1 files changed, 481 insertions, 0 deletions

diff --git a/Metrics/Metrics-Calculation/metrics_plot/model_evolve_comparison/src/metrics_distance.ipynb b/Metrics/Metrics-Calculation/metrics_plot/model_evolve_comparison/src/metrics_distance.ipynb
new file mode 100644
index 00000000..550e3978
--- /dev/null
+++ b/Metrics/Metrics-Calculation/metrics_plot/model_evolve_comparison/src/metrics_distance.ipynb
@@ -0,0 +1,481 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Compare Metrics Distances to The Human Models"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from GraphType import GraphStat\n",
+    "from GraphType import GraphCollection\n",
+    "from scipy import stats\n",
+    "from ipywidgets import interact, fixed, interactive\n",
+    "import readCSV as reader\n",
+    "import ipywidgets as widgets\n",
+    "import matplotlib.pyplot as plt\n",
+    "import random\n",
+    "import numpy as np\n",
+    "import constants\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Classes"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "* Record the average distances of different metrics for a model to the human models "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class GraphDistance:\n",
+    "    #init with a graph stat and a collection of graph stats\n",
+    "    def __init__(self, graphStat, collection):\n",
+    "        self.graph = graphStat\n",
+    "        self.collection = collection\n",
+    "        self.out_d_distance = average_ks_distance(collection.out_ds, graphStat.out_d)\n",
+    "        self.na_distance = average_ks_distance(collection.nas, graphStat.na)\n",
+    "        self.mpc_distance = average_ks_distance(collection.mpcs, graphStat.mpc)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Methods"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "* Calculate the average ks distance"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def average_ks_distance(targets, sample):\n",
+    "    distance = 0.0\n",
+    "    for target in targets:\n",
+    "        value, p = stats.ks_2samp(target, sample)\n",
+    "        distance += value\n",
+    "    distance = distance / len(targets)\n",
+    "    return distance\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "pycharm": {
+     "name": "#%% md\n"
+    }
+   },
+   "source": [
+    "* Find the median ks distance of the same number of nodes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "def find_median(x, metric_distances):\n",
+    "    distance_dic = {}\n",
+    "    for index, num_of_nodes in enumerate(x):\n",
+    "        if num_of_nodes[0] not in distance_dic:\n",
+    "            distance_dic[num_of_nodes[0]] = []\n",
+    "        distance_dic[num_of_nodes[0]].append(metric_distances[index])\n",
+    "    median_x = []\n",
+    "    y = []\n",
+    "    for num_of_nodes, distances in distance_dic.items():\n",
+    "        median_x.append(num_of_nodes)\n",
+    "        y.append(np.median(distances))\n",
+    "    order = np.argsort(median_x)\n",
+    "    median_x = np.array(median_x)[order]\n",
+    "    median_y = np.array(y)[order]\n",
+    "    return median_x, median_y\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "* Plot Diagram"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# metric_selector: GraphDistance -> float\n",
+    "def plot(infos, lines, id, metric_selector,colors, title):\n",
+    "    metric_distances = retrive_info_from_list(metric_selector, list(infos.values()))\n",
+    "    x = retrive_info_from_list(lambda a : a.graph.num_nodes, list(infos.values()))\n",
+    "    graph = plt.figure(id,figsize=(18, 10))\n",
+    "    plt.title(title)\n",
+    "    plt.plot(x, metric_distances, color='red', linestyle='', marker='o',alpha=0.7)\n",
+    "    #plot ks distance median\n",
+    "    median_x, median_y = find_median(x, metric_distances)\n",
+    "    plt.plot(median_x, median_y, color='black',marker='o')\n",
+    "    for i in range(0, len(lines)):\n",
+    "        line_infos = retrive_info_from_list(lambda a: infos[a], lines[i])\n",
+    "        line_y = retrive_info_from_list(metric_selector, line_infos)\n",
+    "        line_x = retrive_info_from_list(lambda a : a.graph.num_nodes, line_infos)\n",
+    "        plt.plot(line_x, line_y, marker='o', color=colors[i])\n",
+    "    #graph.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "* Retrieve information from a list "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def retrive_info_from_list(selector, distances):\n",
