880 lines
36 KiB
Plaintext
880 lines
36 KiB
Plaintext
{
|
|
"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 readVaersDescrsForYears(self, years):\n",
|
|
" return [self.readVaersDescrForYear(year) for year in years]\n",
|
|
"\n",
|
|
" def readVaersDescrForYear(self, year):\n",
|
|
" return {\n",
|
|
" 'VAERSDATA': self._readVAERSDATA('{dataDir}/{year}VAERSDATA.csv'.format(dataDir = self.dataDir, year = year)),\n",
|
|
" 'VAERSVAX': self._readVAERSVAX('{dataDir}/{year}VAERSVAX.csv'.format(dataDir = self.dataDir, year = year))\n",
|
|
" }\n",
|
|
"\n",
|
|
" def readNonDomesticVaersDescr(self):\n",
|
|
" return {\n",
|
|
" 'VAERSDATA': self._readVAERSDATA(self.dataDir + \"/NonDomesticVAERSDATA.csv\"),\n",
|
|
" 'VAERSVAX': self._readVAERSVAX(self.dataDir + \"/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._convertColumnsOfDataFrame_Y_to_1_else_0(\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 _convertColumnsOfDataFrame_Y_to_1_else_0(dataFrame, columns):\n",
|
|
" for column in columns:\n",
|
|
" DataFrameNormalizer._convertColumnOfDataFrame_Y_to_1_else_0(dataFrame, column)\n",
|
|
"\n",
|
|
" @staticmethod\n",
|
|
" def _convertColumnOfDataFrame_Y_to_1_else_0(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 _isCovid19(self, dataFrame):\n",
|
|
" return dataFrame[\"VAX_TYPE\"] == \"COVID19\"\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "c62cfaff",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"class SummationTableFactory:\n",
|
|
"\n",
|
|
" @staticmethod\n",
|
|
" def createSummationTable(\n",
|
|
" groupBy,\n",
|
|
" columnNameMappingsDict = {\n",
|
|
" \"DIED_size\": \"Adverse Reaction Reports\",\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",
|
|
"\n",
|
|
" summationTable = groupBy.agg({\n",
|
|
" 'DIED': ['sum', 'size'],\n",
|
|
" 'L_THREAT': 'sum',\n",
|
|
" 'DISABLE': 'sum',\n",
|
|
" 'HOSPITAL': 'sum',\n",
|
|
" 'ER_VISIT': 'sum',\n",
|
|
" 'SEVERE': 'sum'\n",
|
|
" })\n",
|
|
" SummationTableFactory._flattenColumns(summationTable)\n",
|
|
" return summationTable.rename(columns = columnNameMappingsDict)\n",
|
|
"\n",
|
|
" @staticmethod\n",
|
|
" def createSummationTableHavingSevereReportsColumn(dataFrame):\n",
|
|
" summationTable = SummationTableFactory.createSummationTable(\n",
|
|
" dataFrame,\n",
|
|
" columnNameMappingsDict = {\n",
|
|
" \"DIED_size\": \"Adverse Reaction Reports\",\n",
|
|
" \"DIED_sum\": \"Deaths\",\n",
|
|
" \"L_THREAT_sum\": \"Life Threatening Illnesses\",\n",
|
|
" \"DISABLE_sum\": \"Disabilities\",\n",
|
|
" \"SEVERE_sum\": \"Severities\"\n",
|
|
" })\n",
|
|
" summationTable['Severe reports'] = summationTable['Severities'] / summationTable['Adverse Reaction Reports'] * 100\n",
|
|
" summationTable['Lethality'] = summationTable['Deaths'] / summationTable['Adverse Reaction Reports'] * 100\n",
|
|
" summationTable = summationTable[\n",
|
|
" [\n",
|
|
" 'Adverse Reaction Reports',\n",
|
|
" 'Deaths',\n",
|
|
" 'Disabilities',\n",
|
|
" 'Life Threatening Illnesses',\n",
|
|
" 'Severe reports',\n",
|
|
" 'Lethality'\n",
|
|
" ]]\n",
|
|
" return summationTable\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": "c40bd0f0",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import pycountry\n",
|
|
"\n",
|
|
"class CountryColumnAdder:\n",
|
|
" \n",
|
|
" @staticmethod\n",
|
|
