{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import cv2 as cv\n",
    "import math\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd\n",
    "import imutils.paths as path \n",
    "\n",
    "from tqdm import tqdm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "PATH = 'D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao'\n",
    "imagePaths = sorted(list(path.list_images(PATH)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "load: 100%|██████████| 62/62 [00:00<00:00, 3245.35it/s]\n"
     ]
    }
   ],
   "source": [
    "data = []\n",
    "for i in tqdm(imagePaths, desc='load'):\n",
    "    imgg = cv.imread(i)\n",
    "    resized_img = cv.resize(imgg, (32, 43))  # Resize dulu\n",
    "    gray_img = cv.cvtColor(resized_img, cv.COLOR_BGR2GRAY)  # Kemudian grayscale\n",
    "    data.append(gray_img)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Fungsi Derajat 0°\n",
    "def derajat0(img):\n",
    "    max_val = np.max(img)\n",
    "    imgTmp = np.zeros([max_val+1, max_val+1])\n",
    "    \n",
    "    for i in range(len(img)):\n",
    "        for j in range(len(img[i])-1):  # Horizontal (kanan)\n",
    "            imgTmp[img[i][j], img[i][j+1]] += 1\n",
    "\n",
    "    transpos = np.transpose(imgTmp)\n",
    "    data = imgTmp + transpos\n",
    "\n",
    "    tmp = np.sum(data)\n",
    "    data /= tmp\n",
    "    return data\n",
    "\n",
    "# Fungsi Derajat 45°\n",
    "def derajat45(img):\n",
    "    max_val = np.max(img)\n",
    "    imgTmp = np.zeros([max_val+1, max_val+1])\n",
    "    \n",
    "    for i in range(1, len(img)):\n",
    "        for j in range(len(img[i])-1):  # Diagonal (kanan atas)\n",
    "            imgTmp[img[i][j], img[i-1][j+1]] += 1\n",
    "\n",
    "    transpos = np.transpose(imgTmp)\n",
    "    data = imgTmp + transpos\n",
    "\n",
    "    tmp = np.sum(data)\n",
    "    data /= tmp\n",
    "    return data\n",
    "\n",
    "# Fungsi Derajat 90°\n",
    "def derajat90(img):\n",
    "    max_val = np.max(img)\n",
    "    imgTmp = np.zeros([max_val+1, max_val+1])\n",
    "    \n",
    "    for i in range(1, len(img)):  # Vertikal (atas)\n",
    "        for j in range(len(img[i])):\n",
    "            imgTmp[img[i][j], img[i-1][j]] += 1\n",
    "\n",
    "    transpos = np.transpose(imgTmp)\n",
    "    data = imgTmp + transpos\n",
    "\n",
    "    tmp = np.sum(data)\n",
    "    data /= tmp\n",
    "    return data\n",
    "\n",
    "# Fungsi Derajat 135°\n",
    "def derajat135(img):\n",
    "    max_val = np.max(img)\n",
    "    imgTmp = np.zeros([max_val+1, max_val+1])\n",
    "    \n",
    "    for i in range(1, len(img)):\n",
    "        for j in range(1, len(img[i])):  # Diagonal (kiri atas)\n",
    "            imgTmp[img[i][j], img[i-1][j-1]] += 1\n",
    "\n",
    "    transpos = np.transpose(imgTmp)\n",
    "    data = imgTmp + transpos\n",
    "\n",
    "    tmp = np.sum(data)\n",
    "    data /= tmp\n",
    "    return data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "GLCM: 100%|██████████| 62/62 [00:00<00:00, 230.03it/s]\n"
     ]
    }
   ],
   "source": [
    "hasil = []\n",
    "for i in tqdm((range (len(data))), desc='GLCM'):\n",
    "    dat= []\n",
    "    dat.append(derajat0(data[i]))\n",
    "    dat.append(derajat45(data[i]))\n",
    "    dat.append(derajat90(data[i]))\n",
    "    dat.append(derajat135(data[i]))\n",
    "    hasil.append(dat)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Fungsi untuk menghitung contrast\n",
    "def contrast(data):\n",
    "    contrast_val = 0\n",
    "    for i in range(len(data)):\n",
    "        for j in range(len(data)):\n",
    "            contrast_val += data[i,j] * pow(i-j, 2)\n",
    "    return contrast_val"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Fungsi untuk menghitung entropy\n",
    "def entropy(data):\n",
    "    entropy_val = 0\n",
    "    for i in range(len(data)):\n",
    "        for j in range(len(data)):\n",
    "            if data[i,j] > 0:\n",
    "                entropy_val += - (data[i,j] * math.log(data[i,j]))\n",
    "    return entropy_val"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Fungsi untuk menghitung homogenitas\n",
    "def homogenitas(data):\n",
    "    homogenitas_val = 0\n",
    "    for i in range(len(data)):\n",
    "        for j in range(len(data)):\n",
    "            homogenitas_val += data[i,j] * (1 + (pow(i-j, 2)))\n",
    "    return homogenitas_val"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Fungsi untuk menghitung energy\n",
    "def energy(data):\n",
    "    energy_val = 0\n",
    "    for i in range(len(data)):\n",
    "        for j in range(len(data)):\n",
    "            energy_val += data[i,j] ** 2\n",
    "    return energy_val"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Ekstraksi: 100%|██████████| 62/62 [00:18<00:00,  3.33it/s]\n"
     ]
    }
   ],
   "source": [
    "# Proses ekstraksi RGB dan grayscale\n",
    "hasilnya = []\n",
    "\n",
    "for j in tqdm(range(len(hasil)), desc='Ekstraksi'):\n",
    "    da = []\n",
    "    da.append(imagePaths[j])\n",
    "    \n",
    "    # Baca gambar asli lagi untuk mendapatkan nilai RGB dan grayscale\n",
    "    imgg = cv.imread(imagePaths[j])\n",
    "    resized_img = cv.resize(imgg, (32, 43))  # Resize image\n",
    "    gray_img = cv.cvtColor(resized_img, cv.COLOR_BGR2GRAY)\n",
    "    \n",
    "    # Hitung rata-rata R, G, B\n",
    "    avg_r = np.mean(resized_img[:, :, 2])  # Kanal merah (R)\n",
    "    avg_g = np.mean(resized_img[:, :, 1])  # Kanal hijau (G)\n",
    "    avg_b = np.mean(resized_img[:, :, 0])  # Kanal biru (B)\n",
    "    \n",
    "    # Hitung rata-rata grayscale\n",
    "    avg_gray = np.mean(gray_img)\n",
    "    \n",
    "    # Tambahkan nilai R, G, B, dan grayscale ke daftar\n",
    "    da.append(avg_r)\n",
    "    da.append(avg_g)\n",
    "    da.append(avg_b)\n",
    "    da.append(avg_gray)\n",
    "    \n",
    "    # Ekstraksi GLCM\n",
    "    for i in hasil[j]:\n",
    "        dx = energy(i)\n",
    "        da.append(dx)\n",
    "\n",
    "        dh = homogenitas(i)\n",
    "        da.append(dh)\n",
    "\n",
    "        den = entropy(i)\n",
    "        da.append(den)\n",
    "\n",
    "        dco = contrast(i)\n",
    "        da.append(dco)\n",
    "\n",
    "    hasilnya.append(da)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "namatabel = ['file', 'avg_R', 'avg_G', 'avg_B', 'avg_grayscale', \n",
    "             'energy_0', 'homogenitas_0', 'entropy_0', 'contrast_0', \n",
    "             'energy_45', 'homogenitas_45', 'entropy_45', 'contrast_45',\n",
    "             'energy_90', 'homogenitas_90', 'entropy_90', 'contrast_90', \n",
    "             'energy_135', 'homogenitas_135', 'entropy_135', 'contrast_135']\n",
    "df = pd.DataFrame(hasilnya, columns=namatabel)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(62, 21)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()\n",
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>file</th>\n",
       "      <th>avg_R</th>\n",
       "      <th>avg_G</th>\n",
       "      <th>avg_B</th>\n",
       "      <th>avg_grayscale</th>\n",
       "      <th>energy_0</th>\n",
       "      <th>homogenitas_0</th>\n",
       "      <th>entropy_0</th>\n",
       "      <th>contrast_0</th>\n",
       "      <th>energy_45</th>\n",
       "      <th>...</th>\n",
       "      <th>entropy_45</th>\n",
       "      <th>contrast_45</th>\n",
       "      <th>energy_90</th>\n",
       "      <th>homogenitas_90</th>\n",
       "      <th>entropy_90</th>\n",
       "      <th>contrast_90</th>\n",
       "      <th>energy_135</th>\n",
       "      <th>homogenitas_135</th>\n",
       "      <th>entropy_135</th>\n",
       "      <th>contrast_135</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy1...</td>\n",
       "      <td>167.330669</td>\n",
       "      <td>141.304506</td>\n",
       "      <td>144.404070</td>\n",
       "      <td>149.433866</td>\n",
       "      <td>0.039669</td>\n",
       "      <td>1183.916729</td>\n",
       "      <td>5.983636</td>\n",
       "      <td>1182.916729</td>\n",
       "      <td>0.037211</td>\n",
       "      <td>...</td>\n",
       "      <td>5.962366</td>\n",
       "      <td>828.537634</td>\n",
       "      <td>0.043967</td>\n",
       "      <td>734.822173</td>\n",
       "      <td>5.867349</td>\n",
       "      <td>733.822173</td>\n",
       "      <td>0.035344</td>\n",
       "      <td>2466.510753</td>\n",
       "      <td>6.159601</td>\n",
       "      <td>2465.510753</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...</td>\n",
       "      <td>195.838663</td>\n",
       "      <td>167.524709</td>\n",
       "      <td>164.731105</td>\n",
       "      <td>175.655523</td>\n",
       "      <td>0.066730</td>\n",
       "      <td>756.364591</td>\n",
       "      <td>5.593014</td>\n",
       "      <td>755.364591</td>\n",
       "      <td>0.057723</td>\n",
       "      <td>...</td>\n",
       "      <td>5.631760</td>\n",
       "      <td>533.014593</td>\n",
       "      <td>0.060906</td>\n",
       "      <td>721.136905</td>\n",
       "      <td>5.653274</td>\n",
       "      <td>720.136905</td>\n",
       "      <td>0.055559</td>\n",
       "      <td>1808.822581</td>\n",
       "      <td>5.831914</td>\n",
       "      <td>1807.822581</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...</td>\n",
       "      <td>195.396802</td>\n",
       "      <td>136.525436</td>\n",
       "      <td>132.470203</td>\n",
       "      <td>153.653343</td>\n",
       "      <td>0.012311</td>\n",
       "      <td>760.389347</td>\n",
       "      <td>6.536436</td>\n",
       "      <td>759.389347</td>\n",
       "      <td>0.009326</td>\n",
       "      <td>...</td>\n",
       "      <td>6.695866</td>\n",
       "      <td>1501.630568</td>\n",
       "      <td>0.011515</td>\n",
       "      <td>722.642113</td>\n",
       "      <td>6.503344</td>\n",
       "      <td>721.642113</td>\n",
       "      <td>0.009677</td>\n",
       "      <td>1008.569892</td>\n",
       "      <td>6.599170</td>\n",
       "      <td>1007.569892</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...</td>\n",
       "      <td>182.253634</td>\n",
       "      <td>156.154070</td>\n",
       "      <td>162.100291</td>\n",
       "      <td>164.632267</td>\n",
       "      <td>0.015513</td>\n",
       "      <td>1284.380345</td>\n",
       "      <td>6.710772</td>\n",
       "      <td>1283.380345</td>\n",
       "      <td>0.012418</td>\n",
       "      <td>...</td>\n",
       "      <td>6.788814</td>\n",
       "      <td>1834.271121</td>\n",
       "      <td>0.014571</td>\n",
       "      <td>1427.281250</td>\n",
       "      <td>6.724166</td>\n",
       "      <td>1426.281250</td>\n",
       "      <td>0.011694</td>\n",
       "      <td>2557.798771</td>\n",
       "      <td>6.833270</td>\n",
       "      <td>2556.798771</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...</td>\n",
       "      <td>159.629360</td>\n",
       "      <td>113.136628</td>\n",
       "      <td>125.544331</td>\n",
       "      <td>128.454942</td>\n",
       "      <td>0.006929</td>\n",
       "      <td>1112.046512</td>\n",
       "      <td>6.948334</td>\n",
       "      <td>1111.046512</td>\n",
       "      <td>0.005335</td>\n",
       "      <td>...</td>\n",
       "      <td>7.037612</td>\n",
       "      <td>1527.529954</td>\n",
       "      <td>0.007129</td>\n",
       "      <td>851.715030</td>\n",
       "      <td>6.886013</td>\n",
       "      <td>850.715030</td>\n",
       "      <td>0.005616</td>\n",
       "      <td>1652.311060</td>\n",
       "      <td>7.006333</td>\n",
       "      <td>1651.311060</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>57</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\phytopht...</td>\n",
       "      <td>172.139535</td>\n",
       "      <td>153.027616</td>\n",
       "      <td>152.499273</td>\n",
       "      <td>158.692587</td>\n",
       "      <td>0.012991</td>\n",
       "      <td>806.343586</td>\n",
       "      <td>6.689354</td>\n",
       "      <td>805.343586</td>\n",
       "      <td>0.009622</td>\n",
       "      <td>...</td>\n",
       "      <td>6.828423</td>\n",
       "      <td>1289.330261</td>\n",
       "      <td>0.013888</td>\n",
       "      <td>617.728423</td>\n",
       "      <td>6.650209</td>\n",
       "      <td>616.728423</td>\n",
       "      <td>0.010934</td>\n",
       "      <td>974.344854</td>\n",
       "      <td>6.729272</td>\n",
       "      <td>973.344854</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>58</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\phytopht...</td>\n",
       "      <td>160.443314</td>\n",
       "      <td>119.247093</td>\n",
       "      <td>122.186047</td>\n",
       "      <td>131.893169</td>\n",
       "      <td>0.004091</td>\n",
       "      <td>975.556639</td>\n",
       "      <td>7.110375</td>\n",
       "      <td>974.556639</td>\n",
       "      <td>0.003058</td>\n",
       "      <td>...</td>\n",
       "      <td>7.192612</td>\n",
       "      <td>1373.503840</td>\n",
       "      <td>0.003498</td>\n",
       "      <td>742.747024</td>\n",
       "      <td>7.111004</td>\n",
       "      <td>741.747024</td>\n",
       "      <td>0.002768</td>\n",
       "      <td>1519.470814</td>\n",
