francois/HowBadIsMyBatch
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactoring

Browse Source
This commit is contained in:
frankknoll
2022-01-28 16:43:05 +01:00
parent f445a8b486
commit 906ec737ec
2 changed files with 122 additions and 760 deletions
Download Patch File Download Diff File Expand all files Collapse all files

873
HowBadIsMyBatch.ipynb
View File

@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"execution_count": null,
"id": "9de5907f-18f5-4cb1-903e-26028ff1fa03",
"metadata": {},
"outputs": [],
@@ -16,7 +16,7 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": null,
"id": "233bc590",
"metadata": {},
"outputs": [],
@@ -39,12 +39,30 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": null,
"id": "dea776cd",
"metadata": {},
"outputs": [],
"source": [
"def createDataFrame2(vaersDescrs, manufacturer):\n",
" def vaersDescr2Vaers(vaersDescr):\n",
" return pd.merge(vaersDescr['VAERSDATA'], vaersDescr['VAERSVAX'], left_index = True, right_index = True)\n",
"\n",
" def vaersDescrs2Vaers():\n",
" return map(vaersDescr2Vaers, vaersDescrs);\n",
"\n",
" df = pd.concat(vaersDescrs2Vaers())\n",
" return df[(df[\"VAX_TYPE\"] == \"COVID19\") & (df[\"VAX_MANU\"] == manufacturer)]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "99945ca8",
"metadata": {},
"outputs": [],
"source": [
"def createBatchCodeTable(df):\n",
"def createBatchCodeTable(df : pd.DataFrame):\n",
" def filter(df, col):\n",
" return df[df[col] == 'Y'][['VAX_LOT']]\n",
"\n",
@@ -59,7 +77,94 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": null,
"id": "3dacedfd",
"metadata": {},
"outputs": [],
"source": [
"import unittest"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e14465d7",
"metadata": {},
"outputs": [],
"source": [
"from pandas.testing import assert_frame_equal\n",
"\n",
"class BatchCodeTableTest(unittest.TestCase):\n",
"\n",
" def test_createBatchCodeTable2(self):\n",
" # Given\n",
" vaersData2021 = pd.DataFrame(columns = ['DIED', 'L_THREAT', 'DISABLE'], index = ['0916600', '0916601'])\n",
" vaersData2021.loc['0916600'] = pd.Series({'DIED': 'Y', 'L_THREAT': np.NaN, 'DISABLE': np.NaN})\n",
" vaersData2021.loc['0916601'] = pd.Series({'DIED': np.NaN, 'L_THREAT': np.NaN, 'DISABLE': 'Y'})\n",
"\n",
" vaersVax2021 = pd.DataFrame(columns = ['VAX_TYPE', 'VAX_MANU', 'VAX_LOT'], index = ['0916600', '0916601'])\n",
" vaersVax2021.loc['0916600'] = pd.Series({'VAX_TYPE': 'COVID19', 'VAX_MANU': 'MODERNA', 'VAX_LOT': '037K20A'})\n",
" vaersVax2021.loc['0916601'] = pd.Series({'VAX_TYPE': 'COVID19', 'VAX_MANU': 'MODERNA', 'VAX_LOT': '025L20A'})\n",
"\n",
" vaersData2022 = pd.DataFrame(columns = ['DIED', 'L_THREAT', 'DISABLE'], index = ['1996873', '1996874'])\n",
" vaersData2022.loc['1996873'] = pd.Series({'DIED': np.NaN, 'L_THREAT': np.NaN, 'DISABLE': np.NaN})\n",
" vaersData2022.loc['1996874'] = pd.Series({'DIED': np.NaN, 'L_THREAT': np.NaN, 'DISABLE': 'Y'})\n",
"\n",
" vaersVax2022 = pd.DataFrame(columns = ['VAX_TYPE', 'VAX_MANU', 'VAX_LOT'], index = ['1996873', '1996874'])\n",
" vaersVax2022.loc['1996873'] = pd.Series({'VAX_TYPE': 'HPV9', 'VAX_MANU': 'MERCK & CO. INC.', 'VAX_LOT': 'R017624'})\n",
" vaersVax2022.loc['1996874'] = pd.Series({'VAX_TYPE': 'COVID19', 'VAX_MANU': 'MODERNA', 'VAX_LOT': '025L20A'})\n",
" \n",
" dataFrame = createDataFrame2(\n",
" [\n",
" {'VAERSDATA': vaersData2021, 'VAERSVAX': vaersVax2021},\n",
" {'VAERSDATA': vaersData2022, 'VAERSVAX': vaersVax2022}\n",
" ],\n",
" \"MODERNA\")\n",
" display(\"dataFrame:\", dataFrame)\n",
"\n",
" # When\n",
" self._test_createBatchCodeTable(dataFrame);\n",
" \n",
" def test_createBatchCodeTable(self):\n",
" # Given\n",
" dataFrame = createDataFrame(\"test/VAERS\", \"MODERNA\")\n",
" display(\"dataFrame:\", dataFrame)\n",
" self._test_createBatchCodeTable(dataFrame);\n",
"\n",
"\n",