" def addCountryColumn(dataFrame):\n",
|
|
" dataFrame['COUNTRY'] = CountryColumnAdder.getCountryColumn(dataFrame)\n",
|
|
" return dataFrame.astype({'COUNTRY': \"string\"})\n",
|
|
"\n",
|
|
" @staticmethod\n",
|
|
" def getCountryColumn(dataFrame):\n",
|
|
" return dataFrame.apply(\n",
|
|
" lambda row:\n",
|
|
" CountryColumnAdder._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"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "3abe3384",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import pycountry\n",
|
|
"\n",
|
|
"class SevereColumnAdder:\n",
|
|
" \n",
|
|
" @staticmethod\n",
|
|
" def addSevereColumn(dataFrame):\n",
|
|
" dataFrame['SEVERE'] = (dataFrame['DIED'] + dataFrame['L_THREAT'] + dataFrame['DISABLE']) > 0\n",
|
|
" dataFrame['SEVERE'].replace({True: 1, False: 0}, inplace = True)\n",
|
|
" return dataFrame\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "2dad09e5",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"class CompanyColumnAdder:\n",
|
|
" \n",
|
|
" @staticmethod\n",
|
|
" def addCompanyColumn(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",
|
|
" @staticmethod\n",
|
|
" def createCompanyByBatchCodeTable(dataFrame):\n",
|
|
" return CompanyColumnAdder._createManufacturerByBatchCodeTable(dataFrame).rename(columns = {\"VAX_MANU\": \"Company\"})\n",
|
|
"\n",
|
|
" @staticmethod\n",
|
|
" def _createManufacturerByBatchCodeTable(dataFrame):\n",
|
|
" manufacturerByBatchCodeTable = dataFrame[['VAX_LOT', 'VAX_MANU']]\n",
|
|
" manufacturerByBatchCodeTable = manufacturerByBatchCodeTable.drop_duplicates(subset = ['VAX_LOT'])\n",
|
|
" return manufacturerByBatchCodeTable.set_index('VAX_LOT')\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "09e6b511",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"class InternationalLotTableFactory:\n",
|
|
" \n",
|
|
" def __init__(self, dataFrame : pd.DataFrame):\n",
|
|
" self.dataFrame = DataFrameFilter().filterByCovid19(dataFrame)\n",
|
|
" self.batchCodeTableByCountryFactory = BatchCodeTableByCountryFactory(dataFrame)\n",
|
|
"\n",
|
|
" def createInternationalLotTable(self):\n",
|
|
" internationalLotTable = self._createInternationalLotTable()\n",
|
|
" return internationalLotTable.sort_values(by = 'Severe reports', ascending = False)\n",
|
|
"\n",
|
|
" def createBatchCodeTableByCountry(self, country):\n",
|
|
" return self.batchCodeTableByCountryFactory.createBatchCodeTableByCountry(country)\n",
|
|
"\n",
|
|
" def createGlobalBatchCodeTable(self):\n",
|
|
" return self.createBatchCodeTableByCountry(None)\n",
|
|
"\n",
|
|
" def _createInternationalLotTable(self):\n",
|
|
" return SummationTableFactory.createSummationTableHavingSevereReportsColumn(self.dataFrame.groupby(self.dataFrame['COUNTRY']))\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "71456a79",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"class BatchCodeTableByCountryFactory:\n",
|
|
"\n",
|
|
" def __init__(self, dataFrame : pd.DataFrame):\n",
|
|
" self.dataFrame = DataFrameFilter().filterByCovid19(dataFrame)\n",
|
|
" self.countryBatchCodeTable = None\n",
|
|
"\n",
|
|
" def createBatchCodeTableByCountry(self, country):\n",
|
|
" batchCodeTable = self._createBatchCodeTableByCountry(country)\n",
|
|
" batchCodeTable = CompanyColumnAdder.addCompanyColumn(batchCodeTable, CompanyColumnAdder.createCompanyByBatchCodeTable(self.dataFrame))\n",
