-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
materials-generate-scripts update lectures and reference
- Loading branch information
1 parent
f3c5145
commit 03b926b
Showing
43 changed files
with
29,657 additions
and
195 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,277 @@ | ||
{ | ||
"cells": [ | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "cell-lec01-0", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"# The pip install can take a minute\n", | ||
"%pip install -q urllib3<2.0 datascience ipywidgets\n", | ||
"import pyodide_http\n", | ||
"pyodide_http.patch_all()\n", | ||
"\n", | ||
"from datascience import *\n", | ||
"import numpy as np\n", | ||
"%matplotlib inline\n", | ||
"import matplotlib.pyplot as plots\n", | ||
"plots.style.use('fivethirtyeight')\n", | ||
"import warnings\n", | ||
"warnings.simplefilter(action=\"ignore\", category=FutureWarning)\n", | ||
"\n", | ||
"from urllib.request import urlopen \n", | ||
"import re\n", | ||
"def read_url(url): \n", | ||
" return re.sub('\\\\s+', ' ', urlopen(url).read().decode())" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "cell-lec01-1", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"2+3" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "cell-lec01-2", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"# Read two books, fast!\n", | ||
"\n", | ||
"huck_finn_url = 'https://www.inferentialthinking.com/data/huck_finn.txt'\n", | ||
"huck_finn_text = read_url(huck_finn_url)\n", | ||
"huck_finn_chapters = huck_finn_text.split('CHAPTER ')[44:]\n", | ||
"\n", | ||
"little_women_url = 'https://www.inferentialthinking.com/data/little_women.txt'\n", | ||
"little_women_text = read_url(little_women_url)\n", | ||
"little_women_chapters = little_women_text.split('CHAPTER ')[1:]" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "cell-lec01-3", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"huck_finn_chapters" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "cell-lec01-4", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"Table().with_column('Chapters', huck_finn_chapters)" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "cell-lec01-5", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"np.char.count(huck_finn_chapters, 'Tom')" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "cell-lec01-6", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"np.char.count(huck_finn_chapters, 'Jim')" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "cell-lec01-7", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"counts = Table().with_columns([\n", | ||
" 'Tom', np.char.count(huck_finn_chapters, 'Tom'),\n", | ||
" 'Jim', np.char.count(huck_finn_chapters, 'Jim'),\n", | ||
" 'Huck', np.char.count(huck_finn_chapters, 'Huck'),\n", | ||
"])\n", | ||
"counts" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "cell-lec01-8", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"# Plot the cumulative counts:\n", | ||
"# how many times in Chapter 1, how many times in Chapters 1 and 2, and so on.\n", | ||
"\n", | ||
"cum_counts = counts.cumsum().with_column('Chapter', np.arange(1, 44, 1))\n", | ||
"cum_counts.plot(column_for_xticks=3)\n", | ||
"plots.title('Cumulative Number of Times Name Appears');" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "cell-lec01-9", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"# The chapters of Little Women\n", | ||
"\n", | ||
"Table().with_column('Chapters', little_women_chapters)" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "cell-lec01-10", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"# Counts of names in the chapters of Little Women\n", | ||
"\n", | ||
"names = ['Amy', 'Beth', 'Jo', 'Laurie', 'Meg']\n", | ||
"mentions = {name: np.char.count(little_women_chapters, name) for name in names}\n", | ||
"\n", | ||
"counts = Table().with_columns([\n", | ||
" 'Amy', mentions['Amy'],\n", | ||
" 'Beth', mentions['Beth'],\n", | ||
" 'Jo', mentions['Jo'],\n", | ||
" 'Laurie', mentions['Laurie'],\n", | ||
" 'Meg', mentions['Meg']\n", | ||
" ])" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "cell-lec01-11", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"# Plot the cumulative counts\n", | ||
"\n", | ||
"cum_counts = counts.cumsum().with_column('Chapter', np.arange(1, 48, 1))\n", | ||
"cum_counts.plot(column_for_xticks=5)\n", | ||
"plots.title('Cumulative Number of Times Name Appears');" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "cell-lec01-12", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"len('Data 8')" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "cell-lec01-13", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"len(read_url(huck_finn_url))" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "cell-lec01-14", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"# In each chapter, count the number of all characters;\n", | ||
"# call this the \"length\" of the chapter.\n", | ||
"# Also count the number of periods.\n", | ||
"\n", | ||
"length_hf = Table().with_columns([\n", | ||
" 'Length', [len(s) for s in huck_finn_chapters],\n", | ||
" 'Periods', np.char.count(huck_finn_chapters, '.')\n", | ||
" ])\n", | ||
"length_lw = Table().with_columns([\n", | ||
" 'Length', [len(s) for s in little_women_chapters],\n", | ||
" 'Periods', np.char.count(little_women_chapters, '.')\n", | ||
" ])" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "cell-lec01-15", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"# The counts for Huckleberry Finn\n", | ||
"\n", | ||
"length_hf" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "cell-lec01-16", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"# The counts for Little Women\n", | ||
"\n", | ||
"length_lw" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "cell-lec01-17", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"plots.figure(figsize=(10,10))\n", | ||
"plots.scatter(length_hf[1], length_hf[0], color='darkblue')\n", | ||
"plots.scatter(length_lw[1], length_lw[0], color='gold')\n", | ||
"plots.xlabel('Number of periods in chapter')\n", | ||
"plots.ylabel('Number of characters in chapter');" | ||
] | ||
} | ||
], | ||
"metadata": { | ||
"anaconda-cloud": {}, | ||
"celltoolbar": "Raw Cell Format", | ||
"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": "3.10.12" | ||
} | ||
}, | ||
"nbformat": 4, | ||
"nbformat_minor": 4 | ||
} |
Oops, something went wrong.