" def _test_createBatchCodeTable(self, dataFrame):\n",
" # When\n",
" batchCodeTable = createBatchCodeTable(dataFrame)\n",
" display(\"batchCodeTable:\", batchCodeTable)\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.MultiIndex.from_arrays([['025L20A', '037K20A']], names = ('VAX_LOT',)))\n",
" display(\"batchCodeTableExpected:\", batchCodeTableExpected)\n",
" assert_frame_equal(batchCodeTable, batchCodeTableExpected, check_dtype = False)\n",
"\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": [],
@@ -72,452 +177,10 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": null,
"id": "ab170c16",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'MODERNA'"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>ADRs</th>\n",
" <th>DEATHS</th>\n",
" <th>DISABILITIES</th>\n",
" <th>LIFE THREATENING ILLNESSES</th>\n",
" </tr>\n",
" <tr>\n",
" <th>VAX_LOT</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>026L20A</th>\n",
" <td>4177</td>\n",
" <td>42.0</td>\n",
" <td>35.0</td>\n",
" <td>28.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>039K20A</th>\n",
" <td>4169</td>\n",
" <td>93.0</td>\n",
" <td>39.0</td>\n",
" <td>37.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>011J20A</th>\n",
" <td>3661</td>\n",
" <td>37.0</td>\n",
" <td>33.0</td>\n",
" <td>28.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>013L20A</th>\n",
" <td>3191</td>\n",
" <td>68.0</td>\n",
" <td>47.0</td>\n",
" <td>32.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>012L20A</th>\n",
" <td>3068</td>\n",
" <td>72.0</td>\n",
" <td>30.0</td>\n",
" <td>30.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>029L2VA</th>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>029L2oa</th>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>029L30A</th>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>029L420A</th>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Ø38B21A</th>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>16284 rows × 4 columns</p>\n",
"</div>"
],
"text/plain": [
" ADRs DEATHS DISABILITIES LIFE THREATENING ILLNESSES\n",
"VAX_LOT \n",
"026L20A 4177 42.0 35.0 28.0\n",
"039K20A 4169 93.0 39.0 37.0\n",
"011J20A 3661 37.0 33.0 28.0\n",
"013L20A 3191 68.0 47.0 32.0\n",
"012L20A 3068 72.0 30.0 30.0\n",
"... ... ... ... ...\n",
"029L2VA 1 0.0 0.0 0.0\n",
"029L2oa 1 0.0 0.0 0.0\n",
"029L30A 1 0.0 0.0 0.0\n",
"029L420A 1 0.0 0.0 0.0\n",
"Ø38B21A 1 0.0 0.0 0.0\n",
"\n",
"[16284 rows x 4 columns]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"'PFIZER\\\\BIONTECH'"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>ADRs</th>\n",
" <th>DEATHS</th>\n",
" <th>DISABILITIES</th>\n",
" <th>LIFE THREATENING ILLNESSES</th>\n",
" </tr>\n",
" <tr>\n",
" <th>VAX_LOT</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>EK9231</th>\n",
" <td>3392</td>\n",
" <td>48.0</td>\n",
" <td>56.0</td>\n",
" <td>35.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ER2613</th>\n",
" <td>3345</td>\n",
" <td>65.0</td>\n",
" <td>62.0</td>\n",
" <td>57.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>EN6201</th>\n",
" <td>2928</td>\n",
" <td>148.0</td>\n",
" <td>69.0</td>\n",
" <td>55.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>EN5318</th>\n",
" <td>2811</td>\n",
" <td>114.0</td>\n",
" <td>62.0</td>\n",
" <td>57.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ER8732</th>\n",
" <td>2705</td>\n",
" <td>50.0</td>\n",
" <td>51.0</td>\n",
" <td>68.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>EN6203 UPC</th>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>EN6203,</th>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>EN6203, EL3247</th>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>EN6203, EN6204</th>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ÉÑ6198</th>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>12447 rows × 4 columns</p>\n",
