1 files changed, 262 insertions, 0 deletions

diff --git a/Metrics/Metrics-Calculation/metrics_plot/src/representative_selector .ipynb b/Metrics/Metrics-Calculation/metrics_plot/src/representative_selector .ipynb
new file mode 100644
index 00000000..4886c215
--- /dev/null
+++ b/Metrics/Metrics-Calculation/metrics_plot/src/representative_selector .ipynb
@@ -0,0 +1,262 @@
+{
+ "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": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "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"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Define a new distance metric"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "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": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "1253"
+      ]
+     },
+     "execution_count": 3,
+     "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",
+    "\n",
+    "humanFiles = reader.readmultiplefiles('../statistics/humanOutput/', 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": 7,
+   "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": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../statistics/humanOutput\\R_20158_run_1.csv\n",
+      "../statistics/humanOutput\\R_20158_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": "markdown",
+   "metadata": {},
+   "source": [
+    "### Find Representative for node activities"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'na_rep_index' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[1;32m<ipython-input-9-7899480190c8>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[0mna_rp_index\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mfindRep\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmodels\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;32mlambda\u001b[0m \u001b[0mm\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mm\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mna\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlist\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmodelToFileName\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mna_rep_index\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      3\u001b[0m \u001b[0mna_rep_model\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmodels\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mna_rep_index\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      4\u001b[0m \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmodelToFileName\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mna_rep_model\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;31mNameError\u001b[0m: name 'na_rep_index' is not defined"
+     ]
+    }
+   ],
+   "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])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../statistics/humanOutput\\R_2016176_run_1.csv\n",
+      "../statistics/humanOutput\\R_2016176_run_1.csv\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(list(modelToFileName.values())[na_rp_index])\n",
+    "na_rep_model = models[na_rp_index]\n",
+    "print(modelToFileName[na_rep_model])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Find Representative for MPC"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../statistics/humanOutput\\R_2015246_run_1.csv\n",
+      "../statistics/humanOutput\\R_2015246_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])"
+   ]
+  }
+ ],
+ "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
+}