First pass of the CDC Vaccination Indicator

.github/workflows/python-ci.yml

@@ -16,7 +16,7 @@ jobs:
     if: github.event.pull_request.draft == false
     strategy:
       matrix:
-        packages: [_delphi_utils_python, changehc, claims_hosp, combo_cases_and_deaths, covid_act_now, doctor_visits, google_symptoms, hhs_hosp, hhs_facilities, jhu, nchs_mortality, nowcast, quidel, quidel_covidtest, safegraph_patterns, sir_complainsalot, usafacts]
+        packages: [_delphi_utils_python, changehc, claims_hosp, combo_cases_and_deaths, covid_act_now, doctor_visits, google_symptoms, hhs_hosp, hhs_facilities, jhu, nchs_mortality, nowcast, quidel, quidel_covidtest, safegraph_patterns, sir_complainsalot, usafacts, cdc_vaccines]
     defaults:
       run:
         working-directory: ${{ matrix.packages }}

cdc_vaccines/.pylintrc

@@ -0,0 +1,22 @@
+
+[MESSAGES CONTROL]
+
+disable=logging-format-interpolation,
+    too-many-locals,
+    too-many-arguments,
+    # Allow pytest functions to be part of a class.
+    no-self-use,
+    # Allow pytest classes to have one test.
+    too-few-public-methods
+
+[BASIC]
+
+# Allow arbitrarily short-named variables.
+variable-rgx=[a-z_][a-z0-9_]*
+argument-rgx=[a-z_][a-z0-9_]*
+attr-rgx=[a-z_][a-z0-9_]*
+
+[DESIGN]
+
+# Don't complain about pytest "unused" arguments.
+ignored-argument-names=(_.*|run_as_module)

cdc_vaccines/Makefile

@@ -0,0 +1,29 @@
+.PHONY = venv, lint, test, clean
+
+dir = $(shell find ./delphi_* -name __init__.py | grep -o 'delphi_[_[:alnum:]]*')
+
+venv:
+	python3.8 -m venv env
+
+install: venv
+	. env/bin/activate; \
+	pip install wheel ; \
+	pip install -e ../_delphi_utils_python ;\
+	pip install -e .
+
+lint:
+	. env/bin/activate; pylint $(dir)
+	. env/bin/activate; pydocstyle $(dir)
+
+test:
+	. env/bin/activate ;\
+	(cd tests && ../env/bin/pytest --cov=$(dir) --cov-report=term-missing)
+
+clean:
+	rm -rf env
+	rm -f params.json
+
+run: 
+	env/bin/python -m $(dir)
+	env/bin/python -m delphi_utils.validator --dry_run
+	env/bin/python -m delphi_utils.archive

cdc_vaccines/README.md

@@ -0,0 +1,70 @@
+# CDC Vaccinations
+
+This indicator provides the number official vaccinations in the US. We export the county-level 
+daily vaccination rates data as-is, and publishes the result as a COVIDcast signal. 
+We also aggregate the data to the HHS, State, and Nation levels. 
+For detailed information see the files DETAILS.md contained in this directory.
+
+Note that individuals could be vaccinated outside of the US. Additionally, 
+there is no county level data for counties in Texas and Hawaii. There are unknown 
+counties in each state and a row for unknown county and unknown state.
+
+
+## Running the Indicator
+
+The indicator is run by directly executing the Python module contained in this
+directory. The safest way to do this is to create a virtual environment,
+installed the common DELPHI tools, and then install the module and its
+dependencies. To do this, run the following command from this directory:
+
+```
+make install
+```
+
+This command will install the package in editable mode, so you can make changes that
+will automatically propagate to the installed package. 
+
+All of the user-changable parameters are stored in `params.json`. To execute
+the module and produce the output datasets (by default, in `receiving`), run
+the following:
+
+```
+env/bin/python -m delphi_cdc_vaccines
+```
+
+If you want to enter the virtual environment in your shell, 
+you can run `source env/bin/activate`. Run `deactivate` to leave the virtual environment. 
+
+Once you are finished, you can remove the virtual environment and 
+params file with the following:
+
+```
+make clean
+```
+
+## Testing the code
+
+To run static tests of the code style, run the following command:
+
+```
+make lint
+```
+
+Unit tests are also included in the module. To execute these, run the following
+command from this directory:
+
+```
+make test
+```
+
+To run individual tests, run the following:
+
+```
+(cd tests && ../env/bin/pytest test_run.py --cov=delphi_ --cov-report=term-missing)
+```
+
+The output will show the number of unit tests that passed and failed, along
+with the percentage of code covered by the tests. 
+
+None of the linting or unit tests should fail, and the code lines that are not covered by unit tests should be small and
+should not include critical sub-routines. 

