From f1a00a87bd99e7391a4eada933e36dcdc9401124 Mon Sep 17 00:00:00 2001 From: frankknoll Date: Tue, 3 Oct 2023 23:50:46 +0200 Subject: [PATCH] invoking RegionCountsByBatchcodeTablesMerger --- src/HowBadIsMyBatch.ipynb | 1501 ++----------------------------------- 1 file changed, 51 insertions(+), 1450 deletions(-) diff --git a/src/HowBadIsMyBatch.ipynb b/src/HowBadIsMyBatch.ipynb index e8ea731aa03..aa2a761a9b7 100644 --- a/src/HowBadIsMyBatch.ipynb +++ b/src/HowBadIsMyBatch.ipynb @@ -2,19 +2,10 @@ "cells": [ { "cell_type": "code", - "execution_count": 1, + "execution_count": null, "id": "9de5907f-18f5-4cb1-903e-26028ff1fa03", "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "2023-10-03 00:48:04.102691: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: SSE4.1 SSE4.2 AVX AVX2 FMA\n", - "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n" - ] - } - ], + "outputs": [], "source": [ "from CountryCountsByBatchcodeTable2BarChartDescriptionTableConverter import CountryCountsByBatchcodeTable2BarChartDescriptionTableConverter\n", "from JensenShannonDistance2BarChartDescriptionColumnAdder import JensenShannonDistance2BarChartDescriptionColumnAdder\n", @@ -31,6 +22,7 @@ "from CountryColumnsMerger import CountryColumnsMerger\n", "from datetime import datetime\n", "from VAERSFileDownloader import updateVAERSFiles\n", + "from GoogleAnalytics.RegionCountsByBatchcodeTablesMerger import RegionCountsByBatchcodeTablesMerger\n", "from IOUtils import IOUtils\n", "import os\n", "import pandas as pd\n", @@ -41,38 +33,20 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": null, "id": "d1e4fa9e", "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "03.10.2023, 00:48:07 Uhr\n" - ] - } - ], + "outputs": [], "source": [ "print(datetime.now().strftime(\"%d.%m.%Y, %H:%M:%S Uhr\"))" ] }, { "cell_type": "code", - "execution_count": 3, + "execution_count": null, "id": "ffad1c04", "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - " lastUpdated: 2023-09-29 00:00:00\n", - "lastUpdatedDataSource: 2023-09-29 00:00:00\n", - "needsUpdate: False\n" - ] - } - ], + "outputs": [], "source": [ "dateProvider = DateProvider()\n", "print(' lastUpdated:', dateProvider.getLastUpdated())\n", @@ -83,7 +57,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": null, "id": "194b7357", "metadata": {}, "outputs": [], @@ -105,7 +79,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": null, "id": "58333a19", "metadata": {}, "outputs": [], @@ -115,649 +89,30 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": null, "id": "f10b558f", "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
VAX_TYPEVAX_MANUVAX_LOTVAX_DOSE_SERIESCOUNTRY
VAERS_ID
902418COVID19PFIZER\\BIONTECHEH98991<NA>
902440COVID19PFIZER\\BIONTECHEH 98991<NA>
902446COVID19PFIZER\\BIONTECHEH98991<NA>
902464COVID19PFIZER\\BIONTECHEH9899UNK<NA>
902465COVID19PFIZER\\BIONTECHEH98991<NA>
..................
2684965COVID19PFIZER\\BIONTECHHD98351<NA>
2684975COVID19MODERNA216C453<NA>
2684979COVID19MODERNA037A22B1<NA>
2684982COVID19MODERNA30046753<NA>
2684990COVID19MODERNANDC:80777-0102-1<NA>
\n", - "