       "      <td>7.229459</td>\n",
       "      <td>1518.470814</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>59</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\phytopht...</td>\n",
       "      <td>180.795785</td>\n",
       "      <td>149.758721</td>\n",
       "      <td>143.757267</td>\n",
       "      <td>158.353198</td>\n",
       "      <td>0.024628</td>\n",
       "      <td>680.713428</td>\n",
       "      <td>6.432822</td>\n",
       "      <td>679.713428</td>\n",
       "      <td>0.017666</td>\n",
       "      <td>...</td>\n",
       "      <td>6.591860</td>\n",
       "      <td>1341.078341</td>\n",
       "      <td>0.020257</td>\n",
       "      <td>676.130208</td>\n",
       "      <td>6.443749</td>\n",
       "      <td>675.130208</td>\n",
       "      <td>0.019240</td>\n",
       "      <td>869.179724</td>\n",
       "      <td>6.529462</td>\n",
       "      <td>868.179724</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>60</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\phytopht...</td>\n",
       "      <td>184.170785</td>\n",
       "      <td>162.387355</td>\n",
       "      <td>166.250000</td>\n",
       "      <td>169.336483</td>\n",
       "      <td>0.039810</td>\n",
       "      <td>1073.855214</td>\n",
       "      <td>6.091023</td>\n",
       "      <td>1072.855214</td>\n",
       "      <td>0.033012</td>\n",
       "      <td>...</td>\n",
       "      <td>6.257683</td>\n",
       "      <td>2000.409370</td>\n",
       "      <td>0.041108</td>\n",
       "      <td>732.640625</td>\n",
       "      <td>6.059936</td>\n",
       "      <td>731.640625</td>\n",
       "      <td>0.036243</td>\n",
       "      <td>760.471582</td>\n",
       "      <td>6.076586</td>\n",
       "      <td>759.471582</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>61</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\phytopht...</td>\n",
       "      <td>156.928052</td>\n",
       "      <td>129.741279</td>\n",
       "      <td>120.791424</td>\n",
       "      <td>136.859738</td>\n",
       "      <td>0.002670</td>\n",
       "      <td>808.151538</td>\n",
       "      <td>7.371438</td>\n",
       "      <td>807.151538</td>\n",
       "      <td>0.002105</td>\n",
       "      <td>...</td>\n",
       "      <td>7.392510</td>\n",
       "      <td>1147.942396</td>\n",
       "      <td>0.002788</td>\n",
       "      <td>674.763393</td>\n",
       "      <td>7.321340</td>\n",
       "      <td>673.763393</td>\n",
       "      <td>0.001992</td>\n",
       "      <td>1246.307988</td>\n",
       "      <td>7.426753</td>\n",
       "      <td>1245.307988</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>62 rows × 21 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 file       avg_R       avg_G  \\\n",
       "0   D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy1...  167.330669  141.304506   \n",
       "1   D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...  195.838663  167.524709   \n",
       "2   D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...  195.396802  136.525436   \n",
       "3   D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...  182.253634  156.154070   \n",
       "4   D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...  159.629360  113.136628   \n",
       "..                                                ...         ...         ...   \n",
       "57  D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\phytopht...  172.139535  153.027616   \n",
       "58  D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\phytopht...  160.443314  119.247093   \n",
       "59  D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\phytopht...  180.795785  149.758721   \n",
       "60  D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\phytopht...  184.170785  162.387355   \n",
       "61  D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\phytopht...  156.928052  129.741279   \n",
       "\n",
       "         avg_B  avg_grayscale  energy_0  homogenitas_0  entropy_0  \\\n",
       "0   144.404070     149.433866  0.039669    1183.916729   5.983636   \n",
       "1   164.731105     175.655523  0.066730     756.364591   5.593014   \n",
       "2   132.470203     153.653343  0.012311     760.389347   6.536436   \n",
       "3   162.100291     164.632267  0.015513    1284.380345   6.710772   \n",
       "4   125.544331     128.454942  0.006929    1112.046512   6.948334   \n",
       "..         ...            ...       ...            ...        ...   \n",
       "57  152.499273     158.692587  0.012991     806.343586   6.689354   \n",
       "58  122.186047     131.893169  0.004091     975.556639   7.110375   \n",
       "59  143.757267     158.353198  0.024628     680.713428   6.432822   \n",
       "60  166.250000     169.336483  0.039810    1073.855214   6.091023   \n",
       "61  120.791424     136.859738  0.002670     808.151538   7.371438   \n",
       "\n",
       "     contrast_0  energy_45  ...  entropy_45  contrast_45  energy_90  \\\n",
       "0   1182.916729   0.037211  ...    5.962366   828.537634   0.043967   \n",
       "1    755.364591   0.057723  ...    5.631760   533.014593   0.060906   \n",
       "2    759.389347   0.009326  ...    6.695866  1501.630568   0.011515   \n",
       "3   1283.380345   0.012418  ...    6.788814  1834.271121   0.014571   \n",
       "4   1111.046512   0.005335  ...    7.037612  1527.529954   0.007129   \n",
       "..          ...        ...  ...         ...          ...        ...   \n",
       "57   805.343586   0.009622  ...    6.828423  1289.330261   0.013888   \n",
       "58   974.556639   0.003058  ...    7.192612  1373.503840   0.003498   \n",
       "59   679.713428   0.017666  ...    6.591860  1341.078341   0.020257   \n",
       "60  1072.855214   0.033012  ...    6.257683  2000.409370   0.041108   \n",
       "61   807.151538   0.002105  ...    7.392510  1147.942396   0.002788   \n",
       "\n",
       "    homogenitas_90  entropy_90  contrast_90  energy_135  homogenitas_135  \\\n",
       "0       734.822173    5.867349   733.822173    0.035344      2466.510753   \n",
       "1       721.136905    5.653274   720.136905    0.055559      1808.822581   \n",
       "2       722.642113    6.503344   721.642113    0.009677      1008.569892   \n",
       "3      1427.281250    6.724166  1426.281250    0.011694      2557.798771   \n",
       "4       851.715030    6.886013   850.715030    0.005616      1652.311060   \n",
       "..             ...         ...          ...         ...              ...   \n",
       "57      617.728423    6.650209   616.728423    0.010934       974.344854   \n",
       "58      742.747024    7.111004   741.747024    0.002768      1519.470814   \n",
       "59      676.130208    6.443749   675.130208    0.019240       869.179724   \n",
       "60      732.640625    6.059936   731.640625    0.036243       760.471582   \n",
       "61      674.763393    7.321340   673.763393    0.001992      1246.307988   \n",
       "\n",
       "    entropy_135  contrast_135  \n",
       "0      6.159601   2465.510753  \n",
       "1      5.831914   1807.822581  \n",
       "2      6.599170   1007.569892  \n",
       "3      6.833270   2556.798771  \n",
       "4      7.006333   1651.311060  \n",
       "..          ...           ...  \n",
       "57     6.729272    973.344854  \n",
       "58     7.229459   1518.470814  \n",
       "59     6.529462    868.179724  \n",
       "60     6.076586    759.471582  \n",
       "61     7.426753   1245.307988  \n",
       "\n",
       "[62 rows x 21 columns]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Data berhasil diekstraksi\n"
     ]
    }
   ],
   "source": [
    "df.to_csv(r'newdata.csv', index = False)\n",
    "print('Data berhasil diekstraksi')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### KNN"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "import seaborn as sns\n",
    "sns.set()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "kakao = pd.read_csv('newdata.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "result = []\n",
    "for value in range(1, 63):\n",
    "    if value <= 21:\n",
    "        result.append('Healthy')\n",
    "    elif value <= 42:\n",
    "        result.append('Monilia')\n",
    "    else:\n",
    "        result.append('Phytophthora')\n",
    "\n",
    "kakao['label'] = result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>file</th>\n",
       "      <th>avg_R</th>\n",
       "      <th>avg_G</th>\n",
       "      <th>avg_B</th>\n",
       "      <th>avg_grayscale</th>\n",
       "      <th>energy_0</th>\n",
       "      <th>homogenitas_0</th>\n",
       "      <th>entropy_0</th>\n",
       "      <th>contrast_0</th>\n",
       "      <th>energy_45</th>\n",
       "      <th>...</th>\n",
       "      <th>contrast_45</th>\n",
       "      <th>energy_90</th>\n",
       "      <th>homogenitas_90</th>\n",
       "      <th>entropy_90</th>\n",
       "      <th>contrast_90</th>\n",
       "      <th>energy_135</th>\n",
       "      <th>homogenitas_135</th>\n",
       "      <th>entropy_135</th>\n",
       "      <th>contrast_135</th>\n",
       "      <th>label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy1...</td>\n",
       "      <td>167.330669</td>\n",
       "      <td>141.304506</td>\n",
       "      <td>144.404070</td>\n",
       "      <td>149.433866</td>\n",
       "      <td>0.039669</td>\n",
       "      <td>1183.916729</td>\n",
       "      <td>5.983636</td>\n",
       "      <td>1182.916729</td>\n",
       "      <td>0.037211</td>\n",
       "      <td>...</td>\n",
       "      <td>828.537634</td>\n",
       "      <td>0.043967</td>\n",
       "      <td>734.822173</td>\n",
       "      <td>5.867349</td>\n",
       "      <td>733.822173</td>\n",
       "      <td>0.035344</td>\n",
       "      <td>2466.510753</td>\n",
       "      <td>6.159601</td>\n",
       "      <td>2465.510753</td>\n",
       "      <td>Healthy</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...</td>\n",
       "      <td>195.838663</td>\n",
       "      <td>167.524709</td>\n",
       "      <td>164.731105</td>\n",
       "      <td>175.655523</td>\n",
       "      <td>0.066730</td>\n",
       "      <td>756.364591</td>\n",
       "      <td>5.593014</td>\n",
       "      <td>755.364591</td>\n",
       "      <td>0.057723</td>\n",
       "      <td>...</td>\n",
       "      <td>533.014593</td>\n",
       "      <td>0.060906</td>\n",
       "      <td>721.136905</td>\n",
       "      <td>5.653274</td>\n",
       "      <td>720.136905</td>\n",
       "      <td>0.055559</td>\n",
       "      <td>1808.822581</td>\n",
       "      <td>5.831914</td>\n",
       "      <td>1807.822581</td>\n",
       "      <td>Healthy</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...</td>\n",
       "      <td>195.396802</td>\n",
       "      <td>136.525436</td>\n",
       "      <td>132.470203</td>\n",
       "      <td>153.653343</td>\n",
       "      <td>0.012311</td>\n",
       "      <td>760.389347</td>\n",
       "      <td>6.536436</td>\n",
       "      <td>759.389347</td>\n",
       "      <td>0.009326</td>\n",
       "      <td>...</td>\n",
       "      <td>1501.630568</td>\n",
       "      <td>0.011515</td>\n",
       "      <td>722.642113</td>\n",
       "      <td>6.503344</td>\n",
       "      <td>721.642113</td>\n",
       "      <td>0.009677</td>\n",
       "      <td>1008.569892</td>\n",
       "      <td>6.599170</td>\n",
       "      <td>1007.569892</td>\n",
       "      <td>Healthy</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...</td>\n",
       "      <td>182.253634</td>\n",
       "      <td>156.154070</td>\n",
       "      <td>162.100291</td>\n",
       "      <td>164.632267</td>\n",
       "      <td>0.015513</td>\n",
       "      <td>1284.380345</td>\n",
       "      <td>6.710772</td>\n",
       "      <td>1283.380345</td>\n",
       "      <td>0.012418</td>\n",
       "      <td>...</td>\n",
       "      <td>1834.271121</td>\n",
       "      <td>0.014571</td>\n",
       "      <td>1427.281250</td>\n",
       "      <td>6.724166</td>\n",
       "      <td>1426.281250</td>\n",
       "      <td>0.011694</td>\n",
       "      <td>2557.798771</td>\n",
       "      <td>6.833270</td>\n",
       "      <td>2556.798771</td>\n",
       "      <td>Healthy</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...</td>\n",
       "      <td>159.629360</td>\n",
       "      <td>113.136628</td>\n",
       "      <td>125.544331</td>\n",
       "      <td>128.454942</td>\n",
       "      <td>0.006929</td>\n",
       "      <td>1112.046512</td>\n",
       "      <td>6.948334</td>\n",
       "      <td>1111.046512</td>\n",
       "      <td>0.005335</td>\n",
       "      <td>...</td>\n",
       "      <td>1527.529954</td>\n",
       "      <td>0.007129</td>\n",
       "      <td>851.715030</td>\n",
       "      <td>6.886013</td>\n",
       "      <td>850.715030</td>\n",
       "      <td>0.005616</td>\n",
       "      <td>1652.311060</td>\n",
       "      <td>7.006333</td>\n",
       "      <td>1651.311060</td>\n",
       "      <td>Healthy</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>57</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\phytopht...</td>\n",
       "      <td>172.139535</td>\n",
       "      <td>153.027616</td>\n",
