diff --git a/DataCleaning/ViMo018_data_imputation/dataImputaion.ipynb b/DataCleaning/ViMo018_data_imputation/dataImputaion.ipynb
new file mode 100644
index 0000000..353e619
--- /dev/null
+++ b/DataCleaning/ViMo018_data_imputation/dataImputaion.ipynb
@@ -0,0 +1,2038 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": 100,
+      "metadata": {
+        "id": "uYTtX0GqhSEN"
+      },
+      "outputs": [],
+      "source": [
+        "import numpy as np\n",
+        "import pandas as pd\n",
+        "import seaborn as sns\n",
+        "import matplotlib.pyplot as plt"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "data = pd.read_csv('full_data.csv')\n",
+        "#Use only 30 columns\n",
+        "\n",
+        "#extract those 30 columns to df\n",
+        "\n",
+        "df = data[[\n",
+        "    'P_MASS','P_RADIUS','P_DENSITY','P_GRAVITY','P_ESCAPE','P_TYPE',\n",
+        "    'P_PERIOD','P_SEMI_MAJOR_AXIS','P_ECCENTRICITY','P_INCLINATION',\n",
+        "    'P_OMEGA','P_PERIASTRON','P_APASTRON','P_IMPACT_PARAMETER','P_HILL_SPHERE',\n",
+        "    'S_MASS','S_RADIUS','S_LUMINOSITY','S_TEMPERATURE','S_AGE',\n",
+        "    'S_METALLICITY','S_LOG_G','S_TYPE','S_MAG','S_DISC','S_MAGNETIC_FIELD',\n",
+        "    'S_SNOW_LINE','S_TIDAL_LOCK','P_DETECTION','P_DISTANCE'\n",
+        "]]"
+      ],
+      "metadata": {
+        "id": "QrIloCdMSvnX"
+      },
+      "execution_count": 115,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df.sample(5)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 290
+        },
+        "id": "_bPlhL_2hvet",
+        "outputId": "e7bf2d7d-6db1-4584-ac4d-2e86d9c538d0"
+      },
+      "execution_count": 116,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "          P_MASS  P_RADIUS  P_DENSITY  P_GRAVITY  P_ESCAPE     P_TYPE  \\\n",
+              "524    915.34465       NaN        NaN        NaN       NaN     Jovian   \n",
+              "3991  1274.49030  16.70290   0.273502   4.568281  8.735189     Jovian   \n",
+              "50     540.30760       NaN        NaN        NaN       NaN     Jovian   \n",
+              "1487     7.94570   4.19254   0.107820   0.452041  1.376662  Neptunian   \n",
+              "2332         NaN   3.30695        NaN        NaN       NaN  Neptunian   \n",
+              "\n",
+              "        P_PERIOD  P_SEMI_MAJOR_AXIS  P_ECCENTRICITY  P_INCLINATION  ...  \\\n",
+              "524   225.620000              0.810           0.310            NaN  ...   \n",
+              "3991    3.352057              0.047           0.100          85.50  ...   \n",
+              "50    733.000000              1.700           0.760            NaN  ...   \n",
+              "1487   31.999600              0.195           0.012          88.89  ...   \n",
+              "2332    5.868075              0.068             NaN            NaN  ...   \n",
+              "\n",
+              "      S_METALLICITY  S_LOG_G  S_TYPE   S_MAG  S_DISC  S_MAGNETIC_FIELD  \\\n",
+              "524           0.210     4.10    F8 V   5.902     NaN               NaN   \n",
+              "3991         -0.500     4.40    F6 V  16.130     NaN               NaN   \n",
+              "50           -0.130     2.48  K3 III   8.699     NaN               NaN   \n",
+              "1487         -0.041     4.37     NaN  14.200     NaN               NaN   \n",
+              "2332            NaN     4.13     NaN  13.182     NaN               NaN   \n",
+              "\n",
+              "      S_SNOW_LINE  S_TIDAL_LOCK      P_DETECTION  P_DISTANCE  \n",
+              "524      5.592619      0.475110  Radial Velocity    0.848920  \n",
+              "3991     3.630496      0.444333          Transit    0.047235  \n",
+              "50      17.162140      0.474781  Radial Velocity    2.190960  \n",
+              "1487     2.747306      0.504141          Transit    0.195014  \n",
+              "2332     4.503484           NaN          Transit    0.068000  \n",
+              "\n",
+              "[5 rows x 30 columns]"
+            ],
+            "text/html": [
+              "\n",
+              "  <div id=\"df-b6e45974-e16e-49c5-82aa-2c4dccc8da64\" class=\"colab-df-container\">\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>P_MASS</th>\n",
+              "      <th>P_RADIUS</th>\n",
+              "      <th>P_DENSITY</th>\n",
+              "      <th>P_GRAVITY</th>\n",
+              "      <th>P_ESCAPE</th>\n",
+              "      <th>P_TYPE</th>\n",
+              "      <th>P_PERIOD</th>\n",
+              "      <th>P_SEMI_MAJOR_AXIS</th>\n",
+              "      <th>P_ECCENTRICITY</th>\n",
+              "      <th>P_INCLINATION</th>\n",
+              "      <th>...</th>\n",
+              "      <th>S_METALLICITY</th>\n",
+              "      <th>S_LOG_G</th>\n",
+              "      <th>S_TYPE</th>\n",
+              "      <th>S_MAG</th>\n",
+              "      <th>S_DISC</th>\n",
+              "      <th>S_MAGNETIC_FIELD</th>\n",
+              "      <th>S_SNOW_LINE</th>\n",
+              "      <th>S_TIDAL_LOCK</th>\n",
+              "      <th>P_DETECTION</th>\n",
+              "      <th>P_DISTANCE</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>524</th>\n",
+              "      <td>915.34465</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>Jovian</td>\n",
+              "      <td>225.620000</td>\n",
+              "      <td>0.810</td>\n",
+              "      <td>0.310</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>...</td>\n",
+              "      <td>0.210</td>\n",
+              "      <td>4.10</td>\n",
+              "      <td>F8 V</td>\n",
+              "      <td>5.902</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>5.592619</td>\n",
+              "      <td>0.475110</td>\n",
+              "      <td>Radial Velocity</td>\n",
+              "      <td>0.848920</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3991</th>\n",
+              "      <td>1274.49030</td>\n",
+              "      <td>16.70290</td>\n",
+              "      <td>0.273502</td>\n",
+              "      <td>4.568281</td>\n",
+              "      <td>8.735189</td>\n",
+              "      <td>Jovian</td>\n",
+              "      <td>3.352057</td>\n",
+              "      <td>0.047</td>\n",
+              "      <td>0.100</td>\n",
+              "      <td>85.50</td>\n",
+              "      <td>...</td>\n",
+              "      <td>-0.500</td>\n",
+              "      <td>4.40</td>\n",
+              "      <td>F6 V</td>\n",
+              "      <td>16.130</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>3.630496</td>\n",
+              "      <td>0.444333</td>\n",
+              "      <td>Transit</td>\n",
+              "      <td>0.047235</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>50</th>\n",
+              "      <td>540.30760</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>Jovian</td>\n",
+              "      <td>733.000000</td>\n",
+              "      <td>1.700</td>\n",
+              "      <td>0.760</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>...</td>\n",
+              "      <td>-0.130</td>\n",
+              "      <td>2.48</td>\n",
+              "      <td>K3 III</td>\n",
+              "      <td>8.699</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>17.162140</td>\n",
+              "      <td>0.474781</td>\n",
+              "      <td>Radial Velocity</td>\n",
+              "      <td>2.190960</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1487</th>\n",
+              "      <td>7.94570</td>\n",
+              "      <td>4.19254</td>\n",
+              "      <td>0.107820</td>\n",
+              "      <td>0.452041</td>\n",
+              "      <td>1.376662</td>\n",
+              "      <td>Neptunian</td>\n",
+              "      <td>31.999600</td>\n",
+              "      <td>0.195</td>\n",
+              "      <td>0.012</td>\n",
+              "      <td>88.89</td>\n",
+              "      <td>...</td>\n",
+              "      <td>-0.041</td>\n",
+              "      <td>4.37</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>14.200</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>2.747306</td>\n",
+              "      <td>0.504141</td>\n",
+              "      <td>Transit</td>\n",
+              "      <td>0.195014</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2332</th>\n",
+              "      <td>NaN</td>\n",
+              "      <td>3.30695</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>Neptunian</td>\n",
+              "      <td>5.868075</td>\n",
+              "      <td>0.068</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>...</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>4.13</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>13.182</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>4.503484</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>Transit</td>\n",
+              "      <td>0.068000</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "<p>5 rows × 30 columns</p>\n",
+              "</div>\n",
+              "    <div class=\"colab-df-buttons\">\n",
+              "\n",
+              "  <div class=\"colab-df-container\">\n",
+              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-b6e45974-e16e-49c5-82aa-2c4dccc8da64')\"\n",
+              "            title=\"Convert this dataframe to an interactive table.\"\n",
+              "            style=\"display:none;\">\n",
+              "\n",
+              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
+              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
+              "  </svg>\n",
+              "    </button>\n",
+              "\n",
+              "  <style>\n",
+              "    .colab-df-container {\n",
+              "      display:flex;\n",
+              "      gap: 12px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert {\n",
+              "      background-color: #E8F0FE;\n",
+              "      border: none;\n",
+              "      border-radius: 50%;\n",
+              "      cursor: pointer;\n",
+              "      display: none;\n",
+              "      fill: #1967D2;\n",
+              "      height: 32px;\n",
+              "      padding: 0 0 0 0;\n",
+              "      width: 32px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert:hover {\n",
+              "      background-color: #E2EBFA;\n",
+              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+              "      fill: #174EA6;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-buttons div {\n",
+              "      margin-bottom: 4px;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert {\n",
+              "      background-color: #3B4455;\n",
+              "      fill: #D2E3FC;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert:hover {\n",
+              "      background-color: #434B5C;\n",
+              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
+              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
+              "      fill: #FFFFFF;\n",
+              "    }\n",
+              "  </style>\n",
+              "\n",
+              "    <script>\n",
+              "      const buttonEl =\n",
