{ "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':\n", " self._read_csv(\n", " folder + year + \"VAERSDATA.csv\",\n", " # FK-TODO: use Column enum\n", " ['VAERS_ID', 'DIED', 'L_THREAT', 'DISABLE', 'HOSPITAL', 'ER_VISIT']),\n", " 'VAERSVAX':\n", " self._read_csv(\n", " folder + year + \"VAERSVAX.csv\",\n", " ['VAERS_ID', 'VAX_DOSE_SERIES', 'VAX_TYPE', 'VAX_MANU', 'VAX_LOT'],\n", " dtype = {\"VAX_DOSE_SERIES\": \"string\"})\n", " }\n", "\n", " def _read_csv(self, file, usecols, dtype = {}):\n", " return pd.read_csv(\n", " file,\n", " index_col = 'VAERS_ID',\n", " encoding = 'latin1',\n", " low_memory = False,\n", " usecols = usecols,\n", " dtype = dtype)\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": "3ebcba86", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "\n", "class DataFrameFilter:\n", " \n", " def __init__(self, dataFrame):\n", " self.dataFrame = dataFrame \n", "\n", " def filterBy(self, manufacturer = None, dose = None):\n", " return self.dataFrame[self._isCovid19() & self._isManufacturer(manufacturer) & self._isDose(dose)]\n", "\n", " def filterForSevereEffects(self, dose):\n", " return self.filterBy(dose = dose)\n", "\n", " def _isCovid19(self):\n", " return self.dataFrame[\"VAX_TYPE\"] == \"COVID19\"\n", "\n", " def _isManufacturer(self, manufacturer):\n", " return self.dataFrame[\"VAX_MANU\"] == manufacturer if manufacturer is not None else True\n", "\n", " def _isDose(self, dose):\n", " return self.dataFrame[\"VAX_DOSE_SERIES\"].str.contains(dose) if dose is not None else True\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", " def createBatchCodeTable(self):\n", " return self._asDataFrame(\n", " {\n", " 'ADRs': self._getADRs(),\n", " 'DEATHS': self._getDEATHS(),\n", " 'DISABILITIES': self._getDISABILITIES(),\n", " 'LIFE THREATENING ILLNESSES': self._getLIFE_THREATENING_ILLNESSES()\n", " })\n", "\n", " # create table from https://www.howbadismybatch.com/combined.html\n", " def createSevereEffectsBatchCodeTable(self):\n", " return self._addCompanyColumn(\n", " self._asDataFrame(\n", " {\n", " 'ADRs': self._getADRs(),\n", " 'DEATHS': self._getDEATHS(),\n", " 'DISABILITIES': self._getDISABILITIES(),\n", " 'LIFE THREATENING ILLNESSES': self._getLIFE_THREATENING_ILLNESSES(),\n", " 'HOSPITALISATIONS': self._getHOSPITALISATIONS(),\n", " 'EMERGENCY ROOM OR DOCTOR VISITS': self._getER_VISITs()\n", " }),\n", " self._createCompanyByBatchCodeTable())\n", "\n", " def _getADRs(self):\n", " return self.dataFrame['VAX_LOT'].value_counts()\n", "\n", " def _getDEATHS(self):\n", " return self._countValues('DIED')\n", "\n", " def _getDISABILITIES(self):\n", " return self._countValues('DISABLE')\n", "\n", " def _getLIFE_THREATENING_ILLNESSES(self):\n", " return self._countValues('L_THREAT')\n", "\n", " def _getHOSPITALISATIONS(self):\n", " return self._countValues('HOSPITAL')\n", "\n", " def _getER_VISITs(self):\n", " return self._countValues('ER_VISIT')\n", "\n", " def _countValues(self, column):\n", " return self.dataFrame[self.dataFrame[column] == 'Y']['VAX_LOT'].value_counts()\n", "\n", " def _asDataFrame(self, dict):\n", " dataFrame = pd.concat(dict, axis = 'columns')\n", " dataFrame.index.name = 'VAX_LOT'\n", " return dataFrame.replace(to_replace = np.nan, value = 0)\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", "class BatchCodeTableFactory:\n", "\n", " @staticmethod\n", " def createBatchCodeTable(dataFrame : pd.DataFrame, manufacturer, dose):\n", " filteredDataFrame = DataFrameFilter(dataFrame).filterBy(manufacturer = manufacturer, dose = dose)\n", " return BatchCodeTableHelper(filteredDataFrame).createBatchCodeTable()\n", "\n", " # create