{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Quick Start\n",
    "\n",
    "This tutorial aims to explain in a simple way, how to create decision matrices, \n",
    "how to analyze them and how to evaluate them with some multi-criteria analysis methods (MCDA).\n",
    "\n",
    "\n",
    "## Conceptual overview\n",
    "\n",
    "Multi-criteria data are complex. This is because at least two syntactically \n",
    "disconnected vectors are needed to describe a problem.\n",
    "\n",
    "1. `matrix`/$A$ choice set.\n",
    "2. And the vector of criteria optimality sense `objectives`/$C$. \n",
    "\n",
    "Additionally it can be accompanied by a vector `w`/$w_j$ with the weighting of the criteria. \n",
    "\n",
    "To summarize all these data (and some extra ones), *Scikit-Criteria* provides\n",
    "a `DecisionMatrix` object along with a `mkdm()` utility function to \n",
    "facilitate the creation and validation of the data.\n",
    "\n",
    "## Your first `DecisionMatrix` object\n",
    "\n",
    "First we need to import the the *Scikit-Criteria* module."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "nbsphinx": "hidden"
   },
   "outputs": [],
   "source": [
    "import skcriteria as skc  # we use skc as an abbreviation for scikit-criteria"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Then we need to create the `matrix` and `objectives` vectors. \n",
    "\n",
    "The `matrix` must be a **2D array-like** where every column is a criteria, \n",
    "and every row is an alternative."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[[1, 2, 3], [4, 5, 6]]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 2 alternatives by 3 criteria\n",
    "matrix = [\n",
    "    [1, 2, 3],  # alternative 1\n",
    "    [4, 5, 6],  # alternative 2\n",
    "]\n",
    "matrix"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The `objectives` vector must be a **1D array-like** with number of elements same \n",
    "as number of columns in the alternative matrix (`matrix`). Every component of the \n",
    "`objectives` vector represent the optimal sense of each criteria."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<function max>, <function max>, <function min>]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# let's says the first two alternatives are\n",
    "# for maximization and the last one for minimization\n",
    "objectives = [max, max, min]\n",
    "objectives"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "as you see the `max` and `min` are the built-in function for find max and mins in collections in python.\n",
    "\n",
    "As you can see the function usage makes the code more readable. Also you can use as aliases of minimization and maximization the numpy function `np.min`, `np.max`, `np.amin`, `np.amax`, `np.nanmin`, `np.nanmax`; the strings `\"min\"`, `\"minimize\"`, `\"max\"`, `\"maximize\"`, `\">\"`, `\"<\"`, `\"+\"`, `\"-\"`; and the values `-1` (minimize) and `1` (maximize).\n",
    "\n",
    "Now we can combine this two vectors in our *Scikit-Criteria* decision matrix."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div class='decisionmatrix'>\n",
       "<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>C0[▼ 1.0]</th>\n",
       "      <th>C1[▲ 1.0]</th>\n",
       "      <th>C2[▼ 1.0]</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A0</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>A1</th>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div><em class='decisionmatrix-dim'>2 Alternatives x 3 Criteria</em>\n",
       "</div>"
      ],
      "text/plain": [
       "    C0[▼ 1.0]  C1[▲ 1.0]  C2[▼ 1.0]\n",
       "A0          1          2          3\n",
       "A1          4          5          6\n",
       "[2 Alternatives x 3 Criteria]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# we use the built-in function as aliases\n",
    "dm = skc.mkdm(matrix, [min, max, min])\n",
    "dm"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As you can see the output of the `DecisionMatrix` object is much more friendly than the plain python lists.\n",
    "\n",
    "To change the generic names of the alternatives (A0 and A1) and the criteria (C0, C1 and C2); let's assume that our data is about cars (*car 0* and *car 1*) and their characteristics of evaluation are *autonomy* ($maximize$), *comfort* ($maximize$) and *price* ($minimize$). \n",
    "\n",
    "To feed this information to our `DecisionMatrix` object we have the parameters: `alternatives` that accept the names of alternatives (must be the same number as the rows that `matrix` has), and `criteria` the criteria names (must have same number of elements with the columns that `matrix` has)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div class='decisionmatrix'>\n",
       "<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>autonomy[▲ 1.0]</th>\n",
       "      <th>comfort[▲ 1.0]</th>\n",
       "      <th>price[▼ 1.0]</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>car 0</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>car 1</th>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div><em class='decisionmatrix-dim'>2 Alternatives x 3 Criteria</em>\n",
       "</div>"
      ],
      "text/plain": [
       "       autonomy[▲ 1.0]  comfort[▲ 1.0]  price[▼ 1.0]\n",
       "car 0                1               2             3\n",
       "car 1                4               5             6\n",
       "[2 Alternatives x 3 Criteria]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dm = skc.mkdm(\n",
    "    matrix,\n",
    "    objectives,\n",
    "    alternatives=[\"car 0\", \"car 1\"],\n",
    "    criteria=[\"autonomy\", \"comfort\", \"price\"],\n",
    ")\n",
