diff --git a/src/HowBadIsMyBatch.ipynb b/src/HowBadIsMyBatch.ipynb index 737bc77aff8..0c5244e27df 100644 --- a/src/HowBadIsMyBatch.ipynb +++ b/src/HowBadIsMyBatch.ipynb @@ -168,151 +168,1039 @@ ] }, { - "attachments": {}, - "cell_type": "markdown", - "id": "2d93b511", + "cell_type": "code", + "execution_count": 6, + "id": "dc8fa52b", "metadata": {}, + "outputs": [], "source": [ - "# Vaccine Distribution by Zipcode" + "import pandas as pd\n", + "from CountriesByBatchcodeProvider import getCountriesByClickedBatchcode, getCountriesByBatchcodeBeforeDeletion" ] }, { "cell_type": "code", - "execution_count": null, - "id": "cfcbad44", + "execution_count": 2, + "id": "b01a5f94", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "b'Skipping line 9: expected 22 fields, saw 23\\n'\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", + "
Countries
Clicked Batchcode
(not set){Germany, Poland, United Kingdom, Australia, B...
FE6208{Germany, Poland, United Kingdom, Australia, B...
039K20A{Sweden, United States, Spain, France, Austral...
EN6201{Sweden, United States, Spain, France, Austral...
FD6840{Sweden, United States, Spain, France, Austral...
......
ZTC540693{United States}
ZU5A21A{}
ZZ3249{Hungary}
026L20A{United States}
ÂK4244{Hungary}
\n", + "

5392 rows × 1 columns

\n", + "
" + ], + "text/plain": [ + " Countries\n", + "Clicked Batchcode \n", + "(not set) {Germany, Poland, United Kingdom, Australia, B...\n", + "FE6208 {Germany, Poland, United Kingdom, Australia, B...\n", + "039K20A {Sweden, United States, Spain, France, Austral...\n", + "EN6201 {Sweden, United States, Spain, France, Austral...\n", + "FD6840 {Sweden, United States, Spain, France, Austral...\n", + "... ...\n", + "ZTC540693 {United States}\n", + "ZU5A21A {}\n", + "ZZ3249 {Hungary}\n", + "  026L20A {United States}\n", + "ÂK4244 {Hungary}\n", + "\n", + "[5392 rows x 1 columns]" + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "vaccineDistributionByZipcode = pd.read_excel(\n", - " io = 'tmp/Amended-22-01962-Pfizer-2022-0426-pulled-2022-0823.xlsx',\n", - " usecols = ['PROVIDER_NAME', 'ZIPCODE_SHP', 'LOT_NUMBER', 'DOSES_SHIPPED'],\n", - " dtype = {'DOSES_SHIPPED': 'int'})\n", - "vaccineDistributionByZipcode" + "countriesByClickedBatchcode = getCountriesByClickedBatchcode()\n", + "countriesByClickedBatchcode" ] }, { "cell_type": "code", - "execution_count": null, - "id": "59c745d2", + "execution_count": 3, + "id": "521ee957", "metadata": {}, - "outputs": [], + "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", + "
Countries
VAX_LOT
6362737[United States]
SCH2[United States]
NO72A[Philippines]
EW096[United States]
FS1926[United States]
......
211221A[United States]
2112D21A[United States]
2114214[United States]
211421A[United States]
Ø94F21A[Norway]
\n", + "

