{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# ML - Modeling"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Motivation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "from pathlib import Path\n",
    "\n",
    "sns.set_theme(style=\"whitegrid\")\n",
    "\n",
    "%matplotlib inline"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's consider the famous wine dataset by [P. Cortez, A. Cerdeira, F. Almeida, T. Matos and J. Reis, 2009](http://dx.doi.org/10.1016/j.dss.2009.05.016). It consists of two datasets related to red and white variants of the __*Portuguese*__ _\"Vinho Verde\"_ wine, each one with 11 attributes. tThe target is the quality of the wine based on sensory data and it is a score between 0 and 10.   "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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>fixed acidity</th>\n",
       "      <th>volatile acidity</th>\n",
       "      <th>citric acid</th>\n",
       "      <th>residual sugar</th>\n",
       "      <th>chlorides</th>\n",
       "      <th>free sulfur dioxide</th>\n",
       "      <th>total sulfur dioxide</th>\n",
       "      <th>density</th>\n",
       "      <th>pH</th>\n",
       "      <th>sulphates</th>\n",
       "      <th>alcohol</th>\n",
       "      <th>quality</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>7.4</td>\n",
       "      <td>0.70</td>\n",
       "      <td>0.00</td>\n",
       "      <td>1.9</td>\n",
       "      <td>0.076</td>\n",
       "      <td>11.0</td>\n",
       "      <td>34.0</td>\n",
       "      <td>0.9978</td>\n",
       "      <td>3.51</td>\n",
       "      <td>0.56</td>\n",
       "      <td>9.4</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>7.8</td>\n",
       "      <td>0.88</td>\n",
       "      <td>0.00</td>\n",
       "      <td>2.6</td>\n",
       "      <td>0.098</td>\n",
       "      <td>25.0</td>\n",
       "      <td>67.0</td>\n",
       "      <td>0.9968</td>\n",
       "      <td>3.20</td>\n",
       "      <td>0.68</td>\n",
       "      <td>9.8</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7.8</td>\n",
       "      <td>0.76</td>\n",
       "      <td>0.04</td>\n",
       "      <td>2.3</td>\n",
       "      <td>0.092</td>\n",
       "      <td>15.0</td>\n",
       "      <td>54.0</td>\n",
       "      <td>0.9970</td>\n",
       "      <td>3.26</td>\n",
       "      <td>0.65</td>\n",
       "      <td>9.8</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>11.2</td>\n",
       "      <td>0.28</td>\n",
       "      <td>0.56</td>\n",
       "      <td>1.9</td>\n",
       "      <td>0.075</td>\n",
       "      <td>17.0</td>\n",
       "      <td>60.0</td>\n",
       "      <td>0.9980</td>\n",
       "      <td>3.16</td>\n",
       "      <td>0.58</td>\n",
       "      <td>9.8</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>7.4</td>\n",
       "      <td>0.70</td>\n",
       "      <td>0.00</td>\n",
       "      <td>1.9</td>\n",
       "      <td>0.076</td>\n",
       "      <td>11.0</td>\n",
       "      <td>34.0</td>\n",
       "      <td>0.9978</td>\n",
       "      <td>3.51</td>\n",
       "      <td>0.56</td>\n",
       "      <td>9.4</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   fixed acidity  volatile acidity  citric acid  residual sugar  chlorides  \\\n",
       "0            7.4              0.70         0.00             1.9      0.076   \n",
       "1            7.8              0.88         0.00             2.6      0.098   \n",
       "2            7.8              0.76         0.04             2.3      0.092   \n",
       "3           11.2              0.28         0.56             1.9      0.075   \n",
       "4            7.4              0.70         0.00             1.9      0.076   \n",
       "\n",
       "   free sulfur dioxide  total sulfur dioxide  density    pH  sulphates  \\\n",
       "0                 11.0                  34.0   0.9978  3.51       0.56   \n",
       "1                 25.0                  67.0   0.9968  3.20       0.68   \n",
       "2                 15.0                  54.0   0.9970  3.26       0.65   \n",
       "3                 17.0                  60.0   0.9980  3.16       0.58   \n",
       "4                 11.0                  34.0   0.9978  3.51       0.56   \n",
       "\n",
       "   alcohol  quality  \n",
       "0      9.4        5  \n",
       "1      9.8        5  \n",
       "2      9.8        5  \n",
       "3      9.8        6  \n",
       "4      9.4        5  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_filepath = \"https://raw.githubusercontent.com/aoguedao/neural_computing_workshop/main/data/winequality-red.csv\"\n",
    "# data_filepath = Path().resolve().parent / \"data\" / \"winequality-red.csv\"  # If you are running locally\n",
    "data = pd.read_csv(data_filepath, sep=\";\")\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x7ff32031f670>"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1920x1200 with 11 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "normalized_data = (data - data.min()) / (data.max() - data.min())\n",
    "sns.relplot(\n",
    "    data=normalized_data.melt(id_vars=\"quality\"),\n",
    "    kind=\"scatter\",\n",
    "    x=\"value\",\n",
    "    y=\"quality\",\n",
    "    col=\"variable\",\n",
    "    col_wrap=4,\n",
    "    height=4,\n",
    "    aspect=1.2,\n",
