{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This page is available as an executable or viewable Jupyter Notebook:\n",
"
\n",
" \n",
" ![](\"https://mybinder.org/badge_logo.svg\")
\n",
"\n",
" \n",
" ![](\"https://raw.githubusercontent.com/jupyter/design/master/logos/Badges/nbviewer_badge.png\")
\n",
"\n",
"
\n",
"
"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"%use lets-plot\n",
"import java.util.Random"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"val rand = java.util.Random(123)\n",
"val n = 200\n",
"val data = mapOf(\n",
" \"cond\" to List(n) { \"A\" } + List(n) { \"B\" },\n",
" \"rating\" to List(n) { rand.nextGaussian() } + List(n) { rand.nextGaussian() * 1.5 + 1.5 },\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"// Basic histogram of \"rating\"\n",
"val p = lets_plot(data) { x = \"rating\" } + ggsize(500, 250)\n",
"p + geom_histogram(binWidth=0.5)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"// Histogram overlaid with kernel density curve\n",
"// - histogram with density instead of count on y-axis\n",
"// - overlay with transparent density plot\n",
"\n",
"p + geom_histogram(binWidth=0.5, color=\"black\", fill=\"white\") { y = \"..density..\" } +\n",
" geom_density(alpha=0.2, fill=0xFF6666)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"p + geom_histogram(binWidth=.5, color=\"black\", fill=\"white\") +\n",
" geom_vline(xintercept=(data[\"rating\"] as List).average(), color=\"red\", linetype=\"dashed\", size=1.0)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Histogram and density plots with multiple groups"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"val p1 = lets_plot(data) {x = \"rating\"; fill=\"cond\"} + ggsize(500, 250)\n",
"\n",
"// Default histogram (stacked)\n",
"p1 + geom_histogram(binWidth=0.5, alpha=.5)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"// Overlaid histograms\n",
"p1 + geom_histogram(binWidth=0.5, alpha=0.5, position=Pos.identity)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"// Interleaved histograms\n",
"p1 + geom_histogram(binWidth=0.5, alpha=.5, position=Pos.dodge)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"// Density plot\n",
"val p2 = ggplot(data) {x=\"rating\"; color=\"cond\"} + ggsize(500, 250)\n",
"p2 + geom_density()"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"// Density plot with semi-transparent fill\n",
"p2 + geom_density(alpha=.3) {fill=\"cond\"} "
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{cond=[A, B], rating=[-0.011843241476365302, 1.5547269440141214]}"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"// Find the mean of each group\n",
"val means = (data[\"cond\"] as List zip data[\"rating\"] as List)\n",
" .groupBy(keySelector = { it.first }, valueTransform = { it.second })\n",
" .mapValues { it.value.average() }\n",
"val cdat = mapOf(\n",
" \"cond\" to means.keys,\n",
" \"rating\" to means.values\n",
")\n",
"cdat"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"// Overlaid histograms with means\n",
"p2 + geom_histogram(alpha=.3, position=Pos.identity, size=0.0, bins=10) {fill=\"cond\"} +\n",
" geom_vline(data=cdat, linetype=\"dashed\", size=1.0) {xintercept=\"rating\"; color=\"cond\"}\n"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"// Use frqpoly instead of histogram\n",
"p2 + geom_freqpoly(bins=10) {color=\"cond\"} +\n",
" geom_vline(data=cdat, linetype=\"dashed\", size=1.0) {xintercept=\"rating\"; color=\"cond\"}\n"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"// Density plots with means\n",
"p2 + geom_density() +\n",
" geom_vline(data=cdat, linetype=\"dashed\", size=1.0) {xintercept=\"rating\"; color=\"cond\"}"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Using facets"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"ggplot(data) {x=\"rating\"} + \n",
" geom_histogram(binWidth=.5, color=\"black\", fill=\"white\") +\n",
" facet_grid(\"cond\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Box plots"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"// A basic box plot\n",
"val p3 = ggplot(data) {x=\"cond\"; y=\"rating\"} + ggsize(300, 200)\n",
"p3 + geom_boxplot()"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"// A basic box with the conditions colored\n",
"p3 + geom_boxplot {fill=\"cond\"}"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"// Style outliers\n",
"p3 + geom_boxplot(outlierColor=\"red\", outlierShape=8, outlierSize=5)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Kotlin",
"language": "kotlin",
"name": "kotlin"
},
"language_info": {
"codemirror_mode": "text/x-kotlin",
"file_extension": ".kt",
"mimetype": "text/x-kotlin",
"name": "kotlin",
"pygments_lexer": "kotlin",
"version": "1.4.20-dev-1121"
},
"pycharm": {
"stem_cell": {
"cell_type": "raw",
"source": [],
"metadata": {
"collapsed": false
}
}
}
},
"nbformat": 4,
"nbformat_minor": 4
}