{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "9021cf31-5181-420a-8d77-8bd0baf69841",
   "metadata": {},
   "source": [
    "# Illustrative example of VMCM and CoCoSo methods"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4f8acda2-65a5-427f-86ee-c06fb7a912ae",
   "metadata": {},
   "source": [
    "## Import necessary packages"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "39f7a6ce-fcf4-47bb-bbf7-71d597fff4d5",
   "metadata": {},
   "source": [
    "Import of the necessary Python packages necessary for running codes provided in examples.\r\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "941989f7-0465-4ab6-8fa3-4f7183246872",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import copy"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3838bd78-f197-4f70-b026-e4346cba6939",
   "metadata": {},
   "source": [
    "Import the necessary Python modules from `pyrepo-mcda` package."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "0916b3d6-0d64-4bab-840c-7576b432b8da",
   "metadata": {},
   "outputs": [],
   "source": [
    "from pyrepo_mcda.additions import rank_preferences\n",
    "from pyrepo_mcda.mcda_methods import VMCM, TOPSIS, EDAS, VIKOR, PROMETHEE_II, PROSA_C, COCOSO\n",
    "from pyrepo_mcda import normalizations as norms\n",
    "from pyrepo_mcda import correlations as corrs"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c23437c9-80d2-4ad5-93a8-2c4ff060125a",
   "metadata": {},
   "source": [
    "Supporting function for running provided examples including visualization. Here is function called `draw_heatmap` for displaying heat map with rankings correlations. You can copy and customize its code to your case. Class `Create_dictionary` helps create a correlation matrix to show rankings correlations."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "e349121d-5547-4ca4-87b0-5a16b557b041",
   "metadata": {},
   "outputs": [],
   "source": [
    "# heat maps with correlations\n",
    "def draw_heatmap(df_new_heatmap, title):\n",
    "    \"\"\"\n",
    "    Visualization method to display heatmap with correlations of compared rankings generated using different methods\n",
    "    \n",
    "    Parameters\n",
    "    ----------\n",
    "        data : DataFrame\n",
    "            DataFrame with correlation values between compared rankings\n",
    "        \n",
    "    Examples\n",
    "    ---------\n",
    "    >>> draw_heatmap(df_new_heatmap)\n",
    "    \"\"\"\n",
    "    \n",
    "    plt.figure(figsize = (11, 5))\n",
    "    sns.set(font_scale = 1.2)\n",
    "    heatmap = sns.heatmap(df_new_heatmap, annot=True, fmt=\".4f\", cmap=\"YlGnBu\",\n",
    "                          linewidth=0.5, linecolor='w')\n",
    "    plt.yticks(va=\"center\")\n",
    "    plt.yticks(va=\"center\")\n",
    "    plt.xlabel('MCDA methods')\n",
    "    plt.ylabel('MCDA methods')\n",
    "    plt.title('Correlation coefficient: ' + title)\n",
    "    plt.tight_layout()\n",
    "    plt.savefig('./results_update2/heatmap.pdf')\n",
    "    plt.savefig('./results_update2/heatmap.eps')\n",
    "    plt.show()\n",
    "\n",
    "# Create dictionary class\n",
    "class Create_dictionary(dict):\n",
    "  \n",
    "    # __init__ function\n",
    "    def __init__(self):\n",
    "        self = dict()\n",
    "          \n",
    "    # Function to add key:value\n",
    "    def add(self, key, value):\n",
    "        self[key] = value"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e1ca888d-8d03-44f9-a023-369ec38a80d4",
   "metadata": {},
   "source": [
    "## Using the VMCM method"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9a74c25e-428e-4790-b774-3dc28b899546",
   "metadata": {},
   "source": [
    "### Select criteria assessment, define criteria types, load the data of alternatives"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "707ddaa9-1153-45a1-97b1-fa3f38f60631",
   "metadata": {},
   "source": [
    "An example decision problem involves selecting the best Waste-to-Energy system for the City of Johannesburg in South Africa based on Alao, M. A., Popoola, O. M., & Ayodele, T. R. (2021). Selection of waste-to-energy technology for distributed generation using IDOCRIW-Weighted TOPSIS method: A case study of the City of Johannesburg, South Africa. Renewable Energy, 178, 162-183. DOI: https://doi.org/10.1016/j.renene.2021.06.031\n",