    ")\n"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "A typical problem would be to predict the quality of a new wine, either through its score or a classification as good/bad wine. \n",
    "\n",
    "__*Can we come out with a mathematical model for predicting/classifing wine without specific rules?*__"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Modeling"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Suppose that we observe a quantitative response $y$ and $p$ different predictors, $ X_1, X_2, \\ldots, X_p$. We assume that there is some relationship between $Y$ and $X = (X_1, X_2,  \\ldots , X_p)$, which can be written in the very general form\n",
    "$$\n",
    "y = f(X) + \\epsilon\n",
    "$$\n",
    "Here $f$ is some fixed but unknown function of $X$, and $\\epsilon$ is a random error term, which is independent of $X$ and has mean zero."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Prediction"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In many situations, a set of inputs $X$ are readily available, but the output $y$ cannot be easily obtained. In this setting, since the error term averages to zero, we can predict $y$ using\n",
    "\n",
    "$$\n",
    "\\hat{y} = \\hat{f}(X),\n",
    "$$\n",
    "\n",
    "where $\\hat{f}$ represents our estimate for $f$, and $\\hat{y}$ represents the resulting prediction for $Y$ . In this setting, $\\hat{f}$ is often treated as a __black-box__, in the sense\n",
    "that one is not typically concerned with the exact form of $\\hat{f}$, provided that it yields accurate predictions for $y$."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Estimation"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now the natural question is: _How do we estimate $f$?_\n",
    "\n",
    "In this workshop we will study several techniques and algorithms, but generally speaking, the idea is to take the observed data for a _learning_ process. These observations are called __Training Data__, because we will use these training observations to train, or teach, our method how to estimate $f$. In other words, we are looking for\n",
    "$$\n",
    "y \\approx \\hat{f}(X)\n",
    "$$\n",
    "\n",
    "Broadly speaking, most statistical learning methods for this task can be characterized as either _parametric_ or _non-parametric_. Parametric models make assumptions about the functional form or shape of $f$ in order to reduce the searching space. A typical example is Linear Regression, where we will need to estimate/fit/train only a few coefficients. On the other hand, non-parametric models do not make explicit assumptions about f, instead they seek an estimate of f that gets as close to the data points as possible. As you can imagine, the parametric models can be very interpretable and non-parametric models can be more accurate. It is important to select an adequate model depending on the trade-off between prediction and interpretability we need."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![Complexity Interpretability](../images/complexity_interpretability.gif)\n",
    "\n",
    "[Image Source](https://ieeexplore.ieee.org/document/8844682/figures#figures)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Most classical machine learning problems fall into one of two categories: _supervised_ or _unsupervised_. The example with the wine dataset is supervised, since we have labels for each sample. If these labels are numeric (score of wine quality) we are in a __Regression__ model; however, if labels are categories (good/bad quality), it is called a __Classification__ model.\n",
    "\n",
    "By contrast, unsupervised learning describes a more challenging situation where observations do not have any label. The situation is referred to as unsupervised because we lack a response variable that can supervise our analysis. A classical example is a __Clustering__ model, when the goal is to find relationships between samples and create groups."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Assessing Model Accuracy"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In order to evaluate the performance of a model on a given data set, we need some way to measure how well its predictions actually match the observed data.\n",
    "\n",
    "Let's define the concept of __*Metric*__, as such functions can explain the performance of a model.\n",
    "\n",
    "The choice of metric completely depends on the type of model and the implementation plan of the model."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Regression Metrics"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We know that target values of regression models are numeric (usually continuous) values. Then we can use metrics based on normed spaces or something similar."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### R² score, the coefficient of determination\n"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "It is the proportion of the variation in the dependent variable that is predictable from the independent variables. It provides an indication of goodness of fit, and therefore a measure of how well unseen samples are likely to be predicted by the model through the proportion of explained variance.\n",
    "\n",
    "If $\\hat{y}_i = \\hat{f}(x_i)$ is the predicted value of the $i$-th sample and $y_i$ is the corresponding true value, then the coefficient of determination is defined as:\n",
