{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "pretty-performer",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2022-06-10 11:42:10.893743: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory\n",
      "2022-06-10 11:42:10.893816: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib.colors\n",
    "from PIL import Image, ImageDraw, ImageFont\n",
    "from library.analysis import testSets, generators"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "engaging-warehouse",
   "metadata": {},
   "source": [
    "# Constants"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "crazy-taxation",
   "metadata": {},
   "outputs": [],
   "source": [
    "kScore = \"cohens kappa score\"\n",
    "f1Score = \"f1 score\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "extensive-future",
   "metadata": {},
   "source": [
    "# Settings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "warming-department",
   "metadata": {},
   "outputs": [],
   "source": [
    "ignoreSet = [\"ozone_level\", \"yeast_me2\"]\n",
    "\n",
    "gans = [g.replace(\"SimpleGAN\", \"GAN\") for g in generators.keys()]\n",
    "algs = [\"LR\", \"RF\", \"GB\", \"KNN\", \"DoG\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "edf5b592",
   "metadata": {},
   "outputs": [],
   "source": [
    "testSets = [t for t in testSets if t[0:7] == \"folding\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "seasonal-greek",
   "metadata": {},
   "source": [
    "# ProWRAS Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "needed-birmingham",
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset  = [\n",
    "    \"abalone9-18\",\n",
    "    \"abalone_17_vs_7_8_9_10\",\n",
    "    \"car-vgood\",\"car_good\",\n",
    "    \"flare-F\",\n",
    "    \"hypothyroid\",\n",
    "    \"kddcup-guess_passwd_vs_satan\",\n",
    "    \"kr-vs-k-three_vs_eleven\",\n",
    "    \"kr-vs-k-zero-one_vs_draw\",\n",
    "    \"shuttle-2_vs_5\",\n",
    "    \"winequality-red-4\",\n",
    "    \"yeast4\",\n",
    "    \"yeast5\",\n",
    "    \"yeast6\",\n",
    "    \"ozone_level\",\n",
    "    \"yeast_me2\",\n",
    "    \"Average\"\n",
    "    ]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d7e8179d",
   "metadata": {},
   "source": [
    "knn_ProWRAS_f1 = [0.384,0.347,0.818,0.641,0.301,0.553,1.0,0.94,0.9,1.0,0.141,0.308,0.714,0.545,0.556,0.339,0.538]\n",
    "knn_ProWRAS_k = [0.35,0.328,0.81,0.622,0.263,0.528,1.0,0.938,0.896,1.0,0.093,0.268,0.704,0.531,0.526,0.305,0.515]\n",
    "\n",
    "lr_ProWRAS_f1 = [0.488,0.315,0.407,0.103,0.341,0.446,0.99,0.928,0.853,1.0,0.158,0.308,0.591,0.326,0.347,0.295,0.472]\n",
    "lr_ProWRAS_k = [0.446,0.287,0.371,0.033,0.3,0.407,0.99,0.926,0.847,1.0,0.119,0.268,0.574,0.3,0.319,0.254,0.441]\n",
    "\n",
    "gb_ProWRAS_f1 = [0.385,0.335,0.959,0.863,0.320,0.803,0.998,0.995,0.969,1.0,0.156,0.335,0.735,0.514,0.329,0.225,0.600]\n",
    "gb_ProWRAS_k = [0.341,0.310,0.957,0.857,0.291,0.794,0.998,0.995,0.967,1.0,0.115,0.303,0.726,0.501,0.303,0.328,0.589]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "6121f46b",
   "metadata": {},
   "outputs": [],
   "source": [
    "statistic = { }"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e825147c",
   "metadata": {},
   "source": [
    "statistic = { \"ProWRAS\": {} }\n",
    "for (n, f1, k) in zip(dataset, lr_ProWRAS_f1, lr_ProWRAS_k):\n",
    "    if n in ignoreSet:\n",
    "        continue\n",
    "    \n",
    "    if n not in statistic[\"ProWRAS\"]:\n",
    "        statistic[\"ProWRAS\"][n] = {}\n",
    "    \n",
    "    statistic[\"ProWRAS\"][n][\"LR\"] = { kScore: k, f1Score: f1 }\n",
    "\n",
    "for (n, f1, k) in zip(dataset, gb_ProWRAS_f1, gb_ProWRAS_k):\n",
    "    if n in ignoreSet:\n",
    "        continue\n",
    "    \n",
    "    if n not in statistic[\"ProWRAS\"]:\n",
    "        statistic[\"ProWRAS\"][n] = {}\n",
    "    \n",
    "    statistic[\"ProWRAS\"][n][\"GB\"] = { kScore: k, f1Score: f1 }\n",
    "\n",
    "    \n",
    "for (n, f1, k) in zip(dataset, knn_ProWRAS_f1, knn_ProWRAS_k):\n",
    "    if n in ignoreSet:\n",
    "        continue\n",
    "    \n",
    "    if n not in statistic[\"ProWRAS\"]:\n",
    "        statistic[\"ProWRAS\"][n] = {}\n",
    "    \n",
    "    statistic[\"ProWRAS\"][n][\"KNN\"] = { kScore: k, f1Score: f1 }\n",
    "    \n",
    "dataset = list(filter(lambda n: n not in ignoreSet, dataset))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "selective-connecticut",
   "metadata": {},
   "source": [
    "# Load data from CSV files"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "a23177bd",
   "metadata": {},
   "outputs": [],
   "source": [
    "def cleanupName(name):\n",
    "    return name.replace(\"folding_\", \"\").replace(\"imblearn_\", \"\").replace(\"kaggle_\", \"\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "304d69ce",
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset = [cleanupName(d) for d in testSets]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "intended-watts",
   "metadata": {},
   "outputs": [],
   "source": [
    "def loadDiagnoseData(ganType, datasetName):\n",
    "    fileName = f\"data_result/{ganType}/{datasetName}.csv\"\n",
    "    r = {}\n",
    "    try:\n",
    "        with open(fileName) as f:\n",
    "            newBlock = True\n",
