refining some tests

src/BatchcodeCompletion.py

@@ -1,4 +1,5 @@
 from SmartRegexpFactory import SmartRegexpFactory
+import pandas as pd
 
 class BatchcodeCompletion:
     
@@ -6,6 +7,8 @@ class BatchcodeCompletion:
         self.ADR_by_Batchcode = ADR_by_Batchcode.sort_values(by = 'Adverse Reaction Reports', ascending = False)
 
     def completeBatchcode(self, partialBatchcode):
+        if pd.isna(partialBatchcode):
+            return None
         return self._getBatchcodeHavingMostADRs(self._filterBy(partialBatchcode))
     
     def _filterBy(self, partialBatchcode):

src/BatchcodeCompletionTest.py

@@ -2,6 +2,7 @@ import unittest
 from TestHelper import TestHelper
 from BatchcodeCompletion import BatchcodeCompletion
 import pandas as pd
+import numpy as np
 
 class BatchcodeCompletionTest(unittest.TestCase):
 
@@ -49,6 +50,29 @@ class BatchcodeCompletionTest(unittest.TestCase):
         # Then
         self.assertIsNone(completedBatchcode)
 
+    def test_completeBatchcode_NaN(self):
+        # Given
+        # FK-TODO: use empty ADR_by_Batchcode
+        ADR_by_Batchcode = TestHelper.createDataFrame(
+                columns = ['Adverse Reaction Reports'],
+                data = [  [1],
+                          [200],
+                          [149]],
+                index = pd.Index(
+                    [
+                        'LOT000057A',
+                        '030L20B',
+                        '000057A'
+                    ],
+                    name = 'VAX_LOT'))
+        batchcodeCompletion = BatchcodeCompletion(ADR_by_Batchcode)
+                        
+        # When
+        completedBatchcode = batchcodeCompletion.completeBatchcode(np.NaN)
+
+        # Then
+        self.assertIsNone(completedBatchcode)
+
     def test_completeBatchcode_empty_ADR_by_Batchcode(self):
         # Given
         ADR_by_Batchcode = TestHelper.createDataFrame(

src/HowBadIsMyBatch.ipynb

@@ -23,6 +23,32 @@
     "from HistogramFactoryAndPersister import createAndSaveGlobalHistograms, createAndSaveHistogramsForCountries"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0cb5849c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "country_By_Clicked_Batchcode = pd.read_csv('data/Country By Clicked Batchcode.csv', header=[0, 1], index_col=0, skiprows=6)\n",
+    "country_By_Clicked_Batchcode.drop(index='Clicked Batchcode', inplace=True)\n",
+    "country_By_Clicked_Batchcode.index.rename('Clicked Batchcode', inplace=True)\n",
+    "country_By_Clicked_Batchcode"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b5066a92",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "country_By_Batchcode_Search_Term = pd.read_csv('data/Country By Batchcode Search Term.csv', header=[0, 1], index_col=0, skiprows=6)\n",
+    "country_By_Batchcode_Search_Term.drop(index='Batchcode Search Term', inplace=True)\n",
+    "country_By_Batchcode_Search_Term.index.rename('Batchcode Search Term', inplace=True)\n",
+    "country_By_Batchcode_Search_Term"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -141,6 +167,46 @@
     "internationalVaersCovid19"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7a1023e8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from BatchCodeTableFactory import BatchCodeTableFactory\n",
+    "\n",
+    "batchCodeTableFactory = BatchCodeTableFactory(internationalVaersCovid19)\n",
+    "batchCodeTable = batchCodeTableFactory.createGlobalBatchCodeTable()\n",
+    "batchCodeTable"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0e7dae70",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from CompletedBatchcodeColumnAdder import CompletedBatchcodeColumnAdder\n",
+    "from BatchcodeCompletion import BatchcodeCompletion\n",
+    "\n",
+    "batchcodeCompletion = BatchcodeCompletion(batchCodeTable)\n",
+    "completedBatchcodeColumnAdder = CompletedBatchcodeColumnAdder(batchcodeCompletion.completeBatchcode)\n",
+    "country_By_Batchcode_Search_Term = completedBatchcodeColumnAdder.addCompletedBatchcodeColumn(country_By_Batchcode_Search_Term)\n",
+    "country_By_Batchcode_Search_Term"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "89c65459",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "country_By_Batchcode_Search_Term.to_excel('tmp/Country_By_Batchcode_Search_Term.xlsx')"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,

src/SmartRegexpFactory.py

@@ -10,7 +10,7 @@ class SmartRegexpFactory:
             flags=re.IGNORECASE)
 
     def getWords(self, searchTerm):
-        return re.split(r'\s+', searchTerm)
+        return [re.escape(word) for word in re.split(r'\s+', searchTerm)]
 
     def assertContainsWords(self, words):
         return ''.join([self.assertContainsWord(word) for word in words])

src/SmartRegexpFactoryTest.py

@@ -17,4 +17,4 @@ class SmartRegexpFactoryTest(unittest.TestCase):
         self.assertTrue(smartSearch(searchTerm = 'one two three', str = 'TESTone twoTEST TESTthreeTEST'))
         self.assertTrue(smartSearch(searchTerm = 'eins zwei drei', str = 'drei, EINS oder zwei?'))
         self.assertFalse(smartSearch(searchTerm = 'eins zwei drei', str = 'drei, ONE oder zwei?'))
-        
+        self.assertFalse(smartSearch(searchTerm = '(not set', str = 'drei, ONE oder zwei?'))