    "dm"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In our final step let's assume we know in our case, that the importance of the autonomy is the *50%*, the comfort only a *5%* and the price is *45%*. The param to feed this to the structure is called `weights` and must be a vector with the same elements as criterias on your alternative matrix (number of columns)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div class='decisionmatrix'>\n",
       "<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>autonomy[▲ 0.50]</th>\n",
       "      <th>comfort[▲ 0.05]</th>\n",
       "      <th>price[▼ 0.45]</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>car 0</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>car 1</th>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div><em class='decisionmatrix-dim'>2 Alternatives x 3 Criteria</em>\n",
       "</div>"
      ],
      "text/plain": [
       "       autonomy[▲ 0.50]  comfort[▲ 0.05]  price[▼ 0.45]\n",
       "car 0                 1                2              3\n",
       "car 1                 4                5              6\n",
       "[2 Alternatives x 3 Criteria]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dm = skc.mkdm(\n",
    "    matrix,\n",
    "    objectives,\n",
    "    weights=[0.5, 0.05, 0.45],\n",
    "    alternatives=[\"car 0\", \"car 1\"],\n",
    "    criteria=[\"autonomy\", \"comfort\", \"price\"],\n",
    ")\n",
    "dm"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Manipulating the Data\n",
    "\n",
    "The data object are immutable, if you want to modify it you need create a new one. All the data are stored as [pandas dataframes](https://pandas.pydata.org/) and [numpy arrays](https://docs.scipy.org/doc/numpy/user/basics.creation.html)\n",
    "\n",
    "You can access to the different parts of your data, simply by typing `dm.<your-parameter-name>` for example:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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>Criteria</th>\n",
       "      <th>autonomy</th>\n",
       "      <th>comfort</th>\n",
       "      <th>price</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Alternatives</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>car 0</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>car 1</th>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Criteria      autonomy  comfort  price\n",
       "Alternatives                          \n",
       "car 0                1        2      3\n",
       "car 1                4        5      6"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dm.matrix  # note how this data ignores the objectives and the weights"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "autonomy    MAX\n",
       "comfort     MAX\n",
       "price       MIN\n",
       "Name: Objectives, dtype: object"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dm.objectives"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "autonomy    0.50\n",
       "comfort     0.05\n",
       "price       0.45\n",
       "Name: Weights, dtype: float64"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dm.weights"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(_ACArray(['car 0', 'car 1'], dtype=object),\n",
       " _ACArray(['autonomy', 'comfort', 'price'], dtype=object))"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dm.alternatives, dm.criteria"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "If you want (for example) change the names of the cars from `car 0` and `car 1`; to `VW` and `Ford` you must the copy method and provide the new names:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div class='decisionmatrix'>\n",
       "<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>autonomy[▲ 0.50]</th>\n",
       "      <th>comfort[▲ 0.05]</th>\n",
       "      <th>price[▼ 0.45]</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>VW</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ford</th>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div><em class='decisionmatrix-dim'>2 Alternatives x 3 Criteria</em>\n",
       "</div>"
      ],
      "text/plain": [
       "      autonomy[▲ 0.50]  comfort[▲ 0.05]  price[▼ 0.45]\n",
       "VW                   1                2              3\n",
       "Ford                 4                5              6\n",
       "[2 Alternatives x 3 Criteria]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dm = dm.copy(alternatives=[\"VW\", \"Ford\"])\n",
    "dm"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<div class=\"alert alert-info\">\n",
    "**Note:** \n",
    "\n",
    "For more complex matiluations you can use the `dm.iloc[x]`, `dm.loc[x]` and `dm[x]` interface.\n",
    "</div>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Plotting\n",
    "\n",
    "The Data structure support some basic routines for plotting. \n",
    "\n",
    "The default scikit criteria uses the Heatmap plot to visualize all the data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Criteria', ylabel='Alternatives'>"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "dm.plot()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In the same fashion you can plot the weights of the criteria "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Criteria'>"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x96 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "dm.plot.wheatmap()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "You can accessing the different kind of plot by passing the name of the plot as first parameter of the method"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:ylabel='Density'>"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "dm.plot(\"kde\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "or by using the name as method call inside the `plot` attribute"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:ylabel='Density'>"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "dm.plot.kde()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Every plot has their own set of parameters, defined by the subjacent function\n",
