diff --git a/.gitignore b/.gitignore index 14e15ff4fc7..3b0fa91ee6e 100644 --- a/.gitignore +++ b/.gitignore @@ -1,2 +1,4 @@ VAERS/ -.ipynb_checkpoints/ \ No newline at end of file +.ipynb_checkpoints/ +VAERSDataUseGuide_en_September2021.pdf +Vaccine Lot Numbers Expiration (1).xlsx diff --git a/HowBadIsMyBatch.ipynb b/HowBadIsMyBatch.ipynb index 92f219163a8..ab6161eba56 100644 --- a/HowBadIsMyBatch.ipynb +++ b/HowBadIsMyBatch.ipynb @@ -24,22 +24,16 @@ " def read_csv(file):\n", " return pd.read_csv(file, index_col='VAERS_ID', encoding='latin1', low_memory=False)\n", " \n", - " def createPatients():\n", - " return pd.concat(\n", - " [\n", - " read_csv(\"VAERS/2021VAERSData/2021VAERSDATA.csv\"),\n", - " read_csv(\"VAERS/2022VAERSData/2022VAERSDATA.csv\")\n", - " ])\n", - "\n", - " def createVax(): \n", - " return pd.concat(\n", - " [\n", - " read_csv(\"VAERS/2021VAERSData/2021VAERSVAX.csv\"),\n", - " read_csv(\"VAERS/2022VAERSData/2022VAERSVAX.csv\")\n", - " ])\n", - "\n", - " df_patients_vax = pd.merge(createPatients(), createVax(), left_index=True, right_index=True)\n", - " return df_patients_vax[(df_patients_vax[\"VAX_TYPE\"] == \"COVID19\") & (df_patients_vax[\"VAX_MANU\"] == manufacturer)]" + " def createDataFrameForYear(year):\n", + " folder = \"VAERS/\" + year + \"VAERSData/\"\n", + " return pd.merge(\n", + " read_csv(folder + year + \"VAERSDATA.csv\"),\n", + " read_csv(folder + year + \"VAERSVAX.csv\"),\n", + " left_index=True,\n", + " right_index=True)\n", + " \n", + " df = pd.concat([createDataFrameForYear(\"2021\"), createDataFrameForYear(\"2022\")])\n", + " return df[(df[\"VAX_TYPE\"] == \"COVID19\") & (df[\"VAX_MANU\"] == manufacturer)]" ] }, { @@ -96,7 +90,7 @@ { "cell_type": "code", "execution_count": null, - "id": "fdf2ab4b", + "id": "bb7b2963", "metadata": {}, "outputs": [], "source": [