    "            n = \"\"\n",
    "            for line in f:\n",
    "                line = line.strip()\n",
    "                if newBlock:\n",
    "                    n = line\n",
    "                    if n == \"GAN\":\n",
    "                        n = \"DoG\"\n",
    "                    newBlock = False\n",
    "                elif line == \"---\":\n",
    "                    newBlock = True\n",
    "                else:\n",
    "                    parts = line.split(\";\")\n",
    "                    if parts[0] == \"avg\":\n",
    "                        r[n] = { f1Score: float(parts[5]), kScore: float(parts[6]) }\n",
    "    except FileNotFoundError as e:\n",
    "        print(f\"Missing file: {fileName}\")\n",
    "    return r"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "classical-rescue",
   "metadata": {},
   "outputs": [],
   "source": [
    "for gan in gans:\n",
    "    if gan not in statistic:\n",
    "        statistic[gan] = {}\n",
    "    \n",
    "    for ds in testSets:\n",
    "        if ds != \"Average\":\n",
    "            statistic[gan][cleanupName(ds)] = loadDiagnoseData(gan, ds)\n",
    "            \n",
    "            d = cleanupName(ds)\n",
    "            if d not in dataset:\n",
    "                dataset.append(d)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "unable-entrance",
   "metadata": {},
   "outputs": [],
   "source": [
    "for gan in statistic.keys():\n",
    "    f1 = { n: 0.0 for n in algs }\n",
    "    k =  { n: 0.0 for n in algs }\n",
    "    c = 0\n",
    "\n",
    "    for ds in dataset:\n",
    "        if ds != \"Average\":\n",
    "            c += 1\n",
    "            for n in algs:\n",
    "                if n in statistic[gan][ds].keys():\n",
    "                    f1[n] += statistic[gan][ds][n][f1Score]\n",
    "                    k[n] += statistic[gan][ds][n][kScore]\n",
    "\n",
    "    avg = {}\n",
    "    for n in algs:\n",
    "        avg[n] = { f1Score: f1[n] / c, kScore: k[n] / c }\n",
    "    statistic[gan][\"Average\"] = avg"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "20ba8039",
   "metadata": {},
   "source": [
    "convGanMax = {}\n",
    "for g in gans:\n",
    "    if g[0:7] == \"convGAN\":\n",
    "        for d in statistic[g].keys():\n",
    "            if d not in convGanMax.keys():\n",
    "                convGanMax[d] = {}\n",
    "            for a in statistic[g][d].keys():\n",
    "                if a not in convGanMax[d].keys():\n",
    "                    convGanMax[d][a] = {}\n",
    "                for s in statistic[g][d][a].keys():\n",
    "                    x = statistic[g][d][a][s]\n",
    "                    if x is None:\n",
    "                        x = 0.0\n",
    "                    if s not in convGanMax[d][a].keys():\n",
    "                        convGanMax[d][a][s] = x\n",
    "                    else:\n",
    "                        convGanMax[d][a][s] = max(x, convGanMax[d][a][s])\n",
    "\n",
    "gs = []\n",
    "for g in list(gans):\n",
    "    if g[0:7] == \"convGAN\":\n",
    "        del statistic[g]\n",
    "    else:\n",
    "        gs.append(g)\n",
    "\n",
    "statistic[\"convGAN\"] = convGanMax\n",
    "gs.append(\"convGAN\")\n",
    "gans = gs"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "public-collins",
   "metadata": {},
   "source": [
    "# Show Statistics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "extra-taiwan",
   "metadata": {},
   "outputs": [],
   "source": [
    "def mix(v, a, b):\n",
    "    return max(0, min(255, int((v * a) + ((1.0 - v) * b))))\n",
    "\n",
    "def mixPixel(v, a, b):\n",
    "    return (mix(v, a[0], b[0]), mix(v, a[1], b[1]), mix(v, a[2], b[2]))\n",
    "    \n",
    "\n",
    "def drawTransparentRect(img, rect, color, opacity=1.0):\n",
    "    ((x0, y0), (x1, y1)) = rect\n",
    "    \n",
    "    for y in range(y0, y1):\n",
    "        for x in range(x0, x1):\n",
    "            p = (x, y)\n",
    "            c = mixPixel(opacity, color, img.getpixel(p))\n",
    "            img.putpixel(p, c)\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "5fec8e83",
   "metadata": {},
   "outputs": [],
   "source": [
    "def drawDiagram(size, rowNames, data, colNames=[], colors=None, border=20, barIndent=10, fontSize=20, markers=[0.25, 0.5, 0.75, 1.00]):\n",
    "    silver = (204, 204, 204)\n",
    "    black = (0,0,0)\n",
    "    white = (255, 255, 255)\n",
    "    \n",
    "    defaultColors = [ (31,119,180)\n",
    "                    , (255,127,14)\n",
    "                    , (44,160,44)\n",
    "                    , (214,40,40)\n",
    "                    , (148,103,189)\n",
    "                    , (140,86,75)\n",
    "                    , (227,119,194)\n",
    "                    , (127,127,127)\n",
    "                    , (40,40,214)\n",
    "                    ]\n",
    "    \n",
    "    \n",
    "    if colors is None:\n",
    "        colors = defaultColors\n",
    "\n",
    "    print((len(data[0]), len(colNames), len(data), len(rowNames)))\n",
    "\n",
    "    font = ImageFont.truetype(\"FreeSans\", fontSize)\n",
    "    \n",
    "    markerSize = 0\n",
    "    for m in markers:\n",
