{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Pairplot: Visualizing High Dimensional Data\n",
    "\n",
    "This example provides how to visualize high dimensional data using the pairplot."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import graspologic\n",
    "\n",
    "import numpy as np\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Simulate a binary graph using stochastic block model\n",
    "The 3-block model is defined as below:\n",
    "\n",
    "\\begin{align*}\n",
    "n &= [50, 50, 50]\\\\\n",
    "P &= \n",
    "\\begin{bmatrix}0.5 & 0.1 & 0.05 \\\\\n",
    "0.1 & 0.4 & 0.15 \\\\\n",
    "0.05 & 0.15 & 0.3\n",
    "\\end{bmatrix}\n",
    "\\end{align*}\n",
    "\n",
    "Thus, the first 50 vertices belong to block 1, the second 50 vertices belong to block 2, and the last 50 vertices belong to block 3."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from graspologic.simulations import sbm\n",
    "\n",
    "n_communities = [50, 50, 50]\n",
    "p = [[0.5, 0.1, 0.05], \n",
    "     [0.1, 0.4, 0.15], \n",
    "     [0.05, 0.15, 0.3],]\n",
    "\n",
    "np.random.seed(2)\n",
    "A = sbm(n_communities, p)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Embed using adjacency spectral embedding to obtain lower dimensional representation of the graph\n",
    "\n",
    "The embedding dimension is automatically chosen. It should embed to 3 dimensions."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from graspologic.embed import AdjacencySpectralEmbed\n",
    "\n",
    "ase = AdjacencySpectralEmbed()\n",
    "X = ase.fit_transform(A)\n",
    "\n",
    "print(X.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Use pairplot to plot the embedded data\n",
    "\n",
    "First we generate labels that correspond to blocks. We pass the labels along with the data for pair plot."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from graspologic.plot import pairplot\n",
    "\n",
    "labels = ['Block 1'] * 50 + ['Block 2'] * 50 + ['Block 3'] * 50\n",
    "\n",
    "plot = pairplot(X, labels)"
   ]
  },
  {
   "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}