       "      <td>152.499273</td>\n",
       "      <td>158.692587</td>\n",
       "      <td>0.012991</td>\n",
       "      <td>806.343586</td>\n",
       "      <td>6.689354</td>\n",
       "      <td>805.343586</td>\n",
       "      <td>0.009622</td>\n",
       "      <td>...</td>\n",
       "      <td>1289.330261</td>\n",
       "      <td>0.013888</td>\n",
       "      <td>617.728423</td>\n",
       "      <td>6.650209</td>\n",
       "      <td>616.728423</td>\n",
       "      <td>0.010934</td>\n",
       "      <td>974.344854</td>\n",
       "      <td>6.729272</td>\n",
       "      <td>973.344854</td>\n",
       "      <td>Phytophthora</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>58</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\phytopht...</td>\n",
       "      <td>160.443314</td>\n",
       "      <td>119.247093</td>\n",
       "      <td>122.186047</td>\n",
       "      <td>131.893169</td>\n",
       "      <td>0.004091</td>\n",
       "      <td>975.556639</td>\n",
       "      <td>7.110375</td>\n",
       "      <td>974.556639</td>\n",
       "      <td>0.003058</td>\n",
       "      <td>...</td>\n",
       "      <td>1373.503840</td>\n",
       "      <td>0.003498</td>\n",
       "      <td>742.747024</td>\n",
       "      <td>7.111004</td>\n",
       "      <td>741.747024</td>\n",
       "      <td>0.002768</td>\n",
       "      <td>1519.470814</td>\n",
       "      <td>7.229459</td>\n",
       "      <td>1518.470814</td>\n",
       "      <td>Phytophthora</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>59</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\phytopht...</td>\n",
       "      <td>180.795785</td>\n",
       "      <td>149.758721</td>\n",
       "      <td>143.757267</td>\n",
       "      <td>158.353198</td>\n",
       "      <td>0.024628</td>\n",
       "      <td>680.713428</td>\n",
       "      <td>6.432822</td>\n",
       "      <td>679.713428</td>\n",
       "      <td>0.017666</td>\n",
       "      <td>...</td>\n",
       "      <td>1341.078341</td>\n",
       "      <td>0.020257</td>\n",
       "      <td>676.130208</td>\n",
       "      <td>6.443749</td>\n",
       "      <td>675.130208</td>\n",
       "      <td>0.019240</td>\n",
       "      <td>869.179724</td>\n",
       "      <td>6.529462</td>\n",
       "      <td>868.179724</td>\n",
       "      <td>Phytophthora</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>60</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\phytopht...</td>\n",
       "      <td>184.170785</td>\n",
       "      <td>162.387355</td>\n",
       "      <td>166.250000</td>\n",
       "      <td>169.336483</td>\n",
       "      <td>0.039810</td>\n",
       "      <td>1073.855214</td>\n",
       "      <td>6.091023</td>\n",
       "      <td>1072.855214</td>\n",
       "      <td>0.033012</td>\n",
       "      <td>...</td>\n",
       "      <td>2000.409370</td>\n",
       "      <td>0.041108</td>\n",
       "      <td>732.640625</td>\n",
       "      <td>6.059936</td>\n",
       "      <td>731.640625</td>\n",
       "      <td>0.036243</td>\n",
       "      <td>760.471582</td>\n",
       "      <td>6.076586</td>\n",
       "      <td>759.471582</td>\n",
       "      <td>Phytophthora</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>61</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\phytopht...</td>\n",
       "      <td>156.928052</td>\n",
       "      <td>129.741279</td>\n",
       "      <td>120.791424</td>\n",
       "      <td>136.859738</td>\n",
       "      <td>0.002670</td>\n",
       "      <td>808.151538</td>\n",
       "      <td>7.371438</td>\n",
       "      <td>807.151538</td>\n",
       "      <td>0.002105</td>\n",
       "      <td>...</td>\n",
       "      <td>1147.942396</td>\n",
       "      <td>0.002788</td>\n",
       "      <td>674.763393</td>\n",
       "      <td>7.321340</td>\n",
       "      <td>673.763393</td>\n",
       "      <td>0.001992</td>\n",
       "      <td>1246.307988</td>\n",
       "      <td>7.426753</td>\n",
       "      <td>1245.307988</td>\n",
       "      <td>Phytophthora</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>62 rows × 22 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 file       avg_R       avg_G  \\\n",
       "0   D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy1...  167.330669  141.304506   \n",
       "1   D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...  195.838663  167.524709   \n",
       "2   D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...  195.396802  136.525436   \n",
       "3   D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...  182.253634  156.154070   \n",
       "4   D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...  159.629360  113.136628   \n",
       "..                                                ...         ...         ...   \n",
       "57  D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\phytopht...  172.139535  153.027616   \n",
       "58  D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\phytopht...  160.443314  119.247093   \n",
       "59  D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\phytopht...  180.795785  149.758721   \n",
       "60  D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\phytopht...  184.170785  162.387355   \n",
       "61  D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\phytopht...  156.928052  129.741279   \n",
       "\n",
       "         avg_B  avg_grayscale  energy_0  homogenitas_0  entropy_0  \\\n",
       "0   144.404070     149.433866  0.039669    1183.916729   5.983636   \n",
       "1   164.731105     175.655523  0.066730     756.364591   5.593014   \n",
       "2   132.470203     153.653343  0.012311     760.389347   6.536436   \n",
       "3   162.100291     164.632267  0.015513    1284.380345   6.710772   \n",
       "4   125.544331     128.454942  0.006929    1112.046512   6.948334   \n",
       "..         ...            ...       ...            ...        ...   \n",
       "57  152.499273     158.692587  0.012991     806.343586   6.689354   \n",
       "58  122.186047     131.893169  0.004091     975.556639   7.110375   \n",
       "59  143.757267     158.353198  0.024628     680.713428   6.432822   \n",
       "60  166.250000     169.336483  0.039810    1073.855214   6.091023   \n",
       "61  120.791424     136.859738  0.002670     808.151538   7.371438   \n",
       "\n",
       "     contrast_0  energy_45  ...  contrast_45  energy_90  homogenitas_90  \\\n",
       "0   1182.916729   0.037211  ...   828.537634   0.043967      734.822173   \n",
       "1    755.364591   0.057723  ...   533.014593   0.060906      721.136905   \n",
       "2    759.389347   0.009326  ...  1501.630568   0.011515      722.642113   \n",
       "3   1283.380345   0.012418  ...  1834.271121   0.014571     1427.281250   \n",
       "4   1111.046512   0.005335  ...  1527.529954   0.007129      851.715030   \n",
       "..          ...        ...  ...          ...        ...             ...   \n",
       "57   805.343586   0.009622  ...  1289.330261   0.013888      617.728423   \n",
       "58   974.556639   0.003058  ...  1373.503840   0.003498      742.747024   \n",
       "59   679.713428   0.017666  ...  1341.078341   0.020257      676.130208   \n",
       "60  1072.855214   0.033012  ...  2000.409370   0.041108      732.640625   \n",
       "61   807.151538   0.002105  ...  1147.942396   0.002788      674.763393   \n",
       "\n",
       "    entropy_90  contrast_90  energy_135  homogenitas_135  entropy_135  \\\n",
       "0     5.867349   733.822173    0.035344      2466.510753     6.159601   \n",
       "1     5.653274   720.136905    0.055559      1808.822581     5.831914   \n",
       "2     6.503344   721.642113    0.009677      1008.569892     6.599170   \n",
       "3     6.724166  1426.281250    0.011694      2557.798771     6.833270   \n",
       "4     6.886013   850.715030    0.005616      1652.311060     7.006333   \n",
       "..         ...          ...         ...              ...          ...   \n",
       "57    6.650209   616.728423    0.010934       974.344854     6.729272   \n",
       "58    7.111004   741.747024    0.002768      1519.470814     7.229459   \n",
       "59    6.443749   675.130208    0.019240       869.179724     6.529462   \n",
       "60    6.059936   731.640625    0.036243       760.471582     6.076586   \n",
       "61    7.321340   673.763393    0.001992      1246.307988     7.426753   \n",
       "\n",
       "    contrast_135         label  \n",
       "0    2465.510753       Healthy  \n",
       "1    1807.822581       Healthy  \n",
       "2    1007.569892       Healthy  \n",
       "3    2556.798771       Healthy  \n",
       "4    1651.311060       Healthy  \n",
       "..           ...           ...  \n",
       "57    973.344854  Phytophthora  \n",
       "58   1518.470814  Phytophthora  \n",
       "59    868.179724  Phytophthora  \n",
       "60    759.471582  Phytophthora  \n",
       "61   1245.307988  Phytophthora  \n",
       "\n",
       "[62 rows x 22 columns]"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "kakao"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>file</th>\n",
       "      <th>avg_R</th>\n",
       "      <th>avg_G</th>\n",
       "      <th>avg_B</th>\n",
       "      <th>avg_grayscale</th>\n",
       "      <th>energy_0</th>\n",
       "      <th>homogenitas_0</th>\n",
       "      <th>entropy_0</th>\n",
       "      <th>contrast_0</th>\n",
       "      <th>energy_45</th>\n",
       "      <th>...</th>\n",
       "      <th>contrast_45</th>\n",
       "      <th>energy_90</th>\n",
       "      <th>homogenitas_90</th>\n",
       "      <th>entropy_90</th>\n",
       "      <th>contrast_90</th>\n",
       "      <th>energy_135</th>\n",
       "      <th>homogenitas_135</th>\n",
       "      <th>entropy_135</th>\n",
       "      <th>contrast_135</th>\n",
       "      <th>label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy1...</td>\n",
       "      <td>167.330669</td>\n",
       "      <td>141.304506</td>\n",
       "      <td>144.404070</td>\n",
       "      <td>149.433866</td>\n",
       "      <td>0.039669</td>\n",
       "      <td>1183.916729</td>\n",
       "      <td>5.983636</td>\n",
       "      <td>1182.916729</td>\n",
       "      <td>0.037211</td>\n",
       "      <td>...</td>\n",
       "      <td>828.537634</td>\n",
       "      <td>0.043967</td>\n",
       "      <td>734.822173</td>\n",
       "      <td>5.867349</td>\n",
       "      <td>733.822173</td>\n",
       "      <td>0.035344</td>\n",
       "      <td>2466.510753</td>\n",
       "      <td>6.159601</td>\n",
       "      <td>2465.510753</td>\n",
       "      <td>Healthy</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...</td>\n",
       "      <td>195.838663</td>\n",
       "      <td>167.524709</td>\n",
       "      <td>164.731105</td>\n",
       "      <td>175.655523</td>\n",
       "      <td>0.066730</td>\n",
       "      <td>756.364591</td>\n",
       "      <td>5.593014</td>\n",
       "      <td>755.364591</td>\n",
       "      <td>0.057723</td>\n",
       "      <td>...</td>\n",
       "      <td>533.014593</td>\n",
       "      <td>0.060906</td>\n",
       "      <td>721.136905</td>\n",
       "      <td>5.653274</td>\n",
       "      <td>720.136905</td>\n",
       "      <td>0.055559</td>\n",
       "      <td>1808.822581</td>\n",
       "      <td>5.831914</td>\n",
       "      <td>1807.822581</td>\n",
       "      <td>Healthy</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...</td>\n",
       "      <td>195.396802</td>\n",
       "      <td>136.525436</td>\n",
       "      <td>132.470203</td>\n",
       "      <td>153.653343</td>\n",
       "      <td>0.012311</td>\n",
       "      <td>760.389347</td>\n",
       "      <td>6.536436</td>\n",
       "      <td>759.389347</td>\n",
       "      <td>0.009326</td>\n",
       "      <td>...</td>\n",
       "      <td>1501.630568</td>\n",
       "      <td>0.011515</td>\n",
       "      <td>722.642113</td>\n",
       "      <td>6.503344</td>\n",
       "      <td>721.642113</td>\n",
       "      <td>0.009677</td>\n",
       "      <td>1008.569892</td>\n",
       "      <td>6.599170</td>\n",
       "      <td>1007.569892</td>\n",
       "      <td>Healthy</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...</td>\n",
       "      <td>182.253634</td>\n",
       "      <td>156.154070</td>\n",
       "      <td>162.100291</td>\n",
       "      <td>164.632267</td>\n",
       "      <td>0.015513</td>\n",
       "      <td>1284.380345</td>\n",
       "      <td>6.710772</td>\n",
       "      <td>1283.380345</td>\n",
       "      <td>0.012418</td>\n",
       "      <td>...</td>\n",
       "      <td>1834.271121</td>\n",
       "      <td>0.014571</td>\n",
       "      <td>1427.281250</td>\n",
       "      <td>6.724166</td>\n",
       "      <td>1426.281250</td>\n",
       "      <td>0.011694</td>\n",
       "      <td>2557.798771</td>\n",
       "      <td>6.833270</td>\n",
       "      <td>2556.798771</td>\n",
       "      <td>Healthy</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...</td>\n",
       "      <td>159.629360</td>\n",
       "      <td>113.136628</td>\n",
       "      <td>125.544331</td>\n",
       "      <td>128.454942</td>\n",
       "      <td>0.006929</td>\n",
       "      <td>1112.046512</td>\n",