    "        markerSize = max(markerSize, font.getsize(f\"{m:0.2f}\")[0])\n",
    "\n",
    "    areaTop = 2 * border + markerSize\n",
    "\n",
    "    barStep = (size[0] - border - areaTop) // len(data)\n",
    "    barSize = max(border, barStep - border)\n",
    "    barIndent = min(barIndent, barSize / (1 + len(data[0])))\n",
    "    barIndent = barSize / (2 + len(data[0]))\n",
    "    \n",
    "    print((size[0], barSize, barSize * len(data)))\n",
    "    \n",
    "    # Create new Image\n",
    "    w = max(size[0], size[1])\n",
    "    img = Image.new(\"RGB\", (w,w))\n",
    "    d = ImageDraw.Draw(img)\n",
    "    \n",
    "    # Set background to white.\n",
    "    d.rectangle(((0,0), (w,w)), fill=white)\n",
    "    \n",
    "    # draw row names\n",
    "    height = size[1]\n",
    "    left = w - height\n",
    "    textSize = 0\n",
    "    for (n, name) in enumerate(rowNames):\n",
    "        s = font.getsize(name)\n",
    "        offset = int(border + barSize - s[1] + 1.5) // 2\n",
    "        textSize = max(textSize, s[0])\n",
    "        pos = (left + border, areaTop + offset + (barStep * n))\n",
    "        d.text(pos, name, fill=black, font=font)\n",
    "        \n",
    "        \n",
    "    # Calculate sizes for bar drawing.\n",
    "    barLength = height - (4 * border) - textSize\n",
    "    areaSize = (barLength, barSize)\n",
    "    areaLeft = left + (2 * border) + textSize\n",
    "    \n",
    "    # Draw Lines for bar height comparing.\n",
    "    markerPos = [areaLeft + int(v * barLength) for v in markers]\n",
    "    for p in markerPos:\n",
    "        d.line(((p, border), (p, size[0] - border)), fill=silver)\n",
    "        \n",
    "    # Draw bars.\n",
    "    for (n, row) in enumerate(data):\n",
    "        area = ((areaLeft, areaTop + (n * barStep) + (border // 2)), areaSize)\n",
    "\n",
    "        indices = list(range(len(row)))\n",
    "        indices.sort(key= lambda i: 1.0 - row[i])\n",
    "\n",
    "        for (n, i) in enumerate(indices):\n",
    "            v = row[i]\n",
    "            c = colors[i]\n",
    "            offset = barIndent * n\n",
    "            tl = (area[0][0], area[0][1] + offset)\n",
    "            br = (tl[0] + int(v * area[1][0]), area[1][1] + tl[1] - offset)\n",
    "            rect = (tl, br)\n",
    "            d.rectangle(rect, fill=c, outline=black)\n",
    "\n",
    "\n",
    "    # Draw axis.\n",
    "    d.line(((areaLeft, areaTop), (areaLeft, size[0] - border)), fill=black)\n",
    "    d.line(((areaLeft, areaTop), (w - border, areaTop)), fill=black)\n",
    "    \n",
    "    # Draw y-axis text.\n",
    "    img = img.rotate(90)\n",
    "    d = ImageDraw.Draw(img)\n",
    "\n",
    "    for (m, p) in zip(markers, markerPos):\n",
    "        d.text((border, size[1] - (p - left)), f\"{m:0.2f}\", fill=black, font=font)\n",
    "    \n",
    "    # Draw legend.\n",
    "    if len(colNames) > 0:\n",
    "        colNameWidth = 0\n",
    "        colNameHeight = fontSize * len(colNames)\n",
    "        for c in colNames:\n",
    "            colNameWidth = max(colNameWidth, font.getsize(c)[0])\n",
    "        \n",
    "        rWidth = int(fontSize * 0.75)\n",
    "        rHeight = fontSize // 2\n",
    "        rPadd = (fontSize - rHeight) // 2\n",
    "        \n",
    "        tl = (size[0] - (int(2.5 * border) + colNameWidth + rWidth), 0)\n",
    "        br = (size[0], int(1.2 * border) + colNameHeight)\n",
    "        drawTransparentRect(img, (tl, br), white, 0.75)\n",
    "\n",
    "        for (n, c) in enumerate(colNames):\n",
    "            t = border + (fontSize * n)\n",
    "            l = size[0] - border - colNameWidth\n",
    "            d.rectangle(((l - border - rWidth, t + rPadd - 1), (l - border, t + rPadd + rHeight)), fill=colors[n], outline=black)\n",
    "            d.text((l, t), c, fill=black, font=font)\n",
    "    \n",
    "    return img.crop((0, 0, size[0], size[1]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "038344f7",
   "metadata": {},
   "outputs": [],
   "source": [
    "def showDiagnose(algo, score):\n",
    "    def valueOf(d, g):\n",
    "        d = cleanupName(d)\n",
    "        if d not in statistic[g].keys():\n",
    "            print(f\"Missing '{d}' in '{g}'\")\n",
    "            return 0.0\n",
    "        \n",
    "        if algo in statistic[g][d].keys():\n",
    "            return statistic[g][d][algo][score]\n",
    "        else:\n",
    "            print(f\"Missing '{algo}' in ('{g}', '{d}')\")\n",
    "            return 0.0\n",
    "    \n",
    "    print(f\"{algo}: {score}\")\n",
    "    \n",
    "    data = [[valueOf(d, g) for g in gans] for d in testSets]        \n",
    "    img = drawDiagram((1024, 1024), [cleanupName(d) for d in testSets], data, colNames=gans)\n",
    "    img.save(f\"data_result/statistics/byAlgorithm/statistic-{algo}-{score}.png\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "8904b4b3",
   "metadata": {},
   "outputs": [],
   "source": [
    "def showDiagnoseAverage(score, onlyOneBar=False):\n",
    "    def valueOf(g, algo):\n",
    "        if algo in statistic[g][\"Average\"].keys():\n",
    "            return statistic[g][\"Average\"][algo][score] \n",
    "        else:\n",
    "            return 0.0\n",
