{ "cells": [ { "cell_type": "code", "execution_count": null, "id": "9de5907f-18f5-4cb1-903e-26028ff1fa03", "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", "import pandas as pd\n", "\n", "pd.set_option('display.max_rows', 100)\n", "pd.set_option('display.max_columns', None)" ] }, { "cell_type": "code", "execution_count": null, "id": "a271254b", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "\n", "class VaersDescrReader:\n", " \n", " def __init__(self, dataDir):\n", " self.dataDir = dataDir \n", "\n", " def readAllVaersDescrs(self):\n", " return self.readVaersDescrs([\"2021\", \"2022\"])\n", " \n", " def readVaersDescrs(self, years):\n", " return [self.readVaersDescr(year) for year in years]\n", "\n", " def readVaersDescr(self, year):\n", " folder = self.dataDir + \"/\" + year + \"VAERSData/\"\n", " return {\n", " 'VAERSDATA': self._readVAERSDATA(folder + year + \"VAERSDATA.csv\"),\n", " 'VAERSVAX': self._readVAERSVAX(folder + year + \"VAERSVAX.csv\")\n", " }\n", "\n", " def readNonDomesticVaersDescr(self):\n", " folder = self.dataDir + \"/NonDomesticVAERSData/\"\n", " return {\n", " 'VAERSDATA': self._readVAERSDATA(folder + \"NonDomesticVAERSDATA.csv\"),\n", " 'VAERSVAX': self._readVAERSVAX(folder + \"NonDomesticVAERSVAX.csv\")\n", " }\n", "\n", " def _readVAERSDATA(self, file):\n", " return self._read_csv(\n", " file = file,\n", " usecols = ['VAERS_ID', 'RECVDATE', 'DIED', 'L_THREAT', 'DISABLE', 'HOSPITAL', 'ER_VISIT', 'SPLTTYPE'],\n", " parse_dates = ['RECVDATE'],\n", " date_parser = lambda dateStr: pd.to_datetime(dateStr, format = \"%m/%d/%Y\"))\n", "\n", " def _readVAERSVAX(self, file):\n", " return self._read_csv(\n", " file = file,\n", " usecols = ['VAERS_ID', 'VAX_DOSE_SERIES', 'VAX_TYPE', 'VAX_MANU', 'VAX_LOT'],\n", " dtype = {\"VAX_DOSE_SERIES\": \"string\"})\n", "\n", " def _read_csv(self, file, **kwargs):\n", " return pd.read_csv(\n", " file,\n", " index_col = 'VAERS_ID',\n", " encoding = 'latin1',\n", " low_memory = False,\n", " **kwargs)\n" ] }, { "cell_type": "code", "execution_count": null, "id": "7b5d6df0", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "\n", "class VaersDescr2DataFrameConverter:\n", "\n", " @staticmethod\n", " def createDataFrameFromDescr(vaersDescr):\n", " return pd.merge(\n", " vaersDescr['VAERSDATA'],\n", " vaersDescr['VAERSVAX'],\n", " how = 'left',\n", " left_index = True,\n", " right_index = True,\n", " validate = 'one_to_many')\n", "\n", " @staticmethod\n", " def createDataFrameFromDescrs(vaersDescrs):\n", " dataFrames = [VaersDescr2DataFrameConverter.createDataFrameFromDescr(vaersDescr) for vaersDescr in vaersDescrs]\n", " return pd.concat(dataFrames)\n" ] }, { "cell_type": "code", "execution_count": null, "id": "6b639196", "metadata": {}, "outputs": [], "source": [ "class DataFrameNormalizer:\n", " \n", " @staticmethod\n", " def normalize(dataFrame):\n", " DataFrameNormalizer.convertVAX_LOTColumnToUpperCase(dataFrame)\n", " DataFrameNormalizer._convertColumnsOfDataFrameToNumerics(\n", " dataFrame,\n", " ['DIED', 'L_THREAT', 'DISABLE', 'HOSPITAL', 'ER_VISIT'])\n", "\n", " @staticmethod\n", " def convertVAX_LOTColumnToUpperCase(dataFrame):\n", " dataFrame['VAX_LOT'] = dataFrame['VAX_LOT'].str.upper()\n", "\n", " @staticmethod\n", " def _convertColumnsOfDataFrameToNumerics(dataFrame, columns):\n", " for column in columns:\n", " DataFrameNormalizer._convertColumnOfDataFrameToNumeric(dataFrame, column)\n", "\n", " @staticmethod\n", " def _convertColumnOfDataFrameToNumeric(dataFrame, column):\n", " dataFrame[column] = DataFrameNormalizer._where(\n", " condition = dataFrame[column] == 'Y',\n", " trueValue = 1,\n", " falseValue = 0)\n", "\n", " @staticmethod\n", " def _where(condition, trueValue, falseValue):\n", " return np.where(condition, trueValue, falseValue) \n", " " ] }, { "cell_type": "code", "execution_count": null, "id": "3ebcba86", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "\n", "class DataFrameFilter:\n", " \n", " def