{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Benchmark"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 155,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Settings\n",
    "root_dir = '/home/dennis/VILLASnode/tests/benchmarks'\n",
    "benchmark_dir = 'benchmarks_20180801_00-11-11'"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Load all files\n",
    "### Results\n",
    "...\n",
    "\n",
    "### Source log\n",
    "..."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 156,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Loaded /home/dennis/VILLASnode/tests/benchmarks/benchmarks_20180801_00-11-11/0_TCP-3-100000-1000000.csv\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import os\n",
    "import re\n",
    "\n",
    "# First, source log\n",
    "\n",
    "# Initialize arrays\n",
    "result_files = []\n",
    "result_paths = []\n",
    "log_paths = []\n",
    "result_array = []\n",
    "\n",
    "# Save complete path of files in an array\n",
    "for subdir, dirs, files in os.walk(root_dir+'/'+benchmark_dir):\n",
    "    for file in files:\n",
    "        # Regex to match .csv files\n",
    "        if re.match(r'.*?csv', file, re.M|re.I):\n",
    "            result_paths.append(os.path.join(subdir, file))\n",
    "        # Regex to match .log files\n",
    "        elif re.match(r'.*?log', file, re.M|re.I):\n",
    "            log_paths.append(os.path.join(subdir, file))\n",
    "        \n",
    "    result_files = files\n",
    "\n",
    "# Loop through array with result files and save the comma separated data into a new array\n",
    "for file in result_paths:\n",
    "    print(\"Loaded {}\".format(file))\n",
    "    \n",
    "    # Load file \n",
    "    result_array.append(np.genfromtxt(file, delimiter=','))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Save characteristics of tests\n",
    "All important settings are contained in the name of the file. We will save them in a separate array. The structure of the name is as follows:\n",
    "\n",
    "```bash\n",
    "root_dir/benchmarks_${DATE}/${ID}_${MODE}-${VALUES IN SMP}-${RATE}-${SENT SMPS}\n",
    "```\n",
    "\n",
    "Thus, we will structure it in the settings_array as follows:\n",
    "\n",
    "* `settings_array[*][0] = ID`\n",
    "* `settings_array[*][1] = MODE`\n",
    "* `settings_array[*][2] = VALUES IN SAMPLE`\n",
    "* `settings_array[*][3] = RATE`\n",
    "* `settings_array[*][4] = TOTAL NUMBER OF SAMPLES`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 157,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# Array with settings\n",
    "settings_array = []\n",
    "\n",
    "for file in result_files:\n",
    "    settings = []\n",
    "    \n",
    "    matchObj = re.match(r'(\\d*)_(\\w*)-(\\d*)-(\\d*)-(\\d*).csv', file, re.M|re.I)\n",
    "\n",
    "    # Fill values to array\n",
    "    if matchObj:\n",
    "        for i in range(0,5):\n",
    "            settings.append(matchObj.group(i+1))\n",
    "    \n",
    "        # Append array to big array\n",
    "        settings_array.append(settings)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Get missed steps from source node\n",
    "..."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 161,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "540\n"
     ]
    }
   ],
   "source": [
    "missing_send_arr = []\n",
    "\n",
    "# This line indicates if we passed the \"node connected\" line. Only after this line\n",
    "# the script will start counting missed steps\n",
    "connected = False\n",
    "\n",
    "for i, file in enumerate(log_paths):\n",
    "    F = open(file, \"r\")\n",
    "    line = F.readline()\n",
    "\n",
    "    missing_send_arr.append(0)\n",
    "\n",
    "    # Loop through file\n",
    "    while line:\n",
    "        #if re.match(r'.*Connection established in node', line):\n",
    "        connected = True\n",
    "    \n",
    "        if connected:\n",
    "            #matchObj = re.match(r'.*Missed steps: (\\d*)', line, re.M|re.I)\n",
    "            matchObj = re.match(r'.*written=0, expected=(\\d*)', line, re.M|re.I)\n",
    "        \n",
    "            if matchObj:\n",
    "                missing_send_arr[i] += int(matchObj.group(1))\n",
    "        \n",
    "        line = F.readline()\n",
    "    \n",
    "    print(missing_send_arr[i])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Process data\n",
    "\n",
    "### Number of samples\n",
    "* First number which appears in `result_array[*][3]` will be the first sample in the benchmark. Ignore all missing samples before that entry.\n",
    "* After that, check how many samples are missing.\n",
    "* Then, calculate the percentage of missing samples."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 162,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Test 0 missed 68 (0.011%) of 995605 (1000000 before correction) samples\n"
     ]
    }
   ],
   "source": [
    "# Sequence number of first sample that occurs are receive side\n",
    "start_sequence = []\n",
    "# Real total number of sent messages, after subtraction of first sequence\n",
    "real_total_arr = []\n",
    "# Number of missing samples after first sample\n",
    "missing_recv_arr = []\n",
    "# Percentage of missed samples\n",
    "perc_miss_arr = []\n",
    "\n",
    "# Generate real total and number of missing samples.\n",
    "# Print percentage of missed samples\n",
    "for (i, csv_vec) in enumerate(result_array):\n",
    "    start_sequence.append(csv_vec[0][3])\n",
    "    \n",
    "    # Real total number = total number - start_seqquence\n",
    "    # Number missing = real total number - length of data arary\n",
