refining SymptomsByBatchcodesTableFactoryTest

src/SymptomsByBatchcodesTableFactory.py

@@ -1,5 +1,5 @@
 import pandas as pd
-
+import numpy as np
 
 class SymptomsByBatchcodesTableFactory:
 
@@ -14,13 +14,13 @@ class SymptomsByBatchcodesTableFactory:
     def _get_VAERSVAX_WITH_VAX_LOTS(VAERSVAX):
         return pd.concat(
             [VAERSVAX, SymptomsByBatchcodesTableFactory._getVaxLotsTable(VAERSVAX)],
-            axis=1).drop_duplicates(subset=['VAX_LOT1', 'VAX_LOT2']).reset_index()
+            axis='columns').reset_index().drop_duplicates(subset=['VAERS_ID', 'VAX_LOT1', 'VAX_LOT2'])
 
     @staticmethod
     def _getVaxLotsTable(VAERSVAX):
         VAX_LOT_LIST_Table = VAERSVAX.groupby("VAERS_ID").agg(VAX_LOT_LIST = pd.NamedAgg(column = 'VAX_LOT', aggfunc = list))
         return pd.DataFrame(
-            VAX_LOT_LIST_Table['VAX_LOT_LIST'].tolist(),
+            [fill(VAX_LOTS, 2, str(np.nan)) for VAX_LOTS in VAX_LOT_LIST_Table['VAX_LOT_LIST'].tolist()],
             columns = ['VAX_LOT1', 'VAX_LOT2'],
             index = VAX_LOT_LIST_Table.index)
 
@@ -33,4 +33,7 @@ class SymptomsByBatchcodesTableFactory:
                 VAERSSYMPTOMS['SYMPTOM3'],
                 VAERSSYMPTOMS['SYMPTOM4'],
                 VAERSSYMPTOMS['SYMPTOM5']
-            ]).dropna().drop_duplicates().to_frame(name = "SYMPTOMS").reset_index()
+            ]).dropna().to_frame(name = "SYMPTOMS").reset_index()
+
+def fill(lst, desiredLen, fillValue):
+    return lst + [fillValue] * (max(desiredLen - len(lst), 0))

