Done some lab stuff
This commit is contained in:
TinyAtoms
338
ISLR/notebooks/3.6.2.R.ipynb
Normal file
338
ISLR/notebooks/3.6.2.R.ipynb
Normal file
@@ -0,0 +1,338 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"library(MASS)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"\n",
|
||||
"<table width=\"100%\" summary=\"page for Boston {MASS}\"><tr><td>Boston {MASS}</td><td style=\"text-align: right;\">R Documentation</td></tr></table>\n",
|
||||
"\n",
|
||||
"<h2>\n",
|
||||
"Housing Values in Suburbs of Boston\n",
|
||||
"</h2>\n",
|
||||
"\n",
|
||||
"<h3>Description</h3>\n",
|
||||
"\n",
|
||||
"<p>The <code>Boston</code> data frame has 506 rows and 14 columns.\n",
|
||||
"</p>\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"<h3>Usage</h3>\n",
|
||||
"\n",
|
||||
"<pre>\n",
|
||||
"Boston\n",
|
||||
"</pre>\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"<h3>Format</h3>\n",
|
||||
"\n",
|
||||
"<p>This data frame contains the following columns:\n",
|
||||
"</p>\n",
|
||||
"\n",
|
||||
"<dl>\n",
|
||||
"<dt><code>crim</code></dt><dd>\n",
|
||||
"<p>per capita crime rate by town.\n",
|
||||
"</p>\n",
|
||||
"</dd>\n",
|
||||
"<dt><code>zn</code></dt><dd>\n",
|
||||
"<p>proportion of residential land zoned for lots over 25,000 sq.ft.\n",
|
||||
"</p>\n",
|
||||
"</dd>\n",
|
||||
"<dt><code>indus</code></dt><dd>\n",
|
||||
"<p>proportion of non-retail business acres per town.\n",
|
||||
"</p>\n",
|
||||
"</dd>\n",
|
||||
"<dt><code>chas</code></dt><dd>\n",
|
||||
"<p>Charles River dummy variable (= 1 if tract bounds river; 0 otherwise).\n",
|
||||
"</p>\n",
|
||||
"</dd>\n",
|
||||
"<dt><code>nox</code></dt><dd>\n",
|
||||
"<p>nitrogen oxides concentration (parts per 10 million).\n",
|
||||
"</p>\n",
|
||||
"</dd>\n",
|
||||
"<dt><code>rm</code></dt><dd>\n",
|
||||
"<p>average number of rooms per dwelling.\n",
|
||||
"</p>\n",
|
||||
"</dd>\n",
|
||||
"<dt><code>age</code></dt><dd>\n",
|
||||
"<p>proportion of owner-occupied units built prior to 1940.\n",
|
||||
"</p>\n",
|
||||
"</dd>\n",
|
||||
"<dt><code>dis</code></dt><dd>\n",
|
||||
"<p>weighted mean of distances to five Boston employment centres.\n",
|
||||
"</p>\n",
|
||||
"</dd>\n",
|
||||
"<dt><code>rad</code></dt><dd>\n",
|
||||
"<p>index of accessibility to radial highways.\n",
|
||||
"</p>\n",
|
||||
"</dd>\n",
|
||||
"<dt><code>tax</code></dt><dd>\n",
|
||||
"<p>full-value property-tax rate per \\$10,000.\n",
|
||||
"</p>\n",
|
||||
"</dd>\n",
|
||||
"<dt><code>ptratio</code></dt><dd>\n",
|
||||
"<p>pupil-teacher ratio by town.\n",
|
||||
"</p>\n",
|
||||
"</dd>\n",
|
||||
"<dt><code>black</code></dt><dd>\n",
|
||||
"<p><i>1000(Bk - 0.63)^2</i> where <i>Bk</i> is the proportion of blacks\n",
|
||||
"by town.\n",
|
||||
"</p>\n",
|
||||
"</dd>\n",
|
||||
"<dt><code>lstat</code></dt><dd>\n",
|
||||
"<p>lower status of the population (percent).\n",
|
||||
"</p>\n",
|
||||
"</dd>\n",
|
||||
"<dt><code>medv</code></dt><dd>\n",
|
||||
"<p>median value of owner-occupied homes in \\$1000s.\n",
|
||||
"</p>\n",
|
||||
"</dd>\n",
|
||||
"</dl>\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"<h3>Source</h3>\n",
|
||||
"\n",
|
||||
"<p>Harrison, D. and Rubinfeld, D.L. (1978)\n",
|
||||
"Hedonic prices and the demand for clean air.\n",
|
||||
"<em>J. Environ. Economics and Management</em>\n",
|
||||
"<b>5</b>, 81–102.\n",
|
||||
"</p>\n",
|
||||
"<p>Belsley D.A., Kuh, E. and Welsch, R.E. (1980)\n",
|
||||
"<em>Regression Diagnostics. Identifying Influential Data and Sources\n",
|
||||
"of Collinearity.</em>\n",
|
||||
"New York: Wiley.\n",
|
||||
"</p>\n",
|
||||
"\n",
|
||||
"<hr /><div style=\"text-align: center;\">[Package <em>MASS</em> version 7.3-51.5 ]</div>"
|
||||
],
|
||||
"text/latex": [
|
||||
"\\inputencoding{utf8}\n",
|
||||
"\\HeaderA{Boston}{Housing Values in Suburbs of Boston}{Boston}\n",
