1 files changed, 392 insertions, 0 deletions

diff --git a/Metrics/Metrics-Calculation/metrics_plot/model_evolve_comparison/src/representative_selector .ipynb b/Metrics/Metrics-Calculation/metrics_plot/model_evolve_comparison/src/representative_selector .ipynb
new file mode 100644
index 00000000..32edb00c
--- /dev/null
+++ b/Metrics/Metrics-Calculation/metrics_plot/model_evolve_comparison/src/representative_selector .ipynb
@@ -0,0 +1,392 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Use K-medoid algorithm to find the suitable human model representitives"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os, sys\n",
+    "lib_path = os.path.abspath(os.path.join('..', '..', 'utils'))\n",
+    "sys.path.append(lib_path)\n",
+    "from GraphType import GraphStat\n",
+    "import readCSV as reader\n",
+    "from scipy import stats\n",
+    "from ipywidgets import interact, fixed, interactive\n",
+    "import ipywidgets as widgets\n",
+    "from pyclustering.cluster.kmedoids import kmedoids\n",
+    "from pyclustering.utils.metric import distance_metric, type_metric\n",
+    "import random\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Define a new distance metric"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def ks_value(dest1, dest2):\n",
+    "    value, p = stats.ks_2samp(dest1, dest2)\n",
+    "    return value\n",
+    "\n",
+    "\n",
+    "ks_metric = distance_metric(type_metric.USER_DEFINED, func=ks_value)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Read Human Models"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "304"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Progress Widge\n",
+    "w = widgets.FloatProgress(\n",
+    "    value=0,\n",
+    "    min=0,\n",
+    "    max=1.0,\n",
+    "    step=0.1,\n",
+    "    description='Loading Files...:',\n",
+    "    bar_style='info',\n",
+    "    orientation='horizontal'\n",
+    ")\n",
+    "\n",
+    "humanFiles = reader.readmultiplefiles('../input/Human/', 1300, False)\n",
+    "modelToFileName = {}\n",
+    "for name in humanFiles:\n",
+    "    modelToFileName[GraphStat(name)] = name\n",
+    "\n",
+    "models = list(modelToFileName.keys())\n",
+    "len(humanFiles)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Find Representative by K-medroid for different dists on GraphStat"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "* Returns the index of the representative"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def findRep(graphStats, func):\n",
+    "    out_ds = list(map(func, models))\n",
+    "\n",
+    "    #choose a random starting point\n",
+    "    start_index = random.randint(0, len(out_ds))\n",
+    "\n",
+    "    # start with one initial metrid [start_index]\n",
+    "    outdegree_kmedoid = kmedoids(out_ds, [start_index], metric=ks_metric)\n",
+    "\n",
+    "    outdegree_kmedoid.process()\n",
+    "    centoids = outdegree_kmedoid.get_medoids()\n",
+    "    return centoids[0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Find representative for out degree"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### For Yakindumm\n",
+    "#### For all human models\n",
+    "* the rep found is ../input/humanOutput\\R_20158_run_1.csv\n",
+    "* the average distance between it and others is 0.05515988287586802\n",
+    "\n",
+    "#### For human models with $100 \\pm 10$ nodes\n",
+    "* the rep found is ../input/human_output_100\\R_2015225_run_1.csv\n",
+    "* the average distance between it and others is $0.046150929558524685$\n",
+    "\n",
+    "#### for human model with $100 \\pm 10$ nodes and new metric\n",
+    "* the rep found is ../input/human_output_100\\R_2015248_run_1.csv\n",
+    "* average distance:  0.052753778714861366\n",
+    "* median:  0.0468131868131868\n",
+    "* std:  0.0246917800149673\n",
+    "* max: 0.15993907083015996\n",
+    "* min: 0.0"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../input/Human\\33_run_1.csv\n",
+      "../input/Human\\33_run_1.csv\n"
+     ]
+    }
+   ],
+   "source": [
+    "od_rep_index = findRep(models, lambda m: m.out_d)\n",
+    "print(list(modelToFileName.values())[od_rep_index])\n",
+    "od_rep_model = models[od_rep_index]\n",
+    "print(modelToFileName[od_rep_model])\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "average distance:  0.04615092955852465\n",