47901 rows × 1 columns

\n", + "
" + ], + "text/plain": [ + " Countries\n", + "VAX_LOT \n", + "6362737 [United States]\n", + "SCH2 [United States]\n", + "NO72A [Philippines]\n", + "EW096 [United States]\n", + "FS1926 [United States]\n", + "... ...\n", + "211221A [United States]\n", + "2112D21A [United States]\n", + "2114214 [United States]\n", + "211421A [United States]\n", + "Ø94F21A [Norway]\n", + "\n", + "[47901 rows x 1 columns]" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "from VaccineDistributionByZipcodeSimplifier import VaccineDistributionByZipcodeSimplifier\n", + "countriesByBatchcodeBeforeDeletion = getCountriesByBatchcodeBeforeDeletion()\n", + "countriesByBatchcodeBeforeDeletion" + ] + }, + { + "cell_type": "code", + "execution_count": 41, + "id": "c91d1b4d", + "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", + "
Countries ClickedCountries Before Deletion
VAX_LOT
FE6208{Germany, Poland, United Kingdom, Australia, B...[Austria, Croatia, Czechia, Germany, Greece, H...
039K20A{Sweden, United States, Spain, France, Austral...[United States]
EN6201{Sweden, United States, Spain, France, Austral...[United Kingdom, United States]
FD6840{Sweden, United States, Spain, France, Austral...[Austria, Croatia, Cyprus, Czechia, Germany, G...
FF0680{Sweden, United States, Canada, Brazil, German...[Austria, Croatia, Czechia, Finland, France, G...
.........
ZTC540693{United States}[United States]
ZU5A21A{}[United States]
ZZ3249{Hungary}[United States]
026L20A{United States}[United States]
ÂK4244{Hungary}[United Kingdom]
\n", + "

5188 rows × 2 columns

\n", + "
" + ], + "text/plain": [ + " Countries Clicked \\\n", + "VAX_LOT \n", + "FE6208 {Germany, Poland, United Kingdom, Australia, B... \n", + "039K20A {Sweden, United States, Spain, France, Austral... \n", + "EN6201 {Sweden, United States, Spain, France, Austral... \n", + "FD6840 {Sweden, United States, Spain, France, Austral... \n", + "FF0680 {Sweden, United States, Canada, Brazil, German... \n", + "... ... \n", + "ZTC540693 {United States} \n", + "ZU5A21A {} \n", + "ZZ3249 {Hungary} \n", + "  026L20A {United States} \n", + "ÂK4244 {Hungary} \n", + "\n", + " Countries Before Deletion \n", + "VAX_LOT \n", + "FE6208 [Austria, Croatia, Czechia, Germany, Greece, H... \n", + "039K20A [United States] \n", + "EN6201 [United Kingdom, United States] \n", + "FD6840 [Austria, Croatia, Cyprus, Czechia, Germany, G... \n", + "FF0680 [Austria, Croatia, Czechia, Finland, France, G... \n", + "... ... \n", + "ZTC540693 [United States] \n", + "ZU5A21A [United States] \n", + "ZZ3249 [United States] \n", + "  026L20A [United States] \n", + "ÂK4244 [United Kingdom] \n", + "\n", + "[5188 rows x 2 columns]" + ] + }, + "execution_count": 41, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "res = pd.merge(\n", + " countriesByClickedBatchcode,\n", + " countriesByBatchcodeBeforeDeletion,\n", + " how = 'inner',\n", + " left_index = True,\n", + " right_index = True,\n", + " suffixes=(' Clicked', ' Before Deletion'))\n", + "res.index.name = 'VAX_LOT'\n", + "res" + ] + }, + { + "cell_type": "code", + "execution_count": 42, + "id": "df6e5ef1", + "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", + "
Countries ClickedCountries Before Deletion
VAX_LOT
FE6208{Germany, Poland, United Kingdom, Australia, B...{Lithuania, Spain, Czechia, Greece, Germany, A...
039K20A{Sweden, United States, Spain, France, Austral...{United States}
EN6201{Sweden, United States, Spain, France, Austral...{United Kingdom, United States}
FD6840{Sweden, United States, Spain, France, Austral...{Lithuania, Cyprus, Czechia, Greece, Germany, ...
FF0680{Sweden, United States, Canada, Brazil, German...{Portugal, Sweden, Czechia, France, Finland, G...
.........
ZTC540693{United States}{United States}
ZU5A21A{}{United States}
ZZ3249{Hungary}{United States}
026L20A{United States}{United States}
ÂK4244{Hungary}{United Kingdom}
\n", + "

