{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "21952f3b-6421-45dd-bb7f-02c370731460",
   "metadata": {},
   "source": [
    "### Session 4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "de7940d2-2f9b-4a6b-910d-8166e0592d77",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Learning Objectives:\n",
    "# 1. Dimensionality reduction techniques - Principal Components Analysis"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fed19881-6bec-4a3f-9f42-37cb53572aa9",
   "metadata": {},
   "source": [
    "## Breakfast Cereals Example"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0479c533-ab83-4e85-b23d-468677ff9fde",
   "metadata": {},
   "source": [
    "\n",
    "#### Data were collected on the nutritional information and consumer rating of 77 breakfast cereals.1 The consumer rating is a rating of cereal “healthiness” for consumer information (not a rating by consumers). For each cereal, the data include 13 numerical variables, and we are interested in reducing this dimension. For each cereal, the information is based on a bowl of cereal rather than a serving size, because most people simply fill a cereal bowl (resulting in constant volume, but not weight). \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "3f164ffe-2128-4959-9e59-d36db02df1eb",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "16e08812-fe63-4aa2-8212-4d318d8b2f49",
   "metadata": {},
   "outputs": [],
   "source": [
    "sns.set_theme(style=\"whitegrid\", palette=\"pastel\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "856be90b-5b80-4f08-9014-d306904a9c1e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(77, 16)\n"
     ]
    }
   ],
   "source": [
    "df = pd. read_csv(r'/Users/patriciaxufre/Documents/SBE - Disciplinas/2957 | ABA/2024-25/Datasets Examples/Cereals.csv')\n",
    "print(df.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "694a8acf-8d1e-4070-93e8-2fdb62a50ae8",
   "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>name</th>\n",
       "      <th>mfr</th>\n",
       "      <th>type</th>\n",
       "      <th>calories</th>\n",
       "      <th>protein</th>\n",
       "      <th>fat</th>\n",
       "      <th>sodium</th>\n",
       "      <th>fiber</th>\n",
       "      <th>carbo</th>\n",
       "      <th>sugars</th>\n",
       "      <th>potass</th>\n",
       "      <th>vitamins</th>\n",
       "      <th>shelf</th>\n",
       "      <th>weight</th>\n",
       "      <th>cups</th>\n",
       "      <th>rating</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>100%_Bran</td>\n",
       "      <td>N</td>\n",
       "      <td>C</td>\n",
       "      <td>70</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>130</td>\n",
       "      <td>10.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>280.0</td>\n",
       "      <td>25</td>\n",
       "      <td>3</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.33</td>\n",
       "      <td>68.402973</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>100%_Natural_Bran</td>\n",
       "      <td>Q</td>\n",
       "      <td>C</td>\n",
       "      <td>120</td>\n",
       "      <td>3</td>\n",
       "      <td>5</td>\n",
       "      <td>15</td>\n",
       "      <td>2.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>135.0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.00</td>\n",
       "      <td>33.983679</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>All-Bran</td>\n",
       "      <td>K</td>\n",
       "      <td>C</td>\n",
       "      <td>70</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>260</td>\n",
       "      <td>9.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>320.0</td>\n",
       "      <td>25</td>\n",
       "      <td>3</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.33</td>\n",
       "      <td>59.425505</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>All-Bran_with_Extra_Fiber</td>\n",
       "      <td>K</td>\n",
       "      <td>C</td>\n",
       "      <td>50</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>140</td>\n",
       "      <td>14.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>330.0</td>\n",
       "      <td>25</td>\n",
       "      <td>3</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.50</td>\n",
       "      <td>93.704912</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Almond_Delight</td>\n",
       "      <td>R</td>\n",
       "      <td>C</td>\n",
       "      <td>110</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>200</td>\n",
       "      <td>1.0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>25</td>\n",
       "      <td>3</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.75</td>\n",