1076871 rows × 5 columns

\n", - "
" - ], - "text/plain": [ - " VAX_TYPE VAX_MANU VAX_LOT VAX_DOSE_SERIES COUNTRY\n", - "VAERS_ID \n", - "902418 COVID19 PFIZER\\BIONTECH EH9899 1 \n", - "902440 COVID19 PFIZER\\BIONTECH EH 9899 1 \n", - "902446 COVID19 PFIZER\\BIONTECH EH9899 1 \n", - "902464 COVID19 PFIZER\\BIONTECH EH9899 UNK \n", - "902465 COVID19 PFIZER\\BIONTECH EH9899 1 \n", - "... ... ... ... ... ...\n", - "2684965 COVID19 PFIZER\\BIONTECH HD9835 1 \n", - "2684975 COVID19 MODERNA 216C45 3 \n", - "2684979 COVID19 MODERNA 037A22B 1 \n", - "2684982 COVID19 MODERNA 3004675 3 \n", - "2684990 COVID19 MODERNA NDC:80777-0102- 1 \n", - "\n", - "[1076871 rows x 5 columns]" - ] - }, - "execution_count": 6, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "international_VAERSVAX_Covid19\n" ] }, { "cell_type": "code", - "execution_count": 7, + "execution_count": null, "id": "3e0908fe", "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
SYMPTOM1SYMPTOM2SYMPTOM3SYMPTOM4SYMPTOM5
VAERS_ID
855017ArthralgiaChillsInjection site painPyrexiaNaN
855018ChillsFatigueHypertensionHypoaesthesiaInjected limb mobility decreased
855018Muscular weaknessPain in extremityPyrexiaTremorVertigo
855019PainPruritusRashNaNNaN
855020ChillsInfluenza like illnessMyalgiaPain in extremityPyrexia
..................
2684975Haemodynamic testHypoaesthesiaLaboratory testMagnetic resonance imaging abdominalMagnetic resonance imaging thoracic
2684975Nervous system disorderRash macularRenal cystRespiratory distressRespiratory failure
2684975VomitingNaNNaNNaNNaN
2684982Anaemia macrocyticBlood magnesiumHypercalcaemiaHypomagnesaemiaMagnesium deficiency
2684982Nerve injuryParaesthesiaSARS-CoV-2 testNaNNaN
\n", - "

2584689 rows × 5 columns

\n", - "
" - ], - "text/plain": [ - " SYMPTOM1 SYMPTOM2 \\\n", - "VAERS_ID \n", - "855017 Arthralgia Chills \n", - "855018 Chills Fatigue \n", - "855018 Muscular weakness Pain in extremity \n", - "855019 Pain Pruritus \n", - "855020 Chills Influenza like illness \n", - "... ... ... \n", - "2684975 Haemodynamic test Hypoaesthesia \n", - "2684975 Nervous system disorder Rash macular \n", - "2684975 Vomiting NaN \n", - "2684982 Anaemia macrocytic Blood magnesium \n", - "2684982 Nerve injury Paraesthesia \n", - "\n", - " SYMPTOM3 SYMPTOM4 \\\n", - "VAERS_ID \n", - "855017 Injection site pain Pyrexia \n", - "855018 Hypertension Hypoaesthesia \n", - "855018 Pyrexia Tremor \n", - "855019 Rash NaN \n", - "855020 Myalgia Pain in extremity \n", - "... ... ... \n", - "2684975 Laboratory test Magnetic resonance imaging abdominal \n", - "2684975 Renal cyst Respiratory distress \n", - "2684975 NaN NaN \n", - "2684982 Hypercalcaemia Hypomagnesaemia \n", - "2684982 SARS-CoV-2 test NaN \n", - "\n", - " SYMPTOM5 \n", - "VAERS_ID \n", - "855017 NaN \n", - "855018 Injected limb mobility decreased \n", - "855018 Vertigo \n", - "855019 NaN \n", - "855020 Pyrexia \n", - "... ... \n", - "2684975 Magnetic resonance imaging thoracic \n", - "2684975 Respiratory failure \n", - "2684975 NaN \n", - "2684982 Magnesium deficiency \n", - "2684982 NaN \n", - "\n", - "[2584689 rows x 5 columns]" - ] - }, - "execution_count": 7, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "international_VAERSSYMPTOMS\n" ] }, { "cell_type": "code", - "execution_count": 8, + "execution_count": null, "id": "781ac80e", "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
RECVDATEDIEDL_THREATER_VISITHOSPITALDISABLESPLTTYPEVAX_TYPEVAX_MANUVAX_LOTVAX_DOSE_SERIESCOUNTRYSEVERE
VAERS_ID
9024182020-12-1500000NaNCOVID19PFIZER\\BIONTECHEH98991United States0
9024402020-12-1500000NaNCOVID19PFIZER\\BIONTECHEH 98991United States0
9024462020-12-1500000NaNCOVID19PFIZER\\BIONTECHEH98991United States0
9024642020-12-1500000NaNCOVID19PFIZER\\BIONTECHEH9899UNKUnited States0
9024652020-12-1500000NaNCOVID19PFIZER\\BIONTECHEH98991United States0
..........................................
26849152023-09-2101010NZPFIZER INCPV20230015804COVID19PFIZER\\BIONTECH<NA>1New Zealand1
26849162023-09-2100010NZPFIZER INCPV20230015804COVID19PFIZER\\BIONTECH<NA>1New Zealand0
26849192023-09-2100001NaNCOVID19PFIZER\\BIONTECHFA46321<NA>1
26849752023-09-2200000NaNCOVID19MODERNA216C453<NA>0
26849822023-09-2200010NaNCOVID19MODERNA30046753<NA>0
\n", - "