    "\n",
    "The problem considers five alternatives (A1-A5) evaluated against 14 criteria (C1-C14). The last row, named Type, denotes criteria types, where 1 represents profit criteria with the aim of maximization, and -1 defines cost criteria with the objective of minimization."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "35a91685-4321-4f04-b4ba-342525c93478",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load data including decision matrix and criteria types\n",
    "data = pd.read_csv('dataset_waste.csv', index_col = 'Alternative')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "19e8ffbd-6660-4089-a956-e9af7ccbffec",
   "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>C1</th>\n",
       "      <th>C2</th>\n",
       "      <th>C3</th>\n",
       "      <th>C4</th>\n",
       "      <th>C5</th>\n",
       "      <th>C6</th>\n",
       "      <th>C7</th>\n",
       "      <th>C8</th>\n",
       "      <th>C9</th>\n",
       "      <th>C10</th>\n",
       "      <th>C11</th>\n",
       "      <th>C12</th>\n",
       "      <th>C13</th>\n",
       "      <th>C14</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Alternative</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A1 (AD)</th>\n",
       "      <td>682.56</td>\n",
       "      <td>20</td>\n",
       "      <td>8.4167</td>\n",
       "      <td>8.4167</td>\n",
       "      <td>370.2000</td>\n",
       "      <td>17.8110</td>\n",
       "      <td>127.270</td>\n",
       "      <td>7.55</td>\n",
       "      <td>0.0951</td>\n",
       "      <td>20.092</td>\n",
       "      <td>0.003483</td>\n",
       "      <td>8.4167</td>\n",
       "      <td>8.1467</td>\n",
       "      <td>8.4167</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>A2 (LFGR)</th>\n",
       "      <td>69.10</td>\n",
       "      <td>10</td>\n",
       "      <td>8.4167</td>\n",
       "      <td>8.4167</td>\n",
       "      <td>16.4170</td>\n",
       "      <td>4.1029</td>\n",
       "      <td>110.060</td>\n",
       "      <td>4.62</td>\n",
       "      <td>0.1156</td>\n",
       "      <td>148.410</td>\n",
       "      <td>0.103280</td>\n",
       "      <td>9.6667</td>\n",
       "      <td>2.9167</td>\n",
       "      <td>1.4167</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>A3 (INC)</th>\n",
       "      <td>882.43</td>\n",
       "      <td>26</td>\n",
       "      <td>9.6667</td>\n",
       "      <td>1.4167</td>\n",
       "      <td>733.1100</td>\n",
       "      <td>2.3826</td>\n",
       "      <td>11.565</td>\n",
       "      <td>6.96</td>\n",
       "      <td>0.1005</td>\n",
       "      <td>1169.800</td>\n",
       "      <td>366.600000</td>\n",
       "      <td>1.4167</td>\n",
       "      <td>0.4167</td>\n",
       "      <td>1.4167</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>A4 (GAS)</th>\n",
       "      <td>2842.20</td>\n",
       "      <td>30</td>\n",
       "      <td>1.4167</td>\n",
       "      <td>1.4167</td>\n",
       "      <td>1393.5000</td>\n",
       "      <td>81.0300</td>\n",
       "      <td>323.950</td>\n",
       "      <td>10.99</td>\n",
       "      <td>0.0626</td>\n",
       "      <td>288.620</td>\n",
       "      <td>0.288200</td>\n",
       "      <td>1.4167</td>\n",
       "      <td>1.4167</td>\n",
       "      <td>1.4167</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>A5 (PYR)</th>\n",
       "      <td>434.12</td>\n",
       "      <td>15</td>\n",
       "      <td>1.4167</td>\n",
       "      <td>1.4167</td>\n",
       "      <td>7.0315</td>\n",
       "      <td>18.3700</td>\n",
       "      <td>247.490</td>\n",
       "      <td>5.99</td>\n",
       "      <td>0.0501</td>\n",
       "      <td>358.560</td>\n",
       "      <td>16.100000</td>\n",
       "      <td>1.4167</td>\n",
       "      <td>1.4167</td>\n",
       "      <td>1.4167</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Type</th>\n",
       "      <td>1.00</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0000</td>\n",
       "      <td>1.0000</td>\n",
