Merge pull request #1991 from cmu-delphi/release/indicators_v0.3.55_utils_v0.3.24

Release covidcast-indicators 0.3.55

Author: melange396

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.3.54
+current_version = 0.3.55
 commit = True
 message = chore: bump covidcast-indicators to {new_version}
 tag = False

.git-blame-ignore-revs

@@ -0,0 +1,6 @@
+# Format geomap.py
+d4b056e7a4c11982324e9224c9f9f6fd5d5ec65c
+# Format test_geomap.py
+79072dcdec3faca9aaeeea65de83f7fa5c00d53f
+# Sort setup.py dependencies
+6912077acba97e835aff7d0cd3d64309a1a9241d

.github/workflows/backfill-corr-ci.yml

@@ -10,57 +10,37 @@ name: R backfill corrections
 
 on:
   push:
-    branches: [ main, prod ]
+    branches: [main, prod]
   pull_request:
-    types: [ opened, synchronize, reopened, ready_for_review ]
-    branches: [ main, prod ]
+    types: [opened, synchronize, reopened, ready_for_review]
+    branches: [main, prod]
 
 jobs:
   build:
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-latest
     if: github.event.pull_request.draft == false
-    strategy:
-      matrix:
-        r-version: [4.2.1]
     defaults:
       run:
         working-directory: backfill_corrections/delphiBackfillCorrection
 
     steps:
-      - uses: actions/checkout@v2
-      - name: Set up R ${{ matrix.r-version }}
+      - uses: actions/checkout@v4
+
+      - name: Set up R 4.2
         uses: r-lib/actions/setup-r@v2
         with:
-          r-version: ${{ matrix.r-version }}
           use-public-rspm: true
-      - name: Install linux dependencies
-        run: |
-            sudo apt-get install \
-              libcurl4-openssl-dev \
-              libgdal-dev \
-              libudunits2-dev \
-              libglpk-dev \
-              libharfbuzz-dev \
-              libfribidi-dev
-      - name: Get date
-        id: get-date
-        run: |
-          echo "::set-output name=date::$(/bin/date -u "+%Y%m%d")"
-      - name: Cache R packages
-        uses: actions/cache@v2
-        with:
-          path: ${{ env.R_LIBS_USER }}
-          key: ${{ runner.os }}-r-backfillcorr-${{ steps.get-date.outputs.date }}
-          restore-keys: |
-            ${{ runner.os }}-r-backfillcorr-
+          r-version: 4.2
+
       - name: Install and cache dependencies
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         uses: r-lib/actions/setup-r-dependencies@v2
         with:
           extra-packages: any::rcmdcheck
           working-directory: backfill_corrections/delphiBackfillCorrection
-          upgrade: 'TRUE'
+          upgrade: "TRUE"
+
       - name: Check package
         uses: r-lib/actions/check-r-package@v2
         with:

.github/workflows/build-container-images.yml

@@ -2,14 +2,15 @@ name: Build indicator container images and upload to registry
 
 on:
   push:
-    branches: [ main, prod ]
+    branches: [main, prod]
+  workflow_dispatch:
 
 jobs:
   build:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        packages: [ backfill_corrections ]
+        packages: [backfill_corrections]
     steps:
       - name: Checkout code
         uses: actions/checkout@v2

.github/workflows/python-ci.yml

@@ -16,28 +16,42 @@ jobs:
     if: github.event.pull_request.draft == false
     strategy:
       matrix:
-        packages:
-          [
-            _delphi_utils_python,
-            changehc,
-            claims_hosp,
-            doctor_visits,
-            google_symptoms,
-            hhs_hosp,
-            nchs_mortality,
-            nwss_wastewater,
-            quidel_covidtest,
-            sir_complainsalot,
-          ]
+        include:
+          - package: "_delphi_utils_python"
+            dir: "delphi_utils"
+          - package: "changehc"
+            dir: "delphi_changehc"
+          - package: "claims_hosp"
+            dir: "delphi_claims_hosp"
+          - package: "doctor_visits"
+            dir: "delphi_doctor_visits"
+          - package: "google_symptoms"
+            dir: "delphi_google_symptoms"
+          - package: "hhs_hosp"
+            dir: "delphi_hhs"
+          - package: "nchs_mortality"
+            dir: "delphi_nchs_mortality"
+          - package: "nssp"
+            dir: "delphi_nssp"
+          - package: "nwss_wastewater"
+            dir: "delphi_nwss"
+          - package: "quidel_covidtest"
+            dir: "delphi_quidel_covidtest"
+          - package: "sir_complainsalot"
+            dir: "delphi_sir_complainsalot"
     defaults:
       run:
-        working-directory: ${{ matrix.packages }}
+        working-directory: ${{ matrix.package }}
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
       - name: Set up Python 3.8
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v5
         with:
           python-version: 3.8
+          cache: "pip"
+          cache-dependency-path: "setup.py"
       - name: Install testing dependencies
         run: |
           python -m pip install --upgrade pip
@@ -51,3 +65,8 @@ jobs:
       - name: Test
         run: |
           make test
+      - uses: akaihola/[email protected]
+        with:
+          options: "--check --diff --isort --color"
+          src: "${{ matrix.package }}/${{ matrix.dir }}"
+          version: "~=2.1.1"