filterByCovid19(self, dataFrame):\n", " return dataFrame[self._isCovid19(dataFrame)]\n", "\n", " def filterBy(self, dataFrame, manufacturer = None, dose = None):\n", " return dataFrame[self._isManufacturer(dataFrame, manufacturer) & self._isDose(dataFrame, dose)]\n", "\n", " def _isCovid19(self, dataFrame):\n", " return dataFrame[\"VAX_TYPE\"] == \"COVID19\"\n", "\n", " def _isManufacturer(self, dataFrame, manufacturer):\n", " return dataFrame[\"VAX_MANU\"] == manufacturer if manufacturer is not None else True\n", "\n", " def _isDose(self, dataFrame, dose):\n", " return dataFrame[\"VAX_DOSE_SERIES\"].str.contains(dose) if dose is not None else True\n" ] }, { "cell_type": "code", "execution_count": null, "id": "c62cfaff", "metadata": {}, "outputs": [], "source": [ "class AggregationHelper:\n", "\n", " @staticmethod\n", " def aggregateAndFlattenColumnsAndRenameColumns(groupBy, aggFunctionsByColumn, columnNameMappingsDict):\n", " aggregatedDataFrame = groupBy.agg(aggFunctionsByColumn)\n", " AggregationHelper._flattenColumns(aggregatedDataFrame)\n", " return aggregatedDataFrame.rename(columns = columnNameMappingsDict)\n", "\n", " @staticmethod\n", " def _flattenColumns(dataFrame):\n", " dataFrame.columns = [\"_\".join(a) for a in dataFrame.columns.to_flat_index()]\n" ] }, { "cell_type": "code", "execution_count": null, "id": "99945ca8", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "\n", "class BatchCodeTableHelper:\n", " \n", " def __init__(self, dataFrame : pd.DataFrame):\n", " self.dataFrame = dataFrame\n", "\n", " # create table from https://www.howbadismybatch.com/combined.html\n", " def createSevereEffectsBatchCodeTable(self):\n", " batchCodeTable = BatchCodeTableHelper.createSummationTable(self.dataFrame.groupby('VAX_LOT'))\n", " batchCodeTable = batchCodeTable[['ADRs', 'DEATHS', 'DISABILITIES', 'LIFE THREATENING ILLNESSES', 'HOSPITALISATIONS', 'EMERGENCY ROOM OR DOCTOR VISITS']]\n", " batchCodeTable = batchCodeTable.sort_values(by = 'ADRs', ascending = False)\n", " return self._addCompanyColumn(batchCodeTable, self._createCompanyByBatchCodeTable())\n", "\n", " @staticmethod\n", " def createSummationTable(\n", " groupBy,\n", " # FK-TODO: rename \"ADRs\" and \"Total reports\" to \"Total Number of Adverse Reaction Reports\" in all places\n", " columnNameMappingsDict = {\n", " \"DIED_size\": \"ADRs\",\n", " \"DIED_sum\": \"DEATHS\",\n", " \"L_THREAT_sum\": \"LIFE THREATENING ILLNESSES\",\n", " \"DISABLE_sum\": \"DISABILITIES\",\n", " 'HOSPITAL_sum': 'HOSPITALISATIONS',\n", " 'ER_VISIT_sum': 'EMERGENCY ROOM OR DOCTOR VISITS'\n", " }):\n", " return AggregationHelper.aggregateAndFlattenColumnsAndRenameColumns(\n", " groupBy = groupBy,\n", " aggFunctionsByColumn = {\n", " 'DIED': ['sum', 'size'],\n", " 'L_THREAT': 'sum',\n", " 'DISABLE': 'sum',\n", " 'HOSPITAL': 'sum',\n", " 'ER_VISIT': 'sum'\n", " },\n", " columnNameMappingsDict = columnNameMappingsDict)\n", "\n", " def _addCompanyColumn(self, batchCodeTable, companyByBatchCodeTable):\n", " return pd.merge(\n", " batchCodeTable,\n", " companyByBatchCodeTable,\n", " how = 'left',\n", " left_index = True,\n", " right_index = True,\n", " validate = 'one_to_one')\n", "\n", " def _createCompanyByBatchCodeTable(self):\n", " return self._createManufacturerByBatchCodeTable().rename(columns = {\"VAX_MANU\": \"COMPANY\"})\n", "\n", " def _createManufacturerByBatchCodeTable(self):\n", " manufacturerByBatchCodeTable = self.dataFrame[['VAX_LOT', 'VAX_MANU']]\n", " manufacturerByBatchCodeTable = manufacturerByBatchCodeTable.drop_duplicates(subset = ['VAX_LOT'])\n", " return manufacturerByBatchCodeTable.set_index('VAX_LOT')\n", "\n", "\n", "class BatchCodeTableFactory:\n", "\n", " @staticmethod\n", " def createBatchCodeTable(dataFrame : pd.DataFrame, manufacturer, dose):\n", " dataFrame = DataFrameFilter().filterByCovid19(dataFrame)\n", " dataFrame = DataFrameFilter().filterBy(dataFrame, manufacturer = manufacturer, dose = dose)\n", " return BatchCodeTableHelper(dataFrame).createSevereEffectsBatchCodeTable()[['ADRs', 