Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: Onboard Iowa Liquor Sales dataset #193

Merged
merged 8 commits into from Oct 13, 2021
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
@@ -0,0 +1,38 @@
# 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 gcr.io/google.com/cloudsdktool/cloud-sdk:slim
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Extra commented line

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"]
@@ -0,0 +1,193 @@
# 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 logging
import os
import pathlib
import subprocess
from datetime import datetime

import pandas as pd
import requests
from google.cloud import storage


def main(
source_url: str,
source_file: pathlib.Path,
target_file: pathlib.Path,
chunksize: str,
target_gcs_bucket: str,
target_gcs_path: str,
) -> None:
logging.info(" Sales pipeline process started")
logging.info("Creating 'files' folder")
pathlib.Path("./files").mkdir(parents=True, exist_ok=True)

logging.info(f"Downloading file {source_url}")
download_file(source_url, source_file)

chunksz = int(chunksize)
logging.info(f"Reading csv file {source_url}")
with pd.read_csv(
source_file,
engine="python",
encoding="utf-8",
quotechar='"',
chunksize=chunksz,
) as reader:
for chunk_number, chunk in enumerate(reader):
logging.info(f"Processing batch {chunk_number}")
target_file_batch = str(target_file).replace(
".csv", "-" + str(chunk_number) + ".csv"
)
df = pd.DataFrame()
df = pd.concat([df, chunk])
processChunk(df, target_file_batch)

logging.info(f"Appending batch {chunk_number} to {target_file}")
if chunk_number == 0:
subprocess.run(["cp", target_file_batch, target_file])
else:
subprocess.check_call(f"sed -i '1d' {target_file_batch}", shell=True)
subprocess.check_call(
f"cat {target_file_batch} >> {target_file}", shell=True
)
subprocess.run(["rm", target_file_batch])

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)


def processChunk(df: pd.DataFrame, target_file_batch: str) -> None:

logging.info("Renaming Headers")
rename_headers(df)

logging.info("Convert Date Format")
df["date"] = df["date"].apply(convert_dt_format)

logging.info("Reordering headers..")
df = df[
[
"invoice_and_item_number",
"date",
"store_number",
"store_name",
"address",
"city",
"zip_code",
"store_location",
"county_number",
"county",
"category",
"category_name",
"vendor_number",
"vendor_name",
"item_number",
"item_description",
"pack",
"bottle_volume_ml",
"state_bottle_cost",
"state_bottle_retail",
"bottles_sold",
"sale_dollars",
"volume_sold_liters",
"volume_sold_gallons",
]
]

df["county_number"] = df["county_number"].astype("Int64")

logging.info(f"Saving to output file.. {target_file_batch}")
try:
save_to_new_file(df, file_path=str(target_file_batch))
except Exception as e:
logging.error(f"Error saving output file: {e}.")
logging.info("..Done!")


def rename_headers(df: pd.DataFrame) -> None:
header_names = {
"Invoice/Item Number": "invoice_and_item_number",
"Date": "date",
"Store Number": "store_number",
"Store Name": "store_name",
"Address": "address",
"City": "city",
"Zip Code": "zip_code",
"Store Location": "store_location",
"County Number": "county_number",
"County": "county",
"Category": "category",
"Category Name": "category_name",
"Vendor Number": "vendor_number",
"Vendor Name": "vendor_name",
"Item Number": "item_number",
"Item Description": "item_description",
"Pack": "pack",
"Bottle Volume (ml)": "bottle_volume_ml",
"State Bottle Cost": "state_bottle_cost",
"State Bottle Retail": "state_bottle_retail",
"Bottles Sold": "bottles_sold",
"Sale (Dollars)": "sale_dollars",
"Volume Sold (Liters)": "volume_sold_liters",
"Volume Sold (Gallons)": "volume_sold_gallons",
}
df = df.rename(columns=header_names, inplace=True)


def convert_dt_format(dt_str: str) -> str:
if dt_str is None or len(dt_str) == 0:
return dt_str
else:
if len(dt_str) == 10:
return datetime.strptime(dt_str, "%m/%d/%Y").strftime("%Y-%m-%d")


def save_to_new_file(df, file_path) -> 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(),
chunksize=os.environ["CHUNKSIZE"],
target_gcs_bucket=os.environ["TARGET_GCS_BUCKET"],
target_gcs_path=os.environ["TARGET_GCS_PATH"],
)
@@ -0,0 +1,3 @@
requests
pandas
google-cloud-storage
26 changes: 26 additions & 0 deletions datasets/iowa_liquor_sales/_terraform/iowa_liquor_sales_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" "iowa_liquor_sales" {
dataset_id = "iowa_liquor_sales"
project = var.project_id
description = "This dataset contains every wholesale purchase of liquor in the State of Iowa by retailers for sale to individuals since January 1, 2012. The State of Iowa controls the wholesale distribution of liquor intended for retail sale (off-premises consumption), which means this dataset offers a complete view of retail liquor consumption in the entire state. The dataset contains every wholesale order of liquor by all grocery stores, liquor stores, convenience stores, etc., with details about the store and location, the exact liquor brand and size, and the number of bottles ordered.\nYou can find more details, as well as sample queries, in the GCP Marketplace here: https://console.cloud.google.com/marketplace/details/iowa-department-of-commerce/iowa-liquor-sales"
}

output "bigquery_dataset-iowa_liquor_sales-dataset_id" {
value = google_bigquery_dataset.iowa_liquor_sales.dataset_id
}
28 changes: 28 additions & 0 deletions datasets/iowa_liquor_sales/_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
}
39 changes: 39 additions & 0 deletions datasets/iowa_liquor_sales/_terraform/sales_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" "sales" {
project = var.project_id
dataset_id = "iowa_liquor_sales"
table_id = "sales"

description = "Sales Dataset"




depends_on = [
google_bigquery_dataset.iowa_liquor_sales
]
}

output "bigquery_table-sales-table_id" {
value = google_bigquery_table.sales.table_id
}

output "bigquery_table-sales-id" {
value = google_bigquery_table.sales.id
}
23 changes: 23 additions & 0 deletions datasets/iowa_liquor_sales/_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" {}

34 changes: 34 additions & 0 deletions datasets/iowa_liquor_sales/dataset.yaml
@@ -0,0 +1,34 @@
# 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: iowa_liquor_sales

friendly_name: iowa_liquor

description: "This dataset contains every wholesale purchase of liquor in the State of Iowa by retailers for sale to individuals since January 1, 2012."

dataset_sources: ~

terms_of_use: ~


resources:

- type: bigquery_dataset
dataset_id: iowa_liquor_sales
description: |-
"This dataset contains every wholesale purchase of liquor in the State of Iowa by retailers for sale to individuals since January 1, 2012. The State of Iowa controls the wholesale distribution of liquor intended for retail sale (off-premises consumption), which means this dataset offers a complete view of retail liquor consumption in the entire state. The dataset contains every wholesale order of liquor by all grocery stores, liquor stores, convenience stores, etc., with details about the store and location, the exact liquor brand and size, and the number of bottles ordered.
You can find more details, as well as sample queries, in the GCP Marketplace here: https://console.cloud.google.com/marketplace/details/iowa-department-of-commerce/iowa-liquor-sales"