Jenkinsfile

@@ -10,7 +10,7 @@
    - TODO: #527 Get this list automatically from python-ci.yml at runtime.
  */
 
-def indicator_list = ["backfill_corrections", "changehc", "claims_hosp", "google_symptoms", "hhs_hosp", "nchs_mortality", "quidel_covidtest", "sir_complainsalot", "doctor_visits", "nwss_wastewater"]
+def indicator_list = ["backfill_corrections", "changehc", "claims_hosp", "google_symptoms", "hhs_hosp", "nchs_mortality", "quidel_covidtest", "sir_complainsalot", "doctor_visits", "nwss_wastewater", "nssp"]
 def build_package_main = [:]
 def build_package_prod = [:]
 def deploy_staging = [:]

README.md

@@ -4,7 +4,7 @@
 
 In early April 2020, Delphi developed a uniform data schema for [a new Epidata endpoint focused on COVID-19](https://cmu-delphi.github.io/delphi-epidata/api/covidcast.html). Our intent was to provide signals that would track in real-time and in fine geographic granularity all facets of the COVID-19 pandemic, aiding both nowcasting and forecasting. Delphi's long history in tracking and forecasting influenza made us uniquely situated to provide access to data streams not available anywhere else, including medical claims data, electronic medical records, lab test records, massive public surveys, and internet search trends. We also process commonly-used publicly-available data sources, both for user convenience and to provide data versioning for sources that do not track revisions themselves.
 
-Each data stream arrives in a different format using a different delivery technique, be it sftp, an access-controlled API, or an email attachment. The purpose of each pipeline in this repository is to fetch the raw source data, extract informative aggregate signals, and output those signals---which we call **COVID-19 indicators**---in a common format for upload to the [COVIDcast API](https://cmu-delphi.github.io/delphi-epidata/api/covidcast.html). 
+Each data stream arrives in a different format using a different delivery technique, be it sftp, an access-controlled API, or an email attachment. The purpose of each pipeline in this repository is to fetch the raw source data, extract informative aggregate signals, and output those signals---which we call **COVID-19 indicators**---in a common format for upload to the [COVIDcast API](https://cmu-delphi.github.io/delphi-epidata/api/covidcast.html).
 
 For client access to the API, along with a variety of other utilities, see our [R](https://cmu-delphi.github.io/covidcast/covidcastR/) and [Python](https://cmu-delphi.github.io/covidcast/covidcast-py/html/) packages.
 
@@ -13,18 +13,19 @@ For interactive visualizations (of a subset of the available indicators), see ou
 ## Organization
 
 Utilities:
-* `_delphi_utils_python` - common behaviors
-* `_template_python` & `_template_r` - starting points for new data sources
-* `ansible` & `jenkins` - automated testing and deployment
-* `sir_complainsalot` - a Slack bot to check for missing data
+
+- `_delphi_utils_python` - common behaviors
+- `_template_python` & `_template_r` - starting points for new data sources
+- `ansible` & `jenkins` - automated testing and deployment
+- `sir_complainsalot` - a Slack bot to check for missing data
 
 Indicator pipelines: all remaining directories.
 
-Each indicator pipeline includes its own documentation. 
+Each indicator pipeline includes its own documentation.
 
-* Consult README.md for directions to install, lint, test, and run the pipeline for that indicator. 
-* Consult REVIEW.md for the checklist to use for code reviews. 
-* Consult DETAILS.md (if present) for implementation details, including handling of corner cases.
+- Consult README.md for directions to install, lint, test, and run the pipeline for that indicator.
+- Consult REVIEW.md for the checklist to use for code reviews.
+- Consult DETAILS.md (if present) for implementation details, including handling of corner cases.
 