+    "    return list(map(selector, distances))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Read Models"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "human = GraphCollection('../statistics/humanOutput/', 300, 'Human', True)\n",
+    "file_names = reader.readmultiplefiles('../statistics/viatraEvolve/', 1000, False)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Calculate Distances"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Progress Widge\n",
+    "w2 = 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",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "ca7932bce2a741afaff6b919042c42b0",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "FloatProgress(value=0.0, bar_style='info', description='Loading Files...:', max=1.0)"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "infos = []\n",
+    "# read all files\n",
+    "counter = 0.0\n",
+    "size = len(file_names)\n",
+    "#display progress bar\n",
+    "display(w2)\n",
+    "for name in file_names:\n",
+    "    infos.append(GraphStat(name))\n",
+    "\n",
+    "info_dic = {}\n",
+    "for info in infos:\n",
+    "    w2.value = (counter/size)\n",
+    "    counter+=1\n",
+    "    info = GraphDistance(info, human)\n",
+    "    info_dic[info.graph.id] = info"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Plot Graphs"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "* widget for select trajectory"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "filenames = reader.readmultiplefiles('../statistics/trajectories/', 10, False)\n",
+    "trajectories = {}\n",
+    "for name in filenames:\n",
+    "    trajectories[name] = reader.readTrajectory(name)\n",
+    "\n",
+    "w = widgets.SelectMultiple(\n",
+    "    options = trajectories,\n",
+    "    value = [trajectories[filenames[0]]],\n",
+    "    description='Trajectory:',\n",
+    "    disabled=False,\n",
+    ")\n",
+    "\n",
+    "#generate random color for each line\n",
+    "colors = []\n",
+    "\n",
+    "for i in range(0, len(trajectories)):\n",
+    "    color = \"#%06x\" % random.randint(0, 0xFFFFFF)\n",
+    "    colors.append(color)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Out Degree"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "08da62cb0c3f4e6e9591c7dc811d27cc",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "interactive(children=(SelectMultiple(description='Trajectory:', index=(1,), options={'../statistics/trajectori…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<function __main__.plot_out_degree(lines)>"
+      ]
+     },
+     "execution_count": 63,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "def plot_out_degree(lines):\n",
+    "    plot(info_dic, lines, 0, lambda a: a.out_d_distance, colors, 'out degree')\n",
+    "interact(plot_out_degree, lines=w)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Node Activity"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a708f43645a24bd2b15b53ea12c7d88f",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "interactive(children=(SelectMultiple(description='Trajectory:', index=(1,), options={'../statistics/trajectori…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<function __main__.plot_na(lines)>"
+      ]
+     },
+     "execution_count": 64,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "def plot_na(lines):\n",
+    "    plot(info_dic, lines, 0, lambda a: a.na_distance, colors, 'node activity')\n",
+    "interact(plot_na, lines=w)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### MPC"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 65,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "124a0cb0ebfb4225bf4ced24c09032f7",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "interactive(children=(SelectMultiple(description='Trajectory:', index=(1,), options={'../statistics/trajectori…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<function __main__.plot_out_degree(lines)>"
+      ]
+     },
+     "execution_count": 65,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "def plot_out_degree(lines):\n",
+    "    plot(info_dic, lines, 0, lambda a: a.mpc_distance, colors, 'MPC')\n",
+    "interact(plot_out_degree, lines=w)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for name in file_names:\n",
+    "    contents = reader.readcsvfile(name)\n",
+    "    if(contents['State Id'][0] == 1032396643):\n",
+    "        print(name)"
+   ]
+  }
+ ],
+ "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"
+  },
+  "pycharm": {
+   "stem_cell": {
+    "cell_type": "raw",
+    "metadata": {
+     "collapsed": false
+    },
+    "source": []
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}