       "      <td>-1.0000</td>\n",
       "      <td>-1.0000</td>\n",
       "      <td>1.000</td>\n",
       "      <td>-1.00</td>\n",
       "      <td>-1.0000</td>\n",
       "      <td>-1.000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.0000</td>\n",
       "      <td>1.0000</td>\n",
       "      <td>1.0000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  C1  C2      C3      C4         C5       C6       C7     C8  \\\n",
       "Alternative                                                                    \n",
       "A1 (AD)       682.56  20  8.4167  8.4167   370.2000  17.8110  127.270   7.55   \n",
       "A2 (LFGR)      69.10  10  8.4167  8.4167    16.4170   4.1029  110.060   4.62   \n",
       "A3 (INC)      882.43  26  9.6667  1.4167   733.1100   2.3826   11.565   6.96   \n",
       "A4 (GAS)     2842.20  30  1.4167  1.4167  1393.5000  81.0300  323.950  10.99   \n",
       "A5 (PYR)      434.12  15  1.4167  1.4167     7.0315  18.3700  247.490   5.99   \n",
       "Type            1.00   1  1.0000  1.0000    -1.0000  -1.0000    1.000  -1.00   \n",
       "\n",
       "                 C9       C10         C11     C12     C13     C14  \n",
       "Alternative                                                        \n",
       "A1 (AD)      0.0951    20.092    0.003483  8.4167  8.1467  8.4167  \n",
       "A2 (LFGR)    0.1156   148.410    0.103280  9.6667  2.9167  1.4167  \n",
       "A3 (INC)     0.1005  1169.800  366.600000  1.4167  0.4167  1.4167  \n",
       "A4 (GAS)     0.0626   288.620    0.288200  1.4167  1.4167  1.4167  \n",
       "A5 (PYR)     0.0501   358.560   16.100000  1.4167  1.4167  1.4167  \n",
       "Type        -1.0000    -1.000   -1.000000 -1.0000  1.0000  1.0000  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5473e43d-24c0-4050-bb5b-caec2056e654",
   "metadata": {},
   "source": [
    "Prepare decision matrix. Then prepare dataframe for VMCM results."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "b75cd6a1-0521-41c6-988e-e1a4eba484e5",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_data = data.iloc[:len(data) - 1, :]\n",
    "matrix = df_data.to_numpy()\n",
    "\n",
    "# Prepare dataframe for VMCM results\n",
    "df_vmcm = pd.DataFrame(index=df_data.index)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "956e580a-f6b7-441f-b9e3-7739b5293c15",
   "metadata": {},
   "source": [
    "### Initialize the VMCM object"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "554b6de4-640b-48c5-ac47-dd4126fdea76",
   "metadata": {},
   "source": [
    "Initialize the VMCM object. Then, determine criteria weights using the function `_weighting` for criteria weighting available in the VMCM class."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "503836f6-2ab1-4d01-a37d-ef64643f5455",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Initialize the VMCM method object\n",
    "vmcm = VMCM()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a3fa58fc-d1b6-4821-bc4f-31b5d622d25e",
   "metadata": {},
   "source": [
    "### Eliminate variables"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "f2fe4810-99f2-4eb4-b944-9ecd93e62c97",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Elimination of variables stage (significance coefficient of features):\n",
      "C1 = 1.1030\n",
      "C2 = 0.3997\n",
      "C3 = 0.6979\n",
      "C4 = 0.9093\n",
      "C5 = 1.1510\n",
      "C6 = 1.3071\n",
      "C7 = 0.7468\n",
      "C8 = 0.3296\n",
      "C9 = 0.3229\n",
      "C10 = 1.1362\n",
      "C11 = 2.1176\n",
      "C12 = 0.9402\n",
      "C13 = 1.0779\n",
      "C14 = 1.1114\n",
      "Criteria to eliminate:\n",
      "None\n"
     ]
    }
   ],
   "source": [
    "# Print the criteria to be eliminated\n",
    "vmcm._elimination(matrix)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d6faf426-9f67-4a90-844e-9a4e209518e4",
   "metadata": {},
   "source": [
    "### Defining criteria types\n",
    "Define criteria types as `numpy.ndarray` types"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "5634ddbd-2dce-4322-b5b3-b3e4c71b5f5d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Provide criteria types\n",
