Weeks 12 and 13

src/ada_topics/chapter_template/config.py

@@ -10,7 +10,7 @@
 
 
 SITE_CONTENTS = {
-    "chapter_title": "Chapter Title",
+    "chapter_title": "Chapter title",
     "pages": tuple(
         itertools.chain(
             *[topic["pages"] for topic in TOPICS],

src/ada_topics/chapter_template/subchapter_slug/objectives_materials.md

@@ -1,4 +1,4 @@
-# Subchapter Title
+# Subchapter title
 
 ## Learning objectives
 
@@ -23,7 +23,7 @@ Download the [slides](chapter_template-subchapter_slug.pdf).
 
 Video with German subtitles:
 
-*(turn subtitles on in the bottom right corner of the video)*
+_(turn subtitles on in the bottom right corner of the video)_
 
 <iframe
   src="https://electure.uni-bonn.de/paella7/ui/watch.html?id=XXXXX"

src/ada_topics/chapter_template/subchapter_slug/screencast/script.md

@@ -1,4 +1,4 @@
-# Script: Subchapter Title
+# Script: Subchapter title
 
 ## First slide
 

src/ada_topics/chapter_template/subchapter_slug/screencast/slides.md

@@ -16,13 +16,12 @@ defaults:
 
 <br/>
 
-# Chapter Title
+# Chapter title
 
-### Subchapter Title
+### Subchapter title
 
 <br/>
 
-
 Hans-Martin von Gaudecker and Aapo Stenhammar
 
 ---

src/ada_topics/config.py

@@ -15,6 +15,7 @@
     "stats_dispersion_concentration",
     "stats_bivariate",
     "stats_misc",
+    "stats_interpretation",
     "jupyter_notebooks",
     "getting_help",
     "python_basics",

src/ada_topics/pandas_basics/config.py

@@ -19,6 +19,7 @@
 from ada_topics.pandas_basics.query import SITE_CONTENTS as query
 from ada_topics.pandas_basics.series_intro import SITE_CONTENTS as series_intro
 from ada_topics.pandas_basics.shift_diff import SITE_CONTENTS as shift_diff
+from ada_topics.pandas_basics.simulating_data import SITE_CONTENTS as simulating_data
 from ada_topics.pandas_basics.types_of_data_dtypes import (
     SITE_CONTENTS as types_of_data_dtypes,
 )
@@ -38,6 +39,7 @@
     shift_diff,
     concatenate,
     merge,
+    simulating_data,
 ]
 
 

src/ada_topics/pandas_basics/simulating_data/__init__.py

@@ -0,0 +1,18 @@
+"""Create exercise and solution notebooks for the current subchapter."""
+
+from pathlib import Path
+
+from pybaum import tree_map
+
+from .config import SITE_CONTENTS as _SITE_CONTENTS
+
+
+def add_this_dir(filename):
+    """Add the current directory's name to the filename."""
+    return f"{Path(__file__).parent.name}/{filename}"
+
+
+SITE_CONTENTS = tree_map(
+    add_this_dir,
+    _SITE_CONTENTS,
+)

src/ada_topics/pandas_basics/simulating_data/config.py

@@ -0,0 +1,7 @@
+"""Definitions of source files for the current chapter."""
+
+SITE_CONTENTS = {
+    "pages": ("objectives_materials.md",),
+    "other": (),
+    "built": ("pandas_basics-simulating_data.pdf",),
+}