cdc_vaccines/REVIEW.md

@@ -0,0 +1,38 @@
+## Code Review (Python)
+
+A code review of this module should include a careful look at the code and the
+output. To assist in the process, but certainly not in replace of it, please
+check the following items.
+
+**Documentation**
+
+- [ ] the README.md file template is filled out and currently accurate; it is
+possible to load and test the code using only the instructions given
+- [ ] minimal docstrings (one line describing what the function does) are
+included for all functions; full docstrings describing the inputs and expected
+outputs should be given for non-trivial functions
+
+**Structure**
+
+- [ ] code should pass lint checks (`make lint`)
+- [ ] any required metadata files are checked into the repository and placed
+within the directory `static`
+- [ ] any intermediate files that are created and stored by the module should
+be placed in the directory `cache`
+- [ ] final expected output files to be uploaded to the API are placed in the
+`receiving` directory; output files should not be committed to the respository
+- [ ] all options and API keys are passed through the file `params.json`
+- [ ] template parameter file (`params.json.template`) is checked into the
+code; no personal (i.e., usernames) or private (i.e., API keys) information is
+included in this template file
+
+**Testing**
+
+- [ ] module can be installed in a new virtual environment (`make install`)
+- [ ] reasonably high level of unit test coverage covering all of the main logic
+of the code (e.g., missing coverage for raised errors that do not currently seem
+possible to reach are okay; missing coverage for options that will be needed are
+not)
+- [ ] all unit tests run without errors (`make test`)
+- [ ] indicator directory has been added to GitHub CI
+(`covidcast-indicators/.github/workflows/python-ci.yml`)

cdc_vaccines/delphi_cdc_vaccines/__init__.py

@@ -0,0 +1,13 @@
+# -*- coding: utf-8 -*-
+"""Module to pull and clean indicators from the CDC source.
+
+This file defines the functions that are made public by the module. As the
+module is intended to be executed though the main method, these are primarily
+for testing.
+"""
+
+from __future__ import absolute_import
+from . import pull
+from . import run
+
+__version__ = "0.1.0"

cdc_vaccines/delphi_cdc_vaccines/__main__.py

@@ -0,0 +1,12 @@
+# -*- coding: utf-8 -*-
+"""Call the function run_module when executed.
+
+This file indicates that calling the module (`python -m MODULE_NAME`) will
+call the function `run_module` found within the run.py file. There should be
+no need to change this template.
+"""
+
+from delphi_utils import read_params
+from .run import run_module  # pragma: no cover
+
+run_module(read_params())  # pragma: no cover

cdc_vaccines/delphi_cdc_vaccines/constants.py

@@ -0,0 +1,54 @@
+"""Registry for variations."""
+
+
+from delphi_utils import Smoother
+
+FULL_VAC_SUM     = "cumulative_counts_tot_vaccine"
+FULL_VAC         = "counts_tot_vaccine"
+FULL_VAC_SUM_12P = "cumulative_counts_tot_vaccine_12P"
+FULL_VAC_12P     = "counts_tot_vaccine_12P"
+FULL_VAC_SUM_18P = "cumulative_counts_tot_vaccine_18P"
+FULL_VAC_18P     = "counts_tot_vaccine_18P"
+FULL_VAC_SUM_65P = "cumulative_counts_tot_vaccine_65P"
+FULL_VAC_65P     = "counts_tot_vaccine_65P"
+PART_VAC_SUM     = "cumulative_counts_part_vaccine"
+PART_VAC         = "counts_part_vaccine"
+PART_VAC_SUM_12P = "cumulative_counts_part_vaccine_12P"
+PART_VAC_12P     = "counts_part_vaccine_12P"
+PART_VAC_SUM_18P = "cumulative_counts_part_vaccine_18P"
+PART_VAC_18P     = "counts_part_vaccine_18P"
+PART_VAC_SUM_65P = "cumulative_counts_part_vaccine_65P"
+PART_VAC_65P     = "counts_part_vaccine_65P"
+
+
+
+SIGNALS = [
+	FULL_VAC_SUM     ,
+	FULL_VAC         ,
+	FULL_VAC_SUM_12P ,
+	FULL_VAC_12P     ,
+	FULL_VAC_SUM_18P ,
+	FULL_VAC_18P     ,
+	FULL_VAC_SUM_65P ,
+	FULL_VAC_65P     ,
+	PART_VAC_SUM     ,
+	PART_VAC         ,
+	PART_VAC_SUM_12P ,
+	PART_VAC_12P     ,
+	PART_VAC_SUM_18P ,
+	PART_VAC_18P     ,
+	PART_VAC_SUM_65P ,
+	PART_VAC_65P
+]
+
+GEOS = [
+    "nation",
+    "state_code",
+    "hrr",
+    "hhs"
+]
+
+SMOOTHERS = [
+    (Smoother("identity", impute_method=None), ""),
+    (Smoother("moving_average", window_length=7), "_7dav"),
+]