logging.getLogger().setLevel(logging.INFO)
+
+    main(
+        source_url=json.loads(os.environ["SOURCE_URL"]),
+        source_file=json.loads(os.environ["SOURCE_FILE"]),
+        target_file=pathlib.Path(os.environ["TARGET_FILE"]).expanduser(),
+        target_gcs_bucket=os.environ["TARGET_GCS_BUCKET"],
+        target_gcs_path=os.environ["TARGET_GCS_PATH"],
+        headers=json.loads(os.environ["CSV_HEADERS"]),
+        pipeline_name=os.environ["PIPELINE_NAME"],
+        joining_key=os.environ["JOINING_KEY"],
+        columns=json.loads(os.environ["TRIM_SPACE"]),
+    )

datasets/bls/_images/run_csv_transform_kub/requirements.txt

@@ -0,0 +1,2 @@
+pandas
+google-cloud-storage

datasets/bls/_terraform/c_cpi_u_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" "c_cpi_u" {
+  project    = var.project_id
+  dataset_id = "bls"
+  table_id   = "c_cpi_u"
+
+  description = "C_CPI_U Dataset"
+
+
+
+
+  depends_on = [
+    google_bigquery_dataset.bls
+  ]
+}
+
+output "bigquery_table-c_cpi_u-table_id" {
+  value = google_bigquery_table.c_cpi_u.table_id
+}
+
+output "bigquery_table-c_cpi_u-id" {
+  value = google_bigquery_table.c_cpi_u.id
+}

datasets/bls/_terraform/cpi_u_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" "cpi_u" {
+  project    = var.project_id
+  dataset_id = "bls"
+  table_id   = "cpi_u"
+
+  description = "CPI_U Dataset"
+
+
+
+
+  depends_on = [
+    google_bigquery_dataset.bls
+  ]
+}
+
+output "bigquery_table-cpi_u-table_id" {
+  value = google_bigquery_table.cpi_u.table_id
+}
+
+output "bigquery_table-cpi_u-id" {
+  value = google_bigquery_table.cpi_u.id
+}

datasets/bls/_terraform/cpsaat18_pipeline.tf

@@ -22,6 +22,9 @@ resource "google_bigquery_table" "cpsaat18" {
 
   description = "Current population survey 18: Employed persons by detailed industry, sex, race, and Hispanic or Latino ethnicity"
 
+
+
+
   depends_on = [
     google_bigquery_dataset.bls
   ]

datasets/bls/_terraform/employment_hours_earnings_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" "employment_hours_earnings" {
+  project    = var.project_id
+  dataset_id = "bls"
+  table_id   = "employment_hours_earnings"
+
+  description = "Employment_Hours_Earnings Dataset"
+
+
+
+
+  depends_on = [
+    google_bigquery_dataset.bls
+  ]
+}
+
+output "bigquery_table-employment_hours_earnings-table_id" {
+  value = google_bigquery_table.employment_hours_earnings.table_id
+}
+
+output "bigquery_table-employment_hours_earnings-id" {
+  value = google_bigquery_table.employment_hours_earnings.id
+}

datasets/bls/_terraform/employment_hours_earnings_series_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" "employment_hours_earnings_series" {
+  project    = var.project_id
+  dataset_id = "bls"
+  table_id   = "employment_hours_earnings_series"
+
+  description = "Employment_Hours_Earnings_Series Dataset"
+
+
+
+
+  depends_on = [
+    google_bigquery_dataset.bls
+  ]
+}
+
+output "bigquery_table-employment_hours_earnings_series-table_id" {
+  value = google_bigquery_table.employment_hours_earnings_series.table_id
+}
+
+output "bigquery_table-employment_hours_earnings_series-id" {
+  value = google_bigquery_table.employment_hours_earnings_series.id
+}