Scale up step 2 (#142)

* Updated config

* Update TeleQ and queries

* Retrained model and updated requirements

* Removed setup.cfg from manifest

* Fix linting

* Updated workflows

* typo

* forgot keyword

* Add removed subsection to changelog

.github/workflows/linting.yml

@@ -12,14 +12,18 @@ jobs:
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v4
+
+    - name: Install uv
+      uses: astral-sh/setup-uv@v3
+
     - name: Set up Python
       uses: actions/setup-python@v5
       with:
         python-version: '3.11'
+
     - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install ruff
+      run: uv sync --only-dev
+
     - name: Analysing the code with ruff
       run: |
-        ruff check .
+        uv run ruff check .

.github/workflows/unit_test.yml

@@ -12,20 +12,21 @@ jobs:
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v4
+
+    - name: Install uv
+      uses: astral-sh/setup-uv@v3
+
     - name: Set up Python
       uses: actions/setup-python@v5
       with:
         python-version: '3.11'
+
     - name: Install dependencies
-      run: |
-        python -m pip install uv
-        uv venv .venv
-        if [ -f requirements.txt ]; then uv pip install -r requirements.txt; fi
-        uv pip install -e ".[test]"
+      run: uv sync --all-extras --dev
+
     - name: Running Unit tests
-      run: |
-        source .venv/bin/activate
-        pytest tests/ --doctest-modules --cov=src --cov-report=xml
+      run: uv run pytest tests/ --doctest-modules --cov=src --cov-report=xml
+
     - name: Code Coverage Summary Report
       uses: irongut/[email protected]
       with:

CHANGELOG.md

@@ -7,6 +7,17 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [1.4.8] - 2024-11-13
+
+### Added
+- New clinics added to the queries and config
+
+### Changed
+- Updated dependencies
+
+### Removed
+- Removed deprecated setup.cfg file
+
 ## [1.4.7] - 2024-11-04
 
 ### Changed

data/raw/poliafspraken_no_show.csv.dvc

@@ -1,5 +1,5 @@
 outs:
-- md5: 148c83475d3eeac86a809cbc569eba0e
-  size: 411770150
+- md5: 530380d7750f4c1e819d94bee3c2c52a
+  size: 499291413
   path: poliafspraken_no_show.csv
   hash: md5

data/sql/data_export.sql

@@ -95,7 +95,26 @@ WHERE 1=1
             'ZH0122', -- Infectieziekten
             'ZH0088', -- Diabetologie
             'ZH0096', -- Endocrinologie
-            'ZH0413' -- Vasculaire geneeskunde
+            'ZH0413', -- Vasculaire geneeskunde
+            -- Longfunctie
+            'ZH0182',
+            -- Neurologie & neurochiurgie
+            'ZH0005', -- Algemene neurochirurgie
+            'ZH0006', -- Algemene neurologie
+            'ZH0035', -- Cerebrovasculaire ziekten
+            'ZH0194', -- Neuro oncologie
+            -- Neuromusculaire ziekten
+            'ZH0197', -- Neuromusculaire ziekten
+            'ZH0105', -- Functionele neurochirurgie
+            -- Zorglijn affectieve en psychotische stoornissen
+            'ZH0298', -- PSY stemming en psychose
+            -- Zorglijn Diagnostiek en vroege psychose
+            'ZH0299', -- PSY Diagnostiek en vroege psychose
+            -- Zorglijn Ontwikkeling in perspectief
+            'ZH0300', -- PSY Ontwikkeling in perspectief
+            -- Zorglijn Acute en intensieve zorg
+            'ZH0297' -- PSY Acute en intensieve zorg
+
         )
     AND APP.identifier_system = 'https://metadata.umcutrecht.nl/ids/HixAgendaAfspraak'
     AND APP.created >= '2015-01-01'

