feat: Onboard CFPB Complaints dataset (#225)

GoogleCloudPlatform · Jan 12, 2022 · 9051773 · 9051773
1 parent 861d0e6
commit 9051773
Show file tree

Hide file tree

Showing 10 changed files with 665 additions and 0 deletions.
diff --git a/datasets/cfpb_complaints/_images/run_csv_transform_kub/Dockerfile b/datasets/cfpb_complaints/_images/run_csv_transform_kub/Dockerfile
@@ -0,0 +1,37 @@
+# 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
+
+# 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"]
diff --git a/datasets/cfpb_complaints/_images/run_csv_transform_kub/csv_transform.py b/datasets/cfpb_complaints/_images/run_csv_transform_kub/csv_transform.py
@@ -0,0 +1,128 @@
+# 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 typing
+
+import numpy as np
+import pandas as pd
+import requests
+from google.cloud import storage
+
+
+def main(
+ source_url: str,
+ source_file: pathlib.Path,
+ target_file: pathlib.Path,
+ target_gcs_bucket: str,
+ target_gcs_path: str,
+ headers: typing.List[str],
+ rename_mappings: dict,
+ pipeline_name: str,
+) -> None:
+
+ logging.info(
+ f"CFPB Complaints {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(f"Downloading file from {source_url}...")
+ download_file(source_url, source_file)
+
+ logging.info(f"Opening file {source_file}...")
+ df = pd.read_csv(str(source_file), compression="zip")
+
+ logging.info(f"Transforming {source_file}... ")
+
+ logging.info("Transform: Rename columns... ")
+ rename_headers(df, rename_mappings)
+
+ logging.info("Transform: Replacing values... ")
+ df = df.replace(
+ to_replace={
+ "timely_response": {
+ "yes": "true",
+ "no": "false",
+ },
+ "consumer_disputed": {"yes": "true", "no": "false", np.nan: ""},
+ }
+ )
+
+ 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(
+ 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"CFPB Complaints {pipeline_name} process completed at "
+ + str(datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S"))
+ )
+
+
+def rename_headers(df: pd.DataFrame, rename_mappings: dict) -> None:
+ df.rename(columns=rename_mappings, inplace=True)
+
+
+def save_to_new_file(df: pd.DataFrame, file_path: str) -> None:
+ df.to_csv(file_path, index=False)
+
+
+def download_file(source_url: str, source_file: pathlib.Path) -> None:
+ logging.info(f"Downloading {source_url} into {source_file}")
+ r = requests.get(source_url, stream=True)
+ if r.status_code == 200:
+ with open(source_file, "wb") as f:
+ for chunk in r:
+ f.write(chunk)
+ else:
+ logging.error(f"Couldn't download {source_url}: {r.text}")
+
+
+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=os.environ["SOURCE_URL"],
+ source_file=pathlib.Path(os.environ["SOURCE_FILE"]).expanduser(),
+ 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"]),
+ rename_mappings=json.loads(os.environ["RENAME_MAPPINGS"]),
+ pipeline_name=os.environ["PIPELINE_NAME"],
+ )
diff --git a/datasets/cfpb_complaints/_images/run_csv_transform_kub/requirements.txt b/datasets/cfpb_complaints/_images/run_csv_transform_kub/requirements.txt
@@ -0,0 +1,4 @@
+google-cloud-storage
+numpy
+pandas
+requests
diff --git a/datasets/cfpb_complaints/_terraform/cfpb_complaints_dataset.tf b/datasets/cfpb_complaints/_terraform/cfpb_complaints_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" "cfpb_complaints" {
+ dataset_id = "cfpb_complaints"
+ project = var.project_id
+ description = "CFPB Complaints dataset"
+}
+
+output "bigquery_dataset-cfpb_complaints-dataset_id" {
+ value = google_bigquery_dataset.cfpb_complaints.dataset_id
+}
diff --git a/datasets/cfpb_complaints/_terraform/complaint_database_pipeline.tf b/datasets/cfpb_complaints/_terraform/complaint_database_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" "cfpb_complaints_complaint_database" {
+ project = var.project_id
+ dataset_id = "cfpb_complaints"
+ table_id = "complaint_database"
+
+ description = "CFPB Complain table"
+
+
+
+
+ depends_on = [
+ google_bigquery_dataset.cfpb_complaints
+ ]
+}
+
+output "bigquery_table-cfpb_complaints_complaint_database-table_id" {
+ value = google_bigquery_table.cfpb_complaints_complaint_database.table_id
+}
+
+output "bigquery_table-cfpb_complaints_complaint_database-id" {
+ value = google_bigquery_table.cfpb_complaints_complaint_database.id
+}
diff --git a/datasets/cfpb_complaints/_terraform/provider.tf b/datasets/cfpb_complaints/_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/cfpb_complaints/_terraform/variables.tf b/datasets/cfpb_complaints/_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" {}
+