From 22067e496ab55332c419740006cca9faeafe1bf0 Mon Sep 17 00:00:00 2001
From: Tim Jammer <tim.jammer@sc.tu-darmstadt.de>
Date: Tue, 13 Sep 2022 13:51:59 +0200
Subject: [PATCH] updated the slides to also include solutions for the last
exercises
---
slides/Day2_PandasDataFrames.ipynb | 24 +++++++++++++++++++-----
1 file changed, 19 insertions(+), 5 deletions(-)
diff --git a/slides/Day2_PandasDataFrames.ipynb b/slides/Day2_PandasDataFrames.ipynb
index 288ef4f..38a5542 100644
--- a/slides/Day2_PandasDataFrames.ipynb
+++ b/slides/Day2_PandasDataFrames.ipynb
@@ -2213,7 +2213,11 @@
"id": "53d45569",
"metadata": {},
"outputs": [],
- "source": []
+ "source": [
+ "cols=[\"sepal length\",\"sepal width\",\"petal length\",\"petal width\"]\n",
+ "df_agg= df.loc[:,cols].agg([np.min, np.max, np.mean, np.std])\n",
+ "df_agg"
+ ]
},
{
"cell_type": "markdown",
@@ -2229,7 +2233,10 @@
"id": "52a96d54",
"metadata": {},
"outputs": [],
- "source": []
+ "source": [
+ "df.loc[:,cols] =((df.loc[:,cols] - df_agg.loc['mean',:] )/ df_agg.loc['std',:])\n",
+ "df.describe()"
+ ]
},
{
"cell_type": "markdown",
@@ -2263,7 +2270,9 @@
"id": "801dd946",
"metadata": {},
"outputs": [],
- "source": []
+ "source": [
+ "grouped_by_species = df.groupby(by=[\"Name\"])"
+ ]
},
{
"cell_type": "code",
@@ -2271,7 +2280,12 @@
"id": "90b8c49e",
"metadata": {},
"outputs": [],
- "source": []
+ "source": [
+ "fig, axs = plt.subplots(1,3)\n",
+ "for ax, (name, group_data) in zip(axs,grouped_by_species): \n",
+ " group_data.boxplot(ax=ax)\n",
+ " ax.set_title(name)"
+ ]
},
{
"cell_type": "code",
@@ -2285,7 +2299,7 @@
"metadata": {
"celltoolbar": "Slideshow",
"kernelspec": {
- "display_name": "Python 3 (ipykernel)",
+ "display_name": "Python 3",
"language": "python",
"name": "python3"
},
--
GitLab