diff --git a/Cancer Cell Analysis with Machine Learning/cancer_analysis.ipynb b/Cancer Cell Analysis with Machine Learning/cancer_analysis.ipynb
new file mode 100644
index 0000000..fc69c72
--- /dev/null
+++ b/Cancer Cell Analysis with Machine Learning/cancer_analysis.ipynb	
@@ -0,0 +1,1050 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 3",
+      "language": "python",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.7.3"
+    },
+    "colab": {
+      "name": "cancer_analysis.ipynb",
+      "provenance": [],
+      "include_colab_link": true
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/hsleonis/cancer-analysis/blob/master/cancer_analysis.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "eTED0DR8lmiE",
+        "colab_type": "text"
+      },
+      "source": [
+        "# Machine Learning for Cancer Analysis"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "hmb4gaXQlmiH",
+        "colab_type": "code",
+        "colab": {}
+      },
+      "source": [
+        "### Some imports\n",
+        "import numpy as np               # efficient matrix-vector operations\n",
+        "import numpy.linalg as la        # linear algebra (solvers etc.)\n",
+        "import pandas as pd              # data processing, CSV file I/O (e.g. pd.read_csv)\n",
+        "import seaborn as sns            # data visualization\n",
+        "import matplotlib.pyplot as plt  # basic plotting"
+      ],
+      "execution_count": 0,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "oj8Fx3hJmlBn",
+        "colab_type": "code",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 244
+        },
+        "outputId": "e128c31b-e7f9-4cc3-a01a-df89f4d7352d"
+      },
+      "source": [
+        "# import dataset\n",
+        "df = pd.read_csv('https://drive.google.com/uc?id=1-ZeH2bMqmqRBo3t9wAuT4JixE9qOKZaa')\n",
+        "\n",
+        "# set target labels\n",
+        "labels = df['diagnosis']\n",
+        "\n",
+        "# drop first unnamed column\n",
+        "df.drop(df.columns[0], axis=1, inplace=True)\n",
+        "\n",
+        "# drop labels\n",
+        "df.drop(['diagnosis'], axis=1, inplace=True)\n",
+        "\n",
+        "# check dataset\n",
+        "df.head()"
+      ],
+      "execution_count": 61,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/html": [
+              "<div>\n",
+              "<style scoped>\n",
+              "    .dataframe tbody tr th:only-of-type {\n",
+              "        vertical-align: middle;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe tbody tr th {\n",
+              "        vertical-align: top;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe thead th {\n",
+              "        text-align: right;\n",
+              "    }\n",
+              "</style>\n",
+              "<table border=\"1\" class=\"dataframe\">\n",
+              "  <thead>\n",
+              "    <tr style=\"text-align: right;\">\n",
+              "      <th></th>\n",
+              "      <th>radius_mean</th>\n",
+              "      <th>texture_mean</th>\n",
+              "      <th>perimeter_mean</th>\n",
+              "      <th>area_mean</th>\n",
+              "      <th>smoothness_mean</th>\n",
+              "      <th>compactness_mean</th>\n",
+              "      <th>concavity_mean</th>\n",
+              "      <th>concave points_mean</th>\n",
+              "      <th>symmetry_mean</th>\n",
+              "      <th>fractal_dimension_mean</th>\n",
+              "      <th>radius_se</th>\n",
+              "      <th>texture_se</th>\n",
+              "      <th>perimeter_se</th>\n",
+              "      <th>area_se</th>\n",
+              "      <th>smoothness_se</th>\n",
+              "      <th>compactness_se</th>\n",
+              "      <th>concavity_se</th>\n",
+              "      <th>concave points_se</th>\n",
+              "      <th>symmetry_se</th>\n",
+              "      <th>fractal_dimension_se</th>\n",
+              "      <th>radius_worst</th>\n",
+              "      <th>texture_worst</th>\n",
+              "      <th>perimeter_worst</th>\n",
+              "      <th>area_worst</th>\n",
+              "      <th>smoothness_worst</th>\n",
+              "      <th>compactness_worst</th>\n",
+              "      <th>concavity_worst</th>\n",
+              "      <th>concave points_worst</th>\n",
+              "      <th>symmetry_worst</th>\n",
+              "      <th>fractal_dimension_worst</th>\n",
+              "      <th>precondition</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>18.770</td>\n",
+              "      <td>21.43</td>\n",
+              "      <td>122.90</td>\n",
+              "      <td>1092.0</td>\n",
+              "      <td>0.09116</td>\n",
+              "      <td>0.14020</td>\n",
+              "      <td>0.10600</td>\n",
+              "      <td>0.060900</td>\n",
+              "      <td>0.1953</td>\n",
+              "      <td>0.06083</td>\n",
+              "      <td>0.6422</td>\n",
+              "      <td>1.530</td>\n",
+              "      <td>4.369</td>\n",
+              "      <td>88.25</td>\n",
+              "      <td>0.007548</td>\n",
+              "      <td>0.03897</td>\n",
+              "      <td>0.03914</td>\n",
+              "      <td>0.018160</td>\n",
+              "      <td>0.02168</td>\n",
+              "      <td>0.004445</td>\n",
+              "      <td>24.54</td>\n",
+              "      <td>34.37</td>\n",
+              "      <td>161.10</td>\n",
+              "      <td>1873.0</td>\n",
+              "      <td>0.1498</td>\n",
+              "      <td>0.48270</td>\n",
+              "      <td>0.4634</td>\n",
+              "      <td>0.20480</td>\n",
+              "      <td>0.3679</td>\n",
+              "      <td>0.09870</td>\n",
+              "      <td>lung</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>13.610</td>\n",
+              "      <td>24.69</td>\n",
+              "      <td>87.76</td>\n",
+              "      <td>572.6</td>\n",
+              "      <td>0.09258</td>\n",
+              "      <td>0.07862</td>\n",
+              "      <td>0.05285</td>\n",
+              "      <td>0.030850</td>\n",
+              "      <td>0.1761</td>\n",
+              "      <td>0.06130</td>\n",
+              "      <td>0.2310</td>\n",
+              "      <td>1.005</td>\n",
+              "      <td>1.752</td>\n",
+              "      <td>19.83</td>\n",
+              "      <td>0.004088</td>\n",
+              "      <td>0.01174</td>\n",
+              "      <td>0.01796</td>\n",
+              "      <td>0.006880</td>\n",
+              "      <td>0.01323</td>\n",
+              "      <td>0.001465</td>\n",
+              "      <td>16.89</td>\n",
+              "      <td>35.64</td>\n",
+              "      <td>113.20</td>\n",
+              "      <td>848.7</td>\n",
+              "      <td>0.1471</td>\n",
+              "      <td>0.28840</td>\n",
+              "      <td>0.3796</td>\n",
+              "      <td>0.13290</td>\n",
+              "      <td>0.3470</td>\n",
+              "      <td>0.07900</td>\n",
+              "      <td>heart</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>12.270</td>\n",
+              "      <td>17.92</td>\n",
+              "      <td>78.41</td>\n",
+              "      <td>466.1</td>\n",
+              "      <td>0.08685</td>\n",
+              "      <td>0.06526</td>\n",
+              "      <td>0.03211</td>\n",
+              "      <td>0.026530</td>\n",
+              "      <td>0.1966</td>\n",
+              "      <td>0.05597</td>\n",
+              "      <td>0.3342</td>\n",
+              "      <td>1.781</td>\n",
+              "      <td>2.079</td>\n",
+              "      <td>25.79</td>\n",
+              "      <td>0.005888</td>\n",
+              "      <td>0.02310</td>\n",
+              "      <td>0.02059</td>\n",
+              "      <td>0.010750</td>\n",
+              "      <td>0.02578</td>\n",
+              "      <td>0.002267</td>\n",
+              "      <td>14.10</td>\n",
+              "      <td>28.88</td>\n",
+              "      <td>89.00</td>\n",
+              "      <td>610.2</td>\n",
+              "      <td>0.1240</td>\n",
+              "      <td>0.17950</td>\n",
+              "      <td>0.1377</td>\n",
+              "      <td>0.09532</td>\n",
+              "      <td>0.3455</td>\n",
+              "      <td>0.06896</td>\n",
+              "      <td>lung</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>11.340</td>\n",
+              "      <td>18.61</td>\n",
+              "      <td>72.76</td>\n",
+              "      <td>391.2</td>\n",
+              "      <td>0.10490</td>\n",
+              "      <td>0.08499</td>\n",
+              "      <td>0.04302</td>\n",
+              "      <td>0.025940</td>\n",
+              "      <td>0.1927</td>\n",
+              "      <td>0.06211</td>\n",
+              "      <td>0.2430</td>\n",
+              "      <td>1.010</td>\n",
+              "      <td>1.491</td>\n",
+              "      <td>18.19</td>\n",
+              "      <td>0.008577</td>\n",
+              "      <td>0.01641</td>\n",
+              "      <td>0.02099</td>\n",
+              "      <td>0.011070</td>\n",
+              "      <td>0.02434</td>\n",
+              "      <td>0.001217</td>\n",
+              "      <td>12.47</td>\n",
+              "      <td>23.03</td>\n",
+              "      <td>79.15</td>\n",
+              "      <td>478.6</td>\n",
+              "      <td>0.1483</td>\n",
+              "      <td>0.15740</td>\n",
+              "      <td>0.1624</td>\n",
+              "      <td>0.08542</td>\n",
+              "      <td>0.3060</td>\n",
+              "      <td>0.06783</td>\n",
+              "      <td>heart</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>9.683</td>\n",
+              "      <td>19.34</td>\n",
+              "      <td>61.05</td>\n",
+              "      <td>285.7</td>\n",
+              "      <td>0.08491</td>\n",
+              "      <td>0.05030</td>\n",
+              "      <td>0.02337</td>\n",
+              "      <td>0.009615</td>\n",
+              "      <td>0.1580</td>\n",
+              "      <td>0.06235</td>\n",
+              "      <td>0.2957</td>\n",
+              "      <td>1.363</td>\n",
+              "      <td>2.054</td>\n",
+              "      <td>18.24</td>\n",
+              "      <td>0.007440</td>\n",
+              "      <td>0.01123</td>\n",
+              "      <td>0.02337</td>\n",
+              "      <td>0.009615</td>\n",
+              "      <td>0.02203</td>\n",
+              "      <td>0.004154</td>\n",
+              "      <td>10.93</td>\n",
+              "      <td>25.59</td>\n",
+              "      <td>69.10</td>\n",
+              "      <td>364.2</td>\n",
+              "      <td>0.1199</td>\n",
+              "      <td>0.09546</td>\n",
+              "      <td>0.0935</td>\n",
+              "      <td>0.03846</td>\n",
+              "      <td>0.2552</td>\n",
+              "      <td>0.07920</td>\n",
+              "      <td>heart</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>"
+            ],
+            "text/plain": [
+              "   radius_mean  texture_mean  ...  fractal_dimension_worst  precondition\n",
+              "0       18.770         21.43  ...                  0.09870          lung\n",
+              "1       13.610         24.69  ...                  0.07900         heart\n",
+              "2       12.270         17.92  ...                  0.06896          lung\n",
+              "3       11.340         18.61  ...                  0.06783         heart\n",
+              "4        9.683         19.34  ...                  0.07920         heart\n",
+              "\n",
+              "[5 rows x 31 columns]"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          },
+          "execution_count": 61
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "T2uwJB17u-6h",
+        "colab_type": "code",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 677
+        },
+        "outputId": "bae032a3-3d91-4108-e1ed-4e851d5f367a"
+      },
+      "source": [
+        "# check data for cleaning\n",
+        "df.info()"
+      ],
+      "execution_count": 62,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "<class 'pandas.core.frame.DataFrame'>\n",
+            "RangeIndex: 569 entries, 0 to 568\n",
+            "Data columns (total 31 columns):\n",
+            " #   Column                   Non-Null Count  Dtype  \n",
+            "---  ------                   --------------  -----  \n",
+            " 0   radius_mean              569 non-null    float64\n",
+            " 1   texture_mean             569 non-null    float64\n",
+            " 2   perimeter_mean           569 non-null    float64\n",
+            " 3   area_mean                569 non-null    float64\n",
+            " 4   smoothness_mean          569 non-null    float64\n",
+            " 5   compactness_mean         569 non-null    float64\n",
+            " 6   concavity_mean           569 non-null    float64\n",