    "\n",
    "    print(f\"Average: {score}\")\n",
    "    \n",
    "    data = [[valueOf(g, algo) for g in gans] for algo in algs]\n",
    "    img = drawDiagram((1024, 1024), algs, data, colNames=gans)\n",
    "    img.save(f\"data_result/statistics/average/statistic-Algo-Average-{score}.png\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "d1f4961a",
   "metadata": {},
   "outputs": [],
   "source": [
    "def showDiagnoseDataset(dataset):\n",
    "    print(f\"{dataset}\")\n",
    "    \n",
    "    def valueOf(algo, score, g):\n",
    "        if dataset in statistic[g]:\n",
    "            if algo in statistic[g][dataset]:\n",
    "                if score in statistic[g][dataset][algo]:\n",
    "                    return statistic[g][dataset][algo][score]\n",
    "        return 0.0\n",
    "    \n",
    "    scores = [f1Score, kScore]\n",
    "    \n",
    "    for score in scores:\n",
    "        data = [[valueOf(algo, score, g) for algo in algs] for g in gans]\n",
    "        img = drawDiagram((1024, 1024), gans, data, colNames=algs)\n",
    "        img.save(f\"data_result/statistics/byDataset/statistic-Classifier-{dataset}-{score}.png\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "57fe8925",
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "LR: f1 score\n",
      "(6, 6, 14, 14)\n",
      "(1024, 46, 644)\n",
      "LR: cohens kappa score\n",
      "(6, 6, 14, 14)\n",
      "(1024, 46, 644)\n",
      "RF: f1 score\n",
      "(6, 6, 14, 14)\n",
      "(1024, 46, 644)\n",
      "RF: cohens kappa score\n",
      "(6, 6, 14, 14)\n",
      "(1024, 46, 644)\n",
      "GB: f1 score\n",
      "(6, 6, 14, 14)\n",
      "(1024, 46, 644)\n",
      "GB: cohens kappa score\n",
      "(6, 6, 14, 14)\n",
      "(1024, 46, 644)\n",
      "KNN: f1 score\n",
      "(6, 6, 14, 14)\n",
      "(1024, 46, 644)\n",
      "KNN: cohens kappa score\n",
      "(6, 6, 14, 14)\n",
      "(1024, 46, 644)\n",
      "DoG: f1 score\n",
      "Missing 'DoG' in ('Repeater', 'abalone_17_vs_7_8_9_10')\n",
      "Missing 'DoG' in ('ProWRAS', 'abalone_17_vs_7_8_9_10')\n",
      "Missing 'DoG' in ('GAN', 'abalone_17_vs_7_8_9_10')\n",
      "Missing 'DoG' in ('ctGAN', 'abalone_17_vs_7_8_9_10')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'abalone_17_vs_7_8_9_10')\n",
      "Missing 'DoG' in ('Repeater', 'abalone9-18')\n",
      "Missing 'DoG' in ('ProWRAS', 'abalone9-18')\n",
      "Missing 'DoG' in ('GAN', 'abalone9-18')\n",
      "Missing 'DoG' in ('ctGAN', 'abalone9-18')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'abalone9-18')\n",
      "Missing 'DoG' in ('Repeater', 'car_good')\n",
      "Missing 'DoG' in ('ProWRAS', 'car_good')\n",
      "Missing 'DoG' in ('GAN', 'car_good')\n",
      "Missing 'DoG' in ('ctGAN', 'car_good')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'car_good')\n",
      "Missing 'DoG' in ('Repeater', 'car-vgood')\n",
      "Missing 'DoG' in ('ProWRAS', 'car-vgood')\n",
      "Missing 'DoG' in ('GAN', 'car-vgood')\n",
      "Missing 'DoG' in ('ctGAN', 'car-vgood')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'car-vgood')\n",
      "Missing 'DoG' in ('Repeater', 'flare-F')\n",
      "Missing 'DoG' in ('ProWRAS', 'flare-F')\n",
      "Missing 'DoG' in ('GAN', 'flare-F')\n",
      "Missing 'DoG' in ('ctGAN', 'flare-F')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'flare-F')\n",
      "Missing 'DoG' in ('Repeater', 'hypothyroid')\n",
      "Missing 'DoG' in ('ProWRAS', 'hypothyroid')\n",
      "Missing 'DoG' in ('GAN', 'hypothyroid')\n",
      "Missing 'DoG' in ('ctGAN', 'hypothyroid')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'hypothyroid')\n",
      "Missing 'DoG' in ('Repeater', 'kddcup-guess_passwd_vs_satan')\n",
      "Missing 'DoG' in ('ProWRAS', 'kddcup-guess_passwd_vs_satan')\n",
      "Missing 'DoG' in ('GAN', 'kddcup-guess_passwd_vs_satan')\n",
      "Missing 'DoG' in ('ctGAN', 'kddcup-guess_passwd_vs_satan')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'kddcup-guess_passwd_vs_satan')\n",
      "Missing 'DoG' in ('Repeater', 'kr-vs-k-three_vs_eleven')\n",
      "Missing 'DoG' in ('ProWRAS', 'kr-vs-k-three_vs_eleven')\n",
      "Missing 'DoG' in ('GAN', 'kr-vs-k-three_vs_eleven')\n",
      "Missing 'DoG' in ('ctGAN', 'kr-vs-k-three_vs_eleven')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'kr-vs-k-three_vs_eleven')\n",
      "Missing 'DoG' in ('Repeater', 'kr-vs-k-zero-one_vs_draw')\n",
      "Missing 'DoG' in ('ProWRAS', 'kr-vs-k-zero-one_vs_draw')\n",
      "Missing 'DoG' in ('GAN', 'kr-vs-k-zero-one_vs_draw')\n",
      "Missing 'DoG' in ('ctGAN', 'kr-vs-k-zero-one_vs_draw')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'kr-vs-k-zero-one_vs_draw')\n",
      "Missing 'DoG' in ('Repeater', 'shuttle-2_vs_5')\n",
      "Missing 'DoG' in ('ProWRAS', 'shuttle-2_vs_5')\n",
      "Missing 'DoG' in ('GAN', 'shuttle-2_vs_5')\n",
      "Missing 'DoG' in ('ctGAN', 'shuttle-2_vs_5')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'shuttle-2_vs_5')\n",
      "Missing 'DoG' in ('Repeater', 'winequality-red-4')\n",
      "Missing 'DoG' in ('ProWRAS', 'winequality-red-4')\n",
      "Missing 'DoG' in ('GAN', 'winequality-red-4')\n",
      "Missing 'DoG' in ('ctGAN', 'winequality-red-4')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'winequality-red-4')\n",
