continuing

src/BatchcodeCompletion.py

@@ -0,0 +1,19 @@
+from SmartRegexpFactory import SmartRegexpFactory
+import pandas as pd
+
+class BatchcodeCompletion:
+    
+    def __init__(self, ADR_by_Batchcode):
+        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):
+        smartRegexp = SmartRegexpFactory().createSmartRegexp(partialBatchcode)
+        return self.ADR_by_Batchcode[self.ADR_by_Batchcode.index.str.contains(smartRegexp, na = False, regex = True)]
+
+    def _getBatchcodeHavingMostADRs(self, ADR_by_Batchcode):
+        return ADR_by_Batchcode.index[0] if not ADR_by_Batchcode.empty else None

src/BatchcodeCompletionTest.py

@@ -0,0 +1,83 @@
+import unittest
+from TestHelper import TestHelper
+from BatchcodeCompletion import BatchcodeCompletion
+import pandas as pd
+import numpy as np
+
+class BatchcodeCompletionTest(unittest.TestCase):
+
+    def test_completeBatchcode(self):
+        # Given
+        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('000057')
+
+        # Then
+        self.assertEqual(completedBatchcode, '000057A')
+
+    def test_completeBatchcode_no_completion(self):
+        # Given
+        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('non existing batch code')
+
+        # Then
+        self.assertIsNone(completedBatchcode)
+
+    def test_completeBatchcode_NaN(self):
+        # Given
+        ADR_by_Batchcode = TestHelper.createDataFrame(
+                columns = ['Adverse Reaction Reports'],
+                data =    [],
+                index = pd.Index(
+                    [],
+                    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(
+                columns = ['Adverse Reaction Reports'],
+                data =    [],
+                index = pd.Index(
+                    [],
+                    name = 'VAX_LOT'))
+        batchcodeCompletion = BatchcodeCompletion(ADR_by_Batchcode)
+                        
+        # When
+        completedBatchcode = batchcodeCompletion.completeBatchcode('non existing batch code')
+
+        # Then
+        self.assertIsNone(completedBatchcode)

src/CountriesColumnAdder.py

@@ -0,0 +1,8 @@
+class CountriesColumnAdder:
+
+    def addCountriesColumn(self, countriesByBatchcodeTable, columnName):
+        countriesByBatchcodeTable[columnName] = countriesByBatchcodeTable.apply(self._getCountriesHavingEvents, axis='columns')
+        return countriesByBatchcodeTable
+
+    def _getCountriesHavingEvents(self, eventCountByCountry):
+        return set(eventCountByCountry[eventCountByCountry > 0].index)

src/CountriesColumnAdderTest.py

@@ -0,0 +1,31 @@
+import unittest
+from TestHelper import TestHelper
+from pandas.testing import assert_frame_equal
+import pandas as pd
+from CountriesColumnAdder import CountriesColumnAdder
+
+class CountriesColumnAdderTest(unittest.TestCase):
+    
+    def test_addCountriesColumn(self):
+        # Given
+        countriesByBatchcodeTable = TestHelper.createDataFrame(
+            columns = ['United States', 'Germany', 'Italy'],
+            data = [  [20,              0,         3]],
+            index = pd.Index(
+                    name = 'Batchcode',
+                    data = ['FE6208']))
+        columnName = 'Countries guessed'
+
+        # When
+        countriesByBatchcodeTableWithCountriesColumn = CountriesColumnAdder().addCountriesColumn(countriesByBatchcodeTable, columnName)
+
+        # Then
+        assert_frame_equal(
+            countriesByBatchcodeTableWithCountriesColumn,
+            TestHelper.createDataFrame(
+                columns = ['United States', 'Germany', 'Italy', columnName],
+                data = [  [20,              0,         3,       {'United States', 'Italy'}]],
+                index = pd.Index(
+                        name = 'Batchcode',
+                        data = ['FE6208'])))
+        

src/CountriesMerger.py

@@ -0,0 +1,15 @@
+import pandas as pd
+
+
+class CountriesMerger:
+
+    @staticmethod
+    def mergeSrcIntoDst(src: pd.Series, dst: pd.Series):
+        def merge(series):
+            return sorted(set().union(*series.dropna()))
+        
+        mergedSeries = (pd
+                        .merge(dst, src, how='left', left_index=True, right_index=True)
+                        .apply(merge, axis='columns'))
+        mergedSeries.name = dst.name
+        return mergedSeries