5188 rows × 2 columns

\n", + "
" + ], + "text/plain": [ + " Countries Clicked \\\n", + "VAX_LOT \n", + "FE6208 {Germany, Poland, United Kingdom, Australia, B... \n", + "039K20A {Sweden, United States, Spain, France, Austral... \n", + "EN6201 {Sweden, United States, Spain, France, Austral... \n", + "FD6840 {Sweden, United States, Spain, France, Austral... \n", + "FF0680 {Sweden, United States, Canada, Brazil, German... \n", + "... ... \n", + "ZTC540693 {United States} \n", + "ZU5A21A {} \n", + "ZZ3249 {Hungary} \n", + "  026L20A {United States} \n", + "ÂK4244 {Hungary} \n", + "\n", + " Countries Before Deletion \n", + "VAX_LOT \n", + "FE6208 {Lithuania, Spain, Czechia, Greece, Germany, A... \n", + "039K20A {United States} \n", + "EN6201 {United Kingdom, United States} \n", + "FD6840 {Lithuania, Cyprus, Czechia, Greece, Germany, ... \n", + "FF0680 {Portugal, Sweden, Czechia, France, Finland, G... \n", + "... ... \n", + "ZTC540693 {United States} \n", + "ZU5A21A {United States} \n", + "ZZ3249 {United States} \n", + "  026L20A {United States} \n", + "ÂK4244 {United Kingdom} \n", + "\n", + "[5188 rows x 2 columns]" + ] + }, + "execution_count": 42, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "res['Countries Before Deletion'] = res['Countries Before Deletion'].map(set)\n", + "res" + ] + }, + { + "cell_type": "code", + "execution_count": 43, + "id": "62d68836", + "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", + "
Countries ClickedCountries Before DeletionCountries Intersection
VAX_LOT
FE6208{Germany, Poland, United Kingdom, Australia, B...{Lithuania, Spain, Czechia, Greece, Germany, A...[Austria, Germany, Hungary, Spain, Sweden, Uni...
039K20A{Sweden, United States, Spain, France, Austral...{United States}[United States]
EN6201{Sweden, United States, Spain, France, Austral...{United Kingdom, United States}[United Kingdom, United States]
FD6840{Sweden, United States, Spain, France, Austral...{Lithuania, Cyprus, Czechia, Greece, Germany, ...[Austria, Germany, Hungary, Sweden, United Kin...
FF0680{Sweden, United States, Canada, Brazil, German...{Portugal, Sweden, Czechia, France, Finland, G...[Austria, Germany, Hungary, Italy, Netherlands...
............
ZTC540693{United States}{United States}[United States]
ZU5A21A{}{United States}[]
ZZ3249{Hungary}{United States}[]
026L20A{United States}{United States}[United States]
ÂK4244{Hungary}{United Kingdom}[]
\n", + "