    "  \n",
    "Let's change the colors of the weight bar plot and show:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAiMAAAHGCAYAAACmS4sdAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/NK7nSAAAACXBIWXMAAA9hAAAPYQGoP6dpAAAwbUlEQVR4nO3de1hVdb7H8c/eyEVELmKCFxLvl7xgoiTkJcPoYuVMM2PNFEpqp2Y0G7TSToLhBSszLJ0sPVrjydHT09TYycGcrZ7STEuiMTW8pOEoN20EgRGMvc8fPu3cIygbcP8E36/n2c/j/u3f+q3vIp72h99a67csDofDIQAAAEOspgsAAADXNsIIAAAwijACAACMIowAAACjCCMAAMAowggAADCKMAIAAIxqZrqA2rDb7Tpx4oRatmwpi8ViuhwAAFALDodDZ86cUbt27WS11jz/0SjCyIkTJxQREWG6DAAAUAfHjh1Thw4davy8UYSRli1bSjp/MIGBgYarAQAAtVFSUqKIiAjn93hNGkUY+fHUTGBgIGEEAIBG5nKXWHABKwAAMIowAgAAjCKMAAAAoxrFNSMAgKtDVVWVzp07Z7oMXCW8vb3l5eVV73EIIwCAy3I4HMrPz9fp06dNl4KrTHBwsMLDw+u1DhhhBABwWT8GkTZt2sjf358FKCGHw6Hy8nIVFhZKktq2bVvnsQgjAIBLqqqqcgaR0NBQ0+XgKtK8eXNJUmFhodq0aVPnUzZcwAoAuKQfrxHx9/c3XAmuRj/+XtTnWiLCCACgVjg1g+o0xO8FYQQAABhFGAEAAEbVKYwsXbpUkZGR8vPzU0xMjHbt2lVj3zfffFMWi8Xl5efnV+eCAQC4UrZu3SqLxXLFbmEeP368xowZc0XGbszcDiPr1q1TcnKyUlNTlZWVpf79+yshIcF5a091AgMDlZeX53x999139SoaAIDLyc/P15QpU9S5c2f5+voqIiJCd999t2w2W43bxMbGKi8vT0FBQZLO/0EdHBzcYDUtXrxYb775ZoON11S4fWvvokWLNGnSJCUlJUmSli1bpg8//FArV67UjBkzqt3GYrEoPDy8fpUCAFBLR48eVVxcnIKDg/Xiiy+qb9++OnfunDZu3Kjf/e53+uabby7a5ty5c/Lx8bki31dVVVWyWCzOkANXbs2MVFZWavfu3YqPj/9pAKtV8fHx2rFjR43blZaWqmPHjoqIiNC9996rvXv3XnI/FRUVKikpcXkBAFBbv/3tb2WxWLRr1y7dd9996t69u2644QYlJyfrs88+k3T+D+XXXntN99xzj1q0aKF58+a5nKbZunWrkpKSVFxc7LzMYPbs2ZLOf09Nnz5d7du3V4sWLRQTE6OtW7c69//jjMr69evVu3dv+fr6Kjc396LTNJmZmbr55psVHBys0NBQjR49WocPH/bgT+rq4NbMyMmTJ1VVVaWwsDCX9rCwsGpTpiT16NFDK1euVL9+/VRcXKyFCxcqNjZWe/fuVYcOHardJj09Xc8995w7paGJGWX9pekSmoRN9ndMlwB43Pfff6/MzEzNmzdPLVq0uOjzC0+7zJ49WwsWLFBGRoaaNWumb7/91vlZbGysMjIylJKSopycHElSQECAJGny5Mnat2+f1q5dq3bt2um9997T7bffrj179qhbt26SpPLycj3//PNasWKFQkND1aZNm4tqKSsrU3Jysvr166fS0lKlpKToZz/7mbKzs2W1Xjv3mFzxFViHDBmiIUOGON/HxsaqV69eev311zVnzpxqt5k5c6aSk5Od70tKShQREXGlSwUANAGHDh2Sw+FQz549L9v317/+tfOyA0kuYcTHx0dBQUEXXWqQm5urVatWKTc3V+3atZMkTZ8+XZmZmVq1apXmz58v6fxpnz/84Q/q379/jfu/7777XN6vXLlS1113nfbt26c+ffrU7oCbALfCSOvWreXl5aWCggKX9oKCglqfY/P29taAAQN06NChGvv4+vrK19fXndIAAJB0/pkptRUdHe32+Hv27FFVVZW6d+/u0l5RUeGyXL6Pj4/69et3ybEOHjyolJQU7dy5UydPnpTdbpd0PvAQRmrg4+OjgQMHymazOc952e122Ww2TZ48uVZjVFVVac+ePbrzzjvdLhYAgMvp1q2bLBZLjZcPXKi60ziXU1paKi8vL+3evfuiZ7H8eBpHOv/clsutTnr33XerY8eOWr58udq1aye73a4+ffqosrLS7boaM7dP0yQnJ2vcuHGKjo7W4MGDlZGRobKyMuc0V2Jiotq3b6/09HRJUlpamm666SZ17dpVp0+f1osvvqjvvvtOEydObNgjAQBAUqtWrZSQkKClS5fq8ccfvyhwnD59uta36/r4+KiqqsqlbcCAAaqqqlJhYaGGDh1a5zpPnTqlnJwcLV++3DnOtm3b6jxeY+Z2GBk7dqyKioqUkpKi/Px8RUVFKTMz03lRa25urstFN//85z81adIk5efnKyQkRAMHDtSnn36q3r17N9xRAABwgaVLlyouLk6DBw9WWlqa+vXrpx9++EGbNm3Sa6+9pv3799dqnMjISJWWlspms6l///7y9/dX9+7d9Zvf/EaJiYl66aWXNGDAABUVFclms6lfv3666667ajV2SEiIQkND9cYbb6ht27bKzc2tcYmMpq5OF7BOnjy5xtMyF97aJEkvv/yyXn755brsBgCAOuncubOysrI0b948TZs2TXl5ebruuus0cOBAvfbaa7UeJzY2Vo8++qjGjh2rU6dOKTU1VbNnz9aqVas0d+5cTZs2TcePH1fr1q110003afTo0bUe22q1au3atXr88cfVp08f9ejRQ6+88opGjBhRhyNu3CwOd670MaSkpERBQUEqLi5WYGCg6XLgAdza2zC4tRcN4ezZszpy5Ig6derE4zxwkUv9ftT2+/vauYkZAABclQgjAADAKMIIAAAwijACAACMIowAAACjCCMAAMAowggAADCKMAIAAIwijAAAAKPqtBw8AACS51dLNrGq8JtvvqknnnhCp0+f9vi+rxXMjAAAABdff/213nvvPY/tjzACAGiyMjMzdfPNNys4OFihoaEaPXq0Dh8+7Px869atslgsLrMe2dnZslgsOnr0qLZu3aqkpCQVFxfLYrHIYrFo9uzZks4/lT4xMVEhISHy9/fXHXfcoYMHDzrHefPNNxUcHKyNGzeqV69eCggI0O233668vDxnH7vdrrS0NHXo0EG+vr6KiopSZmam8/OjR4/KYrHof/7nfzR06FA1b95cgwYN0oEDB/T5558rOjpaAQEBuuOOO1RUVCRJ+vjjj+Xt7a38/HyXn8UTTzyhoUOH1urnlpaWpueee06eenwdYQQA0GSVlZUpOTlZX3zxhWw2m6xWq372s5/JbrfXavvY2FhlZGQoMDBQeXl5ysvL0/Tp0yVJ48eP1xdffKH169drx44dcjgcuvPOO3Xu3Dnn9uXl5Vq4cKFWr16tjz/+WLm5uc7tJWnx4sV66aWXtHDhQv39739XQkKC7rnnHpdQI0mpqal69tlnlZWVpWbNmunXv/61nnrqKS1evFiffPKJDh06pJSUFEnSsGHD1LlzZ61evdq5/blz5/T222/r4Ycfvuwx79u3T++++66++uor/eUvf6nVz6m+CCMAgCbrvvvu089//nN17dpVUVFRWrlypfbs2aN9+/bVansfHx8FBQXJYrEoPDxc4eHhCggI0MGDB7V+/XqtWLFCQ4cOVf/+/fX222/r+PHjev/9953bnzt3TsuWLVN0dLRuvPFGTZ48WTabzfn5woUL9fTTT+v+++9Xjx499PzzzysqKkoZGRkudUyfPl0JCQnq1auXpk6dqt27d2vWrFmKi4vTgAEDNGHCBG3ZssXZf8KECVq1apXz/QcffKCzZ8/qV7/61WWPee7cuc6wNmfOnFr9nOqLMAIAaLIOHjyoBx54QJ07d1ZgYKAiIyMlSbm5ufUad//+/WrWrJliYmKcbaGhoerRo4f279/vbPP391eXLl2c79u2bavCwkJJUklJiU6cOKG4uDiXsePi4lzGkKR+/fo5/x0WFiZJ6tu3r0vbj+NK52dtDh06pM8++0zS+VNGv/rVr9SiRYtLHteBAwe0bt065/usrCx98MEHl9ymIRBGAABN1t13363vv/9ey5cv186dO7Vz505JUmVlpSTJaj3/NXjhtREXnmapL29vb5f3FoulTtdhXDiOxWKptu3CU09t2rTR3XffrVWrVqmgoEB//etfa3WK5sJZkR95YnaEMAIAaJJOnTqlnJwcPfvss7r11lvVq1cv/fOf/3Tpc91110mSy0Wl2dnZLn18fHxUVVXl0tarVy/98MMPznBz4f569+5dq/oCAwPVrl07bd++3aV9+/bttR7jUiZOnKh169bpjTfeUJcuXS6agfl3hw8f1po1ay5q//zzz7Vhw4Z613MphBEAQJMUEhKi0NBQvfHGGzp06JA2b96s5ORklz5du3ZVRESEZs+erYMHD+rDDz/USy+95NInMjJSpaWlstlsOnnypMrLy9WtWzfde++9mjRpkrZt26avvvpKDz74oNq3b69777231jU++eSTev7557Vu3Trl5ORoxowZys7O1tSpU+t9/AkJCQoMDNTcuXOVlJR02f7z5s27KHT9KC0trd71XAqLngEA6szEImS1ZbVatXbtWj3++OPq06ePevTooVdeeUUjRoxw9vH29taf/vQnPfbYY+rXr58GDRqkuXPn6pe//Gkxt9jYWD366KMaO3asTp06pdTUVM2ePVurVq3S1KlTNXr0aFVWVmrYsGHasGHDRadmLuXxxx9XcXGxpk2bpsLCQvXu3Vvr169Xt27dGuT4x48fr/nz5ysxMfGSfY8cOeJy982/27lzpzZu3KiEhIR611Udi8NTNxHXQ0lJiYKCglRcXKzAwEDT5cADPL2qY1N1NX9RoPE4e/asjhw5ok6dOsnPz890OXDDhAkTVFRUpPXr11+y36RJk7RixYpL9omNjb3olJJ06d+P2n5/MzMCAEATU1xcrD179mjNmjWXDSLl5eUqKCio1azHoUOH1LVr14Yq04kwAgBAE3Pvvfdq165devTRRzVq1KhL9vX3979sYLnSCCMAADQxW7duNV2CW7ibBgAAGEUYAQAARhFGAACAUYQRAABgFBewAkAt2PO7my7BGPu5dnJUPSvHuXNyeFnqPZ7Fu+/lO+GawswIAAAwijACAACM4jQNAKDOurz2UR22qss25337+LQ6b+tJ33zzjcaPH6/s7Gz17NnzoicBwxUzIwAANLDU1FS1aNFCOTk5stls9RorMjJSGRkZDVPYVYowAgBAAzt8+LBuvvlmdezYUaGhoXUao7Kyss77//rrr/Xee+/VeXtPI4wAAJosu92uF154QV27dpWvr6+uv/56zZs3z/n5nj17NHLkSDVv3lyhoaF65JFHVFpa6vx8/PjxGjNmjObPn6+wsDAFBwcrLS1NP/zwg5588km1atVKHTp00KpVq5zbWCwW7d69W2lpabJYLJo9e7Zb+5o3b57atWunHj16aMSIEfruu+/0+9//XhaLRRZL7e5mSktL03PPPSeHw1HPn6BnEEYAAE3WzJkztWDBAs2aNUv79u3TmjVrFBYWJkkqKytTQkKCQkJC9Pnnn+udd97R3/72N02ePNlljM2bN+vEiRP6+OOPtWjRIqWmpmr06NEKCQnRzp079eijj+o//uM/9I9//EOSlJeXpxtuuEHTpk1TXl6epk+fXut92Ww25eTkaNOmTfrf//1f/fnPf1aHDh2UlpamvLw85eXlXfaY9+3bp3fffVdfffWV/vKXvzTQT/LKIowAAJqkM2fOaPHixXrhhRc0btw4denSRTfffLMmTpwoSVqzZo3Onj2rP/7xj+rTp49GjhypJUuWaPXq1SooKHCO06pVK73yyivq0aOHHn74YfXo0UPl5eV65pln1K1bN82cOVM+Pj7atm2bJCk8PFzNmjVTQECAwsPDFRAQUOt9tWjRQitWrNANN9ygG264Qa1atZKXl5datmyp8PBwhYeHX/a4586dK7vdLkmaM2dOQ/5IrxjCCACgSdq/f78qKip066231vh5//791aJFC2dbXFyc7Ha7cnJynG033HCDrNafvi7DwsLUt+9PC7d5eXkpNDRUhYWFl6ylNvvq27evfHx83DvQCxw4cEDr1q1zvs/KytIHH3xQ5/E8hTACAGiSmjdv3iDjeHt7u7y3WCzVtv04G1EfF4aVurhwVuRHjWF2hDACAGiSunXrpubNm9d4a22vXr301VdfqayszNm2fft2Wa1W9ejRo0Frqc++fHx8VFVVddl9HD58WGvWrLmo/fPPP9eGDRvcL9qDWPQMAFBnhx+7ze1tPPVsGj8/Pz399NN66qmn5OPjo7i4OBUVFWnv3r2aMGGCfvOb3yg1NVXjxo3T7NmzVVRUpClTpuihhx5yXuTaUOqzr8jISH388ce6//775evrq9atW1fbb968eTWGlrS0NN155531Po4rhZkRAECTNWvWLE2bNk0pKSnq1auXxo4d67y2w9/fXxs3btT333+vQYMG6Re/+IVuvfVWLVmypMHrqM++0tLSdPToUXXp0kXXXXddtX2OHDmi1atX1zjGzp07tXHjxjrXf6VZHI3gJuSSkhIFBQWpuLhYgYGBpsuBB4yy/tJ0CU3CJvs7pktoMq7lp/aePddOR4ufVaeObeTnx1N7r0aTJk3SihUrLtknNjZW27dvb/B9nz17VkeOHFGnTp3k5+fn8lltv785TQMAQCNWXl6ugoICJSQkXLbvoUOH1LVrVw9U5R7CCAAAjZi/v7/Wr19vuox64ZoRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEA4N8cPXpUFotF2dnZpku5JrDOCACgzhyn7nN/m3rszxp+oB5b115ERITy8vJqfA4MGhYzIwAAXKCyslJeXl4KDw9Xs2ZX5m/2u+66SxaL5bKvN99884rs/2pDGAEANFkjRozQ5MmTNXnyZAUFBal169aaNWuWLnwsW2RkpObMmaPExEQFBgbqkUceqfY0zd69ezV69GgFBgaqZcuWGjp0qA4fPuz8fMWKFerVq5f8/PzUs2dP/eEPf6ixrpSUlMvW3rlzZz344IN1O/BGhjACAGjS3nrrLTVr1ky7du3S4sWLtWjRooseKrdw4UL1799fX375pWbNmnXRGMePH9ewYcPk6+urzZs3a/fu3Xr44Yf1ww8/SJLefvttpaSkaN68edq/f7/mz5+vWbNm6a233qq2ppiYGN12222XrPuZZ565YjMzV5tr4ygBANesiIgIvfzyy7JYLOrRo4f27Nmjl19+WZMmTXL2GTlypKZNm+Z8f/ToUZcxli5dqqCgIK1du1be3t6SpO7df3qSc2pqql566SX9/Oc/lyR16tRJ+/bt0+uvv65x48ZVW1dKSoo++uijaj+LjIxUYmJinY63MWJmBADQpN10002yWCzO90OGDNHBgwdVVVXlbIuOjr7kGNnZ2Ro6dKgziFyorKxMhw8f1oQJExQQEOB8zZ071+U0zr+Li4vTyJEjq/1s5syZ1e6rqWJmBABwzWvRosUlP2/evHmNn5WWlkqSli9frpiYGJfPvLy8LjluSkqKNm/e7NJ2/fXXa/z48ZfcrqlhZgQA0KTt3LnT5f1nn32mbt26XTYoXKhfv3765JNPdO7cuYs+CwsLU7t27fTtt9+qa9euLq9OnTpdctzhw4dr2LBhLm0zZsyQj49PrWtrCuoURpYuXarIyEj5+fkpJiZGu3btqtV2a9eulcVi0ZgxY+qyWwAA3Jabm6vk5GTl5OToT3/6k1599VVNnTrVrTEmT56skpIS3X///friiy908OBBrV69Wjk5OZKk5557Tunp6XrllVd04MAB7dmzR6tWrdKiRYsuO3Zqaqrz3x06dNCECRPcO8AmwO3TNOvWrVNycrKWLVummJgYZWRkKCEhQTk5OWrTpk2N2x09elTTp0/X0KFD61UwAODqYQl91/1tvPtegUpqlpiYqH/9618aPHiwvLy8NHXqVD3yyCNujREaGqrNmzfrySef1PDhw+Xl5aWoqCjFxcVJkiZOnCh/f3+9+OKLevLJJ9WiRQv17dtXTzzxxGXHHjlypOLi4rR9+3Y9/fTT19ysiCRZHBfebF0LMTExGjRokJYsWSJJstvtioiI0JQpUzRjxoxqt6mqqtKwYcP08MMP65NPPtHp06f1/vvv17iPiooKVVRUON+XlJQoIiJCxcXFCgwMdKdcNFKjrL80XUKTsMn+jukSmgx7fvfLd2qizp5rp6PFz6pTxzby87NcfoPL8GQYGTFihKKiopSRkeGxfdbFRx99pKSkJH377bfy9fU1XY5bzp49qyNHjqhTp07y8/Nz+aykpERBQUGX/f526zRNZWWldu/erfj4+J8GsFoVHx+vHTt21LhdWlqa2rRpU+upp/T0dAUFBTlfERER7pQJAECjctttt+ntt99udEGkobgVRk6ePKmqqiqFhYW5tIeFhSk/P7/abbZt26b/+q//0vLly2u9n5kzZ6q4uNj5OnbsmDtlAgDQ6IwYMcJ0CcZc0Vt7z5w5o4ceekjLly9362FDvr6+12w6BAA0nK1bt5ouAbXgVhhp3bq1vLy8VFBQ4NJeUFCg8PDwi/ofPnxYR48e1d133+1ss9vt53fcrJlycnLUpUuXutQNAACaCLdO0/j4+GjgwIGy2WzONrvdLpvNpiFDhlzUv2fPntqzZ4+ys7Odr3vuuUe33HKLsrOzuRYEABoFuySH3LzfAdeIhvi9cPs0TXJyssaNG6fo6GgNHjxYGRkZKisrU1JSkqTzt1C1b99e6enp8vPzU58+fVy2Dw4OlqSL2gEAVydvr2LJ8YPKzzp0iYVIcY0qLy+XpHotX+92GBk7dqyKioqUkpKi/Px8RUVFKTMz03lRa25urqxWFnYFgKbCy/ovBfttUVHhnZKC5e9ncXnWi7ssVWcbrjgY43A4VF5ersLCQgUHB7u1ou2/c3udERNqe58ymg7WGWkYrDPScK7ldUYkyeGwqKD0Xp0+e4tkaSapHmHEq33DFQbjgoODFR4eXm1Are33Nw/KAwBclsXiUHjL93Vdi0ydqwpWfR5tZr0us8Hqglne3t71mhH5EWEEAFBrXtaz8rJWv65UbVn/bZVOgIs7AACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFF1CiNLly5VZGSk/Pz8FBMTo127dtXY989//rOio6MVHBysFi1aKCoqSqtXr65zwQAAoGlxO4ysW7dOycnJSk1NVVZWlvr376+EhAQVFhZW279Vq1b6z//8T+3YsUN///vflZSUpKSkJG3cuLHexQMAgMbP4nA4HO5sEBMTo0GDBmnJkiWSJLvdroiICE2ZMkUzZsyo1Rg33nij7rrrLs2ZM6fazysqKlRRUeF8X1JSooiICBUXFyswMNCdctFIjbL+0nQJTcIm+zumS2gy7PndTZfQZFjDD5guAR5SUlKioKCgy35/uzUzUllZqd27dys+Pv6nAaxWxcfHa8eOHZfd3uFwyGazKScnR8OGDauxX3p6uoKCgpyviIgId8oEAACNiFth5OTJk6qqqlJYWJhLe1hYmPLz82vcrri4WAEBAfLx8dFdd92lV199VaNGjaqx/8yZM1VcXOx8HTt2zJ0yAQBAI9LMEztp2bKlsrOzVVpaKpvNpuTkZHXu3FkjRoyotr+vr698fX09URoAADDMrTDSunVreXl5qaCgwKW9oKBA4eHhNW5ntVrVtWtXSVJUVJT279+v9PT0GsMIAAC4drh1msbHx0cDBw6UzWZzttntdtlsNg0ZMqTW49jtdpcLVAEAwLXL7dM0ycnJGjdunKKjozV48GBlZGSorKxMSUlJkqTExES1b99e6enpks5fjBodHa0uXbqooqJCGzZs0OrVq/Xaa6817JEAAIBGye0wMnbsWBUVFSklJUX5+fmKiopSZmam86LW3NxcWa0/TbiUlZXpt7/9rf7xj3+oefPm6tmzp/77v/9bY8eObbijAAAAjZbb64yYUNv7lNF0sM5Iw2CdkYbDOiMNh3VGrh1XZJ0RAACAhkYYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFF1CiNLly5VZGSk/Pz8FBMTo127dtXYd/ny5Ro6dKhCQkIUEhKi+Pj4S/YHAADXFrfDyLp165ScnKzU1FRlZWWpf//+SkhIUGFhYbX9t27dqgceeEBbtmzRjh07FBERodtuu03Hjx+vd/EAAKDxszgcDoc7G8TExGjQoEFasmSJJMlutysiIkJTpkzRjBkzLrt9VVWVQkJCtGTJEiUmJtZqnyUlJQoKClJxcbECAwPdKReN1CjrL02X0CRssr9juoQmw57f3XQJTYY1/IDpEuAhtf3+dmtmpLKyUrt371Z8fPxPA1itio+P144dO2o1Rnl5uc6dO6dWrVrV2KeiokIlJSUuLwAA0DS5FUZOnjypqqoqhYWFubSHhYUpPz+/VmM8/fTTateunUug+Xfp6ekKCgpyviIiItwpEwAANCIevZtmwYIFWrt2rd577z35+fnV2G/mzJkqLi52vo4dO+bBKgEAgCc1c6dz69at5eXlpYKCApf2goIChYeHX3LbhQsXasGCBfrb3/6mfv36XbKvr6+vfH193SkNAAA0Um7NjPj4+GjgwIGy2WzONrvdLpvNpiFDhtS43QsvvKA5c+YoMzNT0dHRda8WAAA0OW7NjEhScnKyxo0bp+joaA0ePFgZGRkqKytTUlKSJCkxMVHt27dXenq6JOn5559XSkqK1qxZo8jISOe1JQEBAQoICGjAQwEAAI2R22Fk7NixKioqUkpKivLz8xUVFaXMzEznRa25ubmyWn+acHnttddUWVmpX/ziFy7jpKamavbs2fWrHgAANHpurzNiAuuMXHtYZ6RhsM5Iw2GdkYbDOiPXjiuyzggAAEBDI4wAAACjCCMAAMAowggAADCKMAIAAIwijAAAAKMIIwAAwCjCCAAAMIowAgAAjCKMAAAAowgjAADAKMIIAAAwijACAACMIowAAACjCCMAAMAowggAADCKMAIAAIwijAAAAKMIIwAAwCjCCAAAMIowAgAAjCKMAAAAowgjAADAKMIIAAAwijACAACMIowAAACjCCMAAMAowggAADCKMAIAAIwijAAAAKMIIwAAwCjCCAAAMIowAgAAjCKMAAAAowgjAADAKMIIAAAwijACAACMIowAAACjCCMAAMAowggAADCKMAIAAIwijAAAAKMIIwAAwCjCCAAAMIowAgAAjCKMAAAAowgjAADAKMIIAAAwijACAACMIowAAACjCCMAAMAowggAADCKMAIAAIwijAAAAKMIIwAAwCjCCAAAMIowAgAAjCKMAAAAowgjAADAKMIIAAAwqk5hZOnSpYqMjJSfn59iYmK0a9euGvvu3btX9913nyIjI2WxWJSRkVHXWgEAQBPkdhhZt26dkpOTlZqaqqysLPXv318JCQkqLCystn95ebk6d+6sBQsWKDw8vN4FAwCApsXtMLJo0SJNmjRJSUlJ6t27t5YtWyZ/f3+tXLmy2v6DBg3Siy++qPvvv1++vr612kdFRYVKSkpcXgAAoGlyK4xUVlZq9+7dio+P/2kAq1Xx8fHasWNHgxWVnp6uoKAg5ysiIqLBxgYAAFcXt8LIyZMnVVVVpbCwMJf2sLAw5efnN1hRM2fOVHFxsfN17NixBhsbAABcXZqZLqA6vr6+tT6lAwAAGje3ZkZat24tLy8vFRQUuLQXFBRwcSoAAKgTt8KIj4+PBg4cKJvN5myz2+2y2WwaMmRIgxcHAACaPrdP0yQnJ2vcuHGKjo7W4MGDlZGRobKyMiUlJUmSEhMT1b59e6Wnp0s6f9Hrvn37nP8+fvy4srOzFRAQoK5duzbgoQAAgMbI7TAyduxYFRUVKSUlRfn5+YqKilJmZqbzotbc3FxZrT9NuJw4cUIDBgxwvl+4cKEWLlyo4cOHa+vWrfU/AgAA0KhZHA6Hw3QRl1NSUqKgoCAVFxcrMDDQdDnwgFHWX5ouoUnYZH/HdAlNhj2/u+kSmgxr+AHTJcBDavv9zbNpAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGAUYQQAABhFGAEAAEYRRgAAgFGEEQAAYBRhBAAAGEUYAQAARhFGAACAUYQRAABgFGEEAAAY1cx0AQCunM6vvGS6hCbj0K9MVwA0XcyMAAAAowgjAADAKMIIAAAwijACAACMIowAAACjCCMAAMAowggAADCKMAIAAIwijAAAAKMIIwAAwCjCCAAAMIowAgAAjCKMAAAAowgjAADAKMIIAAAwijACAACMIowAAACjCCMAAMAowggAADCKMAIAAIwijAAAAKMIIwAAwCjCCAAAMIowAgAAjCKMAAAAowgjAADAKMIIAAAwijACAACMIowAAACjCCMAAMAowggAADCqTmFk6dKlioyMlJ+fn2JiYrRr165L9n/nnXfUs2dP+fn5qW/fvtqwYUOdigUAAE2P22Fk3bp1Sk5OVmpqqrKystS/f38lJCSosLCw2v6ffvqpHnjgAU2YMEFffvmlxowZozFjxujrr7+ud/EAAKDxczuMLFq0SJMmTVJSUpJ69+6tZcuWyd/fXytXrqy2/+LFi3X77bfrySefVK9evTRnzhzdeOONWrJkSb2LBwAAjV8zdzpXVlZq9+7dmjlzprPNarUqPj5eO3bsqHabHTt2KDk52aUtISFB77//fo37qaioUEVFhfN9cXGxJKmkpMSdctGI/eA4Z7qEJsF+9qzpEpqMkjNVpktoMqz+/L/8WvHj97bD4bhkP7fCyMmTJ1VVVaWwsDCX9rCwMH3zzTfVbpOfn19t//z8/Br3k56erueee+6i9oiICHfKBfD0X0xX0GSEPG26gqYkyHQB8LAzZ84oKKjm/+5uhRFPmTlzpstsit1u1/fff6/Q0FBZLBaDlQFoaCUlJYqIiNCxY8cUGBhouhwADcjhcOjMmTNq167dJfu5FUZat24tLy8vFRQUuLQXFBQoPDy82m3Cw8Pd6i9Jvr6+8vX1dWkLDg52p1QAjUxgYCBhBGiCLjUj8iO3LmD18fHRwIEDZbPZnG12u102m01DhgypdpshQ4a49JekTZs21dgfAABcW9w+TZOcnKxx48YpOjpagwcPVkZGhsrKypSUlCRJSkxMVPv27ZWeni5Jmjp1qoYPH66XXnpJd911l9auXasvvvhCb7zxRsMeCQAAaJTcDiNjx45VUVGRUlJSlJ+fr6ioKGVmZjovUs3NzZXV+tOES2xsrNasWaNnn31WzzzzjLp166b3339fffr0abijANBo+fr6KjU19aJTswCuHRbH5e63AQAAuIJ4Ng0AADCKMAIAAIwijAAAAKMIIwAAwCjCCAAAMIowAgAAjCKMAPCot956Sx9++KHz/VNPPaXg4GDFxsbqu+++M1gZAFMIIwA8av78+WrevLkkaceOHVq6dKleeOEFtW7dWr///e8NVwfABBY9A+BR/v7++uabb3T99dfr6aefVl5env74xz9q7969GjFihIqKikyXCMDDmBkB4FEBAQE6deqUJOmjjz7SqFGjJEl+fn7617/+ZbI0AIa4/WwaAKiPUaNGaeLEiRowYIAOHDigO++8U5K0d+9eRUZGmi0OgBHMjADwqKVLl2rIkCEqKirSu+++q9DQUEnS7t279cADDxiuDoAJXDMCwKNyc3PVoUMHl6d7S5LD4dCxY8d0/fXXG6oMgCmEEQAe5eXlpby8PLVp08al/dSpU2rTpo2qqqoMVQbAFE7TAPComv7+KS0tlZ+fn4erAXA14AJWAB6RnJwsSbJYLEpJSZG/v7/zs6qqKu3cuVNRUVGGqgNgEmEEgEd8+eWXks7PjOzZs0c+Pj7Oz3x8fNS/f39Nnz7dVHkADOKaEQAelZSUpMWLFyswMNB0KQCuEoQRAABgFKdpAHhUWVmZFixYIJvNpsLCQtntdpfPv/32W0OVATCFMALAoyZOnKj/+7//00MPPaS2bdvKYrGYLgmAYZymAeBRwcHB+vDDDxUXF2e6FABXCdYZAeBRISEhatWqlekyAFxFCCMAPGrOnDlKSUlReXm56VIAXCU4TQPgihswYIDLtSGHDh2Sw+FQZGSkvL29XfpmZWV5ujwAhnEBK4ArbsyYMaZLAHAVY2YEAAAYxTUjAADAKE7TAPCokJCQatcWsVgs8vPzU9euXTV+/HglJSUZqA6ACYQRAB6VkpKiefPm6Y477tDgwYMlSbt27VJmZqZ+97vf6ciRI3rsscf0ww8/aNKkSYarBeAJXDMCwKPuu+8+jRo1So8++qhL++uvv66PPvpI7777rl599VW98cYb2rNnj6EqAXgSYQSARwUEBCg7O1tdu3Z1aT906JCioqJUWlqqw4cPq1+/fiorKzNUJQBP4gJWAB7VqlUrffDBBxe1f/DBB86VWcvKytSyZUtPlwbAEK4ZAeBRs2bN0mOPPaYtW7Y4rxn5/PPPtWHDBi1btkyStGnTJg0fPtxkmQA8iNM0ADxu+/btWrJkiXJyciRJPXr00JQpUxQbG2u4MgAmEEYAAIBRnKYBcMWVlJQoMDDQ+e9L+bEfgGsHMyMArjgvLy/l5eWpTZs2slqt1S565nA4ZLFYVFVVZaBCACYxMwLgitu8ebPzTpktW7YYrgbA1YaZEQAAYBTrjADwuE8++UQPPvigYmNjdfz4cUnS6tWrtW3bNsOVATCBMALAo959910lJCSoefPmysrKUkVFhSSpuLhY8+fPN1wdABMIIwA8au7cuVq2bJmWL18ub29vZ3tcXJyysrIMVgbAFMIIAI/KycnRsGHDLmoPCgrS6dOnPV8QAOMIIwA8Kjw8XIcOHbqofdu2bercubOBigCYRhgB4FGTJk3S1KlTtXPnTlksFp04cUJvv/22pk+frscee8x0eQAMYJ0RAB5x5MgRderUSTNmzJDdbtett96q8vJyDRs2TL6+vpo+fbqmTJliukwABrDOCACPsFqt6tixo2655RbdcsstGjFihM6cOaPS0lL17t1bAQEBpksEYAhhBIBHbN261fnauXOnKisr1blzZ40cOVIjR47UiBEjFBYWZrpMAAYQRgB43NmzZ/Xpp586w8muXbt07tw59ezZU3v37jVdHgAPI4wAMKayslLbt2/XX//6V73++usqLS3lQXnANYgwAsBjKisr9dlnn2nLli3O0zUREREaNmyYhg0bpuHDh+v66683XSYADyOMAPCIkSNHaufOnerUqZOGDx+uoUOHavjw4Wrbtq3p0gAYRhgB4BHe3t5q27atxowZoxEjRmj48OEKDQ01XRaAqwBhBIBHlJWV6ZNPPtHWrVu1ZcsWZWdnq3v37ho+fLgznFx33XWmywRgAGEEgBFnzpzRtm3bnNePfPXVV+rWrZu+/vpr06UB8DCWgwdgRIsWLdSqVSu1atVKISEhatasmfbv32+6LAAGMDMCwCPsdru++OIL52ma7du3q6ysTO3bt3euynrLLbeoY8eOpksF4GGEEQAeERgYqLKyMoWHh7ssCd+lSxfTpQEwjDACwCNef/113XLLLerevbvpUgBcZQgjAADAKC5gBQAARhFGAACAUYQRAABgFGEEAAAYRRgBAABGEUYAAIBRhBEAAGDU/wN4qSnQR9zyoQAAAABJRU5ErkJggg==",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "dm.plot.wbar(cmap=\"viridis\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Data transformation\n",
    "\n",
    "Data in its current form is difficult to understand and analyze. On one \n",
    "hand they are out of scale, and on the other they have both minimizing and \n",
    "maximizing criteria.\n",
    "\n",
    "<div class=\"alert alert-info\">\n",
    "Note: Scikit-Criteria objective preference\n",
    "\n",
    "For a design decision *Scikit-Criteria* always prefers **Maximize** objectives.\n",
    "There are some functionalities that trigger warnings against  **Minimize** \n",
    "criteria, and others that directly and others directly fail.\n",
    "</div>\n",
    "\n",
    "To solve these problems, we will use two processors:\n",
    "\n",
    "- First `InvertMinimize` which inverts the minimizing objectives.\n",