+            " 7   concave points_mean      569 non-null    float64\n",
+            " 8   symmetry_mean            569 non-null    float64\n",
+            " 9   fractal_dimension_mean   569 non-null    float64\n",
+            " 10  radius_se                569 non-null    float64\n",
+            " 11  texture_se               569 non-null    float64\n",
+            " 12  perimeter_se             569 non-null    float64\n",
+            " 13  area_se                  569 non-null    float64\n",
+            " 14  smoothness_se            569 non-null    float64\n",
+            " 15  compactness_se           569 non-null    float64\n",
+            " 16  concavity_se             569 non-null    float64\n",
+            " 17  concave points_se        569 non-null    float64\n",
+            " 18  symmetry_se              569 non-null    float64\n",
+            " 19  fractal_dimension_se     569 non-null    float64\n",
+            " 20  radius_worst             569 non-null    float64\n",
+            " 21  texture_worst            569 non-null    float64\n",
+            " 22  perimeter_worst          569 non-null    float64\n",
+            " 23  area_worst               569 non-null    float64\n",
+            " 24  smoothness_worst         569 non-null    float64\n",
+            " 25  compactness_worst        569 non-null    float64\n",
+            " 26  concavity_worst          569 non-null    float64\n",
+            " 27  concave points_worst     569 non-null    float64\n",
+            " 28  symmetry_worst           569 non-null    float64\n",
+            " 29  fractal_dimension_worst  569 non-null    float64\n",
+            " 30  precondition             569 non-null    object \n",
+            "dtypes: float64(30), object(1)\n",
+            "memory usage: 137.9+ KB\n"
+          ],
+          "name": "stdout"
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "F0kZQuszvJKR",
+        "colab_type": "code",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 69
+        },
+        "outputId": "bec0a069-7536-4385-e0b4-8c002ef9c0e3"
+      },
+      "source": [
+        "# check distribution of diagnosis\n",
+        "labels.value_counts()"
+      ],
+      "execution_count": 63,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "B    357\n",
+              "M    212\n",
+              "Name: diagnosis, dtype: int64"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          },
+          "execution_count": 63
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "eAB_zUbEoycR",
+        "colab_type": "code",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 244
+        },
+        "outputId": "5a9733ef-e7b8-4e6e-cd26-e48cd5657ee0"
+      },
+      "source": [
+        "# one hot encoding of precondition\n",
+        "new_df = pd.get_dummies(df)\n",
+        "new_df.head()"
+      ],
+      "execution_count": 64,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/html": [
+              "<div>\n",
+              "<style scoped>\n",
+              "    .dataframe tbody tr th:only-of-type {\n",
+              "        vertical-align: middle;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe tbody tr th {\n",
+              "        vertical-align: top;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe thead th {\n",
+              "        text-align: right;\n",
+              "    }\n",
+              "</style>\n",
+              "<table border=\"1\" class=\"dataframe\">\n",
+              "  <thead>\n",
+              "    <tr style=\"text-align: right;\">\n",
+              "      <th></th>\n",
+              "      <th>radius_mean</th>\n",
+              "      <th>texture_mean</th>\n",
+              "      <th>perimeter_mean</th>\n",
+              "      <th>area_mean</th>\n",
+              "      <th>smoothness_mean</th>\n",
+              "      <th>compactness_mean</th>\n",
+              "      <th>concavity_mean</th>\n",
+              "      <th>concave points_mean</th>\n",
+              "      <th>symmetry_mean</th>\n",
+              "      <th>fractal_dimension_mean</th>\n",
+              "      <th>radius_se</th>\n",
+              "      <th>texture_se</th>\n",
+              "      <th>perimeter_se</th>\n",
+              "      <th>area_se</th>\n",
+              "      <th>smoothness_se</th>\n",
+              "      <th>compactness_se</th>\n",
+              "      <th>concavity_se</th>\n",
+              "      <th>concave points_se</th>\n",
+              "      <th>symmetry_se</th>\n",
+              "      <th>fractal_dimension_se</th>\n",
+              "      <th>radius_worst</th>\n",
+              "      <th>texture_worst</th>\n",
+              "      <th>perimeter_worst</th>\n",
+              "      <th>area_worst</th>\n",
+              "      <th>smoothness_worst</th>\n",
+              "      <th>compactness_worst</th>\n",
+              "      <th>concavity_worst</th>\n",
+              "      <th>concave points_worst</th>\n",
+              "      <th>symmetry_worst</th>\n",
+              "      <th>fractal_dimension_worst</th>\n",
+              "      <th>precondition_heart</th>\n",
+              "      <th>precondition_lung</th>\n",
+              "      <th>precondition_other</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>18.770</td>\n",
+              "      <td>21.43</td>\n",
+              "      <td>122.90</td>\n",
+              "      <td>1092.0</td>\n",
+              "      <td>0.09116</td>\n",
+              "      <td>0.14020</td>\n",
+              "      <td>0.10600</td>\n",
+              "      <td>0.060900</td>\n",
+              "      <td>0.1953</td>\n",
+              "      <td>0.06083</td>\n",
+              "      <td>0.6422</td>\n",
+              "      <td>1.530</td>\n",
+              "      <td>4.369</td>\n",
+              "      <td>88.25</td>\n",
+              "      <td>0.007548</td>\n",
+              "      <td>0.03897</td>\n",
+              "      <td>0.03914</td>\n",
+              "      <td>0.018160</td>\n",
+              "      <td>0.02168</td>\n",
+              "      <td>0.004445</td>\n",
+              "      <td>24.54</td>\n",
+              "      <td>34.37</td>\n",
+              "      <td>161.10</td>\n",
+              "      <td>1873.0</td>\n",
+              "      <td>0.1498</td>\n",
+              "      <td>0.48270</td>\n",
+              "      <td>0.4634</td>\n",
+              "      <td>0.20480</td>\n",
+              "      <td>0.3679</td>\n",
+              "      <td>0.09870</td>\n",
+              "      <td>0</td>\n",
+              "      <td>1</td>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>13.610</td>\n",
+              "      <td>24.69</td>\n",
+              "      <td>87.76</td>\n",
+              "      <td>572.6</td>\n",
+              "      <td>0.09258</td>\n",
+              "      <td>0.07862</td>\n",
+              "      <td>0.05285</td>\n",
+              "      <td>0.030850</td>\n",
+              "      <td>0.1761</td>\n",
+              "      <td>0.06130</td>\n",
+              "      <td>0.2310</td>\n",
+              "      <td>1.005</td>\n",
+              "      <td>1.752</td>\n",
+              "      <td>19.83</td>\n",
+              "      <td>0.004088</td>\n",
+              "      <td>0.01174</td>\n",
+              "      <td>0.01796</td>\n",
+              "      <td>0.006880</td>\n",
+              "      <td>0.01323</td>\n",
+              "      <td>0.001465</td>\n",
+              "      <td>16.89</td>\n",
+              "      <td>35.64</td>\n",
+              "      <td>113.20</td>\n",
+              "      <td>848.7</td>\n",
+              "      <td>0.1471</td>\n",
+              "      <td>0.28840</td>\n",
+              "      <td>0.3796</td>\n",
+              "      <td>0.13290</td>\n",
+              "      <td>0.3470</td>\n",
+              "      <td>0.07900</td>\n",
+              "      <td>1</td>\n",
+              "      <td>0</td>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>12.270</td>\n",
+              "      <td>17.92</td>\n",
+              "      <td>78.41</td>\n",
+              "      <td>466.1</td>\n",
+              "      <td>0.08685</td>\n",
+              "      <td>0.06526</td>\n",
+              "      <td>0.03211</td>\n",
+              "      <td>0.026530</td>\n",
+              "      <td>0.1966</td>\n",
+              "      <td>0.05597</td>\n",
+              "      <td>0.3342</td>\n",
+              "      <td>1.781</td>\n",
+              "      <td>2.079</td>\n",
+              "      <td>25.79</td>\n",
+              "      <td>0.005888</td>\n",
+              "      <td>0.02310</td>\n",
+              "      <td>0.02059</td>\n",
+              "      <td>0.010750</td>\n",
+              "      <td>0.02578</td>\n",
+              "      <td>0.002267</td>\n",
+              "      <td>14.10</td>\n",
+              "      <td>28.88</td>\n",
+              "      <td>89.00</td>\n",
+              "      <td>610.2</td>\n",
+              "      <td>0.1240</td>\n",
+              "      <td>0.17950</td>\n",
+              "      <td>0.1377</td>\n",
+              "      <td>0.09532</td>\n",
+              "      <td>0.3455</td>\n",
+              "      <td>0.06896</td>\n",
+              "      <td>0</td>\n",
+              "      <td>1</td>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>11.340</td>\n",
+              "      <td>18.61</td>\n",
+              "      <td>72.76</td>\n",
+              "      <td>391.2</td>\n",
+              "      <td>0.10490</td>\n",
+              "      <td>0.08499</td>\n",
+              "      <td>0.04302</td>\n",
+              "      <td>0.025940</td>\n",
+              "      <td>0.1927</td>\n",
+              "      <td>0.06211</td>\n",
+              "      <td>0.2430</td>\n",
+              "      <td>1.010</td>\n",
+              "      <td>1.491</td>\n",
+              "      <td>18.19</td>\n",
+              "      <td>0.008577</td>\n",
+              "      <td>0.01641</td>\n",
+              "      <td>0.02099</td>\n",
+              "      <td>0.011070</td>\n",
+              "      <td>0.02434</td>\n",
+              "      <td>0.001217</td>\n",
+              "      <td>12.47</td>\n",
+              "      <td>23.03</td>\n",
+              "      <td>79.15</td>\n",
+              "      <td>478.6</td>\n",
+              "      <td>0.1483</td>\n",
+              "      <td>0.15740</td>\n",
+              "      <td>0.1624</td>\n",
+              "      <td>0.08542</td>\n",
+              "      <td>0.3060</td>\n",
+              "      <td>0.06783</td>\n",
+              "      <td>1</td>\n",
+              "      <td>0</td>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>9.683</td>\n",
+              "      <td>19.34</td>\n",
+              "      <td>61.05</td>\n",
+              "      <td>285.7</td>\n",
+              "      <td>0.08491</td>\n",
+              "      <td>0.05030</td>\n",
+              "      <td>0.02337</td>\n",
+              "      <td>0.009615</td>\n",
+              "      <td>0.1580</td>\n",
+              "      <td>0.06235</td>\n",
+              "      <td>0.2957</td>\n",
+              "      <td>1.363</td>\n",
+              "      <td>2.054</td>\n",
+              "      <td>18.24</td>\n",
+              "      <td>0.007440</td>\n",
+              "      <td>0.01123</td>\n",
+              "      <td>0.02337</td>\n",
+              "      <td>0.009615</td>\n",
+              "      <td>0.02203</td>\n",
+              "      <td>0.004154</td>\n",
+              "      <td>10.93</td>\n",
+              "      <td>25.59</td>\n",
+              "      <td>69.10</td>\n",
+              "      <td>364.2</td>\n",
+              "      <td>0.1199</td>\n",
+              "      <td>0.09546</td>\n",
+              "      <td>0.0935</td>\n",
+              "      <td>0.03846</td>\n",
+              "      <td>0.2552</td>\n",
+              "      <td>0.07920</td>\n",
+              "      <td>1</td>\n",
+              "      <td>0</td>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>"
+            ],
+            "text/plain": [
+              "   radius_mean  texture_mean  ...  precondition_lung  precondition_other\n",
+              "0       18.770         21.43  ...                  1                   0\n",
+              "1       13.610         24.69  ...                  0                   0\n",
+              "2       12.270         17.92  ...                  1                   0\n",
+              "3       11.340         18.61  ...                  0                   0\n",
+              "4        9.683         19.34  ...                  0                   0\n",
+              "\n",
+              "[5 rows x 33 columns]"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          },
+          "execution_count": 64
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "N-X0sIoboFvh",
+        "colab_type": "code",
+        "colab": {}
+      },
+      "source": [
+        "# split train and test data\n",
+        "from sklearn.model_selection import train_test_split\n",