table from https://www.howbadismybatch.com/combined.html\n", " @staticmethod\n", " def createSevereEffectsBatchCodeTable(dataFrame : pd.DataFrame, dose):\n", " severeEffectsDataFrame = DataFrameFilter(dataFrame).filterForSevereEffects(dose)\n", " return BatchCodeTableHelper(severeEffectsDataFrame).createSevereEffectsBatchCodeTable()\n" ] }, { "cell_type": "code", "execution_count": null, "id": "41d4fa30", "metadata": {}, "outputs": [], "source": [ "class DoseAnalysis:\n", " \n", " @staticmethod\n", " def getNthDoseTable(dataFrame, dose):\n", " return pd.Series(DoseAnalysis._getNthDoseDict(DataFrameFilter(dataFrame).filterBy(dose = dose)))\n", "\n", " @staticmethod\n", " def _getNthDoseDict(df):\n", " nthDoseDict = {\n", " 'Total reports': len(df.index),\n", " 'Deaths': DoseAnalysis._count(df, 'DIED'),\n", " 'Disabilities': DoseAnalysis._count(df, 'DISABLE'),\n", " 'Life Threatening Illnesses': DoseAnalysis._count(df, 'L_THREAT')\n", " }\n", " nthDoseDict['Severe reports'] = (nthDoseDict['Deaths'] + nthDoseDict['Disabilities'] + nthDoseDict['Life Threatening Illnesses']) / nthDoseDict['Total reports'] * 100\n", " return nthDoseDict\n", "\n", " @staticmethod\n", " def _count(dataFrame, column):\n", " return len(dataFrame[dataFrame[column] == 'Y'])\n" ] }, { "cell_type": "code", "execution_count": null, "id": "3dacedfd", "metadata": {}, "outputs": [], "source": [ "import unittest" ] }, { "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_filterBy(self):\n", " # Given\n", " dataFrameFilter = DataFrameFilter(\n", " VaersDescr2DataFrameConverter.createDataFrameFromDescrs(\n", " [\n", " {\n", " 'VAERSDATA': self.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE'],\n", " data = [ ['Y', np.NaN, np.NaN],\n", " [np.NaN, np.NaN, 'Y']],\n", " index = [\n", " \"0916600\",\n", " \"0916601\"]),\n", " 'VAERSVAX': self.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': self.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE'],\n", " data = [ [np.NaN, np.NaN, np.NaN],\n", " [np.NaN, np.NaN, 'Y']],\n", " index = [\n", " \"1996873\",\n", " \"1996874\"]),\n", " 'VAERSVAX': self.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", " \n", " # When\n", " dataFrame = dataFrameFilter.filterBy(manufacturer = \"MODERNA\", dose = '1')\n", " \n", " # Then\n", " dataFrameExpected = self.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE', 'VAX_TYPE', 'VAX_MANU', 'VAX_LOT', 'VAX_DOSE_SERIES'],\n", " data = [ ['Y', np.NaN, np.NaN, 'COVID19', 'MODERNA', '037K20A', '1'],\n", " [np.NaN, np.NaN, 'Y', 'COVID19', 'MODERNA', '025L20A', '1'],\n", " [np.NaN, np.NaN, 'Y', '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_filterForSevereEffects(self):\n", " # Given\n", " dataFrameFilter = DataFrameFilter(\n", " VaersDescr2DataFrameConverter.createDataFrameFromDescrs(\n", " [\n", " {\n", " 'VAERSDATA': self.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE', 'HOSPITAL', 'ER_VISIT'],\n", " data = [ ['Y', 'Y', np.NaN, 'Y', 'Y'],\n", " [np.NaN, np.NaN, 'Y', np.NaN, 'Y']],\n", " index = [\n", " \"0916600\",\n", " \"0916601\"]),\n", " 'VAERSVAX': self.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", " dataFrame = dataFrameFilter.filterForSevereEffects(dose = '1')\n", " \n", " # Then\n", " dataFrameExpected = self.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE', 'HOSPITAL', 'ER_VISIT', 'VAX_TYPE', 'VAX_MANU', 'VAX_LOT', 'VAX_DOSE_SERIES'],\n", " data = [ ['Y', 'Y', np.NaN, 'Y', 'Y', 'COVID19', 'MODERNA', '037K20A', '1'],\n", " [np.NaN, np.NaN, 'Y', np.NaN, 'Y', '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", " dataFrameFilter = DataFrameFilter(\n", " VaersDescr2DataFrameConverter.createDataFrameFromDescrs(\n", " [\n", " {\n", " 'VAERSDATA': self.