'DEATHS', 'DISABILITIES', 'LIFE THREATENING ILLNESSES']]\n", "\n", " # create table from https://www.howbadismybatch.com/combined.html\n", " @staticmethod\n", " def createSevereEffectsBatchCodeTable(dataFrame : pd.DataFrame, dose):\n", " dataFrame = DataFrameFilter().filterByCovid19(dataFrame)\n", " dataFrame = DataFrameFilter().filterBy(dataFrame, dose = dose)\n", " return BatchCodeTableHelper(dataFrame).createSevereEffectsBatchCodeTable()\n" ] }, { "cell_type": "code", "execution_count": null, "id": "41d4fa30", "metadata": {}, "outputs": [], "source": [ "class DoseAnalysis:\n", " \n", " @staticmethod\n", " def getDoseTable(dataFrame):\n", " dataFrame = DataFrameFilter().filterByCovid19(dataFrame)\n", " return DoseAnalysis._getDoseTable(\n", " dataFrame.groupby(\n", " dataFrame['VAX_DOSE_SERIES'].rename('Dose')))\n", "\n", " @staticmethod\n", " def getDoseByMonthTable(dataFrame):\n", " dataFrame = DataFrameFilter().filterByCovid19(dataFrame)\n", " return DoseAnalysis._getDoseTable(\n", " dataFrame.groupby(\n", " [\n", " dataFrame['RECVDATE'].dt.year.rename('Year'),\n", " dataFrame['RECVDATE'].dt.month.rename('Month'),\n", " dataFrame['VAX_DOSE_SERIES'].rename('Dose')\n", " ]))\n", "\n", " # FK-TODO: DRY because it generates a subset of BatchCodeTableHelper.createSevereEffectsBatchCodeTable()\n", " @staticmethod\n", " def _getDoseTable(dataFrame):\n", " doseTable = BatchCodeTableHelper.createSummationTable(\n", " dataFrame,\n", " columnNameMappingsDict = {\n", " \"DIED_size\": \"Total reports\",\n", " \"DIED_sum\": \"Deaths\",\n", " \"L_THREAT_sum\": \"Life Threatening Illnesses\",\n", " \"DISABLE_sum\": \"Disabilities\"\n", " })\n", " doseTable = doseTable[['Total reports', 'Deaths', 'Disabilities', 'Life Threatening Illnesses']]\n", " doseTable['Severe reports (%)'] = (doseTable['Deaths'] + doseTable['Disabilities'] + doseTable['Life Threatening Illnesses']) / doseTable['Total reports'] * 100\n", " return doseTable\n" ] }, { "cell_type": "code", "execution_count": null, "id": "09e6b511", "metadata": {}, "outputs": [], "source": [ "import pycountry\n", "\n", "class InternationalLotAnalysis:\n", " \n", " @staticmethod\n", " def getInternationalLotTable(dataFrame):\n", " dataFrame = DataFrameFilter().filterByCovid19(dataFrame)\n", " internationalLotTable = InternationalLotAnalysis._getInternationalLotTable(dataFrame)\n", " return internationalLotTable.sort_values(by = 'Severe reports (%)', ascending = False)\n", "\n", " @staticmethod\n", " def _getInternationalLotTable(dataFrame):\n", " countryColumnName = 'Country'\n", " InternationalLotAnalysis._addCountryColumn(dataFrame, countryColumnName = countryColumnName)\n", " return DoseAnalysis._getDoseTable(dataFrame.groupby(dataFrame[countryColumnName]))\n", "\n", " @staticmethod\n", " def _addCountryColumn(dataFrame, countryColumnName):\n", " dataFrame[countryColumnName] = dataFrame.apply(\n", " lambda row:\n", " InternationalLotAnalysis._getCountryNameOfSplttypeOrDefault(\n", " splttype = row['SPLTTYPE'],\n", " default = 'Unknown Country'),\n", " axis = 'columns')\n", "\n", " @staticmethod\n", " def _getCountryNameOfSplttypeOrDefault(splttype, default):\n", " if not isinstance(splttype, str):\n", " return default\n", " \n", " country = pycountry.countries.get(alpha_2 = splttype[:2])\n", " return country.name if country is not None else default\n" ] }, { "cell_type": "code", "execution_count": null, "id": "3dacedfd", "metadata": {}, "outputs": [], "source": [ "import unittest" ] }, { "cell_type": "code", "execution_count": null, "id": "fcc855dd", "metadata": {}, "outputs": [], "source": [ "class TestHelper:\n", "\n", " @staticmethod\n", " def createDataFrame(index, columns, data, dtypes = {}):\n", " return pd.DataFrame(index = index, columns = columns, data = data).astype(dtypes)\n" ] }, { "cell_type": "code", "execution_count": null, "id": "ccb9838d", "metadata": {}, "outputs": [], "source": [ "from pandas.testing import