From 85663354d1c24cf4f14f746c0917426c5f80b100 Mon Sep 17 00:00:00 2001
From: frankknoll <Knoll_Frank@web.de>
Date: Mon, 24 Jan 2022 12:16:58 +0100
Subject: [PATCH] merging multiple series into a single DataFrame

---
 HowBadIsMyBatch.ipynb | 121 ++++++++++--------------------------------
 README.md             |   2 +-
 2 files changed, 28 insertions(+), 95 deletions(-)

diff --git a/HowBadIsMyBatch.ipynb b/HowBadIsMyBatch.ipynb
index c24b568f82e..b4c77cfbf05 100644
--- a/HowBadIsMyBatch.ipynb
+++ b/HowBadIsMyBatch.ipynb
@@ -121,16 +121,6 @@
     "df_PFIZER_BIONTECH = df_patients_COVID19[df_patients_COVID19[\"VAX_MANU\"] == \"MODERNA\"]"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "e41885a8",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df_PFIZER_BIONTECH"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -144,21 +134,11 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "4b3cb943",
+   "id": "0ad4aab2",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# table = pd.pivot_table(df_PFIZER_BIONTECH, values='DIED', columns=['DIED'], aggfunc=np.sum)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "284bf448",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "pd.set_option('display.max_rows', None)"
+    "df_PFIZER_BIONTECH"
    ]
   },
   {
@@ -170,24 +150,7 @@
    },
    "outputs": [],
    "source": [
-    "df_DIED = df_PFIZER_BIONTECH[df_PFIZER_BIONTECH['DIED']=='Y'][['VAX_LOT']]\n",
-    "df_DIED"
-   ]
-  },
-  {
-   "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",
-    "df_DIED.value_counts()"
+    "df_DIED = df_PFIZER_BIONTECH[df_PFIZER_BIONTECH['DIED']=='Y'][['VAX_LOT']]"
    ]
   },
   {
@@ -199,18 +162,7 @@
    },
    "outputs": [],
    "source": [
-    "df_DISABLE = df_PFIZER_BIONTECH[df_PFIZER_BIONTECH['DISABLE']=='Y'][['VAX_LOT']]\n",
-    "df_DISABLE"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "3d782392",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df_DISABLE.value_counts()"
+    "df_DISABLE = df_PFIZER_BIONTECH[df_PFIZER_BIONTECH['DISABLE']=='Y'][['VAX_LOT']]"
    ]
   },
   {
@@ -222,20 +174,7 @@
    },
    "outputs": [],
    "source": [
-    "df_L_THREAT = df_PFIZER_BIONTECH[df_PFIZER_BIONTECH['L_THREAT']=='Y'][['VAX_LOT']]\n",
-    "df_L_THREAT"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "1a629007",
-   "metadata": {
-    "scrolled": false
-   },
-   "outputs": [],
-   "source": [
-    "df_L_THREAT.value_counts()"
+    "df_L_THREAT = df_PFIZER_BIONTECH[df_PFIZER_BIONTECH['L_THREAT']=='Y'][['VAX_LOT']]"
    ]
   },
   {
@@ -247,41 +186,35 @@
    },
    "outputs": [],
    "source": [
-    "df_ADR = df_PFIZER_BIONTECH[['VAX_LOT']]\n",
-    "df_ADR"
+    "df_ADR = df_PFIZER_BIONTECH[['VAX_LOT']]"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "7b3005db",
-   "metadata": {
-    "scrolled": false
-   },
-   "outputs": [],
-   "source": [
-    "df_ADR_valueCounts = df_ADR.value_counts()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "07c93e74",
-   "metadata": {
-    "scrolled": false
-   },
-   "outputs": [],
-   "source": [
-    "df_ADR_valueCounts"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "1244c494",
+   "id": "99945ca8",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "df = pd.concat(\n",
+    "    {\n",
+    "        'ADRs': df_ADR.value_counts(),\n",
+    "        'DEATHS': df_DIED.value_counts(),\n",
+    "        'DISABILITIES': df_DISABLE.value_counts(),\n",
+    "        'LIFE THREATENING ILLNESSES': df_L_THREAT.value_counts()\n",
+    "    },\n",
+    "    axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d9191d12",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df"
+   ]
   }
  ],
  "metadata": {
diff --git a/README.md b/README.md
index 70db6b98e8a..ddbea0ca3a4 100644
--- a/README.md
+++ b/README.md
@@ -3,7 +3,7 @@
 jupyter notebook
 
 FK-TODO:
-- VAX_LOT-Spalte normalisieren, d.h. toUpperCase(), Format des jeweiligen Herstellers berücksichtigen und "verschmutzte" Einträge Säubern, denn sie stellen alle dieselbe Charge dar:
+- VAX_LOT-Spalte normalisieren, d.h. toUpperCase(), Format des jeweiligen Herstellers berücksichtigen und "verschmutzte" Einträge säubern, denn sie stellen alle dieselbe Charge dar:
 039k20a
 MOD039K20A
 #039K20A