       "      <td>34.384843</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                        name mfr type  calories  protein  fat  sodium  fiber  \\\n",
       "0                  100%_Bran   N    C        70        4    1     130   10.0   \n",
       "1          100%_Natural_Bran   Q    C       120        3    5      15    2.0   \n",
       "2                   All-Bran   K    C        70        4    1     260    9.0   \n",
       "3  All-Bran_with_Extra_Fiber   K    C        50        4    0     140   14.0   \n",
       "4             Almond_Delight   R    C       110        2    2     200    1.0   \n",
       "\n",
       "   carbo  sugars  potass  vitamins  shelf  weight  cups     rating  \n",
       "0    5.0     6.0   280.0        25      3     1.0  0.33  68.402973  \n",
       "1    8.0     8.0   135.0         0      3     1.0  1.00  33.983679  \n",
       "2    7.0     5.0   320.0        25      3     1.0  0.33  59.425505  \n",
       "3    8.0     0.0   330.0        25      3     1.0  0.50  93.704912  \n",
       "4   14.0     8.0     NaN        25      3     1.0  0.75  34.384843  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "f2f037a3-9496-4aa5-a565-2073961c0fee",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 77 entries, 0 to 76\n",
      "Data columns (total 16 columns):\n",
      " #   Column    Non-Null Count  Dtype  \n",
      "---  ------    --------------  -----  \n",
      " 0   name      77 non-null     object \n",
      " 1   mfr       77 non-null     object \n",
      " 2   type      77 non-null     object \n",
      " 3   calories  77 non-null     int64  \n",
      " 4   protein   77 non-null     int64  \n",
      " 5   fat       77 non-null     int64  \n",
      " 6   sodium    77 non-null     int64  \n",
      " 7   fiber     77 non-null     float64\n",
      " 8   carbo     76 non-null     float64\n",
      " 9   sugars    76 non-null     float64\n",
      " 10  potass    75 non-null     float64\n",
      " 11  vitamins  77 non-null     int64  \n",
      " 12  shelf     77 non-null     int64  \n",
      " 13  weight    77 non-null     float64\n",
      " 14  cups      77 non-null     float64\n",
      " 15  rating    77 non-null     float64\n",
      "dtypes: float64(7), int64(6), object(3)\n",
      "memory usage: 9.8+ KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "26b38437-0b4c-4cab-9913-d7c27ec4b3de",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.decomposition import PCA"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "ca912145-e7b2-4b40-8d6a-6ab1c27e02fa",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of rows after removing the observations with missing values:  74\n"
     ]
    }
   ],
   "source": [
    "# remove observations with missing values\n",
    "reduced_df = df.dropna()\n",
    "print('Number of rows after removing the observations with missing values: ', len(reduced_df))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "4b1f6ee8-3772-49bc-a7ec-e1fa8e6fdf8e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Pre-process the Dataset\n",
    "std_scaler = StandardScaler()\n",
    "scaled_df = std_scaler.fit_transform(reduced_df.iloc[:,3:15])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "id": "935c3039-c658-406e-88bb-d44506eb0b45",
   "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>PC1</th>\n",
       "      <th>PC2</th>\n",
       "      <th>PC3</th>\n",
       "      <th>PC4</th>\n",
       "      <th>PC5</th>\n",
       "      <th>PC6</th>\n",
       "      <th>PC7</th>\n",
       "      <th>PC8</th>\n",
       "      <th>PC9</th>\n",
       "      <th>PC10</th>\n",
       "      <th>PC11</th>\n",
       "      <th>PC12</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Standard Deviation</th>\n",
       "      <td>1.8344</td>\n",
       "      <td>1.6381</td>\n",
       "      <td>1.3455</td>\n",
       "      <td>1.0156</td>\n",
       "      <td>0.9989</td>\n",
       "      <td>0.8362</td>\n",
       "      <td>0.8179</td>\n",
       "      <td>0.6494</td>\n",
       "      <td>0.5639</td>\n",
       "      <td>0.3050</td>\n",
       "      <td>0.2389</td>\n",
       "      <td>0.1353</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Proportion of Variance</th>\n",
       "      <td>0.2766</td>\n",
       "      <td>0.2206</td>\n",
       "      <td>0.1488</td>\n",
       "      <td>0.0848</td>\n",
       "      <td>0.0820</td>\n",
       "      <td>0.0575</td>\n",
       "      <td>0.0550</td>\n",
       "      <td>0.0347</td>\n",
       "      <td>0.0261</td>\n",
       "      <td>0.0076</td>\n",
       "      <td>0.0047</td>\n",
       "      <td>0.0015</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Cumulative proportion</th>\n",
       "      <td>0.2766</td>\n",
       "      <td>0.4972</td>\n",