+        "X_train, X_test, y_train, y_test = train_test_split(new_df, labels, test_size=.33, random_state=42)"
+      ],
+      "execution_count": 0,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "UJbnHUt0oYe-",
+        "colab_type": "code",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 52
+        },
+        "outputId": "b0fde0ce-0b6b-4cdb-9d18-4dfcee742bfd"
+      },
+      "source": [
+        "from sklearn.ensemble import RandomForestClassifier\n",
+        "\n",
+        "# Random Forest Classifier\n",
+        "clf = RandomForestClassifier()\n",
+        "clf.fit(X_train, y_train)\n",
+        "\n",
+        "# Accuracy Scores\n",
+        "print(\"Train accuracy: \", round(clf.score(X_train, y_train), 4))\n",
+        "print(\"Test accuracy: \", round(clf.score(X_test, y_test), 4))"
+      ],
+      "execution_count": 66,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "Train accuracy:  1.0\n",
+            "Test accuracy:  0.9521\n"
+          ],
+          "name": "stdout"
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "aH7a0rNJqnKJ",
+        "colab_type": "code",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 347
+        },
+        "outputId": "9c2203fa-1010-4f9c-fa32-11d35aedaa71"
+      },
+      "source": [
+        "# Feature importance\n",
+        "feature_importance = pd.Series(clf.feature_importances_, index=new_df.columns).sort_values()\n",
+        "plt.figure(figsize=(10, 5))\n",
+        "feature_importance[-10:].plot(kind='barh')"
+      ],
+      "execution_count": 67,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "<matplotlib.axes._subplots.AxesSubplot at 0x7f16edc36208>"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          },
+          "execution_count": 67
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "image/png": "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\n",
+            "text/plain": [
+              "<Figure size 720x360 with 1 Axes>"
+            ]
+          },
+          "metadata": {
+            "tags": [],
+            "needs_background": "light"
+          }
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "osAt7Fpysr_k",
+        "colab_type": "code",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 330
+        },
+        "outputId": "6e49dbf6-6bf4-40e2-c703-f326416eaba2"
+      },
+      "source": [
+        "# training and testing accuracy depending on the number of trees\n",
+        "train_acc, test_acc = [], []\n",
+        "\n",
+        "for i in range(1, 21):\n",
+        "  clf = RandomForestClassifier(n_estimators=i)\n",
+        "  clf.fit(X_train, y_train)\n",
+        "  \n",
+        "  train_acc.append(round(clf.score(X_train, y_train), 4))\n",
+        "  test_acc.append(round(clf.score(X_test, y_test), 4))\n",
+        "\n",
+        "x_ax = [i for i in range(1, 21)]\n",
+        "plt.figure(figsize=(10, 5))\n",
+        "plt.plot(x_ax, train_acc, label=\"Train Accuracy\", color='blue')\n",
+        "plt.plot(x_ax, test_acc, label=\"Test Accuracy\", color='green')\n",
+        "plt.legend(loc='lower right')\n",
+        "plt.show()"
+      ],
+      "execution_count": 68,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "image/png": "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\n",
+            "text/plain": [
+              "<Figure size 720x360 with 1 Axes>"
+            ]
+          },
+          "metadata": {
+            "tags": [],
+            "needs_background": "light"
+          }
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "zkXypvtryYyi",
+        "colab_type": "code",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 52
+        },
+        "outputId": "4463376d-d264-4692-a78e-b45cd2f3b445"
+      },
+      "source": [
+        "# import Logistic Regression\n",
+        "from sklearn.linear_model import LogisticRegression\n",
+        "\n",
+        "clf2 = LogisticRegression(max_iter=10000, dual=False, solver='lbfgs')\n",
+        "clf2.fit(X_train, y_train)\n",
+        "\n",
+        "# Accuracy Scores\n",
+        "print(\"Train accuracy: \", round(clf2.score(X_train, y_train), 4))\n",
+        "print(\"Test accuracy: \", round(clf2.score(X_test, y_test), 4))"
+      ],
+      "execution_count": 76,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "Train accuracy:  0.9711\n",
+            "Test accuracy:  0.9574\n"
+          ],
+          "name": "stdout"
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "Rf9_cgNR0VZ4",
+        "colab_type": "code",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 347
+        },
+        "outputId": "edb0ca3a-5d4b-4dcd-8de2-d79f4d8811da"
+      },
+      "source": [
+        "# Feature importance\n",
+        "feature_importance = pd.Series(np.abs(clf.coef_[0]), index=new_df.columns).sort_values()\n",
+        "plt.figure(figsize=(10, 5))\n",
+        "feature_importance[-10:].plot(kind='barh')"
+      ],
+      "execution_count": 77,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "<matplotlib.axes._subplots.AxesSubplot at 0x7f16f09f4358>"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          },
+          "execution_count": 77
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "image/png": "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\n",
+            "text/plain": [
+              "<Figure size 720x360 with 1 Axes>"
+            ]
+          },
+          "metadata": {
+            "tags": [],
+            "needs_background": "light"
+          }
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "UNQtyEUp-jrf",
+        "colab_type": "text"
+      },
+      "source": [
+        "# Compare Machine Learning Algorithms Consistently\n",
+        "\n",
+        "The key to a fair comparison of machine learning algorithms is ensuring that each algorithm is evaluated in the same way on the same data.\n",
+        "\n",
+        "We can achieve this by forcing each algorithm to be evaluated on a consistent test harness.\n",
+        "\n",
+        "Different algorithms are compared below:\n",
+        "\n",
+        "    1. Logistic Regression\n",
+        "    2. Linear Discriminant Analysis\n",
+        "    3. K-Nearest Neighbors\n",
+        "    4. Classification and Regression Trees\n",
+        "    5. Naive Bayes\n",
+        "    6. Support Vector Machines\n",
+        "    7. Random Forest\n",
+        "\n",
+        "The 10-fold cross validation procedure is used to evaluate each algorithm, importantly configured with the same random seed to ensure that the same splits to the training data are performed and that each algorithms is evaluated in precisely the same way.\n",
+        "\n",
+        "Each algorithm is given a short name, useful for summarizing results afterward."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "GDwje3UG79PR",
+        "colab_type": "code",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 427
+        },
+        "outputId": "94ba891a-af3d-4fa7-ec48-156ace8aecef"
+      },
+      "source": [
+        "from sklearn import model_selection\n",
+        "from sklearn.tree import DecisionTreeClassifier\n",
+        "from sklearn.neighbors import KNeighborsClassifier\n",
+        "from sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n",
+        "from sklearn.naive_bayes import GaussianNB\n",
+        "from sklearn.svm import SVC\n",
+        "\n",
+        "# prepare configuration for cross validation test harness\n",
+        "seed = 42\n",
+        "kfold = model_selection.KFold(n_splits=10, random_state=seed, shuffle=True)\n",
+        "\n",
+        "# prepare models\n",
+        "models = []\n",
+        "models.append(('LR', LogisticRegression(max_iter=10000)))\n",
+        "models.append(('LDA', LinearDiscriminantAnalysis()))\n",
+        "models.append(('KNN', KNeighborsClassifier()))\n",
+        "models.append(('CART', DecisionTreeClassifier()))\n",
+        "models.append(('NB', GaussianNB()))\n",
+        "models.append(('SVM', SVC()))\n",
+        "models.append(('RF', RandomForestClassifier()))\n",
+        "\n",
+        "# evaluate each model in turn\n",
+        "results = []\n",
+        "names = []\n",
+        "scoring = 'accuracy'\n",
+        "for name, model in models:\n",
+        "\tcv_results = model_selection.cross_val_score(model, new_df, labels, cv=kfold, scoring=scoring)\n",
+        "\tresults.append(cv_results)\n",
+        "\tnames.append(name)\n",
+        "\tmsg = \"%s: %f (%f)\" % (name, cv_results.mean(), cv_results.std())\n",
+        "\tprint(msg)\n",
+        "\n",
+        "# boxplot algorithm comparison\n",
+        "fig = plt.figure()\n",
+        "fig.suptitle('Algorithm Comparison')\n",
+        "ax = fig.add_subplot(111)\n",
+        "plt.boxplot(results)\n",
+        "ax.set_xticklabels(names)\n",
+        "plt.show()"
+      ],
+      "execution_count": 82,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "LR: 0.950752 (0.020591)\n",
+            "LDA: 0.957832 (0.027389)\n",
+            "KNN: 0.929699 (0.020762)\n",
+            "CART: 0.931454 (0.026560)\n",
+            "NB: 0.933208 (0.038290)\n",
+            "SVM: 0.917419 (0.032351)\n",
+            "RF: 0.964850 (0.029357)\n"
+          ],
+          "name": "stdout"
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "image/png": "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\n",
+            "text/plain": [
+              "<Figure size 432x288 with 1 Axes>"
+            ]
+          },
+          "metadata": {
+            "tags": [],
+            "needs_background": "light"
+          }
+        }
+      ]
+    }
+  ]
+}
\ No newline at end of file
diff --git a/Cancer Cell Analysis with Machine Learning/titanic-machine-learning-from-disaster.ipynb b/Cancer Cell Analysis with Machine Learning/titanic-machine-learning-from-disaster.ipynb
new file mode 100644
index 0000000..9cc0617
--- /dev/null
+++ b/Cancer Cell Analysis with Machine Learning/titanic-machine-learning-from-disaster.ipynb	
@@ -0,0 +1 @@
+{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport matplotlib.pyplot as plt # plotting\nimport seaborn as sns # complex plotting\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":988,"outputs":[{"output_type":"stream","text":"/kaggle/input/titanic/train.csv\n/kaggle/input/titanic/gender_submission.csv\n/kaggle/input/titanic/test.csv\n","name":"stdout"}]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"# Load train data\ntrain_data = pd.read_csv(\"/kaggle/input/titanic/train.csv\")\ndisplay(train_data.head())\n\n# Load test data\ntest_data = pd.read_csv(\"/kaggle/input/titanic/test.csv\")\ndisplay(test_data.head())","execution_count":989,"outputs":[{"output_type":"display_data","data":{"text/plain":"   PassengerId  Survived  Pclass  \\\n0            1         0       3   \n1            2         1       1   \n2            3         1       3   \n3            4         1       1   \n4            5         0       3   \n\n                                                Name     Sex   Age  SibSp  \\\n0                            Braund, Mr. Owen Harris    male  22.0      1   \n1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n2                             Heikkinen, Miss. Laina  female  26.0      0   \n3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n4                           Allen, Mr. William Henry    male  35.0      0   \n\n   Parch            Ticket     Fare Cabin Embarked  \n0      0         A/5 21171   7.2500   NaN        S  \n1      0          PC 17599  71.2833   C85        C  \n2      0  STON/O2. 3101282   7.9250   NaN        S  \n3      0            113803  53.1000  C123        S  \n4      0            373450   8.0500   NaN        S  ","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>PassengerId</th>\n      <th>Survived</th>\n      <th>Pclass</th>\n      <th>Name</th>\n      <th>Sex</th>\n      <th>Age</th>\n      <th>SibSp</th>\n      <th>Parch</th>\n      <th>Ticket</th>\n      <th>Fare</th>\n      <th>Cabin</th>\n      <th>Embarked</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>0</td>\n      <td>3</td>\n      <td>Braund, Mr. Owen Harris</td>\n      <td>male</td>\n      <td>22.0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>A/5 21171</td>\n      <td>7.2500</td>\n      <td>NaN</td>\n      <td>S</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2</td>\n      <td>1</td>\n      <td>1</td>\n      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n      <td>female</td>\n      <td>38.0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>PC 17599</td>\n      <td>71.2833</td>\n      <td>C85</td>\n      <td>C</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>3</td>\n      <td>1</td>\n      <td>3</td>\n      <td>Heikkinen, Miss. Laina</td>\n      <td>female</td>\n      <td>26.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>STON/O2. 3101282</td>\n      <td>7.9250</td>\n      <td>NaN</td>\n      <td>S</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4</td>\n      <td>1</td>\n      <td>1</td>\n      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n      <td>female</td>\n      <td>35.0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>113803</td>\n      <td>53.1000</td>\n      <td>C123</td>\n      <td>S</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5</td>\n      <td>0</td>\n      <td>3</td>\n      <td>Allen, Mr. William Henry</td>\n      <td>male</td>\n      <td>35.