 ## Development
 
@@ -35,6 +36,28 @@ Each indicator pipeline includes its own documentation.
 3. Add new commits to your branch in response to feedback.
 4. When approved, tag an admin to merge the PR. Let them know if this change should be released immediately, at a set future date, or if it can just go along for the ride whenever the next release happens.
 
+### Linting and Formatting
+
+Each indicator has a `make lint` command to check for linting errors and a `make
+format` command to incrementally format your code (using
+[darker](https://github.com/akaihola/darker)). These are both automated with a
+[Github Action](.github/workflows/python-ci.yml).
+
+If you get the error `ERROR:darker.git:fatal: Not a valid commit name <hash>`,
+then it's likely because your local main branch is not up to date; either you
+need to rebase or merge. Note that `darker` reads from `pyproject.toml` for
+default settings.
+
+If the lines you change are in a file that uses 2 space indentation, `darker`
+will indent the lines around your changes and not the rest, which will likely
+break the code; in that case, you should probably just pass the whole file
+through black. You can do that with the following command (using the same
+virtual environment as above):
+
+```sh
+env/bin/black <file>
+```
+
 ## Release Process
 
 The release process consists of multiple steps which can all be done via the GitHub website:

_delphi_utils_python/.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.3.23
+current_version = 0.3.24
 commit = True
 message = chore: bump delphi_utils to {new_version}
 tag = False

_delphi_utils_python/.pylintrc

@@ -14,9 +14,12 @@ install-ci: venv
 	pip install .
 
 lint:
-	. env/bin/activate; pylint delphi_utils
+	. env/bin/activate; pylint delphi_utils --rcfile=../pyproject.toml
 	. env/bin/activate; pydocstyle delphi_utils
 
+format:
+	. env/bin/activate; darker delphi_utils
+
 test:
 	. env/bin/activate ;\
 	(cd tests && ../env/bin/pytest --cov=delphi_utils --cov-report=term-missing)

_delphi_utils_python/Makefile

@@ -1,4 +1,4 @@
-# Geocoding data processing pipeline
+# Geocoding Data Processing
 
 Authors: Jingjing Tang, James Sharpnack, Dmitry Shemetov
 
@@ -7,42 +7,37 @@ Authors: Jingjing Tang, James Sharpnack, Dmitry Shemetov
 Requires the following source files below.
 