    "  by dividing out the inverse of each criterion value ($1/C_j$).\n",
    "- Second, `SumScaler` which will divide each criterion value by the total sum \n",
    "  of the criteria, taking all of them into the range $[0, 1]$.\n",
    "\n",
    "First we start by importing the two necessary modules."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "from skcriteria.preprocessing import invert_objectives, scalers"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Data in its current form is difficult to understand and analyze. \n",
    "The first thing we must do now is to reverse the maximization criteria.\n",
    "\n",
    "This involves:\n",
    "\n",
    "1. Create the transformer and store it in the `inverter` variable.\n",
    "2. Apply the transformation by calling the `transform` method of the transformer and\n",
    "   passing it as parameter our decision matrix `dm`.\n",
    "3. Save the transformed decision matrix in a new variable `dmt`.\n",
    "\n",
    "In code:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div class='decisionmatrix'>\n",
       "<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>autonomy[▲ 0.50]</th>\n",
       "      <th>comfort[▲ 0.05]</th>\n",
       "      <th>price[▲ 0.45]</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>VW</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>0.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ford</th>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>0.166667</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div><em class='decisionmatrix-dim'>2 Alternatives x 3 Criteria</em>\n",
       "</div>"
      ],
      "text/plain": [
       "      autonomy[▲ 0.50]  comfort[▲ 0.05]  price[▲ 0.45]\n",
       "VW                   1                2       0.333333\n",
       "Ford                 4                5       0.166667\n",
       "[2 Alternatives x 3 Criteria]"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "inverter = invert_objectives.InvertMinimize()\n",
    "dmt = inverter.transform(dm)\n",
    "dmt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The next step is to scale the values between $[0, 1]$ using the `SumScaler`.\n",
    "\n",
    "For this step we need\n",
    "\n",
    "1. Create the transformer and store it in the `inverter` variable.\n",
    "   In this case the *scalers* support a parameter called `target` which can \n",
    "   have three different values:\n",
    "   \n",
    "   - `target=\"matrix\"` The matrix $A$ is normalized.\n",
    "   - `target=\"weights\"` normalizes the weights $w$.\n",
    "   - `target=\"both\"` normalizes matrix $A$ and weights $w$.\n",
    "\n",
    "    In our case we are going to ask the scaler to scale both components of the \n",
    "    decision matrix (`target=\"both\"`)\n",
    "2. Apply the transformation by calling the `transform` method of the transformer and\n",
    "   passing it as parameter our decision matrix `dmt`.\n",
    "3. Save the transformed decision by overwriting the variable `dmt`.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div class='decisionmatrix'>\n",
       "<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>autonomy[▲ 0.50]</th>\n",
       "      <th>comfort[▲ 0.05]</th>\n",
       "      <th>price[▲ 0.45]</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>VW</th>\n",
       "      <td>0.2</td>\n",
       "      <td>0.285714</td>\n",
       "      <td>0.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ford</th>\n",
       "      <td>0.8</td>\n",
       "      <td>0.714286</td>\n",
       "      <td>0.333333</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div><em class='decisionmatrix-dim'>2 Alternatives x 3 Criteria</em>\n",
       "</div>"
      ],
      "text/plain": [
       "      autonomy[▲ 0.50]  comfort[▲ 0.05]  price[▲ 0.45]\n",
       "VW                 0.2         0.285714       0.666667\n",
       "Ford               0.8         0.714286       0.333333\n",
       "[2 Alternatives x 3 Criteria]"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "scaler = scalers.SumScaler(target=\"both\")\n",
    "dmt = scaler.transform(dmt)\n",
    "dmt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now we can analyze if the matrix graphically by creating\n",
    "a graph for the matrix, and another for the weights.\n",
    "\n",
    "<div class=\"alert alert-info\">\n",
    "Note: Advanced plots with Matplotlib\n",
    "\n",
    "If you need more information on how to make graphs using \n",
    "*Matplotlib* please che this tutorial https://matplotlib.org/stable/tutorials/index\n",
    "\n",
    "</div>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x500 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# we are going to user matplotlib capabilities of creat multiple figures\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# we create 2 axis with the same y axis\n",
    "fig, axs = plt.subplots(1, 2, figsize=(12, 5), sharey=True)\n",
    "\n",
    "# in the first axis we plot the criteria KDE\n",
    "dmt.plot.kde(ax=axs[0])\n",
    "axs[0].set_title(\"Criteria\")\n",
    "\n",
    "\n",
    "# in the second axis we plot the weights as bars\n",
    "dmt.plot.wbar(ax=axs[1])\n",
    "axs[1].set_title(\"Weights\")\n",
    "\n",
    "# adjust the layout of the figute based on the content\n",
    "fig.tight_layout()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Using this data to feed some MCDA methods\n",
    "\n",
    "### Weighted Sum Model\n",
    "\n",
    "Let's rank our dummy data by [Weighted Sum Model](https://en.wikipedia.org/wiki/Weighted_sum_model)\n",
    "\n",