|
|
" batchCodeTable = batchCodeTable[\n",
|
|
" [\n",
|
|
" 'Adverse Reaction Reports',\n",
|
|
" 'Deaths',\n",
|
|
" 'Disabilities',\n",
|
|
" 'Life Threatening Illnesses',\n",
|
|
" 'Company',\n",
|
|
" 'Severe reports',\n",
|
|
" 'Lethality'\n",
|
|
" ]]\n",
|
|
" return batchCodeTable.sort_values(by = 'Severe reports', ascending = False)\n",
|
|
"\n",
|
|
" # FK-TODO: refactor\n",
|
|
" def _createBatchCodeTableByCountry(self, country):\n",
|
|
" if country is None:\n",
|
|
" return SummationTableFactory.createSummationTableHavingSevereReportsColumn(self.dataFrame.groupby('VAX_LOT'))\n",
|
|
"\n",
|
|
" if self.countryBatchCodeTable is None:\n",
|
|
" self.countryBatchCodeTable = self._getCountryBatchCodeTable()\n",
|
|
" \n",
|
|
" return self._getCountry(self.countryBatchCodeTable, country)\n",
|
|
"\n",
|
|
" def _getCountryBatchCodeTable(self):\n",
|
|
" return SummationTableFactory.createSummationTableHavingSevereReportsColumn(\n",
|
|
" self.dataFrame.groupby(\n",
|
|
" [\n",
|
|
" self.dataFrame['COUNTRY'],\n",
|
|
" self.dataFrame['VAX_LOT']\n",
|
|
" ]))\n",
|
|
"\n",
|
|
" def _getCountry(self, countryBatchCodeTable, country):\n",
|
|
" return countryBatchCodeTable.loc[country] if country in countryBatchCodeTable.index else self._getEmptyBatchCodeTable(countryBatchCodeTable)\n",
|
|
" \n",
|
|
" def _getEmptyBatchCodeTable(self, countryBatchCodeTable):\n",
|
|
" return countryBatchCodeTable[0:0].droplevel(0)\n",
|
|
"\n",
|
|
" "
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "6aa28541",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import os\n",
|
|
"\n",
|
|
"class IOUtils:\n",
|
|
"\n",
|
|
" @staticmethod\n",
|
|
" def saveDataFrame(dataFrame, file):\n",
|
|
" IOUtils.saveDataFrameAsExcelFile(dataFrame, file)\n",
|
|
" IOUtils.saveDataFrameAsHtml(dataFrame, file)\n",
|
|
" IOUtils.saveDataFrameAsJson(dataFrame, file)\n",
|
|
"\n",
|
|
" @staticmethod\n",
|
|
" def saveDataFrameAsExcelFile(dataFrame, file):\n",
|
|
" IOUtils.ensurePath(file)\n",
|
|
" dataFrame.to_excel(file + '.xlsx')\n",
|
|
"\n",
|
|
" @staticmethod\n",
|
|
" def saveDataFrameAsHtml(dataFrame, file):\n",
|
|
" IOUtils.ensurePath(file)\n",
|
|
" dataFrame.reset_index().to_html(\n",
|
|
" file + '.html',\n",
|
|
" index = False,\n",
|
|
" table_id = 'batchCodeTable',\n",
|
|
" classes = 'display',\n",
|
|
" justify = 'unset',\n",
|
|
" border = 0)\n",
|
|
"\n",
|
|
" @staticmethod\n",
|
|
" def saveDataFrameAsJson(dataFrame, file):\n",
|
|
" IOUtils.ensurePath(file)\n",
|
|
" dataFrame.reset_index().to_json(\n",
|
|
" file + '.json',\n",
|
|
" orient = \"split\",\n",
|
|
" index = False)\n",
|
|
"\n",
|
|
" @staticmethod\n",
|
|
" def ensurePath(file):\n",
|
|
" directory = os.path.dirname(file)\n",
|
|
" if not os.path.exists(directory):\n",
|
|
" os.makedirs(directory)\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(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",
|
|
" \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"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "c784bfef",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from pandas.testing import assert_frame_equal\n",
|
|
"\n",
|
|
"class InternationalLotTableFactoryTest(unittest.TestCase):\n",
|
|
"\n",
|
|
" def test_createInternationalLotTable(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', 'COUNTRY'],\n",