1596698 rows × 13 columns

\n", - "
" - ], - "text/plain": [ - " RECVDATE DIED L_THREAT ER_VISIT HOSPITAL DISABLE \\\n", - "VAERS_ID \n", - "902418 2020-12-15 0 0 0 0 0 \n", - "902440 2020-12-15 0 0 0 0 0 \n", - "902446 2020-12-15 0 0 0 0 0 \n", - "902464 2020-12-15 0 0 0 0 0 \n", - "902465 2020-12-15 0 0 0 0 0 \n", - "... ... ... ... ... ... ... \n", - "2684915 2023-09-21 0 1 0 1 0 \n", - "2684916 2023-09-21 0 0 0 1 0 \n", - "2684919 2023-09-21 0 0 0 0 1 \n", - "2684975 2023-09-22 0 0 0 0 0 \n", - "2684982 2023-09-22 0 0 0 1 0 \n", - "\n", - " SPLTTYPE VAX_TYPE VAX_MANU VAX_LOT \\\n", - "VAERS_ID \n", - "902418 NaN COVID19 PFIZER\\BIONTECH EH9899 \n", - "902440 NaN COVID19 PFIZER\\BIONTECH EH 9899 \n", - "902446 NaN COVID19 PFIZER\\BIONTECH EH9899 \n", - "902464 NaN COVID19 PFIZER\\BIONTECH EH9899 \n", - "902465 NaN COVID19 PFIZER\\BIONTECH EH9899 \n", - "... ... ... ... ... \n", - "2684915 NZPFIZER INCPV20230015804 COVID19 PFIZER\\BIONTECH \n", - "2684916 NZPFIZER INCPV20230015804 COVID19 PFIZER\\BIONTECH \n", - "2684919 NaN COVID19 PFIZER\\BIONTECH FA4632 \n", - "2684975 NaN COVID19 MODERNA 216C45 \n", - "2684982 NaN COVID19 MODERNA 3004675 \n", - "\n", - " VAX_DOSE_SERIES COUNTRY SEVERE \n", - "VAERS_ID \n", - "902418 1 United States 0 \n", - "902440 1 United States 0 \n", - "902446 1 United States 0 \n", - "902464 UNK United States 0 \n", - "902465 1 United States 0 \n", - "... ... ... ... \n", - "2684915 1 New Zealand 1 \n", - "2684916 1 New Zealand 0 \n", - "2684919 1 1 \n", - "2684975 3 0 \n", - "2684982 3 0 \n", - "\n", - "[1596698 rows x 13 columns]" - ] - }, - "execution_count": 8, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "internationalVaersCovid19 = getInternationalVaersCovid19(dataDir = 'VAERS', years = years_from_start_of_COVID_vaccination_to_present)\n", "internationalVaersCovid19" @@ -765,295 +120,10 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": null, "id": "29366235", "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
RECVDATEDIEDL_THREATER_VISITHOSPITALDISABLESPLTTYPEVAX_TYPEVAX_MANUVAX_LOTVAX_DOSE_SERIESSEVERECOUNTRY
VAERS_ID
9024182020-12-1500000NaNCOVID19PFIZER\\BIONTECHEH989910United States
9024402020-12-1500000NaNCOVID19PFIZER\\BIONTECHEH 989910United States
9024462020-12-1500000NaNCOVID19PFIZER\\BIONTECHEH989910United States
9024642020-12-1500000NaNCOVID19PFIZER\\BIONTECHEH9899UNK0United States
9024652020-12-1500000NaNCOVID19PFIZER\\BIONTECHEH989910United States
..........................................
26849752023-09-2200000NaNCOVID19MODERNA216C4530<NA>
26849792023-09-2200001NaNCOVID19MODERNA037A22B11United States
26849822023-09-2200010NaNCOVID19MODERNA300467530<NA>
26849892023-09-2200000NaNCOVID19MODERNA<NA>UNK0United States
26849902023-09-2200000NaNCOVID19MODERNANDC:80777-0102-10United States
\n", - "