assert_frame_equal\n", "\n", "class DataFrameNormalizerTest(unittest.TestCase):\n", "\n", " def test_convertVAX_LOTColumnToUpperCase(self):\n", " # Given\n", " dataFrame = TestHelper.createDataFrame(\n", " columns = ['VAX_LOT'],\n", " data = [ ['037K20A'],\n", " ['025l20A'],\n", " ['025L20A']],\n", " index = [\n", " \"0916600\",\n", " \"0916601\",\n", " \"1996874\"])\n", " \n", " # When\n", " DataFrameNormalizer.convertVAX_LOTColumnToUpperCase(dataFrame)\n", " \n", " # Then\n", " dataFrameExpected = TestHelper.createDataFrame(\n", " columns = ['VAX_LOT'],\n", " data = [ ['037K20A'],\n", " ['025L20A'],\n", " ['025L20A']],\n", " index = [\n", " \"0916600\",\n", " \"0916601\",\n", " \"1996874\"])\n", " assert_frame_equal(dataFrame, dataFrameExpected, check_dtype = False)\n" ] }, { "cell_type": "code", "execution_count": null, "id": "e59a1825", "metadata": {}, "outputs": [], "source": [ "from pandas.testing import assert_frame_equal\n", "\n", "class DataFrameFilterTest(unittest.TestCase):\n", "\n", " def test_filterByCovid19_filterBy(self):\n", " # Given\n", " dataFrame = VaersDescr2DataFrameConverter.createDataFrameFromDescrs(\n", " [\n", " {\n", " 'VAERSDATA': TestHelper.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE'],\n", " data = [ [1, 0, 0],\n", " [0, 0, 1]],\n", " index = [\n", " \"0916600\",\n", " \"0916601\"]),\n", " 'VAERSVAX': TestHelper.createDataFrame(\n", " columns = ['VAX_TYPE', 'VAX_MANU', 'VAX_LOT', 'VAX_DOSE_SERIES'],\n", " data = [ ['COVID19', 'MODERNA', '037K20A', '1'],\n", " ['COVID19', 'MODERNA', '025L20A', '1']],\n", " index = [\n", " \"0916600\",\n", " \"0916601\"],\n", " dtypes = {'VAX_DOSE_SERIES': \"string\"})\n", " },\n", " {\n", " 'VAERSDATA': TestHelper.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE'],\n", " data = [ [0, 0, 0],\n", " [0, 0, 1]],\n", " index = [\n", " \"1996873\",\n", " \"1996874\"]),\n", " 'VAERSVAX': TestHelper.createDataFrame(\n", " columns = ['VAX_TYPE', 'VAX_MANU', 'VAX_LOT', 'VAX_DOSE_SERIES'],\n", " data = [ ['HPV9', 'MERCK & CO. INC.', 'R017624', 'UNK'],\n", " ['COVID19', 'MODERNA', '025L20A', '1']],\n", " index = [\n", " \"1996873\",\n", " \"1996874\"],\n", " dtypes = {'VAX_DOSE_SERIES': \"string\"})\n", " }\n", " ])\n", " dataFrameFilter = DataFrameFilter()\n", " \n", " # When\n", " dataFrame = dataFrameFilter.filterByCovid19(dataFrame)\n", " dataFrame = dataFrameFilter.filterBy(dataFrame, manufacturer = \"MODERNA\", dose = '1')\n", " \n", " # Then\n", " dataFrameExpected = TestHelper.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE', 'VAX_TYPE', 'VAX_MANU', 'VAX_LOT', 'VAX_DOSE_SERIES'],\n", " data = [ [1, 0, 0, 'COVID19', 'MODERNA', '037K20A', '1'],\n", " [0, 0, 1, 'COVID19', 'MODERNA', '025L20A', '1'],\n", " [0, 0, 1, 'COVID19', 'MODERNA', '025L20A', '1']],\n", " index = [\n", " \"0916600\",\n", " \"0916601\",\n", " \"1996874\"],\n", " dtypes = {'VAX_DOSE_SERIES': \"string\"})\n", " assert_frame_equal(dataFrame, dataFrameExpected, check_dtype = False)\n", "\n", " def test_filterByDose(self):\n", " # Given\n", " dataFrame = VaersDescr2DataFrameConverter.createDataFrameFromDescrs(\n", " [\n", " {\n", " 'VAERSDATA': TestHelper.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE', 'HOSPITAL', 'ER_VISIT'],\n", " data = [ [1, 1, 0, 1, 1],\n", " [0, 0, 1, 0, 1]],\n", " index = [\n", " \"0916600\",\n", " \"0916601\"]),\n", " 'VAERSVAX': TestHelper.createDataFrame(\n", " columns = ['VAX_TYPE', 'VAX_MANU', 'VAX_LOT', 'VAX_DOSE_SERIES'],\n", " data = [ ['COVID19', 'MODERNA', '037K20A', '1'],\n", " ['COVID19', 'PFIZER\\BIONTECH', '025L20A', '1']],\n", " index = [\n", " \"0916600\",\n", " \"0916601\"],\n", " dtypes = {'VAX_DOSE_SERIES': \"string\"})\n", " }\n", " ])\n", " dataFrameFilter = DataFrameFilter()\n", " dataFrame = dataFrameFilter.filterByCovid19(dataFrame)\n", "\n", " # When\n", " dataFrame = dataFrameFilter.filterBy(dataFrame, dose = '1')\n", " \n", " # Then\n", " dataFrameExpected = TestHelper.