Changes to allow local runs

.github/CODEOWNERS

@@ -1 +0,0 @@
-*       @vim-usds @travis-newby @sampowers-usds @mattbowen-usds

.github/workflows/codeql-analysis.yml

@@ -45,7 +45,7 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v1
+      uses: github/codeql-action/init@v2
       with:
         languages: ${{ matrix.language }}
         # If you wish to specify custom queries, you can do so here or in a config file.
@@ -56,7 +56,7 @@ jobs:
     # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
     # If this step fails, then you should remove it and run the build manually (see below)
     - name: Autobuild
-      uses: github/codeql-action/autobuild@v1
+      uses: github/codeql-action/autobuild@v2
 
     # ℹ️ Command-line programs to run using the OS shell.
     # 📚 https://git.io/JvXDl
@@ -70,4 +70,4 @@ jobs:
     #   make release
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v1
+      uses: github/codeql-action/analyze@v2

.github/workflows/data-checks.yml

@@ -16,7 +16,7 @@ jobs:
     strategy:
       matrix:
         # checks all of the versions allowed in pyproject.toml
-        python-version: [3.8, 3.9]
+        python-version: [3.10.15]
     steps:
       # installs Python
       # one execution of the tests per version listed above

data/data-pipeline/data_pipeline/constants.py

@@ -0,0 +1,7 @@
+import logging
+
+LOG_LEVEL = logging.DEBUG
+"""Log level for all loggers."""
+
+NO_SSL_VERIFY = True
+"""Set to true to skip SSL verification when downloading files. Useful for local development."""

data/data-pipeline/data_pipeline/etl/datasource.py

@@ -22,6 +22,7 @@ from pathlib import Path
 from typing import List
 from dataclasses import dataclass
 from abc import ABC, abstractmethod
+from data_pipeline.constants import NO_SSL_VERIFY
 
 from data_pipeline.etl.downloader import Downloader
 from data_pipeline.etl.sources.census_acs.etl_utils import (
@@ -65,7 +66,7 @@ class FileDataSource(DataSource):
         Downloader.download_file_from_url(
             file_url=self.source,
             download_file_name=self.destination,
-            verify=True,
+            verify=not NO_SSL_VERIFY,
         )
 
     def __str__(self):
@@ -85,7 +86,7 @@ class ZIPDataSource(DataSource):
         Downloader.download_zip_file_from_url(
             file_url=self.source,
             unzipped_file_path=self.destination,
-            verify=True,
+            verify=not NO_SSL_VERIFY,
         )
 
     def __str__(self):

data/data-pipeline/data_pipeline/etl/downloader.py

@@ -6,7 +6,9 @@ import shutil
 
 from pathlib import Path
 from data_pipeline.config import settings
+from data_pipeline.utils import get_module_logger
 
+logger = get_module_logger(__name__)
 
 class Downloader:
     """A simple class to encapsulate the download capabilities of the application"""
@@ -34,12 +36,13 @@ class Downloader:
         urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
         download_file_name.parent.mkdir(parents=True, exist_ok=True)
-
+        logger.debug(f"Downloading {file_url}")
         response = requests.get(
             file_url, verify=verify, timeout=settings.REQUESTS_DEFAULT_TIMOUT
         )
         if response.status_code == 200:
             file_contents = response.content
+            logger.debug("Downloaded.")
         else:
             raise Exception(
                 f"HTTP response {response.status_code} from url {file_url}. Info: {response.content}"

data/data-pipeline/data_pipeline/etl/sources/census/etl.py

@@ -215,6 +215,7 @@ class CensusETL(ExtractTransformLoad):
             state_gdf = gpd.read_file(file_name)
             usa_df = usa_df.append(state_gdf)
 
+        logger.debug("Converting to CRS")
         usa_df = usa_df.to_crs(
             "+proj=longlat +ellps=WGS84 +datum=WGS84 +no_defs"
         )

data/data-pipeline/data_pipeline/utils.py

@@ -13,6 +13,7 @@ import requests
 import urllib3
 import yaml
 from data_pipeline.config import settings
+from data_pipeline.constants import LOG_LEVEL
 from data_pipeline.content.schemas.download_schemas import CodebookConfig
 from data_pipeline.content.schemas.download_schemas import CSVConfig
 from data_pipeline.content.schemas.download_schemas import ExcelConfig
@@ -48,7 +49,7 @@ def get_module_logger(module_name: str) -> logging.Logger:
     )
     handler.setFormatter(formatter)
     logger.addHandler(handler)
-    logger.setLevel(logging.INFO)
+    logger.setLevel(LOG_LEVEL)
     logger.propagate = False  # don't send log messages to the parent logger (to avoid duplicate log messages)
     return logger
 

data/data-pipeline/pyproject.toml

@@ -17,7 +17,7 @@ packages = [
 
 [tool.poetry.dependencies]
 CensusData = "^1.13"
-certifi = "^2022.12.07" # explicit callout due to https://pyup.io/v/52365/f17/
+certifi = ">= 2024.07.04" # Due to https://data.safetycli.com/v/72083/f17
 click = "8.0.4"  # pinning for now per https://github.com/psf/black/issues/2964
 dynaconf = "^3.1.4"
 geopandas = "^0.11.0"
@@ -29,19 +29,20 @@ marshmallow-dataclass = "^8.5.3"
 marshmallow-enum = "^1.5.1"
 matplotlib = "^3.4.2"
 numpy = "^1.22.1"
-pandas = "^1.2.5"
+pandas = "~1.4.3"
 pylint = "^2.11.1"
-pillow = "9.3.0"
-python = "^3.8"
+pillow = "9.3.0" # Newer versions break tile generation
+python = "^3.10"
 pypandoc = "^1.6.3"
 PyYAML = "^6.0"
 requests = "^2.25.1"
-tqdm = "4.62.0"
+tqdm = "^4.66.3"
 types-requests = "^2.25.0"
 us = "^2.0.2"
 xlsxwriter = "^2.0.0"
 pydantic = "^1.9.0"
 Rtree = "^1.0.0"
+fiona = "~1.8.21"
 
 [tool.poetry.dev-dependencies]
 black = {version = "^21.6b0", allow-prereleases = true}
@@ -59,7 +60,7 @@ pandas-vet = "^0.2.2"
 pytest-snapshot = "^0.8.1"
 seaborn = "^0.11.2"
 papermill = "^2.3.4"
-jupyterlab = "3.4.4"
+jupyterlab = "^3.6.7"
 
 [build-system]
 build-backend = "poetry.core.masonry.api"

data/data-pipeline/tox.ini

@@ -1,7 +1,7 @@
 [tox]
 # required because we use pyproject.toml
 isolated_build = true
-envlist = py38, py39, lint, checkdeps, pytest
+envlist = py310, lint, checkdeps, pytest
 # only checks python versions installed locally
 skip_missing_interpreters = true
 
@@ -16,7 +16,9 @@ commands = black data_pipeline
 # checks the dependencies for security vulnerabilities and open source licenses
 allowlist_externals = bash
 commands = pip install -U wheel
-           safety check --ignore 51457 --ignore 44715  # known issue: https://github.com/pyupio/safety/issues/364
+           # known issue: https://github.com/pyupio/safety/issues/364
+           # jinja2 false positive for our use: https://data.safetycli.com/v/70612/f17
+           safety check --ignore 51457 --ignore 44715 --ignore 70612
            bash scripts/run-liccheck.sh
 
 [testenv:pytest]