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE'],\n", " data = [ ['Y', np.NaN, np.NaN]],\n", " index = [\n", " \"1048786\"]),\n", " 'VAERSVAX': self.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", " \n", " # When\n", " dataFrame = dataFrameFilter.filterBy(manufacturer = \"MODERNA\", dose = '1')\n", " \n", " # Then\n", " dataFrameExpected = self.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE', 'VAX_TYPE', 'VAX_MANU', 'VAX_LOT', 'VAX_DOSE_SERIES'],\n", " data = [ ['Y', np.NaN, np.NaN, '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", " dataFrameFilter = DataFrameFilter(\n", " VaersDescr2DataFrameConverter.createDataFrameFromDescrs(\n", " [\n", " {\n", " 'VAERSDATA': self.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE'],\n", " data = [ ['Y', np.NaN, np.NaN]],\n", " index = [\n", " \"1048786\"]),\n", " 'VAERSVAX': self.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", "\n", " # When\n", " dataFrame = dataFrameFilter.filterBy(manufacturer = \"MODERNA\", dose = '2')\n", " \n", " # Then\n", " dataFrameExpected = self.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE', 'VAX_TYPE', 'VAX_MANU', 'VAX_LOT', 'VAX_DOSE_SERIES'],\n", " data = [ ['Y', np.NaN, np.NaN, 'COVID19', 'MODERNA', '016M20A', '2']],\n", " index = [\n", " \"1048786\"],\n", " dtypes = {'VAX_DOSE_SERIES': \"string\"})\n", " assert_frame_equal(dataFrame, dataFrameExpected, check_dtype = False)\n", "\n", " def createDataFrame(self, index, columns, data, dtypes = {}):\n", " return pd.DataFrame(index = index, columns = columns, data = data).astype(dtypes)\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 test_createSevereEffectsBatchCodeTable(self):\n", " # Given\n", " dataFrame = VaersDescr2DataFrameConverter.createDataFrameFromDescrs(\n", " [\n", " {\n", " 'VAERSDATA': self.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE', 'HOSPITAL', 'ER_VISIT'],\n", " data = [ ['Y', 'Y', np.NaN, 'Y', 'Y'],\n", " [np.NaN, np.NaN, 'Y', np.NaN, 'Y']],\n", " index = [\n", " \"0916600\",\n", " \"0916601\"]),\n", " 'VAERSVAX': self.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': [1, 0],\n", " 'DISABILITIES': [0, 1],\n", " 'LIFE THREATENING ILLNESSES': [1, 0],\n", " 'HOSPITALISATIONS': [1, 0],\n", " 'EMERGENCY ROOM OR DOCTOR VISITS': [1, 1],\n", " 'COMPANY': ['MODERNA', 'PFIZER\\BIONTECH']\n", " },\n", " index = pd.Index(['037K20A', '025L20A'], 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': self.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE'],\n", " data = [ ['Y', np.NaN, np.NaN],\n", " [np.NaN, np.NaN, 'Y']],\n", " index = [\n", " \"0916600\",\n", " \"0916601\"]),\n", " 'VAERSVAX': self.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': self.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE'],\n", " data = [ [np.NaN, np.NaN, np.NaN],\n", " [np.NaN, np.NaN, 'Y']],\n", " index = [\n", " \"1996873\",\n", " \"1996874\"]),\n", " 'VAERSVAX': self.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", " 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", "\n", " def createDataFrame(self, index, columns, data, dtypes = {}):\n", " return pd.DataFrame(index = index, columns = columns, data = data).astype(dtypes)\n" ] }, { "cell_type": "code", "execution_count": null, "id": "44c121ec", "metadata": {}, "outputs": [], "source": [ "from pandas.testing import assert_series_equal\n", "\n", "class DoseAnalysisTest(unittest.TestCase):\n", "\n", " def test_getFirstDoseTable(self):\n", " self._test_getNthDoseTable(\n", " dataFrame = self.