feat: Github actions integration for test (#1)

github actions + rename tests

Author: BPDanek

.github/workflows/run-unit-tests.yml

@@ -0,0 +1,72 @@
+name: pytest unittest
+
+on:
+  pull_request:
+      branches: [ "develop", "master" ]
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.9"]
+
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: 'pip' # caching pip dependencies
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install pytest
+          if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+      
+      - name: Download artifact
+        id: download-artifact
+        uses: dawidd6/action-download-artifact@v2
+        with:
+          # Optional, the status or conclusion of a completed workflow to search for
+          # Can be one of a workflow conclusion:
+          #   "failure", "success", "neutral", "cancelled", "skipped", "timed_out", "action_required"
+          # Or a workflow status:
+          #   "completed", "in_progress", "queued"
+          # Use the empty string ("") to ignore status or conclusion in the search
+          workflow_conclusion: success
+          run_id: 4246999530
+          run_number: 26
+          # Optional, uploaded artifact name,
+          # will download all artifacts if not specified
+          # and extract them into respective subdirectories
+          # https://github.com/actions/download-artifact#download-all-artifacts
+          name: datasets
+          # Optional, a directory where to extract artifact(s), defaults to the current directory
+          path: /home/runner/.cache/pyhealth/datasets/
+          # Optional, search for the last workflow run whose stored an artifact named as in `name` input
+          # default false
+          search_artifacts: true
+          # Optional, choose how to exit the action if no artifact is found
+          # can be one of:
+          #  "fail", "warn", "ignore"
+          # default fail
+          if_no_artifact_found: warn
+       
+      - name: validate cached data is correctly placed
+        run: | 
+          ls -al /home/runner/.cache/pyhealth/datasets/
+
+      - name: Test with pytest
+        run: |
+          cd pyhealth/unittests
+          pytest -rP
+  
+      - name: dataset pickles to upload
+        run: |
+          ls -al /home/runner/.cache/pyhealth/datasets/
+      - name: upload datasets pickle
+        uses: actions/upload-artifact@v3
+        with:
+          name: datasets
+          path: /home/runner/.cache/pyhealth/datasets/

pyhealth/datasets/base_ehr_dataset.py

@@ -115,7 +115,7 @@ def __init__(
         )
         filename = hash_str("+".join([str(arg) for arg in args_to_hash])) + ".pkl"
         self.filepath = os.path.join(MODULE_CACHE_PATH, filename)
-
+        
         # check if cache exists or refresh_cache is True
         if os.path.exists(self.filepath) and (not refresh_cache):
             # load from cache

pyhealth/datasets/mimic3.py

@@ -361,7 +361,7 @@ def lab_unit(p_id, p_info):
 
 if __name__ == "__main__":
     dataset = MIMIC3Dataset(
-        root="/srv/local/data/physionet.org/files/mimiciii/1.4",
+        root="https://storage.googleapis.com/pyhealth/mimiciii-demo/1.4/",
         tables=[
             "DIAGNOSES_ICD",
             "PROCEDURES_ICD",

…alth/unittests/test_datasets/test_mimic3 …h/unittests/test_datasets/test_mimic3.pypyhealth/unittests/test_datasets/test_mimic3 renamed to pyhealth/unittests/test_datasets/test_mimic3.py pyhealth/unittests/test_datasets/test_mimic3 renamed to pyhealth/unittests/test_datasets/test_mimic3.py

@@ -1,5 +1,10 @@
 import datetime
 import unittest
+import os, sys
+
+current = os.path.dirname(os.path.realpath(__file__))
+repo_root = os.path.dirname(os.path.dirname(os.path.dirname(current)))
+sys.path.append(repo_root)
 
 from pyhealth.datasets import MIMIC3Dataset
 
@@ -10,19 +15,16 @@
 # used for testing correctness
 # like the MIMIC4 dataset, if this test suite fails, it may be due to a regression in the
 # code, or due to the dataset at the root chaning.
-class Mimic3Tests(unittest.TestCase):
+class TestsMimic3(unittest.TestCase):
 
     ROOT = "https://storage.googleapis.com/pyhealth/mimiciii-demo/1.4/"
     TABLES = ["DIAGNOSES_ICD", "PRESCRIPTIONS"]
     CODE_MAPPING = {"NDC": ("ATC", {"target_kwargs": {"level": 3}})}
-    DEV = True
 
     dataset = MIMIC3Dataset(
         root=ROOT,
         tables=TABLES,
         code_mapping=CODE_MAPPING,
-        dev=DEV, # since we are using the demo dataset it doesn't matter. 
-        refresh_cache=True,
     )
 
     def setUp(self):

…alth/unittests/test_datasets/test_mimic4 …h/unittests/test_datasets/test_mimic4.pypyhealth/unittests/test_datasets/test_mimic4 renamed to pyhealth/unittests/test_datasets/test_mimic4.py pyhealth/unittests/test_datasets/test_mimic4 renamed to pyhealth/unittests/test_datasets/test_mimic4.py

@@ -1,5 +1,10 @@
 import datetime
 import unittest
+import os, sys
+
+current = os.path.dirname(os.path.realpath(__file__))
+repo_root = os.path.dirname(os.path.dirname(os.path.dirname(current)))
+sys.path.append(repo_root)
 
 from pyhealth.datasets import MIMIC4Dataset
 
@@ -8,7 +13,7 @@
 # and a single sample from the dataset.
 
 
-class Mimic4Tests(unittest.TestCase):
+class TestMimic4(unittest.TestCase):
 
     # to test the file this path needs to be updated
     ROOT = "https://storage.googleapis.com/pyhealth/mimiciv-demo/hosp/"
@@ -23,7 +28,7 @@ class Mimic4Tests(unittest.TestCase):
         dev=DEV,
         refresh_cache=False,
     )
-
+    
     def setUp(self):
         pass