|
|
" data = [ [1, 0, 0, 'COVID19', 'MODERNA', '016M20A', '2', 'GBPFIZER INC2020486806', 0, 0, 'United Kingdom'],\n",
|
|
" [1, 0, 0, 'COVID19', 'MODERNA', '030L20A', '1', 'FRMODERNATX, INC.MOD20224', 0, 0, 'France'],\n",
|
|
" [1, 1, 1, 'COVID19', 'MODERNA', '030L20B', '1', 'FRMODERNATX, INC.MOD20224', 0, 0, 'France'],\n",
|
|
" [0, 0, 0, 'COVID19', 'MODERNA', '030L20B', '1', 'dummy', 0, 0, 'Unknown Country'],\n",
|
|
" [0, 0, 0, 'COVID19', 'MODERNA', '030L20B', '1', 123, 0, 0, 'Unknown Country']],\n",
|
|
" index = [\n",
|
|
" \"1048786\",\n",
|
|
" \"1048786\",\n",
|
|
" \"4711\",\n",
|
|
" \"0815\",\n",
|
|
" \"0816\"])\n",
|
|
" dataFrame = SevereColumnAdder.addSevereColumn(dataFrame)\n",
|
|
" internationalLotTableFactory = InternationalLotTableFactory(dataFrame)\n",
|
|
" \n",
|
|
" # When\n",
|
|
" internationalLotTable = internationalLotTableFactory.createInternationalLotTable()\n",
|
|
"\n",
|
|
" # Then\n",
|
|
" assert_frame_equal(\n",
|
|
" internationalLotTable,\n",
|
|
" TestHelper.createDataFrame(\n",
|
|
" columns = ['Adverse Reaction Reports', 'Deaths', 'Disabilities', 'Life Threatening Illnesses', 'Severe reports', 'Lethality'],\n",
|
|
" data = [ [2, 2, 1, 1, 2/2 * 100, 2/2 * 100],\n",
|
|
" [1, 1, 0, 0, 1/1 * 100, 1/1 * 100],\n",
|
|
" [2, 0, 0, 0, 0/2 * 100, 0/2 * 100]],\n",
|
|
" index = pd.Index(\n",
|
|
" [\n",
|
|
" 'France',\n",
|
|
" 'United Kingdom',\n",
|
|
" 'Unknown Country'\n",
|
|
" ],\n",
|
|
" name = 'COUNTRY')))\n",
|
|
"\n",
|
|
" def test_createBatchCodeTableByCountry(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', 'COUNTRY'],\n",
|
|
" data = [ [1, 0, 0, 'COVID19', 'PFIZER\\BIONTECH', '016M20A', '2', 'GBPFIZER INC2020486806', 0, 0, 'United Kingdom'],\n",
|
|
" [0, 0, 0, 'COVID19', 'MODERNA', '030L20A', '1', 'FRMODERNATX, INC.MOD20224', 0, 0, 'France'],\n",
|
|
" [1, 1, 1, 'COVID19', 'MODERNA', '030L20B', '1', 'FRMODERNATX, INC.MOD20224', 0, 0, 'France'],\n",
|
|
" [0, 1, 1, 'COVID19', 'MODERNA', '030L20B', '1', 'FRMODERNATX, INC.MOD20224', 0, 0, 'France']],\n",
|
|
" index = [\n",
|
|
" \"1048786\",\n",
|
|
" \"1048786\",\n",
|
|
" \"4711\",\n",
|
|
" \"0815\"])\n",
|
|
" dataFrame = SevereColumnAdder.addSevereColumn(dataFrame)\n",
|
|
" internationalLotTableFactory = InternationalLotTableFactory(dataFrame)\n",
|
|
" \n",
|
|
" # When\n",
|
|
" batchCodeTable = internationalLotTableFactory.createBatchCodeTableByCountry('France')\n",
|
|
"\n",
|
|
" # Then\n",
|
|
" assert_frame_equal(\n",
|
|
" batchCodeTable,\n",
|
|
" TestHelper.createDataFrame(\n",
|
|
" columns = ['Adverse Reaction Reports', 'Deaths', 'Disabilities', 'Life Threatening Illnesses', 'Company', 'Severe reports', 'Lethality'],\n",
|
|
" data = [ [2, 1, 2, 2, 'MODERNA', 2/2 * 100, 1/2 * 100],\n",
|
|
" [1, 0, 0, 0, 'MODERNA', 0/1 * 100, 0/1 * 100]],\n",
|
|
" index = pd.Index(\n",
|
|
" [\n",
|
|
" '030L20B',\n",
|
|
" '030L20A'\n",
|
|
" ],\n",
|
|
" name = 'VAX_LOT')),\n",
|
|
" check_dtype = False)\n",
|
|
"\n",
|
|
" def test_createGlobalBatchCodeTable(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', 'COUNTRY'],\n",
|
|
" data = [ [1, 0, 0, 'COVID19', 'PFIZER\\BIONTECH', '016M20A', '2', 'GBPFIZER INC2020486806', 0, 0, 'United Kingdom'],\n",
|
|
" [0, 0, 0, 'COVID19', 'MODERNA', '030L20A', '1', 'FRMODERNATX, INC.MOD20224', 0, 0, 'France'],\n",