       "      <td>6.948334</td>\n",
       "      <td>1111.046512</td>\n",
       "      <td>0.005335</td>\n",
       "      <td>...</td>\n",
       "      <td>1527.529954</td>\n",
       "      <td>0.007129</td>\n",
       "      <td>851.715030</td>\n",
       "      <td>6.886013</td>\n",
       "      <td>850.715030</td>\n",
       "      <td>0.005616</td>\n",
       "      <td>1652.311060</td>\n",
       "      <td>7.006333</td>\n",
       "      <td>1651.311060</td>\n",
       "      <td>Healthy</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 22 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                file       avg_R       avg_G  \\\n",
       "0  D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy1...  167.330669  141.304506   \n",
       "1  D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...  195.838663  167.524709   \n",
       "2  D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...  195.396802  136.525436   \n",
       "3  D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...  182.253634  156.154070   \n",
       "4  D:\\Kuliah\\SKRIPSI\\Kakao\\dataset_kakao\\healthy8...  159.629360  113.136628   \n",
       "\n",
       "        avg_B  avg_grayscale  energy_0  homogenitas_0  entropy_0   contrast_0  \\\n",
       "0  144.404070     149.433866  0.039669    1183.916729   5.983636  1182.916729   \n",
       "1  164.731105     175.655523  0.066730     756.364591   5.593014   755.364591   \n",
       "2  132.470203     153.653343  0.012311     760.389347   6.536436   759.389347   \n",
       "3  162.100291     164.632267  0.015513    1284.380345   6.710772  1283.380345   \n",
       "4  125.544331     128.454942  0.006929    1112.046512   6.948334  1111.046512   \n",
       "\n",
       "   energy_45  ...  contrast_45  energy_90  homogenitas_90  entropy_90  \\\n",
       "0   0.037211  ...   828.537634   0.043967      734.822173    5.867349   \n",
       "1   0.057723  ...   533.014593   0.060906      721.136905    5.653274   \n",
       "2   0.009326  ...  1501.630568   0.011515      722.642113    6.503344   \n",
       "3   0.012418  ...  1834.271121   0.014571     1427.281250    6.724166   \n",
       "4   0.005335  ...  1527.529954   0.007129      851.715030    6.886013   \n",
       "\n",
       "   contrast_90  energy_135  homogenitas_135  entropy_135  contrast_135  \\\n",
       "0   733.822173    0.035344      2466.510753     6.159601   2465.510753   \n",
       "1   720.136905    0.055559      1808.822581     5.831914   1807.822581   \n",
       "2   721.642113    0.009677      1008.569892     6.599170   1007.569892   \n",
       "3  1426.281250    0.011694      2557.798771     6.833270   2556.798771   \n",
       "4   850.715030    0.005616      1652.311060     7.006333   1651.311060   \n",
       "\n",
       "     label  \n",
       "0  Healthy  \n",
       "1  Healthy  \n",
       "2  Healthy  \n",
       "3  Healthy  \n",
       "4  Healthy  \n",
       "\n",
       "[5 rows x 22 columns]"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "kakao.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Data berhasil diekstraksi\n"
     ]
    }
   ],
   "source": [
    "df.to_excel(r'newdata_label.xlsx', index = False)\n",
    "print('Data berhasil diekstraksi')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>avg_R</th>\n",
       "      <th>avg_G</th>\n",
       "      <th>avg_B</th>\n",
       "      <th>avg_grayscale</th>\n",
       "      <th>energy_0</th>\n",
       "      <th>homogenitas_0</th>\n",
       "      <th>entropy_0</th>\n",
       "      <th>contrast_0</th>\n",
       "      <th>energy_45</th>\n",
       "      <th>homogenitas_45</th>\n",
       "      <th>entropy_45</th>\n",
       "      <th>contrast_45</th>\n",
       "      <th>energy_90</th>\n",
       "      <th>homogenitas_90</th>\n",
       "      <th>entropy_90</th>\n",
       "      <th>contrast_90</th>\n",
       "      <th>energy_135</th>\n",
       "      <th>homogenitas_135</th>\n",
       "      <th>entropy_135</th>\n",
       "      <th>contrast_135</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>62.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>62.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>167.612739</td>\n",
       "      <td>151.614908</td>\n",
       "      <td>144.273197</td>\n",
       "      <td>155.563133</td>\n",
       "      <td>0.022301</td>\n",
       "      <td>1031.947523</td>\n",
       "      <td>6.538107</td>\n",
       "      <td>1030.947523</td>\n",
       "      <td>0.019124</td>\n",
       "      <td>1415.361801</td>\n",
       "      <td>6.621816</td>\n",
       "      <td>1414.361801</td>\n",
       "      <td>0.022892</td>\n",
       "      <td>749.355259</td>\n",
       "      <td>6.460528</td>\n",
       "      <td>748.355259</td>\n",
       "      <td>0.018981</td>\n",
       "      <td>1532.331351</td>\n",
       "      <td>6.632939</td>\n",
       "      <td>1531.331351</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>22.272542</td>\n",
       "      <td>22.642722</td>\n",
       "      <td>22.742072</td>\n",
       "      <td>20.970352</td>\n",
       "      <td>0.020948</td>\n",
       "      <td>343.081312</td>\n",
       "      <td>0.462335</td>\n",
       "      <td>343.081312</td>\n",
       "      <td>0.019655</td>\n",
       "      <td>560.365791</td>\n",
       "      <td>0.460039</td>\n",
       "      <td>560.365791</td>\n",
       "      <td>0.021157</td>\n",
       "      <td>257.135032</td>\n",
       "      <td>0.467994</td>\n",
       "      <td>257.135032</td>\n",
       "      <td>0.018932</td>\n",
       "      <td>646.156383</td>\n",
       "      <td>0.459115</td>\n",
       "      <td>646.156383</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>100.042878</td>\n",
       "      <td>98.269622</td>\n",
       "      <td>90.578488</td>\n",
       "      <td>97.949128</td>\n",
       "      <td>0.002243</td>\n",
       "      <td>291.342086</td>\n",
       "      <td>5.330751</td>\n",
       "      <td>290.342086</td>\n",
       "      <td>0.001822</td>\n",
       "      <td>460.836406</td>\n",
       "      <td>5.345357</td>\n",
       "      <td>459.836406</td>\n",
       "      <td>0.002355</td>\n",
       "      <td>209.236607</td>\n",
       "      <td>5.257688</td>\n",
       "      <td>208.236607</td>\n",
       "      <td>0.001846</td>\n",
       "      <td>351.430876</td>\n",
       "      <td>5.499313</td>\n",
       "      <td>350.430876</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>153.698765</td>\n",
       "      <td>137.100836</td>\n",
       "      <td>128.549055</td>\n",
       "      <td>142.162609</td>\n",
       "      <td>0.009079</td>\n",
       "      <td>784.673668</td>\n",
       "      <td>6.257600</td>\n",
       "      <td>783.673668</td>\n",
       "      <td>0.007115</td>\n",
       "      <td>1038.387865</td>\n",
       "      <td>6.363616</td>\n",
       "      <td>1037.387865</td>\n",
       "      <td>0.009957</td>\n",
       "      <td>580.302827</td>\n",
       "      <td>6.120985</td>\n",
       "      <td>579.302827</td>\n",
       "      <td>0.007400</td>\n",
       "      <td>1012.409946</td>\n",
       "      <td>6.341192</td>\n",
       "      <td>1011.409946</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>171.200218</td>\n",
       "      <td>152.820858</td>\n",
       "      <td>143.470203</td>\n",
       "      <td>157.698765</td>\n",
       "      <td>0.014183</td>\n",
       "      <td>969.632783</td>\n",
       "      <td>6.644320</td>\n",
       "      <td>968.632783</td>\n",
       "      <td>0.011717</td>\n",
       "      <td>1345.942780</td>\n",
       "      <td>6.706082</td>\n",
       "      <td>1344.942780</td>\n",
       "      <td>0.014866</td>\n",
       "      <td>702.539807</td>\n",
       "      <td>6.538309</td>\n",
       "      <td>701.539807</td>\n",
       "      <td>0.011325</td>\n",
       "      <td>1426.953917</td>\n",
       "      <td>6.734918</td>\n",
       "      <td>1425.953917</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>182.233648</td>\n",
       "      <td>167.307413</td>\n",
       "      <td>163.134266</td>\n",
       "      <td>169.142987</td>\n",
       "      <td>0.028603</td>\n",
       "      <td>1246.162791</td>\n",
       "      <td>6.893080</td>\n",
       "      <td>1245.162791</td>\n",
       "      <td>0.022679</td>\n",
       "      <td>1761.274770</td>\n",
       "      <td>6.969399</td>\n",
       "      <td>1760.274770</td>\n",
       "      <td>0.027765</td>\n",
       "      <td>856.057106</td>\n",
       "      <td>6.752996</td>\n",
       "      <td>855.057106</td>\n",
       "      <td>0.024031</td>\n",
       "      <td>1789.654762</td>\n",
       "      <td>6.949453</td>\n",
       "      <td>1788.654762</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>209.154070</td>\n",
       "      <td>217.186773</td>\n",
       "      <td>196.622093</td>\n",
       "      <td>206.047965</td>\n",
       "      <td>0.101022</td>\n",
       "      <td>2009.757689</td>\n",
       "      <td>7.371438</td>\n",
       "      <td>2008.757689</td>\n",
       "      <td>0.103409</td>\n",
       "      <td>2858.314900</td>\n",
       "      <td>7.392510</td>\n",
       "      <td>2857.314900</td>\n",
       "      <td>0.104137</td>\n",
       "      <td>1427.281250</td>\n",
       "      <td>7.321340</td>\n",
       "      <td>1426.281250</td>\n",
       "      <td>0.093297</td>\n",
       "      <td>3278.226575</td>\n",
       "      <td>7.426753</td>\n",
       "      <td>3277.226575</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            avg_R       avg_G       avg_B  avg_grayscale   energy_0  \\\n",
       "count   62.000000   62.000000   62.000000      62.000000  62.000000   \n",
       "mean   167.612739  151.614908  144.273197     155.563133   0.022301   \n",
       "std     22.272542   22.642722   22.742072      20.970352   0.020948   \n",
       "min    100.042878   98.269622   90.578488      97.949128   0.002243   \n",
       "25%    153.698765  137.100836  128.549055     142.162609   0.009079   \n",
       "50%    171.200218  152.820858  143.470203     157.698765   0.014183   \n",
       "75%    182.233648  167.307413  163.134266     169.142987   0.028603   \n",
       "max    209.154070  217.186773  196.622093     206.047965   0.101022   \n",
       "\n",
       "       homogenitas_0  entropy_0   contrast_0  energy_45  homogenitas_45  \\\n",
       "count      62.000000  62.000000    62.000000  62.000000       62.000000   \n",
       "mean     1031.947523   6.538107  1030.947523   0.019124     1415.361801   \n",
       "std       343.081312   0.462335   343.081312   0.019655      560.365791   \n",
       "min       291.342086   5.330751   290.342086   0.001822      460.836406   \n",
       "25%       784.673668   6.257600   783.673668   0.007115     1038.387865   \n",
       "50%       969.632783   6.644320   968.632783   0.011717     1345.942780   \n",
       "75%      1246.162791   6.893080  1245.162791   0.022679     1761.274770   \n",
       "max      2009.757689   7.371438  2008.757689   0.103409     2858.314900   \n",
       "\n",
       "       entropy_45  contrast_45  energy_90  homogenitas_90  entropy_90  \\\n",
       "count   62.000000    62.000000  62.000000       62.000000   62.000000   \n",
       "mean     6.621816  1414.361801   0.022892      749.355259    6.460528   \n",
       "std      0.460039   560.365791   0.021157      257.135032    0.467994   \n",
       "min      5.345357   459.836406   0.002355      209.236607    5.257688   \n",
       "25%      6.363616  1037.387865   0.009957      580.302827    6.120985   \n",
       "50%      6.706082  1344.942780   0.014866      702.539807    6.538309   \n",
       "75%      6.969399  1760.274770   0.027765      856.057106    6.752996   \n",
       "max      7.392510  2857.314900   0.104137     1427.281250    7.321340   \n",
       "\n",
       "       contrast_90  energy_135  homogenitas_135  entropy_135  contrast_135  \n",
       "count    62.000000   62.000000        62.000000    62.000000     62.000000  \n",
       "mean    748.355259    0.018981      1532.331351     6.632939   1531.331351  \n",
       "std     257.135032    0.018932       646.156383     0.459115    646.156383  \n",
       "min     208.236607    0.001846       351.430876     5.499313    350.430876  \n",
       "25%     579.302827    0.007400      1012.409946     6.341192   1011.409946  \n",
       "50%     701.539807    0.011325      1426.953917     6.734918   1425.953917  \n",
       "75%     855.057106    0.024031      1789.654762     6.949453   1788.654762  \n",
       "max    1426.281250    0.093297      3278.226575     7.426753   3277.226575  "
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "kakao.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 62 entries, 0 to 61\n",
      "Data columns (total 22 columns):\n",
      " #   Column           Non-Null Count  Dtype  \n",
      "---  ------           --------------  -----  \n",
      " 0   file             62 non-null     object \n",
      " 1   avg_R            62 non-null     float64\n",
      " 2   avg_G            62 non-null     float64\n",
      " 3   avg_B            62 non-null     float64\n",
      " 4   avg_grayscale    62 non-null     float64\n",
      " 5   energy_0         62 non-null     float64\n",