    "    real_total = int(settings_array[i][4]) - int(start_sequence[i])\n",
    "    missing_recv = real_total - len(csv_vec)\n",
    "    perc_miss = round(missing_recv / real_total * 100, 3)\n",
    "    \n",
    "    print(\"Test {} missed {} ({}%) of {} ({} before correction) samples\"\n",
    "          .format(i, number_miss, perc_miss, real_total, settings_array[i][4]))\n",
    "    \n",
    "    real_total_arr.append(real_total)\n",
    "    missing_recv_arr.append(number_miss)\n",
    "    perc_miss_arr.append(perc_miss)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "## Plot data\n",
    "We want to plot the offset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "from matplotlib.font_manager import FontProperties\n",
    "import os\n",
    "\n",
    "# Start creating plots\n",
    "for i, val in enumerate(result_array):\n",
    "    # Create figure\n",
    "    fig = plt.figure(num=None, figsize=(12, 8), dpi=90, facecolor='w', edgecolor='k')\n",
    "\n",
    "    # Add plot and set title\n",
    "    ax = fig.add_subplot(111)\n",
    "    \n",
    "    # Set subtitle \n",
    "    title = \"Test {} — Mode: {}, Values in Sample: {}, Rate: {}, Total number of Samples: {}\".format(settings_array[i][0],\n",
    "                                                                                                     settings_array[i][1], \n",
    "                                                                                                     settings_array[i][2], \n",
    "                                                                                                     settings_array[i][3], \n",
    "                                                                                                     settings_array[i][4])\n",
    "    ax.set_title(title, fontsize=12, pad=12, loc='center')\n",
    "    \n",
    "    # Set grid\n",
    "    ax.set_axisbelow(True)\n",
    "    ax.grid(True, linestyle='--')\n",
    "\n",
    "    bins = 6250\n",
    "    x_limit=0.0001\n",
    "    \n",
    "    # Data in plot\n",
    "    # http://www.color-hex.com/color-palette/33602\n",
    "    val_t = val.transpose()\n",
    "    \n",
    "    ax.hist(val_t[2], label='t_sent -> t_recv offset', edgecolor='black', bins=bins, color='#00549f')\n",
    "\n",
    "    # Set axis and calculate values above limit\n",
    "    plt.xlim([0,x_limit])\n",
    "       \n",
    "\n",
    "    plt.xticks(np.arange(0, x_limit + 0.000001, 0.00001), fontsize=11)\n",
    "    plt.yticks(fontsize=11)\n",
    "\n",
    "    # Labels\n",
    "    ax.set_xlabel('time [s]', fontsize=13, labelpad=20)\n",
    "    ax.set_ylabel('frequency', fontsize=13, labelpad=20)\n",
    "    ax.set_yscale('log')\n",
    "\n",
    "    # Create text for offset\n",
    "    off_smaller_4us  = round((np.size(val_t[2][val_t[2] < 0.000004]) / np.size(val_t[2])) * 100, 3)\n",
    "    off_smaller_5us  = round((np.size(val_t[2][val_t[2] < 0.000005]) / np.size(val_t[2])) * 100, 3)\n",
    "    off_smaller_10us = round((np.size(val_t[2][val_t[2] < 0.00001]) / np.size(val_t[2])) * 100, 3)\n",
    "    off_bigger_100us = round((np.size(val_t[2][val_t[2] > x_limit]) / np.size(val_t[2])) * 100, 4)\n",
    "    \n",
    "    offset_text  = 'offset <     {} for {}% of samples\\n'.format('4µs', off_smaller_4us)\n",
    "    offset_text += 'offset <     {} for {}% of samples\\n'.format('5µs', off_smaller_5us)\n",
    "    offset_text += 'offset <   {} for {}% of samples\\n'.format('10µs', off_smaller_10us)\n",
    "    offset_text += 'offset > {} for {}% of samples'.format('100µs', off_bigger_100us)\n",
    "    \n",
    "    # Create text for missed steps\n",
    "    #ToDo: Add percentage\n",
    "    missed_text  = 'missed by villas-pipe:  {0: <23}\\n'.format(missing_recv_arr[i])\n",
    "    missed_text += 'missed by villas-node: {0: <23}'.format(0)\n",
    "           \n",
    "    # bbox accepts FancyBboxPatch prop dict\n",
    "    font_header = FontProperties()\n",
    "    font_header.set_weight('bold')\n",
    "    font_header.set_size(10)\n",
    "    \n",
    "    # Offset boxes\n",
    "    ax.text(0.983, 0.88, \"Offset Ranges\",\n",
    "            verticalalignment='top', horizontalalignment='right',\n",
    "            transform=ax.transAxes,\n",
    "            color='black', fontproperties = font_header)\n",
    "    ax.text(0.712, 0.84, offset_text,\n",
    "            verticalalignment='top', horizontalalignment='left',\n",
    "            transform=ax.transAxes,\n",
    "            color='black', fontsize=9.25,\n",
    "            bbox={'facecolor':'white', 'alpha':0.85, 'pad':0.3, 'boxstyle':'round',\n",
    "                  'edgecolor':'#dbdbdb'})\n",
    "    \n",
    "    # Missed steps\n",
    "    ax.text(0.983, 0.70, \"Missed steps\",\n",
    "            verticalalignment='top', horizontalalignment='right',\n",
    "            transform=ax.transAxes,\n",
    "            color='black', fontproperties = font_header)\n",
    "    ax.text(0.712, 0.66, missed_text,\n",
    "            verticalalignment='top', horizontalalignment='left',\n",
    "            transform=ax.transAxes,\n",
    "            color='black', fontsize=9.25,\n",
    "            bbox={'facecolor':'white', 'alpha':0.85, 'pad':0.3, 'boxstyle':'round',\n",
    "                  'edgecolor':'#dbdbdb'})\n",
    "\n",
    "    #Create legend\n",
    "    ax.legend(loc=1, fontsize=12)\n",
    "    \n",
    "\n",
    "    #Show plot\n",
    "    plt.show()\n",
    "    \n",
    "    #Save plot\n",
    "    fig.savefig('./plots/test{}.png'.format(i))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}