src/ada_topics/pandas_basics/simulating_data/examples.ipynb

@@ -0,0 +1,170 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import plotly.graph_objects as go\n",
+    "import plotly.io as pio\n",
+    "\n",
+    "pio.templates.default = \"plotly_dark+presentation\"\n",
+    "pd.options.plotting.backend = \"plotly\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "rng = np.random.default_rng(seed=4352)\n",
+    "\n",
+    "samples = pd.Series(rng.normal(loc=10, scale=5, size=10), name=\"x\")\n",
+    "\n",
+    "print(samples.to_markdown())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "size = 100\n",
+    "data = pd.DataFrame(\n",
+    "    {\n",
+    "        \"x\": rng.normal(loc=10, scale=5, size=size),\n",
+    "        \"u\": rng.normal(loc=0, scale=15, size=size),\n",
+    "    }\n",
+    ")\n",
+    "data[\"y\"] = 5 + 2 * data[\"x\"] + data[\"u\"]\n",
+    "\n",
+    "data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig_ols_happy_path = data.plot.scatter(\n",
+    "    x=\"x\",\n",
+    "    y=\"y\",\n",
+    "    trendline=\"ols\",\n",
+    ")\n",
+    "fig_ols_happy_path.update_layout(\n",
+    "    showlegend=False,\n",
+    "    xaxis_range=[-9, 29],\n",
+    "    yaxis_range=[-30, 84],\n",
+    ")\n",
+    "fig_ols_happy_path.write_image(\"screencast/public/ols_happy_path.svg\")\n",
+    "fig_ols_happy_path.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig_ols_happy_path.add_trace(\n",
+    "    go.Scatter(\n",
+    "        x=[0, 20],\n",
+    "        y=[5, 45],\n",
+    "        mode=\"lines\",\n",
+    "    )\n",
+    ")\n",
+    "fig_ols_happy_path.update_layout(\n",
+    "    showlegend=False,\n",
+    "    xaxis_range=[-9, 29],\n",
+    "    yaxis_range=[-30, 84],\n",
+    ")\n",
+    "\n",
+    "fig_ols_happy_path.write_image(\"screencast/public/ols_happy_path_with_truth.svg\")\n",
+    "fig_ols_happy_path.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data_corr = data.copy()\n",
+    "data_corr[\"x\"] = data_corr[\"x\"] - data_corr[\"u\"] / 3\n",
+    "data_corr[\"y\"] = 5 + 2 * data_corr[\"x\"] + data_corr[\"u\"]\n",
+    "\n",
+    "data_corr"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig_ols_confounder = data_corr.plot.scatter(\n",
+    "    x=\"x\",\n",
+    "    y=\"y\",\n",
+    "    trendline=\"ols\",\n",
+    ")\n",
+    "fig_ols_confounder.update_layout(\n",
+    "    showlegend=False,\n",
+    "    xaxis_range=[-9, 29],\n",
+    "    yaxis_range=[-30, 84],\n",
+    ")\n",
+    "fig_ols_confounder.write_image(\"screencast/public/ols_confounder.svg\")\n",
+    "fig_ols_confounder.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig_ols_confounder.add_trace(\n",
+    "    go.Scatter(\n",
+    "        x=[0, 20],\n",
+    "        y=[5, 45],\n",
+    "        mode=\"lines\",\n",
+    "    )\n",
+    ")\n",
+    "fig_ols_confounder.update_layout(\n",
+    "    showlegend=False,\n",
+    "    xaxis_range=[-9, 29],\n",
+    "    yaxis_range=[-30, 84],\n",
+    ")\n",
+    "fig_ols_confounder.write_image(\"screencast/public/ols_confounder_with_truth.svg\")\n",
+    "fig_ols_confounder.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

src/ada_topics/pandas_basics/simulating_data/objectives_materials.md

@@ -0,0 +1,34 @@
+# Simulating data
+
+## Learning objectives
+
+After working through this topic, you should be able to:
+
+- explain when and why it is useful to simulate data
+- simulate data using `numpy` and `pandas`
+
+## Materials
+
+Video with English subtitles:
+
+<iframe
+  src="https://electure.uni-bonn.de/paella7/ui/watch.html?id=8a4b21d6-de7a-4b04-86c0-c18527fb33c6"
+  width="640"
+  height="360"
+  frameborder="0"
+  allowfullscreen
+></iframe>
+
+Download the [slides](pandas_basics-simulating_data.pdf).
+
+Video with German subtitles:
+
+*(turn subtitles on in the bottom right corner of the video)*
+
+<iframe
+  src="https://electure.uni-bonn.de/paella7/ui/watch.html?id=cd8ce887-fc7d-4ab7-be7f-1ecbaa4cee38"
+  width="640"
+  height="360"
+  frameborder="0"
+  allowfullscreen
+></iframe>

src/ada_topics/pandas_basics/simulating_data/screencast/script.md

@@ -0,0 +1,6 @@
+# Script: Simulating data
+
+## First slide
+
+- Some bullet point
+- Another bullet point