      " 6   homogenitas_0    62 non-null     float64\n",
      " 7   entropy_0        62 non-null     float64\n",
      " 8   contrast_0       62 non-null     float64\n",
      " 9   energy_45        62 non-null     float64\n",
      " 10  homogenitas_45   62 non-null     float64\n",
      " 11  entropy_45       62 non-null     float64\n",
      " 12  contrast_45      62 non-null     float64\n",
      " 13  energy_90        62 non-null     float64\n",
      " 14  homogenitas_90   62 non-null     float64\n",
      " 15  entropy_90       62 non-null     float64\n",
      " 16  contrast_90      62 non-null     float64\n",
      " 17  energy_135       62 non-null     float64\n",
      " 18  homogenitas_135  62 non-null     float64\n",
      " 19  entropy_135      62 non-null     float64\n",
      " 20  contrast_135     62 non-null     float64\n",
      " 21  label            62 non-null     object \n",
      "dtypes: float64(20), object(2)\n",
      "memory usage: 10.8+ KB\n"
     ]
    }
   ],
   "source": [
    "kakao.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>avg_R</th>\n",
       "      <th>avg_G</th>\n",
       "      <th>avg_B</th>\n",
       "      <th>avg_grayscale</th>\n",
       "      <th>energy_0</th>\n",
       "      <th>homogenitas_0</th>\n",
       "      <th>entropy_0</th>\n",
       "      <th>contrast_0</th>\n",
       "      <th>energy_45</th>\n",
       "      <th>homogenitas_45</th>\n",
       "      <th>entropy_45</th>\n",
       "      <th>contrast_45</th>\n",
       "      <th>energy_90</th>\n",
       "      <th>homogenitas_90</th>\n",
       "      <th>entropy_90</th>\n",
       "      <th>contrast_90</th>\n",
       "      <th>energy_135</th>\n",
       "      <th>homogenitas_135</th>\n",
       "      <th>entropy_135</th>\n",
       "      <th>contrast_135</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>avg_R</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.699021</td>\n",
       "      <td>0.835264</td>\n",
       "      <td>0.863648</td>\n",
       "      <td>0.285931</td>\n",
       "      <td>-0.442675</td>\n",
       "      <td>-0.258907</td>\n",
       "      <td>-0.442675</td>\n",
       "      <td>0.270942</td>\n",
       "      <td>-0.321727</td>\n",
       "      <td>-0.245946</td>\n",
       "      <td>-0.321727</td>\n",
       "      <td>0.284467</td>\n",
       "      <td>-0.348829</td>\n",
       "      <td>-0.233020</td>\n",
       "      <td>-0.348829</td>\n",
       "      <td>0.281491</td>\n",
       "      <td>-0.424277</td>\n",
       "      <td>-0.265119</td>\n",
       "      <td>-0.424277</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>avg_G</th>\n",
       "      <td>0.699021</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.864850</td>\n",
       "      <td>0.962579</td>\n",
       "      <td>0.405252</td>\n",
       "      <td>-0.352584</td>\n",
       "      <td>-0.396929</td>\n",
       "      <td>-0.352584</td>\n",
       "      <td>0.394040</td>\n",
       "      <td>-0.288278</td>\n",
       "      <td>-0.390909</td>\n",
       "      <td>-0.288278</td>\n",
       "      <td>0.415033</td>\n",
       "      <td>-0.296224</td>\n",
       "      <td>-0.397389</td>\n",
       "      <td>-0.296224</td>\n",
       "      <td>0.404104</td>\n",
       "      <td>-0.331044</td>\n",
       "      <td>-0.396607</td>\n",
       "      <td>-0.331044</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>avg_B</th>\n",
       "      <td>0.835264</td>\n",
       "      <td>0.864850</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.936858</td>\n",
       "      <td>0.461969</td>\n",
       "      <td>-0.157039</td>\n",
       "      <td>-0.450595</td>\n",
       "      <td>-0.157039</td>\n",
       "      <td>0.441764</td>\n",
       "      <td>-0.133460</td>\n",
       "      <td>-0.436815</td>\n",
       "      <td>-0.133460</td>\n",
       "      <td>0.467696</td>\n",
       "      <td>-0.109673</td>\n",
       "      <td>-0.429388</td>\n",
       "      <td>-0.109673</td>\n",
       "      <td>0.458185</td>\n",
       "      <td>-0.196467</td>\n",
       "      <td>-0.456696</td>\n",
       "      <td>-0.196467</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>avg_grayscale</th>\n",
       "      <td>0.863648</td>\n",
       "      <td>0.962579</td>\n",
       "      <td>0.936858</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.404714</td>\n",
       "      <td>-0.383369</td>\n",
       "      <td>-0.389412</td>\n",
       "      <td>-0.383369</td>\n",
       "      <td>0.390352</td>\n",
       "      <td>-0.301258</td>\n",
       "      <td>-0.379773</td>\n",
       "      <td>-0.301258</td>\n",
       "      <td>0.411155</td>\n",
       "      <td>-0.311978</td>\n",
       "      <td>-0.378862</td>\n",
       "      <td>-0.311978</td>\n",
       "      <td>0.402113</td>\n",
       "      <td>-0.368785</td>\n",
       "      <td>-0.391940</td>\n",
       "      <td>-0.368785</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>energy_0</th>\n",
       "      <td>0.285931</td>\n",
       "      <td>0.405252</td>\n",
       "      <td>0.461969</td>\n",
       "      <td>0.404714</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.161109</td>\n",
       "      <td>-0.888651</td>\n",
       "      <td>0.161109</td>\n",
       "      <td>0.995157</td>\n",
       "      <td>0.006243</td>\n",
       "      <td>-0.907828</td>\n",
       "      <td>0.006243</td>\n",
       "      <td>0.994848</td>\n",
       "      <td>0.054713</td>\n",
       "      <td>-0.865163</td>\n",
       "      <td>0.054713</td>\n",
       "      <td>0.998015</td>\n",
       "      <td>0.124720</td>\n",
       "      <td>-0.883550</td>\n",
       "      <td>0.124720</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>homogenitas_0</th>\n",
       "      <td>-0.442675</td>\n",
       "      <td>-0.352584</td>\n",
       "      <td>-0.157039</td>\n",
       "      <td>-0.383369</td>\n",
       "      <td>0.161109</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.143428</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.150978</td>\n",
       "      <td>0.667826</td>\n",
       "      <td>-0.152576</td>\n",
       "      <td>0.667826</td>\n",
       "      <td>0.170531</td>\n",
       "      <td>0.766407</td>\n",
       "      <td>-0.142880</td>\n",
       "      <td>0.766407</td>\n",
       "      <td>0.162183</td>\n",
       "      <td>0.796541</td>\n",
       "      <td>-0.152188</td>\n",
       "      <td>0.796541</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>entropy_0</th>\n",
       "      <td>-0.258907</td>\n",
       "      <td>-0.396929</td>\n",
       "      <td>-0.450595</td>\n",
       "      <td>-0.389412</td>\n",
       "      <td>-0.888651</td>\n",
       "      <td>-0.143428</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.143428</td>\n",
       "      <td>-0.858710</td>\n",
       "      <td>-0.098443</td>\n",
       "      <td>0.992151</td>\n",
       "      <td>-0.098443</td>\n",
       "      <td>-0.885214</td>\n",
       "      <td>-0.043106</td>\n",
       "      <td>0.990924</td>\n",
       "      <td>-0.043106</td>\n",
       "      <td>-0.877552</td>\n",
       "      <td>-0.042534</td>\n",
       "      <td>0.993670</td>\n",
       "      <td>-0.042534</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>contrast_0</th>\n",
       "      <td>-0.442675</td>\n",
       "      <td>-0.352584</td>\n",
       "      <td>-0.157039</td>\n",
       "      <td>-0.383369</td>\n",
       "      <td>0.161109</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.143428</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.150978</td>\n",
       "      <td>0.667826</td>\n",
       "      <td>-0.152576</td>\n",
       "      <td>0.667826</td>\n",
       "      <td>0.170531</td>\n",
       "      <td>0.766407</td>\n",
       "      <td>-0.142880</td>\n",
       "      <td>0.766407</td>\n",
       "      <td>0.162183</td>\n",
       "      <td>0.796541</td>\n",
       "      <td>-0.152188</td>\n",
       "      <td>0.796541</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>energy_45</th>\n",
       "      <td>0.270942</td>\n",
       "      <td>0.394040</td>\n",
       "      <td>0.441764</td>\n",
       "      <td>0.390352</td>\n",
       "      <td>0.995157</td>\n",
       "      <td>0.150978</td>\n",
       "      <td>-0.858710</td>\n",
       "      <td>0.150978</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.023490</td>\n",
       "      <td>-0.885269</td>\n",
       "      <td>-0.023490</td>\n",
       "      <td>0.994005</td>\n",
       "      <td>0.036755</td>\n",
       "      <td>-0.837969</td>\n",
       "      <td>0.036755</td>\n",
       "      <td>0.996557</td>\n",
       "      <td>0.130599</td>\n",
       "      <td>-0.853066</td>\n",
       "      <td>0.130599</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>homogenitas_45</th>\n",
       "      <td>-0.321727</td>\n",
       "      <td>-0.288278</td>\n",
       "      <td>-0.133460</td>\n",
       "      <td>-0.301258</td>\n",
       "      <td>0.006243</td>\n",
       "      <td>0.667826</td>\n",
       "      <td>-0.098443</td>\n",
       "      <td>0.667826</td>\n",
       "      <td>-0.023490</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.028852</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.019543</td>\n",
       "      <td>0.666507</td>\n",
       "      <td>-0.094378</td>\n",
       "      <td>0.666507</td>\n",
       "      <td>0.022159</td>\n",
       "      <td>0.185878</td>\n",
       "      <td>-0.159211</td>\n",
       "      <td>0.185878</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>entropy_45</th>\n",
       "      <td>-0.245946</td>\n",
       "      <td>-0.390909</td>\n",
       "      <td>-0.436815</td>\n",
       "      <td>-0.379773</td>\n",
       "      <td>-0.907828</td>\n",
       "      <td>-0.152576</td>\n",
       "      <td>0.992151</td>\n",
       "      <td>-0.152576</td>\n",
       "      <td>-0.885269</td>\n",
       "      <td>-0.028852</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.028852</td>\n",
       "      <td>-0.905517</td>\n",
       "      <td>-0.028938</td>\n",
       "      <td>0.985754</td>\n",
       "      <td>-0.028938</td>\n",
       "      <td>-0.896774</td>\n",
       "      <td>-0.097930</td>\n",
       "      <td>0.979777</td>\n",
       "      <td>-0.097930</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>contrast_45</th>\n",
       "      <td>-0.321727</td>\n",
       "      <td>-0.288278</td>\n",
       "      <td>-0.133460</td>\n",
       "      <td>-0.301258</td>\n",
       "      <td>0.006243</td>\n",
       "      <td>0.667826</td>\n",
       "      <td>-0.098443</td>\n",
       "      <td>0.667826</td>\n",
       "      <td>-0.023490</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.028852</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.019543</td>\n",
       "      <td>0.666507</td>\n",
       "      <td>-0.094378</td>\n",
       "      <td>0.666507</td>\n",
       "      <td>0.022159</td>\n",
       "      <td>0.185878</td>\n",
       "      <td>-0.159211</td>\n",
       "      <td>0.185878</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>energy_90</th>\n",
       "      <td>0.284467</td>\n",
       "      <td>0.415033</td>\n",
       "      <td>0.467696</td>\n",
       "      <td>0.411155</td>\n",
       "      <td>0.994848</td>\n",
       "      <td>0.170531</td>\n",
       "      <td>-0.885214</td>\n",
       "      <td>0.170531</td>\n",
       "      <td>0.994005</td>\n",
       "      <td>0.019543</td>\n",
       "      <td>-0.905517</td>\n",
       "      <td>0.019543</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.036989</td>\n",
       "      <td>-0.869930</td>\n",
       "      <td>0.036989</td>\n",
       "      <td>0.997294</td>\n",
       "      <td>0.111972</td>\n",
       "      <td>-0.884792</td>\n",
       "      <td>0.111972</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>homogenitas_90</th>\n",
       "      <td>-0.348829</td>\n",
       "      <td>-0.296224</td>\n",
       "      <td>-0.109673</td>\n",
       "      <td>-0.311978</td>\n",
       "      <td>0.054713</td>\n",
       "      <td>0.766407</td>\n",
       "      <td>-0.043106</td>\n",
       "      <td>0.766407</td>\n",
       "      <td>0.036755</td>\n",
       "      <td>0.666507</td>\n",
       "      <td>-0.028938</td>\n",
       "      <td>0.666507</td>\n",
       "      <td>0.036989</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.009020</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.045947</td>\n",
       "      <td>0.722782</td>\n",
       "      <td>-0.036136</td>\n",
       "      <td>0.722782</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>entropy_90</th>\n",
       "      <td>-0.233020</td>\n",
       "      <td>-0.397389</td>\n",
       "      <td>-0.429388</td>\n",
       "      <td>-0.378862</td>\n",
       "      <td>-0.865163</td>\n",
       "      <td>-0.142880</td>\n",
       "      <td>0.990924</td>\n",
       "      <td>-0.142880</td>\n",
       "      <td>-0.837969</td>\n",
       "      <td>-0.094378</td>\n",
       "      <td>0.985754</td>\n",
       "      <td>-0.094378</td>\n",
       "      <td>-0.869930</td>\n",
       "      <td>0.009020</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.009020</td>\n",
       "      <td>-0.856833</td>\n",