       "      <td>0.6460</td>\n",
       "      <td>0.7308</td>\n",
       "      <td>0.8129</td>\n",
       "      <td>0.8704</td>\n",
       "      <td>0.9253</td>\n",
       "      <td>0.9600</td>\n",
       "      <td>0.9862</td>\n",
       "      <td>0.9938</td>\n",
       "      <td>0.9985</td>\n",
       "      <td>1.0000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                           PC1     PC2     PC3     PC4     PC5     PC6  \\\n",
       "Standard Deviation      1.8344  1.6381  1.3455  1.0156  0.9989  0.8362   \n",
       "Proportion of Variance  0.2766  0.2206  0.1488  0.0848  0.0820  0.0575   \n",
       "Cumulative proportion   0.2766  0.4972  0.6460  0.7308  0.8129  0.8704   \n",
       "\n",
       "                           PC7     PC8     PC9    PC10    PC11    PC12  \n",
       "Standard Deviation      0.8179  0.6494  0.5639  0.3050  0.2389  0.1353  \n",
       "Proportion of Variance  0.0550  0.0347  0.0261  0.0076  0.0047  0.0015  \n",
       "Cumulative proportion   0.9253  0.9600  0.9862  0.9938  0.9985  1.0000  "
      ]
     },
     "execution_count": 68,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "# Principal Component Analysis\n",
    "pcs = PCA()\n",
    "pcs.fit(scaled_df)\n",
    "pcsSummary = pd.DataFrame({'Standard Deviation': np.sqrt(pcs.explained_variance_),\n",
    "                           'Proportion of Variance': pcs.explained_variance_ratio_,\n",
    "                           'Cumulative proportion': np.cumsum(pcs.explained_variance_ratio_)})\n",
    "pcsSummary = pcsSummary.transpose()\n",
    "pcsSummary.columns = ['PC{}'.format(i) for i in range(1, len(pcsSummary.columns)+1)]\n",
    "pcsSummary.round(4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "7109ab8c-6c81-4533-9e58-3d37b7e5451c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "nums = np.arange(12)\n",
    "var_ratio = np.cumsum(pcs.explained_variance_ratio_)\n",
    "\n",
    "plt.figure(figsize=(8,5))\n",
    "plt.grid(True, linestyle='--')\n",
    "plt.plot(nums,var_ratio,marker='o')\n",
    "plt.xlabel('n_components')\n",
    "plt.ylabel('Explained variance ratio')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "d74c0081-5490-46e2-ba46-ed4315f720b0",
   "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>PC1</th>\n",
       "      <th>PC2</th>\n",
       "      <th>PC3</th>\n",
       "      <th>PC4</th>\n",
       "      <th>PC5</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>calories</th>\n",
       "      <td>0.036594</td>\n",
       "      <td>0.571142</td>\n",
       "      <td>-0.077927</td>\n",
       "      <td>-0.164032</td>\n",
       "      <td>0.186667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>protein</th>\n",
       "      <td>0.330888</td>\n",
       "      <td>-0.045367</td>\n",
       "      <td>0.326405</td>\n",
       "      <td>-0.281265</td>\n",
       "      <td>0.372134</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>fat</th>\n",
       "      <td>0.212549</td>\n",
       "      <td>0.249143</td>\n",
       "      <td>-0.291274</td>\n",
       "      <td>-0.124324</td>\n",
       "      <td>0.597422</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>sodium</th>\n",
       "      <td>-0.050894</td>\n",
       "      <td>0.304684</td>\n",
       "      <td>0.343108</td>\n",
       "      <td>-0.168916</td>\n",
       "      <td>-0.292344</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>fiber</th>\n",
       "      <td>0.458623</td>\n",
       "      <td>-0.201029</td>\n",
       "      <td>0.173912</td>\n",
       "      <td>-0.075295</td>\n",
       "      <td>-0.229653</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>carbo</th>\n",
       "      <td>-0.268609</td>\n",
       "      <td>0.175660</td>\n",
       "      <td>0.513002</td>\n",
       "      <td>-0.071305</td>\n",
       "      <td>0.191830</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>sugars</th>\n",
       "      <td>0.081440</td>\n",
       "      <td>0.364844</td>\n",
       "      <td>-0.495338</td>\n",
       "      <td>0.016033</td>\n",
       "      <td>-0.360371</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>potass</th>\n",
       "      <td>0.502603</td>\n",
       "      <td>-0.070345</td>\n",
       "      <td>0.130460</td>\n",
       "      <td>-0.112708</td>\n",
       "      <td>-0.124888</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>vitamins</th>\n",
       "      <td>0.018839</td>\n",
       "      <td>0.300574</td>\n",
       "      <td>0.327563</td>\n",
       "      <td>0.594798</td>\n",
       "      <td>-0.105582</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>shelf</th>\n",
       "      <td>0.308929</td>\n",
       "      <td>0.065114</td>\n",