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>373450</td>\n      <td>8.0500</td>\n      <td>NaN</td>\n      <td>S</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"   PassengerId  Pclass                                          Name     Sex  \\\n0          892       3                              Kelly, Mr. James    male   \n1          893       3              Wilkes, Mrs. James (Ellen Needs)  female   \n2          894       2                     Myles, Mr. Thomas Francis    male   \n3          895       3                              Wirz, Mr. Albert    male   \n4          896       3  Hirvonen, Mrs. Alexander (Helga E Lindqvist)  female   \n\n    Age  SibSp  Parch   Ticket     Fare Cabin Embarked  \n0  34.5      0      0   330911   7.8292   NaN        Q  \n1  47.0      1      0   363272   7.0000   NaN        S  \n2  62.0      0      0   240276   9.6875   NaN        Q  \n3  27.0      0      0   315154   8.6625   NaN        S  \n4  22.0      1      1  3101298  12.2875   NaN        S  ","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>PassengerId</th>\n      <th>Pclass</th>\n      <th>Name</th>\n      <th>Sex</th>\n      <th>Age</th>\n      <th>SibSp</th>\n      <th>Parch</th>\n      <th>Ticket</th>\n      <th>Fare</th>\n      <th>Cabin</th>\n      <th>Embarked</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>892</td>\n      <td>3</td>\n      <td>Kelly, Mr. James</td>\n      <td>male</td>\n      <td>34.5</td>\n      <td>0</td>\n      <td>0</td>\n      <td>330911</td>\n      <td>7.8292</td>\n      <td>NaN</td>\n      <td>Q</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>893</td>\n      <td>3</td>\n      <td>Wilkes, Mrs. James (Ellen Needs)</td>\n      <td>female</td>\n      <td>47.0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>363272</td>\n      <td>7.0000</td>\n      <td>NaN</td>\n      <td>S</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>894</td>\n      <td>2</td>\n      <td>Myles, Mr. Thomas Francis</td>\n      <td>male</td>\n      <td>62.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>240276</td>\n      <td>9.6875</td>\n      <td>NaN</td>\n      <td>Q</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>895</td>\n      <td>3</td>\n      <td>Wirz, Mr. Albert</td>\n      <td>male</td>\n      <td>27.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>315154</td>\n      <td>8.6625</td>\n      <td>NaN</td>\n      <td>S</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>896</td>\n      <td>3</td>\n      <td>Hirvonen, Mrs. Alexander (Helga E Lindqvist)</td>\n      <td>female</td>\n      <td>22.0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>3101298</td>\n      <td>12.2875</td>\n      <td>NaN</td>\n      <td>S</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Explore a pattern\ndef bar_chart(feature):\n    survived = train_data[train_data[\"Survived\"] == 1][feature].value_counts()\n    non_survived = train_data[train_data[\"Survived\"] == 0][feature].value_counts()\n    df = pd.DataFrame([survived, non_survived])\n    df.index = ['Survived', 'None']\n    df.plot(kind ='bar', stacked=True, figsize=(10, 5))","execution_count":990,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Problem Analysis\n# Explore a pattern\nwomen = train_data.loc[train_data.Sex == 'female'][\"Survived\"]\nrate_women = sum(women)/len(women)\nprint(\"% of women who survived:\", rate_women)\n\nmen = train_data.loc[train_data.Sex == 'male'][\"Survived\"]\nrate_men = sum(men)/len(men)\nprint(\"% of men who survived:\", rate_men)\n\nbar_chart('Sex')","execution_count":991,"outputs":[{"output_type":"stream","text":"% of women who survived: 0.7420382165605095\n% of men who survived: 0.18890814558058924\n","name":"stdout"},{"output_type":"display_data","data":{"text/plain":"<Figure size 720x360 with 1 Axes>","image/png":"iVBORw0KGgoAAAANSUhEUgAAAlYAAAFRCAYAAAC2SOM6AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjEsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+j8jraAAAdqklEQVR4nO3df3RU9Z3/8ddkkhRJgECYSVLIxoLxtBWxolZTq2uTJjEJrQFd24oURy2eytFv1GLxVxpsUetiNRx1zZjKQj3+aGMN4KBEQrui7da2aFNXrRslGJBMchImGAIkuZnvH26nxSRkgM9w74Tn46/Mzfx4X8xcn+feO3dc4XA4LAAAAByzBLsHAAAAGCsIKwAAAEMIKwAAAEMIKwAAAEMIKwAAAEMIKwAAAEMS7R5AkgYHB2VZXPUB0XG7Xfy9ADCObQuilZTkHvF3jggryworFOq1ewzEibS08fy9ADCObQui5fFMGPF3HAoEAAAwhLACAAAwhLACAAAwxBHnWA3Hsga0Z0+HBgb67B7FURITkzV5skdut2P/0wEAcMJy7P+d9+zp0Lhx45WSkimXy2X3OI4QDoe1b99e7dnToalTs+weBwAAfIpjDwUODPQpJWUiUfVPXC6XUlImshcPAACHcmxYSSKqhsG/CQAAzuXosHKCX/3qGS1YcJmWL78zJs//85/X6KmnfhGT5wYAAMeXY8+x+rTUiSfppM+YG3f/wQH17N0/6v2ef/5XWrlylT772WnGXhsAAIxNcRNWJ30mUScvCxh7vpb7ytQzyn3+/d/v0Ucf7dKyZTeroKBIu3bt1AcfvC/LGtDVVy/WBRdcpI0bN2jr1t/Ksga1ffv7+va3F6i/v1+bNm1UUlKyVq6s1sSJk7R+/fNav/559ff3a/r06brrrh9r3Lhxh7zerl079cADP1UotEfjxo3TD394p3JyTja2zgAAILY4FHgYS5ferqlTPVq1qkYHDhzQWWedo9ratVq1qkaPPLJK+/d/ssfrgw/eV1XVT+T3r5Hf/6jGjRun1auf0qxZp+ullz6JwX/916+ptnat1qx5Wjk5n9MLL9QPeb3771+hm25aqieeeFJLllTogQfuO67rCwAAjk3c7LGy2+uv/7deffW/9PTTT0qS+voOKhhskyTNmXO2xo9P0fjxKUpJSdX5518oSZox4xS9/36zpE/i6/HH/0M9PR9r//79+vKXzzvk+Xt7e/XXvzbprruWRZb19/PpPwDmpU9KVELySXaP4UiH+w64E9Vg3351dg/YPUbcIKyiFA6HtWLF/fqXfzn5kOVvv/2WkpKSIrcTEhKUlJQc+dmyPvljvOee5brnnpXKzT1VGzdu0Btv/PlTzz+oCRNS9Z//+VRsVwTACS8h+SSpapLdYyBOJFR1S/rY7jHiBocCo3TuuXmqq3tW4XBYkvTee+8e0eN7e/dp6tSpGhgYUEPDi0N+n5KSqqysadqyZbOkT0Luf//3vWMfHAAAHDfssYrSVVddo+rqB7Ro0bcVDoeVlfVZ3X//Q1E//tprv6/Fi69SRkamZs48Rb29vUPuU1n5Y61ceZ/WrPm5LGtABQVFys091eRqAACAGHKF/74Lxkb9/ZZCoUNDo61thzIzcyK37brcghN9+t/mRJOWNn7I3wuA6Hk8EzgUiOhVdaujg0OB/+xw5+LFzR6rnr37R708AgAAgJ04xwoAAMAQwgoAAMAQwgoAAMAQwgoAAMAQwgoAAMAQwipGtm37k269tcLuMQAAwHEUN5dbMP3dVnz3EQAAMC1uwsr0d1tF891Hu3d/pFtuuUGzZ39J//M/f9Upp5yq0tJv6IknarRnzx5VVv5YkrRq1c908OABfeYz43T77ZVDvk9w//79evDB+/XBB+/LsgZ09dWLdcEFFxlbFwAA4AwcChzFrl079W//9h2tWfOMduxo0csvv6RHH/25liz5f/rFL1YrJ+dkPfywX6tXP6VrrrlONTWPDHmOtWuf0FlnnaPa2rVatapGjzyySvv3x+dV3wEAwMjiZo+VXbKyPquZM0+RJH3uczN09tlflsvl0owZp2j37t3q6enRT35SpZ07P5TL5dLAwNDDi6+//t969dX/0tNPPylJ6us7qGCwTSef/LnjuCYAACDWCKtRJCUlRX5OSEiI3E5ISJBlDai29jHNmXO27r13pXbv/kg33HDdkOcIh8NaseL+IYcIAQDA2MKhwGPU09Mjj8cjSdq4ccOw9zn33DzV1T2rv3/f9XvvvXvc5gMAAMcPYXWMFiz4rh577BF9//tXa3BwcNj7XHXVNRoYGNCiRd/WwoWXq7b2seM8JQAAOB5c4b/vRjmM/Px8paSkKCEhQW63W7/+9a8VCoV00003adeuXZo2bZoeeughTZr0yaf2ampqVFdXp4SEBN1555264IILDvv8/f2WQqHeQ5a1te1QZmZO5DaXW/iHT//bnGjS0sYP+XsBED2PZ4LRT1ljjKvqVkfH4T9Ff6LxeCaM+Luoz7Fas2aNpkyZErnt9/uVl5enxYsXy+/3y+/3a+nSpWpublYgEFAgEFAwGJTP59OmTZvkdruPaSU+iSD+wwIAAOc66kOBjY2NKi8vlySVl5dr8+bNkeVlZWVKTk5Wdna2cnJy1NTUZGZaAAAAB4s6rK655hrNnz9fzz77rCSps7NTXq9XkuT1etXV1SVJCgaDyszMjDwuIyNDwWDQ5MwAAACOFNWhwKeffloZGRnq7OyUz+fTjBkzRrzvcKdsuVyuwz6/2+1SWtr4Q5a1tycoIcE16mNPNOFwWAkJCUP+vU4kbveJvf4AcLyxzY1eVGGVkZEhSUpPT1dhYaGampqUnp6u9vZ2eb1etbe3R86/yszMVFtbW+SxwWAwsmdrJJYVHnIyckJCovbuDSklZSJx9X/C4bD27durhITEE/rkbU5eB47N4U68BYbDNvdQx3Tyem9vrwYHB5Wamqre3l699tpruv7665Wfn6/6+notXrxY9fX1KigokPTJJwhvueUW+Xw+BYNBtbS0aPbs2Uc89OTJHu3Z06GentARP3YsS0xM1uTJHrvHAAAAwxg1rDo7O7VkyRJJkmVZmjt3ri688EKdfvrpqqioUF1dnbKyslRdXS1Jys3NVUlJiUpLS+V2u1VZWXlUnwh0uxM1dWrWET8OAADALlFdxyrWhruOFTASDgUCx4brWOGIcB2rIQ53KJArrwMAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABhCWAEAABgSdVhZlqXy8nJdd911kqRQKCSfz6eioiL5fD51d3dH7ltTU6PCwkIVFxdr69at5qcGAABwoKjDau3atZo5c2bktt/vV15enhoaGpSXlye/3y9Jam5uViAQUCAQUG1trZYvXy7LssxPDgAA4DBRhVVbW5t++9vf6rLLLossa2xsVHl5uSSpvLxcmzdvjiwvKytTcnKysrOzlZOTo6amphiMDgAA4CxRhdU999yjpUuXKiHhH3fv7OyU1+uVJHm9XnV1dUmSgsGgMjMzI/fLyMhQMBg0OTMAAIAjJY52h9/85jeaMmWKZs2apT/84Q+jPmE4HB6yzOVyHfYxbrdLaWnjR31uQJLc7gT+XgDgOGKbG71Rw2rbtm3asmWLXnnlFR08eFA9PT36wQ9+oPT0dLW3t8vr9aq9vV1TpkyRJGVmZqqtrS3y+GAwGNmzNRLLCisU6j3GVcGJIi1tPH8vwDHweCbYPQLiDNvcQx3uPTTqocBbbrlFr7zyirZs2aKf/exnOu+887Ry5Url5+ervr5eklRfX6+CggJJUn5+vgKBgPr6+tTa2qqWlhbNnj3b0KoAAAA416h7rEayePFiVVRUqK6uTllZWaqurpYk5ebmqqSkRKWlpXK73aqsrJTb7TY2MAAAgFO5wsOdFHWc9fdb7GZE1DgUCBwbj2eCVDXJ7jEQL6q61dHxsd1TOMoxHQoEAABAdAgrAAAAQwgrAAAAQwgrAAAAQwgrAAAAQwgrAAAAQwgrAAAAQwgrAAAAQwgrAAAAQwgrAAAAQwgrAAAAQwgrAAAAQwgrAAAAQwgrAAAAQwgrAAAAQwgrAAAAQwgrAAAAQwgrAAAAQwgrAAAAQwgrAAAAQwgrAAAAQwgrAAAAQwgrAAAAQxLtHgAjS5+UqITkk+wew5E8ngl2j+A4g3371dk9YPcYAHBCI6wcLCH5JKlqkt1jIE4kVHVL+tjuMQDghMahQAAAAEMIKwAAAEMIKwAAAEMIKwAAAEMIKwAAAEMIKwAAAEMIKwAAAEMIKwAAAEMIKwAAAEMIKwAAAEMIKwAAAEMIKwAAAEMIKwAAAEMIKwAAAENGDauDBw/qsssu0ze/+U2VlZVp1apVkqRQKCSfz6eioiL5fD51d3dHHlNTU6PCwkIVFxdr69atsZseAADAQUYNq+TkZK1Zs0br169XfX29tm7dqjfffFN+v195eXlqaGhQXl6e/H6/JKm5uVmBQECBQEC1tbVavny5LMuK+YoAAADYbdSwcrlcSklJkSQNDAxoYGBALpdLjY2NKi8vlySVl5dr8+bNkqTGxkaVlZUpOTlZ2dnZysnJUVNTUwxXAQAAwBkSo7mTZVmaP3++PvzwQ11xxRU644wz1NnZKa/XK0nyer3q6uqSJAWDQZ1xxhmRx2ZkZCgYDB72+d1ul9LSxh/tOgD4P7yPAMQC25boRRVWbrdb69at0969e7VkyRK99957I943HA4PWeZyuQ77/JYVVijUG80oJxSPZ4LdIyDO8D5CNNi24EixbTnU4d5DR/SpwIkTJ+rcc8/V1q1blZ6ervb2dklSe3u7pkyZIknKzMxUW1tb5DHBYDCyZwsAAGAsGzWsurq6tHfvXknSgQMH9Lvf/U4zZsxQfn6+6uvrJUn19fUqKCiQJOXn5ysQCKivr0+tra1qaWnR7NmzY7gKAAAAzjDqocD29nYtW7ZMlmUpHA7r4osv1te+9jV96UtfUkVFherq6pSVlaXq6mpJUm5urkpKSlRaWiq3263Kykq53e6YrwgAAIDdXOHhToo6zvr7LY7fDsPjmSBVTbJ7DMSLqm51dHxs9xSIA2xbcETYtgxh7BwrAAAAjIywAgAAMISwAgAAMISwAgAAMISwAgAAMISwAgAAMISwAgAAMISwAgAAMISwAgAAMISwAgAAMISwAgAAMISwAgAAMISwAgAAMISwAgAAMISwAgAAMISwAgAAMISwAgAAMISwAgAAMISwAgAAMISwAgAAMISwAgAAMISwAgAAMISwAgAAMISwAgAAMISwAgAAMISwAgAAMCTR7gEwsnD/Abmquu0eA3Ei3H/A7hEA4IRHWDmYK2mcTl4WsHsMxImW+8ok9ds9BgCc0DgUCAAAYAhhBQAAYAhhBQAAYAhhBQAAYAhhBQAAYAhhBQAAYAhhBQAAYAhhBQAAYAhhBQAAYAhhBQAAYMioYbV7924tXLhQJSUlKisr05o1ayRJoVBIPp9PRUVF8vl86u7+x3fa1dTUqLCwUMXFxdq6dWvspgcAAHCQUcPK7XZr2bJlevHFF/Xss8/qqaeeUnNzs/x+v/Ly8tTQ0KC8vDz5/X5JUnNzswKBgAKBgGpra7V8+XJZlhXzFQEAALDbqGHl9Xp12mmnSZJSU1M1Y8YMBYNBNTY2qry8XJJUXl6uzZs3S5IaGxtVVlam5ORkZWdnKycnR01NTTFcBQAAAGc4onOsdu7cqXfeeUdnnHGGOjs75fV6JX0SX11dXZKkYDCozMzMyGMyMjIUDAYNjgwAAOBMidHecd++fbrxxht1++23KzU1dcT7hcPhIctcLtdhn9vtdiktbXy0owAYAe8jALHAtiV6UYVVf3+/brzxRn3jG99QUVGRJCk9PV3t7e3yer1qb2/XlClTJEmZmZlqa2uLPDYYDEb2bI3EssIKhXqPdh3GLI9ngt0jIM7wPkI02LbgSLFtOdTh3kOjHgoMh8O64447NGPGDPl8vsjy/Px81dfXS5Lq6+tVUFAQWR4IBNTX16fW1la1tLRo9uzZx7oOAAAAjjfqHqs///nPWrdunU499VRdcsklkqSbb75ZixcvVkVFherq6pSVlaXq6mpJUm5urkpKSlRaWiq3263Kykq53e7YrgUAAIADuMLDnRR1nPX3W+xmHIbHM0EnLwvYPQbiRMt9Zero+NjuMRAHPJ4JUtUku8dAvKjqZtvyKcd0KBAAAADRIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMIawAAAAMGTWsbrvtNuXl5Wnu3LmRZaFQSD6fT0VFRfL5fOru7o78rqamRoWFhSouLtbWrVtjMzUAAIADjRpW8+fPV21t7SHL/H6/8vLy1NDQoLy8PPn9fklSc3OzAoGAAoGAamtrtXz5clmWFZvJAQAAHGbUsDrnnHM0adKkQ5Y1NjaqvLxcklReXq7NmzdHlpeVlSk5OVnZ2dnKyclRU1NTDMYGAABwnqM6x6qzs1Ner1eS5PV61dXVJUkKBoPKzMyM3C8jI0PBYNDAmAAAAM6XaPLJwuHwkGUul2vUx7ndLqWljTc5CnBC4n0EIBbYtkTvqMIqPT1d7e3t8nq9am9v15QpUyRJmZmZamtri9wvGAxG9mwdjmWFFQr1Hs0oY5rHM8HuERBneB8hGmxbcKTYthzqcO+hozoUmJ+fr/r6eklSfX29CgoKIssDgYD6+vrU2tqqlpYWzZ49+2heAgAAIO6Musfq5ptv1uuvv649e/bowgsv1A033KDFixeroqJCdXV1ysrKUnV1tSQpNzdXJSUlKi0tldvtVmVlpdxud8xXAgAAwAlc4eFOjDrO+vstdjMOw+OZoJOXBeweA3Gi5b4ydXR8bPcYiAMezwSpatLodwQkqaqbbcunGD8UCAAAgKEIKwAAAEMIKwAAAEMIKwAAAEOMXiAUAOB84f4DclV12z0G4kS4/4DdI8QVwgoATjCupHF84hhRa7mvTFK/3WPEDQ4FAgAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGEJYAQAAGBKzsHrllVdUXFyswsJC+f3+WL0MAACAY8QkrCzL0t13363a2loFAgG98MILam5ujsVLAQAAOEZMwqqpqUk5OTnKzs5WcnKyysrK1NjYGIuXAgAAcIyYhFUwGFRmZmbkdkZGhoLBYCxeCgAAwDESY/Gk4XB4yDKXyzXi/ZOS3PJ4JsRilLjXcl+Z3SMgjvA+QrTYtuBIsG2JXkz2WGVmZqqtrS1yOxgMyuv1xuKlAAAAHCMmYXX66aerpaVFra2t6uvrUyAQUH5+fixeCgAAwDFicigwMTFRlZWVuvbaa2VZli699FLl5ubG4qUAAAAcwxUe7oQoAAAAHDGuvA4AAGAIYQUAAGAIYQUAAGAIYQUAAGAIYQUAOKH96U9/0nPPPSdJ6urqUmtrq80TIZ7F5HILgAlnnnnmYa/Yv23btuM4DYCx6OGHH9Zbb72l7du369JLL1V/f7+WLl2qZ555xu7REKcIKzjWG2+8IUmqrq7W1KlTdckll0iS1q9fr3379tk5GoAx4uWXX1Z9fb3mzZsn6ZPvtmX7gmPBoUA43quvvqoFCxYoNTVVqampuuKKK9TQ0GD3WADGgKSkJLlcrsje8d7eXpsnQrwjrOB4brdb69evl2VZGhwc1Pr16+V2u+0eC8AYUFJSosrKSu3du1e//OUv5fP5dPnll9s9FuIYV16H4+3cuVMrVqzQtm3b5HK5NGfOHN1+++2aPn263aMBGANee+01vfrqq5Kkr371qzr//PNtngjxjLACAAAwhEOBcLzt27dr0aJFmjt3riTp3Xff1aOPPmrzVADGgoaGBhUVFemss87SnDlzdOaZZ2rOnDl2j4U4xh4rON6VV16pW2+9VZWVlaqvr5ckzZ07Vy+88ILNkwGId4WFhXrsscc0c+ZMu0fBGMEeKzje/v37NXv27EOWcfI6ABPS09OJKhjFdazgeJMnT9aHH34Y+Tj0Sy+9JI/HY/NUAMaCWbNmqaKiQl//+teVnJwcWV5UVGTjVIhnHAqE47W2tuquu+7SG2+8oYkTJ2r69OlauXKlpk2bZvdoAOLcbbfdNuzye++99zhPgrGCsILjWZYlt9ut3t5eDQ4OKjU11e6RAAAYFudYwfEKCgp011136S9/+YtSUlLsHgfAGNLW1qYlS5YoLy9PX/nKV3TDDTeora3N7rEQx9hjBcc7cOCAtmzZoo0bN+rtt9/WRRddpNLSUp199tl2jwYgzvl8Ps2dO/eQ7yLdsGGDVq9ebfNkiFeEFeJKd3e3VqxYoQ0bNuidd96xexwAce6SSy7RunXrRl0GRItDgYgLr7/+uqqqqjRv3jwdPHhQDz30kN0jARgDJk+erHXr1smyLFmWpXXr1iktLc3usRDH2GMFx8vPz9cXvvAFlZSUKD8/X+PHj7d7JABjxEcffaS7775bb775plwul84880zdcccdfOoYR42wguP19PTwSUAAQFzgAqFwrMcff1zf+9739OCDD0YuDvrP7rzzThumAjAWPPzwwyP+zuVyacmSJcdxGowlhBUc6+9fMzFr1iybJwEw1gx3SkFvb6+ee+45hUIhwgpHjUOBcLy3335bX/ziF+0eA8AY1dPTo7Vr16qurk4lJSW6+uqrlZ6ebvdYiFOEFRxv4cKF6ujo0MUXX6yysjLl5ubaPRKAMSAUCmn16tXasGGD5s2bp+9+97uaNGmS3WMhzhFWiAsdHR168cUXtXHjRu3bt08lJSW6/vrr7R4LQJz66U9/qpdfflmXX365FixYwLc6wBjCCnHlb3/7m2pra/Xiiy/qrbfesnscAHHq85//vJKTk+V2uw/5cEw4HJbL5dK2bdtsnA7xjLCC473//vvauHGjNm3apLS0NJWWlqq4uJhzIAAAjkNYwfEuv/xylZWV6eKLL1ZGRobd4wAAMCIutwBHsyxL2dnZWrRokd2jAAAwKr4rEI7mdrsVCoXU19dn9ygAAIyKPVZwvGnTpuk73/nOkO8J9Pl8Nk4FAMBQhBUcz+v1yuv1KhwOa9++fXaPAwDAiDh5HQAAwBD2WMHxFi5cOOyXMK9du9aGaQAAGBlhBcf74Q9/GPn54MGDamhokNvttnEiAACGx6FAxKUrr7xSTz75pN1jAABwCPZYwfFCoVDk58HBQb311lvq6OiwcSIAAIZHWMHx5s+fHznHKjExUdOmTdOKFStsngoAgKEIKzhWU1OTsrKytGXLFknS888/r02bNmn69Ok65ZRTbJ4OAIChuPI6HOtHP/qRkpKSJEl//OMf9cADD2jevHlKTU1VZWWlzdMBADAUYQXHsixLaWlpkqSNGzfqW9/6loqLi1VRUaEdO3bYPB0AAEMRVnCswcFBDQwMSJJ+//vf67zzzov8zrIsu8YCAGBEnGMFxyorK9OVV16pyZMna9y4cTr77LMlSTt27FBqaqrN0wEAMBTXsYKjvfnmm+ro6ND5558f+QLm7du3q7e3V6eddprN0wEAcCjCCgAAwBDOsQIAADCEsAIAADCEsAIAADCEsAIAADCEsAIAADDk/wPUc/GmzazmGwAAAABJRU5ErkJggg==\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Explore