       "      <td>-0.022422</td>\n",
       "      <td>0.989236</td>\n",
       "      <td>-0.022422</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>contrast_90</th>\n",
       "      <td>-0.348829</td>\n",
       "      <td>-0.296224</td>\n",
       "      <td>-0.109673</td>\n",
       "      <td>-0.311978</td>\n",
       "      <td>0.054713</td>\n",
       "      <td>0.766407</td>\n",
       "      <td>-0.043106</td>\n",
       "      <td>0.766407</td>\n",
       "      <td>0.036755</td>\n",
       "      <td>0.666507</td>\n",
       "      <td>-0.028938</td>\n",
       "      <td>0.666507</td>\n",
       "      <td>0.036989</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.009020</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.045947</td>\n",
       "      <td>0.722782</td>\n",
       "      <td>-0.036136</td>\n",
       "      <td>0.722782</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>energy_135</th>\n",
       "      <td>0.281491</td>\n",
       "      <td>0.404104</td>\n",
       "      <td>0.458185</td>\n",
       "      <td>0.402113</td>\n",
       "      <td>0.998015</td>\n",
       "      <td>0.162183</td>\n",
       "      <td>-0.877552</td>\n",
       "      <td>0.162183</td>\n",
       "      <td>0.996557</td>\n",
       "      <td>0.022159</td>\n",
       "      <td>-0.896774</td>\n",
       "      <td>0.022159</td>\n",
       "      <td>0.997294</td>\n",
       "      <td>0.045947</td>\n",
       "      <td>-0.856833</td>\n",
       "      <td>0.045947</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.107529</td>\n",
       "      <td>-0.877061</td>\n",
       "      <td>0.107529</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>homogenitas_135</th>\n",
       "      <td>-0.424277</td>\n",
       "      <td>-0.331044</td>\n",
       "      <td>-0.196467</td>\n",
       "      <td>-0.368785</td>\n",
       "      <td>0.124720</td>\n",
       "      <td>0.796541</td>\n",
       "      <td>-0.042534</td>\n",
       "      <td>0.796541</td>\n",
       "      <td>0.130599</td>\n",
       "      <td>0.185878</td>\n",
       "      <td>-0.097930</td>\n",
       "      <td>0.185878</td>\n",
       "      <td>0.111972</td>\n",
       "      <td>0.722782</td>\n",
       "      <td>-0.022422</td>\n",
       "      <td>0.722782</td>\n",
       "      <td>0.107529</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.007203</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>entropy_135</th>\n",
       "      <td>-0.265119</td>\n",
       "      <td>-0.396607</td>\n",
       "      <td>-0.456696</td>\n",
       "      <td>-0.391940</td>\n",
       "      <td>-0.883550</td>\n",
       "      <td>-0.152188</td>\n",
       "      <td>0.993670</td>\n",
       "      <td>-0.152188</td>\n",
       "      <td>-0.853066</td>\n",
       "      <td>-0.159211</td>\n",
       "      <td>0.979777</td>\n",
       "      <td>-0.159211</td>\n",
       "      <td>-0.884792</td>\n",
       "      <td>-0.036136</td>\n",
       "      <td>0.989236</td>\n",
       "      <td>-0.036136</td>\n",
       "      <td>-0.877061</td>\n",
       "      <td>0.007203</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.007203</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>contrast_135</th>\n",
       "      <td>-0.424277</td>\n",
       "      <td>-0.331044</td>\n",
       "      <td>-0.196467</td>\n",
       "      <td>-0.368785</td>\n",
       "      <td>0.124720</td>\n",
       "      <td>0.796541</td>\n",
       "      <td>-0.042534</td>\n",
       "      <td>0.796541</td>\n",
       "      <td>0.130599</td>\n",
       "      <td>0.185878</td>\n",
       "      <td>-0.097930</td>\n",
       "      <td>0.185878</td>\n",
       "      <td>0.111972</td>\n",
       "      <td>0.722782</td>\n",
       "      <td>-0.022422</td>\n",
       "      <td>0.722782</td>\n",
       "      <td>0.107529</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.007203</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                    avg_R     avg_G     avg_B  avg_grayscale  energy_0  \\\n",
       "avg_R            1.000000  0.699021  0.835264       0.863648  0.285931   \n",
       "avg_G            0.699021  1.000000  0.864850       0.962579  0.405252   \n",
       "avg_B            0.835264  0.864850  1.000000       0.936858  0.461969   \n",
       "avg_grayscale    0.863648  0.962579  0.936858       1.000000  0.404714   \n",
       "energy_0         0.285931  0.405252  0.461969       0.404714  1.000000   \n",
       "homogenitas_0   -0.442675 -0.352584 -0.157039      -0.383369  0.161109   \n",
       "entropy_0       -0.258907 -0.396929 -0.450595      -0.389412 -0.888651   \n",
       "contrast_0      -0.442675 -0.352584 -0.157039      -0.383369  0.161109   \n",
       "energy_45        0.270942  0.394040  0.441764       0.390352  0.995157   \n",
       "homogenitas_45  -0.321727 -0.288278 -0.133460      -0.301258  0.006243   \n",
       "entropy_45      -0.245946 -0.390909 -0.436815      -0.379773 -0.907828   \n",
       "contrast_45     -0.321727 -0.288278 -0.133460      -0.301258  0.006243   \n",
       "energy_90        0.284467  0.415033  0.467696       0.411155  0.994848   \n",
       "homogenitas_90  -0.348829 -0.296224 -0.109673      -0.311978  0.054713   \n",
       "entropy_90      -0.233020 -0.397389 -0.429388      -0.378862 -0.865163   \n",
       "contrast_90     -0.348829 -0.296224 -0.109673      -0.311978  0.054713   \n",
       "energy_135       0.281491  0.404104  0.458185       0.402113  0.998015   \n",
       "homogenitas_135 -0.424277 -0.331044 -0.196467      -0.368785  0.124720   \n",
       "entropy_135     -0.265119 -0.396607 -0.456696      -0.391940 -0.883550   \n",
       "contrast_135    -0.424277 -0.331044 -0.196467      -0.368785  0.124720   \n",
       "\n",
       "                 homogenitas_0  entropy_0  contrast_0  energy_45  \\\n",
       "avg_R                -0.442675  -0.258907   -0.442675   0.270942   \n",
       "avg_G                -0.352584  -0.396929   -0.352584   0.394040   \n",
       "avg_B                -0.157039  -0.450595   -0.157039   0.441764   \n",
       "avg_grayscale        -0.383369  -0.389412   -0.383369   0.390352   \n",
       "energy_0              0.161109  -0.888651    0.161109   0.995157   \n",
       "homogenitas_0         1.000000  -0.143428    1.000000   0.150978   \n",
       "entropy_0            -0.143428   1.000000   -0.143428  -0.858710   \n",
       "contrast_0            1.000000  -0.143428    1.000000   0.150978   \n",
       "energy_45             0.150978  -0.858710    0.150978   1.000000   \n",
       "homogenitas_45        0.667826  -0.098443    0.667826  -0.023490   \n",
       "entropy_45           -0.152576   0.992151   -0.152576  -0.885269   \n",
       "contrast_45           0.667826  -0.098443    0.667826  -0.023490   \n",
       "energy_90             0.170531  -0.885214    0.170531   0.994005   \n",
       "homogenitas_90        0.766407  -0.043106    0.766407   0.036755   \n",
       "entropy_90           -0.142880   0.990924   -0.142880  -0.837969   \n",
       "contrast_90           0.766407  -0.043106    0.766407   0.036755   \n",
       "energy_135            0.162183  -0.877552    0.162183   0.996557   \n",
       "homogenitas_135       0.796541  -0.042534    0.796541   0.130599   \n",
       "entropy_135          -0.152188   0.993670   -0.152188  -0.853066   \n",
       "contrast_135          0.796541  -0.042534    0.796541   0.130599   \n",
       "\n",
       "                 homogenitas_45  entropy_45  contrast_45  energy_90  \\\n",
       "avg_R                 -0.321727   -0.245946    -0.321727   0.284467   \n",
       "avg_G                 -0.288278   -0.390909    -0.288278   0.415033   \n",
       "avg_B                 -0.133460   -0.436815    -0.133460   0.467696   \n",
       "avg_grayscale         -0.301258   -0.379773    -0.301258   0.411155   \n",
       "energy_0               0.006243   -0.907828     0.006243   0.994848   \n",
       "homogenitas_0          0.667826   -0.152576     0.667826   0.170531   \n",
       "entropy_0             -0.098443    0.992151    -0.098443  -0.885214   \n",
       "contrast_0             0.667826   -0.152576     0.667826   0.170531   \n",
       "energy_45             -0.023490   -0.885269    -0.023490   0.994005   \n",
       "homogenitas_45         1.000000   -0.028852     1.000000   0.019543   \n",
       "entropy_45            -0.028852    1.000000    -0.028852  -0.905517   \n",
       "contrast_45            1.000000   -0.028852     1.000000   0.019543   \n",
       "energy_90              0.019543   -0.905517     0.019543   1.000000   \n",
       "homogenitas_90         0.666507   -0.028938     0.666507   0.036989   \n",
       "entropy_90            -0.094378    0.985754    -0.094378  -0.869930   \n",
       "contrast_90            0.666507   -0.028938     0.666507   0.036989   \n",
       "energy_135             0.022159   -0.896774     0.022159   0.997294   \n",
       "homogenitas_135        0.185878   -0.097930     0.185878   0.111972   \n",
       "entropy_135           -0.159211    0.979777    -0.159211  -0.884792   \n",
       "contrast_135           0.185878   -0.097930     0.185878   0.111972   \n",
       "\n",
       "                 homogenitas_90  entropy_90  contrast_90  energy_135  \\\n",
       "avg_R                 -0.348829   -0.233020    -0.348829    0.281491   \n",
       "avg_G                 -0.296224   -0.397389    -0.296224    0.404104   \n",
       "avg_B                 -0.109673   -0.429388    -0.109673    0.458185   \n",
       "avg_grayscale         -0.311978   -0.378862    -0.311978    0.402113   \n",
       "energy_0               0.054713   -0.865163     0.054713    0.998015   \n",
       "homogenitas_0          0.766407   -0.142880     0.766407    0.162183   \n",
       "entropy_0             -0.043106    0.990924    -0.043106   -0.877552   \n",
       "contrast_0             0.766407   -0.142880     0.766407    0.162183   \n",
       "energy_45              0.036755   -0.837969     0.036755    0.996557   \n",
       "homogenitas_45         0.666507   -0.094378     0.666507    0.022159   \n",
       "entropy_45            -0.028938    0.985754    -0.028938   -0.896774   \n",
       "contrast_45            0.666507   -0.094378     0.666507    0.022159   \n",
       "energy_90              0.036989   -0.869930     0.036989    0.997294   \n",
       "homogenitas_90         1.000000    0.009020     1.000000    0.045947   \n",
       "entropy_90             0.009020    1.000000     0.009020   -0.856833   \n",
       "contrast_90            1.000000    0.009020     1.000000    0.045947   \n",
       "energy_135             0.045947   -0.856833     0.045947    1.000000   \n",
       "homogenitas_135        0.722782   -0.022422     0.722782    0.107529   \n",
       "entropy_135           -0.036136    0.989236    -0.036136   -0.877061   \n",
       "contrast_135           0.722782   -0.022422     0.722782    0.107529   \n",
       "\n",
       "                 homogenitas_135  entropy_135  contrast_135  \n",
       "avg_R                  -0.424277    -0.265119     -0.424277  \n",
       "avg_G                  -0.331044    -0.396607     -0.331044  \n",
       "avg_B                  -0.196467    -0.456696     -0.196467  \n",
       "avg_grayscale          -0.368785    -0.391940     -0.368785  \n",
       "energy_0                0.124720    -0.883550      0.124720  \n",
       "homogenitas_0           0.796541    -0.152188      0.796541  \n",
       "entropy_0              -0.042534     0.993670     -0.042534  \n",
       "contrast_0              0.796541    -0.152188      0.796541  \n",
       "energy_45               0.130599    -0.853066      0.130599  \n",
       "homogenitas_45          0.185878    -0.159211      0.185878  \n",
       "entropy_45             -0.097930     0.979777     -0.097930  \n",
       "contrast_45             0.185878    -0.159211      0.185878  \n",
       "energy_90               0.111972    -0.884792      0.111972  \n",
       "homogenitas_90          0.722782    -0.036136      0.722782  \n",
       "entropy_90             -0.022422     0.989236     -0.022422  \n",
       "contrast_90             0.722782    -0.036136      0.722782  \n",
       "energy_135              0.107529    -0.877061      0.107529  \n",
       "homogenitas_135         1.000000     0.007203      1.000000  \n",
       "entropy_135             0.007203     1.000000      0.007203  \n",
       "contrast_135            1.000000     0.007203      1.000000  "
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "kakao_correlation = kakao.drop(columns=['file']).select_dtypes(include=[float, int]).corr()\n",
    "kakao_correlation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x1000 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Filter hanya kolom numerik\n",
    "numeric_data = kakao.select_dtypes(include=[float, int])\n",
    "\n",
    "# Buat heatmap menggunakan data numerik\n",
    "f, axis = plt.subplots(figsize=(10, 10))\n",
    "sns.heatmap(numeric_data.corr(), annot=True, fmt='.2f', ax=axis, cmap='coolwarm')\n",
    "\n",
    "# Tampilkan heatmap\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = kakao[['energy_0', 'homogenitas_0', 'entropy_0', 'contrast_0', \n",
    "            'energy_45', 'homogenitas_45', 'entropy_45', 'contrast_45', \n",
    "            'energy_90', 'homogenitas_90', 'entropy_90', 'contrast_90', \n",