+              "        document.querySelector('#df-b6e45974-e16e-49c5-82aa-2c4dccc8da64 button.colab-df-convert');\n",
+              "      buttonEl.style.display =\n",
+              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "\n",
+              "      async function convertToInteractive(key) {\n",
+              "        const element = document.querySelector('#df-b6e45974-e16e-49c5-82aa-2c4dccc8da64');\n",
+              "        const dataTable =\n",
+              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
+              "                                                    [key], {});\n",
+              "        if (!dataTable) return;\n",
+              "\n",
+              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
+              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
+              "          + ' to learn more about interactive tables.';\n",
+              "        element.innerHTML = '';\n",
+              "        dataTable['output_type'] = 'display_data';\n",
+              "        await google.colab.output.renderOutput(dataTable, element);\n",
+              "        const docLink = document.createElement('div');\n",
+              "        docLink.innerHTML = docLinkHtml;\n",
+              "        element.appendChild(docLink);\n",
+              "      }\n",
+              "    </script>\n",
+              "  </div>\n",
+              "\n",
+              "\n",
+              "    <div id=\"df-eb7f4f78-516e-4814-b500-8d0d28155549\">\n",
+              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-eb7f4f78-516e-4814-b500-8d0d28155549')\"\n",
+              "                title=\"Suggest charts\"\n",
+              "                style=\"display:none;\">\n",
+              "\n",
+              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
+              "     width=\"24px\">\n",
+              "    <g>\n",
+              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
+              "    </g>\n",
+              "</svg>\n",
+              "      </button>\n",
+              "\n",
+              "<style>\n",
+              "  .colab-df-quickchart {\n",
+              "      --bg-color: #E8F0FE;\n",
+              "      --fill-color: #1967D2;\n",
+              "      --hover-bg-color: #E2EBFA;\n",
+              "      --hover-fill-color: #174EA6;\n",
+              "      --disabled-fill-color: #AAA;\n",
+              "      --disabled-bg-color: #DDD;\n",
+              "  }\n",
+              "\n",
+              "  [theme=dark] .colab-df-quickchart {\n",
+              "      --bg-color: #3B4455;\n",
+              "      --fill-color: #D2E3FC;\n",
+              "      --hover-bg-color: #434B5C;\n",
+              "      --hover-fill-color: #FFFFFF;\n",
+              "      --disabled-bg-color: #3B4455;\n",
+              "      --disabled-fill-color: #666;\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-quickchart {\n",
+              "    background-color: var(--bg-color);\n",
+              "    border: none;\n",
+              "    border-radius: 50%;\n",
+              "    cursor: pointer;\n",
+              "    display: none;\n",
+              "    fill: var(--fill-color);\n",
+              "    height: 32px;\n",
+              "    padding: 0;\n",
+              "    width: 32px;\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-quickchart:hover {\n",
+              "    background-color: var(--hover-bg-color);\n",
+              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+              "    fill: var(--button-hover-fill-color);\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-quickchart-complete:disabled,\n",
+              "  .colab-df-quickchart-complete:disabled:hover {\n",
+              "    background-color: var(--disabled-bg-color);\n",
+              "    fill: var(--disabled-fill-color);\n",
+              "    box-shadow: none;\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-spinner {\n",
+              "    border: 2px solid var(--fill-color);\n",
+              "    border-color: transparent;\n",
+              "    border-bottom-color: var(--fill-color);\n",
+              "    animation:\n",
+              "      spin 1s steps(1) infinite;\n",
+              "  }\n",
+              "\n",
+              "  @keyframes spin {\n",
+              "    0% {\n",
+              "      border-color: transparent;\n",
+              "      border-bottom-color: var(--fill-color);\n",
+              "      border-left-color: var(--fill-color);\n",
+              "    }\n",
+              "    20% {\n",
+              "      border-color: transparent;\n",
+              "      border-left-color: var(--fill-color);\n",
+              "      border-top-color: var(--fill-color);\n",
+              "    }\n",
+              "    30% {\n",
+              "      border-color: transparent;\n",
+              "      border-left-color: var(--fill-color);\n",
+              "      border-top-color: var(--fill-color);\n",
+              "      border-right-color: var(--fill-color);\n",
+              "    }\n",
+              "    40% {\n",
+              "      border-color: transparent;\n",
+              "      border-right-color: var(--fill-color);\n",
+              "      border-top-color: var(--fill-color);\n",
+              "    }\n",
+              "    60% {\n",
+              "      border-color: transparent;\n",
+              "      border-right-color: var(--fill-color);\n",
+              "    }\n",
+              "    80% {\n",
+              "      border-color: transparent;\n",
+              "      border-right-color: var(--fill-color);\n",
+              "      border-bottom-color: var(--fill-color);\n",
+              "    }\n",
+              "    90% {\n",
+              "      border-color: transparent;\n",
+              "      border-bottom-color: var(--fill-color);\n",
+              "    }\n",
+              "  }\n",
+              "</style>\n",
+              "\n",
+              "      <script>\n",
+              "        async function quickchart(key) {\n",
+              "          const quickchartButtonEl =\n",
+              "            document.querySelector('#' + key + ' button');\n",
+              "          quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
+              "          quickchartButtonEl.classList.add('colab-df-spinner');\n",
+              "          try {\n",
+              "            const charts = await google.colab.kernel.invokeFunction(\n",
+              "                'suggestCharts', [key], {});\n",
+              "          } catch (error) {\n",
+              "            console.error('Error during call to suggestCharts:', error);\n",
+              "          }\n",
+              "          quickchartButtonEl.classList.remove('colab-df-spinner');\n",
+              "          quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
+              "        }\n",
+              "        (() => {\n",
+              "          let quickchartButtonEl =\n",
+              "            document.querySelector('#df-eb7f4f78-516e-4814-b500-8d0d28155549 button');\n",
+              "          quickchartButtonEl.style.display =\n",
+              "            google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "        })();\n",
+              "      </script>\n",
+              "    </div>\n",
+              "\n",
+              "    </div>\n",
+              "  </div>\n"
+            ],
+            "application/vnd.google.colaboratory.intrinsic+json": {
+              "type": "dataframe"
+            }
+          },
+          "metadata": {},
+          "execution_count": 116
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Objective\n",
+        "\n",
+        "the aim of this project is to fill missing values preserving the real meaning of\n",
+        "dataset\n"
+      ],
+      "metadata": {
+        "id": "RA961Cbsh0yi"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "First we will get the percentage of missing values here\n"
+      ],
+      "metadata": {
+        "id": "aWt_uuxsiDHw"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df.info()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "nS1Mho2FI7a9",
+        "outputId": "3aad219c-f2c5-4ed9-add7-717df9cb33dd"
+      },
+      "execution_count": 117,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "<class 'pandas.core.frame.DataFrame'>\n",
+            "RangeIndex: 4048 entries, 0 to 4047\n",
+            "Data columns (total 30 columns):\n",
+            " #   Column              Non-Null Count  Dtype  \n",
+            "---  ------              --------------  -----  \n",
+            " 0   P_MASS              1598 non-null   float64\n",
+            " 1   P_RADIUS            3139 non-null   float64\n",
+            " 2   P_DENSITY           706 non-null    float64\n",
+            " 3   P_GRAVITY           706 non-null    float64\n",
+            " 4   P_ESCAPE            706 non-null    float64\n",
+            " 5   P_TYPE              4031 non-null   object \n",
+            " 6   P_PERIOD            3938 non-null   float64\n",
+            " 7   P_SEMI_MAJOR_AXIS   2367 non-null   float64\n",
+            " 8   P_ECCENTRICITY      1380 non-null   float64\n",
+            " 9   P_INCLINATION       844 non-null    float64\n",
+            " 10  P_OMEGA             746 non-null    float64\n",
+            " 11  P_PERIASTRON        3978 non-null   float64\n",
+            " 12  P_APASTRON          3978 non-null   float64\n",
+            " 13  P_IMPACT_PARAMETER  1409 non-null   float64\n",
+            " 14  P_HILL_SPHERE       1546 non-null   float64\n",
+            " 15  S_MASS              3283 non-null   float64\n",
+            " 16  S_RADIUS            3723 non-null   float64\n",
+            " 17  S_LUMINOSITY        3786 non-null   float64\n",
+            " 18  S_TEMPERATURE       3841 non-null   float64\n",
+            " 19  S_AGE               2031 non-null   float64\n",
+            " 20  S_METALLICITY       2842 non-null   float64\n",
+            " 21  S_LOG_G             3575 non-null   float64\n",
+            " 22  S_TYPE              1370 non-null   object \n",
+            " 23  S_MAG               3869 non-null   float64\n",
+            " 24  S_DISC              0 non-null      float64\n",
+            " 25  S_MAGNETIC_FIELD    0 non-null      float64\n",
+            " 26  S_SNOW_LINE         3786 non-null   float64\n",
+            " 27  S_TIDAL_LOCK        3281 non-null   float64\n",
+            " 28  P_DETECTION         4048 non-null   object \n",
+            " 29  P_DISTANCE          3978 non-null   float64\n",
+            "dtypes: float64(27), object(3)\n",
+            "memory usage: 948.9+ KB\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "percentage = df.isnull().mean()*100 #percentage of missing values\n",
+        "percentage"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 1000
+        },
+        "id": "51PQmqHDh7O0",
+        "outputId": "db2463e6-6a97-49e1-8391-548c2d1594fc"
+      },
+      "execution_count": 118,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "P_MASS                 60.523715\n",
+              "P_RADIUS               22.455534\n",
+              "P_DENSITY              82.559289\n",
