-
Notifications
You must be signed in to change notification settings - Fork 0
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
Migration for new data package format #122
Merged
Merged
Changes from all commits
Commits
Show all changes
3 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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 +1,171 @@ | ||
| import argparse | ||
| import enum | ||
| import io | ||
| import json | ||
| import os | ||
|
|
||
| import awswrangler | ||
| import boto3 | ||
| import pandas | ||
| from rich import progress | ||
|
|
||
|
|
||
| class JsonFilename(enum.Enum): | ||
| """stores names of expected kinds of persisted S3 JSON files""" | ||
|
|
||
| COLUMN_TYPES = "column_types" | ||
| TRANSACTIONS = "transactions" | ||
| DATA_PACKAGES = "data_packages" | ||
| STUDY_PERIODS = "study_periods" | ||
|
|
||
|
|
||
| class BucketPath(enum.Enum): | ||
| """stores root level buckets for managing data processing state""" | ||
|
|
||
| ADMIN = "admin" | ||
| AGGREGATE = "aggregates" | ||
| ARCHIVE = "archive" | ||
| CACHE = "cache" | ||
| CSVAGGREGATE = "csv_aggregates" | ||
| ERROR = "error" | ||
| LAST_VALID = "last_valid" | ||
| LATEST = "latest" | ||
| META = "metadata" | ||
| STUDY_META = "study_metadata" | ||
| UPLOAD = "site_upload" | ||
|
|
||
|
|
||
| def get_csv_column_datatypes(dtypes): | ||
| """helper for generating column type for dashboard API""" | ||
| column_dict = {} | ||
| for column in dtypes.index: | ||
| if column.endswith("year"): | ||
| column_dict[column] = "year" | ||
| elif column.endswith("month"): | ||
| column_dict[column] = "month" | ||
| elif column.endswith("week"): | ||
| column_dict[column] = "week" | ||
| elif column.endswith("day") or str(dtypes[column]) == "datetime64": | ||
| column_dict[column] = "day" | ||
| elif "cnt" in column or str(dtypes[column]) in ( | ||
| "Int8", | ||
| "Int16", | ||
| "Int32", | ||
| "Int64", | ||
| "UInt8", | ||
| "UInt16", | ||
| "UInt32", | ||
| "UInt64", | ||
| ): | ||
| column_dict[column] = "integer" | ||
| elif str(dtypes[column]) in ("Float32", "Float64"): | ||
| column_dict[column] = "float" | ||
| elif str(dtypes[column]) == "boolean": | ||
| column_dict[column] = "float" | ||
| else: | ||
| column_dict[column] = "string" | ||
| return column_dict | ||
|
|
||
|
|
||
| def _put_s3_data(key: str, bucket_name: str, client, data: dict) -> None: | ||
| """Convenience class for writing a dict to S3""" | ||
| b_data = io.BytesIO(json.dumps(data).encode()) | ||
| client.upload_fileobj(Bucket=bucket_name, Key=key, Fileobj=b_data) | ||
|
|
||
|
|
||
| def update_column_type_metadata(bucket: str): | ||
| """creates a new metadata dict for column types. | ||
|
|
||
| By design, this will replaces an existing column type dict if one already exists. | ||
| """ | ||
| client = boto3.client("s3") | ||
| res = client.list_objects_v2(Bucket=bucket, Prefix="aggregates/") | ||
| contents = res["Contents"] | ||
| output = {} | ||
| for resource in progress.track(contents): | ||
| dirs = resource["Key"].split("/") | ||
| study = dirs[1] | ||
| subscription = dirs[2].split("__")[1] | ||
| version = dirs[3] | ||
| bytes_buffer = io.BytesIO() | ||
| client.download_fileobj(Bucket=bucket, Key=resource["Key"], Fileobj=bytes_buffer) | ||
| df = pandas.read_parquet(bytes_buffer) | ||
| type_dict = get_csv_column_datatypes(df.dtypes) | ||
| output.setdefault(study, {}) | ||
| output[study].setdefault(subscription, {}) | ||
| output[study][subscription].setdefault(version, {}) | ||
| output[study][subscription][version]["column_types_format_version"] = 2 | ||
| output[study][subscription][version]["columns"] = type_dict | ||
| output[study][subscription][version]["last_data_update"] = ( | ||
| resource["LastModified"].now().isoformat() | ||
| ) | ||
| output[study][subscription][version]["s3_path"] = resource["Key"][:-8] + ".csv" | ||
| output[study][subscription][version]["total"] = int(df["cnt"][0]) | ||
| _put_s3_data("metadata/column_types.json", bucket, client, output) | ||
|
|