src/CountriesMergerTest.py

@@ -0,0 +1,25 @@
+import unittest
+import pandas as pd
+from CountriesMerger import CountriesMerger
+from pandas.testing import assert_series_equal
+
+
+class CountriesMergerTest(unittest.TestCase):
+
+    def test_mergeSrcIntoDst(self):
+        # Given
+        dstCountries = pd.Series({'NO72A': ['CountryA-1'], 'EW096': ['CountryA-2']}, name='dstCountries')
+        srcCountries = pd.Series({'NO72A': ['CountryB-1'], 'FS192': ['CountryB-2']}, name='srcCountries')
+
+        # When
+        mergedCountries = CountriesMerger.mergeSrcIntoDst(src = srcCountries, dst = dstCountries)
+
+        # Then
+        assert_series_equal(
+            mergedCountries,
+            pd.Series(
+                {
+                    'NO72A': ['CountryA-1', 'CountryB-1'],
+                    'EW096': ['CountryA-2']
+                },
+                name=dstCountries.name))

src/SmartRegexpFactory.py

@@ -0,0 +1,19 @@
+import re
+
+
+# adapted from function _fnFilterCreateSearch() defined in https://github.com/DataTables/DataTablesSrc/blob/master/js/core/core.filter.js
+class SmartRegexpFactory:
+
+    def createSmartRegexp(self, searchTerm):
+        return re.compile(
+            rf'^{self.assertContainsWords(self.getWords(searchTerm))}.*$',
+            flags=re.IGNORECASE)
+
+    def getWords(self, 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])
+
+    def assertContainsWord(self, word):
+        return f'(?=.*?{word})'

src/SmartRegexpFactoryTest.py

@@ -0,0 +1,20 @@
+import unittest
+from SmartRegexpFactory import SmartRegexpFactory
+
+
+class SmartRegexpFactoryTest(unittest.TestCase):
+
+    def test_smartSearch(self):
+        def smartSearch(searchTerm, str):
+            smartRegexp = SmartRegexpFactory().createSmartRegexp(searchTerm)
+            return bool(smartRegexp.match(str))
+
+        self.assertTrue(smartSearch(searchTerm = 'one two three', str = 'one two three'))
+        self.assertTrue(smartSearch(searchTerm = 'one two three', str = 'ONE two ThReE'))
+        self.assertFalse(smartSearch(searchTerm = 'one two three', str = 'one two'))
+        self.assertFalse(smartSearch(searchTerm = 'one two three', str = 'three two'))
+        self.assertTrue(smartSearch(searchTerm = 'one two three', str = 'three two one'))
+        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?'))

