{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true,
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "# Louvain hierarchy"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "This notebook illustrates the hierarchical clustering of graphs by [Louvain](https://scikit-network.readthedocs.io/en/latest/reference/hierarchy.html) (successive aggregations, in a bottom-up manner)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "pycharm": {
     "is_executing": false,
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "from IPython.display import SVG"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "pycharm": {
     "is_executing": false,
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "pycharm": {
     "is_executing": false,
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "from sknetwork.data import karate_club, painters, movie_actor\n",
    "from sknetwork.hierarchy import LouvainHierarchy\n",
    "from sknetwork.hierarchy import cut_straight, dasgupta_score, tree_sampling_divergence\n",
    "from sknetwork.visualization import visualize_graph, visualize_bigraph, visualize_dendrogram"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "## Graphs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "pycharm": {
     "is_executing": false,
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "graph = karate_club(metadata=True)\n",
    "adjacency = graph.adjacency\n",
    "position = graph.position"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "pycharm": {
     "is_executing": false,
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "# hierarchical clustering\n",
    "louvain = LouvainHierarchy()\n",
    "dendrogram = louvain.fit_predict(adjacency)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "pycharm": {
     "is_executing": false,
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "image = visualize_dendrogram(dendrogram)\n",
    "SVG(image)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "pycharm": {
     "is_executing": false,
     "name": "#%%\n"
    },
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0 0 0 0 3 3 3 0 1 0 3 0 0 0 1 1 3 0 1 0 1 0 1 2 2 2 1 2 2 1 1 2 1 1]\n"
     ]
    }
   ],
   "source": [
    "# cuts\n",
    "labels = cut_straight(dendrogram)\n",
    "print(labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "pycharm": {
     "is_executing": false,
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0 0 0 0 3 3 3 0 1 0 3 0 0 0 1 1 3 0 1 0 1 0 1 2 2 2 1 2 2 1 1 2 1 1]\n"
     ]
    }
   ],
   "source": [
    "labels, dendrogram_aggregate = cut_straight(dendrogram, n_clusters=4, return_dendrogram=True)\n",
    "print(labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "_, counts = np.unique(labels, return_counts=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "image = visualize_dendrogram(dendrogram_aggregate, names=counts, rotate_names=False)\n",
    "SVG(image)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "pycharm": {
     "is_executing": false,
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "image = visualize_graph(adjacency, position, labels=labels)\n",
    "SVG(image)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "pycharm": {
     "is_executing": false,
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.5878582202111614"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# metrics\n",
    "dasgupta_score(adjacency, dendrogram)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "## Directed graphs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "pycharm": {
     "is_executing": false,
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "graph = painters(metadata=True)\n",
    "adjacency = graph.adjacency\n",
    "position = graph.position\n",
    "names = graph.names"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "pycharm": {
     "is_executing": false,
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "# hierarchical clustering\n",
    "louvain = LouvainHierarchy()\n",
    "dendrogram = louvain.fit_predict(adjacency)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "pycharm": {
     "is_executing": false,
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "image = visualize_dendrogram(dendrogram, names, rotate=True)\n",
    "SVG(image)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "pycharm": {
     "is_executing": false,
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[1 0 2 0 2 2 1 0 1 2 1 0 0 1]\n"
     ]
    }
   ],
   "source": [
    "# cut with 3 clusters\n",
    "labels = cut_straight(dendrogram, n_clusters = 3)\n",
    "print(labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "pycharm": {
     "is_executing": false,
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "image = visualize_graph(adjacency, position, names=names, labels=labels)\n",
    "SVG(image)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "pycharm": {
     "is_executing": false,
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.4842857142857142"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# metrics\n",
    "dasgupta_score(adjacency, dendrogram)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "## Bipartite graphs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "graph = movie_actor(metadata=True)\n",
    "biadjacency = graph.biadjacency\n",
    "names_row = graph.names_row\n",
    "names_col = graph.names_col"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "# hierarchical clustering\n",
    "louvain = LouvainHierarchy()\n",
    "louvain.fit(biadjacency)\n",
    "dendrogram_row = louvain.dendrogram_row_\n",
    "dendrogram_col = louvain.dendrogram_col_\n",
    "dendrogram_full = louvain.dendrogram_full_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "image = visualize_dendrogram(dendrogram_row, names_row, n_clusters=4, rotate=True)\n",
    "SVG(image)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "image = visualize_dendrogram(dendrogram_col, names_col, n_clusters=4, rotate=True)\n",
    "SVG(image)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "# cuts\n",
    "labels = cut_straight(dendrogram_full, n_clusters = 4)\n",
    "n_row = biadjacency.shape[0]\n",
    "labels_row = labels[:n_row]\n",
    "labels_col = labels[n_row:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "image = visualize_bigraph(biadjacency, names_row, names_col, labels_row, labels_col)\n",
    "SVG(image)\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.13"
  },
  "pycharm": {
   "stem_cell": {
    "cell_type": "raw",
    "metadata": {
     "collapsed": false
    },
    "source": []
   }
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}