||
|
|
||
| def get_s3_json_as_dict(bucket, key: str): | ||
| """reads a json object as dict (typically metadata in this case)""" | ||
| s3_client = boto3.client("s3") | ||
| bytes_buffer = io.BytesIO() | ||
| print(bucket) | ||
| print(key) | ||
| s3_client.download_fileobj( | ||
| Bucket=bucket, | ||
| Key=key, | ||
| Fileobj=bytes_buffer, | ||
| ) | ||
| return json.loads(bytes_buffer.getvalue().decode()) | ||
|
|
||
|
|
||
| def cache_api_data(s3_bucket_name: str, db: str) -> None: | ||
| s3_client = boto3.client("s3") | ||
| df = awswrangler.athena.read_sql_query( | ||
| ( | ||
| f"SELECT table_name FROM information_schema.tables " # noqa: S608 | ||
| f"WHERE table_schema = '{db}'" # nosec | ||
| ), | ||
| database=db, | ||
| s3_output=f"s3://{s3_bucket_name}/awswrangler", | ||
| workgroup=os.environ.get("WORKGROUP_NAME"), | ||
| ) | ||
| data_packages = df[df["table_name"].str.contains("__")].iloc[:, 0] | ||
| column_types = get_s3_json_as_dict( | ||
| s3_bucket_name, | ||
| f"{BucketPath.META.value}/{JsonFilename.COLUMN_TYPES.value}.json", | ||
| ) | ||
| dp_details = [] | ||
| for dp in list(data_packages): | ||
| dp_detail = { | ||
| "study": dp.split("__", 1)[0], | ||
| "name": dp.split("__", 1)[1], | ||
| } | ||
| try: | ||
| versions = column_types[dp_detail["study"]][dp_detail["name"]] | ||
| for version in versions: | ||
| dp_details.append( | ||
| { | ||
| **dp_detail, | ||
| **versions[version], | ||
| "version": version, | ||
| "id": dp + "__" + version, | ||
| } | ||
| ) | ||
| except KeyError: | ||
| continue | ||
| s3_client.put_object( | ||
| Bucket=s3_bucket_name, | ||
| Key=f"{BucketPath.CACHE.value}/{JsonFilename.DATA_PACKAGES.value}.json", | ||
| Body=json.dumps(dp_details), | ||
| ) | ||
|
|
||
|
|
||
| if __name__ == "__main__": | ||
| parser = argparse.ArgumentParser( | ||
| description="""Creates data package metadata for existing aggregates. """ | ||
| ) | ||
| parser.add_argument("-b", "--bucket", help="bucket name") | ||
| parser.add_argument("-d", "--db", help="database name") | ||
| args = parser.parse_args() | ||
| update_column_type_metadata(args.bucket) | ||
| cache_api_data(args.bucket, args.db) |
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
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 +1,35 @@ | ||
| """Pandas functions used across different functions""" | ||
|
|
||
| import pandas | ||
|
|
||
|
|
||
| def get_column_datatypes(dtypes: pandas.DataFrame): | ||
| """helper for generating column type for dashboard API""" | ||
| column_dict = {} | ||
| for column in dtypes.index: | ||
| if column.endswith("year"): | ||
| column_dict[column] = "year" | ||
| elif column.endswith("month"): | ||
| column_dict[column] = "month" | ||
| elif column.endswith("week"): | ||
| column_dict[column] = "week" | ||
| elif column.endswith("day") or str(dtypes[column]) == "datetime64": | ||
| column_dict[column] = "day" | ||
| elif column.startswith("cnt") or str(dtypes[column]) in ( | ||
| "Int8", | ||
| "Int16", | ||
| "Int32", | ||
| "Int64", | ||
| "UInt8", | ||
| "UInt16", | ||
| "UInt32", | ||
| "UInt64", | ||
| ): | ||
| column_dict[column] = "integer" | ||
| elif str(dtypes[column]) in ("Float32", "Float64"): | ||
| column_dict[column] = "float" | ||
| elif str(dtypes[column]) == "boolean": | ||
| column_dict[column] = "boolean" | ||
| else: | ||
| column_dict[column] = "string" | ||
| return column_dict |
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
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
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
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
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.
Can you explain to a n00b what implications this has?
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.
At :some: point - it might be useful for a downstream consumer to realize the format has changed. Right now, it's primarily documentation.
This version change does mean that insight needs to be updated to expect a different kind of data back.