5188 rows × 3 columns

\n", + "
" + ], + "text/plain": [ + " Countries Clicked \\\n", + "VAX_LOT \n", + "FE6208 {Germany, Poland, United Kingdom, Australia, B... \n", + "039K20A {Sweden, United States, Spain, France, Austral... \n", + "EN6201 {Sweden, United States, Spain, France, Austral... \n", + "FD6840 {Sweden, United States, Spain, France, Austral... \n", + "FF0680 {Sweden, United States, Canada, Brazil, German... \n", + "... ... \n", + "ZTC540693 {United States} \n", + "ZU5A21A {} \n", + "ZZ3249 {Hungary} \n", + "  026L20A {United States} \n", + "ÂK4244 {Hungary} \n", + "\n", + " Countries Before Deletion \\\n", + "VAX_LOT \n", + "FE6208 {Lithuania, Spain, Czechia, Greece, Germany, A... \n", + "039K20A {United States} \n", + "EN6201 {United Kingdom, United States} \n", + "FD6840 {Lithuania, Cyprus, Czechia, Greece, Germany, ... \n", + "FF0680 {Portugal, Sweden, Czechia, France, Finland, G... \n", + "... ... \n", + "ZTC540693 {United States} \n", + "ZU5A21A {United States} \n", + "ZZ3249 {United States} \n", + "  026L20A {United States} \n", + "ÂK4244 {United Kingdom} \n", + "\n", + " Countries Intersection \n", + "VAX_LOT \n", + "FE6208 [Austria, Germany, Hungary, Spain, Sweden, Uni... \n", + "039K20A [United States] \n", + "EN6201 [United Kingdom, United States] \n", + "FD6840 [Austria, Germany, Hungary, Sweden, United Kin... \n", + "FF0680 [Austria, Germany, Hungary, Italy, Netherlands... \n", + "... ... \n", + "ZTC540693 [United States] \n", + "ZU5A21A [] \n", + "ZZ3249 [] \n", + "  026L20A [United States] \n", + "ÂK4244 [] \n", + "\n", + "[5188 rows x 3 columns]" + ] + }, + "execution_count": 43, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "def intersect(series):\n", + " return sorted(set.intersection(*series))\n", "\n", - "vaccineDistributionByZipcode = VaccineDistributionByZipcodeSimplifier.sumDoses(vaccineDistributionByZipcode)\n", - "vaccineDistributionByZipcode" + "res['Countries Intersection'] = res.apply(intersect, axis = 'columns')\n", + "res" ] }, { "cell_type": "code", - "execution_count": null, - "id": "8cd250f7", + "execution_count": 46, + "id": "a700cb34", "metadata": {}, - "outputs": [], + "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", + "
Countries ClickedCountries Before DeletionCountries Intersection
VAX_LOT
FH3253{Australia, Malaysia}{Austria, Switzerland, Belgium}[]
FE2090{United Kingdom, Australia, Germany}{Estonia, Spain, France, Denmark, South Africa...[]
FF0884{Australia, Malaysia, Japan}{Ireland, Denmark}[]
FG2872{Malaysia, Brazil}{Georgia, United States, Israel}[]
FG3716{Australia, Italy, Malaysia}{Estonia, Spain, France, Norway, Austria, Denm...[]
............
YFL8095{Japan}{United States}[]
Z07AZ1A{Brazil}{United States}[]
ZU5A21A{}{United States}[]
ZZ3249{Hungary}{United States}[]
ÂK4244{Hungary}{United Kingdom}[]
\n", + "