src/SymptomsByBatchcodesTableFactoryTest.py

@@ -57,3 +57,114 @@ class SymptomsByBatchcodesTableFactoryTest(unittest.TestCase):
                 index = pd.MultiIndex.from_tuples(
                     names =   ['VAX_LOT1', 'VAX_LOT2'],
                     tuples = [['1808982',  'EW0175']] * 13)))
+
+    def test_createSymptomsByBatchcodesTable_two_patients_same_symptoms(self):
+        # Given
+        VAERSVAX = TestHelper.createDataFrame(
+            columns = ['VAX_TYPE', 'VAX_MANU',        'VAX_LOT', 'VAX_DOSE_SERIES'],
+            data = [  ['COVID19',  'JANSSEN',         'EW0175', '1'],
+                      ['COVID19',  'JANSSEN',         'EW0175',  '1']],
+            index = pd.Index(
+                    name = 'VAERS_ID',
+                    data=[
+                        2547730,
+                        2547731]),
+            dtypes = {
+                'VAX_DOSE_SERIES': 'string',
+                'VAX_LOT': 'string'})
+        VAERSSYMPTOMS = TestHelper.createDataFrame(
+            columns = ['SYMPTOM1',                           'SYMPTOM2', 'SYMPTOM3', 'SYMPTOM4', 'SYMPTOM5'],
+            data = [  ['Blood pressure orthostatic abnormal', np.nan,    np.nan,     np.nan,     np.nan],
+                      ['Blood pressure orthostatic abnormal', np.nan,    np.nan,     np.nan,     np.nan]],
+            index = pd.Index(
+                    name = 'VAERS_ID',
+                    data=[
+                        2547730,
+                        2547731]))
+                
+        # When
+        symptomsByBatchcodesTable = SymptomsByBatchcodesTableFactory.createSymptomsByBatchcodesTable(VAERSVAX, VAERSSYMPTOMS)
+
+        # Then
+        assert_frame_equal(
+            symptomsByBatchcodesTable,
+            TestHelper.createDataFrame(
+                columns = ['SYMPTOMS'],
+                data = [  ['Blood pressure orthostatic abnormal'],
+                          ['Blood pressure orthostatic abnormal']],
+                index = pd.MultiIndex.from_tuples(
+                    names =   ['VAX_LOT1', 'VAX_LOT2'],
+                    tuples = [['EW0175', str(np.nan)]] * 2)),
+                check_dtype = False)
+
+    def test_createSymptomsByBatchcodesTable_two_patients_distinct_symptoms(self):
+        # Given
+        VAERSVAX = TestHelper.createDataFrame(
+            columns = ['VAX_TYPE', 'VAX_MANU',        'VAX_LOT', 'VAX_DOSE_SERIES'],
+            data = [  ['COVID19',  'JANSSEN',         '1808982', 'UNK'],
+                      ['COVID19',  'PFIZER\BIONTECH', 'EW0175',  '1'],
+                      ['COVID19',  'PFIZER\BIONTECH', 'EW0175',  '1'],
+                      ['COVID19',  'PFIZER\BIONTECH', 'EW0167',  '2']],
+            index = pd.Index(
+                    name = 'VAERS_ID',
+                    data=[
+                        2547730,
+                        2547730,
+                        2547744,
+                        2547744]),
+            dtypes = {
+                'VAX_DOSE_SERIES': 'string',
+                'VAX_LOT': 'string'})
+        VAERSSYMPTOMS = TestHelper.createDataFrame(
+            columns = ['SYMPTOM1',                            'SYMPTOM2',                        'SYMPTOM3',        'SYMPTOM4',                             'SYMPTOM5'],
+            data = [  ['Blood pressure orthostatic abnormal', 'COVID-19',                        'Coma',            'Computerised tomogram',                'Exposure to SARS-CoV-2'],
+                      ['Head injury',                         'Headache',                        'Laboratory test', 'Magnetic resonance imaging',           'SARS-CoV-2 antibody test negative'],
+                      ['SARS-CoV-2 test positive',            'Unresponsive to stimuli',         'X-ray',           np.nan,                                 np.nan],
+                      ['Computerised tomogram head abnormal', 'Ear pain',                        'Headache',        'Idiopathic intracranial hypertension', 'Intracranial pressure increased'],
+                      ['Lumbar puncture',                     'Magnetic resonance imaging head', 'Pain',            'Swelling',                             'Vision blurred']],
+            index = pd.Index(
+                    name = 'VAERS_ID',
+                    data=[
+                        2547730,
+                        2547730,
+                        2547730,
+                        2547744,
+                        2547744]))
+                
+        # When
+        symptomsByBatchcodesTable = SymptomsByBatchcodesTableFactory.createSymptomsByBatchcodesTable(VAERSVAX, VAERSSYMPTOMS)
+
+        # Then
+        assert_frame_equal(
+            symptomsByBatchcodesTable,
+            TestHelper.createDataFrame(
+                columns = ['SYMPTOMS'],
+                data = [  ['Blood pressure orthostatic abnormal'],
+                          ['Head injury'],
+                          ['SARS-CoV-2 test positive'],
+                          ['COVID-19'],
+                          ['Headache'],
+                          ['Unresponsive to stimuli'],
+                          ['Coma'],
+                          ['Laboratory test'],
+                          ['X-ray'],
+                          ['Computerised tomogram'],
+                          ['Magnetic resonance imaging'],
+                          ['Exposure to SARS-CoV-2'],
+                          ['SARS-CoV-2 antibody test negative'],
+                          
+                          ['Computerised tomogram head abnormal'],
+                          ['Lumbar puncture'],
+                          ['Ear pain'],
+                          ['Magnetic resonance imaging head'],
+                          ['Headache'],
+                          ['Pain'],
+                          ['Idiopathic intracranial hypertension'],
+                          ['Swelling'],
+                          ['Intracranial pressure increased'], 
+                          ['Vision blurred']],
+                index = pd.MultiIndex.from_tuples(
+                    names =   ['VAX_LOT1', 'VAX_LOT2'],
+                    tuples = [['1808982',  'EW0175']] * 13 + [['EW0175', 'EW0167']] * 10)))
+
+