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 San Francisco Bikeshare Stations #191
Merged
adlersantos
merged 4 commits into
GoogleCloudPlatform:main
from
nlarge-google:san-francisco-bikeshare-stations
Oct 13, 2021
Merged
Changes from all commits
Commits
Show all changes
4 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
There are no files selected for viewing
38 changes: 38 additions & 0 deletions
38
datasets/san_francisco_bikeshare_stations/_images/run_csv_transform_kub/Dockerfile
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -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 | ||
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"] |
215 changes: 215 additions & 0 deletions
215
datasets/san_francisco_bikeshare_stations/_images/run_csv_transform_kub/csv_transform.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,215 @@ | ||
# 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 json | ||
import logging | ||
import os | ||
import pathlib | ||
|
||
import pandas as pd | ||
import requests | ||
from google.cloud import storage | ||
|
||
|
||
def main( | ||
source_url_json: str, | ||
source_file: pathlib.Path, | ||
target_file: pathlib.Path, | ||
chunksize: str, | ||
target_gcs_bucket: str, | ||
target_gcs_path: str, | ||
) -> None: | ||
|
||
logging.info("San Francisco Bikeshare Stations process started") | ||
|
||
pathlib.Path("./files").mkdir(parents=True, exist_ok=True) | ||
source_file_stations_json = str(source_file).replace(".csv", "") + "_stations.json" | ||
download_file_json(source_url_json, source_file_stations_json, source_file) | ||
|
||
chunksz = int(chunksize) | ||
|
||
logging.info(f"Opening batch file {source_file}") | ||
with pd.read_csv( | ||
source_file, # path to main source file to load in batches | ||
engine="python", | ||
encoding="utf-8", | ||
quotechar='"', # string separator, typically double-quotes | ||
chunksize=chunksz, # size of batch data, in no. of records | ||
sep=",", # data column separator, typically "," | ||
) as reader: | ||
for chunk_number, chunk in enumerate(reader): | ||
target_file_batch = str(target_file).replace( | ||
".csv", "-" + str(chunk_number) + ".csv" | ||
) | ||
df = pd.DataFrame() | ||
df = pd.concat([df, chunk]) | ||
process_chunk(df, target_file_batch, target_file, (not chunk_number == 0)) | ||
|
||
upload_file_to_gcs(target_file, target_gcs_bucket, target_gcs_path) | ||
|
||
logging.info("San Francisco Bikeshare Stations process completed") | ||
|
||
|
||
def process_chunk( | ||
df: pd.DataFrame, target_file_batch: str, target_file: str, skip_header: bool | ||
) -> None: | ||
df = rename_headers(df) | ||
df = filter_empty_data(df) | ||
df = generate_location(df) | ||
df = resolve_datatypes(df) | ||
df = reorder_headers(df) | ||
save_to_new_file(df, file_path=str(target_file_batch)) | ||
append_batch_file(target_file_batch, target_file, skip_header, not (skip_header)) | ||
|
||
|
||
def rename_headers(df: pd.DataFrame) -> None: | ||
logging.info("Renaming Headers") | ||
header_names = { | ||
"data.stations.station_id": "station_id", | ||
"data.stations.name": "name", | ||
"data.stations.short_name": "short_name", | ||
"data.stations.lat": "lat", | ||
"data.stations.lon": "lon", | ||
"data.stations.region_id": "region_id", | ||
"data.stations.rental_methods": "rental_methods", | ||
"data.stations.capacity": "capacity", | ||
"data.stations.eightd_has_key_dispenser": "eightd_has_key_dispenser", | ||
"data.stations.has_kiosk": "has_kiosk", | ||
"data.stations.external_id": "external_id", | ||
} | ||
|
||
df.rename(columns=header_names) | ||
|
||
return df | ||
|
||
|
||
def filter_empty_data(df: pd.DataFrame) -> pd.DataFrame: | ||
logging.info("Filter rows with empty key data") | ||
df = df[df["station_id"] != ""] | ||
df = df[df["name"] != ""] | ||
df = df[df["lat"] != ""] | ||
df = df[df["lon"] != ""] | ||
|
||
return df | ||
|
||
|
||
def generate_location(df: pd.DataFrame) -> pd.DataFrame: | ||
logging.info("Generating location data") | ||
df["station_geom"] = ( | ||
"POINT(" | ||
+ df["lon"][:].astype("string") | ||
+ " " | ||
+ df["lat"][:].astype("string") | ||
+ ")" | ||
) | ||
|
||
return df | ||
|
||
|
||
def resolve_datatypes(df: pd.DataFrame) -> pd.DataFrame: | ||
logging.info("Resolving datatypes") | ||
df["region_id"] = df["region_id"].astype("Int64") | ||