    "First we need to import the required module"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "from skcriteria.agg import simple"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To use the methods of MCDA structure we proceed in the same way as when using transformers:\n",
    "\n",
    "1. We create the decision maker and store it in some variable (`dec` in our case).\n",
    "2. Execute the `evaluate()` method inside the decision maker to create the result.\n",
    "3. We store the result in some variable (`rank` in our case).\n",
    "\n",
    "<div class=\"alert alert-info\">\n",
    "Note: Hyper-parameters\n",
    "\n",
    "Some multi-criteria methods support \"*hyper parameters*\", which are \n",
    "provided at the time of creation of the decision maker.\n",
    "\n",
    "We will see an example with the *ELECTRE-1* method later on.\n",
    "\n",
    "</div>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div class='skcresult-rank skcresult'>\n",
       "<style type=\"text/css\">\n",
       "</style>\n",
       "<table id=\"T_35ad3\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th class=\"index_name level0\" >Alternatives</th>\n",
       "      <th id=\"T_35ad3_level0_col0\" class=\"col_heading level0 col0\" >VW</th>\n",
       "      <th id=\"T_35ad3_level0_col1\" class=\"col_heading level0 col1\" >Ford</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th id=\"T_35ad3_level0_row0\" class=\"row_heading level0 row0\" >Rank</th>\n",
       "      <td id=\"T_35ad3_row0_col0\" class=\"data row0 col0\" >2</td>\n",
       "      <td id=\"T_35ad3_row0_col1\" class=\"data row0 col1\" >1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<em class='skcresult-method'>Method: WeightedSumModel</em>\n",
       "</div>"
      ],
      "text/plain": [
       "Alternatives  VW  Ford\n",
       "Rank           2     1\n",
       "[Method: WeightedSumModel]"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dec = simple.WeightedSumModel()\n",
    "rank = dec.evaluate(dmt)  # we use the tansformed version of the data\n",
    "rank"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can see that `WeightedSumModel` prefers the alternative *Ford* over the *VW*.\n",
    "\n",
    "\n",
    "We can access the intermediate calculators of the method through the `e_` \n",
    "attribute of the result object., which (in the case of `WeightedSumModel`) \n",
    "contains the resulting scores"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<extra {'score'}>"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rank.e_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.41428571, 0.58571429])"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rank.e_.score"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Obviously you can acces all the parts of the ranking as attributes of \n",
    "result object"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([2, 1])"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rank.rank_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['VW', 'Ford'], dtype=object)"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rank.alternatives"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'WeightedSumModel'"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rank.method"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS)\n",
    "\n",
    "The following example will be approached with the \n",
    "[TOPSIS](https://en.wikipedia.org/wiki/TOPSIS). This method was chosen because \n",
    "of its popularity and because it uses another scaling technique \n",
    "(`VectorScaler`). \n",
    "\n",
    "So the first thing one would intuitively do is to invert the original matrix \n",
    "criteria (`dm`) and then apply the  normalization; but if we have several \n",
    "matrices or several methods this solution becomes cumbersome.\n",
    "\n",
    "The proposed solution of *Scikit-Criteria* is to offer `pipelines`. The\n",
    "pipelines combine one or several transformers and one decision-maker the\n",
    "facilitate the execution of the experiments.\n",
    "\n",
    "So, let's import the necessary modules for *TOPSIS* and the *pipelines*:\n",
    "\n",
    "<div class=\"alert alert-warning\">\n",
    "Distances and InvertMinimize\n",
    "\n",
    "Since `TOPSIS` uses distances as a comparison metric, it is not recommended to \n",
    "use the `InvertMinimize` transformer. Instead we use `NegateMinimize`.\n",
    "\n",
    "</div>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from skcriteria.agg import topsis # here lives TOPSIS\n",
    "from skcriteria.pipeline import mkpipe  # this function is for create pipelines"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The trick is that the weights still need to be scaled with `SumScaler` so be \n",
    "careful to assign the *targets* correctly in each transformer."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<SKCPipeline [steps=[('negateminimize', <NegateMinimize []>), ('vectorscaler', <VectorScaler [target='matrix']>), ('sumscaler', <SumScaler [target='weights']>), ('topsis', <TOPSIS [metric='euclidean']>)]]>"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pipe = mkpipe(\n",
    "    invert_objectives.NegateMinimize(),\n",
    "    scalers.VectorScaler(target=\"matrix\"),  # this scaler transform the matrix\n",
    "    scalers.SumScaler(target=\"weights\"),  # and this transform the weights\n",
    "    topsis.TOPSIS(),\n",
    ")\n",
    "\n",
    "pipe"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now we can directly call the pipeline `evaluate()` method with the original\n",
    "decision-matrix (`dm`).\n",
    "\n",
    "This method sequentially executes the three transformers and finally the evaluator to obtain a\n",
    "result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div class='skcresult-rank skcresult'>\n",