1596698 rows × 13 columns

\n", - "
" - ], - "text/plain": [ - " RECVDATE DIED L_THREAT ER_VISIT HOSPITAL DISABLE SPLTTYPE \\\n", - "VAERS_ID \n", - "902418 2020-12-15 0 0 0 0 0 NaN \n", - "902440 2020-12-15 0 0 0 0 0 NaN \n", - "902446 2020-12-15 0 0 0 0 0 NaN \n", - "902464 2020-12-15 0 0 0 0 0 NaN \n", - "902465 2020-12-15 0 0 0 0 0 NaN \n", - "... ... ... ... ... ... ... ... \n", - "2684975 2023-09-22 0 0 0 0 0 NaN \n", - "2684979 2023-09-22 0 0 0 0 1 NaN \n", - "2684982 2023-09-22 0 0 0 1 0 NaN \n", - "2684989 2023-09-22 0 0 0 0 0 NaN \n", - "2684990 2023-09-22 0 0 0 0 0 NaN \n", - "\n", - " VAX_TYPE VAX_MANU VAX_LOT VAX_DOSE_SERIES SEVERE \\\n", - "VAERS_ID \n", - "902418 COVID19 PFIZER\\BIONTECH EH9899 1 0 \n", - "902440 COVID19 PFIZER\\BIONTECH EH 9899 1 0 \n", - "902446 COVID19 PFIZER\\BIONTECH EH9899 1 0 \n", - "902464 COVID19 PFIZER\\BIONTECH EH9899 UNK 0 \n", - "902465 COVID19 PFIZER\\BIONTECH EH9899 1 0 \n", - "... ... ... ... ... ... \n", - "2684975 COVID19 MODERNA 216C45 3 0 \n", - "2684979 COVID19 MODERNA 037A22B 1 1 \n", - "2684982 COVID19 MODERNA 3004675 3 0 \n", - "2684989 COVID19 MODERNA UNK 0 \n", - "2684990 COVID19 MODERNA NDC:80777-0102- 1 0 \n", - "\n", - " COUNTRY \n", - "VAERS_ID \n", - "902418 United States \n", - "902440 United States \n", - "902446 United States \n", - "902464 United States \n", - "902465 United States \n", - "... ... \n", - "2684975 \n", - "2684979 United States \n", - "2684982 \n", - "2684989 United States \n", - "2684990 United States \n", - "\n", - "[1596698 rows x 13 columns]" - ] - }, - "execution_count": 9, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "internationalVaersCovid19 = CountryColumnsMerger.mergeCountryColumnOfSrcIntoDst(\n", " src = getInternationalVaersCovid19BeforeDeletion(),\n", @@ -1063,216 +133,10 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": null, "id": "0915aa5a", "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
BatchAdverse Reaction ReportsDeathsDisabilitiesLife Threatening IllnessesCompanySevere reportsLethality
0C2021050263300UNKNOWN MANUFACTURERNaNNaN
1J2021000343300UNKNOWN MANUFACTURERNaNNaN
2JJ-21C14-024040JANSSENNaNNaN
3J2021030113300UNKNOWN MANUFACTURERNaNNaN
4J202103113300UNKNOWN MANUFACTURERNaNNaN
...........................
922621C19-0220000JANSSENNaNNaN
922721C19-056000JANSSENNaNNaN
922821C13-048000JANSSENNaNNaN
922921C11023000JANSSENNaNNaN
923021C14-0510000JANSSENNaNNaN
\n", - "

