diff --git a/HowBadIsMyBatch.ipynb b/HowBadIsMyBatch.ipynb new file mode 100644 index 00000000000..6c3b6319dcf --- /dev/null +++ b/HowBadIsMyBatch.ipynb @@ -0,0 +1,204 @@ +{ + "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", + "pd.set_option('display.max_rows', 10)\n", + "pd.set_option('display.max_columns', None)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "ad0e6044", + "metadata": {}, + "outputs": [], + "source": [ + "df_patients_22 = pd.read_csv(\"2021VAERSData/2021VAERSDATA.csv\", index_col='VAERS_ID', encoding='latin1', low_memory=False)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "4472e902", + "metadata": {}, + "outputs": [], + "source": [ + "df_patients_22.index\n", + "df_patients_22" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "fb54ec47", + "metadata": {}, + "outputs": [], + "source": [ + "df_vax_22 = pd.read_csv(\"2021VAERSData/2021VAERSVAX.csv\", index_col='VAERS_ID', encoding='latin1')" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "d8942466", + "metadata": { + "scrolled": false + }, + "outputs": [], + "source": [ + "df_vax_22" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "d31c5225", + "metadata": {}, + "outputs": [], + "source": [ + "df_COVID19_22 = df_vax_22[df_vax_22[\"VAX_TYPE\"] == \"COVID19\"]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "be2b57c9", + "metadata": { + "scrolled": false + }, + "outputs": [], + "source": [ + "df_COVID19_22" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "8c432ab2", + "metadata": {}, + "outputs": [], + "source": [ + "df_patients_COVID19 = pd.merge(df_patients_22, df_COVID19_22, left_index=True, right_index=True)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "fef882ff", + "metadata": {}, + "outputs": [], + "source": [ + "df_patients_22.shape, df_COVID19_22.shape, df_patients_COVID19.shape" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "6ce15322", + "metadata": { + "scrolled": false + }, + "outputs": [], + "source": [ + "# pd.set_option('display.max_rows', 100)\n", + "df_patients_COVID19" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "233bc590", + "metadata": {}, + "outputs": [], + "source": [ + "df_PFIZER_BIONTECH = df_patients_COVID19[df_patients_COVID19[\"VAX_MANU\"] == \"MODERNA\"]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "86e0e4f2", + "metadata": {}, + "outputs": [], + "source": [ + "df_PFIZER_BIONTECH.info()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "4b3cb943", + "metadata": {}, + "outputs": [], + "source": [ + "# table = pd.pivot_table(df_PFIZER_BIONTECH, values='DIED', columns=['DIED'], aggfunc=np.sum)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "349da946", + "metadata": { + "scrolled": false + }, + "outputs": [], + "source": [ + "df = df_PFIZER_BIONTECH[df_PFIZER_BIONTECH['DIED']=='Y'][['VAX_LOT']]\n", + "df" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "9c5ff2fd", + "metadata": { + "scrolled": false + }, + "outputs": [], + "source": [ + "# df = df.groupby(['VAX_LOT']).count()\n", + "#df2 = df.sort_values(by=['DIED'], ascending=False)\n", + "#pd.set_option('display.max_rows', None)\n", + "#print(df2)\n", + "pd.set_option('display.max_rows', None)\n", + "df.value_counts()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "eff80ae1", + "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 +} diff --git a/README.md b/README.md index 759292c87e8..e604f3739dd 100644 --- a/README.md +++ b/README.md @@ -1 +1,3 @@ # HowBadIsMyBatch + +jupyter notebook