From c55cabc9ced8bd991a4a6028a8db117f8cd6566e Mon Sep 17 00:00:00 2001
From: frankknoll <Knoll_Frank@web.de>
Date: Mon, 23 Jan 2023 10:03:44 +0100
Subject: [PATCH] refining SymptomByBatchcodeTableFactoryTest

---
 src/SymptomByBatchcodeTableFactory.py     |  2 ++
 src/SymptomByBatchcodeTableFactoryTest.py | 43 ++++++++++++++++++++++-
 2 files changed, 44 insertions(+), 1 deletion(-)

diff --git a/src/SymptomByBatchcodeTableFactory.py b/src/SymptomByBatchcodeTableFactory.py
index 9184961027f..d69163be69d 100644
--- a/src/SymptomByBatchcodeTableFactory.py
+++ b/src/SymptomByBatchcodeTableFactory.py
@@ -1,10 +1,12 @@
 import pandas as pd
 import numpy as np
+from DataFrameNormalizer import DataFrameNormalizer
 
 class SymptomByBatchcodeTableFactory:
 
     @staticmethod
     def createSymptomByBatchcodeTable(VAERSVAX, VAERSSYMPTOMS):
+        DataFrameNormalizer.convertVAX_LOTColumnToUpperCase(VAERSVAX)
         index_columns = SymptomByBatchcodeTableFactory._getIndexColumns(VAERSVAX)
         symptomColumn = 'SYMPTOM'
         return (pd
diff --git a/src/SymptomByBatchcodeTableFactoryTest.py b/src/SymptomByBatchcodeTableFactoryTest.py
index 68c2ee2f421..c05b250e7dd 100644
--- a/src/SymptomByBatchcodeTableFactoryTest.py
+++ b/src/SymptomByBatchcodeTableFactoryTest.py
@@ -5,7 +5,6 @@ from SymptomByBatchcodeTableFactory import SymptomByBatchcodeTableFactory
 import pandas as pd
 import numpy as np
 
-# FIXME: brauchen Normalisierung analog zu DataFrameNormalizer.removeUnknownBatchCodes(dataFrame) und DataFrameNormalizer.convertVAX_LOTColumnToUpperCase(dataFrame)
 class SymptomByBatchcodeTableFactoryTest(unittest.TestCase):
 
     def test_createSymptomByBatchcodeTable(self):
@@ -168,3 +167,45 @@ class SymptomByBatchcodeTableFactoryTest(unittest.TestCase):
                 index = pd.MultiIndex.from_tuples(
                     names =   ['VAX_LOT1', 'VAX_LOT2'],
                     tuples = [['1808982',  'EW0175']] * 13 + [['EW0167', 'EW0175']] * 10)))
+
+    def test_createSymptomByBatchcodeTable_after_convertVAX_LOTColumnToUpperCase(self):
+        # Given
+        VAX_LOT = 'EW0175'
+        VAX_LOT_lower = VAX_LOT.lower()
+        VAERSVAX = TestHelper.createDataFrame(
+            columns = ['VAX_TYPE', 'VAX_MANU', 'VAX_LOT',     'VAX_DOSE_SERIES'],
+            data = [  ['COVID19',  'JANSSEN',  VAX_LOT,       '1'],
+                      ['COVID19',  'JANSSEN',  VAX_LOT_lower, '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
+        symptomByBatchcodeTable = SymptomByBatchcodeTableFactory.createSymptomByBatchcodeTable(VAERSVAX, VAERSSYMPTOMS)
+
+        # Then
+        assert_frame_equal(
+            symptomByBatchcodeTable,
+            TestHelper.createDataFrame(
+                columns = ['SYMPTOM'],
+                data = [  ['Blood pressure orthostatic abnormal'],
+                          ['Blood pressure orthostatic abnormal']],
+                index = pd.Index(
+                    name = 'VAX_LOT1',
+                    data = [VAX_LOT,
+                            VAX_LOT])),
+                check_dtype = False)