+              "P_GRAVITY              82.559289\n",
+              "P_ESCAPE               82.559289\n",
+              "P_TYPE                  0.419960\n",
+              "P_PERIOD                2.717391\n",
+              "P_SEMI_MAJOR_AXIS      41.526680\n",
+              "P_ECCENTRICITY         65.909091\n",
+              "P_INCLINATION          79.150198\n",
+              "P_OMEGA                81.571146\n",
+              "P_PERIASTRON            1.729249\n",
+              "P_APASTRON              1.729249\n",
+              "P_IMPACT_PARAMETER     65.192688\n",
+              "P_HILL_SPHERE          61.808300\n",
+              "S_MASS                 18.898221\n",
+              "S_RADIUS                8.028656\n",
+              "S_LUMINOSITY            6.472332\n",
+              "S_TEMPERATURE           5.113636\n",
+              "S_AGE                  49.827075\n",
+              "S_METALLICITY          29.792490\n",
+              "S_LOG_G                11.684783\n",
+              "S_TYPE                 66.156126\n",
+              "S_MAG                   4.421937\n",
+              "S_DISC                100.000000\n",
+              "S_MAGNETIC_FIELD      100.000000\n",
+              "S_SNOW_LINE             6.472332\n",
+              "S_TIDAL_LOCK           18.947628\n",
+              "P_DETECTION             0.000000\n",
+              "P_DISTANCE              1.729249\n",
+              "dtype: float64"
+            ],
+            "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>0</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>P_MASS</th>\n",
+              "      <td>60.523715</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_RADIUS</th>\n",
+              "      <td>22.455534</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_DENSITY</th>\n",
+              "      <td>82.559289</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_GRAVITY</th>\n",
+              "      <td>82.559289</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_ESCAPE</th>\n",
+              "      <td>82.559289</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_TYPE</th>\n",
+              "      <td>0.419960</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_PERIOD</th>\n",
+              "      <td>2.717391</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_SEMI_MAJOR_AXIS</th>\n",
+              "      <td>41.526680</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_ECCENTRICITY</th>\n",
+              "      <td>65.909091</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_INCLINATION</th>\n",
+              "      <td>79.150198</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_OMEGA</th>\n",
+              "      <td>81.571146</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_PERIASTRON</th>\n",
+              "      <td>1.729249</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_APASTRON</th>\n",
+              "      <td>1.729249</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_IMPACT_PARAMETER</th>\n",
+              "      <td>65.192688</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_HILL_SPHERE</th>\n",
+              "      <td>61.808300</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_MASS</th>\n",
+              "      <td>18.898221</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_RADIUS</th>\n",
+              "      <td>8.028656</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_LUMINOSITY</th>\n",
+              "      <td>6.472332</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_TEMPERATURE</th>\n",
+              "      <td>5.113636</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_AGE</th>\n",
+              "      <td>49.827075</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_METALLICITY</th>\n",
+              "      <td>29.792490</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_LOG_G</th>\n",
+              "      <td>11.684783</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_TYPE</th>\n",
+              "      <td>66.156126</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_MAG</th>\n",
+              "      <td>4.421937</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_DISC</th>\n",
+              "      <td>100.000000</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_MAGNETIC_FIELD</th>\n",
+              "      <td>100.000000</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_SNOW_LINE</th>\n",
+              "      <td>6.472332</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_TIDAL_LOCK</th>\n",
+              "      <td>18.947628</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_DETECTION</th>\n",
+              "      <td>0.000000</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_DISTANCE</th>\n",
+              "      <td>1.729249</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div><br><label><b>dtype:</b> float64</label>"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 118
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#columns having more than certain amount of missing values should be eliminated"
+      ],
+      "metadata": {
+        "id": "SHjeQkU4isKl"
+      },
+      "execution_count": 119,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "columns_to_drop = percentage[percentage > 80].index.tolist()\n",
+        "columns_to_drop"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "konMxSD0ouwl",
+        "outputId": "c614da6c-dee4-42bb-9480-57ca451d7a8f"
+      },
+      "execution_count": 120,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "['P_DENSITY', 'P_GRAVITY', 'P_ESCAPE', 'P_OMEGA', 'S_DISC', 'S_MAGNETIC_FIELD']"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 120
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "columns_to_drop = percentage[percentage > 60].index.tolist()\n",
+        "columns_to_drop"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "XXeJHdNOqWzJ",
+        "outputId": "1b10a7b0-4581-43ad-9e2f-454f23ce3959"
+      },
+      "execution_count": 121,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "['P_MASS',\n",
+              " 'P_DENSITY',\n",
+              " 'P_GRAVITY',\n",
+              " 'P_ESCAPE',\n",
+              " 'P_ECCENTRICITY',\n",
+              " 'P_INCLINATION',\n",
+              " 'P_OMEGA',\n",
+              " 'P_IMPACT_PARAMETER',\n",
+              " 'P_HILL_SPHERE',\n",
+              " 'S_TYPE',\n",
+              " 'S_DISC',\n",
+              " 'S_MAGNETIC_FIELD']"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 121
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#drop more than 60% values\n",
+        "\n",
+        "df = df.drop(columns_to_drop, axis=1)"
+      ],
+      "metadata": {
+        "id": "n2A3SESjqjw7"
+      },
+      "execution_count": 122,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df.head()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 313
+        },
+        "id": "_hKHg850qaax",
+        "outputId": "e930cdbe-24cc-40f5-852f-fea7d48b3de4"
+      },
+      "execution_count": 123,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "   P_RADIUS  P_TYPE    P_PERIOD  P_SEMI_MAJOR_AXIS  P_PERIASTRON  P_APASTRON  \\\n",
+              "0       NaN  Jovian   326.03000               1.29       0.99201     1.58799   \n",
+              "1       NaN  Jovian   516.21997               1.53       1.40760     1.65240   \n",
+              "2       NaN  Jovian   185.84000               0.83       0.83000     0.83000   \n",
+              "3       NaN  Jovian  1773.40000               2.93       1.84590     4.01410   \n",
+              "4       NaN  Jovian   798.50000               1.66       0.53120     2.78880   \n",
+              "\n",
+              "   S_MASS  S_RADIUS  S_LUMINOSITY  S_TEMPERATURE  S_AGE  S_METALLICITY  \\\n",
+              "0    2.70     19.00    163.546800         4742.0    NaN          -0.35   \n",
+              "1    2.78     29.79    250.492940         4213.0    NaN          -0.02   \n",
+              "2    2.20     11.00     58.175144         4813.0    NaN          -0.24   \n",
+              "3    0.90      0.93      0.629171         5338.0    NaN           0.41   \n",
+              "4    1.08      1.13      1.250596         5750.0    NaN           0.06   \n",
+              "\n",
+              "   S_LOG_G  S_MAG  S_SNOW_LINE  S_TIDAL_LOCK      P_DETECTION  P_DISTANCE  \n",
+              "0     2.31  4.740    34.529063      0.642400  Radial Velocity    1.324418  \n",
+              "1     1.93  5.016    42.732816      0.648683  Radial Velocity    1.534896  \n",
+              "2     2.63  5.227    20.593611      0.600010  Radial Velocity    0.830000  \n",
+              "3     4.45  6.610     2.141648      0.445415  Radial Velocity    3.130558  \n",
+              "4     4.36  6.250     3.019411      0.473325  Radial Velocity    2.043792  "
+            ],
+            "text/html": [
+              "\n",
+              "  <div id=\"df-3dd26c77-da9a-48a1-ac2c-fae80daebb8c\" class=\"colab-df-container\">\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>P_RADIUS</th>\n",
+              "      <th>P_TYPE</th>\n",
+              "      <th>P_PERIOD</th>\n",
+              "      <th>P_SEMI_MAJOR_AXIS</th>\n",
+              "      <th>P_PERIASTRON</th>\n",
+              "      <th>P_APASTRON</th>\n",
+              "      <th>S_MASS</th>\n",
+              "      <th>S_RADIUS</th>\n",
+              "      <th>S_LUMINOSITY</th>\n",
+              "      <th>S_TEMPERATURE</th>\n",
+              "      <th>S_AGE</th>\n",
+              "      <th>S_METALLICITY</th>\n",
+              "      <th>S_LOG_G</th>\n",
+              "      <th>S_MAG</th>\n",
+              "      <th>S_SNOW_LINE</th>\n",
+              "      <th>S_TIDAL_LOCK</th>\n",
+              "      <th>P_DETECTION</th>\n",
+              "      <th>P_DISTANCE</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>NaN</td>\n",
+              "      <td>Jovian</td>\n",
+              "      <td>326.03000</td>\n",
+              "      <td>1.29</td>\n",
+              "      <td>0.99201</td>\n",
+              "      <td>1.58799</td>\n",
+              "      <td>2.70</td>\n",
+              "      <td>19.00</td>\n",
+              "      <td>163.546800</td>\n",
+              "      <td>4742.0</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>-0.35</td>\n",
+              "      <td>2.31</td>\n",
+              "      <td>4.740</td>\n",
+              "      <td>34.529063</td>\n",
+              "      <td>0.642400</td>\n",
+              "      <td>Radial Velocity</td>\n",
+              "      <td>1.324418</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>NaN</td>\n",
+              "      <td>Jovian</td>\n",
+              "      <td>516.21997</td>\n",
+              "      <td>1.53</td>\n",
+              "      <td>1.40760</td>\n",
+              "      <td>1.65240</td>\n",
+              "      <td>2.78</td>\n",
+              "      <td>29.79</td>\n",
+              "      <td>250.492940</td>\n",
+              "      <td>4213.0</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>-0.02</td>\n",
+              "      <td>1.93</td>\n",
+              "      <td>5.016</td>\n",
+              "      <td>42.732816</td>\n",