      "Missing 'DoG' in ('Repeater', 'yeast4')\n",
      "Missing 'DoG' in ('ProWRAS', 'yeast4')\n",
      "Missing 'DoG' in ('GAN', 'yeast4')\n",
      "Missing 'DoG' in ('ctGAN', 'yeast4')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'yeast4')\n",
      "Missing 'DoG' in ('Repeater', 'yeast5')\n",
      "Missing 'DoG' in ('ProWRAS', 'yeast5')\n",
      "Missing 'DoG' in ('GAN', 'yeast5')\n",
      "Missing 'DoG' in ('ctGAN', 'yeast5')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'yeast5')\n",
      "Missing 'DoG' in ('Repeater', 'yeast6')\n",
      "Missing 'DoG' in ('ProWRAS', 'yeast6')\n",
      "Missing 'DoG' in ('GAN', 'yeast6')\n",
      "Missing 'DoG' in ('ctGAN', 'yeast6')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'yeast6')\n",
      "(6, 6, 14, 14)\n",
      "(1024, 46, 644)\n",
      "DoG: cohens kappa score\n",
      "Missing 'DoG' in ('Repeater', 'abalone_17_vs_7_8_9_10')\n",
      "Missing 'DoG' in ('ProWRAS', 'abalone_17_vs_7_8_9_10')\n",
      "Missing 'DoG' in ('GAN', 'abalone_17_vs_7_8_9_10')\n",
      "Missing 'DoG' in ('ctGAN', 'abalone_17_vs_7_8_9_10')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'abalone_17_vs_7_8_9_10')\n",
      "Missing 'DoG' in ('Repeater', 'abalone9-18')\n",
      "Missing 'DoG' in ('ProWRAS', 'abalone9-18')\n",
      "Missing 'DoG' in ('GAN', 'abalone9-18')\n",
      "Missing 'DoG' in ('ctGAN', 'abalone9-18')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'abalone9-18')\n",
      "Missing 'DoG' in ('Repeater', 'car_good')\n",
      "Missing 'DoG' in ('ProWRAS', 'car_good')\n",
      "Missing 'DoG' in ('GAN', 'car_good')\n",
      "Missing 'DoG' in ('ctGAN', 'car_good')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'car_good')\n",
      "Missing 'DoG' in ('Repeater', 'car-vgood')\n",
      "Missing 'DoG' in ('ProWRAS', 'car-vgood')\n",
      "Missing 'DoG' in ('GAN', 'car-vgood')\n",
      "Missing 'DoG' in ('ctGAN', 'car-vgood')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'car-vgood')\n",
      "Missing 'DoG' in ('Repeater', 'flare-F')\n",
      "Missing 'DoG' in ('ProWRAS', 'flare-F')\n",
      "Missing 'DoG' in ('GAN', 'flare-F')\n",
      "Missing 'DoG' in ('ctGAN', 'flare-F')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'flare-F')\n",
      "Missing 'DoG' in ('Repeater', 'hypothyroid')\n",
      "Missing 'DoG' in ('ProWRAS', 'hypothyroid')\n",
      "Missing 'DoG' in ('GAN', 'hypothyroid')\n",
      "Missing 'DoG' in ('ctGAN', 'hypothyroid')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'hypothyroid')\n",
      "Missing 'DoG' in ('Repeater', 'kddcup-guess_passwd_vs_satan')\n",
      "Missing 'DoG' in ('ProWRAS', 'kddcup-guess_passwd_vs_satan')\n",
      "Missing 'DoG' in ('GAN', 'kddcup-guess_passwd_vs_satan')\n",
      "Missing 'DoG' in ('ctGAN', 'kddcup-guess_passwd_vs_satan')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'kddcup-guess_passwd_vs_satan')\n",
      "Missing 'DoG' in ('Repeater', 'kr-vs-k-three_vs_eleven')\n",
      "Missing 'DoG' in ('ProWRAS', 'kr-vs-k-three_vs_eleven')\n",
      "Missing 'DoG' in ('GAN', 'kr-vs-k-three_vs_eleven')\n",
      "Missing 'DoG' in ('ctGAN', 'kr-vs-k-three_vs_eleven')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'kr-vs-k-three_vs_eleven')\n",
      "Missing 'DoG' in ('Repeater', 'kr-vs-k-zero-one_vs_draw')\n",
      "Missing 'DoG' in ('ProWRAS', 'kr-vs-k-zero-one_vs_draw')\n",
      "Missing 'DoG' in ('GAN', 'kr-vs-k-zero-one_vs_draw')\n",
      "Missing 'DoG' in ('ctGAN', 'kr-vs-k-zero-one_vs_draw')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'kr-vs-k-zero-one_vs_draw')\n",
      "Missing 'DoG' in ('Repeater', 'shuttle-2_vs_5')\n",
      "Missing 'DoG' in ('ProWRAS', 'shuttle-2_vs_5')\n",
      "Missing 'DoG' in ('GAN', 'shuttle-2_vs_5')\n",
      "Missing 'DoG' in ('ctGAN', 'shuttle-2_vs_5')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'shuttle-2_vs_5')\n",
      "Missing 'DoG' in ('Repeater', 'winequality-red-4')\n",
      "Missing 'DoG' in ('ProWRAS', 'winequality-red-4')\n",
      "Missing 'DoG' in ('GAN', 'winequality-red-4')\n",
      "Missing 'DoG' in ('ctGAN', 'winequality-red-4')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'winequality-red-4')\n",
      "Missing 'DoG' in ('Repeater', 'yeast4')\n",
      "Missing 'DoG' in ('ProWRAS', 'yeast4')\n",
      "Missing 'DoG' in ('GAN', 'yeast4')\n",
      "Missing 'DoG' in ('ctGAN', 'yeast4')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'yeast4')\n",
      "Missing 'DoG' in ('Repeater', 'yeast5')\n",
      "Missing 'DoG' in ('ProWRAS', 'yeast5')\n",
      "Missing 'DoG' in ('GAN', 'yeast5')\n",
      "Missing 'DoG' in ('ctGAN', 'yeast5')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'yeast5')\n",
      "Missing 'DoG' in ('Repeater', 'yeast6')\n",
      "Missing 'DoG' in ('ProWRAS', 'yeast6')\n",
      "Missing 'DoG' in ('GAN', 'yeast6')\n",
      "Missing 'DoG' in ('ctGAN', 'yeast6')\n",
      "Missing 'DoG' in ('CTAB-GAN', 'yeast6')\n",
      "(6, 6, 14, 14)\n",
      "(1024, 46, 644)\n",
      "Average: f1 score\n",
      "(6, 6, 5, 5)\n",
      "(1024, 165, 825)\n",
      "Average: cohens kappa score\n",
      "(6, 6, 5, 5)\n",
      "(1024, 165, 825)\n",