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE', 'HOSPITAL', 'ER_VISIT', 'VAX_TYPE', 'VAX_MANU', 'VAX_LOT', 'VAX_DOSE_SERIES'],\n", " data = [ [1, 1, 0, 1, 1, 'COVID19', 'MODERNA', '037K20A', '1'],\n", " [0, 0, 1, 0, 1, 'COVID19', 'PFIZER\\BIONTECH', '025L20A', '1']],\n", " index = [\n", " \"0916600\",\n", " \"0916601\"],\n", " dtypes = {'VAX_DOSE_SERIES': \"string\"})\n", " assert_frame_equal(dataFrame, dataFrameExpected, check_dtype = False)\n", "\n", " def test_filterByFirstDose(self):\n", " # Given\n", " dataFrame = VaersDescr2DataFrameConverter.createDataFrameFromDescrs(\n", " [\n", " {\n", " 'VAERSDATA': TestHelper.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE'],\n", " data = [ [1, 0, 0]],\n", " index = [\n", " \"1048786\"]),\n", " 'VAERSVAX': TestHelper.createDataFrame(\n", " columns = ['VAX_TYPE', 'VAX_MANU', 'VAX_LOT', 'VAX_DOSE_SERIES'],\n", " data = [ ['COVID19', 'MODERNA', '016M20A', '2'],\n", " ['COVID19', 'MODERNA', '030L20A', '1']],\n", " index = [\n", " \"1048786\",\n", " \"1048786\"],\n", " dtypes = {'VAX_DOSE_SERIES': \"string\"})\n", " }\n", " ])\n", " dataFrameFilter = DataFrameFilter()\n", " \n", " # When\n", " dataFrame = dataFrameFilter.filterByCovid19(dataFrame)\n", " dataFrame = dataFrameFilter.filterBy(dataFrame, manufacturer = \"MODERNA\", dose = '1')\n", " \n", " # Then\n", " dataFrameExpected = TestHelper.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE', 'VAX_TYPE', 'VAX_MANU', 'VAX_LOT', 'VAX_DOSE_SERIES'],\n", " data = [ [1, 0, 0, 'COVID19', 'MODERNA', '030L20A', '1']],\n", " index = [\n", " \"1048786\"],\n", " dtypes = {'VAX_DOSE_SERIES': \"string\"})\n", " assert_frame_equal(dataFrame, dataFrameExpected, check_dtype = False)\n", "\n", " def test_filterBySecondDose(self):\n", " # Given\n", " dataFrame = VaersDescr2DataFrameConverter.createDataFrameFromDescrs(\n", " [\n", " {\n", " 'VAERSDATA': TestHelper.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE'],\n", " data = [ [1, 0, 0]],\n", " index = [\n", " \"1048786\"]),\n", " 'VAERSVAX': TestHelper.createDataFrame(\n", " columns = ['VAX_TYPE', 'VAX_MANU', 'VAX_LOT', 'VAX_DOSE_SERIES'],\n", " data = [ ['COVID19', 'MODERNA', '016M20A', '2'],\n", " ['COVID19', 'MODERNA', '030L20A', '1']],\n", " index = [\n", " \"1048786\",\n", " \"1048786\"],\n", " dtypes = {'VAX_DOSE_SERIES': \"string\"})\n", " }\n", " ])\n", " dataFrameFilter = DataFrameFilter()\n", "\n", " # When\n", " dataFrame = dataFrameFilter.filterByCovid19(dataFrame)\n", " dataFrame = dataFrameFilter.filterBy(dataFrame, manufacturer = \"MODERNA\", dose = '2')\n", " \n", " # Then\n", " dataFrameExpected = TestHelper.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE', 'VAX_TYPE', 'VAX_MANU', 'VAX_LOT', 'VAX_DOSE_SERIES'],\n", " data = [ [1, 0, 0, 'COVID19', 'MODERNA', '016M20A', '2']],\n", " index = [\n", " \"1048786\"],\n", " dtypes = {'VAX_DOSE_SERIES': \"string\"})\n", " assert_frame_equal(dataFrame, dataFrameExpected, check_dtype = False)\n" ] }, { "cell_type": "code", "execution_count": null, "id": "e14465d7", "metadata": {}, "outputs": [], "source": [ "from pandas.testing import assert_frame_equal\n", "\n", "class BatchCodeTableFactoryTest(unittest.TestCase):\n", "\n", " def testcreateSummationTable(self):\n", " # Given\n", " dataFrame = VaersDescr2DataFrameConverter.createDataFrameFromDescrs(\n", " [\n", " {\n", " 'VAERSDATA': TestHelper.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE', 'HOSPITAL', 'ER_VISIT'],\n", " data = [ [1, 1, 0, 1, 1],\n", " [0, 0, 1, 0, 1]],\n", " index = [\n", " \"0916600\",\n", " \"0916601\"]),\n", " 'VAERSVAX': TestHelper.createDataFrame(\n", " columns = ['VAX_TYPE', 'VAX_MANU', 'VAX_LOT', 'VAX_DOSE_SERIES'],\n", " data = [ ['COVID19', 'MODERNA', '037K20A', '1'],\n", " ['COVID19', 'PFIZER\\BIONTECH', '025L20A', '1']],\n", " index = [\n", " \"0916600\",\n", " \"0916601\"],\n", " dtypes = {'VAX_DOSE_SERIES': \"string\"})\n", " }\n", " ])\n", "\n", " # When\n", " batchCodeTable = BatchCodeTableFactory.createSevereEffectsBatchCodeTable(dataFrame, '1')\n", "\n", " # Then\n", " batchCodeTableExpected = pd.DataFrame(\n", " data = {\n", " 'ADRs': [1, 1],\n", " 'DEATHS': [0, 1],\n", " 'DISABILITIES': [1, 0],\n", " 'LIFE THREATENING ILLNESSES': [0, 1],\n", " 'HOSPITALISATIONS': [0, 1],\n", " 'EMERGENCY ROOM OR DOCTOR VISITS': [1, 1],\n", " 'COMPANY': ['PFIZER\\BIONTECH', 'MODERNA']\n", " },\n", " index = pd.Index(['025L20A', '037K20A'], name = 'VAX_LOT'))\n", " assert_frame_equal(batchCodeTable, batchCodeTableExpected, check_dtype = False)\n", "\n", " def test_createBatchCodeTable2(self):\n", " dataFrame = VaersDescr2DataFrameConverter.createDataFrameFromDescrs(\n", " [\n", " {\n", " 'VAERSDATA': TestHelper.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE', 'HOSPITAL', 'ER_VISIT'],\n", " data = [ [1, 0, 0, 0, 0],\n", " [0, 0, 1, 0, 0]],\n", " index = [\n", " \"0916600\",\n", " \"0916601\"]),\n", " 'VAERSVAX': TestHelper.createDataFrame(\n", " columns = ['VAX_TYPE', 'VAX_MANU', 'VAX_LOT', 'VAX_DOSE_SERIES'],\n", " data = [ ['COVID19', 'MODERNA', '037K20A', '1'],\n", " ['COVID19', 'MODERNA', '025L20A', '1']],\n", " index = [\n", " \"0916600\",\n", " \"0916601\"],\n", " dtypes = {'VAX_DOSE_SERIES': \"string\"})\n", " },\n", " {\n", " 'VAERSDATA': TestHelper.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE', 'HOSPITAL', 'ER_VISIT'],\n", " data = [ [0, 0, 0, 0, 0],\n", " [0, 0, 1, 0, 0]],\n", " index = [\n", " \"1996873\",\n", " \"1996874\"]),\n", " 'VAERSVAX': TestHelper.createDataFrame(\n", " columns = ['VAX_TYPE', 'VAX_MANU', 'VAX_LOT', 'VAX_DOSE_SERIES'],\n", " data = [ ['HPV9', 'MERCK & CO. INC.', 'R017624', 'UNK'],\n", " ['COVID19', 'MODERNA', '025L20A', '1']],\n", " index = [\n", " \"1996873\",\n", " \"1996874\"],\n", " dtypes = {'VAX_DOSE_SERIES': \"string\"})\n", " }\n", " ])\n", " self._test_createBatchCodeTable(dataFrame, \"MODERNA\", '1')\n", "\n", " def test_createBatchCodeTable(self):\n", " dataFrame = VaersDescr2DataFrameConverter.createDataFrameFromDescrs(\n", " VaersDescrReader(dataDir = \"test/VAERS\").readAllVaersDescrs())\n", " DataFrameNormalizer.normalize(dataFrame)\n", " self._test_createBatchCodeTable(dataFrame, \"MODERNA\", '1')\n", "\n", " def _test_createBatchCodeTable(self, dataFrame, manufacturer, dose):\n", " # When\n", " batchCodeTable = BatchCodeTableFactory.createBatchCodeTable(dataFrame, manufacturer, dose)\n", "\n", " # Then\n", " batchCodeTableExpected = pd.DataFrame(\n", " data = {\n", " 'ADRs': [2, 1],\n", " 'DEATHS': [0, 1],\n", " 'DISABILITIES': [2, 0],\n", " 'LIFE THREATENING ILLNESSES': [0, 0]\n", " },\n", " index = pd.Index(['025L20A', '037K20A'], name = 'VAX_LOT'))\n", " assert_frame_equal(batchCodeTable, batchCodeTableExpected, check_dtype = False)\n" ] }, { "cell_type": "code", "execution_count": null, "id": "44c121ec", "metadata": {}, "outputs": [], "source": [ "from pandas.testing import assert_frame_equal\n", "\n", "class DoseAnalysisTest(unittest.TestCase):\n", "\n", " def test_getDoseTable(self):\n", " # Given\n", " dataFrame = TestHelper.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE', 'VAX_TYPE', 'VAX_MANU', 'VAX_LOT', 'VAX_DOSE_SERIES', 'HOSPITAL', 'ER_VISIT'],\n", " data = [ [1, 0, 0, 'COVID19', 'MODERNA', '016M20A', '2', 0, 0],\n", " [1, 0, 0, 'COVID19', 'MODERNA', '030L20A', '1', 0, 0],\n", " [1, 1, 1, 'COVID19', 'MODERNA', '030L20B', '1', 0, 0]],\n", " index = [\n", " \"1048786\",\n", " \"1048786\",\n", " \"4711\"],\n", " dtypes = {'VAX_DOSE_SERIES': \"string\"})\n", " \n", " # When\n", " doseTable = DoseAnalysis.getDoseTable(dataFrame)\n", "\n", " # Then\n", " assert_frame_equal(\n", " doseTable,\n", " pd.DataFrame(\n", " data = {\n", " 'Total reports': [2, 1],\n", " 'Deaths': [2, 1],\n", " 'Disabilities': [1, 0],\n", " 'Life Threatening Illnesses': [1, 0],\n", " 'Severe reports (%)': [(2 + 1 + 1)/2 * 100, (1 + 0 + 0)/1 * 100]\n", " },\n", " index = pd.Index(['1', '2'], dtype = \"string\", name = 'Dose')))\n", " \n", " def test_getDoseByMonthTable(self):\n", " # Given\n", " parseDate = lambda dateStr: pd.to_datetime(dateStr, format = \"%m/%d/%Y\")\n", " dataFrame = TestHelper.createDataFrame(\n", " columns = ['RECVDATE', 'DIED', 'L_THREAT', 'DISABLE', 'VAX_TYPE', 'VAX_MANU', 'VAX_LOT', 'VAX_DOSE_SERIES', 'HOSPITAL', 'ER_VISIT'],\n", " data = [ [parseDate('01/01/2021'), 1, 0, 0, 'COVID19', 'MODERNA', '016M20A', '2', 0, 0],\n", " [parseDate('01/01/2021'), 1, 0, 0, 'COVID19', 'MODERNA', '030L20A', '1', 0, 0],\n", " [parseDate('01/01/2021'), 1, 1, 1, 'COVID19', 'MODERNA', '030L20B', '1', 0, 0]],\n", " index = [\n", " \"1048786\",\n", " \"1048786\",\n", " \"4711\"],\n", " dtypes = {'VAX_DOSE_SERIES': \"string\"})\n", " \n", " # When\n", " doseByMonthTable = DoseAnalysis.getDoseByMonthTable(dataFrame)\n", "\n", " # Then\n", " assert_frame_equal(\n", " doseByMonthTable,\n", " pd.DataFrame(\n", " data = {\n", " 'Total reports': [2, 1],\n", " 'Deaths': [2, 1],\n", " 'Disabilities': [1, 0],\n", " 'Life Threatening Illnesses': [1, 0],\n", " 'Severe reports (%)': [(2 + 1 + 1)/2 * 100, (1 + 0 + 0)/1 * 100]\n", " },\n", " index = pd.MultiIndex.from_tuples(\n", " [\n", " (2021, 1, '1'),\n", " (2021, 1, '2'),\n", " ],\n", " names = ('Year', 'Month', 'Dose'))),\n", " check_index_type = False)\n" ] }, { "cell_type": "code", "execution_count": null, "id": "c784bfef", "metadata": {}, "outputs": [], "source": [ "from pandas.testing import assert_frame_equal\n", "\n", "class InternationalLotAnalysisTest(unittest.TestCase):\n", "\n", " def test_getInternationalLotTable(self):\n", " # Given\n", " dataFrame = TestHelper.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE', 'VAX_TYPE', 'VAX_MANU', 'VAX_LOT', 'VAX_DOSE_SERIES', 'SPLTTYPE', 'HOSPITAL', 'ER_VISIT'],\n", " data = [ [1, 0, 0, 'COVID19', 'MODERNA', '016M20A', '2', 'GBPFIZER INC2020486806', 0, 0],\n", " [1, 0, 0, 'COVID19', 'MODERNA', '030L20A', '1', 'FRMODERNATX, INC.MOD20224', 0, 0],\n", " [1, 1, 1, 'COVID19', 'MODERNA', '030L20B', '1', 'FRMODERNATX, INC.MOD20224', 0, 0],\n", " [0, 0, 0, 'COVID19', 'MODERNA', '030L20B', '1', 'dummy'],\n", " [0, 0, 0, 'COVID19', 'MODERNA', '030L20B', '1', 123]],\n", " index = [\n", " \"1048786\",\n", " \"1048786\",\n", " \"4711\",\n", " \"0815\",\n", " \"0816\"])\n", " \n", " # When\n", " internationalLotTable = InternationalLotAnalysis.getInternationalLotTable(dataFrame)\n", "\n", " # Then\n", " assert_frame_equal(\n", " internationalLotTable,\n", " TestHelper.createDataFrame(\n", " columns = ['Total reports', 'Deaths', 'Disabilities', 'Life Threatening Illnesses', 'Severe reports (%)'],\n", " data = [ [2, 2, 1, 1, (2 + 1 + 1) / 2 * 100],\n", " [1, 1, 0, 0, (1 + 0 + 0) / 1 * 100],\n", " [2, 0, 0, 0, (0 + 0 + 0) / 2 * 100]],\n", " index = pd.Index(\n", " [\n", " 'France',\n", " 'United Kingdom',\n", " 'Unknown Country'\n", " ],\n", " name = 'Country')))\n" ] }, { "cell_type": "code", "execution_count": null, "id": "5a8bff1b", "metadata": {}, "outputs": [], "source": [ "unittest.main(argv = [''], verbosity = 2, exit = False)" ] }, { "cell_type": "code", "execution_count": null, "id": "86e0e4f2", "metadata": {}, "outputs": [], "source": [ "def saveBatchCodeTable(manufacturer, excelFile):\n", " vaersDescrs = VaersDescrReader(dataDir = \"VAERS\").readAllVaersDescrs()\n", " dataFrame = VaersDescr2DataFrameConverter.createDataFrameFromDescrs(vaersDescrs)\n", " DataFrameNormalizer.normalize(dataFrame)\n", " batchCodeTable = BatchCodeTableFactory.createBatchCodeTable(dataFrame, manufacturer = manufacturer, dose = '1')\n", " display(batchCodeTable)\n", " batchCodeTable.to_excel(excelFile)" ] }, { "cell_type": "markdown", "id": "987a04d1", "metadata": {}, "source": [ "### Moderna batch codes" ] }, { "cell_type": "code", "execution_count": null, "id": "ab170c16", "metadata": {}, "outputs": [], "source": [ "# https://www.howbadismybatch.com/moderna.html\n", "saveBatchCodeTable(\"MODERNA\", \"results/moderna.xlsx\")" ] }, { "cell_type": "markdown", "id": "29dd4daa", "metadata": {}, "source": [ "### Pfizer batch