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE', 'VAX_TYPE', 'VAX_MANU', 'VAX_LOT', 'VAX_DOSE_SERIES'],\n", " data = [ ['Y', np.NaN, np.NaN,\t 'COVID19', 'MODERNA', '016M20A', '2'],\n", " ['Y', np.NaN, np.NaN, 'COVID19', 'MODERNA', '030L20A', '1'],\n", " ['Y', 'Y', 'Y', 'COVID19', 'MODERNA', '030L20B', '1']],\n", " index = [\n", " \"1048786\",\n", " \"1048786\",\n", " \"4711\"],\n", " dtypes = {'VAX_DOSE_SERIES': \"string\"}),\n", " dose = '1',\n", " doseTableExpected = pd.Series(\n", " {\n", " 'Total reports': 2,\n", " 'Deaths': 2,\n", " 'Disabilities': 1,\n", " 'Life Threatening Illnesses': 1,\n", " 'Severe reports': (2 + 1 + 1)/2 * 100\n", " }))\n", "\n", " def test_getSecondDoseTable(self):\n", " self._test_getNthDoseTable(\n", " dataFrame = self.createDataFrame(\n", " columns = ['DIED', 'L_THREAT', 'DISABLE', 'VAX_TYPE', 'VAX_MANU', 'VAX_LOT', 'VAX_DOSE_SERIES'],\n", " data = [ ['Y', np.NaN, np.NaN,\t 'COVID19', 'MODERNA', '016M20A', '2'],\n", " ['Y', np.NaN, np.NaN, 'COVID19', 'MODERNA', '030L20A', '1'],\n", " ['Y', 'Y', 'Y', 'COVID19', 'MODERNA', '030L20B', '1']],\n", " index = [\n", " \"1048786\",\n", " \"1048786\",\n", " \"4711\"],\n", " dtypes = {'VAX_DOSE_SERIES': \"string\"}),\n", " dose = '2',\n", " doseTableExpected = pd.Series(\n", " {\n", " 'Total reports': 1,\n", " 'Deaths': 1,\n", " 'Disabilities': 0,\n", " 'Life Threatening Illnesses': 0,\n", " 'Severe reports': (1 + 0 + 0)/1 * 100\n", " }))\n", "\n", " def _test_getNthDoseTable(self, dataFrame, dose, doseTableExpected):\n", " # When\n", " doseTable = DoseAnalysis.getNthDoseTable(dataFrame, dose)\n", " \n", " # Then\n", " assert_series_equal(doseTable, doseTableExpected)\n", "\n", " def createDataFrame(self, index, columns, data, dtypes = {}):\n", " return pd.DataFrame(index = index, columns = columns, data = data).astype(dtypes)\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", " batchCodeTable = BatchCodeTableFactory.createBatchCodeTable(dataFrame, manufacturer = manufacturer, dose = '1')\n", " display(manufacturer + ':', batchCodeTable)\n", " batchCodeTable.to_excel(excelFile)" ] }, { "cell_type": "code", "execution_count": null, "id": "ab170c16", "metadata": {}, "outputs": [], "source": [ "saveBatchCodeTable(\"MODERNA\", \"results/moderna.xlsx\")\n", "saveBatchCodeTable(\"PFIZER\\BIONTECH\", \"results/pfizer.xlsx\")\n", "saveBatchCodeTable(\"JANSSEN\", \"results/janssen.xlsx\")" ] }, { "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", " severeEffectsBatchCodeTable = BatchCodeTableFactory.createSevereEffectsBatchCodeTable(dataFrame, dose = '1')\n", " display('severeEffectsBatchCodeTable:', 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 saveNthDoseTable(dose, excelFile):\n", " vaersDescrs = VaersDescrReader(dataDir = \"VAERS\").readAllVaersDescrs()\n", " dataFrame = VaersDescr2DataFrameConverter.createDataFrameFromDescrs(vaersDescrs)\n", " doseTable = DoseAnalysis.getNthDoseTable(dataFrame, dose)\n", " display(f'doseTable(dose = {dose}):', doseTable)\n", " doseTable.to_excel(excelFile)\n" ] }, { "cell_type": "code", "execution_count": null, "id": "394fa19d", "metadata": {}, "outputs": [], "source": [ "saveNthDoseTable(dose = '1', excelFile = 'results/firstDoseTable.xlsx')" ] }, { "cell_type": "code", "execution_count": null, "id": "686d4ddf", "metadata": {}, "outputs": [], "source": [ "saveNthDoseTable(dose = '2', excelFile = 'results/secondDoseTable.xlsx')" ] }, { "cell_type": "code", "execution_count": null, "id": "e6bc676b", "metadata": {}, "outputs": [], "source": [] } ], "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 }