    "\n",
    "$$\n",
    "R^2(y, \\hat{y}) = 1 - \\frac{\\sum_{i=1}^n \\left( y_i - \\hat{y}_i\\right)^2}{\\sum_{i=1}^n \\left( y_i - \\bar{y}_i\\right)^2}\n",
    "= 1 - \\frac{\\sum_{i=1}^n e_i^2}{\\sum_{i=1}^n \\left( y_i - \\bar{y}_i\\right)^2}\n",
    "$$\n",
    "\n",
    "where $n$ is the total of samples, $y = \\tfrac{1}{n} \\sum_{i=1}^n y_i$ (the mean value).\n",
    "\n",
    "Since we can define the residuals as $e_i = y_i - \\hat{y}_i$ is isual to read in literature the analogous definition\n",
    "\n",
    "$$\n",
    "R^2(y, \\hat{y})  = 1 - \\frac{SS_{\\text{res}}}{SS_{\\text{tot}}}\n",
    "$$\n",
    "\n",
    "where $SS_{\\text{res}} = \\sum_{i=1}^n \\left( y_i - \\hat{y}_i\\right)^2 = \\sum_{i=1}^n e_i^2$ is called the _residual sum of squares_ and $SS_{\\text{tot}} = \\sum_{i=1}^n \\left( y_i - \\bar{y}_i\\right)^2$ is the _total sum of squares_.\n",
    "\n",
    "\n",
    "Note that the best possible score is 1.0 and it can be negative (because the model can be arbitrarily worse). A constant model that always predicts the expected (average) value of $y$, disregarding the input features, would get an  score of 0.0."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Mean squared error"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The mean square error corresponds to the expected value of the squared (quadratic) error or $\\ell_2$ - norm loss. It is defined as \n",
    "\n",
    "$$\n",
    "MSE(y, \\hat{y}) = \\frac{1}{n} \\sum_{i=1}^n \\left( y_i - \\hat{y}_i \\right)^2\n",
    "$$"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Mean absolute error"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The mean absolute error corresponds to the expected value of the absolute error or $\\ell_1$-norm loss. It is defined as\n",
    "\n",
    "$$\n",
    "MAE(y, \\hat{y}) = \\frac{1}{n} \\sum_{i=1}^n \\left\\lvert y_i - \\hat{y}_i \\right\\rvert\n",
    "$$"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Classification Metrics"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In order to measure a classification model we need different types of metrics, since we are working with categories. Before defining metrics, we will introduce a very useful tool for classification tasks."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Confusion Matrix"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "A confusion matrix, also known as an error matrix, is a specific table layout that allows visualization of the performance of an algorithm. Each row of the matrix represents the instances in an actual class, while each column represents the instances in a predicted class, or vice versa – both variants are found in literature. The name stems from the fact that it makes it easy to see whether the system is confusing two classes (i.e. commonly mislabeling one as another). [- Source -](https://en.wikipedia.org/wiki/Confusion_matrix)\n",
    "\n",
    "For a binary classification problem a confusion matrix looks like this:"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![confusion_matrix](../images/confusion_matrix.png)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Initially, the aim is to maximize the sum of the well-classified elements, however, this depends on the problem to be solved."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Accuracy"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "$$\\textrm{accuracy}= \\frac{TP+TN}{TP+TN+FP+FN}$$"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Recall"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "$$\\textrm{recall} = \\frac{TP}{TP+FN}$$"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Precision"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "$$\\textrm{precision} = \\frac{TP}{TP+FP} $$"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### F-Score"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "$$\\text{F-score} = 2\\times \\frac{  \\textrm{precision} \\times \\textrm{recall} }{  \\textrm{precision} + \\textrm{recall} } $$"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's take for example a really bad model for the wine dataset. Consider a random predictor between the minimum and the maximum wine quaility."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "def random_model(X, target):\n",
    "    values = X[target]\n",
    "    min_target = values.min()\n",
    "    max_target = values.max()\n",
    "    return np.random.uniform(low=min_target, high=max_target, size=X.shape[0])\n"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can compute any metric with a few lines of code."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2.7120489387905935"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.metrics import mean_squared_error\n",
    "\n",
    "y_true = data[\"quality\"]\n",
    "y_pred = random_model(data, \"quality\")\n",
    "mean_squared_error(y_true, y_pred)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Is this a good model?\n",
    "\n",
    "Answer:\n",
    "\n",
    "![box](../images/box.jpg)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.9.13 ('pinn')",
   "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": "3.10.9"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "b495ef8c557e1213b070efa440d5756e52b9d742e01b39c369ce0fdb1e54097c"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}