1345 rows × 3 columns

\n", + "
" + ], + "text/plain": [ + " Countries Clicked \\\n", + "VAX_LOT \n", + "FH3253 {Australia, Malaysia} \n", + "FE2090 {United Kingdom, Australia, Germany} \n", + "FF0884 {Australia, Malaysia, Japan} \n", + "FG2872 {Malaysia, Brazil} \n", + "FG3716 {Australia, Italy, Malaysia} \n", + "... ... \n", + "YFL8095 {Japan} \n", + "Z07AZ1A {Brazil} \n", + "ZU5A21A {} \n", + "ZZ3249 {Hungary} \n", + "ÂK4244 {Hungary} \n", + "\n", + " Countries Before Deletion \\\n", + "VAX_LOT \n", + "FH3253 {Austria, Switzerland, Belgium} \n", + "FE2090 {Estonia, Spain, France, Denmark, South Africa... \n", + "FF0884 {Ireland, Denmark} \n", + "FG2872 {Georgia, United States, Israel} \n", + "FG3716 {Estonia, Spain, France, Norway, Austria, Denm... \n", + "... ... \n", + "YFL8095 {United States} \n", + "Z07AZ1A {United States} \n", + "ZU5A21A {United States} \n", + "ZZ3249 {United States} \n", + "ÂK4244 {United Kingdom} \n", + "\n", + " Countries Intersection \n", + "VAX_LOT \n", + "FH3253 [] \n", + "FE2090 [] \n", + "FF0884 [] \n", + "FG2872 [] \n", + "FG3716 [] \n", + "... ... \n", + "YFL8095 [] \n", + "Z07AZ1A [] \n", + "ZU5A21A [] \n", + "ZZ3249 [] \n", + "ÂK4244 [] \n", + "\n", + "[1345 rows x 3 columns]" + ] + }, + "execution_count": 46, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "OVERALL_DOSES_SHIPPED_by_LOT_NUMBER = vaccineDistributionByZipcode.groupby('LOT_NUMBER').agg(OVERALL_DOSES_SHIPPED = pd.NamedAgg(column = 'DOSES_SHIPPED', aggfunc = sum))\n", - "OVERALL_DOSES_SHIPPED_by_LOT_NUMBER" + "res[res['Countries Intersection'].apply(lambda s: len(s) == 0)]" ] }, { "cell_type": "code", - "execution_count": null, - "id": "1a5667be", + "execution_count": 50, + "id": "8fcb32f0", "metadata": {}, - "outputs": [], + "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", + "
Countries ClickedCountries Before DeletionCountries Intersection
VAX_LOT
FE6208{Germany, Poland, United Kingdom, Australia, B...{Lithuania, Spain, Czechia, Greece, Germany, A...[Austria, Germany, Hungary, Spain, Sweden, Uni...
039K20A{Sweden, United States, Spain, France, Austral...{United States}[United States]
EN6201{Sweden, United States, Spain, France, Austral...{United Kingdom, United States}[United Kingdom, United States]
FD6840{Sweden, United States, Spain, France, Austral...{Lithuania, Cyprus, Czechia, Greece, Germany, ...[Austria, Germany, Hungary, Sweden, United Kin...
FF0680{Sweden, United States, Canada, Brazil, German...{Portugal, Sweden, Czechia, France, Finland, G...[Austria, Germany, Hungary, Italy, Netherlands...
............
XXXXXX{United States}{United States}[United States]
XYZ98765{Germany}{Germany}[Germany]
Z01AZ1A{United States}{United States}[United States]
ZTC540693{United States}{United States}[United States]
026L20A{United States}{United States}[United States]
\n", + "