    "types = data.iloc[len(data) - 1, :].to_numpy()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "882998a9-aef0-4e06-894c-cd8464c22631",
   "metadata": {},
   "source": [
    "### Assign weights to criteria assessment"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "5fc5bf05-c2a7-443a-a896-97504b867def",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Determine criteria weights\n",
    "weights = vmcm._weighting(matrix)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "884f3c40-729b-44cf-892b-ac9d9740e3de",
   "metadata": {},
   "source": [
    "Print weights calculated for criteria assessment."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "aca51c70-18ad-4072-8092-8924917861d6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.08261625, 0.02994112, 0.05227225, 0.06810541, 0.08621138,\n",
       "       0.09790768, 0.05593705, 0.02468653, 0.02418794, 0.08510636,\n",
       "       0.15861659, 0.07042509, 0.08073944, 0.08324691])"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "weights"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cae0c5a7-cd0b-4963-856f-48e20835d058",
   "metadata": {},
   "source": [
    "### Determine pattern and anti-pattern"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c368538f-6d27-4b64-a032-c40374dd8d22",
   "metadata": {},
   "source": [
    "Determine and display criteria that should be eliminated from the model because of the low value of the significance coefficient (between 0 and 0.1)."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dd459c25-5101-4282-a1ba-6d372b9ce451",
   "metadata": {},
   "source": [
    "Determine pattern and anti-pattern using function `_pattern_determination` provided in the VMCM class."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "8e38fc8c-1dae-4af6-b92e-a082d191fe3b",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Determine pattern and anti-pattern\n",
    "pattern, antipattern = vmcm._pattern_determination(matrix, types)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "31780dd0-928c-49a0-a402-3b02612cd316",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([-0.0919959 ,  0.71829724,  0.62283181,  1.09544512, -0.84052497,\n",
       "       -0.63815391,  0.68086454, -0.51759361, -0.81014919, -0.55117529,\n",
       "       -0.47158638, -0.72624194,  0.01749959, -0.4472136 ])"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pattern"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "ad3facf8-d596-4408-b09f-dc6a8eb515b0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([-0.50586297, -0.64399063, -1.08690257, -0.73029674,  0.39482264,\n",
       "       -0.19696234, -0.44078313,  0.1378009 ,  0.5741905 , -0.08541002,\n",
       "       -0.3729944 ,  0.94054284, -0.4686001 , -0.4472136 ])"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "antipattern"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "05d072b3-fc66-4ba7-a1d1-28a0b1ec0d75",
   "metadata": {},
   "source": [
    "### Calculate the synthetic measure values for evaluated alternatives"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "afb05eb9-2ec1-4c44-a9aa-aec11c8ec63a",
   "metadata": {},
   "source": [
    "Calculate synthetic measure values for each evaluated alternative. It is required for ranking alternatives and assigning classes to them. An alternative that got the highest synthetic measure value is considered the best evaluated option."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "e583acfc-b770-450e-8fd7-ba0600883db6",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Calculate value of the synthetic measure for each object\n",
    "pref = vmcm(matrix, weights, types, pattern, antipattern)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "abab682b-5fd7-47e9-8ce7-4b9a9fb27e36",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.58312231, 0.41569885, 0.38703968, 0.41406911, 0.50804565])"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pref"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9ab9c772-8310-468a-a225-c57acb69bd1c",
   "metadata": {},
   "source": [
    "### Classify evaluated objects"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1fdc791f-b6ee-45a7-9767-ed008fc25ab0",
   "metadata": {},
   "source": [
