Some initial hacking at the data service

I had some free time and wanted the data service to at least use the out-of-the-box, uncleaned up dataset to ensure the API was properly defined.

data_service.py

@@ -1,4 +1,5 @@
 from contextlib import contextmanager
+import pandas as pd
 
 class DataService(object):
   @contextmanager
@@ -17,8 +18,27 @@ class DataService(object):
     raise Exception("Should not use the base class")
 
 class DefaultDataService(DataService):
+
+  def __init__(self):
+    self._dataset_url = "https://huggingface.co/datasets/patjs/patient1/raw/main/patient_encounters1_notes.csv"
+    self._initialized = False
+
+  def initialize(func):
+    def wrapper(self):
+      if not self._initialized:
+        self._df = pd.read_csv(self._dataset_url)
+        self._initialized = True
+      return func(self)
+
+    return wrapper
+
   def close(self):
-    raise Exception("Not implemented")
+    #raise Exception("Not implemented")
+    pass
 
+  @initialize
   def get_patients(self) -> list[str]:
-    raise Exception("Not implemented")
+    col = self._df["FIRST"]
+    u = col.unique()
+    l = u.tolist()
+    return l

test/test_app.py

@@ -1,15 +1,15 @@
 import unittest
-from unittest.mock import MagicMock
+from unittest.mock import MagicMock, create_autospec
 from data_service import DataService
 from llm_service import LLMService
 from g34_final_project import App
 
 class TestApp(unittest.TestCase):
   def test_app(self):
-    data_service = DataService()
-    with DataService().build() as data_service, LLMService().build() as llm_service:
+    mock_tmp = MagicMock()
+    mock_tmp.return_value.__enter__.return_value = create_autospec(DataService)
+    with mock_tmp() as data_service, LLMService().with_key("").build() as llm_service:
       data_service.get_patients = MagicMock(return_value=["kareem", "abdul", "jabbar"])
-      data_service.close = MagicMock(return_value=None)
 
       llm_service.get_summary = MagicMock(return_value="This is a summary")
       llm_service.answer_query = MagicMock(return_value="This is the query answer")

test/test_data_service.py

@@ -1,7 +1,12 @@
 import unittest
 
+from data_service import DataService
+
 class TestDataService(unittest.TestCase):
   def test_get_patients(self):
     # TODO: I'm just stubbing out what I think the API could look like.
-    data_service = DataService().to("").withCreds("").build()
-    self.fail()
+    #data_service = DataService().to("").withCreds("").build()
+    with DataService().build() as data_service:
+      patients = data_service.get_patients()
+      self.assertTrue(isinstance(patients, list))
+      self.assertTrue(len(patients) > 0)