codes" ] }, { "cell_type": "code", "execution_count": null, "id": "6121e2b3", "metadata": {}, "outputs": [], "source": [ "# https://www.howbadismybatch.com/pfizer.html\n", "saveBatchCodeTable(\"PFIZER\\BIONTECH\", \"results/pfizer.xlsx\")" ] }, { "cell_type": "markdown", "id": "7e83a551", "metadata": {}, "source": [ "### Janssen batch codes " ] }, { "cell_type": "code", "execution_count": null, "id": "1a64eef5", "metadata": {}, "outputs": [], "source": [ "# https://www.howbadismybatch.com/janssen.html\n", "saveBatchCodeTable(\"JANSSEN\", \"results/janssen.xlsx\")" ] }, { "cell_type": "markdown", "id": "f677b620", "metadata": {}, "source": [ "### Short-list of 2000 batches having severe effects" ] }, { "cell_type": "code", "execution_count": null, "id": "bc56831d", "metadata": {}, "outputs": [], "source": [ "def saveSevereEffectsBatchCodeTable(excelFile):\n", " vaersDescrs = VaersDescrReader(dataDir = \"VAERS\").readAllVaersDescrs()\n", " dataFrame = VaersDescr2DataFrameConverter.createDataFrameFromDescrs(vaersDescrs)\n", " DataFrameNormalizer.normalize(dataFrame)\n", " severeEffectsBatchCodeTable = BatchCodeTableFactory.createSevereEffectsBatchCodeTable(dataFrame, dose = '1')\n", " display(severeEffectsBatchCodeTable)\n", " severeEffectsBatchCodeTable.to_excel(excelFile)" ] }, { "cell_type": "code", "execution_count": null, "id": "ace3fed9", "metadata": {}, "outputs": [], "source": [ "saveSevereEffectsBatchCodeTable('results/severeEffects.xlsx')" ] }, { "cell_type": "markdown", "id": "1b228a16", "metadata": {}, "source": [ "### Variation in Effect of First and Second Doses" ] }, { "cell_type": "code", "execution_count": null, "id": "202f7c3f", "metadata": {}, "outputs": [], "source": [ "# https://www.howbadismybatch.com/firstsecond.html\n", "\n", "def getDoseTable():\n", " vaersDescrs = VaersDescrReader(dataDir = \"VAERS\").readAllVaersDescrs()\n", " dataFrame = VaersDescr2DataFrameConverter.createDataFrameFromDescrs(vaersDescrs)\n", " DataFrameNormalizer.normalize(dataFrame)\n", " return DoseAnalysis.getDoseTable(dataFrame)\n", "\n", "def getDoseByMonthTable():\n", " vaersDescrs = VaersDescrReader(dataDir = \"VAERS\").readAllVaersDescrs()\n", " dataFrame = VaersDescr2DataFrameConverter.createDataFrameFromDescrs(vaersDescrs)\n", " DataFrameNormalizer.normalize(dataFrame)\n", " return DoseAnalysis.getDoseByMonthTable(dataFrame)" ] }, { "cell_type": "code", "execution_count": null, "id": "394fa19d", "metadata": {}, "outputs": [], "source": [ "getDoseTable()" ] }, { "cell_type": "code", "execution_count": null, "id": "b333e5fb", "metadata": {}, "outputs": [], "source": [ "doseByMonthTable = getDoseByMonthTable()\n", "doseByMonthTable.to_excel('results/doseByMonthTable.xlsx')\n", "doseByMonthTable" ] }, { "cell_type": "markdown", "id": "075aa6c9", "metadata": {}, "source": [ "### International Deadly Lots" ] }, { "cell_type": "code", "execution_count": null, "id": "8f8880f4", "metadata": {}, "outputs": [], "source": [ "# https://www.howbadismybatch.com/international.html\n", "\n", "def getInternationalLotTable():\n", " vaersDescr = VaersDescrReader(dataDir = 'VAERS').readNonDomesticVaersDescr()\n", " dataFrame = VaersDescr2DataFrameConverter.createDataFrameFromDescr(vaersDescr)\n", " DataFrameNormalizer.normalize(dataFrame)\n", " return InternationalLotAnalysis.getInternationalLotTable(dataFrame)\n" ] }, { "cell_type": "code", "execution_count": null, "id": "54e03231", "metadata": {}, "outputs": [], "source": [ "internationalLotTable = getInternationalLotTable()" ] }, { "cell_type": "code", "execution_count": null, "id": "7e80e958", "metadata": {}, "outputs": [], "source": [ "# FK-TODO: make filter on 'Total reports' a parameter in getInternationalLotTable() \n", "internationalLotTable = internationalLotTable[internationalLotTable['Total reports'] > 50]\n", "internationalLotTable.to_excel('results/International_Deadly_Lots.xlsx')\n", "internationalLotTable" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.9.7" } }, "nbformat": 4, "nbformat_minor": 5 }