9231 rows × 8 columns

\n", - "
" - ], - "text/plain": [ - " Batch Adverse Reaction Reports Deaths Disabilities \\\n", - "0 C202105026 3 3 0 \n", - "1 J202100034 3 3 0 \n", - "2 JJ-21C14-02 4 0 4 \n", - "3 J202103011 3 3 0 \n", - "4 J20210311 3 3 0 \n", - "... ... ... ... ... \n", - "9226 21C19-02 20 0 0 \n", - "9227 21C19-05 6 0 0 \n", - "9228 21C13-04 8 0 0 \n", - "9229 21C1102 3 0 0 \n", - "9230 21C14-05 10 0 0 \n", - "\n", - " Life Threatening Illnesses Company Severe reports \\\n", - "0 0 UNKNOWN MANUFACTURER NaN \n", - "1 0 UNKNOWN MANUFACTURER NaN \n", - "2 0 JANSSEN NaN \n", - "3 0 UNKNOWN MANUFACTURER NaN \n", - "4 0 UNKNOWN MANUFACTURER NaN \n", - "... ... ... ... \n", - "9226 0 JANSSEN NaN \n", - "9227 0 JANSSEN NaN \n", - "9228 0 JANSSEN NaN \n", - "9229 0 JANSSEN NaN \n", - "9230 0 JANSSEN NaN \n", - "\n", - " Lethality \n", - "0 NaN \n", - "1 NaN \n", - "2 NaN \n", - "3 NaN \n", - "4 NaN \n", - "... ... \n", - "9226 NaN \n", - "9227 NaN \n", - "9228 NaN \n", - "9229 NaN \n", - "9230 NaN \n", - "\n", - "[9231 rows x 8 columns]" - ] - }, - "execution_count": 10, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "batchCodeTable = createGlobalBatchCodeTable(\n", " deleteEntriesWithADRsLessThanOrEqual = 2,\n", @@ -1330,154 +194,10 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": null, "id": "70fcc420", "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/home/frankknoll/Dokumente/Corona/projects/HowBadIsMyBatch/src/CountriesByBatchcodeProvider.py:39: FutureWarning: The behavior of indexing on a MultiIndex with a nested sequence of labels is deprecated and will change in a future version. `series.loc[label, sequence]` will raise if any members of 'sequence' or not present in the index's second level. To retain the old behavior, use `series.index.isin(sequence, level=1)`\n", - " return countryCountsByBatchcode.loc[(batchcodes2Retain, slice(None)), :]\n" - ] - }, - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
COUNTRY_COUNT_BY_VAX_LOT ClickedCOUNTRY_COUNT_BY_VAX_LOT Before Deletion
VAX_LOTCOUNTRY
J202100034Austria10
Germany10
United States10
JJ-21C14-02Belgium13
Poland10
............
21C13-04Switzerland10
United States10
21C1102France02
Germany30
21C14-05France010
\n", - "

