{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Pick Sampling"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"%useLatestDescriptors\n",
"%use lets-plot"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"fun genWord(length:Int):String {\n",
" val letters = ('a'..'z')\n",
" return List(length) { letters.random() }.joinToString(\"\")\n",
"} \n",
"\n",
"fun genWordSet(n:Int):Set {\n",
" val words = HashSet()\n",
" while(words.size < n) {\n",
" words.add(genWord(5))\n",
" }\n",
" return words\n",
"}\n",
"\n",
"fun data(n:Int, words:Set):Map {\n",
" return mapOf(\n",
" \"word\" to List(n) { words.random() },\n",
" \"g\" to List(n) { listOf('a','b','c').random() }\n",
" )\n",
"}"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"// Number of unique words exceeds threshold (50) of default 'pick' sampling on bar chart.\n",
"val words = genWordSet(500)\n",
"val dat = data(1000, words)\n",
"val p = ggplot(dat) { x = \"word\" }"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"// Disable sampling to see the overplotting.\n",
"p + geomBar(sampling = samplingNone, size = 0)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"// Draw plot with default sampling.\n",
"p + geomBar(size = 0)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"// 'pick' sampling preserves groups on bar chart.\n",
"p + geomBar(size = 0) { fill = \"g\" }"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" \n",
" "
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"// Orgering words by `count` might be a good idea.\n",
"p + geomBar(size = 0) {\n",
" fill = \"g\"\n",
" x = asDiscrete(\"word\", orderBy = \"..count..\")\n",
"}"
]
}
],
"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",
"nbconvert_exporter": "",
"pygments_lexer": "kotlin",
"version": "1.8.0-dev-3517"
}
},
"nbformat": 4,
"nbformat_minor": 4
}