src/data/Selected Country.csv

@@ -0,0 +1,91 @@
+# ----------------------------------------
+# HowBadIsMyBatch
+# Batchcode By Country-Selected Country
+# 20230201-20230401
+# ----------------------------------------
+
+Country,United States,Germany,Canada,United Kingdom,Italy,Japan,Romania,Australia,Austria,Poland,Hungary,France,Netherlands,Switzerland,Brazil,Spain,Sweden,Singapore,Argentina,Portugal,Totals
+Item ID,Active users,Active users,Active users,Active users,Active users,Active users,Active users,Active users,Active users,Active users,Active users,Active users,Active users,Active users,Active users,Active users,Active users,Active users,Active users,Active users,Active users
+,1734,542,264,237,156,89,114,75,54,51,51,38,38,25,14,28,26,4,19,17,3817,Grand total
+Global,1730,538,261,237,156,88,114,75,54,51,50,38,38,25,14,28,26,4,19,17,3804
+United States,327,4,3,2,4,3,0,1,2,0,0,0,0,0,0,1,0,1,1,0,352
+Germany,0,137,0,1,6,1,0,0,6,2,1,1,0,0,0,2,0,1,0,1,163
+Canada,2,1,59,0,1,1,0,0,0,0,0,0,0,0,1,0,0,1,0,0,67
+Australia,0,1,1,0,1,1,0,23,1,1,0,0,0,0,0,0,0,0,0,0,31
+Japan,0,1,0,0,2,18,0,0,0,0,0,0,0,0,1,0,0,0,0,0,23
+Switzerland,0,3,1,1,1,0,0,0,0,0,0,0,0,11,0,0,1,1,0,0,19
+Unknown Country,3,1,0,9,2,0,0,1,0,0,0,0,0,0,0,1,1,0,0,0,19
+Israel,0,1,1,1,3,1,0,0,2,0,0,0,0,0,0,0,0,1,0,0,15
+New Zealand,1,0,1,1,0,1,0,0,0,0,0,0,1,0,1,0,0,1,0,0,12
+Philippines,1,0,1,0,0,0,0,1,0,0,0,0,0,0,0,0,0,1,0,0,10
+Brazil,0,4,0,0,0,1,1,0,0,0,0,0,0,0,1,0,0,0,0,1,8
+Argentina,0,1,0,0,1,0,0,0,0,1,0,0,0,0,0,0,0,0,4,0,7
+China,0,2,1,0,0,2,0,0,0,0,0,0,0,0,0,0,0,0,0,0,7
+India,0,1,1,0,1,1,0,0,0,0,1,0,0,0,0,0,0,1,0,0,7
+Norway,0,0,1,1,0,0,0,0,1,0,0,0,0,0,0,0,0,1,0,0,7
+Afghanistan,1,2,0,0,1,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,6
+Mexico,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,1,0,1,6
+"Iran, Islamic Republic of",0,2,1,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,5
+Malaysia,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,5
+Peru,0,0,1,0,1,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,5
+Albania,0,3,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,4
+Bahamas,0,1,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,4
+Costa Rica,0,0,1,0,1,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,4
+Hong Kong,0,1,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,1,0,1,4
+Nepal,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,4
+Thailand,1,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,4
+Ukraine,1,0,1,1,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,4
+Uruguay,2,0,0,0,0,0,0,0,0,1,0,0,0,0,0,1,0,0,0,0,4
+"Venezuela, Bolivarian Republic of",2,0,0,0,0,1,0,0,0,1,0,0,0,0,0,0,0,0,0,0,4
+Viet Nam,1,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,4
+Andorra,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,3
+Chile,1,1,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,3
+Colombia,0,1,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,3
+French Polynesia,0,0,0,0,0,0,0,0,0,0,0,3,0,0,0,0,0,0,0,0,3
+Indonesia,0,0,0,0,0,0,0,0,0,0,0,1,0,0,1,0,0,1,0,0,3
+"Korea, Republic of",0,0,1,0,0,1,0,0,0,0,0,0,0,0,1,0,0,0,0,0,3
+South Africa,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,3
+Algeria,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,1,0,0,0,0,2
+Bahrain,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,2
+Bosnia and Herzegovina,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,2
+Cayman Islands,0,0,2,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,2
+Côte d'Ivoire,0,1,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,2
+Dominican Republic,0,0,0,0,0,0,0,0,1,0,0,0,0,0,1,0,0,0,0,0,2
+Egypt,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,2
+Guatemala,0,1,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,2
+"Korea, Democratic People's Republic of",0,0,0,1,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,2
+Mauritius,0,1,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,2
+"Moldova, Republic of",1,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,2
+Nigeria,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,1,0,0,2
+Pakistan,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,2
+Russian Federation,0,0,0,0,0,0,1,1,0,0,0,0,0,0,0,0,0,0,0,0,2
+Saudi Arabia,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,2
+Serbia,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,2
+Tunisia,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,2
+Turkey,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,2
+United Arab Emirates,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,2
+Azerbaijan,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1
+Bangladesh,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1
+Bermuda,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1
+Brunei Darussalam,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1
+Ecuador,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1
+El Salvador,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,1
+Georgia,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1
+Ghana,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,1
+Iraq,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1
+Jamaica,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1
+Jordan,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,1
+Kuwait,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,1
+Lesotho,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,1
+Liberia,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1
+Macao,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,1
+Mongolia,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1
+Morocco,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1
+Nicaragua,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1
+"Palestine, State of",0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1
+Paraguay,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1
+Réunion,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,1
+Singapore,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,1
+Sri Lanka,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,1
+"Tanzania, United Republic of",0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,1
+