      "abalone_17_vs_7_8_9_10\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "abalone9-18\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "car_good\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "car-vgood\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "flare-F\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "hypothyroid\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "kddcup-guess_passwd_vs_satan\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "kr-vs-k-three_vs_eleven\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "kr-vs-k-zero-one_vs_draw\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "shuttle-2_vs_5\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "winequality-red-4\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "yeast4\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "yeast5\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "yeast6\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "Average\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n",
      "(5, 5, 6, 6)\n",
      "(1024, 134, 804)\n"
     ]
    }
   ],
   "source": [
    "gans = [g for g in statistic.keys() if not g.startswith(\"convGAN\") or g == \"convGAN-majority-full\"]\n",
    "\n",
    "for a in algs:\n",
    "    showDiagnose(a, f1Score)\n",
    "    showDiagnose(a, kScore)\n",
    "    \n",
    "showDiagnoseAverage(f1Score)\n",
    "showDiagnoseAverage(kScore)\n",
    "\n",
    "for t in testSets:\n",
    "    showDiagnoseDataset(cleanupName(t))\n",
    "\n",
    "showDiagnoseDataset(\"Average\")\n",
    "\n",
    "gans = list(statistic.keys())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "63841c55",
   "metadata": {},
   "outputs": [],
   "source": [
    "def getValueOf(gan, dataset, algo, score):\n",
    "    if dataset not in statistic[gan].keys():\n",
    "        #print(f\"Missing '{dataset}' in '{gan}'\")\n",
    "        return None\n",
    "\n",
    "    if algo not in statistic[gan][dataset].keys():\n",
    "        #print(f\"Missing '{algo}' in ('{gan}', '{dataset}')\")\n",
    "        return None\n",
    "    \n",
    "    if score not in statistic[gan][dataset][algo].keys():\n",
    "        #print(f\"Missing '{score}' in ('{gan}', '{dataset}', '{algo}')\")\n",
    "        return None\n",
    "    \n",
    "    return statistic[gan][dataset][algo][score]\n",
    "    \n",
    "    \n",
    "    \n",
    "def calcTable(algo, score, ignore=[]):\n",
    "    table = []\n",
    "    \n",
    "    def calc(gc, g):\n",
    "        n = 0\n",
    "        for d in testSets:\n",
    "            d = cleanupName(d)\n",
    "            if d not in ignore:\n",
    "                vc = getValueOf(gc, d, algo, score)\n",
    "                v = getValueOf(g, d, algo, score)\n",
    "                if vc is not None and v is not None and vc >= v:\n",
    "                    n += 1\n",
    "        return n\n",
    "    \n",
    "    for gc in gans:\n",
    "        table.append([calc(gc, g) for g in gans])\n",
    "    return table"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "177774b0",
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[[14, 3, 6, 10, 5, 2, 2, 2, 1],\n",
       " [11, 14, 8, 11, 7, 11, 5, 12, 3],\n",
       " [9, 7, 14, 12, 8, 8, 3, 9, 4],\n",
       " [4, 3, 2, 14, 3, 3, 2, 3, 2],\n",
       " [10, 7, 7, 11, 14, 9, 5, 9, 5],\n",
       " [12, 3, 6, 11, 6, 14, 0, 9, 1],\n",
       " [12, 11, 11, 13, 9, 14, 14, 14, 10],\n",
       " [12, 2, 5, 11, 5, 6, 0, 14, 0],\n",
       " [13, 11, 10, 13, 9, 13, 4, 14, 14]]"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tables = {}\n",
    "ignore = [# \"webpage\"\n",
    "         #, \"mammography\"\n",
    "         #, \"protein_homo\"\n",
    "         #, \"ozone_level\"\n",
    "         #, \"creditcard\"\n",
    "         ]\n",
    "for a in algs:\n",
    "    tables[a + \" - \" + f1Score] = calcTable(a, f1Score, ignore)\n",
    "    tables[a + \" - \" + kScore] = calcTable(a, kScore, ignore)\n",
    "    \n",
    "tables[algs[0] + \" - \" + f1Score]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "453f491d",
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "LR - f1 score\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x432 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "LR - cohens kappa score\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x432 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "RF - f1 score\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x432 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "RF - cohens kappa score\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x432 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "GB - f1 score\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x432 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "GB - cohens kappa score\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x432 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "KNN - f1 score\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x432 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "KNN - cohens kappa score\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x432 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "DoG - f1 score\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 360x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "DoG - cohens kappa score\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 360x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "cmap = matplotlib.colors.ListedColormap([\n",