a pattern\nyoung = train_data.loc[train_data.Age < 40][\"Survived\"]\nrate_young = sum(young)/len(young)\nprint(\"% of young who survived:\", rate_young)\n\nold = train_data.loc[train_data.Age >= 40][\"Survived\"]\nrate_old = sum(old)/len(old)\nprint(\"% of old who survived:\", rate_old)","execution_count":992,"outputs":[{"output_type":"stream","text":"% of young who survived: 0.41560798548094374\n% of old who survived: 0.37423312883435583\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Explore a pattern\npc1 = train_data.loc[train_data.Pclass == 1][\"Survived\"]\nrate_pc1 = sum(pc1)/len(pc1)\nprint(\"% of Pclass 1 who survived:\", rate_pc1)\n\npc2 = train_data.loc[train_data.Pclass == 2][\"Survived\"]\nrate_pc2 = sum(pc2)/len(pc2)\nprint(\"% of Pclass 2 who survived:\", rate_pc2)\n\npc3 = train_data.loc[train_data.Pclass == 3][\"Survived\"]\nrate_pc3 = sum(pc3)/len(pc3)\nprint(\"% of Pclass 3 who survived:\", rate_pc3)\n\nbar_chart('Pclass')","execution_count":993,"outputs":[{"output_type":"stream","text":"% of Pclass 1 who survived: 0.6296296296296297\n% of Pclass 2 who survived: 0.47282608695652173\n% of Pclass 3 who survived: 0.24236252545824846\n","name":"stdout"},{"output_type":"display_data","data":{"text/plain":"<Figure size 720x360 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Explore a pattern\nfare = train_data.loc[train_data.Fare > 76][\"Survived\"]\nrate_fare = sum(fare)/len(fare)\nprint(\"% of fare who survived:\", rate_fare)\n\nbar_chart('SibSp')","execution_count":994,"outputs":[{"output_type":"stream","text":"% of fare who survived: 0.7604166666666666\n","name":"stdout"},{"output_type":"display_data","data":{"text/plain":"<Figure size 720x360 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"bar_chart('Parch')","execution_count":995,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 720x360 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"bar_chart('Embarked')","execution_count":996,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 720x360 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Data Integration\n# Inspect data to find inconsistency\ntrain_data.info()\n\nsns.heatmap(train_data.isnull(), yticklabels=False, cbar=False, cmap='viridis')","execution_count":997,"outputs":[{"output_type":"stream","text":"<class 'pandas.core.frame.DataFrame'>\nRangeIndex: 891 entries, 0 to 890\nData columns (total 12 columns):\n #   Column       Non-Null Count  Dtype  \n---  ------       --------------  -----  \n 0   PassengerId  891 non-null    int64  \n 1   Survived     891 non-null    int64  \n 2   Pclass       891 non-null    int64  \n 3   Name         891 non-null    object \n 4   Sex          891 non-null    object \n 5   Age          714 non-null    float64\n 6   SibSp        891 non-null    int64  \n 7   Parch        891 non-null    int64  \n 8   Ticket       891 non-null    object \n 9   Fare         891 non-null    float64\n 10  Cabin        204 non-null    object \n 11  Embarked     889 non-null    object \ndtypes: float64(2), int64(5), object(5)\nmemory usage: 83.7+ KB\n","name":"stdout"},{"output_type":"execute_result","execution_count":997,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fd5192f7f90>"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 432x288 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Inspect test data to find inconsistency\ntest_data.info()\n\nsns.heatmap(test_data.isnull(), yticklabels=False, cbar=False, cmap='viridis')","execution_count":998,"outputs":[{"output_type":"stream","text":"<class 'pandas.core.frame.DataFrame'>\nRangeIndex: 418 entries, 0 to 417\nData columns (total 11 columns):\n #   Column       Non-Null Count  Dtype  \n---  ------       --------------  -----  \n 0   PassengerId  418 non-null    int64  \n 1   Pclass       418 non-null    int64  \n 2   Name         418 non-null    object \n 3   Sex          418 non-null    object \n 4   Age          332 non-null    float64\n 5   SibSp        418 non-null    int64  \n 6   Parch        418 non-null    int64  \n 7   Ticket       418 non-null    object \n 8   Fare         417 non-null    float64\n 9   Cabin        91 non-null     object \n 10  Embarked     418 non-null    object \ndtypes: float64(2), int64(4), object(5)\nmemory usage: 36.0+ KB\n","name":"stdout"},{"output_type":"execute_result","execution_count":998,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fd5192ce190>"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 432x288 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Feature Engineering\n\n# Get name prefix\ndef get_titles(data):\n    return data.apply(lambda x: x.split(',')[1].split('.')[0].strip())\n\n# update data (we no longer need full name)\ntrain_data['Title'] = get_titles(train_data['Name'])\ntest_data['Title'] = get_titles(test_data['Name'])\n\n# check\ntrain_data.head()","execution_count":999,"outputs":[{"output_type":"execute_result","execution_count":999,"data":{"text/plain":"   PassengerId  Survived  Pclass  \\\n0            1         0       3   \n1            2         1       1   \n2            3         1       3   \n3            4         1       1   \n4            5         0       3   \n\n                                                Name     Sex   Age  SibSp  \\\n0                            Braund, Mr. Owen Harris    male  22.0      1   \n1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n2                             Heikkinen, Miss. Laina  female  26.0      0   \n3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n4                           Allen, Mr. William Henry    male  35.0      0   \n\n   Parch            Ticket     Fare Cabin Embarked Title  \n0      0         A/5 21171   7.2500   NaN        S    Mr  \n1      0          PC 17599  71.2833   C85        C   Mrs  \n2      0  STON/O2. 3101282   7.9250   NaN        S  Miss  \n3      0            113803  53.1000  C123        S   Mrs  \n4      0            373450   8.0500   NaN        S    Mr  ","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>PassengerId</th>\n      <th>Survived</th>\n      <th>Pclass</th>\n      <th>Name</th>\n      <th>Sex</th>\n      <th>Age</th>\n      <th>SibSp</th>\n      <th>Parch</th>\n      <th>Ticket</th>\n      <th>Fare</th>\n      <th>Cabin</th>\n      <th>Embarked</th>\n      <th>Title</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>0</td>\n      <td>3</td>\n      <td>Braund, Mr. Owen Harris</td>\n      <td>male</td>\n      <td>22.0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>A/5 21171</td>\n      <td>7.2500</td>\n      <td>NaN</td>\n      <td>S</td>\n      <td>Mr</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2</td>\n      <td>1</td>\n      <td>1</td>\n      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n      <td>female</td>\n      <td>38.0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>PC 17599</td>\n      <td>71.2833</td>\n      <td>C85</td>\n      <td>C</td>\n      <td>Mrs</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>3</td>\n      <td>1</td>\n      <td>3</td>\n      <td>Heikkinen, Miss. Laina</td>\n      <td>female</td>\n      <td>26.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>STON/O2. 3101282</td>\n      <td>7.9250</td>\n      <td>NaN</td>\n      <td>S</td>\n      <td>Miss</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4</td>\n      <td>1</td>\n      <td>1</td>\n      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n      <td>female</td>\n      <td>35.0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>113803</td>\n      <td>53.1000</td>\n      <td>C123</td>\n      <td>S</td>\n      <td>Mrs</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5</td>\n      <td>0</td>\n      <td>3</td>\n      <td>Allen, Mr. William Henry</td>\n      <td>male</td>\n      <td>35.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>373450</td>\n      <td>8.0500</td>\n      <td>NaN</td>\n      <td>S</td>\n      <td>Mr</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Preprocessing & Feature Engineering\n\n# check unique name prefix from data for feature encoding\ndisplay(train_data['Title'].unique())\ndisplay(test_data['Title'].unique())\n\nbar_chart('Title')","execution_count":1000,"outputs":[{"output_type":"display_data","data":{"text/plain":"array(['Mr', 'Mrs', 'Miss', 'Master', 'Don', 'Rev', 'Dr', 'Mme', 'Ms',\n       'Major', 'Lady', 'Sir', 'Mlle', 'Col', 'Capt', 'the Countess',\n       'Jonkheer'], dtype=object)"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"array(['Mr', 'Mrs', 'Miss', 'Master', 'Ms', 'Col', 'Rev', 'Dr', 'Dona'],\n      dtype=object)"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 720x360 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Preprocessing & Feature Engineering\n# Ordinal encoding: create name prefix dictionary based on value\n# children gets most importance: Mr: 0, Miss: 1, Mrs: 2, Others: 0\nprefix_dict = {\n    'Mr': 0,\n    'Mrs': 2, \n    'Miss': 1,\n    'Master': 3,\n    'Don': 3,\n    'Rev': 3,\n    'Dr': 3,\n    'Mme': 3,\n    'Ms': 3,\n    'Major': 3,\n    'Lady': 3,\n    'Sir': 3,\n    'Mlle': 3,\n    'Col': 3, \n    'Capt': 3,\n    'the Countess': 3,\n    'Jonkheer': 3,\n    'Dona': 3 \n}\n\n# replace data\ntrain_data['Title'] = train_data['Title'].map(prefix_dict)\ntest_data['Title'] = test_data['Title'].map(prefix_dict)\n\ntrain_data.head()","execution_count":1001,"outputs":[{"output_type":"execute_result","execution_count":1001,"data":{"text/plain":"   PassengerId  Survived  Pclass  \\\n0            1         0       3   \n1            2         1       1   \n2            3         1       3   \n3            4         1       1   \n4            5         0       3   \n\n                                                Name     Sex   Age  SibSp  \\\n0                            Braund, Mr. Owen Harris    male  22.0      1   \n1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n2                             Heikkinen, Miss. Laina  female  26.0      0   \n3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n4                           Allen, Mr. William Henry    male  35.0      0   \n\n   Parch            Ticket     Fare Cabin Embarked  Title  \n0      0         A/5 21171   7.2500   NaN        S      0  \n1      0          PC 17599  71.2833   C85        C      2  \n2      0  STON/O2. 3101282   7.9250   NaN        S      1  \n3      0            113803  53.1000  C123        S      2  \n4      0            373450   8.0500   NaN        S      0  ","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>PassengerId</th>\n      <th>Survived</th>\n      <th>Pclass</th>\n      <th>Name</th>\n      <th>Sex</th>\n      <th>Age</th>\n      <th>SibSp</th>\n      <th>Parch</th>\n      <th>Ticket</th>\n      <th>Fare</th>\n      <th>Cabin</th>\n      <th>Embarked</th>\n      <th>Title</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>0</td>\n      <td>3</td>\n      <td>Braund, Mr. Owen Harris</td>\n      <td>male</td>\n      <td>22.0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>A/5 21171</td>\n      <td>7.2500</td>\n      <td>NaN</td>\n      <td>S</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2</td>\n      <td>1</td>\n      <td>1</td>\n      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n      <td>female</td>\n      <td>38.0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>PC 17599</td>\n      <td>71.2833</td>\n      <td>C85</td>\n      <td>C</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>3</td>\n      <td>1</td>\n      <td>3</td>\n      <td>Heikkinen, Miss. Laina</td>\n      <td>female</td>\n      <td>26.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>STON/O2. 3101282</td>\n      <td>7.9250</td>\n      <td>NaN</td>\n      <td>S</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4</td>\n      <td>1</td>\n      <td>1</td>\n      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n      <td>female</td>\n      <td>35.0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>113803</td>\n      <td>53.1000</td>\n      <td>C123</td>\n      <td>S</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5</td>\n      <td>0</td>\n      <td>3</td>\n      <td>Allen, Mr. William Henry</td>\n      <td>male</td>\n      <td>35.