|
||
return df | ||
|
||
|
||
def reorder_headers(df: pd.DataFrame) -> pd.DataFrame: | ||
logging.info("Reordering Headers") | ||
df = df[ | ||
[ | ||
"station_id", | ||
"name", | ||
"short_name", | ||
"lat", | ||
"lon", | ||
"region_id", | ||
"rental_methods", | ||
"capacity", | ||
"external_id", | ||
"eightd_has_key_dispenser", | ||
"has_kiosk", | ||
"station_geom", | ||
] | ||
] | ||
|
||
return df | ||
|
||
|
||
def append_batch_file( | ||
batch_file_path: str, target_file_path: str, skip_header: bool, truncate_file: bool | ||
) -> None: | ||
data_file = open(batch_file_path, "r") | ||
if truncate_file: | ||
target_file = open(target_file_path, "w+").close() | ||
target_file = open(target_file_path, "a+") | ||
if skip_header: | ||
logging.info( | ||
f"Appending batch file {batch_file_path} to {target_file_path} with skip header" | ||
) | ||
next(data_file) | ||
else: | ||
logging.info(f"Appending batch file {batch_file_path} to {target_file_path}") | ||
target_file.write(data_file.read()) | ||
data_file.close() | ||
target_file.close() | ||
if os.path.exists(batch_file_path): | ||
os.remove(batch_file_path) | ||
|
||
|
||
def save_to_new_file(df, file_path) -> None: | ||
df.to_csv(file_path, index=False) | ||
|
||
|
||
def download_file_json( | ||
source_url_json: str, source_file_json: str, source_file_csv: str | ||
) -> None: | ||
|
||
# this function extracts the json from a source url and creates | ||
# a csv file from that data to be used as an input file | ||
logging.info(f"Downloading stations json file {source_url_json}") | ||
|
||
# download json url into object r | ||
r = requests.get(source_url_json + ".json", stream=True) | ||
|
||
# push object r (json) into json file | ||
with open(source_file_json, "wb") as f: | ||
for chunk in r: | ||
f.write(chunk) | ||
|
||
f = open( | ||
source_file_json.strip(), | ||
) | ||
json_data = json.load(f) | ||
df = pd.DataFrame(json_data["data"]["stations"]) | ||
df.to_csv(source_file_csv, index=False) | ||
|
||
|
||
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=os.environ["SOURCE_URL_JSON"], | ||
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"], | ||
) |
3 changes: 3 additions & 0 deletions
3
datasets/san_francisco_bikeshare_stations/_images/run_csv_transform_kub/requirements.txt
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,3 @@ | ||
requests | ||
pandas | ||
google-cloud-storage |
39 changes: 39 additions & 0 deletions
39
datasets/san_francisco_bikeshare_stations/_terraform/bikeshare_stations_pipeline.tf
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -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" "bikeshare_stations" { | ||
project = var.project_id | ||
dataset_id = "san_francisco_bikeshare_stations" | ||
table_id = "bikeshare_stations" | ||
|
||
description = "san francisco bikeshare stations" | ||
|
||
|
||
|
||
|
||
depends_on = [ | ||
google_bigquery_dataset.san_francisco_bikeshare_stations | ||
] | ||
} | ||
|
||
output "bigquery_table-bikeshare_stations-table_id" { | ||
value = google_bigquery_table.bikeshare_stations.table_id | ||
} | ||
|
||
output "bigquery_table-bikeshare_stations-id" { | ||
value = google_bigquery_table.bikeshare_stations.id | ||
} |
28 changes: 28 additions & 0 deletions
28
datasets/san_francisco_bikeshare_stations/_terraform/provider.tf
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -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 | ||
} |
26 changes: 26 additions & 0 deletions
26
...s/san_francisco_bikeshare_stations/_terraform/san_francisco_bikeshare_stations_dataset.tf
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -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" "san_francisco_bikeshare_stations" { | ||
dataset_id = "san_francisco_bikeshare_stations" | ||
project = var.project_id | ||
description = "san_francisco_bikeshare_stations" | ||
} | ||
|
||
output "bigquery_dataset-san_francisco_bikeshare_stations-dataset_id" { | ||
value = google_bigquery_dataset.san_francisco_bikeshare_stations.dataset_id | ||
} |
23 changes: 23 additions & 0 deletions
23
datasets/san_francisco_bikeshare_stations/_terraform/variables.tf
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -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" {} | ||
|
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Extra commented line