3843 rows × 3 columns

\n", + "
" + ], + "text/plain": [ + " Countries Clicked \\\n", + "VAX_LOT \n", + "FE6208 {Germany, Poland, United Kingdom, Australia, B... \n", + "039K20A {Sweden, United States, Spain, France, Austral... \n", + "EN6201 {Sweden, United States, Spain, France, Austral... \n", + "FD6840 {Sweden, United States, Spain, France, Austral... \n", + "FF0680 {Sweden, United States, Canada, Brazil, German... \n", + "... ... \n", + "XXXXXX {United States} \n", + "XYZ98765 {Germany} \n", + "Z01AZ1A {United States} \n", + "ZTC540693 {United States} \n", + "  026L20A {United States} \n", + "\n", + " Countries Before Deletion \\\n", + "VAX_LOT \n", + "FE6208 {Lithuania, Spain, Czechia, Greece, Germany, A... \n", + "039K20A {United States} \n", + "EN6201 {United Kingdom, United States} \n", + "FD6840 {Lithuania, Cyprus, Czechia, Greece, Germany, ... \n", + "FF0680 {Portugal, Sweden, Czechia, France, Finland, G... \n", + "... ... \n", + "XXXXXX {United States} \n", + "XYZ98765 {Germany} \n", + "Z01AZ1A {United States} \n", + "ZTC540693 {United States} \n", + "  026L20A {United States} \n", + "\n", + " Countries Intersection \n", + "VAX_LOT \n", + "FE6208 [Austria, Germany, Hungary, Spain, Sweden, Uni... \n", + "039K20A [United States] \n", + "EN6201 [United Kingdom, United States] \n", + "FD6840 [Austria, Germany, Hungary, Sweden, United Kin... \n", + "FF0680 [Austria, Germany, Hungary, Italy, Netherlands... \n", + "... ... \n", + "XXXXXX [United States] \n", + "XYZ98765 [Germany] \n", + "Z01AZ1A [United States] \n", + "ZTC540693 [United States] \n", + "  026L20A [United States] \n", + "\n", + "[3843 rows x 3 columns]" + ] + }, + "execution_count": 50, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "from OVERALL_DOSES_SHIPPEDColumnAdder import OVERALL_DOSES_SHIPPEDColumnAdder\n", - "\n", - "vaccineDistributionByZipcode = OVERALL_DOSES_SHIPPEDColumnAdder(OVERALL_DOSES_SHIPPED_by_LOT_NUMBER).addColumn(vaccineDistributionByZipcode)\n", - "vaccineDistributionByZipcode" + "res[res['Countries Intersection'].apply(lambda s: len(s) != 0)]" ] }, { "cell_type": "code", - "execution_count": null, - "id": "f77505c6", + "execution_count": 44, + "id": "7750d699", "metadata": {}, "outputs": [], "source": [ - "from ADR_by_Batchcode_Table_Factory import create_ADR_by_Batchcode_Table_4USA\n", - "\n", - "ADR_by_Batchcode_Table_4USA = create_ADR_by_Batchcode_Table_4USA(internationalVaersCovid19)\n", - "ADR_by_Batchcode_Table_4USA" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "99120c77", - "metadata": {}, - "outputs": [], - "source": [ - "from ADRColumnAdder import ADRColumnAdder\n", - "\n", - "vaccineDistributionByZipcode = ADRColumnAdder(ADR_by_Batchcode_Table_4USA).addADRColumn(vaccineDistributionByZipcode)\n", - "vaccineDistributionByZipcode" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "3276cce7", - "metadata": {}, - "outputs": [], - "source": [ - "vaccineDistributionByZipcode['Statistical Number of Adverse Reaction Reports'] = (vaccineDistributionByZipcode['DOSES_SHIPPED'] / vaccineDistributionByZipcode['OVERALL_DOSES_SHIPPED'] * vaccineDistributionByZipcode['Adverse Reaction Reports']).round(2)\n", - "vaccineDistributionByZipcode['Statistical Number of Adverse Reaction Reports (per 100,000)'] = (vaccineDistributionByZipcode['DOSES_SHIPPED'] / vaccineDistributionByZipcode['OVERALL_DOSES_SHIPPED'] * 100000).round().astype(int)\n", - "vaccineDistributionByZipcode" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "10cf731f", - "metadata": {}, - "outputs": [], - "source": [ - "vaccineDistributionByZipcode = vaccineDistributionByZipcode[['PROVIDER_NAME', 'ZIPCODE_SHP', 'LOT_NUMBER', 'DOSES_SHIPPED', 'Statistical Number of Adverse Reaction Reports', 'Statistical Number of Adverse Reaction Reports (per 100,000)']]\n", - "vaccineDistributionByZipcode" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "0c2020e9", - "metadata": {}, - "outputs": [], - "source": [ - "vaccineDistributionByZipcode = vaccineDistributionByZipcode.rename(\n", - " columns = {\n", - " 'PROVIDER_NAME': 'Provider',\n", - " 'ZIPCODE_SHP': 'ZIP Code',\n", - " 'LOT_NUMBER': 'Lot Number',\n", - " 'DOSES_SHIPPED': 'Doses Shipped'\n", - " })\n", - "vaccineDistributionByZipcode" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "f68c72d0", - "metadata": {}, - "outputs": [], - "source": [ - "# vaccineDistributionByZipcode.to_excel('tmp/Amended-22-01962-Pfizer-2022-0426-pulled-2022-0823_sumDoses.xlsx')" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "9b8f0b6e", - "metadata": {}, - "outputs": [], - "source": [ - "from IOUtils import IOUtils\n", - "\n", - "IOUtils.saveDataFrameAsJson(vaccineDistributionByZipcode, '../docs/data/vaccineDistributionByZipcode/VaccineDistributionByZipcode.json')" + "res.to_excel('tmp/res.xlsx')" ] } ],