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>373450</td>\n      <td>8.0500</td>\n      <td>NaN</td>\n      <td>S</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"bar_chart('Title')","execution_count":1002,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 720x360 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.drop(['Name'], axis=1, inplace=True)\ntest_data.drop(['Name'], axis=1, inplace=True)","execution_count":1003,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Preprocessing & Feature Engineering\n# Label Encoding\nfrom sklearn.preprocessing import LabelEncoder\nle_train_data = LabelEncoder()\nle_test_data = LabelEncoder()\ntrain_data[\"Sex\"] = le_train_data.fit_transform(train_data[\"Sex\"])\ntest_data[\"Sex\"] = le_test_data.fit_transform(test_data[\"Sex\"])\n\ntrain_data.head()","execution_count":1004,"outputs":[{"output_type":"execute_result","execution_count":1004,"data":{"text/plain":"   PassengerId  Survived  Pclass  Sex   Age  SibSp  Parch            Ticket  \\\n0            1         0       3    1  22.0      1      0         A/5 21171   \n1            2         1       1    0  38.0      1      0          PC 17599   \n2            3         1       3    0  26.0      0      0  STON/O2. 3101282   \n3            4         1       1    0  35.0      1      0            113803   \n4            5         0       3    1  35.0      0      0            373450   \n\n      Fare Cabin Embarked  Title  \n0   7.2500   NaN        S      0  \n1  71.2833   C85        C      2  \n2   7.9250   NaN        S      1  \n3  53.1000  C123        S      2  \n4   8.0500   NaN        S      0  ","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>PassengerId</th>\n      <th>Survived</th>\n      <th>Pclass</th>\n      <th>Sex</th>\n      <th>Age</th>\n      <th>SibSp</th>\n      <th>Parch</th>\n      <th>Ticket</th>\n      <th>Fare</th>\n      <th>Cabin</th>\n      <th>Embarked</th>\n      <th>Title</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>0</td>\n      <td>3</td>\n      <td>1</td>\n      <td>22.0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>A/5 21171</td>\n      <td>7.2500</td>\n      <td>NaN</td>\n      <td>S</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>38.0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>PC 17599</td>\n      <td>71.2833</td>\n      <td>C85</td>\n      <td>C</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>3</td>\n      <td>1</td>\n      <td>3</td>\n      <td>0</td>\n      <td>26.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>STON/O2. 3101282</td>\n      <td>7.9250</td>\n      <td>NaN</td>\n      <td>S</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>35.0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>113803</td>\n      <td>53.1000</td>\n      <td>C123</td>\n      <td>S</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5</td>\n      <td>0</td>\n      <td>3</td>\n      <td>1</td>\n      <td>35.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>373450</td>\n      <td>8.0500</td>\n      <td>NaN</td>\n      <td>S</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Age data\nplt.figure(figsize=(12, 7))\nsns.boxplot(x='Title',y='Age',data=train_data, palette='winter')","execution_count":1005,"outputs":[{"output_type":"execute_result","execution_count":1005,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fd519308d90>"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 864x504 with 1 Axes>","image/png":"iVBORw0KGgoAAAANSUhEUgAAAs0AAAGpCAYAAAB2wgtQAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjEsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+j8jraAAAgAElEQVR4nO3df5BddWE3/vf+IK1LINldskkaA7qgU4faOK0Osw4VyJIfGpSt0EoUbFN91hHbSKJpF6hV52uVPnR4oE47dadTCTBNqynPRkmNIasEBxj8UZXRahWWmJiRLOwPeJIAye7e7x8pKYHQE0PunrvZ1+uvnJPdc95799yz7/u5n3tOXaVSqQQAAHhJ9WUHAACAWqc0AwBAAaUZAAAKKM0AAFBAaQYAgAKNZQc4FhMTExkfd5EPAACq65RTGo66fkqU5vHxSkZH95cdAwCAk9ycOacddb3pGQAAUEBpBgCAAkozAAAUUJoBAKCA0gwAAAWUZgAAKKA0AwBAAaUZAAAKKM0AAFBAaQYAgAJKMwAAFFCaAQCgQFVL86233poVK1bkkksuydq1a/Pss89mdHQ0q1atytKlS7Nq1ao8+eST1YzACwwPD6WnZ01GRobLjgIAMGVUrTTv2bMnt912W/71X/81d911V8bHx7N58+b09vamo6MjW7duTUdHR3p7e6sVgaPYsOGO/PCHP8iGDXeUHQUAYMqo6kjz+Ph4nnnmmYyNjeWZZ55JW1tb+vv709XVlSTp6urKtm3bqhmB5xkeHkp//1dTqVSybdsWo80AAMeoaqV57ty5+aM/+qNcdNFFOf/88zNz5sycf/75GRoaSltbW5Kkra0tw8OK22TZsOGOTExMJEkmJiaMNgMAHKPGam34ySefTH9/f/r7+3Paaaflwx/+cDZt2nRc22poqMvs2U0nOOH0s3371zI2NpYkGRsbyz339Oe663pKTgUAUPuqVprvv//+vPKVr0xLS0uSZOnSpfnud7+b1tbWDA4Opq2tLYODg4f//38yPl7J6Oj+akWdNi64YHHuvvsrGRsbS2NjYy68sNPjCgDwPHPmnHbU9VWbnvFrv/Zr+f73v5+nn346lUolDzzwQM4+++wsXrw4fX19SZK+vr50dnZWKwIvsHLllamvP/Qrr6+vz8qVV5acCABgaqjaSPOiRYuybNmy/O7v/m4aGxvzute9Lu9617uyb9++XHPNNdm4cWPmz5+fW265pVoReIGWltZ0di7Lli135eKLl6e5uXiUHwCApK5SqVTKDlHk4MFx0whOkOHhofzv//2p/NmffUxpBgB4gZeanqE0AwDAf5n0Oc0AAHCyUJoBAKCA0gwAAAWUZgAAKKA0AwBAAaUZAAAKKM0AAFBAaQYAgAJKMwAAFFCaAQCggNIMAAAFlGYAACigNAMAQAGlGQAACijNAABQQGkGAIACSvM0Mzw8lJ6eNRkZGS47CgDAlKE0TzMbNtyRH/7wB9mw4Y6yowAATBlK8zQyPDyU/v6vplKpZNu2LUabAQCOkdI8jWzYcEcmJiaSJBMTE0abAQCOkdI8jWzf3p+xsbEkydjYWO65Z1vJiQAApgaleRq54ILONDY2JkkaGxtz4YUXl5wIAGBqUJqnkZUrr0x9/aFfeX19fVauvLLkRAAAU4PSPI20tLSms3NZ6urqcvHFy9Pc3FJ2JACAKaGx7ABMrpUrr8yuXTuMMgMA/BLqKpVKpewQRQ4eHM/o6P6yYwAAcJKbM+e0o643PQMAAAoozQAAUEBpBgCAAkrzNDMw8HB+//ffkUcfHSg7CgDAlKE0TzM33viZ7N+/Pzfe+OmyowAATBlK8zQyMPBwdu36WZJk584dRpsBAI6R0jyN3HjjZ16wbLQZAOBYKM3TyHOjzM/ZuXNHOUEAAKaYqt0RcGBgIGvWrDm8vGvXrqxevTpdXV1Zs2ZNdu/enQULFuTmm2/OrFmzqhWD5zn11JnZt2/v4eWZM2eWmAYAYOqo2khze3t7Nm3alE2bNuXOO+/MK17xiixZsiS9vb3p6OjI1q1b09HRkd7e3mpF4AXGxg4esXzw4MGX+EoAAJ6vaiPNz/fAAw9k4cKFWbBgQfr7+3P77bcnSbq6unLVVVdl3bp1kxFj2mtrm3fEFI25c+eXmAYApq7+/q25++4tZcfI6OhIkmT27OZScyxZsjydnUtLzVBtk1KaN2/enEsuuSRJMjQ0lLa2tiRJW1tbhoeHC7+/oaEus2c3VTXjdPDEE4NHLD/++B6PKwAch6amX0ljY0PZMTIycqg0n3HGGaXmaGr6lZO+U1S9NB84cCBf+9rX8pGPfOS4tzE+Xsno6P4TmGp6uvDCi7Nly12pVCqpq6vLRRct8bgCwHHo6LggHR0XlB0jPT1rkySf+tSNJSfJSdMp5sw57ajrq371jHvvvTfnnnvu4VdAra2tGRw8NOI5ODiYlpaWakfgv6xceWUaGw+9TmpsPCUrV15ZciIAgKmh6qV58+bNWbFixeHlxYsXp6+vL0nS19eXzs7Oakfgv7S0tObii5enrq4uS5YsT3OzFywAAMeiqqX56aefzv3335+lS/97Ynh3d3fuu+++LF26NPfdd1+6u7urGYEXWLnyypx77m8YZQYA+CXUVSqVStkhihw8OH7SzJMBADhRnpvTfMMNN5Wc5ORR2pxmAACY6pRmAAAooDQDAEABpRkAAAoozQAAUEBpBgCAAkozAAAUUJqnmeHhofT0rMnIyHDZUQAApgyleZrZsOGO/PCHP8iGDXeUHQUAYMpQmqeR4eGh9Pd/NZVKJdu2bTHaDABwjJTmaWTDhjsyMTGRJJmYmDDaDABwjJTmaWT79v6MjY0lScbGxnLPPdtKTgQAMDUozdPIBRd0pq6uLklSV1eXCy+8uOREAABTg9I8jaxceWUqlUqSpFKpZOXKK0tOBAAwNSjN08jPfrbjiOWdO39WThAAgClGaZ5Gbrjh/zti+TOf+WRJSQAAphaleRrZt2/vEct79+59ia8EAOD5lOZp5NRTZx6xPHPmzJf4SgAAnk9pnkb+4A/+6IjlP/zD/1VSEgCAqUVpnka+/OVNRyx/6Uv/t6QkAABTi9I8jezadeTVMnbu3FFOEDiK4eGh9PSscXt3AGqS0jyNLFx41hHLZ575qnKCwFFs2HBHfvjDH7i9OwA1SWmeRtatu/YFy9eVlASONDw8lP7+r6ZSqWTbti1GmwGoOY1lB2DytLefk4ULz8quXT/LmWe+Kq9+dXvZkSDJoVHmiYmJJMnExEQ2bLgjV1+9uuRU1IL+/q25++4tpWYYHR1Jksye3VxqjiRZsmR5OjuXlh0DpiUjzdPMunXXpqmpySgzNWX79v6MjY0lScbGxnLPPdtKTgT/bXh4OMPD3v2A6c5I8zTT3n5OvvCFL5UdA45wwQWdufvur2RsbCyNjY258MKLy45EjejsXFr6yGpPz9okyQ033FRqDqBcRpqB0q1ceWXq6w+djurr67Ny5ZUlJwKAIynNQOlaWlrT2bksdXV1ufji5Wlubik7EgAcwfSMSVILH2ZJaucDLT7MwgutXHlldu3aYZQZgJqkNE8zz32YpezSDC/U0tKaG274P2XHAICjUponSS18mCXxgRYAgONhTjMAABRQmgEAoIDSDAAABapamp966qmsXr06y5cvz1vf+tZ897vfzejoaFatWpWlS5dm1apVefLJJ6sZAQAAXraqlua//Mu/zO/8zu9ky5Yt2bRpU84+++z09vamo6MjW7duTUdHR3p7e6sZAQAAXraqlea9e/fmW9/6Vi6//PIkyYwZM3L66aenv78/XV1dSZKurq5s27atWhEAAOCEqNol53bt2pWWlpZce+21+fGPf5xzzz03119/fYaGhtLW1pYkaWtrO3zdYAAAqFVVK81jY2P5j//4j3zsYx/LokWL8qlPfeq4p2I0NNRl9uymE5xwempsbEgSjyfAMXLepJY5PidP1UrzvHnzMm/evCxatChJsnz58vT29qa1tTWDg4Npa2vL4OBgWlpaCrc1Pl7J6Oj+akWdVsbGxpPE4wlwjJw3qWWOzxNvzpzTjrq+anOa58yZk3nz5mVgYCBJ8sADD+Tss8/O4sWL09fXlyTp6+tLZ2dntSIAAMAJUdXbaH/sYx/LRz/60Rw8eDALFy7MZz7zmUxMTOSaa67Jxo0bM3/+/Nxyyy3VjAAAAC9bVUvz6173utx5550vWr9+/fpq7haYggYGHk5Pz9r81V/dnFe/ur3sOABwBHcEBGrCjTd+Jvv378+NN3667CgA8CJKM1C6gYGHs2vXz5IkO3fuyKOPDpScCACOpDQDpbvxxs+8YNloMwC1RWkGSvfcKPNzdu7cUU4QAHgJSjNQuoULzzpi+cwzX1VOEAB4CUozULp16659wfJ1JSUBgKNTmoHStbefc3i0+cwzX+WScwDUHKUZqAnr1l2bpqYmo8wA1KSq3twE4Fi1t5+TL3zhS2XHAICjMtIMAAAFlGYAACigNAMAQAGlGQAACijNAABQQGkGAIACSjMAABRQmgEAoIDSDNSE4eGh9PSsycjIcNlRAOBFlGagJmzYcEd++MMfZMOGO8qOAgAvojQDpRseHkp//1dTqVSybdsWo80A1BylGSjdhg13ZGJiIkkyMTFhtBmAmqM0A6Xbvr0/Y2NjSZKxsbHcc8+2khMBwJGUZqB0F1zQmcbGxiRJY2NjLrzw4pITAcCRlGagdCtXXpn6+kOno/r6+qxceWXJiQDgSEozULqWltZ0di5LXV1dLr54eZqbW8qOBABHaCw7AEByaLR5164dRpkBqElKM1ATWlpac8MN/6fsGABwVKZnAABAAaUZAAAKKM0AAFBAaQYAgAJKMwAAFFCaAQCggNIMAAAFlGYAAChQ1ZubLF68OKeeemrq6+vT0NCQO++8M6Ojo1mzZk12796dBQsW5Oabb86sWbOqGQMAAF6Wqo80r1+/Pps2bcqdd96ZJOnt7U1HR0e2bt2ajo6O9Pb2VjsCAAC8LJN+G+3+/v7cfvvtSZKurq5cddVVWbdu3WTHAJ6nv39r7r57S6kZRkdHkiSzZzeXmiNJlixZns7OpWXHAKCGVL00v+9970tdXV3e9a535V3veleGhobS1taWJGlra8vw8HDhNhoa6jJ7dlO1o04LjY0NSeLx5AhNTb9y+Ngoy8jIodJ8xhlnlJojOfR4eI7wHOdNapnjc/JUtTRv2LAhc+fOzdDQUFatWpX29vbj2s74eCWjo/tPcLrpaWxsPEk8nhyho+OCdHRcUGqGnp61SZJPferGUnM8x3OE5zhvUsscnyfenDmnHXV9Vec0z507N0nS2tqaJUuW5KGHHkpra2sGBweTJIODg2lpaalmBAAAeNmqVpr379+fvXv3Hv73fffdl9e85jVZvHhx+vr6kiR9fX3p7OysVgQAADghqjY9Y2hoKB/60IeSJOPj47nkkkvylre8Ja9//etzzTXXZOPGjZk/f35uueWWakUAAIATomqleeHChfnSl770ovXNzc1Zv359tXYLAAAnnDsCAgBAAaUZAAAKKM0AAFBAaQYAgAJKMwAAFFCaAQCggNIMAAAFlGYAACigNAMAQAGlGQAACijNAABQQGkGAIACSjMAABRQmgEAoIDSDAAABZRmAAAooDQDAEABpRkAAAoozQAAUKCx7AAA1J7e3r/LwMDDZceoCQMDjyRJenrWlpykNrS3n5Pu7qvLjgGTTmkG4EUGBh7OQ//54xyY1Vp2lNLV1x/6U/ntxx4vOUn5Zjw5VHYEKI3SDMBRHZjVmscueHvZMagh87Z/uewIUBpzmgEAoIDSDAAABZRmAAAooDQDAEABpRkAAAoozQAAUEBpBgCAAkozAAAUKCzNTzzxRK677rq8//3vT5I8/PDD+eIXv1j1YAAAUCsKS3NPT0/OP//8DA4OJkle9apX5bbbbqt6MAAAqBWFpXlkZCRve9vbUl9/6EsbGxsP/xsAAKaDwvbb1NSUkZGR1NXVJUm+973v5bTTTqt6MAAAqBWNRV/Q09OTD37wg9m5c2euuOKKjIyM5JZbbjnmHYyPj+eyyy7L3Llz87nPfS6jo6NZs2ZNdu/enQULFuTmm2/OrFmzXtYPAQAA1VRYms8999zccccdefTRR1OpVPLqV786p5xyyjHv4LbbbsvZZ5+dvXv3Jkl6e3vT0dGR7u7u9Pb2pre3N+vWrTv+nwAAAKqscHrG1q1b87WvfS2PPvpoduzYka9//et54IEHMjQ0VLjxxx57LPfcc08uv/zyw+v6+/vT1dWVJOnq6sq2bdteRnwAAKi+wpHmjRs35nvf+17OO++8JMk3v/nNLFq0KDt27MjVV199uAAfzac//emsW7cu+/btO7xuaGgobW1tSZK2trYMDw8XhmxoqMvs2U2FX0exxsaGJPF4UnMcm7Xlud8HvFBjY4PnaQ1x7pw8haW5vr4+//Zv/5YzzjgjyaHrNn/iE5/IF77whVx55ZUvWZq//vWvp6WlJb/xG7+RBx988GWFHB+vZHR0/8vaBoeMjY0niceTmuPYrC3P/T7ghcbGxj1Pa4hz54k3Z87RL3hRWJp37959uDAnSWtra3bs2JHZs2ensfGlv/3f//3f87WvfS333ntvnn322ezduzcf/ehH09ramsHBwbS1tWVwcDAtLS3H8eMAANNVb+/fZWDg4bJj1ISBgUeSJD09a0tOUhva289Jd/fVVdl2YWn+7d/+7XzgAx/I8uXLkyRf/epX88Y3vjH79+//Hy8995GPfCQf+chHkiQPPvhg/vEf/zF//dd/nb/6q79KX19furu709fXl87OzhP0owAA08HAwMN56Kc/yoF5s8uOUrr6Vxz6eNq3/98vSk5SvhmPjVZ1+4Wl+eMf/3i2bt2a73znO0mS3/zN38zjjz+epqam3H777b/0Dru7u3PNNddk48aNmT9//i91+brj5RXpf/OK9EjVfEUKQPUcmDc7j7/3orJjUEPm3Pb1qm6/sDTX1dXlzDPPzPe///1s2bIlCxYsyLJly36pnZx33nmHP0jY3Nyc9evXH1/a4zQw8HAe+sFPc7BhwaTutxbVT5yaJPnOj8x9OmV8d9kRAIAp4iVL86OPPprNmzdn8+bNmT17dt72trelUqkc1+hyLTjYsCDDTR8uOwY1pGV/9d/lAABODi9Zmt/61rfmjW98Y/7+7/8+Z511VpLk1ltvnaxcAABQM17y5iaf/exnc8YZZ+S9731v/vzP/zwPPPBAKpXKZGYDAICa8JIjzUuWLMmSJUuyf//+bNu2LbfeemuGhoby8Y9/PEuWLMn5558/mTkBAKA0hbfRbmpqyjve8Y587nOfy/bt2/O6170uvb29k5ENAABqQuHVM55v9uzZueKKK3LFFVdUKw8AANScwpFmAACY7pRmAAAooDQDAEABpRkAAAoozQAAUEBpBgCAAkozAAAUUJoBAKCA0gwAAAV+qTsCAjA9jIyMZMboUOZt/3LZUaghM0aHMvIrqgPTk5FmAAAo4OUiAC/S3NycR54dy2MXvL3sKNSQedu/nObm5rJjQCmMNAMAQAGlGQAACijNAABQQGkGAIACSjMAABRQmgEAoIDSDAAABZRmAAAooDQDAEABpRkAAAoozQAAUEBpBgCAAkozAAAUUJoBAKCA0gwAAAWUZgAAKKA0AwBAgcZqbfjZZ5/Ne97znhw4cCDj4+NZtmxZVq9endHR0axZsya7d+/OggULcvPNN2fWrFnVigEAAC9b1UaaZ8yYkfXr1+dLX/pS+vr68o1vfCPf+9730tvbm46OjmzdujUdHR3p7e2tVgQAADghqjbSXFdXl1NPPTVJMjY2lrGxsdTV1aW/vz+33357kqSrqytXXXVV1q1bV60YSZKRkZGcMv54WvbfUtX9MLWcMv7zjIzMKTVDb+/fZWDg4VIz1IqBgUeSJD09a0tOUhva289Jd/fVZccA4L9UrTQnyfj4eN75zndm586defe7351FixZlaGgobW1tSZK2trYMDw8XbqehoS6zZzcdd46Ghrrj/l5Obi/32Hq5du58NA/9x3/mwCvmlZahVtSP/WqS5NuPPllykvLNePqxNDY2lHpsNjY2lLZvalvZx+ZzGeBoqnl8VrU0NzQ0ZNOmTXnqqafyoQ99KD/5yU+Oazvj45WMju4/7hynnz47BxtmZLjpw8e9DU4+LftvyemnN72sY+vlGhsbz4FXzMvjr3lvaRmoPXN+elvGxsZLPzbhaMo+Np/LAEdzIo7POXNOO+r6Sbl6xumnn57zzjsv3/jGN9La2prBwcEkyeDgYFpaWiYjAgAAHLeqlebh4eE89dRTSZJnnnkm999/f9rb27N48eL09fUlSfr6+tLZ2VmtCAAAcEJUbXrG4OBgenp6Mj4+nkqlkuXLl+eiiy7KG97whlxzzTXZuHFj5s+fn1tu8eE8AABqW9VK86//+q8fHlF+vubm5qxfv75auwUAgBPOHQEBAKCA0gwAAAWUZgAAKFDV6zQDMHXNeHIo87Z/uewYpat/5tA1Xyd+tdwbetSCGU8OJfPKvZMqlEVpBuBF2tvPKTtCzXjuFu/tymIyb45jg2lLaQbgRbq7ry47Qs3o6VmbJLnhhptKTgKUyZxmAAAooDQDAEABpRkAAAoozQAAUEBpBgCAAkozAAAUUJoBAKCA0gwAAAWUZgAAKKA0AwBAAaUZAAAKKM0AAFBAaQYAgAJKMwAAFFCaAQCggNIMAAAFlGYAACjQWHaAyXLK+O607L+l7Bilq594KkkyUX96yUnKd8r47iSvKTsGADAFTIvS3N5+TtkRasbAwC+SJO3t80pOUgte49gAAI7JtCjN3d1Xlx2hZvT0rE2S3HDDTSUnAQCYOsxpBgCAAkozAAAUUJoBAKCA0gwAAAWUZgAAKKA0AwBAgWlxyTmoVSMjI5nx9GDm/PS2sqNQQ2Y8/VhGRibKjgHA8xhpBgCAAlUbaf7FL36RP/3TP80TTzyR+vr6/P7v/37+4A/+IKOjo1mzZk12796dBQsW5Oabb86sWbOqFQNqWnNzcx4Zrc/jr3lv2VGoIXN+eluam50XAWpJ1UaaGxoa0tPTk6985Sv5l3/5l/zTP/1THn744fT29qajoyNbt25NR0dHent7qxUBAABOiKqV5ra2tpx77rlJkpkzZ6a9vT179uxJf39/urq6kiRdXV3Ztm1btSIAAMAJMSkfBPz5z3+eH/3oR1m0aFGGhobS1taW5FCxHh4eLvz+hoa6zJ7dVO2Y00JjY0OSeDxrxHO/D3ihxsYGz9Ma4bxZe5w7eSnVPHdWvTTv27cvq1evznXXXZeZM2ce1zbGxysZHd1/gpNNT2Nj40ni8awRz/0+4IXGxsY9T2uE82btce7kpZyIc+ecOacddX1Vr55x8ODBrF69Om9/+9uzdOnSJElra2sGBweTJIODg2lpaalmBAAAeNmqVporlUquv/76tLe3Z9WqVYfXL168OH19fUmSvr6+dHZ2VisCAACcEFWbnvGd73wnmzZtymtf+9pceumlSZK1a9emu7s711xzTTZu3Jj58+fnlltuqVYEAAA4IapWmt/4xjfmP//zP4/6f+vXr6/WbgEA4IRzR0AAACigNAMAQAGlGQAACijNAABQQGkGAIACSjMAABRQmgEAoIDSDAAABZRmAAAooDQDAEABpRkAAAoozQAAUEBpBgCAAkozAAAUUJoBAKCA0gwAAAWUZgAAKKA0AwBAAaUZAAAKNJYdAKa7GU8/ljk/va3sGKWrP7g3STJxysySk5RvxtOPJZlVdoya0N+/NXffvaXUDAMDjyRJenrWlpojSZYsWZ7OzqVlx4BpSWmGErW3n1N2hJoxMPBEkqT91QtKTlILZjk2akhLS0vZEYAaoDRDibq7ry47Qs14bhTvhhtuKjkJtaSzc6mRVaAmmNMMAAAFlGYAACigNAMAQAGlGQAACijNAABQQGkGAIACSjMAABRQmgEAoIDSDAAABZRmAAAooDQDAECBxrIDTBf9/Vtz991byo6RgYFHkiQ9PWtLzbFkyfJ0di4tNQMAwLFSmqeZlpaWsiMAAEw5VSvN1157be655560trbmrrvuSpKMjo5mzZo12b17dxYsWJCbb745s2bNqlaEmtLZudTIKgDAFFW1Oc3vfOc78w//8A9HrOvt7U1HR0e2bt2ajo6