+              "      <td>0.648683</td>\n",
+              "      <td>Radial Velocity</td>\n",
+              "      <td>1.534896</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>NaN</td>\n",
+              "      <td>Jovian</td>\n",
+              "      <td>185.84000</td>\n",
+              "      <td>0.83</td>\n",
+              "      <td>0.83000</td>\n",
+              "      <td>0.83000</td>\n",
+              "      <td>2.20</td>\n",
+              "      <td>11.00</td>\n",
+              "      <td>58.175144</td>\n",
+              "      <td>4813.0</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>-0.24</td>\n",
+              "      <td>2.63</td>\n",
+              "      <td>5.227</td>\n",
+              "      <td>20.593611</td>\n",
+              "      <td>0.600010</td>\n",
+              "      <td>Radial Velocity</td>\n",
+              "      <td>0.830000</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>NaN</td>\n",
+              "      <td>Jovian</td>\n",
+              "      <td>1773.40000</td>\n",
+              "      <td>2.93</td>\n",
+              "      <td>1.84590</td>\n",
+              "      <td>4.01410</td>\n",
+              "      <td>0.90</td>\n",
+              "      <td>0.93</td>\n",
+              "      <td>0.629171</td>\n",
+              "      <td>5338.0</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>0.41</td>\n",
+              "      <td>4.45</td>\n",
+              "      <td>6.610</td>\n",
+              "      <td>2.141648</td>\n",
+              "      <td>0.445415</td>\n",
+              "      <td>Radial Velocity</td>\n",
+              "      <td>3.130558</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>NaN</td>\n",
+              "      <td>Jovian</td>\n",
+              "      <td>798.50000</td>\n",
+              "      <td>1.66</td>\n",
+              "      <td>0.53120</td>\n",
+              "      <td>2.78880</td>\n",
+              "      <td>1.08</td>\n",
+              "      <td>1.13</td>\n",
+              "      <td>1.250596</td>\n",
+              "      <td>5750.0</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>0.06</td>\n",
+              "      <td>4.36</td>\n",
+              "      <td>6.250</td>\n",
+              "      <td>3.019411</td>\n",
+              "      <td>0.473325</td>\n",
+              "      <td>Radial Velocity</td>\n",
+              "      <td>2.043792</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>\n",
+              "    <div class=\"colab-df-buttons\">\n",
+              "\n",
+              "  <div class=\"colab-df-container\">\n",
+              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-3dd26c77-da9a-48a1-ac2c-fae80daebb8c')\"\n",
+              "            title=\"Convert this dataframe to an interactive table.\"\n",
+              "            style=\"display:none;\">\n",
+              "\n",
+              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
+              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
+              "  </svg>\n",
+              "    </button>\n",
+              "\n",
+              "  <style>\n",
+              "    .colab-df-container {\n",
+              "      display:flex;\n",
+              "      gap: 12px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert {\n",
+              "      background-color: #E8F0FE;\n",
+              "      border: none;\n",
+              "      border-radius: 50%;\n",
+              "      cursor: pointer;\n",
+              "      display: none;\n",
+              "      fill: #1967D2;\n",
+              "      height: 32px;\n",
+              "      padding: 0 0 0 0;\n",
+              "      width: 32px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert:hover {\n",
+              "      background-color: #E2EBFA;\n",
+              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+              "      fill: #174EA6;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-buttons div {\n",
+              "      margin-bottom: 4px;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert {\n",
+              "      background-color: #3B4455;\n",
+              "      fill: #D2E3FC;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert:hover {\n",
+              "      background-color: #434B5C;\n",
+              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
+              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
+              "      fill: #FFFFFF;\n",
+              "    }\n",
+              "  </style>\n",
+              "\n",
+              "    <script>\n",
+              "      const buttonEl =\n",
+              "        document.querySelector('#df-3dd26c77-da9a-48a1-ac2c-fae80daebb8c button.colab-df-convert');\n",
+              "      buttonEl.style.display =\n",
+              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "\n",
+              "      async function convertToInteractive(key) {\n",
+              "        const element = document.querySelector('#df-3dd26c77-da9a-48a1-ac2c-fae80daebb8c');\n",
+              "        const dataTable =\n",
+              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
+              "                                                    [key], {});\n",
+              "        if (!dataTable) return;\n",
+              "\n",
+              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
+              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
+              "          + ' to learn more about interactive tables.';\n",
+              "        element.innerHTML = '';\n",
+              "        dataTable['output_type'] = 'display_data';\n",
+              "        await google.colab.output.renderOutput(dataTable, element);\n",
+              "        const docLink = document.createElement('div');\n",
+              "        docLink.innerHTML = docLinkHtml;\n",
+              "        element.appendChild(docLink);\n",
+              "      }\n",
+              "    </script>\n",
+              "  </div>\n",
+              "\n",
+              "\n",
+              "    <div id=\"df-6eacd3ac-569e-4236-bfd8-685bf8d875be\">\n",
+              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-6eacd3ac-569e-4236-bfd8-685bf8d875be')\"\n",
+              "                title=\"Suggest charts\"\n",
+              "                style=\"display:none;\">\n",
+              "\n",
+              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
+              "     width=\"24px\">\n",
+              "    <g>\n",
+              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
+              "    </g>\n",
+              "</svg>\n",
+              "      </button>\n",
+              "\n",
+              "<style>\n",
+              "  .colab-df-quickchart {\n",
+              "      --bg-color: #E8F0FE;\n",
+              "      --fill-color: #1967D2;\n",
+              "      --hover-bg-color: #E2EBFA;\n",
+              "      --hover-fill-color: #174EA6;\n",
+              "      --disabled-fill-color: #AAA;\n",
+              "      --disabled-bg-color: #DDD;\n",
+              "  }\n",
+              "\n",
+              "  [theme=dark] .colab-df-quickchart {\n",
+              "      --bg-color: #3B4455;\n",
+              "      --fill-color: #D2E3FC;\n",
+              "      --hover-bg-color: #434B5C;\n",
+              "      --hover-fill-color: #FFFFFF;\n",
+              "      --disabled-bg-color: #3B4455;\n",
+              "      --disabled-fill-color: #666;\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-quickchart {\n",
+              "    background-color: var(--bg-color);\n",
+              "    border: none;\n",
+              "    border-radius: 50%;\n",
+              "    cursor: pointer;\n",
+              "    display: none;\n",
+              "    fill: var(--fill-color);\n",
+              "    height: 32px;\n",
+              "    padding: 0;\n",
+              "    width: 32px;\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-quickchart:hover {\n",
+              "    background-color: var(--hover-bg-color);\n",
+              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+              "    fill: var(--button-hover-fill-color);\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-quickchart-complete:disabled,\n",
+              "  .colab-df-quickchart-complete:disabled:hover {\n",
+              "    background-color: var(--disabled-bg-color);\n",
+              "    fill: var(--disabled-fill-color);\n",
+              "    box-shadow: none;\n",
+              "  }\n",
+              "\n",
+              "  .colab-df-spinner {\n",
+              "    border: 2px solid var(--fill-color);\n",
+              "    border-color: transparent;\n",
+              "    border-bottom-color: var(--fill-color);\n",
+              "    animation:\n",
+              "      spin 1s steps(1) infinite;\n",
+              "  }\n",
+              "\n",
+              "  @keyframes spin {\n",
+              "    0% {\n",
+              "      border-color: transparent;\n",
+              "      border-bottom-color: var(--fill-color);\n",
+              "      border-left-color: var(--fill-color);\n",
+              "    }\n",
+              "    20% {\n",
+              "      border-color: transparent;\n",
+              "      border-left-color: var(--fill-color);\n",
+              "      border-top-color: var(--fill-color);\n",
+              "    }\n",
+              "    30% {\n",
+              "      border-color: transparent;\n",
+              "      border-left-color: var(--fill-color);\n",
+              "      border-top-color: var(--fill-color);\n",
+              "      border-right-color: var(--fill-color);\n",
+              "    }\n",
+              "    40% {\n",
+              "      border-color: transparent;\n",
+              "      border-right-color: var(--fill-color);\n",
+              "      border-top-color: var(--fill-color);\n",
+              "    }\n",
+              "    60% {\n",
+              "      border-color: transparent;\n",
+              "      border-right-color: var(--fill-color);\n",
+              "    }\n",
+              "    80% {\n",
+              "      border-color: transparent;\n",
+              "      border-right-color: var(--fill-color);\n",
+              "      border-bottom-color: var(--fill-color);\n",
+              "    }\n",
+              "    90% {\n",
+              "      border-color: transparent;\n",
+              "      border-bottom-color: var(--fill-color);\n",
+              "    }\n",
+              "  }\n",
+              "</style>\n",
+              "\n",
+              "      <script>\n",
+              "        async function quickchart(key) {\n",
+              "          const quickchartButtonEl =\n",
+              "            document.querySelector('#' + key + ' button');\n",
+              "          quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
+              "          quickchartButtonEl.classList.add('colab-df-spinner');\n",
+              "          try {\n",
+              "            const charts = await google.colab.kernel.invokeFunction(\n",
+              "                'suggestCharts', [key], {});\n",
+              "          } catch (error) {\n",