|
||||
"\\keyword{datasets}{Boston}\n",
|
||||
"%\n",
|
||||
"\\begin{Description}\\relax\n",
|
||||
"The \\code{Boston} data frame has 506 rows and 14 columns.\n",
|
||||
"\\end{Description}\n",
|
||||
"%\n",
|
||||
"\\begin{Usage}\n",
|
||||
"\\begin{verbatim}\n",
|
||||
"Boston\n",
|
||||
"\\end{verbatim}\n",
|
||||
"\\end{Usage}\n",
|
||||
"%\n",
|
||||
"\\begin{Format}\n",
|
||||
"This data frame contains the following columns:\n",
|
||||
"\\begin{description}\n",
|
||||
"\n",
|
||||
"\\item[\\code{crim}] \n",
|
||||
"per capita crime rate by town.\n",
|
||||
"\n",
|
||||
"\\item[\\code{zn}] \n",
|
||||
"proportion of residential land zoned for lots over 25,000 sq.ft.\n",
|
||||
"\n",
|
||||
"\\item[\\code{indus}] \n",
|
||||
"proportion of non-retail business acres per town.\n",
|
||||
"\n",
|
||||
"\\item[\\code{chas}] \n",
|
||||
"Charles River dummy variable (= 1 if tract bounds river; 0 otherwise).\n",
|
||||
"\n",
|
||||
"\\item[\\code{nox}] \n",
|
||||
"nitrogen oxides concentration (parts per 10 million).\n",
|
||||
"\n",
|
||||
"\\item[\\code{rm}] \n",
|
||||
"average number of rooms per dwelling.\n",
|
||||
"\n",
|
||||
"\\item[\\code{age}] \n",
|
||||
"proportion of owner-occupied units built prior to 1940.\n",
|
||||
"\n",
|
||||
"\\item[\\code{dis}] \n",
|
||||
"weighted mean of distances to five Boston employment centres.\n",
|
||||
"\n",
|
||||
"\\item[\\code{rad}] \n",
|
||||
"index of accessibility to radial highways.\n",
|
||||
"\n",
|
||||
"\\item[\\code{tax}] \n",
|
||||
"full-value property-tax rate per \\bsl{}\\$10,000.\n",
|
||||
"\n",
|
||||
"\\item[\\code{ptratio}] \n",
|
||||
"pupil-teacher ratio by town.\n",
|
||||
"\n",
|
||||
"\\item[\\code{black}] \n",
|
||||
"\\eqn{1000(Bk - 0.63)^2}{} where \\eqn{Bk}{} is the proportion of blacks\n",
|
||||
"by town.\n",
|
||||
"\n",
|
||||
"\\item[\\code{lstat}] \n",
|
||||
"lower status of the population (percent).\n",
|
||||
"\n",
|
||||
"\\item[\\code{medv}] \n",
|
||||
"median value of owner-occupied homes in \\bsl{}\\$1000s.\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\\end{description}\n",
|
||||
"\n",
|
||||
"\\end{Format}\n",
|
||||
"%\n",
|
||||
"\\begin{Source}\\relax\n",
|
||||
"Harrison, D. and Rubinfeld, D.L. (1978)\n",
|
||||
"Hedonic prices and the demand for clean air.\n",
|
||||
"\\emph{J. Environ. Economics and Management}\n",
|
||||
"\\bold{5}, 81--102.\n",
|
||||
"\n",
|
||||
"Belsley D.A., Kuh, E. and Welsch, R.E. (1980)\n",
|
||||
"\\emph{Regression Diagnostics. Identifying Influential Data and Sources\n",
|
||||
"of Collinearity.}\n",
|
||||
"New York: Wiley.\n",
|
||||
"\\end{Source}"
|
||||
],
|
||||
"text/plain": [
|
||||
"Boston package:MASS R Documentation\n",
|
||||
"\n",
|
||||
"_\bH_\bo_\bu_\bs_\bi_\bn_\bg _\bV_\ba_\bl_\bu_\be_\bs _\bi_\bn _\bS_\bu_\bb_\bu_\br_\bb_\bs _\bo_\bf _\bB_\bo_\bs_\bt_\bo_\bn\n",
|
||||
"\n",
|
||||
"_\bD_\be_\bs_\bc_\br_\bi_\bp_\bt_\bi_\bo_\bn:\n",
|
||||
"\n",
|
||||
" The ‘Boston’ data frame has 506 rows and 14 columns.\n",
|
||||
"\n",
|
||||
"_\bU_\bs_\ba_\bg_\be:\n",
|
||||
"\n",
|
||||
" Boston\n",
|
||||
" \n",
|
||||
"_\bF_\bo_\br_\bm_\ba_\bt:\n",
|
||||
"\n",
|
||||
" This data frame contains the following columns:\n",
|
||||
"\n",
|
||||
" ‘crim’ per capita crime rate by town.\n",
|
||||
"\n",
|
||||
" ‘zn’ proportion of residential land zoned for lots over 25,000\n",
|
||||
" sq.ft.\n",
|
||||
"\n",
|
||||
" ‘indus’ proportion of non-retail business acres per town.\n",
|
||||
"\n",
|
||||
" ‘chas’ Charles River dummy variable (= 1 if tract bounds river; 0\n",
|
||||
" otherwise).\n",
|
||||
"\n",
|
||||
" ‘nox’ nitrogen oxides concentration (parts per 10 million).\n",
|
||||
"\n",
|
||||
" ‘rm’ average number of rooms per dwelling.\n",
|
||||
"\n",
|
||||
" ‘age’ proportion of owner-occupied units built prior to 1940.\n",
|
||||
"\n",
