Update patients.

scripts/transform_patients.py

@@ -102,12 +102,11 @@ def calculate_shift(merged):
 
     # Update death date if from tumor registry
     merged.loc[pd.notna(merged['Vital Status']), 'DEATH_SOURCE'] = 'Tumor Registry'
-    merged.loc[pd.notna(merged['Vital Status']), 'DEATH_DATE'] = 'Date of Last Contact-Date'
+    merged.loc[pd.notna(merged['Vital Status']), 'DEATH_DATE'] = merged['Date of Last Contact-Date']
 
     # Calculate date Shift for death date
     merged['DEATH_DATE'] = merged['DEATH_DATE'] + merged['Shift']
 
-
     # Shift to total seconds
     time_delta_series = merged['Shift']
     merged['Shift'] = time_delta_series.apply(get_seconds)

tests/test_transform_patients.py

@@ -11,9 +11,9 @@ DEMOGRAPHIC_STRING = """MRN,PAT_ID,PAT_LAST_NAME,PAT_FIRST_NAME,GENDER,BIRTH_DAT
 """
 
 
-DEMO_MERGED_STRING = """MRN,GENDER,ETHNICITY,RACE,BIRTH_DATE,Date
-934,FEMALE,AmIndAN,@,27-JUN-1957,11/27/2017
-822,FEMALE,White,@,29-JUL-1913,03/10/2015
+DEMO_MERGED_STRING = """MRN,GENDER,ETHNICITY,RACE,BIRTH_DATE,DEATH_DATE,DEATH_SOURCE,Date of Last Contact-Date,Vital Status
+934,FEMALE,AmIndAN,@,27-JUN-1957,11/27/2017,EPIC,,
+822,FEMALE,White,@,29-JUL-1913,,,03/10/2015,0
 """
 
 
@@ -25,7 +25,7 @@ def demographic():
 
 
 @pytest.fixture
-def demographic_diagnosis():
+def demographic_death():
     merged_file = StringIO(DEMO_MERGED_STRING)
     merged_df = pd.read_csv(merged_file)
     return merged_df
@@ -81,14 +81,16 @@ def test_check_race_unknown(demographic_2):
 
 
 @pytest.mark.unit
-def test_check_shift(demographic_diagnosis):
-    check_shift = transform_patients.calculate_shift(demographic_diagnosis)
-    assert check_shift.loc[0,'Age'] == 60
+def test_check_shift(demographic_death):
+    check_shift = transform_patients.calculate_shift(demographic_death)
+    check_shift['DEATH_DATE'] = check_shift['DEATH_DATE'].astype(str)
+    assert check_shift.loc[0,'DEATH_DATE'] == '1860-06-03'
     assert check_shift.loc[0,'Shift'] == -4969728000.0
 
 
 @pytest.mark.unit
-def test_check_shift_90_over(demographic_diagnosis):
-    check_shift_90_over = transform_patients.calculate_shift(demographic_diagnosis)
-    assert check_shift_90_over.loc[1,'Age'] == '90 or above'
-    assert check_shift_90_over.loc[1,'Shift'] == -3583958400.0
+def test_check_shift_tumor_registry(demographic_death):
+    check_shift_tumor_registry = transform_patients.calculate_shift(demographic_death)
+    check_shift_tumor_registry['DEATH_DATE'] = check_shift_tumor_registry['DEATH_DATE'].astype(str)
+    assert check_shift_tumor_registry.loc[1,'DEATH_DATE'] == '1901-08-14'
+    assert check_shift_tumor_registry.loc[1,'Shift'] == -3583958400.0