    "    (1.0, x / 255.0, 0.0)\n",
    "    for x in range(256)\n",
    "    ] + [\n",
    "    ((255 - x) / 255.0, (255 - x) / 255.0, x / 255.0)\n",
    "    for x in range(256)\n",
    "    ])\n",
    "\n",
    "#cmap.set_extremes(bad=cmap(0.0), under=cmap(0.0), over=cmap(1.0))\n",
    "\n",
    "for k in tables.keys():\n",
    "    print(k)\n",
    "    labels = list(gans)\n",
    "    t = tables[k]\n",
    "    if k[0:3] == \"DoG\":\n",
    "        #continue\n",
    "        labels = labels[-4:]\n",
    "        t = [r[-4:] for r in t[-4:]]\n",
    "        f = plt.figure(figsize=(5, 4))\n",
    "        f.add_axes([0.4, 0.45, 0.6, 0.5])\n",
    "    else:\n",
    "        f = plt.figure(figsize=(7, 6))\n",
    "        f.add_axes([0.27, 0.25, 0.7, 0.74])\n",
    "    p = plt.imshow(t, cmap=cmap)\n",
    "    plt.colorbar(p)\n",
    "    plt.xticks(range(len(labels)), labels, rotation=\"vertical\")\n",
    "    plt.yticks(range(len(labels)), labels)\n",
    "    plt.savefig(f\"data_result/statistics/successCount/statistic-{k}.pdf\")\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "e4397945",
   "metadata": {},
   "outputs": [],
   "source": [
    "class Table:\n",
    "    def __init__(self, heading):\n",
    "        self.heading = [str(h) for h in heading]\n",
    "        self.sizes = [len(h) for h in self.heading]\n",
    "        self.rows = []\n",
    "        \n",
    "    def add(self, row):\n",
    "        row = [str(r) for r in row]\n",
    "        self.rows.append(row)\n",
    "        self.sizes = [max(a,len(b)) for (a, b) in zip(self.sizes, row)]\n",
    "        \n",
    "    def separator(self):\n",
    "        return \"|\".join([\"-\" * n for n in self.sizes])\n",
    "    \n",
    "    def showRow(self, row):\n",
    "        def pad(n, t):\n",
    "            while len(t) < n:\n",
    "                t += \" \"\n",
    "            return t\n",
    "        \n",
    "        return \"|\".join([pad(n, t) for (n,t) in zip(self.sizes, row)])\n",
    "    \n",
    "    def show(self):\n",
    "        print(self.showRow(self.heading))\n",
    "        print(self.separator())\n",
    "        for row in self.rows:\n",
    "            print(self.showRow(row))\n",
    "            \n",
    "    def showLatex(self, caption, key):\n",
    "        \n",
    "        columnConfig = \"|\".join([\"l\"] + [\"@{\\\\hskip3pt}c@{\\\\hskip3pt}\" for h in self.heading[1:]])\n",
    "\n",
    "        text = \"\\\\begin{table*}[ht]\\\\scriptsize\"\n",
    "        text += \"\\\\caption{\" + caption + \"}\\\\label{\" + key + \"}\"\n",
    "        text += \"\\\\centering\\\\tabularnewline\\n\"\n",
    "\n",
    "        text += \"\\\\begin{tabular}{\" + columnConfig + \"}\\\\hline\\n\"\n",
    "        text += \" & \".join([\"\\\\textbf{\" + h + \"}\" for h in self.heading])\n",
    "        text += \"\\n\\\\tabularnewline\\n\\\\hline\\n\"\n",
    "        \n",
    "        for row in self.rows:\n",
    "            text += \" & \".join(row)\n",
    "            text += \"\\n\\\\tabularnewline\\n\"\n",
    "            \n",
    "        text += \"\\hline\\end{tabular}\\end{table*}\\n\"\n",
    "        \n",
    "        return text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "d0e2faa0",
   "metadata": {},
   "outputs": [],
   "source": [
    "def tableRow(algo, dataset, myGans):\n",
    "    row = []\n",
    "    for gan in myGans:\n",
    "        v = getValueOf(gan, dataset, algo, f1Score)\n",
    "        w = getValueOf(gan, dataset, algo, kScore)\n",
    "        row.append((v, w))\n",
    "    return row"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "8c820b02",
   "metadata": {
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "def p(f, bold=False):\n",
    "    if f is None:\n",
    "        text = \"?\"\n",
    "    else:\n",
    "        text = f\"{f:0.3f}\"\n",
    "        \n",
    "    if bold:\n",
    "        return \" \\\\textbf{\" + text + \"} \"\n",
    "    else:\n",
    "        return \" \" + text + \" \"\n",
    "\n",
    "def latex(text):\n",
    "    r = \"\"\n",
    "    for x in text:\n",
    "        if x == \"_\" or x == \"-\":\n",
    "            r += \" \"\n",
    "        else:\n",
    "            r += x\n",
    "    return r\n",
    "\n",
    "def pairMax(row):\n",
    "    a = 0.0\n",
    "    b = 0.0\n",
    "    \n",
    "    for (x,y) in row:\n",
    "        a = max(a, x)\n",
    "        b = max(b, y)\n",
    "    \n",
    "    return (a, b)\n",
    "    \n",
    "with open(\"data_result/statistics/Tables.tex\", \"w\") as latexFile:\n",
    "    for algo in algs:\n",
    "        latexFile.write(\"\\n\")\n",
    "        latexFile.write(\"% ### \" + algo + \"\\n\")\n",
    "        latexFile.write(\"\\n\")\n",
    "        f = \"\"\n",
    "        heading = [\"dataset ($f_1~$score$~/~\\\\kappa~$score)\"]\n",
    "        \n",
    "        myGans = gans\n",
    "        if algo[0:3] == \"DoG\":\n",
    "            myGans = list(gans)[-4:]\n",
    "\n",
    "        for g in myGans:\n",
    "            heading.append(latex(g))\n",