|
|
" [1, 1, 1, 'COVID19', 'MODERNA', '030L20B', '1', 'FRMODERNATX, INC.MOD20224', 0, 0, 'France'],\n",
|
|
" [0, 1, 1, 'COVID19', 'MODERNA', '030L20B', '1', 'FRMODERNATX, INC.MOD20224', 0, 0, 'France']],\n",
|
|
" index = [\n",
|
|
" \"1048786\",\n",
|
|
" \"1048786\",\n",
|
|
" \"4711\",\n",
|
|
" \"0815\"])\n",
|
|
" dataFrame = SevereColumnAdder.addSevereColumn(dataFrame)\n",
|
|
" internationalLotTableFactory = InternationalLotTableFactory(dataFrame)\n",
|
|
" \n",
|
|
" # When\n",
|
|
" batchCodeTable = internationalLotTableFactory.createGlobalBatchCodeTable()\n",
|
|
"\n",
|
|
" # Then\n",
|
|
" assert_frame_equal(\n",
|
|
" batchCodeTable,\n",
|
|
" TestHelper.createDataFrame(\n",
|
|
" columns = ['Adverse Reaction Reports', 'Deaths', 'Disabilities', 'Life Threatening Illnesses', 'Company', 'Severe reports', 'Lethality'],\n",
|
|
" data = [ [1, 1, 0, 0, 'PFIZER\\BIONTECH', 1/1 * 100, 1/1 * 100],\n",
|
|
" [2, 1, 2, 2, 'MODERNA', 2/2 * 100, 1/2 * 100],\n",
|
|
" [1, 0, 0, 0, 'MODERNA', 0/1 * 100, 0/1 * 100]],\n",
|
|
" index = pd.Index(\n",
|
|
" [\n",
|
|
" '016M20A',\n",
|
|
" '030L20B',\n",
|
|
" '030L20A'\n",
|
|
" ],\n",
|
|
" name = 'VAX_LOT')),\n",
|
|
" check_dtype = False)\n",
|
|
"\n",
|
|
" def test_createBatchCodeTableByNonExistingCountry(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', 'COUNTRY'],\n",
|
|
" data = [ [1, 0, 0, 'COVID19', 'PFIZER\\BIONTECH', '016M20A', '2', 'GBPFIZER INC2020486806', 0, 0, 'United Kingdom'],\n",
|
|
" [0, 0, 0, 'COVID19', 'MODERNA', '030L20A', '1', 'FRMODERNATX, INC.MOD20224', 0, 0, 'France'],\n",
|
|
" [1, 1, 1, 'COVID19', 'MODERNA', '030L20B', '1', 'FRMODERNATX, INC.MOD20224', 0, 0, 'France'],\n",
|
|
" [0, 1, 1, 'COVID19', 'MODERNA', '030L20B', '1', 'FRMODERNATX, INC.MOD20224', 0, 0, 'France']],\n",
|
|
" index = [\n",
|
|
" \"1048786\",\n",
|
|
" \"1048786\",\n",
|
|
" \"4711\",\n",
|
|
" \"0815\"])\n",
|
|
" dataFrame = SevereColumnAdder.addSevereColumn(dataFrame)\n",
|
|
" internationalLotTableFactory = InternationalLotTableFactory(dataFrame)\n",
|
|
" \n",
|
|
" # When\n",
|
|
" batchCodeTable = internationalLotTableFactory.createBatchCodeTableByCountry('non existing country')\n",
|
|
"\n",
|
|
" # Then\n",
|
|
" assert_frame_equal(\n",
|
|
" batchCodeTable,\n",
|
|
" TestHelper.createDataFrame(\n",
|
|
" columns = ['Adverse Reaction Reports', 'Deaths', 'Disabilities', 'Life Threatening Illnesses', 'Company', 'Severe reports', 'Lethality'],\n",
|
|
" data = [ ],\n",
|
|
" index = pd.Index([], name = 'VAX_LOT')),\n",
|
|
" check_dtype = False)\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 getVaersForYear(year):\n",
|
|
" return getVaersForYears([year])\n",
|
|
"\n",
|
|
"def getVaersForYears(years):\n",
|
|
" def addCountryColumn(dataFrame):\n",
|
|
" dataFrame['COUNTRY'] = 'United States'\n",
|
|
" return dataFrame\n",
|
|
"\n",
|
|
" return _getVaers(\n",
|
|
" _getVaersDescrReader().readVaersDescrsForYears(years),\n",
|
|
" addCountryColumn)\n",
|
|
"\n",
|
|
"def getNonDomesticVaers():\n",
|
|
" return _getVaers(\n",
|
|
" [_getVaersDescrReader().readNonDomesticVaersDescr()],\n",
|
|
" CountryColumnAdder.addCountryColumn)\n",
|
|
"\n",
|
|
"def _getVaersDescrReader():\n",
|
|
" return VaersDescrReader(dataDir = \"VAERS\")\n",
|
|
"\n",
|
|