29310 rows × 2 columns

\n", - "
" - ], - "text/plain": [ - " COUNTRY_COUNT_BY_VAX_LOT Clicked \\\n", - "VAX_LOT COUNTRY \n", - "J202100034 Austria 1 \n", - " Germany 1 \n", - " United States 1 \n", - "JJ-21C14-02 Belgium 1 \n", - " Poland 1 \n", - "... ... \n", - "21C13-04 Switzerland 1 \n", - " United States 1 \n", - "21C1102 France 0 \n", - " Germany 3 \n", - "21C14-05 France 0 \n", - "\n", - " COUNTRY_COUNT_BY_VAX_LOT Before Deletion \n", - "VAX_LOT COUNTRY \n", - "J202100034 Austria 0 \n", - " Germany 0 \n", - " United States 0 \n", - "JJ-21C14-02 Belgium 3 \n", - " Poland 0 \n", - "... ... \n", - "21C13-04 Switzerland 0 \n", - " United States 0 \n", - "21C1102 France 2 \n", - " Germany 0 \n", - "21C14-05 France 10 \n", - "\n", - "[29310 rows x 2 columns]" - ] - }, - "execution_count": 11, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "countryCountsByBatchcode = filterByBatchcodes(getCountryCountsByBatchcodeTable(), batchCodeTable['Batch'].values)\n", "countryCountsByBatchcode" @@ -1485,165 +205,46 @@ }, { "cell_type": "code", - "execution_count": 42, - "id": "0d755bc8", + "execution_count": null, + "id": "0257505b", "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
COUNTRY_COUNT_BY_VAX_LOT ClickedCOUNTRY_COUNT_BY_VAX_LOT Before Deletion
VAX_LOTCOUNTRY
EX8679Germany10991132
FC3095Germany8711099
FD7958Germany8461049
FD9234Germany759878
ET3045Germany704716
............
026C21AGermany01
000 106AGermany03
0000437Germany03
JO7BX03Germany02
6202Germany01
\n", - "

2520 rows × 2 columns

\n", - "
" - ], - "text/plain": [ - " COUNTRY_COUNT_BY_VAX_LOT Clicked \\\n", - "VAX_LOT COUNTRY \n", - "EX8679 Germany 1099 \n", - "FC3095 Germany 871 \n", - "FD7958 Germany 846 \n", - "FD9234 Germany 759 \n", - "ET3045 Germany 704 \n", - "... ... \n", - "026C21A Germany 0 \n", - "000 106A Germany 0 \n", - "0000437 Germany 0 \n", - "JO7BX03 Germany 0 \n", - "6202 Germany 0 \n", - "\n", - " COUNTRY_COUNT_BY_VAX_LOT Before Deletion \n", - "VAX_LOT COUNTRY \n", - "EX8679 Germany 1132 \n", - "FC3095 Germany 1099 \n", - "FD7958 Germany 1049 \n", - "FD9234 Germany 878 \n", - "ET3045 Germany 716 \n", - "... ... \n", - "026C21A Germany 1 \n", - "000 106A Germany 3 \n", - "0000437 Germany 3 \n", - "JO7BX03 Germany 2 \n", - "6202 Germany 1 \n", - "\n", - "[2520 rows x 2 columns]" - ] - }, - "execution_count": 42, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ - "# df = countryCountsByBatchcode.loc[(slice(None), 'Germany'), :][['COUNTRY_COUNT_BY_VAX_LOT Clicked']].sort_values(by = 'COUNTRY_COUNT_BY_VAX_LOT Clicked', ascending = False)\n", - "df = countryCountsByBatchcode.loc[(slice(None), 'Germany'), :].sort_values(by = 'COUNTRY_COUNT_BY_VAX_LOT Clicked', ascending = False)\n", + "regionCountsByClickedBatchcodeTable = RegionCountsByBatchcodeTablesMerger.getRegionCountsByClickedBatchcode('data/GoogleAnalytics')\n", + "regionCountsByClickedBatchcodeTable" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "c276eede", + "metadata": {}, + "outputs": [], + "source": [ + "df = regionCountsByClickedBatchcodeTable.loc[(slice(None), 'Germany', slice(None)), :].sort_values(by = 'VAX_LOT', ascending = False)\n", "df" ] }, { "cell_type": "code", - "execution_count": 43, - "id": "c0ada157", + "execution_count": null, + "id": "64c57c23", "metadata": {}, "outputs": [], "source": [ - "df.to_excel('tmp/tst.xlsx')" + "df.to_excel('tmp/germany.xlsx')" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "0d755bc8", + "metadata": {}, + "outputs": [], + "source": [ + "# df = countryCountsByBatchcode.loc[(slice(None), 'Germany'), :][['COUNTRY_COUNT_BY_VAX_LOT Clicked']].sort_values(by = 'COUNTRY_COUNT_BY_VAX_LOT Clicked', ascending = False)\n", + "df = countryCountsByBatchcode.loc[(slice(None), 'Germany'), :].sort_values(by = 'COUNTRY_COUNT_BY_VAX_LOT Clicked', ascending = False)\n", + "df" ] }, {