data/sql/data_prediction.sql

@@ -117,7 +117,25 @@ WHERE 1=1
         'ZH0122', -- Infectieziekten
         'ZH0088', -- Diabetologie
         'ZH0096', -- Endocrinologie
-        'ZH0413' -- Vasculaire geneeskunde
+        'ZH0413', -- Vasculaire geneeskunde
+        -- Longfunctie
+        'ZH0182',
+        -- Neurologie & neurochiurgie
+        'ZH0005', -- Algemene neurochirurgie
+        'ZH0006', -- Algemene neurologie
+        'ZH0035', -- Cerebrovasculaire ziekten
+        'ZH0194', -- Neuro oncologie
+        -- Neuromusculaire ziekten
+        'ZH0197', -- Neuromusculaire ziekten
+        'ZH0105', -- Functionele neurochirurgie
+        -- Zorglijn affectieve en psychotische stoornissen
+        'ZH0298', -- PSY stemming en psychose
+        -- Zorglijn Diagnostiek en vroege psychose
+        'ZH0299', -- PSY Diagnostiek en vroege psychose
+        -- Zorglijn Ontwikkeling in perspectief
+        'ZH0300', -- PSY Ontwikkeling in perspectief
+        -- Zorglijn Acute en intensieve zorg
+        'ZH0297' -- PSY Acute en intensieve zorg
     )
     AND APP.identifier_system = 'https://metadata.umcutrecht.nl/ids/HixAgendaAfspraak'
     AND APP.[created] >= '2015-01-01'
@@ -200,7 +218,25 @@ WHERE 1=1
                 'ZH0122', -- Infectieziekten
                 'ZH0088', -- Diabetologie
                 'ZH0096', -- Endocrinologie
-                'ZH0413' -- Vasculaire geneeskunde
+                'ZH0413', -- Vasculaire geneeskunde
+                -- Longfunctie
+                'ZH0182',
+                -- Neurologie & neurochiurgie
+                'ZH0005', -- Algemene neurochirurgie
+                'ZH0006', -- Algemene neurologie
+                'ZH0035', -- Cerebrovasculaire ziekten
+                'ZH0194', -- Neuro oncologie
+                -- Neuromusculaire ziekten
+                'ZH0197', -- Neuromusculaire ziekten
+                'ZH0105', -- Functionele neurochirurgie
+                -- Zorglijn affectieve en psychotische stoornissen
+                'ZH0298', -- PSY stemming en psychose
+                -- Zorglijn Diagnostiek en vroege psychose
+                'ZH0299', -- PSY Diagnostiek en vroege psychose
+                -- Zorglijn Ontwikkeling in perspectief
+                'ZH0300', -- PSY Ontwikkeling in perspectief
+                -- Zorglijn Acute en intensieve zorg
+                'ZH0297' -- PSY Acute en intensieve zorg
             )
             AND APP2.identifier_system = 'https://metadata.umcutrecht.nl/ids/HixAgendaAfspraak'
             AND CONVERT(DATE, APP2.[start]) = @start_date

dvc.lock

@@ -5,17 +5,17 @@ stages:
     deps:
     - path: data/processed/featuretable.parquet
       hash: md5
-      md5: 1b447d4fc41fb782d93804cde240e002
-      size: 76540090
+      md5: 98d6d67a29704828698fcd1fbd039e83
+      size: 93522680
     - path: src/noshow/model/train_model.py
       hash: md5
       md5: 00964a947199825f721ebbbe0bb23da6
       size: 3708
     outs:
     - path: output/models/no_show_model_cv.pickle
       hash: md5
-      md5: 3d81bdcc860f51a1843593988ac2c1f6
-      size: 1591119
+      md5: f30c648b054c4ee8f336638f1982f381
+      size: 1860467
   feature_building:
     cmd: python src/noshow/features/feature_pipeline.py
     deps:
@@ -24,14 +24,14 @@ stages:
       size: 279455
     - path: data/raw/poliafspraken_no_show.csv
       hash: md5
-      md5: 148c83475d3eeac86a809cbc569eba0e
-      size: 411770150
+      md5: 530380d7750f4c1e819d94bee3c2c52a
+      size: 499291413
     - path: src/noshow/features/feature_pipeline.py
       hash: md5
       md5: 71ffb7a162976bde11e0aed72ea19f98
       size: 2889
     outs:
     - path: data/processed/featuretable.parquet
       hash: md5
-      md5: 1b447d4fc41fb782d93804cde240e002
-      size: 76540090
+      md5: 98d6d67a29704828698fcd1fbd039e83
+      size: 93522680

manifest_admin_dash.json

@@ -86,9 +86,6 @@
     "run/config/config.toml.dvc": {
       "checksum": "9859113746e147a7efab10481e7a1769"
     },
-    "setup.cfg": {
-      "checksum": "bbbe201f135ed769da1877db5cc56fb6"
-    },
     "src/noshow/__init__.py": {
       "checksum": "d41d8cd98f00b204e9800998ecf8427e"
     },

manifest_api.json

@@ -89,9 +89,6 @@
     "run/config/config.toml.dvc": {
       "checksum": "9859113746e147a7efab10481e7a1769"
     },
-    "setup.cfg": {
-      "checksum": "bbbe201f135ed769da1877db5cc56fb6"
-    },
     "src/noshow/__init__.py": {
       "checksum": "d41d8cd98f00b204e9800998ecf8427e"
     },

manifest_dash.json

@@ -80,9 +80,6 @@
     "run/config/config.toml": {
       "checksum": "fc166438569074175c386c4a31d0184c"
     },
-    "setup.cfg": {
-      "checksum": "bbbe201f135ed769da1877db5cc56fb6"
-    },
     "src/noshow/__init__.py": {
       "checksum": "d41d8cd98f00b204e9800998ecf8427e"
     },