       "<style type=\"text/css\">\n",
       "</style>\n",
       "<table id=\"T_d14ce\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th class=\"index_name level0\" >Alternatives</th>\n",
       "      <th id=\"T_d14ce_level0_col0\" class=\"col_heading level0 col0\" >VW</th>\n",
       "      <th id=\"T_d14ce_level0_col1\" class=\"col_heading level0 col1\" >Ford</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th id=\"T_d14ce_level0_row0\" class=\"row_heading level0 row0\" >Rank</th>\n",
       "      <td id=\"T_d14ce_row0_col0\" class=\"data row0 col0\" >2</td>\n",
       "      <td id=\"T_d14ce_row0_col1\" class=\"data row0 col1\" >1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<em class='skcresult-method'>Method: TOPSIS</em>\n",
       "</div>"
      ],
      "text/plain": [
       "Alternatives  VW  Ford\n",
       "Rank           2     1\n",
       "[Method: TOPSIS]"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rank = pipe.evaluate(dm)\n",
    "rank"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<extra {'similarity', 'ideal', 'anti_ideal'}>\n",
      "Ideal: [ 0.48507125  0.04642383 -0.20124612]\n",
      "Anti-Ideal: [ 0.12126781  0.01856953 -0.40249224]\n",
      "Similarity index: [0.35548671 0.64451329]\n"
     ]
    }
   ],
   "source": [
    "print(rank.e_)\n",
    "print(\"Ideal:\", rank.e_.ideal)\n",
    "print(\"Anti-Ideal:\", rank.e_.anti_ideal)\n",
    "print(\"Similarity index:\", rank.e_.similarity)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Where the `ideal` and `anti_ideal` are the normalizated sintetic better and \n",
    "worst altenatives created by TOPSIS, and the `similarity` is how far from the \n",
    "*anti-ideal* and how closer to the *ideal* are the real alternatives"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### ÉLimination et Choix Traduisant la REalité (ELECTRE)\n",
    "\n",
    "For our final example, we are going to use the\n",
    "method [ELECTRE-I](https://en.wikipedia.org/wiki/%C3%89LECTRE) which has two\n",
    "particularities:\n",
    "\n",
    "1. It does not return a ranking but a kernel.\n",
    "2. It supports two hyper-parameters: a concordance threshold `p` and a discordance threshold `q`. \n",
    "\n",
    "Let's test the default threshold (`p=0.65, q=0.35`) but with two normalizations\n",
    "for different matrix: `VectorScaler` and `SumScaler`.\n",
    "\n",
    "For this we will make two pipelines"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "from skcriteria.agg import electre\n",
    "\n",
    "\n",
    "pipe_vector = mkpipe(\n",
    "    invert_objectives.InvertMinimize(),\n",
    "    scalers.VectorScaler(target=\"matrix\"),  # this scaler transform the matrix\n",
    "    scalers.SumScaler(target=\"weights\"),  # and this transform the weights\n",
    "    electre.ELECTRE1(p=0.65, q=0.35),\n",
    ")\n",
    "\n",
    "pipe_sum = mkpipe(\n",
    "    invert_objectives.InvertMinimize(),\n",
    "    scalers.SumScaler(target=\"weights\"),  # transform the matrix and weights\n",
    "    electre.ELECTRE1(p=0.65, q=0.35),\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div class='skcresult-kernel skcresult'>\n",
       "<style type=\"text/css\">\n",
       "</style>\n",
       "<table id=\"T_7195d\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th class=\"index_name level0\" >Alternatives</th>\n",
       "      <th id=\"T_7195d_level0_col0\" class=\"col_heading level0 col0\" >VW</th>\n",
       "      <th id=\"T_7195d_level0_col1\" class=\"col_heading level0 col1\" >Ford</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th id=\"T_7195d_level0_row0\" class=\"row_heading level0 row0\" >Kernel</th>\n",
       "      <td id=\"T_7195d_row0_col0\" class=\"data row0 col0\" >True</td>\n",
       "      <td id=\"T_7195d_row0_col1\" class=\"data row0 col1\" >True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<em class='skcresult-method'>Method: ELECTRE1</em>\n",
       "</div>"
      ],
      "text/plain": [
       "Alternatives    VW  Ford\n",
       "Kernel        True  True\n",
       "[Method: ELECTRE1]"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "kernel_vector = pipe_vector.evaluate(dm)\n",
    "kernel_vector"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div class='skcresult-kernel skcresult'>\n",
       "<style type=\"text/css\">\n",
       "</style>\n",
       "<table id=\"T_c4ed0\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th class=\"index_name level0\" >Alternatives</th>\n",
       "      <th id=\"T_c4ed0_level0_col0\" class=\"col_heading level0 col0\" >VW</th>\n",
       "      <th id=\"T_c4ed0_level0_col1\" class=\"col_heading level0 col1\" >Ford</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th id=\"T_c4ed0_level0_row0\" class=\"row_heading level0 row0\" >Kernel</th>\n",
       "      <td id=\"T_c4ed0_row0_col0\" class=\"data row0 col0\" >True</td>\n",
       "      <td id=\"T_c4ed0_row0_col1\" class=\"data row0 col1\" >True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<em class='skcresult-method'>Method: ELECTRE1</em>\n",
       "</div>"
      ],
      "text/plain": [
       "Alternatives    VW  Ford\n",
       "Kernel        True  True\n",
       "[Method: ELECTRE1]"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "kernel_sum = pipe_sum.evaluate(dm)\n",
    "kernel_sum"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As can be seen for this case both scalings give the same results"
   ]
  }
 ],
 "metadata": {
  "celltoolbar": "Edit 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": "3.10.12"
  },
  "vscode": {
   "interpreter": {
    "hash": "ead1b95f633dc9c51826328e1846203f51a198c6fb5f2884a80417ba131d4e82"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}