O9Pb2Vmv3AABwwlStNL/pTW960Shyf39/urq6kiRdXV3Ztm1btXYPAAAnzKTOaR4aGkpbW1uSpK2tLcPDw8f0fQ0NdZk9u6ma0YCSNTY2JInnOlDoufMFvFBjY0PV/o5MiQ8Cjo9XMjq6v+wYQBWNjY0niec6UOi58wW80NjY+Mv+OzJnzmlHXT+p12lubW3N4OBgkmRwcNCVHAAAmBImdaR58eLF6evrS3d3d/r6+tLZ2TmZuwcATgIjIyOZ8cRo5tz29bKjUENmPDaakbFfrdr2qzbSvHbt2lxxxRV59NFH85a3vCVf/OIX093dnfvuuy9Lly7Nfffdl+7u7mrtHgAATpiqjTTfdNNNR12/fv36au0SAJgGmpub80jjM3n8vReVHYUaMue2r6f5tOaqbX9S5zQDAMBUpDQDAEABpRkAAAoozQAAUEBpBgCAAkozAAAUUJoBAKCA0gwAAAWUZgAAKKA0AwBAAaUZAAAKKM0AAFBAaQYAgAJKMwAAFFCaAQCggNIMAAAFlGYAACigNAMAQAGlGQAACijNAABQQGkGAIACSjMAABRQmgEAoEBj2QEAAH5ZMx4bzZzbvl52jNLV730mSTIx81dLTlK+GY+NJqfNr9r2lWYAYEppbz+n7Ag1Y+DxR5Ik7fOrVxanjNPmV/XYUJoBgCmlu/vqsiPUjJ6etUmSG264qeQkJz9zmgEAoIDSDAAABZRmAAAooDQDAEABpRkAAAoozQAAUEBpBgCAAq7TDKS/f2vuvntLqRkGBg5doP+5a46WacmS5ensXFp2DABqSCkjzffee2+WLVuWJUuWpLe3t4wIQI1paWlJS0tL2TEA4KjqKpVKZTJ3OD4+nmXLluXzn/985s6dm2E4AWQAAAWsSURBVMsvvzw33XRTzjnnpW97ePDgeEZH909iSgCAl1YL79Al//0uXXv72aXmOJneoZsz57Sjrp/0keaHHnooZ511VhYuXJgZM2ZkxYoV6e/vn+wYAABTnnfpJs+kz2nes2dP5s2bd3h57ty5eeihh/7H72loqMvs2U3VjgYAcEwuu6wrl13WVXYMJtGkl+ajzQapq6v7H79nfLxiegYAAFVXM9Mz5s2bl8cee+zw8p49e9LW1jbZMQAA4JhNeml+/etfnx07dmTXrl05cOBANm/enMWLF092DAAAOGaTPj2jsbExf/EXf5H3v//9GR8fz2WXXZbXvOY1kx0DAACO2aRfcu54uOQcAACToWbmNAMAwFSjNAMAQAGlGQAACijNAABQQGkGAIACSjMAABRQmgEAoIDSDAAABZRmAAAooDQDAECBKXEbbQAAKJORZgAAKKA0AwBAAaUZAAAKKM0AAFBAaQYAgAJKMwAAFFCaAQCggNI8jdx7771ZtmxZlixZkt7e3rLjwGHXXnttOjo6cskll5QdBY7wi1/8IldddVXe+ta3ZsWKFVm/fn3ZkSBJ8uyzz+byyy/PO97xjqxYsSJ/8zd/U3akk56bm0wT4+PjWbZsWT7/+c9n7ty5ufzyy3PTTTflnHPOKTsa5Fvf+laampryZ3/2Z7nrrrvKjgOHDQ4O5vHHH8+5556bvXv35rLLLsvf/u3fOndSukqlkv379+fUU0/NwYMH8+53vzvXX3993vCGN5Qd7aRlpHmaeOihh3LWWWdl4cKFmTFjRlasWJH+/v6yY0GS5E1velNmzZpVdgx4kba2tpx77rlJkpkzZ6a9vT179uwpORUkdXV1OfXUU5MkY2NjGRsbS11dXcmpTm5K8zSxZ8+ezJs37/Dy3LlznfgBfgk///nP86Mf/SiLFi0qOwokOfQu8qWXXpo3v/nNefOb3+zYrDKleZo42iwcr0gBjs2+ffuyevXqXHfddZk5c2bZcSBJ0tDQkE2bNmX79u156KGH8pOf/KTsSCc1pXmamDdvXh577LHDy3v27ElbW1uJiQCmhoMHD2b16tV5+9vfnqVLl5YdB17k9NNPz3nnnZdvfOMbZUc5qSnN08TrX//67NixI7t27cqBAweyefPmLF68uOxYADWtUqnk+uuvT3t7e1atWlV2HDhseHg4Tz31VJLkmWeeyf3335/29vaSU53cXD1jGtm+fXs+/elPZ3x8PJdddlk++MEPlh0JkiRr167NN7/5zYyMjKS1tTV/8id/kt/7vd8rOxbk29/+dt7znvfkta99berrD40zrV27NhdccEHJyZjufvzjH6enpyfj4+OpVCpZvnx5/viP/7jsWCc1pRkAAAqYngEAAAWUZgAAKKA0AwBAAaUZAAAKKM0AAFCgsewAABy7kZGR/OEf/mGS5Iknnkh9fX1aWlqyc+fOXHrppfnEJz6RBx98MKecckp+67d+K0ny2c9+Nk1NTXnf+95XYnKAqU1pBphCmpubs2nTpiQvXYa/+c1vpqmp6XBpBuDlMz0D4CTw4IMP5gMf+EB+/vOf55//+Z9z66235tJLL823v/3tI75u586ded/73pd3vvOdefe7351HHnmkpMQAU4uRZoCTyCtf+cpcccUVR4xAP/DAA4f//2Mf+1g++clP5lWvelW+//3v55Of/GRuu+22suICTBlKM8A0sW/fvnz3u9/Nhz/84cPrDhw4UGIigKlDaQaYJiqVSk4//fTDc6IBOHbmNAOcZE499dTs27fvRetnzpyZV77ylfnKV76S5FCJ/vGPfzzZ8QCmJKUZ4CRz0UUX5e677z7qBwFvvPHGbNy4Me94xzuyYsWKbNu2raSUAFNLXaVSqZQdAgAAapmRZgAAKKA0AwBAAaUZAAAKKM0AAFBAaQYAgAJKMwAAFFCaAQCgwP8P1sqEaNclhioAAAAASUVORK5CYII=\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Preprocessing\n# Impute age columns based on median from passenger class\ntrain_data['Age'].fillna(train_data.groupby('Title')['Age'].transform('median'), inplace=True)\ntest_data['Age'].fillna(train_data.groupby('Title')['Age'].transform('median'), inplace=True)","execution_count":1006,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.set_style('darkgrid')\nfacet = sns.FacetGrid(train_data, hue='Survived', aspect=4)\nfacet.map(sns.kdeplot, 'Age', shade=True)\nfacet.set(xlim=(0, train_data['Age'].max()))\nfacet.add_legend()\n\nplt.show()","execution_count":1007,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 915.875x216 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"facet = sns.FacetGrid(train_data, hue='Survived', aspect=4)\nfacet.map(sns.kdeplot, 'Age', shade=True)\nfacet.set(xlim=(0, train_data['Age'].max()))\nfacet.add_legend()\nplt.xlim(0, 20)","execution_count":1008,"outputs":[{"output_type":"execute_result","execution_count":1008,"data":{"text/plain":"(0.0, 20.0)"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 915.875x216 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"facet = sns.FacetGrid(train_data, hue='Survived', aspect=4)\nfacet.map(sns.kdeplot, 'Age', shade=True)\nfacet.set(xlim=(0, train_data['Age'].max()))\nfacet.add_legend()\nplt.xlim(20, 30)","execution_count":1009,"outputs":[{"output_type":"execute_result","execution_count":1009,"data":{"text/plain":"(20.0, 30.0)"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 915.875x216 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"facet = sns.FacetGrid(train_data, hue='Survived', aspect=4)\nfacet.map(sns.kdeplot, 'Age', shade=True)\nfacet.set(xlim=(0, train_data['Age'].max()))\nfacet.add_legend()\nplt.xlim(30, 40)","execution_count":1010,"outputs":[{"output_type":"execute_result","execution_count":1010,"data":{"text/plain":"(30.0, 40.0)"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 915.875x216 with 1 Axes>","image/png":"iVBORw0KGgoAAAANSUhEUgAAA5AAAADRCAYAAAC6oF1wAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjEsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+j8jraAAAgAElEQVR4nOzde5Bc5X3n//dz+t493XOfHo00ktAFMCAQBgK+LErGkbFRHFRcUoXjVH6uZamtTQWvMXbssMtibCmOY7tSm9+WjUMWx5BoE2IDCTJrLQNI/tlcFhsk7hJIA7rNRZpLT89Md0/3Ob8/zumbZqQZCY16pPm8qrq6zznPOfM0Ppbmo+/zPMc4juMgIiIiIiIiMgOr1h0QERERERGRs4MCpIiIiIiIiMyKAqSIiIiIiIjMigKkiIiIiIiIzIoCpIiIiIiIiMyKAqSIiIiIiIjMin82jXbs2MGmTZuwbZtbbrmF22+/veq44zhs2rSJ7du3Ew6H+da3vsXFF18MQFdXF7FYDMuy8Pl8/PSnPz3930JERERERETm3IwBslAocN999/Hggw+STCa5+eab6erqYtWqVaU2O3bsoKenh23btrFz507uvfdeHnnkkdLxv//7v6epqWnWnSoUbAYHx07yq4icXnV1IdLpbK27IQuc7kOZL3Qvynyg+1Dmi9bWeK27UDMzDmHdtWsXy5Yto7Ozk2AwyIYNG+ju7q5q093dzcaNGzHGsHbtWlKpFP39/afcKWPMKZ8rcrr4/b5ad0FE96HMG7oXZT7QfShSezMGyL6+Ptrb20vbyWSSvr6+E7Zpb2+vavPv//2/58Ybb+Sf/umfTkefRUREREREpAZmHMLqOM6UfcdWCE/UZsuWLSSTSY4ePcrnP/95VqxYwVVXXXXCn2kMNDREZ+qayJzy+Szdh1Jzug9lvtC9KPOB7kOR2psxQLa3t9Pb21va7uvro62t7YRtent7S22SySQAzc3NrF+/nl27ds0YIB0HhofHZ/8tROZAQ0NU96HUnO5DmS90L8p8oPtQ5gvNgTyBNWvW0NPTw/79+8nlcmzdupWurq6qNl1dXTz22GM4jsMrr7xCPB6nra2N8fFx0uk0AOPj4/zyl79k9erVc/NNREREREREZE7NWIH0+/3cc8893HbbbRQKBW666SZWr17Nli1bALj11ltZt24d27dvZ/369UQiETZv3gzA0aNH+ZM/+RPAXc31937v97j22mtn7NTwRI6fvdFH0GfRGA3QFA3SFA2QCPu1wI6IiIiIiEiNGGe6CYw1tuvAML////5yyn6fZWiMBGiOuYGyKRqkKRYofS6GzeZogIZIAL9vxgKryHFpmIzMB7oPZb7QvSjzge5DmS8W8hDWGSuQtdDZGOEb119ALm+TyuZJZ/OMZgukM3lS2TypTJ7e0Sy7B8YYmZgkb0+fgevD/lLIbI4FaYy4nxsjXtCMBWiMBmiOBgkHtCy0iIiIiIjIiczLAOn3WbTWhQBYPENbx3HITLpBczSTZzRbfqW9sJnK5Dk4kmFkIs/EZGHa60QCPpqiXtCsqGQ2VlQ3m70wGg9pKK2IiIiIiCw88zJAngxjDJGgj0jQRzIemrH9ZMFm1KtkFgNnscKZykwyms3z7pExXsmMkMrkma626beMGygrhtIWA6YbOMvzNhuiQfyWwqaIiIiIiJz9zvoAebICPoumWJCmWHDGtrbtkM7lS4GzGDSLwTOVyXM4leXt/uMPpTVAfcRPYzRYPXcz6g2ljQXpqA+zrDFCQHM2RURERERkHltwAfJkWJYhEQ6QCAc+0FDa4vbIxCQHhiemHUrrswxLGyOsbImxojnqvWJ0NoS1GJCIiIiIiMwLCpCnyckOpc3lbdLZPCOZPEfGshxOZTmUyvLqoRTdbw+Uhs76LcPypigrW6Kc54XKFc1RljRE8GlorIiIiIiInEEKkDUS9Fs0+d2htOc1R6uO5fI2vaMZDqey9KayHBrJ8JsDI/z8rYHy+T7DsqYoq1pirGiJcl5TjJUtUTrqw1ha4EdEREREROaAAuQ8FPRbLG2MsrSxOlhmJgv0jmbpTbnh8nAqy4vvD/Pkm/2lNiG/VapUrmwpD4VtT4QULEVERERE5ANRgDyLhAM+ljdFWd5UHSwnJgscTmXo9ULl4VSG53sG+dkbfaU2kYDFec0xVjZHWdFSHgqbjIf0SBIREREREZkVBchzQCTg8wJhrGr/eK7AoVKwzHA4leEXewf5t9fLwTIW9LlVyorFe1a2xGiJBRUsRURERESkigLkOSwa9LGqJcaqlupgmc7mS5XK3lSWQ6kMz+w5wuOv5ktt4iF/VaWyGDKbowEFSxERERGRBUoBcgGqC/lZ3epndWt1sBzN5DmUytA36i7ccyiV4f+83U86W37kSH3Y7z1qJMZ5zdHSPMvG6MzP1RQRERERkbObAqSUxMN+LgjXcUFbXWmf4zikMnm3WjnqPW5kJMPP3uxjPFcOlo2RgBsmS0Nh3ff6SKAWX0VEREREROaAAqSckDGG+kiA+kiAC5Px0n7HcRieqAyWGQ6NZPi313qZmLRL7ZpjAVY2x1jZEuOi9jiXdiRYlNDCPSIiIiIiZyMFSDklxhgaowEaowEuaq8OlkPjk+7iPV7F8vBIhp2HUmz5zUEAWmJBLlucYM2iBJd2JLigrY6g36rVVxERERERkVlSgJTTyhhDUyxIUyzIJYvK+23b4VAqw96j4+w7Os6rh1J07z4CQNBnuDAZ57KOBGs63FDZHNOcShERERGR+UYBUs4IyzIsaYiwpCHCtSubARiZmGTf0XH2DY6z9+g4/+vlgzz00gEAFteHq6qUK1ti+CwNexURERERqSUFSKmZ+kiAtUvqWbukHoDJgs3+4Qn2HZ1g39FxfrVviJ+90Q9ANODjko5ylfKS9gTxsG5fEREREZEzSb+By7wR8Fne6q3u40Ucx+Ho+CT7jo6x7+gE7x4d4++efx/bAQOsaIlxaUeCSzviXNpRT2dDWIvziIiIiIjMIQVImbeMMbTEgrTEgly1tBGAzGSBnsEJerxhr9ve6ufRXYcBaIj4ubSjnks74qzpSHBRMk444KvlVxAREREROacoQMpZJRzwcWGyjguT7rMqbcehN5UtzaXcM5Bmx7tHAfBZhgva6qoW50nGQ7XsvoiIiIjIWU0BUs5qljF01IfpqA/zsRVNAKSz+arFeX6y83DpESLJeKhqcZ7zW2P4fXqEiIiIiIjIbChAyjmnLuRnjVd1BCjYDgeGJ9g36D5C5Df7R9j21gAAIb/Fxe3xUqhc05GgIRKoZfdFREREROatWQXIHTt2sGnTJmzb5pZbbuH222+vOu44Dps2bWL79u2Ew2G+9a1vcfHFF5eOFwoFbrrpJpLJJPfff//p/QYiM/BZhmVNUZY1RfntVe6+ofGcV6Wc4N0jY/z4xQMUHAeAZY0RLl1czzUrm1nVGGZ5UxRLi/OIiIiIiMwcIAuFAvfddx8PPvggyWSSm2++ma6uLlatWlVqs2PHDnp6eti2bRs7d+7k3nvv5ZFHHikd//GPf8zKlStJp9Nz8y1ETlJjNEhjNMiHOxsAyOVt3huaKA17fXbPEf7ttV4A4iE/azriXNrhVikvXhQnFlTxXkREREQWnhl/C961axfLli2js7MTgA0bNtDd3V0VILu7u9m4cSPGGNauXUsqlaK/v5+2tjZ6e3t59tln+Y//8T/yox/9aM6+iMgHEfRbrG6Nsbq1/AiRMRte2z9UqlI+t28IB7AMrGqNcVlHfSlYdiT0CBEREREROffNGCD7+vpob28vbSeTSXbt2nXCNu3t7fT19dHW1sbmzZv58pe/zNjY2GnstsjcMsbQXh+iztfENcvdfeO5AvsGx91HiBwZ599e6+WRVw4B0BwLeIEywRWd9ZzfWofPUqAUERERkXPLjAHS8eaFVTq20nK8Ns888wxNTU1ccsklvPDCC7PulAHq6vS4Bakty7Kq7sM6oK0pytXetm077B+a4J2BNO/0j/FGX5qn9xwBIB72c/XyJq5e0cQ15zVzflsdlgKlnAKfz6KhIVrrbojoXpR5QfehSO3NGCDb29vp7e0tbRcriydq09vbS1tbGz//+c95+umn2bFjB9lslnQ6zV133cV3vvOdE/5MB0insyf5VUROr7q60Iz3YXPIR/OSeq5eUg/A8MQkewbS7BkY49WDIzz1Vj8ADRE/V3Q2cEVnA1d2NrC8KaIhrzIrDQ1RhofHa90NEd2LMi/oPpT5orU1Xusu1MyMAXLNmjX09PSwf/9+kskkW7du5bvf/W5Vm66uLh5++GE2bNjAzp07icfjtLW18aUvfYkvfelLALzwwgv8z//5P2cMjyJns4ZIgKuWNnLV0kYABsdy7PYC5SsHU3TvdiuUzbEgVy5t4Iol9VzZ2cCSBs2hFBEREZH5b8YA6ff7ueeee7jttttKj+NYvXo1W7ZsAeDWW29l3bp1bN++nfXr1xOJRNi8efOcd1zkbNAUC3JNrIlrljfhOA5HxnLs7h9jz8AYL/QM8fM33QplMh7iys4Gruis58qlDSxKhGvccxERERGRqYwz3QTGGhvNTPLLN3pnbigyh2YzhPWDcByHvtEsuwfcQPlWX5rRbB6AxfVht0LZ6VYoWzUneMHScC2ZL3Qvynyg+1DmCw1hFZEzzhhDeyJMeyLMtSubsR2HwyMZ9hwZ4+3+MZ56e4DHX3X/IWVZY8QLlG6obIoGa9x7EREREVmIFCBF5gnLGBY3RFjcEOG3V7Vg2w4HRibYM+AGyp+90cdPdh4GYGVLlCs7G7mys54Pd9aTCAdq3HsRERERWQgUIEXmKcsyLG2MsrQxyifOb6VgO7w/NMGegTRv94/x6K7D/NPLBzHA+W11XOnNn1y7uJ66kP6vLSIiIiKnn37LFDlL+CzDec1RzmuO8skLIV+w6Rn0AuXAGP/8yiH+4dcH8Rm4MBnnKm8O5WWL64kEfLXuvoiIiIicAxQgRc5Sfp/FqtYYq1pjfBrI5W32DY6XKpQP/d8D/OjF/fgtw8WL4lzlPYdyTUeCkN+qdfdFRERE5CykVVhFjmOuV2Gda9m8zbtHxrw5lGl6BsexHQj6DGs6Em6FckkDFy+KE/ApUM5XWnFQ5gvdizIf6D6U+UKrsIrIOSfkt7ioPc5F7e4fcBO5Au8UA+VAmvt/+R4O7xH2W6xdUs+VnfVc0dnAhck4fsvUuPciIiIiMh8pQIosEJGgjzUdCdZ0JAAYy+bZMzDmPTYkzfM9QwBEgz4+vMQNk1d21rO6tQ6fAqWIiIiIoAApsmDFQn7WLqln7ZJ6AFKZPHsG0qUhr//f3kEAEiE/H+4sBsoGVrREsYwCpYiIiMhCpAApIgAkwn6u8BbaARiemGR3f5o9R8Z4o3eUZ985CkBjJMAVSxu4Ykk9V3Y2sKwpglGgFBEREVkQFCBFZFoNkQC/tayR31rWCMDRsRx7BtLsHhjjN/uHeertAQBaYkGuLAbKpQ0srg8rUIqIiIicoxQgRWRWmmNBmmNNXLO8CcdxGEjn2DMwxu6BNM/1DPK/3+wHoD0ecgNlp1uhbE+Ea9xzERERETldFCBF5KQZY2iLh2iLh/jYCjdQ9o5m2dM/xu4jY2x/5yhPvN4HwJKGMFd6Q2Ov7KynpS5U496LiIiIyKlSgBSRD8wYw6JEmEWJMNeuasZ2HA6NZLxHhoyx7e0BHnvVfbbr8qYoV3Y2cOXSeq5Y0kBDNFDj3ouIiIjIbClAishpZxnDkoYISxoi/M7qFmzbYf/wBHuOjLG7f4wn3ujlX3YeAmBVS4wrl7rVycuX1JMIK1CKiIiIzFcKkCIy5yzLsKwpyrKmKL97fisF2+G9oXF3DmX/GD/deZj/9ZuDGOCCZJ1boexsYO2SBLGg/pgSERERmS/0m5mInHE+y7CiOcaK5hjXXQiTBZuewQl3ldf+Mf7Xbw7y8EsH8Bn4UHucq5Y2cMWSBi5bnCAc8NW6+yIiIiILlnEcx6l1J441mpnkl2/01robssDV1YVIp7O17saClMvb7D06zp4jbqDce2ScguPgtwyXLPICZWcDlyxKEPJbte7unGpoiDI8PF7rbojoXpR5QfehzBetrfFad6FmVIEUkXkn6Le4MFnHhck6uBgykwXePTLuzaFM83fPv8/fPvc+QZ/FpR1xbw5lAxe1xwn4zu1AKSIiIlJLCpAiMu+FAz4uXhTn4kXuv/ZN5ArsOTLmzaFMc/8v3+MHvEfYb3H5kvrSI0MuSMbxW6bGvRcRERE5dyhAishZJxL0cWlHgks7EgCks3n2DHiBciDNcz1DAMSCPj7c6T4u5MrOBla3xbCMAqWIiIjIqVKAFJGzXl3Iz+VL3MeAAKQyk+weGOOdgTHe7k/zi3cHAYiH/Fy5tIErltRzxdIGVjZHMQqUIiIiIrOmACki55xEOFB6FAjA0PgkuwfS7BkY47XDKZ7ZcwSAxqjb7opOd9jrssaIAqWIiIjICcwqQO7YsYNNmzZh2za33HILt99+e9Vxx3HYtGkT27dvJxwO861vfYuLL76YbDbLH/7hH5LL5SgUClx33XXccccdM/48X36cxqMvYRwb4xTAsUufjWNj8LZxt3FsLO99ShtvGyqPFTCOA07BO88B3MVojfdO1eK0Uz+bqrVrpzk+zb6p12Vq29JxZ4bjsz+/6lrHWXTXMQawcIyFY3w4xgJj4eDDMQbH+Nxt77NTOuaeQ0U795i33/hwMFXXLbe3Kl7FdsWfU7xGxbbXBlN9LlU/s6Lv3jlgjvnZFigkLCiN0QBXL2vk6mWNABwZy7GnP83ugTF+vX+Y//P2AACtdcFSoLxyaQOL6yO17LaIiIjIvDNjgCwUCtx33308+OCDJJNJbr75Zrq6uli1alWpzY4dO+jp6WHbtm3s3LmTe++9l0ceeYRgMMjf//3fE4vFmJyc5LOf/SzXXnsta9euPeHPjKb2cvUv/58P/OVm4oYRq/Re5oYLpypjmON8Lu6aetyZ4fiUvkxpe5yQM83x6lhopvmZU487x255QR0cL3y7oZxSGHfDtsE+znXPHuWA6wVNK4BtBbz3II4VAH+QPOV9dqlNENvye9tuW9u4x2xf+bNjBSgY93jBCuAY9738c8rXrfoZJlBxbf8x96acDi2xIC3nNfGR85pwHIf+dK40f/JX+wZ58s1+AJLxEGsXJ7i0o57LFidY1RLDp0V5REREZAGbMUDu2rWLZcuW0dnZCcCGDRvo7u6uCpDd3d1s3LgRYwxr164llUrR399PW1sbsVgMgHw+Tz6fn9XwsGyknX0X3VVVMaqukJnyPq/yhDHVoaC4r/S5HBTdaxpVoU6VV7GtDJtuyKz+jGO71VGvIox33P1ccezY0MpxroPjVoypDLNO1fWqroUNDuVrFY8f+zNxME4eY+exnALGzmOcPH5TgPwklp3Flx/HOJMYu4DltS2eY+xJLDvvHndOf7i2jR/H8pfCamX4dCpDbSm8Bkvt7SltveBrKo6ZAAVf2HtFjvlc3rZ9oXMyzBpjSMZDJOMhPr7CDZSHU1n2DIzx7tEx/u/7w/z8LbdCGfUW73FDZYJLFiWIBHw1/gYiIiIiZ86MAbKvr4/29vbSdjKZZNeuXSds097eTl9fH21tbRQKBW688Ubef/99PvvZz3LZZZfN2KmCP0Kq4aKT+R5yJhkD3rBUOLb6ee6IRIJMTORO7iRv2LRlT3oBs4Bx8l7AzHvhs4BxJrGKxxz3vfjZbVuoaF/Rxs5XB1jvZ1mFDL58eppwmy//fC/sfpAKshskwxT8EffdV34v+IvBM1pu5wuT94UpWBEKvhAFX4R8VSitCKx+9zOmtoHMGENHfZiO+jDrVjXjOA6D45O8e2SMvYPjvDswxgs9QziAz8D5bXWsXVLPZR0JLutI0FIXqmn/RURERObSjAHSmW7O3TGVuxO18fl8PP7446RSKf7kT/6E3bt3c/7555/wZxrcX95FaskYc9rvw3kx+NexK0KmVz21c1iFHFYhW/rss3MVn7OYQg7LzmHZ2VJbq5DDb+cI5tKYCXfbFLLesSzGyZ9092wriO0PY/sj2L5I6XPBHy1tF3zl4wW/F0T9kXLl1Nvnto1455ev51iBk+pTPB5mWTJOl7c9ls3zTr+7KM/uvlF+uvMwW359EIDOxghXLmvkw0sbuWJZIytbYlgfYNirz2fR0BA95fNFThfdizIf6D4Uqb0ZA2R7ezu9vb2l7WJl8URtent7p7RJJBJcffXV/OIXv5gxQDpw8pUfkdPslCqQZxU/pT8CTPXm6VKsevrsrBs+C14