+              "            console.error('Error during call to suggestCharts:', error);\n",
+              "          }\n",
+              "          quickchartButtonEl.classList.remove('colab-df-spinner');\n",
+              "          quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
+              "        }\n",
+              "        (() => {\n",
+              "          let quickchartButtonEl =\n",
+              "            document.querySelector('#df-6eacd3ac-569e-4236-bfd8-685bf8d875be button');\n",
+              "          quickchartButtonEl.style.display =\n",
+              "            google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "        })();\n",
+              "      </script>\n",
+              "    </div>\n",
+              "\n",
+              "    </div>\n",
+              "  </div>\n"
+            ],
+            "application/vnd.google.colaboratory.intrinsic+json": {
+              "type": "dataframe",
+              "variable_name": "df",
+              "summary": "{\n  \"name\": \"df\",\n  \"rows\": 4048,\n  \"fields\": [\n    {\n      \"column\": \"P_RADIUS\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 4.776829779149972,\n        \"min\": 0.3363,\n        \"max\": 77.349,\n        \"num_unique_values\": 763,\n        \"samples\": [\n          7.65643,\n          1.67029,\n          16.01909\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"P_TYPE\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 6,\n        \"samples\": [\n          \"Jovian\",\n          \"Superterran\",\n          \"Miniterran\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"P_PERIOD\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 116701.16177221051,\n        \"min\": 0.09070629,\n        \"max\": 7300000.0,\n        \"num_unique_values\": 3933,\n        \"samples\": [\n          2.4435781,\n          76.536959,\n          5.7918016\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"P_SEMI_MAJOR_AXIS\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 80.78324047273989,\n        \"min\": 0.0044,\n        \"max\": 2500.0,\n        \"num_unique_values\": 1409,\n        \"samples\": [\n          0.689,\n          0.0651,\n          0.01985\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"P_PERIASTRON\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 62.34184686000545,\n        \"min\": 0.004136,\n        \"max\": 2500.0,\n        \"num_unique_values\": 3350,\n        \"samples\": [\n          0.076488344,\n          0.051065487,\n          0.055\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"P_APASTRON\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 62.51933565212492,\n        \"min\": 0.004664,\n        \"max\": 2500.0,\n        \"num_unique_values\": 3360,\n        \"samples\": [\n          0.0694,\n          0.01908954,\n          0.13082387\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"S_MASS\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.652902985502673,\n        \"min\": 0.01,\n        \"max\": 23.56,\n        \"num_unique_values\": 228,\n        \"samples\": [\n          0.03,\n          0.61,\n          0.4\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"S_RADIUS\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 3.7078077242581324,\n        \"min\": 0.01,\n        \"max\": 71.23,\n        \"num_unique_values\": 367,\n        \"samples\": [\n          2.13,\n          0.52,\n          0.94\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"S_LUMINOSITY\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 49.23778521440965,\n        \"min\": 7.9331386e-07,\n        \"max\": 1486.8958,\n        \"num_unique_values\": 2736,\n        \"samples\": [\n          2.2025273,\n          1.0873195,\n          3.5148023\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"S_TEMPERATURE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1764.9576314601197,\n        \"min\": 575.0,\n        \"max\": 57000.0,\n        \"num_unique_values\": 1646,\n        \"samples\": [\n          3180.0,\n          57000.0,\n          4103.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"S_AGE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 67372536.35260175,\n        \"min\": -2147483600.0,\n        \"max\": 14.9,\n        \"num_unique_values\": 362,\n        \"samples\": [\n          4.75,\n          7.2,\n          0.03\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"S_METALLICITY\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.17651161382949168,\n        \"min\": -0.89,\n        \"max\": 0.69,\n        \"num_unique_values\": 193,\n        \"samples\": [\n          -0.04,\n          -0.323,\n          -0.127\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"S_LOG_G\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.5246998141261074,\n        \"min\": -4.9949999,\n        \"max\": 5.52,\n        \"num_unique_values\": 236,\n        \"samples\": [\n          4.6,\n          2.6,\n          2.49\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"S_MAG\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2.9556920448202537,\n        \"min\": 0.85,\n        \"max\": 20.15,\n        \"num_unique_values\": 2204,\n        \"samples\": [\n          14.277,\n          13.2,\n          14.669\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"S_SNOW_LINE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 5.4631707707021295,\n        \"min\": 0.0024048406,\n        \"max\": 104.11278,\n        \"num_unique_values\": 2736,\n        \"samples\": [\n          4.0070468,\n          2.8154146,\n          5.0619077\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"S_TIDAL_LOCK\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.07428525183102512,\n        \"min\": 0.030706817,\n        \"max\": 1.3225423,\n        \"num_unique_values\": 1510,\n        \"samples\": [\n          0.46545916,\n          0.44807189,\n          0.44948986\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"P_DETECTION\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 10,\n        \"samples\": [\n          \"Transit Timing Variations\",\n          \"Imaging\",\n          \"Orbital Brightness Modulation\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"P_DISTANCE\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 62.43599393751667,\n        \"min\": 0.00440792,\n        \"max\": 2500.0,\n        \"num_unique_values\": 3383,\n        \"samples\": [\n          0.29772765,\n          0.066368101,\n          0.064337813\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
+            }
+          },
+          "metadata": {},
+          "execution_count": 123
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df.info()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "tosqYkSBq5A0",
+        "outputId": "7e73245b-af5f-4da6-87a2-63df7c07d775"
+      },
+      "execution_count": 124,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "<class 'pandas.core.frame.DataFrame'>\n",
+            "RangeIndex: 4048 entries, 0 to 4047\n",
+            "Data columns (total 18 columns):\n",
+            " #   Column             Non-Null Count  Dtype  \n",
+            "---  ------             --------------  -----  \n",
+            " 0   P_RADIUS           3139 non-null   float64\n",
+            " 1   P_TYPE             4031 non-null   object \n",
+            " 2   P_PERIOD           3938 non-null   float64\n",
+            " 3   P_SEMI_MAJOR_AXIS  2367 non-null   float64\n",
+            " 4   P_PERIASTRON       3978 non-null   float64\n",
+            " 5   P_APASTRON         3978 non-null   float64\n",
+            " 6   S_MASS             3283 non-null   float64\n",
+            " 7   S_RADIUS           3723 non-null   float64\n",
+            " 8   S_LUMINOSITY       3786 non-null   float64\n",
+            " 9   S_TEMPERATURE      3841 non-null   float64\n",
+            " 10  S_AGE              2031 non-null   float64\n",
+            " 11  S_METALLICITY      2842 non-null   float64\n",
+            " 12  S_LOG_G            3575 non-null   float64\n",
+            " 13  S_MAG              3869 non-null   float64\n",
+            " 14  S_SNOW_LINE        3786 non-null   float64\n",
+            " 15  S_TIDAL_LOCK       3281 non-null   float64\n",
+            " 16  P_DETECTION        4048 non-null   object \n",
+            " 17  P_DISTANCE         3978 non-null   float64\n",
+            "dtypes: float64(16), object(2)\n",
+            "memory usage: 569.4+ KB\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "num_cols = df.select_dtypes(include=[np.number]).columns\n",
+        "cat_cols = df.select_dtypes(exclude=[np.number]).columns\n",
+        "\n",
+        "num_cols, cat_cols\n"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "z02SaGZnJee_",
+        "outputId": "468a03d5-3880-4716-b182-5282afab89b9"
+      },
+      "execution_count": 126,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "(Index(['P_RADIUS', 'P_PERIOD', 'P_SEMI_MAJOR_AXIS', 'P_PERIASTRON',\n",
+              "        'P_APASTRON', 'S_MASS', 'S_RADIUS', 'S_LUMINOSITY', 'S_TEMPERATURE',\n",
+              "        'S_AGE', 'S_METALLICITY', 'S_LOG_G', 'S_MAG', 'S_SNOW_LINE',\n",
+              "        'S_TIDAL_LOCK', 'P_DISTANCE'],\n",
+              "       dtype='object'),\n",
+              " Index(['P_TYPE', 'P_DETECTION'], dtype='object'))"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 126
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#distribution curve of each and every column\n",
+        "\n",
+        "for col in num_cols:\n",
+        "    sns.distplot(df[col])\n",
+        "    plt.show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 1000
+        },
+        "id": "Tu1xvN24I3ZJ",
+        "outputId": "118f4526-57fd-4af4-9f66-f25513eb886c"
+      },
+      "execution_count": 127,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/tmp/ipython-input-3541476722.py:4: UserWarning: \n",
+            "\n",
+            "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n",
+            "\n",
+            "Please adapt your code to use either `displot` (a figure-level function with\n",
+            "similar flexibility) or `histplot` (an axes-level function for histograms).\n",
+            "\n",
+            "For a guide to updating your code to use the new functions, please see\n",
+            "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n",
+            "\n",
+            "  sns.distplot(df[col])\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/tmp/ipython-input-3541476722.py:4: UserWarning: \n",
+            "\n",
+            "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n",
+            "\n",
+            "Please adapt your code to use either `displot` (a figure-level function with\n",
+            "similar flexibility) or `histplot` (an axes-level function for histograms).\n",
+            "\n",
+            "For a guide to updating your code to use the new functions, please see\n",
+            "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n",
+            "\n",
+            "  sns.distplot(df[col])\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/tmp/ipython-input-3541476722.py:4: UserWarning: \n",
+            "\n",
+            "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n",