    "            'energy_135', 'homogenitas_135', 'entropy_135', 'contrast_135']].to_numpy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[3.96690508e-02 1.18391673e+03 5.98363636e+00 1.18291673e+03\n",
      "  3.72114507e-02 8.29537634e+02 5.96236594e+00 8.28537634e+02\n",
      "  4.39674568e-02 7.34822173e+02 5.86734900e+00 7.33822173e+02\n",
      "  3.53435339e-02 2.46651075e+03 6.15960073e+00 2.46551075e+03]\n",
      " [6.67301109e-02 7.56364591e+02 5.59301410e+00 7.55364591e+02\n",
      "  5.77231413e-02 5.34014593e+02 5.63175955e+00 5.33014593e+02\n",
      "  6.09058890e-02 7.21136905e+02 5.65327367e+00 7.20136905e+02\n",
      "  5.55590950e-02 1.80882258e+03 5.83191440e+00 1.80782258e+03]\n",
      " [1.23108422e-02 7.60389347e+02 6.53643647e+00 7.59389347e+02\n",
      "  9.32572127e-03 1.50263057e+03 6.69586648e+00 1.50163057e+03\n",
      "  1.15150227e-02 7.22642113e+02 6.50334370e+00 7.21642113e+02\n",
      "  9.67730137e-03 1.00856989e+03 6.59916958e+00 1.00756989e+03]\n",
      " [1.55130681e-02 1.28438035e+03 6.71077214e+00 1.28338035e+03\n",
      "  1.24179745e-02 1.83527112e+03 6.78881428e+00 1.83427112e+03\n",
      "  1.45712093e-02 1.42728125e+03 6.72416559e+00 1.42628125e+03\n",
      "  1.16938728e-02 2.55779877e+03 6.83327020e+00 2.55679877e+03]\n",
      " [6.92924544e-03 1.11204651e+03 6.94833362e+00 1.11104651e+03\n",
      "  5.33475617e-03 1.52852995e+03 7.03761192e+00 1.52752995e+03\n",
      "  7.12934914e-03 8.51715030e+02 6.88601274e+00 8.50715030e+02\n",
      "  5.61613823e-03 1.65231106e+03 7.00633266e+00 1.65131106e+03]\n",
      " [2.30492732e-02 9.04736684e+02 6.10161155e+00 9.03736684e+02\n",
      "  1.86192930e-02 1.01527343e+03 6.11632182e+00 1.01427343e+03\n",
      "  2.10616962e-02 6.47441964e+02 5.96284230e+00 6.46441964e+02\n",
      "  1.70404270e-02 1.65419355e+03 6.30850784e+00 1.65319355e+03]\n",
      " [1.16307209e-02 7.74384096e+02 6.81311589e+00 7.73384096e+02\n",
      "  9.69883271e-03 9.92482335e+02 6.86698847e+00 9.91482335e+02\n",
      "  1.35287676e-02 3.87159226e+02 6.62402401e+00 3.86159226e+02\n",
      "  9.86960861e-03 1.00980031e+03 6.87171107e+00 1.00880031e+03]\n",
      " [1.19773942e-02 5.30628657e+02 6.69612861e+00 5.29628657e+02\n",
      "  9.89733389e-03 7.24573733e+02 6.76703376e+00 7.23573733e+02\n",
      "  1.09575406e-02 4.87221726e+02 6.67495805e+00 4.86221726e+02\n",
      "  8.84908247e-03 1.00840323e+03 6.87701008e+00 1.00740323e+03]\n",
      " [9.14913650e-03 1.30057089e+03 6.89017481e+00 1.29957089e+03\n",
      "  6.26856709e-03 1.70731106e+03 6.98992687e+00 1.70631106e+03\n",
      "  7.35881918e-03 7.96486607e+02 6.87619973e+00 7.95486607e+02\n",
      "  6.69417958e-03 1.75057066e+03 7.00064488e+00 1.74957066e+03]\n",
      " [6.03723699e-03 7.62009002e+02 7.02578108e+00 7.61009002e+02\n",
      "  4.97698212e-03 7.28920123e+02 7.01962542e+00 7.27920123e+02\n",
      "  5.67696154e-03 6.97389881e+02 6.97809913e+00 6.96389881e+02\n",
      "  4.59266259e-03 1.64232335e+03 7.13332269e+00 1.64132335e+03]\n",
      " [1.34667951e-02 8.43828957e+02 6.56635271e+00 8.42828957e+02\n",
      "  1.09458803e-02 1.34980722e+03 6.68119778e+00 1.34880722e+03\n",
      "  1.43370336e-02 5.42686012e+02 6.41848780e+00 5.41686012e+02\n",
      "  1.09559086e-02 9.85562212e+02 6.59757147e+00 9.84562212e+02]\n",
      " [1.01311900e-02 8.25649662e+02 6.77372225e+00 8.24649662e+02\n",
      "  7.98104535e-03 1.05127496e+03 6.84167897e+00 1.05027496e+03\n",
      "  1.07183824e-02 5.54941220e+02 6.68781897e+00 5.53941220e+02\n",
      "  8.07719897e-03 1.20152151e+03 6.84985490e+00 1.20052151e+03]\n",
      " [1.01021504e-01 5.49151538e+02 5.63832663e+00 5.48151538e+02\n",
      "  1.03409088e-01 4.94325653e+02 5.57681419e+00 4.93325653e+02\n",
      "  1.04137049e-01 3.50770833e+02 5.57078892e+00 3.49770833e+02\n",
      "  9.32973259e-02 8.91295699e+02 5.73694446e+00 8.90295699e+02]\n",
      " [6.16780227e-03 8.60296324e+02 7.20770143e+00 8.59296324e+02\n",
      "  4.86962041e-03 1.03409217e+03 7.25241719e+00 1.03309217e+03\n",
      "  5.63903947e-03 5.96430060e+02 7.16866322e+00 5.95430060e+02\n",
      "  4.67790307e-03 1.27786406e+03 7.27676064e+00 1.27686406e+03]\n",
      " [2.71058012e-02 5.97040510e+02 6.33339668e+00 5.96040510e+02\n",
      "  2.18970696e-02 9.92242704e+02 6.44685107e+00 9.91242704e+02\n",
      "  2.77830370e-02 4.06403274e+02 6.09791502e+00 4.05403274e+02\n",
      "  2.31332040e-02 7.72687404e+02 6.40911855e+00 7.71687404e+02]\n",
      " [5.41164924e-02 1.14692573e+03 5.68106314e+00 1.14592573e+03\n",
      "  4.78246276e-02 1.87694624e+03 5.79580683e+00 1.87594624e+03\n",
      "  6.07276276e-02 5.59707589e+02 5.54747025e+00 5.58707589e+02\n",
      "  4.85637717e-02 9.68721198e+02 5.71860148e+00 9.67721198e+02]\n",
      " [2.75565891e-02 5.18582896e+02 6.21899538e+00 5.17582896e+02\n",
      "  2.25710298e-02 5.03962366e+02 6.25172626e+00 5.02962366e+02\n",
      "  2.66367940e-02 3.59756696e+02 6.11350765e+00 3.58756696e+02\n",
      "  2.19221403e-02 9.91268049e+02 6.37092185e+00 9.90268049e+02]\n",
      " [1.62857669e-02 1.61553563e+03 5.89378601e+00 1.61453563e+03\n",
      "  1.27618859e-02 2.85831490e+03 6.02781541e+00 2.85731490e+03\n",
      "  1.67980929e-02 1.10766369e+03 5.69833104e+00 1.10666369e+03\n",
      "  1.35387835e-02 1.87430952e+03 5.93332196e+00 1.87330952e+03]\n",
      " [1.30326092e-02 7.26875469e+02 6.50660053e+00 7.25875469e+02\n",
      "  9.91149148e-03 1.16714823e+03 6.68902737e+00 1.16614823e+03\n",
      "  1.31102408e-02 4.98614583e+02 6.41936456e+00 4.97614583e+02\n",
      "  1.03176373e-02 8.94302611e+02 6.60907051e+00 8.93302611e+02]\n",
      " [8.62068480e-03 2.91342086e+02 6.59403239e+00 2.90342086e+02\n",
      "  7.12244662e-03 4.60836406e+02 6.69249283e+00 4.59836406e+02\n",
      "  1.11288819e-02 2.09236607e+02 6.39943824e+00 2.08236607e+02\n",
      "  7.36489532e-03 3.51430876e+02 6.67683835e+00 3.50430876e+02]\n",
      " [1.24667326e-02 5.32964741e+02 6.57316755e+00 5.31964741e+02\n",
      "  1.00701744e-02 7.68644393e+02 6.69048768e+00 7.67644393e+02\n",
      "  1.28240261e-02 5.06792411e+02 6.45236673e+00 5.05792411e+02\n",
      "  9.10067461e-03 1.06001536e+03 6.74056371e+00 1.05901536e+03]\n",
      " [8.83904397e-03 9.44428357e+02 6.92048216e+00 9.43428357e+02\n",
      "  6.85433730e-03 1.96203149e+03 7.06099168e+00 1.96103149e+03\n",
      "  9.20260682e-03 1.33357961e+03 6.93235136e+00 1.33257961e+03\n",
      "  6.93161413e-03 1.82629263e+03 7.03200869e+00 1.82529263e+03]\n",
      " [6.51242143e-02 1.24519730e+03 5.64403851e+00 1.24419730e+03\n",
      "  5.85080026e-02 2.45550922e+03 5.80686390e+00 2.45450922e+03\n",
      "  7.05953931e-02 9.16709821e+02 5.53686226e+00 9.15709821e+02\n",
      "  5.97966380e-02 1.11484332e+03 5.67792263e+00 1.11384332e+03]\n",
      " [1.27523441e-02 1.58683496e+03 6.65957540e+00 1.58583496e+03\n",
      "  1.10933551e-02 1.77926267e+03 6.74080769e+00 1.77826267e+03\n",
      "  1.42769673e-02 7.87718750e+02 6.53643695e+00 7.86718750e+02\n",
      "  1.03117383e-02 2.34719201e+03 6.79054267e+00 2.34619201e+03]\n",
      " [3.19122354e-02 1.40642386e+03 6.23372384e+00 1.40542386e+03\n",
      "  2.74424199e-02 2.12767819e+03 6.35398345e+00 2.12667819e+03\n",
      "  3.51692598e-02 8.25988839e+02 6.11366695e+00 8.24988839e+02\n",
      "  3.01243980e-02 1.54958065e+03 6.25545563e+00 1.54858065e+03]\n",
      " [9.78142135e-03 1.12426407e+03 6.89741887e+00 1.12326407e+03\n",
      "  7.11300823e-03 1.68415591e+03 6.98848243e+00 1.68315591e+03\n",
      "  1.06630217e-02 6.57297619e+02 6.77609391e+00 6.56297619e+02\n",
      "  8.05065349e-03 1.40849846e+03 6.96615363e+00 1.40749846e+03]\n",
      " [3.70000602e-02 1.36784471e+03 6.24906416e+00 1.36684471e+03\n",
      "  3.09723785e-02 2.59963594e+03 6.39251322e+00 2.59863594e+03\n",
      "  3.69873047e-02 1.16875893e+03 6.19095098e+00 1.16775893e+03\n",
      "  3.35862233e-02 1.73830108e+03 6.28800708e+00 1.73730108e+03]\n",
      " [1.32813586e-02 9.69909227e+02 6.72464001e+00 9.68909227e+02\n",
      "  1.16991819e-02 1.07130338e+03 6.78023915e+00 1.07030338e+03\n",
      "  1.51608006e-02 5.04443452e+02 6.57913330e+00 5.03443452e+02\n",
      "  1.09302479e-02 1.37796851e+03 6.83635205e+00 1.37696851e+03]\n",
      " [1.14860861e-02 1.49054539e+03 6.89404846e+00 1.48954539e+03\n",
      "  9.69352361e-03 2.40440553e+03 6.95742879e+00 2.40340553e+03\n",
      "  1.31935587e-02 8.29593006e+02 6.73497139e+00 8.28593006e+02\n",
      "  1.02368211e-02 1.49379800e+03 6.87665531e+00 1.49279800e+03]\n",
      " [4.97554996e-03 1.26518680e+03 6.96095062e+00 1.26418680e+03\n",
      "  4.04228636e-03 2.21246313e+03 7.08888943e+00 2.21146313e+03\n",
      "  5.69024810e-03 1.10041741e+03 6.89442449e+00 1.09941741e+03\n",
      "  3.97533276e-03 2.05957373e+03 7.07638077e+00 2.05857373e+03]\n",
      " [1.77335219e-02 1.24648462e+03 6.69332132e+00 1.24548462e+03\n",
      "  1.59883412e-02 1.12658065e+03 6.69855019e+00 1.12558065e+03\n",
      "  2.04604791e-02 7.04846726e+02 6.55076412e+00 7.03846726e+02\n",
      "  1.50468616e-02 2.16991782e+03 6.81616027e+00 2.16891782e+03]\n",
      " [1.77450589e-02 2.00975769e+03 6.73125964e+00 2.00875769e+03\n",
      "  1.51017223e-02 2.11419048e+03 6.77770841e+00 2.11319048e+03\n",
      "  1.81967807e-02 1.28168304e+03 6.67861032e+00 1.28068304e+03\n",
      "  1.38304888e-02 3.12192243e+03 6.85294927e+00 3.12092243e+03]\n",
      " [2.18331027e-02 1.36554389e+03 6.64925914e+00 1.36454389e+03\n",
      "  1.93696452e-02 1.44435868e+03 6.68340650e+00 1.44335868e+03\n",
      "  2.22937482e-02 1.11381548e+03 6.57882275e+00 1.11281548e+03\n",
      "  1.79993086e-02 2.40064439e+03 6.76690763e+00 2.39964439e+03]\n",
      " [9.61219300e-02 1.67475169e+03 5.33075115e+00 1.67375169e+03\n",
      "  8.64394492e-02 1.12411751e+03 5.34535690e+00 1.12311751e+03\n",
      "  9.40276338e-02 9.61043155e+02 5.25768765e+00 9.60043155e+02\n",
      "  8.35108931e-02 3.27822657e+03 5.49931317e+00 3.27722657e+03]\n",
      " [2.08524562e-02 1.26538785e+03 6.60070494e+00 1.26438785e+03\n",
      "  1.66328064e-02 1.66131260e+03 6.68123740e+00 1.66031260e+03\n",
      "  2.08535400e-02 1.14944717e+03 6.52698990e+00 1.14844717e+03\n",
      "  1.57806966e-02 2.12941628e+03 6.71446580e+00 2.12841628e+03]\n",
      " [2.91214026e-02 9.37651913e+02 6.28320914e+00 9.36651913e+02\n",
      "  2.44590032e-02 1.38931874e+03 6.40573450e+00 1.38831874e+03\n",
      "  3.51263552e-02 5.74927083e+02 6.14293718e+00 5.73927083e+02\n",
      "  2.54871980e-02 9.35368664e+02 6.33943652e+00 9.34368664e+02]\n",
      " [3.07703520e-02 7.84251313e+02 5.98220299e+00 7.83251313e+02\n",
      "  2.27143754e-02 1.35730261e+03 6.17893595e+00 1.35630261e+03\n",
      "  2.77124522e-02 6.67101190e+02 5.99786846e+00 6.66101190e+02\n",
      "  2.43307000e-02 1.02023886e+03 6.12144542e+00 1.01923886e+03]\n",
      " [3.58398865e-02 1.60244186e+03 6.31286799e+00 1.60144186e+03\n",
      "  3.28863075e-02 1.17116820e+03 6.29251847e+00 1.17016820e+03\n",
      "  3.78022140e-02 9.92157738e+02 6.21486696e+00 9.91157738e+02\n",
      "  3.19439430e-02 3.01678341e+03 6.44974438e+00 3.01578341e+03]\n",
      " [1.68443274e-02 1.76543061e+03 6.60179903e+00 1.76443061e+03\n",
      "  1.42139235e-02 2.31373195e+03 6.71361349e+00 2.31273195e+03\n",
      "  1.78712598e-02 1.26982292e+03 6.53875471e+00 1.26882292e+03\n",
      "  1.39947758e-02 2.79166667e+03 6.72803087e+00 2.79066667e+03]\n",
      " [4.91417866e-02 1.59809227e+03 6.07235440e+00 1.59709227e+03\n",
      "  4.34865066e-02 1.19987020e+03 6.09404681e+00 1.19887020e+03\n",
      "  4.72982324e-02 1.12585937e+03 6.06272358e+00 1.12485937e+03\n",
      "  4.11401814e-02 3.05022350e+03 6.22935848e+00 3.04922350e+03]\n",
      " [6.39966818e-02 1.12313128e+03 5.61650979e+00 1.12213128e+03\n",
      "  5.54980404e-02 2.28998233e+03 5.77721566e+00 2.28898233e+03\n",
      "  6.25282339e-02 8.57504464e+02 5.59813768e+00 8.56504464e+02\n",
      "  5.74048905e-02 8.16122120e+02 5.63479976e+00 8.15122120e+02]\n",
      " [5.34839261e-03 1.05051163e+03 6.89503745e+00 1.04951163e+03\n",
      "  4.55107468e-03 1.56248310e+03 6.97338914e+00 1.56148310e+03\n",
      "  5.20141325e-03 9.30510417e+02 6.90247553e+00 9.29510417e+02\n",
      "  4.61389898e-03 1.47327880e+03 6.97572911e+00 1.47227880e+03]\n",
      " [4.49999972e-03 7.85940735e+02 7.22778926e+00 7.84940735e+02\n",
      "  3.60163143e-03 9.51026114e+02 7.29179993e+00 9.50026114e+02\n",
      "  4.26055839e-03 5.15743304e+02 7.15130853e+00 5.14743304e+02\n",
      "  3.78420532e-03 1.22824270e+03 7.29861326e+00 1.22724270e+03]\n",
      " [8.91586362e-03 7.46317329e+02 6.76636648e+00 7.45317329e+02\n",
      "  7.49555806e-03 1.10698003e+03 6.85462363e+00 1.10598003e+03\n",
      "  9.94720805e-03 6.79436756e+02 6.73995623e+00 6.78436756e+02\n",
      "  6.64492297e-03 1.18585330e+03 6.89935064e+00 1.18485330e+03]\n",
      " [1.00726607e-02 7.58542386e+02 6.71500208e+00 7.57542386e+02\n",
      "  8.76797129e-03 9.22161290e+02 6.76862696e+00 9.21161290e+02\n",
      "  9.98457651e-03 7.00232887e+02 6.67033636e+00 6.99232887e+02\n",
      "  7.66397437e-03 1.48182642e+03 6.87482665e+00 1.48082642e+03]\n",
      " [1.49809583e-02 1.12580570e+03 6.65341880e+00 1.12480570e+03\n",