       "      <td>0.000546</td>\n",
       "      <td>0.667703</td>\n",
       "      <td>0.265485</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>weight</th>\n",
       "      <td>0.257160</td>\n",
       "      <td>0.448962</td>\n",
       "      <td>0.122030</td>\n",
       "      <td>-0.160396</td>\n",
       "      <td>-0.232905</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>cups</th>\n",
       "      <td>-0.371154</td>\n",
       "      <td>0.106553</td>\n",
       "      <td>0.082695</td>\n",
       "      <td>-0.030683</td>\n",
       "      <td>0.115826</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               PC1       PC2       PC3       PC4       PC5\n",
       "calories  0.036594  0.571142 -0.077927 -0.164032  0.186667\n",
       "protein   0.330888 -0.045367  0.326405 -0.281265  0.372134\n",
       "fat       0.212549  0.249143 -0.291274 -0.124324  0.597422\n",
       "sodium   -0.050894  0.304684  0.343108 -0.168916 -0.292344\n",
       "fiber     0.458623 -0.201029  0.173912 -0.075295 -0.229653\n",
       "carbo    -0.268609  0.175660  0.513002 -0.071305  0.191830\n",
       "sugars    0.081440  0.364844 -0.495338  0.016033 -0.360371\n",
       "potass    0.502603 -0.070345  0.130460 -0.112708 -0.124888\n",
       "vitamins  0.018839  0.300574  0.327563  0.594798 -0.105582\n",
       "shelf     0.308929  0.065114  0.000546  0.667703  0.265485\n",
       "weight    0.257160  0.448962  0.122030 -0.160396 -0.232905\n",
       "cups     -0.371154  0.106553  0.082695 -0.030683  0.115826"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pcsComponents = pd.DataFrame(pcs.components_.transpose(),\n",
    "                             columns = pcsSummary.columns, index= df.iloc[:,3:15].columns)\n",
    "pcsComponents.iloc[:,:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5fb6e4e5-3b4d-4a9e-84f1-1f93035b3e27",
   "metadata": {},
   "outputs": [],
   "source": [
    "# In PCA, loadings indicate the contribution of each original feature to the principal components.\n",
    "# Positive or negative: direction of the relationship.\n",
    "# Higher absolute values: stronger contribution to principal components."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "51f7b289-75cd-4f00-a93b-b8be4eb0272d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "pcs = PCA(n_components = 5)\n",
    "pcs.fit(scaled_df)\n",
    "loadings = pcs.components_.T*np.sqrt(pcs.explained_variance_)\n",
    "loadings_df = pd.DataFrame(loadings, index = df.iloc[:,3:15].columns, \n",
    "                           columns = [f'PC{i+1}' for i in range(loadings.shape[1])])\n",
    "\n",
    "# Plot the heatmap for the PCA loadings\n",
    "plt.figure(figsize=(8, 6))\n",
    "sns.heatmap(loadings_df, annot=True, cmap ='PiYG', center=0, fmt=\".2f\", annot_kws={'size': 8})\n",
    "plt.title('PCA Loadings Heatmap')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "436858f9-99cf-4836-8f1b-c8ef9d90a27e",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d824c9de-0285-453a-96aa-9744e6121b36",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9d94c92a-6635-49d7-a089-ee0818fb62a3",
   "metadata": {},
   "outputs": [],
   "source": [
    "# PC1 is related to fiber and potassium\n",
    "# PC2 represents the calories and the weight of each cup\n",
    "# PC3 is carbonates and sugars\n",
    "# PC4 is related both with vitamins and the display shelf\n",
    "# PC5 tries to capture the fat"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "6e359d9d-014f-4382-91b3-56496e83ae77",
   "metadata": {},
   "outputs": [],
   "source": [
    "reduced_df = reduced_df.copy()\n",
    "reduced_df['Target'] = 0\n",
    "reduced_df.loc[(reduced_df['rating'] > 50),'Target'] = 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "b4347cd5-b212-47c3-8209-2e02f5438801",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "pcs = PCA(n_components=2)\n",
    "pcs_transformed = pcs.fit_transform(scaled_df)\n",
    "colors = ['r','g']\n",
    "labels = ['Class 1', 'Class 2']\n",
    "for i, c, l in zip(np.unique(reduced_df['Target']), colors, labels):\n",
    "    plt.scatter(pcs_transformed[reduced_df['Target'] == i, 0],\n",
    "                pcs_transformed[reduced_df['Target'] == i, 1],\n",
    "                color = c, label = l)\n",
    "\n",
    "plt.xlabel(\"PC1\")\n",
    "plt.ylabel(\"PC2\")\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "98f79811-fe79-4ebc-b953-72869dee54a7",
   "metadata": {},
   "outputs": [],
   "source": [
    "# negative values of PC2 are associated with posite ratings"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:base] *",
   "language": "python",
   "name": "conda-base-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}