    "Assign classes to evaluated alternatives based on synthetic measure values."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "cd04cef8-3285-461e-bcfe-d38714ecdfc2",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Classify evaluated objects according to synthetic measure values\n",
    "classes = vmcm._classification(pref)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "1e1e291f-858c-498f-9aba-03c3d386856f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1., 3., 3., 3., 2.])"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "classes"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c69b76f9-4551-4552-8ac7-a5ac3fed34af",
   "metadata": {},
   "source": [
    "### Rank evaluated objects"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "6e396169-4de8-4932-b3c8-bbdae67a44ff",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Rank evaluated objects according to synthetic measure values\n",
    "rank = rank_preferences(pref, reverse = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "7a9db9fa-e0be-480c-b707-be7c90b83b76",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 3, 5, 4, 2])"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rank"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "000e3a8b-9a97-4aa1-b55c-10d460122bce",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_vmcm['Synthetic measure'] = pref\n",
    "df_vmcm['Class'] = classes\n",
    "df_vmcm['Rank'] = rank"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e5d1898f-2ce6-41c2-8c91-d00b56592086",
   "metadata": {},
   "source": [
    "Display results obtained using the VMCM method, including synthetic measure values, classes, and ranking."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "21cae6e9-651b-4996-abd1-4f635879b179",
   "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>Synthetic measure</th>\n",
       "      <th>Class</th>\n",
       "      <th>Rank</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Alternative</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A1 (AD)</th>\n",
       "      <td>0.583122</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>A2 (LFGR)</th>\n",
       "      <td>0.415699</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>A3 (INC)</th>\n",
       "      <td>0.387040</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>A4 (GAS)</th>\n",
       "      <td>0.414069</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>A5 (PYR)</th>\n",
       "      <td>0.508046</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Synthetic measure  Class  Rank\n",
       "Alternative                                \n",
       "A1 (AD)               0.583122    1.0     1\n",
       "A2 (LFGR)             0.415699    3.0     3\n",
       "A3 (INC)              0.387040    3.0     5\n",
       "A4 (GAS)              0.414069    3.0     4\n",
       "A5 (PYR)              0.508046    2.0     2"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_vmcm"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e2eccb54-b1e6-4380-93d8-b66ac5daf2e7",
   "metadata": {},
   "source": [
    "## Comparative analysis of VMCM with other MCDA methods\n",
    "Compare VMCM ranking with rankings provided by other MCDA methods.\n",
    "\n",
    "### Create MCDA rankings to compare them with VMCM ranking."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "ac915733-1c6e-491d-9b15-b9917ee39f63",
   "metadata": {},
   "outputs": [],
   "source": [
    "# COMAPRATIVE ANALYSIS\n",
    "df_comparative = pd.DataFrame(index=df_data.index)\n",
    "df_comparative['VMCM'] = rank\n",
    "\n",
    "topsis = TOPSIS(normalization_method=norms.minmax_normalization)\n",
    "pref = topsis(matrix, weights, types)\n",
    "rank = rank_preferences(pref, reverse = True)\n",
    "df_comparative['TOPSIS'] = rank\n",
    "\n",
    "vikor = VIKOR()\n",
    "pref = vikor(matrix, weights, types)\n",
    "rank = rank_preferences(pref, reverse = False)\n",
    "df_comparative['VIKOR'] = rank\n",
    "\n",
    "edas = EDAS()\n",
    "pref = edas(matrix, weights, types)\n",
    "rank = rank_preferences(pref, reverse = True)\n",
    "df_comparative['EDAS'] = rank\n",
    "\n",
    "promethee_II = PROMETHEE_II()\n",
    "preference_functions = [promethee_II._linear_function for pf in range(len(weights))]\n",