"</div>"
],
"text/plain": [
" ADRs DEATHS DISABILITIES LIFE THREATENING ILLNESSES\n",
"VAX_LOT \n",
"EK9231 3392 48.0 56.0 35.0\n",
"ER2613 3345 65.0 62.0 57.0\n",
"EN6201 2928 148.0 69.0 55.0\n",
"EN5318 2811 114.0 62.0 57.0\n",
"ER8732 2705 50.0 51.0 68.0\n",
"... ... ... ... ...\n",
"EN6203 UPC 1 0.0 0.0 0.0\n",
"EN6203, 1 0.0 0.0 0.0\n",
"EN6203, EL3247 1 0.0 0.0 0.0\n",
"EN6203, EN6204 1 0.0 0.0 0.0\n",
"ÉÑ6198 1 0.0 0.0 0.0\n",
"\n",
"[12447 rows x 4 columns]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"'JANSSEN'"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>ADRs</th>\n",
" <th>DEATHS</th>\n",
" <th>DISABILITIES</th>\n",
" <th>LIFE THREATENING ILLNESSES</th>\n",
" </tr>\n",
" <tr>\n",
" <th>VAX_LOT</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Unknown</th>\n",
" <td>7312</td>\n",
" <td>264.0</td>\n",
" <td>19.0</td>\n",
" <td>31.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>043A21A</th>\n",
" <td>2347</td>\n",
" <td>37.0</td>\n",
" <td>31.0</td>\n",
" <td>49.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>042A21A</th>\n",
" <td>2170</td>\n",
" <td>44.0</td>\n",
" <td>41.0</td>\n",
" <td>43.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1805018</th>\n",
" <td>1756</td>\n",
" <td>35.0</td>\n",
" <td>36.0</td>\n",
" <td>49.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>202A21A</th>\n",
" <td>1726</td>\n",
" <td>25.0</td>\n",
" <td>21.0</td>\n",
" <td>25.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>180E018</th>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>180D068</th>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>180C068</th>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>180B982</th>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>zz</th>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>2456 rows × 4 columns</p>\n",
"</div>"
],
"text/plain": [
" ADRs DEATHS DISABILITIES LIFE THREATENING ILLNESSES\n",
"VAX_LOT \n",
"Unknown 7312 264.0 19.0 31.0\n",
"043A21A 2347 37.0 31.0 49.0\n",
"042A21A 2170 44.0 41.0 43.0\n",
"1805018 1756 35.0 36.0 49.0\n",
"202A21A 1726 25.0 21.0 25.0\n",
"... ... ... ... ...\n",
"180E018 1 0.0 0.0 0.0\n",
"180D068 1 0.0 0.0 0.0\n",
"180C068 1 0.0 0.0 0.0\n",
"180B982 1 0.0 0.0 0.0\n",
"zz 1 0.0 0.0 0.0\n",
"\n",
"[2456 rows x 4 columns]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"outputs": [],
"source": [
"saveBatchCodeTable(\"MODERNA\", \"results/moderna.xlsx\")\n",
"saveBatchCodeTable(\"PFIZER\\BIONTECH\", \"results/pfizer.xlsx\")\n",
@@ -526,318 +189,10 @@
},
{
"cell_type": "code",
"execution_count": 6,
"id": "9f506ac8",
"metadata": {},
"outputs": [],
"source": [
"import unittest"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "e14465d7",
"metadata": {},
"outputs": [],
"source": [
"from pandas.testing import assert_frame_equal\n",
"\n",
"\n",
"class HowBadIsMyBatchTest(unittest.TestCase):\n",
"\n",
" def test_createBatchCodeTable(self):\n",
" # Given\n",
" dataFrame = createDataFrame(\"test/VAERS\", \"MODERNA\")\n",
" display(\"dataFrame:\", dataFrame)\n",
"\n",
" # When\n",
" batchCodeTable = createBatchCodeTable(dataFrame)\n",
" display(\"batchCodeTable:\", batchCodeTable)\n",
"\n",
" # Then\n",
" batchCodeTableExpected = pd.DataFrame(\n",
" {\n",
" 'ADRs': [2, 1],\n",
" 'DEATHS': [0, 1],\n",
" 'DISABILITIES': [2, 0],\n",
" 'LIFE THREATENING ILLNESSES': [0, 0]\n",
" },\n",
" index = pd.MultiIndex.from_arrays([['025L20A', '037K20A']], names = ('VAX_LOT',)))\n",
" display(\"batchCodeTableExpected:\", batchCodeTableExpected)\n",
" assert_frame_equal(batchCodeTable, batchCodeTableExpected, check_dtype = False)\n"
]
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": null,
"id": "ef8f99c4",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"test_createBatchCodeTable (__main__.HowBadIsMyBatchTest) ... "
