mirror of
https://github.com/DOI-DO/j40-cejst-2.git
synced 2025-02-23 18:14:19 -08:00
5504528fdf
* Adds flake8, pylint, liccheck, flake8 to dependencies for data-pipeline * Sets up and runs black autoformatting * Adds flake8 to tox linting * Fixes flake8 error F541 f string missing placeholders * Fixes flake8 E501 line too long * Fixes flake8 F401 imported but not used * Adds pylint to tox and disables the following pylint errors: - C0114: module docstrings - R0201: method could have been a function - R0903: too few public methods - C0103: name case styling - W0511: fix me - W1203: f-string interpolation in logging * Adds utils.py to tox.ini linting, runs black on utils.py * Fixes import related pylint errors: C0411 and C0412 * Fixes or ignores remaining pylint errors (for discussion later) * Adds safety and liccheck to tox.ini
60 lines
2 KiB
Python
60 lines
2 KiB
Python
from pathlib import Path
|
|
|
|
from config import settings
|
|
from utils import unzip_file_from_url, remove_all_from_dir
|
|
|
|
|
|
class ExtractTransformLoad:
|
|
"""
|
|
A class used to instantiate an ETL object to retrieve and process data from
|
|
datasets.
|
|
|
|
Attributes:
|
|
DATA_PATH (pathlib.Path): Local path where all data will be stored
|
|
TMP_PATH (pathlib.Path): Local path where temporary data will be stored
|
|
GEOID_FIELD_NAME (str): The common column name for a Census Block Group identifier
|
|
GEOID_TRACT_FIELD_NAME (str): The common column name for a Census Tract identifier
|
|
"""
|
|
|
|
DATA_PATH: Path = settings.APP_ROOT / "data"
|
|
TMP_PATH: Path = DATA_PATH / "tmp"
|
|
GEOID_FIELD_NAME: str = "GEOID10"
|
|
GEOID_TRACT_FIELD_NAME: str = "GEOID10_TRACT"
|
|
|
|
def get_yaml_config(self) -> None:
|
|
"""Reads the YAML configuration file for the dataset and stores
|
|
the properies in the instance (upcoming feature)"""
|
|
|
|
pass
|
|
|
|
def check_ttl(self) -> None:
|
|
"""Checks if the ETL process can be run based on a the TLL value on the
|
|
YAML config (upcoming feature)"""
|
|
|
|
pass
|
|
|
|
def extract(self, source_url: str = None, extract_path: Path = None) -> None:
|
|
"""Extract the data from
|
|
a remote source. By default it provides code to get the file from a source url,
|
|
unzips it and stores it on an extract_path."""
|
|
|
|
# this can be accessed via super().extract()
|
|
if source_url and extract_path:
|
|
unzip_file_from_url(source_url, self.TMP_PATH, extract_path)
|
|
|
|
def transform(self) -> None:
|
|
"""Transform the data extracted into a format that can be consumed by the
|
|
score generator"""
|
|
|
|
raise NotImplementedError
|
|
|
|
def load(self) -> None:
|
|
"""Saves the transformed data in the specified local data folder or remote AWS S3
|
|
bucket"""
|
|
|
|
raise NotImplementedError
|
|
|
|
def cleanup(self) -> None:
|
|
"""Clears out any files stored in the TMP folder"""
|
|
|
|
remove_all_from_dir(self.TMP_PATH)
|