    "pref = promethee_II(matrix, weights, types, preference_functions)\n",
    "rank = rank_preferences(pref, reverse=True)\n",
    "df_comparative['PROMETHEE II'] = rank\n",
    "\n",
    "prosa_c = PROSA_C()\n",
    "pref = prosa_c(matrix, weights, types, preference_functions)\n",
    "rank = rank_preferences(pref, reverse=True)\n",
    "df_comparative['PROSA C'] = rank"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "551c3f2f-1e43-473d-abec-fcc7d5640b8a",
   "metadata": {},
   "source": [
    "### Using the CoCoSo method\n",
    "Evaluate objects with the CoCoSo method. Using this method is analogous to most MCDA methods available in the `pyrepo-mcda` package. During initialization of the COCOSO object, you can pass the type of normalization method and lambda parameter. The default normalization for this method is `minmax_normalization`. The default lambda parameter is equal to 0.5, and it is not necessary to pass it as a function argument if you want to set its value as 0.5."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "c166bfd6-dbc3-45d0-8046-93bc97810334",
   "metadata": {},
   "outputs": [],
   "source": [
    "cocoso = COCOSO(normalization_method=norms.minmax_normalization, lambda_param = 0.5)\n",
    "pref = cocoso(matrix, weights, types)\n",
    "rank = rank_preferences(pref, reverse=True)\n",
    "df_comparative['COCOSO'] = rank"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "363a76f5-3c66-481a-9d1f-ce4c06bc6ae2",
   "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>VMCM</th>\n",
       "      <th>TOPSIS</th>\n",
       "      <th>VIKOR</th>\n",
       "      <th>EDAS</th>\n",
       "      <th>PROMETHEE II</th>\n",
       "      <th>PROSA C</th>\n",
       "      <th>COCOSO</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Alternative</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A1 (AD)</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>A2 (LFGR)</th>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>A3 (INC)</th>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>A4 (GAS)</th>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>A5 (PYR)</th>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             VMCM  TOPSIS  VIKOR  EDAS  PROMETHEE II  PROSA C  COCOSO\n",
       "Alternative                                                          \n",
       "A1 (AD)         1       1      1     1             1        1       1\n",
       "A2 (LFGR)       3       2      2     2             3        3       3\n",
       "A3 (INC)        5       5      5     5             5        5       5\n",
       "A4 (GAS)        4       4      4     4             4        4       4\n",
       "A5 (PYR)        2       3      3     3             2        2       2"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_comparative"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9c2c0c45-2c07-49b9-910f-152d31248ed5",
   "metadata": {},
   "source": [
    "### Calculate correlations between compared rankings\n",
    "Calculate correlation values between compared rankings to evaluate their convergence."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "d12385c0-8d18-4ae9-bcca-9ffe59c81eca",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1100x500 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Rankings correlations\n",
    "results = copy.deepcopy(df_comparative)\n",
    "method_types = list(results.columns)\n",
    "dict_new_heatmap_rw = Create_dictionary()\n",
    "\n",
    "for el in method_types:\n",
    "    dict_new_heatmap_rw.add(el, [])\n",
    "\n",
    "# heatmaps for correlations coefficients\n",
    "for i, j in [(i, j) for i in method_types[::-1] for j in method_types]:\n",
    "    dict_new_heatmap_rw[j].append(corrs.weighted_spearman(results[i], results[j]))\n",
    "\n",
    "df_new_heatmap_rw = pd.DataFrame(dict_new_heatmap_rw, index = method_types[::-1])\n",
    "df_new_heatmap_rw.columns = method_types\n",
    "\n",
    "# correlation matrix with rw coefficient\n",
    "draw_heatmap(df_new_heatmap_rw, r'$r_w$')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e3cf45eb-9ddf-495d-b61d-0afafcca0498",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}