|
||||
" ‘dis’ weighted mean of distances to five Boston employment\n",
|
||||
" centres.\n",
|
||||
"\n",
|
||||
" ‘rad’ index of accessibility to radial highways.\n",
|
||||
"\n",
|
||||
" ‘tax’ full-value property-tax rate per \\$10,000.\n",
|
||||
"\n",
|
||||
" ‘ptratio’ pupil-teacher ratio by town.\n",
|
||||
"\n",
|
||||
" ‘black’ 1000(Bk - 0.63)^2 where Bk is the proportion of blacks by\n",
|
||||
" town.\n",
|
||||
"\n",
|
||||
" ‘lstat’ lower status of the population (percent).\n",
|
||||
"\n",
|
||||
" ‘medv’ median value of owner-occupied homes in \\$1000s.\n",
|
||||
"\n",
|
||||
"_\bS_\bo_\bu_\br_\bc_\be:\n",
|
||||
"\n",
|
||||
" Harrison, D. and Rubinfeld, D.L. (1978) Hedonic prices and the\n",
|
||||
" demand for clean air. _J. Environ. Economics and Management_ *5*,\n",
|
||||
" 81-102.\n",
|
||||
"\n",
|
||||
" Belsley D.A., Kuh, E. and Welsch, R.E. (1980) _Regression\n",
|
||||
" Diagnostics. Identifying Influential Data and Sources of\n",
|
||||
" Collinearity._ New York: Wiley.\n"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"?Boston"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 23,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\n",
|
||||
"Call:\n",
|
||||
"lm(formula = medv ~ lstat, data = Boston)\n",
|
||||
"\n",
|
||||
"Residuals:\n",
|
||||
" Min 1Q Median 3Q Max \n",
|
||||
"-15.168 -3.990 -1.318 2.034 24.500 \n",
|
||||
"\n",
|
||||
"Coefficients:\n",
|
||||
" Estimate Std. Error t value Pr(>|t|) \n",
|
||||
"(Intercept) 34.55384 0.56263 61.41 <2e-16 ***\n",
|
||||
"lstat -0.95005 0.03873 -24.53 <2e-16 ***\n",
|
||||
"---\n",
|
||||
"Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1\n",
|
||||
"\n",
|
||||
"Residual standard error: 6.216 on 504 degrees of freedom\n",
|
||||
"Multiple R-squared: 0.5441,\tAdjusted R-squared: 0.5432 \n",
|
||||
"F-statistic: 601.6 on 1 and 504 DF, p-value: < 2.2e-16\n"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"lm.fit = lm(medv~lstat, data=Boston)\n",
|
||||
"summary(lm.fit)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "R",
|
||||
"language": "R",
|
||||
"name": "ir"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": "r",
|
||||
"file_extension": ".r",
|
||||
"mimetype": "text/x-r-source",
|
||||
"name": "R",
|
||||
"pygments_lexer": "r",
|
||||
"version": "3.6.3"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
90
ISLR/notebooks/3.6.2.python.ipynb
Normal file
90
ISLR/notebooks/3.6.2.python.ipynb
Normal file
@@ -0,0 +1,90 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 59,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import seaborn as sns\n",
|
||||
"import pandas as pd\n",
|
||||
"import numpy as np\n",
|
||||
"from matplotlib import pyplot as plt\n",
|
||||
"from sklearn import linear_model\n",
|
||||
"from sklearn.metrics import classification_report as summary\n",
|
||||
"\n",
|
||||
"sns.set()\n",
|
||||
"sns.set(style=\"whitegrid\")\n",
|
||||
"tips = sns.load_dataset(\"tips\")\n",
|
||||
"plt.rcParams[\"figure.figsize\"] = (5,8)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 66,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"Boston = pd.read_csv(\"../../datasets/Boston.csv\")\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 67,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"[-0.95004935] 34.5538408793831\n",
|
||||
"0.5441462975864797\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"X = np.array(Boston[\"lstat\"]).reshape(-1,1)\n",
|
||||
"y = Boston[\"medv\"]\n",
|
||||
"model = linear_model.LinearRegression()\n",
|
||||
"model.fit(X, y)\n",
|
||||
"print(model.coef_, model.intercept_)\n",
|
||||
"print(model.score(X,y))\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"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": "3.8.2"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
Reference in New Issue
Block a user