+            "\n",
+            "Please adapt your code to use either `displot` (a figure-level function with\n",
+            "similar flexibility) or `histplot` (an axes-level function for histograms).\n",
+            "\n",
+            "For a guide to updating your code to use the new functions, please see\n",
+            "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n",
+            "\n",
+            "  sns.distplot(df[col])\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/tmp/ipython-input-3541476722.py:4: UserWarning: \n",
+            "\n",
+            "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n",
+            "\n",
+            "Please adapt your code to use either `displot` (a figure-level function with\n",
+            "similar flexibility) or `histplot` (an axes-level function for histograms).\n",
+            "\n",
+            "For a guide to updating your code to use the new functions, please see\n",
+            "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n",
+            "\n",
+            "  sns.distplot(df[col])\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/tmp/ipython-input-3541476722.py:4: UserWarning: \n",
+            "\n",
+            "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n",
+            "\n",
+            "Please adapt your code to use either `displot` (a figure-level function with\n",
+            "similar flexibility) or `histplot` (an axes-level function for histograms).\n",
+            "\n",
+            "For a guide to updating your code to use the new functions, please see\n",
+            "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n",
+            "\n",
+            "  sns.distplot(df[col])\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/tmp/ipython-input-3541476722.py:4: UserWarning: \n",
+            "\n",
+            "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n",
+            "\n",
+            "Please adapt your code to use either `displot` (a figure-level function with\n",
+            "similar flexibility) or `histplot` (an axes-level function for histograms).\n",
+            "\n",
+            "For a guide to updating your code to use the new functions, please see\n",
+            "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n",
+            "\n",
+            "  sns.distplot(df[col])\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/tmp/ipython-input-3541476722.py:4: UserWarning: \n",
+            "\n",
+            "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n",
+            "\n",
+            "Please adapt your code to use either `displot` (a figure-level function with\n",
+            "similar flexibility) or `histplot` (an axes-level function for histograms).\n",
+            "\n",
+            "For a guide to updating your code to use the new functions, please see\n",
+            "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n",
+            "\n",
+            "  sns.distplot(df[col])\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjcAAAGwCAYAAABVdURTAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAPV1JREFUeJzt3Xl8VOW9x/HvzGRmkrAEMJIABoKiIqUQChIj9WprlKq34nppq2Wx0qrQ0ubaIvYKapegVkoXrlQLonWBq0VrW0VpFCxKRba64wYEhSwoJCGQmWTm3D+SOUnITDIzmeQMJ5/36zUlOXPmzHMyGL59nt/zPA7DMAwBAADYhNPqBgAAACQS4QYAANgK4QYAANgK4QYAANgK4QYAANgK4QYAANgK4QYAANhKitUN6G7BYFD79u1Tnz595HA4rG4OAACIgmEYqqmp0eDBg+V0tt830+PCzb59+5STk2N1MwAAQBz27t2rk046qd1zely46dOnj6TGH07fvn0tbg0AAIhGdXW1cnJyzH/H29Pjwk1oKKpv376EGwAAjjPRlJRQUAwAAGyFcAMAAGyFcAMAAGzF8nCzdOlS5ebmKjU1Vfn5+dq8eXO75x86dEizZ8/WoEGD5PV6ddppp+nZZ5/tptYCAIBkZ2lB8erVq1VUVKRly5YpPz9fS5Ys0eTJk7Vz504NHDiwzfl+v18XXHCBBg4cqCeffFJDhgzRnj171K9fv+5vPAAASEoOwzAMq948Pz9fZ555pn7/+99LalxgLycnR9///vd1yy23tDl/2bJluueee/Tee+/J7XbH9Z7V1dXKyMhQVVUVs6UAADhOxPLvt2XDUn6/X1u3blVhYWFzY5xOFRYWatOmTWFf88wzz6igoECzZ89WVlaWRo8erV/+8pcKBAIR38fn86m6urrVAwAA2Jdl4ebAgQMKBALKyspqdTwrK0tlZWVhX/Pxxx/rySefVCAQ0LPPPqvbbrtN9957r37+859HfJ/i4mJlZGSYD1YnBgDA3iwvKI5FMBjUwIEDdf/992v8+PGaOnWqfvrTn2rZsmURXzN//nxVVVWZj71793ZjiwEAQHezrKA4MzNTLpdL5eXlrY6Xl5crOzs77GsGDRokt9stl8tlHjvjjDNUVlYmv98vj8fT5jVer1derzexjQcAAEnLsp4bj8ej8ePHq6SkxDwWDAZVUlKigoKCsK+ZNGmSPvzwQwWDQfPY+++/r0GDBoUNNgAAoOexdFiqqKhIDzzwgB566CG9++67uvHGG1VbW6uZM2dKkqZNm6b58+eb59944436/PPPNXfuXL3//vv6+9//rl/+8peaPXu2VbcAAACSjKXr3EydOlWVlZVasGCBysrKlJeXp7Vr15pFxqWlpXI6m/NXTk6Onn/+ef3oRz/SmDFjNGTIEM2dO1fz5s2z6hYAAECSsXSdGyuwzg0AAMef42KdGwAAgK5g6bAUGj32Wmm7z38rf2g3tQQAgOMfPTcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWCDcAAMBWkiLcLF26VLm5uUpNTVV+fr42b94c8dyVK1fK4XC0eqSmpnZjawEAQDKzPNysXr1aRUVFWrhwobZt26axY8dq8uTJqqioiPiavn37av/+/eZjz5493dhiAACQzCwPN4sXL9asWbM0c+ZMjRo1SsuWLVN6erpWrFgR8TUOh0PZ2dnmIysrqxtbDAAAkpml4cbv92vr1q0qLCw0jzmdThUWFmrTpk0RX3f48GENGzZMOTk5mjJlit5+++2I5/p8PlVXV7d6AAAA+7I03Bw4cECBQKBNz0tWVpbKysrCvub000/XihUr9Je//EWPPPKIgsGgzj77bH3yySdhzy8uLlZGRob5yMnJSfh9AACA5GH5sFSsCgoKNG3aNOXl5encc8/VmjVrdOKJJ+oPf/hD2PPnz5+vqqoq87F3795ubjEAAOhOKVa+eWZmplwul8rLy1sdLy8vV3Z2dlTXcLvdGjdunD788MOwz3u9Xnm93k63FQAAHB8s7bnxeDwaP368SkpKzGPBYFAlJSUqKCiI6hqBQEBvvvmmBg0a1FXNBAAAxxFLe24kqaioSNOnT9eECRM0ceJELVmyRLW1tZo5c6Ykadq0aRoyZIiKi4slSXfeeafOOussjRgxQocOHdI999yjPXv26Prrr7fyNgAAQJKwPNxMnTpVlZWVWrBggcrKypSXl6e1a9eaRcalpaVyOps7mA4ePKhZs2aprKxM/fv31/jx4/Xqq69q1KhRVt0CAABIIg7DMAyrG9GdqqurlZGRoaqqKvXt29fq5kiSHnuttN3nv5U/tJtaAgBAcorl3+/jbrYUAABAewg3AADAVgg3AADAVgg3AADAVgg3AADAVgg3AADAVgg3AADAVgg3AADAVgg3Sej98hrt+azW6mYAAHBcItwkmaP+gB7etFsrX92tQLBHLR4NAEBCEG6STK2/QUFD8jUEVX203urmAABw3CHcJBlfQ9D8+vMjfgtbAgDA8Ylwk2R8DQHz689rCTcAAMSKcJNk/PUtem4INwAAxIxwk2TqGgg3AAB0BuEmybQcljpIzQ0AADEj3CQZPz03AAB0CuEmybScLXXEH1BdfaCdswEAwLEIN0nGd0yYofcGAIDYEG6STMueG4lwAwBArAg3SebYcENRMQAAsSHcJJnQbKm+qSmSpM/ouQEAICaEmyQT6rnJzkiVJB0k3AAAEBPCTZIJTQUflJEmiZobAABiRbhJMm16bo74FQgaVjYJAIDjCuEmyYSmgg/s45XL4VDQkPZXHbW4VQAAHD8IN0km1HOT6napX7pbkvTpQcINAADRItwkkUDQUEPTEJQ3xSmvu/HjOeJnlWIAAKJFuEkiLTfN9Ka45HY2fjxswQAAQPQIN0kkNCSV4nTI5XTI7WoKNw2EGwAAokW4SSKhcONJafxYUlyOxuP1wYivAQAArRFukoi/afjJa4YbhqUAAIgV4SaJhHpuvCkuSZLb2dhzU9dAzw0AANEi3CSRUIgJzZJy03MDAEDMCDdJxN/QeljK3VRzU0fNDQAAUSPcJJFjh6VCNTc+ZksBABA1wk0SaQ43rWdL0XMDAED0CDdJJDTl2xyWalrEz0fNDQAAUSPcJJHQ8JMnNFsq1HPDsBQAAFEj3CSR5k0zj50txbAUAADRItwkkbYrFFNQDABArAg3ScRnTgVvmi3lpKAYAIBYEW6SiP+Y2VIs4gcAQOwIN0mkzWwpcyo44QYAgGgRbpLIscNSFBQDABA7wk0S8R2zt1RoET8fG2cCABA1wk2SMAwjYs0Ni/gBABA9wk2S8AeCMpq+bjNbiqngAABEjXCTJEJDTw41FxKHem7qA4YCQSPSSwEAQAtJEW6WLl2q3NxcpaamKj8/X5s3b47qdatWrZLD4dBll13WtQ3sBv765gX8HI7W4UZixhQAANGyPNysXr1aRUVFWrhwobZt26axY8dq8uTJqqioaPd1u3fv1s0336xzzjmnm1ratY7dEVxqLihu+TwAAGif5eFm8eLFmjVrlmbOnKlRo0Zp2bJlSk9P14oVKyK+JhAI6JprrtEdd9yhk08+uRtb23XMaeBul3nM6XDI5WStGwAAYmFpuPH7/dq6dasKCwvNY06nU4WFhdq0aVPE1915550aOHCgvvOd73T4Hj6fT9XV1a0eyShcz43UcgsGwg0AANGwNNwcOHBAgUBAWVlZrY5nZWWprKws7Gs2btyo5cuX64EHHojqPYqLi5WRkWE+cnJyOt3urnDsppkhLOQHAEBsLB+WikVNTY2+/e1v64EHHlBmZmZUr5k/f76qqqrMx969e7u4lfFpCDSGF7fz2HDDdHAAAGKRYuWbZ2ZmyuVyqby8vNXx8vJyZWdntzn/o48+0u7du/X1r3/dPBYMNoaClJQU7dy5U6ecckqr13i9Xnm93i5ofWI1NE31bllE3Ph9aCE/em4AAIiGpT03Ho9H48ePV0lJiXksGAyqpKREBQUFbc4fOXKk3nzzTe3YscN8XHrppfrKV76iHTt2JO2QUzTMcONsHW7ouQEAIDaW9txIUlFRkaZPn64JEyZo4sSJWrJkiWprazVz5kxJ0rRp0zRkyBAVFxcrNTVVo0ePbvX6fv36SVKb48ebQNOwVIrz2IJitmAAACAWloebqVOnqrKyUgsWLFBZWZny8vK0du1as8i4tLRUTudxVRoUl/qmnhuXK0LPDcNSAABExfJwI0lz5szRnDlzwj63fv36dl+7cuXKxDfIAqHtFdxthqVCs6XouQEAIBr27xI5ToRmS7mOHZYKFRSzQjEAAFEh3CSJSLOl3CziBwBATAg3SSLSbKkUFvEDACAmhJskEWAqOAAACUG4SRJmzY0r0vYLhBsAAKJBuEkSkYelGr+noBgAgOgQbpJExBWKnfTcAAAQC8JNkmgIhGZLHTsVvKnnhoJiAACiQrhJEoHQBqAs4gcAQKcQbpJEaFjKxWwpAAA6hXCTJJqHpY4pKDY3zmRYCgCAaBBukkRDMPyu4OawFD03AABEhXCTJCIt4pfCruAAAMSEcJMk6gORViimoBgAgFgQbpKE2XPTZoViem4AAIgF4SZJhGpu2syWChUUU3MDAEBUCDdJIGgYauq4ibz9Aj03AABEhXCTBELTwKUwU8Gbhqn8gaA5dAUAACIj3CSBlqGl7VTw5rDD0BQAAB0j3CSBUL2NQ9Ixo1LmbCmJoSkAAKJBuEkCoWEpl9Mhh6N1unE6HGzBAABADAg3SaAhGH7rhZDUFJckpoMDABANwk0SiLT1QojXzUJ+AABEi3CTBBoirE4c4jV7bgg3AAB0hHCTBDoclnKHFvJjWAoAgI7EFW4+/vjjRLejR2veNDP8x5HqpucGAIBoxRVuRowYoa985St65JFHVFdXl+g29TiRtl4IaQ439NwAANCRuMLNtm3bNGbMGBUVFSk7O1vf+973tHnz5kS3rcfouOaG/aUAAIhWXOEmLy9Pv/nNb7Rv3z6tWLFC+/fv15e//GWNHj1aixcvVmVlZaLbaWsd19wwLAUAQLQ6VVCckpKiK664Qk888YTuuusuffjhh7r55puVk5OjadOmaf/+/Ylqp60FOpgKTkExAADR61S42bJli2666SYNGjRIixcv1s0336yPPvpI69at0759+zRlypREtdPW6lusUBxOKlPBAQCIWko8L1q8eLEefPBB7dy5UxdffLEefvhhXXzxxXI29TwMHz5cK1euVG5ubiLbaluBDoalvBQUAwAQtbjCzX333afrrrtOM2bM0KBBg8KeM3DgQC1fvrxTjespGjqYCh4qKKbnBgCAjsUVbtatW6ehQ4eaPTUhhmFo7969Gjp0qDwej6ZPn56QRtpd8/YLkXpuGn/OfmpuAADoUFw1N6eccooOHDjQ5vjnn3+u4cOHd7pRPY25K3ikYammmhsKigEA6Fhc4cYwjLDHDx8+rNTU1E41qCcK1dy4O1jnhp4bAAA6FtOwVFFRkSTJ4XBowYIFSk9PN58LBAJ67bXXlJeXl9AG9gTNKxSHz5oeV1O4CRBuAADoSEzhZvv27ZIae27efPNNeTwe8zmPx6OxY8fq5ptvTmwLewBzheKIs6VYoRgAgGjFFG5eeuklSdLMmTP1m9/8Rn379u2SRvU0zbOlwocbs+eGYSkAADoU12ypBx98MNHt6NE6CjdeVigGACBqUYebK664QitXrlTfvn11xRVXtHvumjVrOt2wniQQaH/7BY+L2VIAAEQr6nCTkZEhh8Nhfo3ECfXcRJ4KTs8NAADRijrctByKYlgqsTqsuWEqOAAAUYtrnZujR4/qyJEj5vd79uzRkiVL9MILLySsYT1JQwfDUs09N8yWAgCgI3GFmylTpujhhx+WJB06dEgTJ07UvffeqylTpui+++5LaAN7go42zqTnBgCA6MUVbrZt26ZzzjlHkvTkk08qOztbe/bs0cMPP6zf/va3CW1gT1AfqrlhWAoAgE6LK9wcOXJEffr0kSS98MILuuKKK+R0OnXWWWdpz549CW1gT9Dx9gvMlgIAIFpxhZsRI0bo6aef1t69e/X888/rwgsvlCRVVFSwsF8cQjU3Llf7NTf03AAA0LG4ws2CBQt08803Kzc3V/n5+SooKJDU2Iszbty4hDawJ+hwET8KigEAiFpc4eaqq65SaWmptmzZorVr15rHzz//fP3617+O+XpLly5Vbm6uUlNTlZ+fr82bN0c8d82aNZowYYL69eunXr16KS8vT3/605/iuY2kEe1U8KDR3MsDAADCi2v7BUnKzs5WdnZ2q2MTJ06M+TqrV69WUVGRli1bpvz8fC1ZskSTJ0/Wzp07NXDgwDbnDxgwQD/96U81cuRIeTwe/e1vf9PMmTM1cOBATZ48Od7bsVTA3Dgz0rCUy/za1xCMeB4AAIiz56a2tla33Xabzj77bI0YMUInn3xyq0csFi9erFmzZmnmzJkaNWqUli1bpvT0dK1YsSLs+eedd54uv/xynXHGGTrllFM0d+5cjRkzRhs3boznViwXDBoKGNHNlpKouwEAoCNx9dxcf/312rBhg7797W9r0KBB5rYMsfL7/dq6davmz59vHnM6nSosLNSmTZs6fL1hGHrxxRe1c+dO3XXXXWHP8fl88vl85vfV1dVxtbWr+FsMM0UalnI5HXI5HQoEDWZMAQDQgbjCzXPPPae///3vmjRpUqfe/MCBAwoEAsrKymp1PCsrS++9917E11VVVWnIkCHy+XxyuVz63//9X11wwQVhzy0uLtYdd9zRqXZ2pZZhJdIiflJjUfERf4CeGwAAOhDXsFT//v01YMCARLclan369NGOHTv0+uuv6xe/+IWKioq0fv36sOfOnz9fVVVV5mPv3r3d29gOtAwrrnZ6wMyF/ALMmAIAoD1x9dz87Gc/04IFC/TQQw8pPT097jfPzMyUy+VSeXl5q+Pl5eVtipVbcjqdGjFihCQpLy9P7777roqLi3Xeeee1Odfr9crr9cbdxq7mN/eVcrQ7vBeaDl5XT88NAADtiSvc3Hvvvfroo4+UlZWl3Nxcud3uVs9v27Ytqut4PB6NHz9eJSUluuyyyyRJwWBQJSUlmjNnTtTtCQaDrepqjie++saemPaGpKSWPTeEGwAA2hNXuAkFkUQoKirS9OnTNWHCBE2cOFFLlixRbW2tZs6cKUmaNm2ahgwZouLiYkmNNTQTJkzQKaecIp/Pp2effVZ/+tOfjtsNO0NhxRVhR/AQcwsGem4AAGhXXOFm4cKFCWvA1KlTVVlZqQULFqisrEx5eXlau3atWWRcWloqZ4t/+Gtra3XTTTfpk08+UVpamkaOHKlHHnlEU6dOTVibulOo5ibSTKkQj4ueGwAAohH3In6HDh3Sk08+qY8++kg//vGPNWDAAG3btk1ZWVkaMmRITNeaM2dOxGGoYwuFf/7zn+vnP/95vM1OOr4ow43X3bQFQz0FxQAAtCeucPPGG2+osLBQGRkZ2r17t2bNmqUBAwZozZo1Ki0t1cMPP5zodtqW2XPTUc0NPTcAAEQlrqngRUVFmjFjhj744AOlpqaaxy+++GK9/PLLCWtcT9A8LNX+RxEqKKbmBgCA9sUVbl5//XV973vfa3N8yJAhKisr63SjepLQsFSkrRdCQgXF9NwAANC+uMKN1+sNu43B+++/rxNPPLHTjepJfA3RTQUPrXPDCsUAALQvrnBz6aWX6s4771R9fb0kyeFwqLS0VPPmzdOVV16Z0AbaXbSzpULhJhSGAABAeHGFm3vvvVeHDx/WiSeeqKNHj+rcc8/ViBEj1KdPH/3iF79IdBttrXmF4uhqbui5AQCgfXHNlsrIyNC6dev0yiuv6N///rcOHz6sL33pSyosLEx0+2wvVCDccc1NqOeGcAMAQHtiDjfBYFArV67UmjVrtHv3bjkcDg0fPlzZ2dkyDKPd/ZHQVqjnxh3t9guEGwAA2hXTsJRhGLr00kt1/fXX69NPP9UXv/hFfeELX9CePXs0Y8YMXX755V3VTtvyN8S4/QLhBgCAdsXUc7Ny5Uq9/PLLKikp0Ve+8pVWz7344ou67LLL9PDDD2vatGkJbaSdRb39AsNSAABEJaaem8cff1y33nprm2AjSV/96ld1yy236NFHH01Y43oCcyp4lOGGYSkAANoXU7h544039LWvfS3i8xdddJH+/e9/d7pRPUm02y8wFRwAgOjEFG4+//xzc7fucLKysnTw4MFON6onCRUUd1RzQ88NAADRiSncBAIBpaRELtNxuVxqaGjodKN6kqh3BaegGACAqMRUUGwYhmbMmCGv1xv2eZ/Pl5BG9SS+aHcFp+cGAICoxBRupk+f3uE5zJSKTWgRP3eHU8GpuQEAIBoxhZsHH3ywq9rRY5nbL0Tbc8Ou4AAAtCuuvaWQOL76xp6YqLdfqCfcAADQHsKNxUI1N25XdMNS9NwAANA+wo3Fol6h2OVqdT4AAAiPcGOxUIGwq6NF/NxsvwAAQDQINxYzh6U6WsTPxVRwAACiQbixWNTbL7iZCg4AQDQINxYL9dx0NFsq1HNTHzAUDBpd3i4AAI5XhBuLhXpiOlzEz+0yv2bGFAAAkRFuLGQYRtTDUp4WU8UpKgYAIDLCjYUagoZCI0wpHfTcuFuEH+puAACIjHBjoZY9MB313DgcjuaF/Oi5AQAgIsKNhVqGlI4KiiV2BgcAIBqEGwuZC/g5HHI6Og433hRX0+sINwAAREK4sVBoE8yOhqRCGJYCAKBjhBsLhaZ0d7SvVIi5MzjhBgCAiAg3FmruuYnuY6DmBgCAjhFuLBSquYm954ap4AAAREK4sVC0C/iF0HMDAEDHCDcWCtXOdLSAX4iHmhsAADpEuLFQ7MNSjVPB6bkBACAywo2FzB3Box2Waio89rFxJgAAERFuLBQKNx3tCB7idTeFm3oKigEAiIRwYyFfrAXFTT03fnpuAACIiHBjoVDtTDT7Skkte24INwAAREK4sVCooDjaYSmPq6mgmJ4bAAAiItxYKOa9pei5AQCgQ4QbC8W6t1RzzQ0FxQAAREK4sRB7SwEAkHiEGwvFv7cU4QYAgEgINxYy95aKMdzQcwMAQGSEGws1r3MT5SJ+Tdsv0HMDAEBkhBsLmcNS7AoOAEDCJEW4Wbp0qXJzc5Wamqr8/Hxt3rw54rkPPPCAzjnnHPXv31/9+/dXYWFhu+cns3iHpUKhCAAAtGV5uFm9erWKioq0cOFCbdu2TWPHjtXkyZNVUVER9vz169frm9/8pl566SVt2rRJOTk5uvDCC/Xpp592c8s7zxyWinYRPwqKAQDokOXhZvHixZo1a5ZmzpypUaNGadmyZUpPT9eKFSvCnv/oo4/qpptuUl5enkaOHKk//vGPCgaDKikp6eaWd16se0uluRtrburYOBMAgIgsDTd+v19bt25VYWGheczpdKqwsFCbNm2K6hpHjhxRfX29BgwYEPZ5n8+n6urqVo9kEfOwlBlu6LkBACASS8PNgQMHFAgElJWV1ep4VlaWysrKorrGvHnzNHjw4FYBqaXi4mJlZGSYj5ycnE63O1GaC4qj+xhCPTdH6bkBACAiy4elOmPRokVatWqVnnrqKaWmpoY9Z/78+aqqqjIfe/fu7eZWRuaLsecmzdPUc+Mn3AAAEEmKlW+emZkpl8ul8vLyVsfLy8uVnZ3d7mt/9atfadGiRfrHP/6hMWPGRDzP6/XK6/UmpL2J5o+xoDi1aePMOmZLAQAQkaU9Nx6PR+PHj29VDBwqDi4oKIj4urvvvls/+9nPtHbtWk2YMKE7mtol4i0org8Yqg9QdwMAQDiW9txIUlFRkaZPn64JEyZo4sSJWrJkiWprazVz5kxJ0rRp0zRkyBAVFxdLku666y4tWLBAjz32mHJzc83anN69e6t3796W3Uc8fPWx7S2V2hRupMYZU+4oa3UAAOhJLA83U6dOVWVlpRYsWKCysjLl5eVp7dq1ZpFxaWmpnC2Gbe677z75/X5dddVVra6zcOFC3X777d3Z9E7zB2LdfsEph0MyjMYZU33ClxkBANCjWR5uJGnOnDmaM2dO2OfWr1/f6vvdu3d3fYO6QSBoqD5gSIq+58bhcCg1xaWj9QHWugEAIALGNSzScn+oaGtupOaiYqaDAwAQHuHGIq3CTZSzpSRWKQYAoCOEG4uEFvBzOhof0UptWuvmKGvdAAAQFuHGIqFp4N4UlxyOGIalUlilGACA9hBuLBIKN6GdvqNlrlLM/lIAAIRFuLFIaFjKG2u4oeYGAIB2EW4sYg5LuWP7CMwtGAg3AACERbixSGi2lCfGVYZT2RkcAIB2EW4s0rKgOBZphBsAANpFuLFIaF+p2IelKCgGAKA9hBuLhPaVinVYqnm2FD03AACEQ7ixiK8+VFAc27CUWXPDIn4AAIRFuLFIc80Ns6UAAEgkwo1F/E3r3MS8iB8FxQAAtItwY5H4e26ouQEAoD2EG4t0dio4s6UAAAiPcGMRfyd7bhiWAgAgPMKNReLdWypUUMxsKQAAwiPcWCTemhtzWKqBcAMAQDiEG4uYe0vFGm5Ci/jRcwMAQFiEG4vEW1BszpZqoKAYAIBwCDcWMWtuYtxbKo0VigEAaBfhxiLmsFSMe0u1nC1lGEbC2wUAwPGOcGMRc1gq5l3Bm8/3MTQFAEAbhBuLmBtnxllzI7FKMQAA4RBuLOILxDcs5XY5leJ0SGIhPwAAwiHcWMRXH19BscQWDAAAtIdwYxF/nFPBJSnVw4wpAAAiIdxYxBfnIn5Siy0YGJYCAKANwo1FQsXAqZ0YlvIRbgAAaINwY5Faf4MkqZcnJebXprEzOAAAERFuLBAIGmYxcC9v7OHGS7gBACAiwo0FjjT12khSuif2gmJmSwEAEBnhxgKhWU5Oh+SNo6CYYSkAACIj3Figtinc9PKkyOFwxPz6UBEyBcUAALRFuLFAra9xWCrdG/uQlCSlsc4NAAAREW4scKRFz008Qgv/MSwFAEBbhBsLhKaBd7bnhoJiAADaItxYIDSclO6Or+eGgmIAACIj3FigszU3oYLiOsINAABtEG4s0Nmam+Z1bgg3AAAci3BjAbPmJo4F/CQplWEpAAAiItxY4Iivqecmjq0XpBbhhqngAAC0QbixQGd7bsxhqQZmSwEAcCzCjQXM2VLxhpvQVHB6bgAAaINwY4FaM9zEOyzV+LFRcwMAQFuEGwscaZoK3ivuqeDMlgIAIBLCjQWaa246WVBMuAEAoA3CjQXMdW7i3X6BnhsAACKyPNwsXbpUubm5Sk1NVX5+vjZv3hzx3LfffltXXnmlcnNz5XA4tGTJku5raAKFVihO6+T2C/UBQw0BZkwBANCSpeFm9erVKioq0sKFC7Vt2zaNHTtWkydPVkVFRdjzjxw5opNPPlmLFi1SdnZ2N7c2cY52tuemxSwrhqYAAGjN0nCzePFizZo1SzNnztSoUaO0bNkypaena8WKFWHPP/PMM3XPPffoG9/4hrxebze3NnE6O1vKm+KU2+WQJNXUNSSsXQAA2IFl4cbv92vr1q0qLCxsbozTqcLCQm3atClh7+Pz+VRdXd3qYbUj/s7NlnI4HOqb6pYkVR2tT1i7AACwA8vCzYEDBxQIBJSVldXqeFZWlsrKyhL2PsXFxcrIyDAfOTk5Cbt2PPwNQdUHDEnx99xIUkYa4QYAgHAsLyjuavPnz1dVVZX52Lt3r6XtCfXaSPGvUCxJfQk3AACEFX/XQSdlZmbK5XKpvLy81fHy8vKEFgt7vd6kqs8JTQP3uJxyu+LPlqGem2rCDQAArVjWc+PxeDR+/HiVlJSYx4LBoEpKSlRQUGBVs7pcqOcmPc56mxB6bgAACM+ynhtJKioq0vTp0zVhwgRNnDhRS5YsUW1trWbOnClJmjZtmoYMGaLi4mJJjUXI77zzjvn1p59+qh07dqh3794aMWKEZfcRi1pf0zTwTtTbSFJGWuPr6bkBAKA1S8PN1KlTVVlZqQULFqisrEx5eXlau3atWWRcWloqp7O5c2nfvn0aN26c+f2vfvUr/epXv9K5556r9evXd3fz49K89ULnem4oKAYAIDxLw40kzZkzR3PmzAn73LGBJTc3V4ZhdEOrus6Rpp6bdG9ne26aam5Y5wYAgFZsP1sq2YR6bnrRcwMAQJcg3HSzo+bqxJ0sKGYRPwAAwiLcdLPObr0QQs8NAADhEW662RFf57ZeCGEqOAAA4VleUNzTxNNz89hrpW2OHaz1m38+9lqpvpU/NDENBADgOEfPTTc7kqCC4rSm1zcEDdUHgp1uFwAAdkG46Wah7RfSOllz40lxytH09dH6QCdbBQCAfRBuupnZc9PJmhunw6FUd+M1QjOwAAAA4abbhbZf6OxsKal5aKqOnhsAAEyEm26WqJobSUoL9dwQbgAAMBFuulltgrZfkFqEG4alAAAwEW66WSJ7blLdjR8fPTcAADQj3HSz5tlSCRiW8jAsBQDAsQg33SwUbnoloqC4aViqjmEpAABMhJtuZBiGuSt4eiengkstC4pZxA8AgBDCTTeqqw/KMBq/TkTPTSrDUgAAtEG46UahXhupudelM5gtBQBAW4SbbnTU3DTTJafT0cHZHTNrbui5AQDARLjpRgePNO7k3Sc1MZuxM1sKAIC2CDfdqKLaJ0ka2Cc1IddjhWIAANoi3HSjippQuPEm5HqhjTP9DUHVB5gxBQCARLjpVpWhcNM3seFGkqqP1ifkmgAAHO8IN92ooqZOknRigoalXE6HvCmNH2F1XUMHZwMA0DMQbrpRooelpOa6myp6bgAAkES46VZdEm48hBsAAFoi3HSjyurQsFTiwk1opeOKpmsDANDTEW66iWEYqjwcKihOTM2NJA3o7ZEk7f6sNmHXBADgeEa46SaHjtSrPtC4sdSJvRPXc5PZdK1dBwg3AABIhJtuE6q36Z/uliclcT/2zF6NPTe7DhxJ2DUBADieEW66SWgaeKJWJw45oannZs9ntTJCW44DANCDEW66ibn1QoIW8Avp38sth6Qj/oDZOwQAQE9GuOkmoeCRyJlSkpTidKq/OTRF3Q0AAISbbtK8OnFiw40kZYZmTBFuAAAg3HQXc1+pBNfcSNIJvZgxBQBACOGmm3TF6sQhJ/RmWAoAgBDCTTep7MJwE1rrhoX8AAAg3HSb0PYIiVydOCTTnA5+RMEg08EBAD0b4aYb1PoaVOsPSOqanpuMNLfcLod8DUHtZ48pAEAPR7jpBqF6m14el3p5UxJ+fZfToZwB6ZKkXZUMTQEAejbCTTeo7KI1bloafkIvSdIu6m4AAD0c4aYbdNXWCy0Nz2wMNzvLqrvsPQAAOB4QbrpBaHG97IyuCzcFp5wgSfrbG/tVVx/osvcBACDZEW66wcYPD0iSzhw+oMve47zTB2pwRqoOHanXc2/t77L3AQAg2RFuulitr0Fb9xyUJJ0zIrPL3sfldOibE4dKkh57rbTL3gcAgGRHuOlim3d9rvqAoZP6p2nYCeld+l7/dWaOXE6HXt99UDvLarr0vQAASFaEmy72zw8ah6TOOTVTDoejS98rq2+qLjgjS5L0h5c/YkE/AECPlPhFV9DKxg8rJUlfHnFit7zftwuGae3bZVqz7VPtOlCrHxaepow0txySjtYHVFcfUGZvrwb3S1P/dHeXBy4AALob4aYLlVfX6f3yw3I4pEkjTuiW95w0IlM/v2y0Fj33nraXHtL0FZsjnjukX5ou/EKWLv7iIE0Y1p+gAwCwBcJNF9rYNCQ1ZkiG+qV7uu19rz1rmArPyNJda9/T9tKDqg8YOuxrkMflVIrLocN1DarxNejTQ0f14Cu79eAru5XZ26NZ55ysK8efZO5VBQDA8Sgpws3SpUt1zz33qKysTGPHjtXvfvc7TZw4MeL5TzzxhG677Tbt3r1bp556qu666y5dfPHF3djijh3xN+hP/9ojSfryqV03Syok3AypM3MH6Mzc8NPP/Q1BfVhxWG/vq9Lb+6t14LBfxc+9p1+9sFMXjGrszTn7lEwN6JXYUFbra9D+qjpV1NTJVx9UfSCoXt4UDezj1aB+aerdBdtTAAB6Fsv/JVm9erWKioq0bNky5efna8mSJZo8ebJ27typgQMHtjn/1Vdf1Te/+U0VFxfrP//zP/XYY4/psssu07Zt2zR69GgL7qCtuvqArn9oi3bsPaQ+3hRdNT7H6ia14UlxatTgvho1uK8urQ/ojU+q9PGBw/r3J1V69s0yPftmmSTp5BN76ZQTe2vogHT1T3erT6pbTocUKlU2DCkQNNQQDKo+YKg+EGx6GPI3BHXwiF/l1XWqqPaposanw76GdtvVL82tcUP76bTsPjptYB+d1D9NWX1T1TfNLZfToRSnQ66mh9PhkEOSwyGG1AAAJodhGJZOqcnPz9eZZ56p3//+95KkYDConJwcff/739ctt9zS5vypU6eqtrZWf/vb38xjZ511lvLy8rRs2bIO36+6uloZGRmqqqpS3759E3YflTU+bXi/Ujv2HtSrH36mjw/UqpfHpYe/k6/xw/q3+9pkWpdmf9VRbS89pA8rDqusi3YY96Y41TfVLU+KU06HVNcQVE1dverqg526rtvlkDfFJW+Ks/HhbvF1ikted8s/nc3nup3yupxyOh0yjObgJsNoFeJC37U8p+VxNR0PBg0FDEOBYPPD3xCULxCUv6HxUd/0dUPQkMfllCfFKbfLIU+LdqW6XUp1N/4Z+j50TylOh/n+ZnNb/Cxa/mfd5j/wVq9pcV7Ea8V2viK8t2FIwaafS+jrYNOfkuR0OORyhv5sDrAup0Muh0NO5zHPOxwy1PwZhD6X0L23Ot7iOaOpYYYMNQQNNQRCfzZ+HoFjvpaj8T2dDsmhpj8dTeHaobDfOx3NbXc61Nj2pntoeZ+hc0I/slB7Qz+7Vp9juHOOvecWP/S21wp/vM3f8xbXCp0XNAzz51EfCDb9aSgQDCpoqMVn1fq+XM7Gn4nL0fx5Oh1N5x/zM3E6FPbeW96TJMmhpv9T0/L/3DS+r445Hvo/QK3+eh77fYS/322fO/Z1kf/pPPapdq/b5tzI7xHtf8sdX7f1c0Gj8XeUv8XvKH8gKF99QEFDSnE55HY1/t5JcTnlDv3pcjQfczmU4nSa5w7o5dFZJye21jSWf78t7bnx+/3aunWr5s+fbx5zOp0qLCzUpk2bwr5m06ZNKioqanVs8uTJevrpp8Oe7/P55PP5zO+rqqokNf6QEmnLhwdU9MhW8/t0j1O/v3q8Tu3v6vC9jtQmz5o0GSnSeSf31nkn99bhunpV1Pj1WU2dDtU1qM4fUF1DUM3/mTjM/23Zo9L8i0tK87jUx+tW79QU9fG61SfVJY/bFfa9j/obVFHjV2VNnSprfKqs8an6aL1qfA2qD3ScwX1NDwCAtcaclKHHZp2V0GuG/i2Npk/G0nBz4MABBQIBZWVltTqelZWl9957L+xrysrKwp5fVlYW9vzi4mLdcccdbY7n5HT9UNFX7+7ytwAAIOnslZRxc9dcu6amRhkZGe2eY3nNTVebP39+q56eYDCozz//XCeccEJS1GlUV1crJydHe/fuTegwWTLqSfcqcb921pPuVeJ+7e54uV/DMFRTU6PBgwd3eK6l4SYzM1Mul0vl5eWtjpeXlys7Ozvsa7Kzs2M63+v1yuttPbW5X79+8Te6i/Tt2zep/1IlUk+6V4n7tbOedK8S92t3x8P9dtRjE2Lp9gsej0fjx49XSUmJeSwYDKqkpEQFBQVhX1NQUNDqfElat25dxPMBAEDPYvmwVFFRkaZPn64JEyZo4sSJWrJkiWprazVz5kxJ0rRp0zRkyBAVFxdLkubOnatzzz1X9957ry655BKtWrVKW7Zs0f3332/lbQAAgCRhebiZOnWqKisrtWDBApWVlSkvL09r1641i4ZLS0vldDZ3MJ199tl67LHH9D//8z+69dZbdeqpp+rpp59OmjVuYuX1erVw4cI2Q2d21JPuVeJ+7awn3avE/dqdHe/X8nVuAAAAEsnSmhsAAIBEI9wAAABbIdwAAABbIdwAAABbIdxYaOnSpcrNzVVqaqry8/O1efNmq5uUEC+//LK+/vWva/DgwXI4HG32/TIMQwsWLNCgQYOUlpamwsJCffDBB9Y0tpOKi4t15plnqk+fPho4cKAuu+wy7dy5s9U5dXV1mj17tk444QT17t1bV155ZZuFKI8X9913n8aMGWMu9lVQUKDnnnvOfN5O93qsRYsWyeFw6Ic//KF5zE73e/vttzduOtniMXLkSPN5O91ryKeffqprr71WJ5xwgtLS0vTFL35RW7ZsMZ+30++q3NzcNp+vw+HQ7NmzJdnv8yXcWGT16tUqKirSwoULtW3bNo0dO1aTJ09WRUWF1U3rtNraWo0dO1ZLly4N+/zdd9+t3/72t1q2bJlee+019erVS5MnT1ZdXdfsQt6VNmzYoNmzZ+tf//qX1q1bp/r6el144YWqra01z/nRj36kv/71r3riiSe0YcMG7du3T1dccYWFrY7fSSedpEWLFmnr1q3asmWLvvrVr2rKlCl6++23JdnrXlt6/fXX9Yc//EFjxoxpddxu9/uFL3xB+/fvNx8bN240n7PbvR48eFCTJk2S2+3Wc889p3feeUf33nuv+vfvb55jp99Vr7/+eqvPdt26dZKkq6++WpL9Pl8ZsMTEiRON2bNnm98HAgFj8ODBRnFxsYWtSjxJxlNPPWV+HwwGjezsbOOee+4xjx06dMjwer3G448/bkELE6uiosKQZGzYsMEwjMZ7c7vdxhNPPGGe8+677xqSjE2bNlnVzITq37+/8cc//tG291pTU2Oceuqpxrp164xzzz3XmDt3rmEY9vtsFy5caIwdOzbsc3a7V8MwjHnz5hlf/vKXIz5v999Vc+fONU455RQjGAza8vOl58YCfr9fW7duVWFhoXnM6XSqsLBQmzZtsrBlXW/Xrl0qKytrde8ZGRnKz8+3xb1XVVVJkgYMGCBJ2rp1q+rr61vd78iRIzV06NDj/n4DgYBWrVql2tpaFRQU2PZeZ8+erUsuuaTVfUn2/Gw/+OADDR48WCeffLKuueYalZaWSrLnvT7zzDOaMGGCrr76ag0cOFDjxo3TAw88YD5v599Vfr9fjzzyiK677jo5HA5bfr6EGwscOHBAgUDAXIU5JCsrS2VlZRa1qnuE7s+O9x4MBvXDH/5QkyZNMlfMLisrk8fjabNZ6/F8v2+++aZ69+4tr9erG264QU899ZRGjRply3tdtWqVtm3bZm7/0pLd7jc/P18rV67U2rVrdd9992nXrl0655xzVFNTY7t7laSPP/5Y9913n0499VQ9//zzuvHGG/WDH/xADz30kCR7/656+umndejQIc2YMUOS/f4uS0mw/QJgF7Nnz9Zbb73Vqk7Bjk4//XTt2LFDVVVVevLJJzV9+nRt2LDB6mYl3N69ezV37lytW7dOqampVjeny1100UXm12PGjFF+fr6GDRum//u//1NaWpqFLesawWBQEyZM0C9/+UtJ0rhx4/TWW29p2bJlmj59usWt61rLly/XRRddpMGDB1vdlC5Dz40FMjMz5XK52lSil5eXKzs726JWdY/Q/dnt3ufMmaO//e1veumll3TSSSeZx7Ozs+X3+3Xo0KFW5x/P9+vxeDRixAiNHz9excXFGjt2rH7zm9/Y7l63bt2qiooKfelLX1JKSopSUlK0YcMG/fa3v1VKSoqysrJsdb/H6tevn0477TR9+OGHtvtsJWnQoEEaNWpUq2NnnHGGORRn199Ve/bs0T/+8Q9df/315jE7fr6EGwt4PB6NHz9eJSUl5rFgMKiSkhIVFBRY2LKuN3z4cGVnZ7e69+rqar322mvH5b0bhqE5c+boqaee0osvvqjhw4e3en78+PFyu92t7nfnzp0qLS09Lu83nGAwKJ/PZ7t7Pf/88/Xmm29qx44d5mPChAm65pprzK/tdL/HOnz4sD766CMNGjTIdp+tJE2aNKnNsg3vv/++hg0bJsl+v6tCHnzwQQ0cOFCXXHKJecyOny+zpSyyatUqw+v1GitXrjTeeecd47vf/a7Rr18/o6yszOqmdVpNTY2xfft2Y/v27YYkY/Hixcb27duNPXv2GIZhGIsWLTL69etn/OUvfzHeeOMNY8qUKcbw4cONo0ePWtzy2N14441GRkaGsX79emP//v3m48iRI+Y5N9xwgzF06FDjxRdfNLZs2WIUFBQYBQUFFrY6frfccouxYcMGY9euXcYbb7xh3HLLLYbD4TBeeOEFwzDsda/htJwtZRj2ut///u//NtavX2/s2rXLeOWVV4zCwkIjMzPTqKioMAzDXvdqGIaxefNmIyUlxfjFL35hfPDBB8ajjz5qpKenG4888oh5jp1+VxlG46zcoUOHGvPmzWvznN0+X8KNhX73u98ZQ4cONTwejzFx4kTjX//6l9VNSoiXXnrJkNTmMX36dMMwGqdY3nbbbUZWVpbh9XqN888/39i5c6e1jY5TuPuUZDz44IPmOUePHjVuuukmo3///kZ6erpx+eWXG/v377eu0Z1w3XXXGcOGDTM8Ho9x4oknGueff74ZbAzDXvcazrHhxk73O3XqVGPQoEGGx+MxhgwZYkydOtX48MMPzeftdK8hf/3rX43Ro0cbXq/XGDlypHH//fe3et5Ov6sMwzCef/55Q1LYe7Db5+swDMOwpMsIAACgC1BzAwAAbIVwAwAAbIVwAwAAbIVwAwAAbIVwAwAAbIVwAwAAbIVwAwAAbIVwAwAAbIVwAwAAbIVwAyChKisrdeONN2ro0KHyer3Kzs7W5MmT9corr3T42tzcXDkcDjkcDqWnp+uLX/yi/vjHP4Y99/HHH5fL5dLs2bPbPLd+/XrzOk6nUxkZGRo3bpx+8pOfaP/+/a3Ovf3225WXl2d+P2PGDF122WURrxnaOTkQCGjRokUaOXKk0tLSNGDAAOXn50dsL4DuQ7gBkFBXXnmltm/froceekjvv/++nnnmGZ133nn67LPPonr9nXfeqf379+utt97Stddeq1mzZum5555rc97y5cv1k5/8RI8//rjq6urCXmvnzp3at2+fXn/9dc2bN0//+Mc/NHr0aL355pudukdJuuOOO/TrX/9aP/vZz/TOO+/opZde0ne/+10z/ACwTorVDQBgH4cOHdI///lPrV+/Xueee64kadiwYZo4cWLU1+jTp4+ys7MlSfPmzdPdd9+tdevW6aKLLjLP2bVrl1599VX9+c9/1ksvvaQ1a9boW9/6VptrDRw4UP369VN2drZOO+00TZkyRePGjdONN96ojRs3dupen3nmGd100026+uqrzWNjx47t1DUBJAY9NwASpnfv3urdu7eefvpp+Xy+Tl0rGAzqz3/+sw4ePCiPx9PquQcffFCXXHKJMjIydO2112r58uVRXTMtLU033HCDXnnlFVVUVHSqfdnZ2XrxxRdVWVnZqesASDzCDYCESUlJ0cqVK/XQQw+pX79+mjRpkm699Va98cYbUV9j3rx56t27t7xer6666ir1799f119/vfl8MBjUypUrde2110qSvvGNb2jjxo3atWtXVNcfOXKkJGn37t3R31gYixcvVmVlpbKzszVmzBjdcMMNYYfPAHQ/wg2AhLryyiu1b98+PfPMM/ra176m9evX60tf+pJWrlwZ1et//OMfa8eOHXrxxReVn5+vX//61xoxYoT5/Lp161RbW6uLL75YkpSZmakLLrhAK1asiOr6hmFIkhwOR2w3doxRo0bprbfe0r/+9S9dd911qqio0Ne//vVWQQyANQg3ABIuNTVVF1xwgW677Ta9+uqrmjFjhhYuXBjVazMzMzVixAidc845euKJJ/SDH/xA77zzjvn88uXL9fnnnystLU0pKSlKSUnRs88+q4ceekjBYLDD67/77ruSGmdmhdO3b19VVVW1OX7o0CG5XC716tXLPOZ0OnXmmWfqhz/8odasWaOVK1dq+fLlUfciAegahBsAXW7UqFGqra2N+XU5OTmaOnWq5s+fL0n67LPP9Je//EWrVq3Sjh07zMf27dt18OBBvfDCC+1e7+jRo7r//vv1H//xHzrxxBPDnnP66afr7bffblMztG3bNg0fPlxutzvi9UeNGiVJcd0rgMRhthSAhPnss8909dVX67rrrtOYMWPUp08fbdmyRXfffbemTJkS1zXnzp2r0aNHa8uWLdq4caNOOOEE/dd//VebYaWLL75Yy5cv19e+9jXzWEVFherq6lRTU6OtW7fq7rvv1oEDB7RmzZqI73fNNdfozjvv1LRp0/STn/xEGRkZevnll7VkyRLdfffd5nlXXXWVJk2apLPPPlvZ2dnatWuX5s+fr9NOO82s6wFgDcINgITp3bu3WSfz0Ucfqb6+Xjk5OZo1a5ZuvfXWuK45atQoXXjhhVqwYIE++eQTXX755WHrZa688kp9+9vf1oEDB8xjp59+uhwOh3r37q2TTz5ZF154oYqKisyp5uH069dP//znP3XLLbfo0ksvVVVVlUaMGKHFixfrO9/5jnne5MmT9fjjj6u4uFhVVVXKzs7WV7/6Vd1+++1KSeFXK2AlhxGqrgMAALABam4AAICtEG4AdItHH33UXOTv2McXvvAFq5sHwEYYlgLQLWpqalReXh72ObfbrWHDhnVziwDYFeEGAADYCsNSAADAVgg3AADAVgg3AADAVgg3AADAVgg3AADAVgg3AADAVgg3AADAVv4fWbgkF/qV9H8AAAAASUVORK5CYII=\n"