notebooks/analyze_rct.ipynb

@@ -110,9 +110,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "data_export = pd.read_csv(\"../data/raw/poliafspraken_rct.csv\").drop(\n",
-    "    columns=[\"specialty_code\", \"name\", \"soort_consult\", \"afspraak_code\", \"start\", \"end\"]\n",
-    ")\n",
+    "data_export = pd.read_csv(\n",
+    "    \"../data/raw/poliafspraken_rct.csv\", parse_dates=[\"start\", \"end\"]\n",
+    ").drop(columns=[\"specialty_code\", \"name\", \"soort_consult\", \"afspraak_code\"])\n",
     "data_export.loc[data_export[\"cancelationReason_code\"] == \"N\", \"outcome\"] = \"No-Show\"\n",
     "data_export.loc[data_export[\"status_code_original\"] == \"J\", \"outcome\"] = \"Show\"\n",
     "data_export = data_export.drop(\n",
@@ -150,7 +150,7 @@
     "\n",
     "live_data_rct[\"prediction_id\"] = live_data_rct[\"prediction_id\"].astype(\"int64\")\n",
     "live_data_rct = live_data_rct[live_data_rct[\"treatment_group\"] != 2]\n",
-    "live_data_rct = live_data_rct[live_data_rct[\"active\"] == 1]\n",
+    "# live_data_rct = live_data_rct[live_data_rct[\"active\"] == 1]\n",
     "live_data_rct = live_data_rct.drop(\n",
     "    columns=[\"active\", \"clinic_reception\", \"request_id\", \"remarks\", \"last_call_date\"]\n",
     ")"
@@ -184,7 +184,6 @@
     "    right_on=\"APP_ID\",\n",
     "    how=\"left\",\n",
     ")\n",
-    "combined_data = combined_data.drop(columns=[\"clinic_name\", \"APP_ID\"])\n",
     "combined_data"
    ]
   },
@@ -204,6 +203,57 @@
     "## Analyze No-Show"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Analyse how many appointments with status \"herinnerd\" are actually completed\n",
+    "combined_data.loc[combined_data[\"call_outcome\"] == \"Herinnerd\"].value_counts(\n",
+    "    \"outcome\", normalize=True\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "combined_data.loc[combined_data[\"call_outcome\"] == \"Geen\"].value_counts(\n",
+    "    \"outcome\", normalize=True\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "combined_data[\"call_outcome\"].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# How many appointments with call outcome verzet/geannulleerd are actually changed and\n",
+    "# subsequently completed\n",
+    "combined_data.loc[\n",
+    "    combined_data[\"start_time\"] != combined_data[\"start\"], \"app_moved\"\n",
+    "] = True\n",
+    "combined_data.loc[\n",
+    "    combined_data[\"start_time\"] == combined_data[\"start\"], \"app_moved\"\n",
+    "] = False\n",
+    "combined_data.loc[combined_data[\"call_outcome\"] == \"Verzet/Geannuleerd\"].value_counts(\n",
+    "    [\"app_moved\", \"outcome\"], dropna=False\n",
+    ").unstack()"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,

output/dvclive/metrics.json

@@ -1,7 +1,7 @@
 {
-    "best_score": 0.7272450402128756,
-    "mean_roc_auc": 0.7272450402128756,
-    "std_roc_auc": 0.002736622346011254,
-    "mean_precision": 0.534075517794019,
-    "mean_recall": 0.014129280503436722
+    "best_score": 0.7402663469877975,
+    "mean_roc_auc": 0.7402663469877975,
+    "std_roc_auc": 0.007219339746532362,
+    "mean_precision": 0.5441756346300849,
+    "mean_recall": 0.01516288989391171
 }

output/dvclive/plots/metrics/best_score.tsv

@@ -1,2 +1,2 @@
 step	best_score
-0	0.7272450402128756
+0	0.7402663469877975

output/dvclive/plots/metrics/mean_precision.tsv

@@ -1,2 +1,2 @@
 step	mean_precision
-0	0.534075517794019
+0	0.5441756346300849

output/dvclive/plots/metrics/mean_recall.tsv

@@ -1,2 +1,2 @@
 step	mean_recall
-0	0.014129280503436722
+0	0.01516288989391171

output/dvclive/plots/metrics/mean_roc_auc.tsv

@@ -1,2 +1,2 @@
 step	mean_roc_auc
-0	0.7272450402128756
+0	0.7402663469877975

output/dvclive/plots/metrics/std_roc_auc.tsv

@@ -1,2 +1,2 @@
 step	std_roc_auc
-0	0.002736622346011254
+0	0.007219339746532362

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "noshow"
-version = "1.4.7"
+version = "1.4.8"
 authors = [
   { name="Ruben Peters", email="[email protected]" },
   { name="Eric Wolters", email="[email protected]" }