      "  1.17357557e-02 1.25860445e+03 6.74057137e+00 1.25760445e+03\n",
      "  1.57996630e-02 6.13310268e+02 6.53786411e+00 6.12310268e+02\n",
      "  1.20610853e-02 1.70697158e+03 6.76687427e+00 1.70597158e+03]\n",
      " [2.38571458e-02 1.19131883e+03 6.29459153e+00 1.19031883e+03\n",
      "  1.98344860e-02 2.15049539e+03 6.43289239e+00 2.14949539e+03\n",
      "  2.67248175e-02 7.88349702e+02 6.17523256e+00 7.87349702e+02\n",
      "  2.07954323e-02 1.20751767e+03 6.34645698e+00 1.20651767e+03]\n",
      " [6.93571743e-03 9.17280570e+02 6.94591802e+00 9.16280570e+02\n",
      "  6.04086588e-03 1.15799616e+03 6.99123188e+00 1.15699616e+03\n",
      "  8.25261745e-03 5.72876488e+02 6.75734297e+00 5.71876488e+02\n",
      "  5.77954040e-03 1.44540937e+03 6.99084268e+00 1.44440937e+03]\n",
      " [3.87601589e-02 9.55087772e+02 6.08950136e+00 9.54087772e+02\n",
      "  3.15277689e-02 1.98355453e+03 6.29893525e+00 1.98255453e+03\n",
      "  3.72021041e-02 8.71627232e+02 6.09947087e+00 8.70627232e+02\n",
      "  3.27173013e-02 9.86917051e+02 6.13772584e+00 9.85917051e+02]\n",
      " [4.19834891e-03 1.04964066e+03 7.10291155e+00 1.04864066e+03\n",
      "  3.63791025e-03 1.41179109e+03 7.15697992e+00 1.41079109e+03\n",
      "  4.62483170e-03 8.51116815e+02 7.05681407e+00 8.50116815e+02\n",
      "  3.36065748e-03 1.73800998e+03 7.22411561e+00 1.73700998e+03]\n",
      " [8.75378259e-03 8.65226557e+02 6.92141738e+00 8.64226557e+02\n",
      "  6.53756126e-03 1.10225730e+03 7.03434015e+00 1.10125730e+03\n",
      "  8.28057460e-03 7.76187500e+02 6.93724977e+00 7.75187500e+02\n",
      "  6.10015078e-03 1.63228111e+03 7.07117463e+00 1.63128111e+03]\n",
      " [1.48982294e-02 7.36834959e+02 6.63938057e+00 7.35834959e+02\n",
      "  1.36877332e-02 6.85789555e+02 6.65377062e+00 6.84789555e+02\n",
      "  1.81234278e-02 4.53901042e+02 6.52549400e+00 4.52901042e+02\n",
      "  1.24380311e-02 1.25260138e+03 6.72872119e+00 1.25160138e+03]\n",
      " [2.89520054e-02 9.69356339e+02 6.39860209e+00 9.68356339e+02\n",
      "  2.58222609e-02 8.81739631e+02 6.39838469e+00 8.80739631e+02\n",
      "  3.16508114e-02 7.08063988e+02 6.30773151e+00 7.07063988e+02\n",
      "  2.56016385e-02 1.80268280e+03 6.50977026e+00 1.80168280e+03]\n",
      " [2.24268370e-03 1.12379895e+03 7.33490797e+00 1.12279895e+03\n",
      "  1.82160967e-03 1.60827112e+03 7.38213042e+00 1.60727112e+03\n",
      "  2.35532038e-03 6.72268601e+02 7.23299587e+00 6.71268601e+02\n",
      "  1.84579555e-03 1.50288863e+03 7.36098277e+00 1.50188863e+03]\n",
      " [9.05571479e-03 8.62482371e+02 6.94581351e+00 8.61482371e+02\n",
      "  6.81215948e-03 1.64156068e+03 7.08351325e+00 1.64056068e+03\n",
      "  9.58625638e-03 6.86680060e+02 6.81584026e+00 6.85680060e+02\n",
      "  7.50470150e-03 1.03774040e+03 7.01211284e+00 1.03674040e+03]\n",
      " [1.10955158e-02 9.79285071e+02 6.76228883e+00 9.78285071e+02\n",
      "  9.13016958e-03 1.22890015e+03 6.83052232e+00 1.22790015e+03\n",
      "  1.16525940e-02 6.08111607e+02 6.70041747e+00 6.07111607e+02\n",
      "  8.66296918e-03 1.36322657e+03 6.85431206e+00 1.36222657e+03]\n",
      " [1.77999301e-02 8.67516129e+02 6.63035314e+00 8.66516129e+02\n",
      "  1.41457901e-02 1.49703763e+03 6.75664690e+00 1.49603763e+03\n",
      "  1.85156582e-02 5.98584077e+02 6.58849042e+00 5.97584077e+02\n",
      "  1.57927895e-02 1.11445929e+03 6.70592553e+00 1.11345929e+03]\n",
      " [1.29909634e-02 8.06343586e+02 6.68935357e+00 8.05343586e+02\n",
      "  9.62244072e-03 1.29033026e+03 6.82842325e+00 1.28933026e+03\n",
      "  1.38875049e-02 6.17728423e+02 6.65020856e+00 6.16728423e+02\n",
      "  1.09343772e-02 9.74344854e+02 6.72927163e+00 9.73344854e+02]\n",
      " [4.09142045e-03 9.75556639e+02 7.11037450e+00 9.74556639e+02\n",
      "  3.05774408e-03 1.37450384e+03 7.19261231e+00 1.37350384e+03\n",
      "  3.49824174e-03 7.42747024e+02 7.11100389e+00 7.41747024e+02\n",
      "  2.76780848e-03 1.51947081e+03 7.22945864e+00 1.51847081e+03]\n",
      " [2.46281563e-02 6.80713428e+02 6.43282166e+00 6.79713428e+02\n",
      "  1.76663104e-02 1.34207834e+03 6.59186034e+00 1.34107834e+03\n",
      "  2.02573054e-02 6.76130208e+02 6.44374877e+00 6.75130208e+02\n",
      "  1.92398673e-02 8.69179724e+02 6.52946213e+00 8.68179724e+02]\n",
      " [3.98103089e-02 1.07385521e+03 6.09102263e+00 1.07285521e+03\n",
      "  3.30119561e-02 2.00140937e+03 6.25768308e+00 2.00040937e+03\n",
      "  4.11080773e-02 7.32640625e+02 6.05993555e+00 7.31640625e+02\n",
      "  3.62434256e-02 7.60471582e+02 6.07658551e+00 7.59471582e+02]\n",
      " [2.66983475e-03 8.08151538e+02 7.37143835e+00 8.07151538e+02\n",
      "  2.10476143e-03 1.14894240e+03 7.39250955e+00 1.14794240e+03\n",
      "  2.78768734e-03 6.74763393e+02 7.32133956e+00 6.73763393e+02\n",
      "  1.99238558e-03 1.24630799e+03 7.42675253e+00 1.24530799e+03]]\n"
     ]
    }
   ],
   "source": [
    "print(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "label = kakao['label'].to_numpy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Healthy', 'Monilia', 'Phytophthora'], dtype=object)"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(kakao['label'].unique())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Model KNN"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split   \n",
    "train_classx, test_classx, train_classy, test_classy = train_test_split(data, label, test_size=0.2, random_state=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([3.96690508e-02, 1.18391673e+03, 5.98363636e+00, 1.18291673e+03,\n",
       "       3.72114507e-02, 8.29537634e+02, 5.96236594e+00, 8.28537634e+02,\n",
       "       4.39674568e-02, 7.34822173e+02, 5.86734900e+00, 7.33822173e+02,\n",
       "       3.53435339e-02, 2.46651075e+03, 6.15960073e+00, 2.46551075e+03])"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7741935483870968"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "neigh = KNeighborsClassifier(n_neighbors=3)\n",
    "neigh.fit(data, label)\n",
    "neigh.score(data, label)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Healthy' 'Monilia' 'Monilia' 'Phytophthora' 'Phytophthora' 'Healthy'\n",
      " 'Healthy' 'Phytophthora' 'Healthy' 'Phytophthora' 'Monilia' 'Healthy'\n",
      " 'Healthy']\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(13,)"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pred_class = neigh.predict(test_classx)\n",
    "print(pred_class)\n",
    "pred_class.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "model accuracy knn : 84.61538461538461 %\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import accuracy_score\n",
    "score = accuracy_score(test_classy, pred_class)\n",
    "print(\"model accuracy knn :\", score*100, \"%\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "     Healthy       0.67      1.00      0.80         4\n",
      "     Monilia       1.00      0.60      0.75         5\n",
      "Phytophthora       1.00      1.00      1.00         4\n",
      "\n",
      "    accuracy                           0.85        13\n",
      "   macro avg       0.89      0.87      0.85        13\n",
      "weighted avg       0.90      0.85      0.84        13\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from sklearn import metrics\n",
    "print(metrics.classification_report(test_classy, pred_class))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = sns.stripplot(x=test_classy)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x1000 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Daftar label untuk menggantikan angka\n",
    "labels = ['Healthy', 'Monilia', 'Phytophthora']\n",
    "\n",
    "# Confusion Matrix\n",
    "from sklearn.metrics import confusion_matrix\n",
    "cm = confusion_matrix(test_classy, pred_class)\n",
    "\n",
    "# Visualisasi Confusion Matrix dengan label kustom\n",
    "plt.figure(figsize=(10, 10))\n",
    "sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', xticklabels=labels, yticklabels=labels)\n",
    "plt.xlabel('Predicted')\n",
    "plt.ylabel('Actual')\n",
    "plt.title('Confusion Matrix')\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Save Model\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['model_knn.pkl']"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import joblib\n",
    "joblib.dump(neigh, 'model_knn.pkl')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Test Model\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "\n",
    "# Misalkan model sudah dilatih\n",
    "model_knn = KNeighborsClassifier(n_neighbors=3)\n",
    "model_knn.fit(data, label)\n",
    "\n",
    "# Simpan model ke file\n",
    "with open('model_knn.pkl', 'wb') as model_file:\n",
    "    pickle.dump(model_knn, model_file)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "\n",
    "# Muat model dari file\n",
    "with open('model_knn.pkl', 'rb') as model_file:\n",
    "    model_knn = pickle.load(model_file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'sklearn.neighbors._classification.KNeighborsClassifier'>\n"
     ]
    }
   ],
   "source": [
    "print(type(model_knn))  # Pastikan ini adalah KNeighborsClassifier"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Tes Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = joblib.load('model_knn.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Prediksi label untuk gambar baru: Healthy\n"
     ]
    }
   ],
   "source": [
    "import cv2 as cv\n",
    "import numpy as np\n",
    "import joblib\n",
    "import math\n",
    "\n",
    "# Fungsi preprocessing gambar\n",
    "def preprocess_image(image_path):\n",
    "    # Baca gambar\n",
    "    img = cv.imread(image_path)\n",
    "    \n",
    "    # Resize gambar ke ukuran yang sama dengan yang digunakan saat training\n",
    "    resized_img = cv.resize(img, (32, 43))\n",
    "    \n",
    "    # Konversi gambar ke grayscale\n",
    "    gray_img = cv.cvtColor(resized_img, cv.COLOR_BGR2GRAY)\n",
    "    \n",
    "    # Fungsi GLCM untuk derajat yang berbeda\n",
    "    def glcm(img, angle):\n",
    "        max_val = np.max(img)\n",
    "        imgTmp = np.zeros([max_val+1, max_val+1])\n",
    "        for i in range(len(img)-1):\n",
    "            for j in range(len(img[i])-1):\n",
    "                if angle == 0:\n",
    "                    imgTmp[img[i][j], img[i,j+1]] += 1\n",
    "                elif angle == 45:\n",
    "                    if i > 0 and j < len(img[i])-1:\n",
    "                        imgTmp[img[i][j], img[i-1,j+1]] += 1\n",
    "                elif angle == 90:\n",
    "                    if i > 0:\n",
    "                        imgTmp[img[i][j], img[i-1,j]] += 1\n",
    "                elif angle == 135:\n",
    "                    if i > 0 and j > 0:\n",
    "                        imgTmp[img[i][j], img[i-1,j-1]] += 1\n",
    "        transpos = np.transpose(imgTmp)\n",
    "        data = imgTmp + transpos\n",
    "        data /= np.sum(data)\n",
    "        return data\n",
    "\n",
    "    # Fungsi untuk menghitung fitur\n",
    "    def contrast(data):\n",
    "        contrast_val = 0\n",
    "        for i in range(len(data)):\n",
    "            for j in range(len(data)):\n",
    "                contrast_val += data[i,j] * pow(i-j, 2)\n",
    "        return contrast_val\n",
    "\n",
    "    def entropy(data):\n",
    "        entropy_val = 0\n",
    "        for i in range(len(data)):\n",
    "            for j in range(len(data)):\n",
    "                if data[i,j] > 0:\n",
    "                    entropy_val += - (data[i,j] * math.log(data[i,j]))\n",
    "        return entropy_val\n",
    "\n",
    "    def homogenitas(data):\n",
    "        homogenitas_val = 0\n",
    "        for i in range(len(data)):\n",
    "            for j in range(len(data)):\n",
    "                homogenitas_val += data[i,j] * (1 + (pow(i-j, 2)))\n",
    "        return homogenitas_val\n",
    "\n",
    "    def energy(data):\n",
    "        energy_val = 0\n",
    "        for i in range(len(data)):\n",
    "            for j in range(len(data)):\n",
    "                energy_val += data[i,j] ** 2\n",
    "        return energy_val\n",
    "\n",
    "    # Ekstraksi GLCM dan fitur untuk setiap derajat\n",
    "    angles = [0, 45, 90, 135]\n",
    "    features = []\n",
    "    for angle in angles:\n",
    "        glcm_matrix = glcm(gray_img, angle)\n",
    "        features.append(energy(glcm_matrix))\n",
    "        features.append(homogenitas(glcm_matrix))\n",
    "        features.append(entropy(glcm_matrix))\n",
    "        features.append(contrast(glcm_matrix))\n",
    "\n",
    "    return np.array(features).reshape(1, -1)  # Mengembalikan 16 fitur\n",
    "\n",
    "# Load model K-NN yang sudah disimpan\n",
    "model = joblib.load('model_knn.pkl')\n",
    "\n",
    "# Gambar baru untuk prediksi\n",
    "new_image_path = 'D:\\Kuliah\\SKRIPSI\\Kakao\\cacao_dataset\\healthy1 .jpg'\n",
    "\n",
    "# Preprocess gambar baru\n",
    "new_image_features = preprocess_image(new_image_path)\n",
    "\n",
    "# Prediksi menggunakan model yang sudah diload\n",
    "predicted_label = model.predict(new_image_features)\n",
    "\n",
    "# Hasil prediksi\n",
    "print(f\"Prediksi label untuk gambar baru: {predicted_label[0]}\")\n"
   ]
  }
 ],
 "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": "3.10.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}