Moved study period source from core (#41)

* Moved study period source from core

This takes the core__study_period table (which was really
specific to this study) and moves it into this study as part
of the covid_symptom__study_period table.

This also removes the no longer required interstitial directory,
and updates the counts builder/pyproject.toml to the 3.0 input
format.

* Ruff cutover

* ci indenting, more generic args

* removed unused imports

* ruff format

.github/workflows/ci.yaml

@@ -10,20 +10,30 @@ jobs:
       - name: Set up Python 
         uses: actions/setup-python@v4
         with:
-          python-version: "3.10"
+          python-version: "3.11"
 
   lint:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
+
+      - name: Set up Python 
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.11"
+
+      - name: Get library from main
+        run: pip install git+https://github.com/smart-on-fhir/cumulus-library.git
+
       - name: Install linters
         run: |
           python -m pip install --upgrade pip
           pip install ".[dev]"
       - name: Run sqlfluff on jinja templates
         run: |
           sqlfluff lint
-      - name: Run black
-        if: success() || failure() # still run black if above checks fails
+      - name: Run ruff
+        if: success() || failure() # still run ruff if above checks fails
         run: |
-          black --check --verbose .
+          ruff check
+          ruff format --check

cumulus_library_covid/covid_symptom/counts.py → cumulus_library_covid/counts.py

@@ -1,4 +1,5 @@
 from pathlib import Path
+
 from cumulus_library.statistics.counts import CountsBuilder
 
 
@@ -98,7 +99,7 @@ def count_symptom(self, duration="week"):
         ]
         return self.count_encounter(view_name, from_table, cols)
 
-    def prepare_queries(self, cursor=None, schema=None, **kwargs):
+    def prepare_queries(self, *args, **kwargs):
         self.queries = [
             self.count_dx("month"),
             self.count_dx("week"),

cumulus_library_covid/covid_symptom/define_symptom.py → cumulus_library_covid/define_symptom.py

@@ -1,4 +1,4 @@
-""" util for sql view creation"""
+"""util for sql view creation"""
 
 import ctakesclient
 
@@ -15,7 +15,7 @@ def main():
 
     table_cols = "AS t (cui, tui, code, system, text, pref);"
     create_view = (
-        "create or replace view covid_symptom__define_symptom as "
+        "create or replace view covid_symptom__define_symptom as "  # noqa: S608
         f"select * from (VALUES \n {values_sql}) \n {table_cols}"
     )
 

cumulus_library_covid/table_study_period.sql

@@ -0,0 +1,106 @@
+CREATE TABLE covid_symptom__study_period AS
+WITH documented_encounter AS (
+    SELECT DISTINCT
+        ce.period_start_day,
+        ce.period_start_week,
+        ce.period_start_month,
+        ce.period_end_day,
+        ce.age_at_visit,
+        cdr.author_day,
+        cdr.author_week,
+        cdr.author_month,
+        cdr.author_year,
+        cp.gender,
+        cp.race_display,
+        cp.ethnicity_display,
+        cp.subject_ref,
+        ce.encounter_ref,
+        ce.status,
+        cdr.documentreference_ref,
+        date_diff(
+            'day', ce.period_start_day, date(cdr.author_day)
+        ) AS diff_enc_note_days,
+        coalesce(ce.class_code, 'None') AS enc_class_code,
+        coalesce(ce.class_display, 'None') AS enc_class_display,
+        coalesce(cdr.type_code, 'None') AS doc_type_code,
+        coalesce(cdr.type_display, 'None') AS doc_type_display
+    FROM
+        core__patient AS cp,
+        core__encounter AS ce,
+        core__documentreference AS cdr
+    WHERE
+        (cp.subject_ref = ce.subject_ref)
+        AND (ce.encounter_ref = cdr.encounter_ref)
+        AND (cdr.author_day BETWEEN date('2016-06-01') AND current_date)
+        AND (ce.period_start_day BETWEEN date('2016-06-01') AND current_date)
+        AND (ce.period_end_day BETWEEN date('2016-06-01') AND current_date)
+),
+
+encounter_with_note AS (
+    SELECT
+        de.period_start_day,
+        de.period_start_week,
+        de.period_start_month,
+        de.period_end_day,
+        de.age_at_visit,
+        de.author_day,
+        de.author_week,
+        de.author_month,
+        de.author_year,
+        de.gender,
+        de.race_display,
+        de.ethnicity_display,
+        de.subject_ref,
+        de.encounter_ref,
+        de.status,
+        de.documentreference_ref,
+        de.diff_enc_note_days,
+        de.enc_class_code,
+        de.enc_class_display,
+        de.doc_type_code,
+        de.doc_type_display,
+        coalesce(ed.code IS NOT NULL, FALSE) AS ed_note
+    FROM documented_encounter AS de
+    LEFT JOIN core__ed_note AS ed
+        ON de.doc_type_code = ed.from_code
+)
+
+SELECT DISTINCT
+    v.variant_era,
+    e.period_start_day AS start_date,
+    e.period_start_week AS start_week,
+    e.period_start_month AS start_month,
+    e.period_end_day AS end_date,
+    e.age_at_visit,
+    e.author_day AS author_date,
+    e.author_week,
+    e.author_month,
+    e.author_year,
+    e.gender,
+    e.race_display,
+    e.subject_ref,
+    e.encounter_ref,
+    e.documentreference_ref,
+    e.diff_enc_note_days,
+    e.enc_class_code,
+    e.enc_class_display,
+    e.doc_type_code,
+    e.doc_type_display,
+    e.ed_note,
+    a.age_group,
+    e.status
+FROM encounter_with_note AS e,
+    covid_symptom__define_period AS v,
+    covid_symptom__define_age AS a
+WHERE
+    e.age_at_visit = a.age
+    AND e.gender IN ('female', 'male')
+    AND e.author_day BETWEEN v.variant_start AND v.variant_end
+    AND e.period_start_day BETWEEN v.variant_start AND v.variant_end
+    AND e.diff_enc_note_days BETWEEN -30 AND 30;
+
+CREATE TABLE covid_symptom__meta_date AS
+SELECT
+    min(start_date) AS min_date,
+    max(end_date) AS max_date
+FROM covid_symptom__study_period;

pyproject.toml

@@ -1,9 +1,9 @@
 [project]
 name = "cumulus-library-covid"
-requires-python = ">= 3.10"
-version = "1.0.0"
+requires-python = ">= 3.11"
+version = "2.0.0"
 dependencies = [
-    "cumulus-library >= 2.0, <3",
+    "cumulus-library >= 3.0, <4",
     "sqlfluff >= 3"
 ]
 description = "SQL generation for cumulus covid symptom analysis"
@@ -28,9 +28,26 @@ build-backend = "flit_core.buildapi"
 
 [project.optional-dependencies]
 dev = [
-    "black >= 24.3, <25",
+    # if you update the ruff version, also update .pre-commit-config.yaml
+    "ruff < 0.6",
     "pylint",    
 ]
 
 [tool.flit.sdist]
 include = ["covid_symptom/"]
+
+[tool.ruff]
+line-length = 100
+
+[tool.ruff.lint]
+allowed-confusables = ["’"]  # allow proper apostrophes
+select = [
+    "A",  # prevent using keywords that clobber python builtins
+    "E",  # pycodestyle
+    "F",  # pyflakes
+    "I",  # isort
+    "PLE",  # pylint errors
+    "RUF",  # the ruff developer's own rules
+    "S",  # bandit security warnings
+    "UP",  # alert you when better syntax is available in your python version
+]