    "        table = Table(heading)\n",
    "        \n",
    "        avg = [[0.0, 0.0] for h in heading[1:]]\n",
    "        mx  = [[0.0, 0.0] for h in heading[1:]]\n",
    "        cnt = 0\n",
    "\n",
    "        for d in testSets:\n",
    "            d = cleanupName(d)\n",
    "            if d not in ignore:\n",
    "                cnt += 1\n",
    "                row = tableRow(algo, d, myGans)\n",
    "                line = [latex(d)]\n",
    "\n",
    "                m = pairMax(row)\n",
    "\n",
    "                for (n, r) in enumerate(row):\n",
    "                    line.append(f\"{p(r[0], r[0] == m[0])} / {p(r[1], r[1] == m[1])}\")\n",
    "                    avg[n][0] += r[0] or 0.0\n",
    "                    avg[n][1] += r[1] or 0.0\n",
    "                    mx[n][0] = max(mx[n][0], r[0] or 0.0)\n",
    "                    mx[n][1] = max(mx[n][1], r[1] or 0.0)\n",
    "                table.add(line)\n",
    "\n",
    "        m = pairMax(avg)\n",
    "        table.add([\"\\\\hline Average\"] + [f\"{p(a / cnt, a == m[0])} / {p(b / cnt, b == m[1])}\" for (a,b) in avg])\n",
    "        #table.add([\"maximum\"] + [f\"{p(a)} / {p(b)}\" for (a,b) in mx])\n",
    "\n",
    "        tableB = None\n",
    "        if len(table.heading) > 5:\n",
    "            heading = [table.heading[0]] + table.heading[6:]\n",
    "            tableB = Table(heading)\n",
    "            tableB.sizes = [table.sizes[0]] + table.sizes[6:]\n",
    "            tableB.rows = [\n",
    "                [r[0]] + r[6:]\n",
    "                for r in table.rows\n",
    "                ]\n",
    "            table.heading = table.heading[0:6]\n",
    "            table.sizes = table.sizes[0:6]\n",
    "            table.rows = [\n",
    "                r[0:6]\n",
    "                for r in table.rows\n",
    "                ]\n",
    "\n",
    "        if tableB is not None:\n",
    "            latexFile.write(table.showLatex(algo + \" (1)\", \"tab:results:\" + algo + \":A\") + \"\\n\")\n",
    "            latexFile.write(\"\\n\")\n",
    "            latexFile.write(tableB.showLatex(algo + \" (2)\", \"tab:results:\" + algo + \":B\") + \"\\n\")\n",
    "        else:\n",
    "            latexFile.write(table.showLatex(algo, \"tab:results:\" + algo + \":A\") + \"\\n\")\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "a3792b44",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "% ### LR\n",
      "% ### RF\n",
      "% ### GB\n",
      "% ### KNN\n",
      "% ### DoG\n"
     ]
    }
   ],
   "source": [
    "for algo in algs:\n",
    "    print(\"% ### \" + algo)\n",
    "    heading = [\"dataset\"]\n",
    "    for g in gans:\n",
    "        if not g.startswith(\"convGAN\") or g == \"convGAN-majority-full\":\n",
    "            heading.append(g)\n",
    "    table = []\n",
    "    \n",
    "    avg = [[0.0, 0.0] for h in heading[1:]]\n",
    "    cnt = 0\n",
    "    \n",
    "    for d in testSets:\n",
    "        d = cleanupName(d)\n",
    "        if d not in ignore:\n",
    "            cnt += 1\n",
    "            row = tableRow(algo, d, heading[1:])\n",
    "            table.append([(d,d)] + row)\n",
    "\n",
    "            for (n, r) in enumerate(row):\n",
    "                avg[n][0] += r[0] or 0.0\n",
    "                avg[n][1] += r[1] or 0.0\n",
    "    \n",
    "    table.append([(\"Average\", \"Average\")] + [(a / cnt, b / cnt) for (a,b) in avg])\n",
    "    \n",
    "    with open(f\"data_result/statistics/{algo}-f1.csv\", \"w\") as f:\n",
    "        f.write((\",\".join(heading)) + \"\\n\")\n",
    "        for row in table:\n",
    "            f.write((\",\".join([str(x[0]) for x in row])) + \"\\n\")\n",
    "\n",
    "    with open(f\"data_result/statistics/{algo}-kappa.csv\", \"w\") as f:\n",
    "        f.write((\",\".join(heading)) + \"\\n\")\n",
    "        for row in table:\n",
    "            f.write((\",\".join([str(x[1]) for x in row])) + \"\\n\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "f1b75f48",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5.480 - winequality-red-4\n",
      "17.141 - flare-F\n",
      "20.768 - abalone_17_vs_7_8_9_10\n",
      "22.928 - yeast4\n",
      "29.056 - abalone9-18\n",
      "33.003 - yeast6\n",
      "40.735 - car_good\n",
      "49.689 - hypothyroid\n",
      "51.936 - yeast5\n",
      "57.451 - car-vgood\n",
      "68.274 - kr-vs-k-zero-one_vs_draw\n",
      "74.547 - kr-vs-k-three_vs_eleven\n",
      "78.777 - shuttle-2_vs_5\n",
      "79.641 - kddcup-guess_passwd_vs_satan\n"
     ]
    }
   ],
   "source": [
    "def dsWeight(d, score):\n",
    "    w = 0.0\n",
    "    for g in gans:\n",
    "        for a in algs:\n",
    "            x = getValueOf(g, d, a, score)\n",
    "            if x is not None:\n",
    "                w += x\n",
    "    return w\n",
    "\n",
    "\n",
    "\n",
    "dataNames = [cleanupName(d) for d in testSets]\n",
    "dataNames.sort(key=lambda d: dsWeight(d, f1Score) + dsWeight(d, kScore))\n",
    "for d in dataNames:\n",
    "    w = dsWeight(d, f1Score) + dsWeight(d, kScore)\n",
    "    print(f\"{w:0.3f} - {d}\")"
   ]
  }
 ],
 "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": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}