{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# * Visualizing of genetic similarity with Lightning + GraphX *"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Setup lightning"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": []
}
],
"source": [
"%libraryDependencies += \"org.viz.lightning\" %% \"lightning-scala\" % \"0.1.6\""
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": []
}
],
"source": [
"%update"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": []
}
],
"source": [
"import org.viz.lightning._\n",
"import org.apache.spark.graphx._"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": []
},
{
"data": {
"text/plain": [
"org.viz.lightning.Lightning@7cd4a5c1"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"val lgn = Lightning(host=\"https://lightning-spark-summit.herokuapp.com\" )\n",
"lgn.enableNotebook()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Load structure similarity data"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Public data from http://www.brain-map.org/"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": []
},
{
"data": {
"text/plain": [
"org.apache.spark.graphx.impl.GraphImpl@36afd257"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"val source = \"/Users/mathisonian/projects/spark-summit/notebooks/data/allen-connectivity.txt\"\n",
"val g = GraphLoader.edgeListFile(sc, source)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Show the network (unlabeled)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": []
},
{
"data": {
"text/plain": [
"org.viz.lightning.Visualization@7a4932cd"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"val links = g.edges.collect().map(e => Array(e.srcId.toInt, e.dstId.toInt))\n",
"\n",
"lgn.force(links)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Show the network colored by degree"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": []
},
{
"data": {
"text/plain": [
"org.viz.lightning.Visualization@417fda19"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"val links = g.edges.collect().map(e => Array(e.srcId.toInt, e.dstId.toInt))\n",
"val degrees = g.degrees.sortBy(_._1).collect().map(x => Math.log(x._2))\n",
"\n",
"lgn.force(links, value=degrees, colormap=\"Lightning\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Show the network colored by connected components"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": []
},
{
"data": {
"text/plain": [
"org.viz.lightning.Visualization@74ca5c41"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"val links = g.edges.collect().map(e => Array(e.srcId.toInt, e.dstId.toInt))\n",
"val connectedComponents = g.connectedComponents().vertices.sortBy(_._1).map(_._2.toInt).collect()\n",
"\n",
"lgn.force(links, label=connectedComponents)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 2",
"language": "python",
"name": "python2"
},
"language_info": {
"name": "scala",
"version": "2.10.4"
}
},
"nbformat": 4,
"nbformat_minor": 0
}