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/tmp/ipython-input-3541476722.py:4: UserWarning: \n",
+            "\n",
+            "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n",
+            "\n",
+            "Please adapt your code to use either `displot` (a figure-level function with\n",
+            "similar flexibility) or `histplot` (an axes-level function for histograms).\n",
+            "\n",
+            "For a guide to updating your code to use the new functions, please see\n",
+            "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n",
+            "\n",
+            "  sns.distplot(df[col])\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/tmp/ipython-input-3541476722.py:4: UserWarning: \n",
+            "\n",
+            "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n",
+            "\n",
+            "Please adapt your code to use either `displot` (a figure-level function with\n",
+            "similar flexibility) or `histplot` (an axes-level function for histograms).\n",
+            "\n",
+            "For a guide to updating your code to use the new functions, please see\n",
+            "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n",
+            "\n",
+            "  sns.distplot(df[col])\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/tmp/ipython-input-3541476722.py:4: UserWarning: \n",
+            "\n",
+            "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n",
+            "\n",
+            "Please adapt your code to use either `displot` (a figure-level function with\n",
+            "similar flexibility) or `histplot` (an axes-level function for histograms).\n",
+            "\n",
+            "For a guide to updating your code to use the new functions, please see\n",
+            "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n",
+            "\n",
+            "  sns.distplot(df[col])\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/tmp/ipython-input-3541476722.py:4: UserWarning: \n",
+            "\n",
+            "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n",
+            "\n",
+            "Please adapt your code to use either `displot` (a figure-level function with\n",
+            "similar flexibility) or `histplot` (an axes-level function for histograms).\n",
+            "\n",
+            "For a guide to updating your code to use the new functions, please see\n",
+            "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n",
+            "\n",
+            "  sns.distplot(df[col])\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/tmp/ipython-input-3541476722.py:4: UserWarning: \n",
+            "\n",
+            "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n",
+            "\n",
+            "Please adapt your code to use either `displot` (a figure-level function with\n",
+            "similar flexibility) or `histplot` (an axes-level function for histograms).\n",
+            "\n",
+            "For a guide to updating your code to use the new functions, please see\n",
+            "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n",
+            "\n",
+            "  sns.distplot(df[col])\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/tmp/ipython-input-3541476722.py:4: UserWarning: \n",
+            "\n",
+            "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n",
+            "\n",
+            "Please adapt your code to use either `displot` (a figure-level function with\n",
+            "similar flexibility) or `histplot` (an axes-level function for histograms).\n",
+            "\n",
+            "For a guide to updating your code to use the new functions, please see\n",
+            "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n",
+            "\n",
+            "  sns.distplot(df[col])\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/tmp/ipython-input-3541476722.py:4: UserWarning: \n",
+            "\n",
+            "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n",
+            "\n",
+            "Please adapt your code to use either `displot` (a figure-level function with\n",
+            "similar flexibility) or `histplot` (an axes-level function for histograms).\n",
+            "\n",
+            "For a guide to updating your code to use the new functions, please see\n",
+            "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n",
+            "\n",
+            "  sns.distplot(df[col])\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/tmp/ipython-input-3541476722.py:4: UserWarning: \n",
+            "\n",
+            "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n",
+            "\n",
+            "Please adapt your code to use either `displot` (a figure-level function with\n",
+            "similar flexibility) or `histplot` (an axes-level function for histograms).\n",
+            "\n",
+            "For a guide to updating your code to use the new functions, please see\n",
+            "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n",
+            "\n",
+            "  sns.distplot(df[col])\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/tmp/ipython-input-3541476722.py:4: UserWarning: \n",
+            "\n",
+            "`distplot` is a deprecated function and will be removed in seaborn v0.14.0.\n",
+            "\n",
+            "Please adapt your code to use either `displot` (a figure-level function with\n",
+            "similar flexibility) or `histplot` (an axes-level function for histograms).\n",
+            "\n",
+            "For a guide to updating your code to use the new functions, please see\n",
+            "https://gist.github.com/mwaskom/de44147ed2974457ad6372750bbe5751\n",
+            "\n",
+            "  sns.distplot(df[col])\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "HERE EVERY PLOT IS HIGHLY SKEWWD SO WE WILL USE MEDIAN IMPUTATION"
+      ],
+      "metadata": {
+        "id": "nC4D1sNvLQOJ"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "num_cols"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "NugCZ8LGNiAQ",
+        "outputId": "5272825a-6033-4460-d526-ab5c84194de1"
+      },
+      "execution_count": 128,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "Index(['P_RADIUS', 'P_PERIOD', 'P_SEMI_MAJOR_AXIS', 'P_PERIASTRON',\n",
+              "       'P_APASTRON', 'S_MASS', 'S_RADIUS', 'S_LUMINOSITY', 'S_TEMPERATURE',\n",
+              "       'S_AGE', 'S_METALLICITY', 'S_LOG_G', 'S_MAG', 'S_SNOW_LINE',\n",
+              "       'S_TIDAL_LOCK', 'P_DISTANCE'],\n",
+              "      dtype='object')"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 128
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "for col in num_cols:\n",
+        "    df[col] = df[col].fillna(df[col].median())"
+      ],
+      "metadata": {
+        "id": "neieX0q8LP_w"
+      },
+      "execution_count": 129,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "For categorical the most frequent replacement will be used here in P_Type and S_tidal_lock"
+      ],
+      "metadata": {
+        "id": "OzlH128lL2eD"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "cat_col = ['P_TYPE', 'S_TIDAL_LOCK']"
+      ],
+      "metadata": {
+        "id": "wzaDJObwLbBT"
+      },
+      "execution_count": 130,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "for col in cat_col:\n",
+        "    df[col] = df[col].fillna(df[col].mode()[0])"
+      ],
+      "metadata": {
+        "id": "eHvdRs-VMIzc"
+      },
+      "execution_count": 131,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df.isnull().sum()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 649
+        },
+        "id": "VBjTsJr_MLmm",
+        "outputId": "b8e6569d-814e-4059-c6cd-0d93def8a082"
+      },
+      "execution_count": 132,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "P_RADIUS             0\n",
+              "P_TYPE               0\n",
+              "P_PERIOD             0\n",
+              "P_SEMI_MAJOR_AXIS    0\n",
+              "P_PERIASTRON         0\n",
+              "P_APASTRON           0\n",
+              "S_MASS               0\n",
+              "S_RADIUS             0\n",
+              "S_LUMINOSITY         0\n",
+              "S_TEMPERATURE        0\n",
+              "S_AGE                0\n",
+              "S_METALLICITY        0\n",
+              "S_LOG_G              0\n",
+              "S_MAG                0\n",
+              "S_SNOW_LINE          0\n",
+              "S_TIDAL_LOCK         0\n",
+              "P_DETECTION          0\n",
+              "P_DISTANCE           0\n",
+              "dtype: int64"
+            ],
+            "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>0</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>P_RADIUS</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_TYPE</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_PERIOD</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_SEMI_MAJOR_AXIS</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_PERIASTRON</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_APASTRON</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_MASS</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_RADIUS</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_LUMINOSITY</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_TEMPERATURE</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_AGE</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_METALLICITY</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_LOG_G</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_MAG</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_SNOW_LINE</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>S_TIDAL_LOCK</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_DETECTION</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>P_DISTANCE</th>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div><br><label><b>dtype:</b> int64</label>"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 132
+        }
+      ]
+    }
+  ]
+}
\ No newline at end of file