]
},
{
"data": {
"text/plain": [
"'dataFrame:'"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>DIED</th>\n",
" <th>L_THREAT</th>\n",
" <th>DISABLE</th>\n",
" <th>VAX_TYPE</th>\n",
" <th>VAX_MANU</th>\n",
" <th>VAX_LOT</th>\n",
" </tr>\n",
" <tr>\n",
" <th>VAERS_ID</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>916600</th>\n",
" <td>Y</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>COVID19</td>\n",
" <td>MODERNA</td>\n",
" <td>037K20A</td>\n",
" </tr>\n",
" <tr>\n",
" <th>916601</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>Y</td>\n",
" <td>COVID19</td>\n",
" <td>MODERNA</td>\n",
" <td>025L20A</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1996874</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>Y</td>\n",
" <td>COVID19</td>\n",
" <td>MODERNA</td>\n",
" <td>025L20A</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" DIED L_THREAT DISABLE VAX_TYPE VAX_MANU VAX_LOT\n",
"VAERS_ID \n",
"916600 Y NaN NaN COVID19 MODERNA 037K20A\n",
"916601 NaN NaN Y COVID19 MODERNA 025L20A\n",
"1996874 NaN NaN Y COVID19 MODERNA 025L20A"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"'batchCodeTable:'"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>ADRs</th>\n",
" <th>DEATHS</th>\n",
" <th>DISABILITIES</th>\n",
" <th>LIFE THREATENING ILLNESSES</th>\n",
" </tr>\n",
" <tr>\n",
" <th>VAX_LOT</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>025L20A</th>\n",
" <td>2</td>\n",
" <td>0.0</td>\n",
" <td>2.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>037K20A</th>\n",
" <td>1</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" ADRs DEATHS DISABILITIES LIFE THREATENING ILLNESSES\n",
"VAX_LOT \n",
"025L20A 2 0.0 2.0 0.0\n",
"037K20A 1 1.0 0.0 0.0"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"'batchCodeTableExpected:'"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>ADRs</th>\n",
" <th>DEATHS</th>\n",
" <th>DISABILITIES</th>\n",
" <th>LIFE THREATENING ILLNESSES</th>\n",
" </tr>\n",
" <tr>\n",
" <th>VAX_LOT</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>025L20A</th>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>037K20A</th>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" ADRs DEATHS DISABILITIES LIFE THREATENING ILLNESSES\n",
"VAX_LOT \n",
"025L20A 2 0 2 0\n",
"037K20A 1 1 0 0"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"ok\n",
"\n",
"----------------------------------------------------------------------\n",
"Ran 1 test in 0.220s\n",
"\n",
"OK\n"
]
},
{
"data": {
"text/plain": [
"<unittest.main.TestProgram at 0x7f43a862bbe0>"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"outputs": [],
"source": [
"unittest.main(argv = [''], verbosity = 2, exit = False)"
]

9
help.txt
View File

@@ -1,7 +1,14 @@
jupyter notebook
FK-TODO:
- Prüfe, ob die VAERS_ID wirklich eindeutig ist.
- "I would suggest that you filter the vax table first for just C19 vaccines, and for just first dose.
Then carry out the analysis as before.
Repeat for second dose and third dose separately. The cumulative effect will then appear.
It should be analysed separately anyway, because adverse reactions increase with each dose."
# 1. filter the vax table first for just C19 vaccines
# 2. and for just n-tn (n \in {1, 2, 3}) dose => VAERSDATA --> VAERSVAX ist 1:1-Beziehung statt 1:n und kann einfacher in eine einzige Tabelle gemergt werden
# 3. filter for manufacturer
- Prüfe, ob die VAERS_ID wirklich eindeutig ist. Antwort: VAERS_ID ist in der VAERSVAX-Tabelle nicht eindeutig, da es mehrere Impfungen pro Person geben kann.
- VAX_LOT-Spalte normalisieren, d.h. mindestens toUpperCase() darauf anwenden
- Format des jeweiligen Herstellers berücksichtigen und "verschmutzte" Einträge säubern, denn sie stellen alle dieselbe Charge dar:
039k20a