+      "median:  0.04402137483980782\n",
+      "std:  0.017305709419913242\n",
+      "max: 0.1411706837186424\n",
+      "min: 0.0\n"
+     ]
+    }
+   ],
+   "source": [
+    "distances = []\n",
+    "for model in models:\n",
+    "    distances.append(ks_value(od_rep_model.out_d, model.out_d))\n",
+    "print('average distance: ', np.mean(distances))\n",
+    "print('median: ', np.median(distances))\n",
+    "print('std: ', np.std(distances))\n",
+    "print('max:', max(distances))\n",
+    "print('min:', min(distances))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Find Representative for node activities"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### For Yakindumm\n",
+    "#### For all human models\n",
+    "* the rep found is ../input/humanOutput\\R_2016176_run_1.csv\n",
+    "* the average distance between it and others is 0.05275267434589047\n",
+    "\n",
+    "#### For human models with $100 \\pm 10$ nodes\n",
+    "* the rep found is ../input/human_output_100\\R_2017419_run_1.csv\n",
+    "* the average distance between it and others is $0.04679429311806747$\n",
+    "\n",
+    "#### for human model with $100 \\pm 10$ nodes and new metric\n",
+    "* the rep found is ../input/human_output_100\\R_2017131_run_1.csv\n",
+    "* average distance:  0.024629205820449567\n",
+    "* median:  0.023787888564682946\n",
+    "* std:  0.013845547883198073\n",
+    "* max: 0.09044674910251294\n",
+    "* min: 0.0"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../input/Human\\288_run_1.csv\n",
+      "../input/Human\\288_run_1.csv\n"
+     ]
+    }
+   ],
+   "source": [
+    "na_rep_index = findRep(models, lambda m: m.na)\n",
+    "print(list(modelToFileName.values())[na_rep_index])\n",
+    "na_rep_model = models[na_rep_index]\n",
+    "print(modelToFileName[na_rep_model])\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "average distance:  0.046794293118067494\n",
+      "median:  0.03898868458274401\n",
+      "std:  0.02880119213919405\n",
+      "max: 0.18702970297029703\n",
+      "min: 0.0\n"
+     ]
+    }
+   ],
+   "source": [
+    "distances = []\n",
+    "for model in models:\n",
+    "    distances.append(ks_value(na_rep_model.na, model.na))\n",
+    "print('average distance: ', np.mean(distances))\n",
+    "print('median: ', np.median(distances))\n",
+    "print('std: ', np.std(distances))\n",
+    "print('max:', max(distances))\n",
+    "print('min:', min(distances))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Find Representative for MPC"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### For Yakindumm\n",
+    "\n",
+    "#### For all human models\n",
+    "* the rep found is ../input/humanOutput\\R_2015246_run_1.csv\n",
+    "* the average distance between it and others is 0.08556632702185384\n",
+    "\n",
+    "#### For human models with $100 \\pm 10$ nodes\n",
+    "* the rep found is ../input/human_output_100\\R_2016324_run_1.csv\n",
+    "* the average distance between it and others is $0.07028909225833631$\n",
+    "\n",
+    "#### for human model with $100 \\pm 10$ nodes and new metric\n",
+    "* average distance:  0.054782550772603904\n",
+    "* median:  0.048330503678551184\n",
+    "* std:  0.028208257424907526\n",
+    "* max: 0.21181525241675614\n",
+    "* min: 0.0"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../input/Human\\151_run_1.csv\n",
+      "../input/Human\\151_run_1.csv\n"
+     ]
+    }
+   ],
+   "source": [
+    "mpc_rep_index = findRep(models, lambda m: m.mpc)\n",
+    "print(list(modelToFileName.values())[mpc_rep_index])\n",
+    "mpc_rep_model = models[mpc_rep_index]\n",
+    "print(modelToFileName[mpc_rep_model])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "average distance:  0.07028909225833632\n",
+      "median:  0.06254480286738351\n",
+      "std:  0.037281890512224164\n",
+      "max: 0.21961550993809065\n",
+      "min: 0.0\n"
+     ]
+    }
+   ],
+   "source": [
+    "distances = []\n",
+    "for model in models:\n",
+    "    distances.append(ks_value(mpc_rep_model.mpc, model.mpc))\n",
+    "print('average distance: ', np.mean(distances))\n",
+    "print('median: ', np.median(distances))\n",
+    "print('std: ', np.std(distances))\n",
+    "print('max:', max(distances))\n",
+    "print('min:', min(distances))"
+   ]
+  }
+ ],
+ "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": 2
+}