"def _getVaers(vaersDescrs, addCountryColumn):\n",
|
|
" dataFrame = VaersDescr2DataFrameConverter.createDataFrameFromDescrs(vaersDescrs)\n",
|
|
" dataFrame = addCountryColumn(dataFrame)\n",
|
|
" DataFrameNormalizer.normalize(dataFrame)\n",
|
|
" dataFrame = SevereColumnAdder.addSevereColumn(dataFrame)\n",
|
|
" return dataFrame\n",
|
|
" "
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "8e3bc9b3",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"vaers = getVaersForYears([2020, 2021, 2022])\n",
|
|
"vaers"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "fbf5006a",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"nonDomesticVaers = getNonDomesticVaers()\n",
|
|
"nonDomesticVaers"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "781ac80e",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"internationalVaers = pd.concat([vaers, nonDomesticVaers])\n",
|
|
"internationalVaers"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "ff259a35",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def createAndSaveBatchCodeTableForCountry(createBatchCodeTableForCountry, country, minADRsForLethality = None):\n",
|
|
" batchCodeTable = createBatchCodeTableForCountry(country)\n",
|
|
" batchCodeTable.index.set_names(\"Batch\", inplace = True)\n",
|
|
" if minADRsForLethality is not None:\n",
|
|
" batchCodeTable.loc[batchCodeTable['Adverse Reaction Reports'] < minADRsForLethality, ['Severe reports', 'Lethality']] = [np.nan, np.nan]\n",
|
|
" IOUtils.saveDataFrame(batchCodeTable, '../docs/data/' + country)\n",
|
|
" display(country + \":\", batchCodeTable)\n",
|
|
"\n",
|
|
"def createAndSaveBatchCodeTablesForCountries(createBatchCodeTableForCountry, countries, minADRsForLethality = None):\n",
|
|
" for country in countries:\n",
|
|
" createAndSaveBatchCodeTableForCountry(createBatchCodeTableForCountry, country, minADRsForLethality)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "cc1ef82a",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def printCountryOptions(countries):\n",
|
|
" for country in countries:\n",
|
|
" printCountryOption(country)\n",
|
|
"\n",
|
|
"def printCountryOption(country):\n",
|
|
" print('<option value=\"{country}\">{country}</option>'.format(country = country))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "0c4d04fb",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"countries = sorted(internationalVaers['COUNTRY'].unique())\n",
|
|
"printCountryOptions(countries)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "7e7e01a5",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"minADRsForLethality = 100\n",
|
|
"internationalLotTableFactory = InternationalLotTableFactory(internationalVaers)\n",
|
|
"\n",
|
|
"createAndSaveBatchCodeTablesForCountries(\n",
|
|
" createBatchCodeTableForCountry = lambda country: internationalLotTableFactory.createBatchCodeTableByCountry(country),\n",
|
|
" countries = countries,\n",
|
|
" minADRsForLethality = minADRsForLethality)\n",
|
|
"\n",
|
|
"createAndSaveBatchCodeTableForCountry(\n",
|
|
" createBatchCodeTableForCountry = lambda country: internationalLotTableFactory.createGlobalBatchCodeTable(),\n",
|
|
" country = 'Global',\n",
|
|
" minADRsForLethality = minADRsForLethality)\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "376b9193",
|
|
"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
|
|
}
|