 Run the following to build the crosswalk tables in `covidcast-indicators/_delph_utils_python/delph_utils/data`
-```
+
+```sh
 $ python geo_data_proc.py
 ```
 
-You can see consistency checks and diffs with old sources in ./consistency_checks.ipynb
+Find data consistency checks in `./source-file-sanity-check.ipynb`.
 
 ## Geo Codes
 
 We support the following geocodes.
 
-- The ZIP code and the FIPS code are the most granular geocodes we support.
-  - The [ZIP code](https://en.wikipedia.org/wiki/ZIP_Code) is a US postal code used by the USPS and the [FIPS code](https://en.wikipedia.org/wiki/FIPS_county_code) is an identifier for US counties and other associated territories. The ZIP code is five digit code (with leading zeros). 
-  - The FIPS code is a five digit code (with leading zeros), where the first two digits are a two-digit state code and the last three are a three-digit county code (see this [US Census Bureau page](https://www.census.gov/library/reference/code-lists/ansi.html) for detailed information).
-- The Metropolitan Statistical Area (MSA) code refers to regions around cities (these are sometimes referred to as CBSA codes). More information on these can be found at the [US Census Bureau](https://www.census.gov/programs-surveys/metro-micro/about.html).
-  - We are reserving 10001-10099 for states codes of the form 100XX where XX is the FIPS code for the state (the current smallest CBSA is 10100). In the case that the CBSA codes change then it should be verified that these are not used.
+- The [ZIP code](https://en.wikipedia.org/wiki/ZIP_Code) is a US postal code used by the USPS and the [FIPS code](https://en.wikipedia.org/wiki/FIPS_county_code) is an identifier for US counties and other associated territories. The ZIP code is five digit code (with leading zeros).
+- The FIPS code is a five digit code (with leading zeros), where the first two digits are a two-digit state code and the last three are a three-digit county code (see this [US Census Bureau page](https://www.census.gov/library/reference/code-lists/ansi.html) for detailed information).
+- The Metropolitan Statistical Area (MSA) code refers to regions around cities (these are sometimes referred to as CBSA codes). More information on these can be found at the [US Census Bureau](https://www.census.gov/programs-surveys/metro-micro/about.html). We rserve 10001-10099 for states codes of the form 100XX where XX is the FIPS code for the state (the current smallest CBSA is 10100). In the case that the CBSA codes change then it should be verified that these are not used.
 - State codes are a series of equivalent identifiers for US state. They include the state name, the state number (state_id), and the state two-letter abbreviation (state_code). The state number is the state FIPS code. See [here](https://en.wikipedia.org/wiki/List_of_U.S._state_and_territory_abbreviations) for more.
 - The Hospital Referral Region (HRR) and the Hospital Service Area (HSA). More information [here](https://www.dartmouthatlas.org/covid-19/hrr-mapping/).
-FIPS codes depart in some special cases, so we produce manual changes listed below.
 
-## Source files
+## Source Files
 
 The source files are requested from a government URL when `geo_data_proc.py` is run (see the top of said script for the URLs). Below we describe the locations to find updated versions of the source files, if they are ever needed.
 
 - ZIP -> FIPS (county) population tables available from [US Census](https://www.census.gov/geographies/reference-files/time-series/geo/relationship-files.html#par_textimage_674173622). This file contains the population of the intersections between ZIP and FIPS regions, allowing the creation of a population-weighted transform between the two. As of 4 February 2022, this source did not include population information for 24 ZIPs that appear in our indicators. We have added those values manually using information available from the [zipdatamaps website](www.zipdatamaps.com).
 - ZIP -> HRR -> HSA crosswalk file comes from the 2018 version at the [Dartmouth Atlas Project](https://atlasdata.dartmouth.edu/static/supp_research_data).
 - FIPS -> MSA crosswalk file comes from the September 2018 version of the delineation files at the [US Census Bureau](https://www.census.gov/geographies/reference-files/time-series/demo/metro-micro/delineation-files.html).
-- State Code -> State ID -> State Name comes from the ANSI standard at the [US Census](https://www.census.gov/library/reference/code-lists/ansi.html#par_textimage_3). The first two digits of a FIPS codes should match the state code here.
+- State Code -> State ID -> State Name comes from the ANSI standard at the [US Census](https://www.census.gov/library/reference/code-lists/ansi.html#par_textimage_3).
 
-
-## Derived files
+## Derived Files
 
 The rest of the crosswalk tables are derived from the mappings above. We provide crosswalk functions from granular to coarser codes, but not the other way around. This is because there is no information gained when crosswalking from coarse to granular.
 
-
-
-## Deprecated source files
+## Deprecated Source Files
 
 - ZIP to FIPS to HRR to states: `02_20_uszips.csv` comes from a version of the table [here](https://simplemaps.com/data/us-zips) modified by Jingjing to include population weights.
   - The `02_20_uszips.csv` file is based on the newest consensus data including 5-digit zipcode, fips code, county name, state, population, HRR, HSA (I downloaded the original file from [here](https://simplemaps.com/data/us-zips). This file matches best to the most recent (2020) situation in terms of the population. But there still exist some matching problems. I manually checked and corrected those lines (~20) with [zip-codes](https://www.zip-codes.com/zip-code/58439/zip-code-58439.asp). The mapping from 5-digit zipcode to HRR is based on the file in 2017 version downloaded from [here](https://atlasdata.dartmouth.edu/static/supp_research_data).
@@ -51,7 +46,3 @@ The rest of the crosswalk tables are derived from the mappings above. We provide
 - CBSA -> FIPS crosswalk from [here](https://data.nber.org/data/cbsa-fips-county-crosswalk.html) (the file is `cbsatocountycrosswalk.csv`).
 - MSA tables from March 2020 [here](https://www.census.gov/geographies/reference-files/time-series/demo/metro-micro/delineation-files.html). This file seems to differ in a few fips codes from the source for the 02_20_uszip file which Jingjing constructed. There are at least 10 additional fips in 03_20_msa that are not in the uszip file, and one of the msa codes seems to be incorrect: 49020 (a google search confirms that it is incorrect in uszip and correct in the census data).
 - MSA tables from 2019 [here](https://apps.bea.gov/regional/docs/msalist.cfm)
-
-## Notes
-
-- The NAs in the coding currently zero-fills.