ALQZTZxLLdsNq5Xu5rffKZ/HlBggUJivO94KqffL/G9nGj12qpoYp+OvIB+rI++vIB2Luu7+8Pelz90162xF/HR+K1LF6ZR2fWt1M3nbYP5xh79Fx3j06xtNv9fPoK4cA99Eha5ckvAplPR9qjxPyz34ocENDlOHh8ZP+jiKnm+5FmQ90H8p80doar3UXambGXxfXrFlDT08P+/fvJ5lMsnXrVr773e9Wtenq6uLhhx9mw4YN7Ny5k3g8TltbG4ODg/j9fhKJBJlMhl/96lf8h//wH+bsy4jI/OJY3vxN5nA1U8f2hvFmSxVSX0UA9Tk5rIIXVJ2s17YcTn2FLJadwZcfJ5g9iq+QwcqP48uPY9mTM/542/gpBGIU/DHygTo3jCbrGDVRjk6G6M0GOdjr51BPgJ8T4TETpaGxmc62VpYvSnL+4kXE6xvBH9G8bBEREZn3ZgyQfr+fe+65h9tuu41CocBNN93E6tWr2bJlCwC33nor69atY/v27axfv55IJMLmzZsB6O/v56tf/SqFQgHHcfjUpz7F7/zO78ztNxKRhcVY2L6Qu8jP6b60PYmvkMFXmHDf8xOlz3474x2rOF6YwJefIJIbJlaYYHF+gsvzE1h2FipHzY56r3fLu2wsJv0xTLAOK1yPE4rjBOP4YvXEiWIH63CCdTjBOHYwXvrsBLz30nZMQVRERETmjHGmm8BYY+Ojw7z2XHetuyEL3Lk/hFXOFGPn3YWOCuUA6uQmODqeZSidJTWRYWxigpA9QdxM0OSboD2Qodk/QcLKECyMY02OYwqZGX+Wg/HCZDFYxqsDZjDuhVE3fNrBOE6oHifcgB1qwAk34ATqFEJlCg0dlPlA96HMFxrCKiIic8ax/BSsOgqBuqr9YWCR97IdODRueGvEYveIxVvDFr2jbogL+WBNE1zeYnNlY4ZL6jPEyWDy45j8hPuanCh/Lu0bh/wEvvQh8LbNpHvOCftrfDjhepxQA3a40Q2VoQZsL2QWg+ax704wAZYeayIiInIuU4AUEZkHLANLYg5LYgV+t6MAwFAW9k0EeW3A4a0Rw9+9ZfhbJ4ohyqp6WNtqsbYF1rYYOmJTV8g+LseGfMYLk+OY3BhmcgxrMo2ZHMPkiu+jmFwa38h7mNzr7vbk2PEvi8EJJXCKwdILn27ArMcONVaHzlA9dth9x6eVt0VERM4GCpAiIvNUYwg6GuDDDe5iPpk8vJOy2J2yeGvEYmuPwyPvuKGxLQJrWw2XtxjWthhWN4D/eI8PMRYEojiB6Mk/x9XOu8Ezl8ZMpsvvk2NYxfDp7fOlD8Hgbm/fKOYEP80JxLBD9TjF0FkKmeXAaVdUQovv+OdwgSYRERGZQgFSROQsEfbDJU02lzS5TxS1HXg/bXh7xOLtEYvf9Ftse98NjVE/XNpsuLzVcFmL+zkaOA3zGi2/V2VMnNx5ju0NoR2rCp1u9TONVQqkY5jMEP7Ufjd0ZlMYp3D8y/pC1cNow41e2KzHCTVWBc/qeZ5abEhERORUKECKiJylLAPL4w7L4wWuW+KGrCMZvHmUPt4esfjBa+7QUp+B8xvg8laLy7xhr8noGQxQxiot7kMsOfvzHAcKWUyuMmR64XMyXa56evutsT78xYpnIXv8y1r+8uJB4WbsSDN2pAkn0oIdbsKOtnj7m7AjLTiRJrD0V6aIiIj+NhQROYe0hOHjYZuPJ90q5Xgedo+4w17fHrb4yTsO/7jbDY4dMTdIrmk2XNhouKCB01OlPJ2MAX8Yxx+mEG05uXMLuepw6VU7i+HTTI5h5UYx2VH8R9/AZEYwuRTGsae9nB2qx4k0Y0davMDZjBNppuC92+Fm7Kj7rsApIiKVvv/97/PEE09gWRaWZXHfffdx2WWXfaBrdnd38+6773L77bd/4P5dfvnlvPzyy7Nqq7/dRETOYVE/rG22WdvshqK8DT1pw9sjPnaPWDx32PCz99zQaIDlCfhQo3FfTW6ojAfnWaicLV8QJ9Lkhjng+ANhKzi2GzqzKUwuhVV8Lw6n9fbNLnA24HgVTLei2YQTbaYQbq4Iok0KnCIi57iXX36ZZ599lkcffZRgMMjg4CCTk5OzOjefz+P3T//3wyc+8Qk+8YlPnM6uzor+thIRWUD8FqxKOKxK5NnQ6Y4QHcrB3lGLnlGLfWmLF3rLoRKgsw4uavJCZSNc2GioD52loXImxqqa4zlj6Jw2cI5i5VKY7Ij7OZvCP/Baqc2MgTPaWlHhbPICZ0tpmK0dacEJNypwioicJQYGBmhsbCQYdFccb2py/2Gzq6uLf/mXf6GpqYlXX32Vb3/72zz00EP8zd/8Df39/Rw8eJDGxkbef/99Nm/ezOrVqwH4oz/6I/7sz/6M3bt389prr/HFL36RG264gaeeegrLspiYmOBTn/oUTz31FIcPH+brX/86Q0NDhMNhvvGNb7By5Ur279/PXXfdRT6f59/9u393Ut9Hf/uIiCxgxkBTCJpCNle2lIPNcBb2pd1QuTdt8fKA4efvl0NjR8wLlQ2GC5vcqmVT+BwNlSdy2gLniLdvFCs7gj992N3Ojky7eq37yJR6nOixQ2qbKIRbvApn+aXAKSJSOx/72Mf4H//jf3DdddfxkY98hOuvv57f+q3fOuE5r7/+Ov/4j/9IOBzmRz/6EU8++SSrV6+mv7+f/v5+LrnkEnbv3g1APB7nggsu4MUXX+Saa67hmWee4eMf/ziBQID/+l//K1//+tdZvnw5O3fu5Otf/zo//vGP2bRpE79gCBsAACAASURBVLfeeisbN27kH/7hH07q++hvExERmaIhBJeHbC5vLofKVA560hb7Ri32pQ2vH7V4an85NCYj8KGKSuWHmgytkQUYKk/kAwROy6toHj9wevuOFzjDFUNqq+ZwtrpVz2ib994Kgejp/+4iIgtULBbjpz/9KS+99BIvvPACX/ziF/nSl750wnO6uroIh8MAfPrTn+bzn/88d9xxB08++SSf+tSnprS//vrr+dnPfsY111zD1q1b+exnP8vY2Bgvv/wyX/jCF0rtcrkc4A6r/Zu/+RsAbrjhBr7zne/M+vsoQIqIyKwkgnBpk82lTeVQOTZZrlTuSxveGbbYftANLADN4eLwV3fo64caDe1RMHqExuxUBE6bJTO3LwXOkVJ1053DmXJDqPc+Y+AMxMqhMtaKHWnDauogbDVUBU070gK+wBx8cRGRc4vP5+Pqq6/m6quv5vzzz+exxx7D5/PhOO6fwdls9crhkUj5OcfJZJKGhgbeeustnnzySb7+9a9PuX5XVxff+973GB4e5vXXX+eaa65hYmKCRCLB448/Pm2fTvXvYgVIERE5ZbEAXNJoc0ljOVRO5N2FenpGfexLG/amLH55CGwvVDaEqKpSfqjRsDimUHlaVAXOWXBsb6jsMFZm2Kt0DrvVTm+fv/9VTGYIKzdKfJpL2OHGUth0Ym0UIq040VYKpapmi3ss3AjGOs1fWERk/tu7dy+WZbF8+XIA3nzzTTo6OshkMrz22musW7eObdu2nfAaGzZs4IEHHmB0dJQLLrhgyvFYLMaaNWvYtGkTv/3bv43P56Ouro4lS5bw5JNP8ulPfxrHcXj77be58MILufzyy9m6dSs33HAD//qv/3pS30cBUkRETquIHz7U4PChhnxpX7YA76UN+0YtetIWe0ctXuyDguOGxnjAC5VN5VVgO+NgKVTOLWO5Q1vDDdj1J25aF7EYO9qPlR3GZIohc8QLnMNYE0cxw+8SnBic9hmcjvHheGGycshsMWhWHnMCde4EXRGRc8D4+Djf/OY3SaVS+Hw+li1bxn333cfevXu5++67uf/++2d8pMd1113Hpk2b+E//6T8dt83111/PF77wBR566KHSvr/6q7/i3nvv5fvf/z75fJ7rr7+eCy+8kLvvvpu77rqLH//4x1x33XUn9X2MU6ybziPjo8O89lx3rbshC1wkEmRiIlfrbsgCdy7fh7kC7B8z3pxKi32jhvfShknbDQ4xP1zYCB9qtNz3JsPyOPgsBYtaqKsLk05nZm7oOJDPVAfN3AhWxg2aJut+NplhTGYI40ydCer4wxUhs3LIbGv5s1fdxB+eg28r81VDQ5Th4fFad0OE1tbpxmQsDKpAiohITQR9sDLhsDJRoLicTN6GA2PGC5RuqHzkHYesFyrDPji/AS5q8kJlo2FFPQQUKucPYyAQwQ5EoG7RiRcKKs3ZLA6hHcHyXsYLoP6jb2IO/gorOzLtJexgAid2bNhsoRCprnQ6kWawfHPylUVEFhIFSBERmTf8FiyPOyyPF/idRW70KNhwcNywL23YN+pj36jhsb0OmYIbGoMWrD4mVK6qh6BPoXLeq5yzmVh64rZ2vjRHs3oIbcV8zdT7WJkhzOTUCpVjLJxwE3bMC5qRFneBoGjSWywoScF71yq0IiLHpwApIiLzms+CpXUOS+sc1rW7S8PYDhz2QmXPqI+9o4atPQ6PvOOGRr8Fq+rL8ykv9CqVdQGFyrOW5XefcxlpmrltPuMGy0zFgkC5lLc9jC99CP+RN9whtPbklNPtYB1OtA27rh07mqQQa6sKmm7YTEIwNgdfVERkflOAFBGRs45lYHHMYXHM4ePJcqjsnzDsHTX0pN0VYJ/ab3h0bzk0tkbgvLjhvHrDeXFYnoDzEoa2iFaBPaf4w9j+MMSSMwyhdTCTY5jMoDeEdhgrM+TN1xzCZIYJDO0lmBnEFKbORXYfd1IOlXbMDZmFWHXY1KJAInIuUYAUEZFzgmWgPerQHnX4qBcqHQeOZNxnVR4atzg0bjg4bnhtn2E8X/6FPuqH8xKwPGE4L25KwXJpHQQ0FPbcZQxOsA4nWHfiIbSOg5kcdx9nkh3y3ouLAQ16w2ffw5oYwhSmLjTk+CNVAdP93EYhmnQrmzF3nxNMKGiKyLynACkiIucsY9yqY2vEhoonIzoODOfg4JjFoQnDoXGLg+OGF3sNW3vKv8D7DCyuc8OkW7E07ucEJIL6RX/BMAYnGMMJxrBZcvx2jgP5Ca+KOVSam+nO23T3+ft+gzUxiMlPTD3dF6qoZrZhR9uxY60Uou3luZuxJE6oQUFTRGpGAVJERBYcY6AxBI0hm0sAKgY6ZvK4lcoJw+Fxi4PjFvtGDL86TOkRIwBNIViRgOUJy6tYwvK4YVFMz69csIyBQBQ7EMWOLz5x28mJ0jBZKzPkPkszUxk0d2JlnsVMjk051fEFq4fORisqmqWg2Y4TblTQFJGSHTt2sGnTJmzb5pZbbuH2228/pesoQIqIiFQI+2FFwmFFwqGyalmwYSDjDoGtHA77v993SE+Wf0kP+WB53KtaJqqHw4b9+mVePKVHnXSceJ5mPlMVLK3ciFvd9OZq+gdexcrswOTSU051rID7KJNYEieWLM/NrAqcSZxIExhrzr6qiNReoVDgvvvu48EHHySZTHLzzTfT1dXFqlWrTvpaCpAiIiKz4LPKcyyvOGY47Oik+6iRg+PluZYvDxh+/j44uKHRAB0xWFFvWB6vnm/ZFFawlOPwh7Hr2qGu/cRBs5CrCpYmO1Q1fNZ35E38B36JlRudcqpj+bEjrTjeXMyqRYAqwqaepSly9tq1axfLli2js7MTgA0bNtDd3T13AXKmcqfjOGzatInt27cTDof51re+xcUXX8zhw4f5yle+wpEjR7Asiz/4gz/gj//4j0+6kyIiIvOVMZAIQiLo8KGGApXDYbMF93Ejh0rDYQ0HRi1e6IVcxXDY+qA7BLZUtfQqmB0x8FkKlzILvqD7DMuZVp4t5Morzk4Mes/SHCpVOX2Du/EfegErOzLlVMf4cKIt5edmxpI4pVVny4sB2ZEWsFSjEJnOT359gH9+af9pveYfXNnJTVecYH420NfXR3t7e2k7mUyya9euU/p5M/6/ezblzh07dtDT08O2bdvYuXMn9957L4888gg+n4+vfvWrXHzxxaTTaW666SY+9rGPnVLSFREROdu4w1kdlserh8PaDhzJGA6NlxfwOTRueOaA4dFcOTAGLFhWGg7rzrEsDouNaDisnApfEDvWBrG2EwdNO1+en1lcEMh7zInJDOMb3ou/9yWszPCUUx1j4USaj5mj6S0GVLEKrR1pBV9gzr6qiJQ5jjNl36k+vmrGADmbcmd3dzcbN27EGMPatWtJpVL09/fT1tZGW1sbAHV1daxYsYK+vj4FSBERWdAsA20Rh7aIw9pmu+pYetJbxKdiOOzrRw3d+8Gm/Jd9e/TYiiUsSxhawlrER04Dy48TbaEQbZk5aGYr5mUes/Ksb7gHf+/LmMwQhupfYB0MTqTJC5TFcFm5GFAxgLaCLzinX1fkTLnpiiUzVgvnQnt7O729vaXtvr6+Uk47WTMGyNmUO49t097ePqVTBw4c4M033+Syyy47pY6KiIgsBHUBOL/e4fz66uGwkzb0TRgOjLnDYQ9NGA6OGV4ZMEwUqquWySh0xAyLorAoCu0xdzjsoqihPapnW8ppZPlxIs0UIs0nbmcXvOGyw5iJQe85msVHnQzhS72Pv3+nGzQde+rp4SbsWBtWfQfxYEt10KwIn/hCc/RFRc5ua9asoaenh/3795NMJtm6dSvf/e53T+laMwbI2ZQ7Z2ozNjbGHXfcwZ//+Z9TV1c3Y6cMEInoX5qktowxug+l5nQfSlEESMRgdUv1fsdxOJpxODAGh8bgyIShfwL6J+DdERjMgFNR+TFAS8SwuM6wOG6xuM6wqM6wuM793FFnEZ/mGZeWZairC8/tl5RzXAzomPaI472wC5BNwfggZmIQMsMwMYiZGHLnbKYOEpp41T3uTK2NOuEGqGvHibsLDzl1SYh773XtOHXtUJeEQGQuv6jIvOP3+7nnnnu47bbbKBQK3HTTTaxevfrUrjVTg9mUO49t09vbW2ozOTnJHXfcwWc+8xk++clPzqpTDjAxkZtVW5G5EokEdR9Kzek+lNmIARfE3Nex8jYczRoGMoYjGcPRrPs+kDH8ptewLVP9fEtwq6CLYsUqplvJXN4coMmXZ1EUmjRMVuZUBEKL3dcx6urCpNMZcGxMbhRrYqi04myxmmllhjAjh7H63sDKDGLs/JTr2MFEadVZO5ak4K1CW4i0lqqZdrQVJ9SgZ2nKtFpb47Xuwklbt24d69at+8DXmTFAzqbc2dXVxcMPP8yGDRvYuXMn8XictrY2HMfh7rvvZsWKFXz+85//wJ0VERGRk+O3IBlxSEamjhYCd0GfkZy7qM9A1nA0Y3nvhvdGDC/1wVjeANnSOcFjh8nG3KGxHTH3czKiYbIyx4yFE6qnEKoHlh+/nWNjcunyczSzIxVzNYcwE4MEht4lmBnEFKb+Y13VszSjbRS8YOk+T7Py1aJ5mrJgzBggj1fu3LJlCwC33nor69atY/v27axfv55IJMLmzZsB+PWvf83jjz/O+eefzw033ADAnXfeeVqSr4iIiHxwloHGEDSGHFZTvVps0XgeUk6QgyN5jmQMR7IWRzJu6NwzbBjMVodFd5gsdHjhclFx/mUMOqLudiyggClngLFwQgmcUAK7ftnx2zkO5CfcBYAyQ5jciLcY0AimuCDQ4Nv4Dz0/7SNOAOxwY6l66UTbKERb3YWAoq1eRdOragYTqmrKWc04001grLHx0WFee6671t2QBU5DB2U+0H0o88WJ7sVJG456w2JLQ2SzhiMThiNZw8AE5J3qX5gTQbyqpTdMNuZuL/IW/GkKnfoS83LuKg1hraXSyrPDXjVzpLRAkLswkLdA0MQQxp6mqukLlaqalcNlqyuare7qs3qe5rx1Ng5hPV10V4qIiMgHErCgPerQHj3+MNnh4jDZjOFo1nIrmRnDvhHDi30wnq8OiyGfFyij5QpmMWS2Rw3NYYiqiim1MNuVZx0HMznmzc305mgWg6e3z3/0DcyBX2LlUlNPLz7mpBQyjwmasXLgdAIxVTXljFGAFBERkTllGbei2BRyOL9++mGyY5OUFvo5ki0OkzUMZODtIcNQbuovx2EfNIeLL0NT2NAcdrx3aA65701hd2EgVTTljDIGJ1iHE6zDjs/w3L/CZPkxJ95zNK3scKma6Usfxn/kDfcxJ9MsCuT4IxVVTW/obKwVO9JWvT/SApZvjr6wLBQKkCIiIlJzsQDEAg7L48UqZvUjGnKF8mqyQzkYyVmM5AwjORjJuZXMlwfcBYEcpgbFoOUGyWLYLAbPYthsCpX3J4IKm3KG+QI40RYK0ZYTtytWNb2FgIw3T7P0OTOEf+A1rMwOTC499XRj4YSbysNnoy3Y0RacSAuFSAt2pMWdpxlpxo40awitTEt3hYiIiMx7QR8sijosKg2TnVrFBHe4bGoSL1wahnOQylmMTLphczhn2D9qePWoGzZtZ2pQ9FvFQFmsbFaEzWP2N4T0SBM5gyqrmnSeuG0hVzVctjRPMzuMyYzgGz2A/8hrmMwwxp6c9hJ2uBE70oITbSlVMO1oC3a42dtuLlc2A9E5+MJyunzta1/j2Wefpbm5mSeeeOIDXUsBUkRERM4ZloGGIDQES4+m50RhMz3phsqRnGFksqKy6YXQw2OGN4dgJDt1ISAAn3FDZHMYWqarbFZUPBuC4LMUNuUM8QWxY20Qazumnn+M4gq02WFMNoWVGcHkUli5lBc63UWC/Kn97uJAk2PTX8YfxY42Y0da3cB5grDphBvAWHPytWV6N954I5/73Of4sz/7sw98LQVIERERWZAs4w5XTcwibDoOjOWnC5vlaufAOOwZdquek/bUoGhRDpuVlc3pPjeGIKCwKWeCMRCIYgeiUNdx4rAJ5fmauZQ7bDY3Wt72wqZvcA/+7EvutjP1io7xeQsEtZYrnF7gLISrt+1IM/hCc/LVF5KrrrqKAwcOnJZrKUCKiIiIzMAYdyGeuoDDktjMYXOiUAyb5YDpDqN1X0MZ2JcyDGchO03YBIgHigEXEkFT8e6QCJqq4/Xe8XjQ7aeG1cqcme18TQDHxuTS5UpmLuVWOSsD6Fgf1uBud4GgQnbay9jBRMUw2uaKcFl+FUOnE4zP7xVpX9kCLz98eq95+edg7a2n95onoAApIiIichoZA1E/RP0OHVEoVzenchzIFCjN1ywGzVTOMJo3jE3CWN4wnIGDaUN60h12O91w2iILqAtCohgwQ174DFSEzyDUV4TTYhjVarVyWhkLJ5TACSVmnrMJkM+UhswWg6bJpSqetTmCP33Yq3xOffQJgOMLeoGyctisO7S2ajvaihNu1EJBp0D/xURERERqxBiI+CHid2ifIWwWOQ5kbUrhMj0J6bxhPG8YyxvG8t62t39wAvaPlsNn4UTh05yg8hlwqA9VVz7j3vH6oBuaFT7lA/GHsf1hiCVnbmvnMblRb86mFzBzoxUBdARf6n38/bsw2eFpH38CYIfqccKN2OEmd1htuAk70uiuVuvtrzzmhOo/2KNQ1t56RquFc0EBUkREROQsYoz7DMywD5pLgXPm4Ale+CxAOg/pyXLgHMsbxibL4XMsD2OThiMT8F7KeO2nX7W2yGfcIbSJUvXTVAyvdUphMxF0Q2p9yJAIQDQAMb8WGJKTZPlxwo0Uwo0zty0+/iSbclelzaa8hYJGMcVXNoVveC/+3E43gBZy018K4y4C9NWe0/t9ziIKkCIiIiILhDEQ9ruvlnDl4kEzK87tLFU+K4bYjuUrw6gbTvvH3Xme6Un3HHua53NWCvvc54FG/d5zQf2mFC5jfjdoNkSzBBy7og1EA6Z0PObtD/tUDZUKFY8/IT6LhYIA8lm3wplLufM4c6OYybS3aFCKs21ZnzvvvJMXX3yRoaEhrr32Wv70T/+UW2655ZSupQApIiIiIjMqz+2EVk4ufNreXM/0pFvNLFY7x/KGibwhU4CJQvEdMnnDRB6GMsbbhvECZAvTP6/wWJbX1+pgWRlIDdGAUwqp0wZSvzsnNBrQirgLkj+E4w8dd7Ggsy1Afu973ztt11KAFBEREZE5ZVUsLNQGnEz4rBQMBxlO55jIVwTOvBcyvc+ZQnHblMNoAYYz0Dvmfp7Iu68TLUZU9XOtchCtDKTFoBkLGKJ+x3uvrqRG/YZYACI+r/rrg5AqpHIWU4AUERERkbOCr6IKyknO/5zOpO0GyWLYrPycKZhS+CyHVe9zHvpyXts8pXOdGYbpFhnKYTLscxdSCvsh4jPue+mYIex3iPgg4jeEfMV25fMjflPRntL5QUshVeaGAqSIiIiILEgBCwJBSFSF0FMLpLYDOW8IbjFkThTK1dFcwZC1DbmCu4putmDI2e6iRtmCIWu7Q3VTWcgU23mvTGH24bSoMqSWAqYXUouBtRhSI36nFEZDx7SfLqQWz1dIXZgUIEVEREREPiCrYoGixtNQHa3kOG619NjAmS1Aznarozm7HFKzhWLbMxNSixXRkK88RDfkMwRLnyFkuftCPoegF1wDpf3Vr6DPHHMe3jnuu19zUmtKAVJEREREZB4zxg1OQZ+7sA+noWJ6rA8aUotV1uI1Unn3PPec8rVz3vU+SL99phwqpwZQUxU2QxaE/MZr51SF0/LxyqBqpgTakM+ttmruqksBUkRERERkgTsTIbV0NQfyTmWwdINmMWROeqE0Z8Ok424X25XaHHuObZj0VuwdzXlh1ikGVq9dYfYLJx1P0HL/G7229jT9xzgLKUCKiIiIiMgZYwwEjDsH1XVsQD29gbVSwQulxfBaDKLlkOmFVK8i64ZZ47Uth92FTAFSREREREQWBJ8FPtwhrq4zF17PFdbMTUREREREREQUIEVERERERGSWFCBFRERERERkVmYVIHfs2MF1113H+vXr+eEPfzjluOM4fPOb32T9+vV85jOf4fXXXy8d+9rXvsZHPvIRfu/3fu/09VpERERERETOuBkDZKFQ4L777uOBBx5g69atPPHEE7zzzjtVbXbs2EFPTw/btm3jG9/4Bvfee2/p2I033sgDDzxw2jsuIiIiIiIiZ9aMAXLXrl0sW7aMzs5OgsEgGzZsoLu7u6pNd3c3GzduxBjD2rVrSaVS9Pf3A3DVVVdRX18/N70XERERERGRM2bGANnX10d7e3tpO5lM0tfXd8I27e3tU9qIiIiIiIjI2W3G50A6ztRnoRhjTrrNyTBAJBI85fNFTgdjjO5DqTndhzJf6F6U+UD3oUjtzRgg29vb6e3tLW339fXR1tZ2wja9vb1T2pwMB5iYyJ3y+SKnQyQS1H0oNaf7UOYL3YsyH+g+FKm9GYewrlmzhp6eHvbv308ul2Pr1q10dXVVtenq6uKxxx7DcRxeeeUV4vH4BwqQIiIiIiIiMv/MWIH0+/3cc8893HbbbRQKBW666SZWr17Nli1bALj11ltZt24d27dvZ/369UQiETZv3lw6/8477+TFF19kaGiIa6+9lj/90z/llltumbtvJCIiIiIiInPCONNNYKyx8dFhXnuue+aGInNIw2RkPtB9KPOF7kWZD3QfynzxW5+8qdZdqJkZh7CKiIiIiIiIgAKkiIiIiIiIzJICpIiIiIiIiMyKAqSIiIiIiIjMigKkiIiIiIiIzIoCpIiIiIiIiMyKAqSIiIiIiIjMigKkiIiIiIiIzIoCpIiIiIiIiMyKAqSIiIiIiIjMigKkiIiIiIiIzIoCpIiIiIiIiMyKAqSIiIiIiIjMigKkiIiIiIiIzIoCpIiIiIiIiMyKAqSIiIiIiIjMigKkiIiIiIiIzIoCpIiIiIiIiMyKAqSIiIiIiIjMigKkiIiIiIiIzIoCpIiIiIiIiMyKAqSIiIiIiIjMigKkiIiIiIiIzMqsAuSOHTu47rrrWL9+PT/84Q+nHHcch29+85usX7+ez3zmM7z++uuzPldERERERETODjMGyEKhwH333ccDDzzA1q1beeKJJ3jnnXeq2uzYsYOenh62bdvGN77xDe69995ZnysiIiIiIiJnhxkD5K5du1i2bBmdnZ0Eg0E2bNhAd3d3VZvu7m42btyIMYa1a9eSSqXo7++f1bkiIiIiIiJydvDP1KCvr4/29vbSdjKZZNeuXSds097eTl9f36zOnbZT/gDNySWz+gIicyUU8hPN5mvdDVngdB/KfKF7UeYD3YcitTdjgHQcZ8o+Y8ys2szm3OkEIzFWXnb1jO1ERERERETkzJkxQLa3t9Pb21va7uvro62t7YRtent7aWtrY3JycsZzRURERERE5Oww4xzINWvW0NPTw/79+8nlcmzdupWurq6qNl1dXTz22GM4jsMrr7xCPB6nra1tVueKiIiIiIjI2WHGCqTf7+eee+7htttuo1AocNNNN7F69Wq2bNkCwK233sq6devYvn0769evJxKJsHnz5hOeKyIiIiIiImcf40w3UVFERERERETkGDMOYRUREREREREBBUgRERERERGZpRnnQM6lbDbLH/7hH5LL5SgUClx33XXccccdDA8P88UvfpGDBw+yePFi/vqv/5r6+vpadlXOYce7D//yL/+SZ555hkAgwNKlS/mLv/gLEolErbsr57Dj3YtFf/d3f8e3v/1tnnvuOZqammrYUzmXneg+fOihh3j44Yfx+/2sW7eOr3zlKzXurZzLjncvvvnmm/y3//bfyGaz+Hw+7r33Xi699NJad1fOccX1XJLJJPfff/+Czis1nQPpOA7j4+PEYjEmJyf57Gc/y9133822bdtoaGjg9ttv54c//CEjIyN8+ctfrlU35Rx3vPswnU5zzTXX4Pf7+au/+isA3Ycyp453L65du5bDhw/zX/7Lf2Hv3r385Cc/UYCUOXO8+zCTyfCDH/yAH/7whwSDQY4ePUpzc3OtuyvnsOPdi//9v/93/viP/7i0iOMDDzzAQw89VOvuyjnuwQcf5LXXXiOdTnP//ffz7W9/e8HmlZoOYTXGEIvFAMjn8+TzeYwxdHd3s3HjRgA2btzIU089VctuyjnuePfhxz/+cfx+t0i/du3aqmeaisyF492LAH/xF3/Bl7/85dK2yFw53n24ZcsWbr/9doLBIIDCo8y5492LxhjGxsYAGB0d1TPGZc719vby7LPPcvPNN5f2LeS8UvM5kIVCgRtuuIGPfvSjfPSjH+Wyyy7j6NGjpT8M2traGBwcrHEv5Vw33X1Y6Sc/+QnXXnttjXonC8l092J3dzdtbW1ceOGFte6eLBDT3Yc9PT289NJL3HLLLXzuc59j165dte6mLADT3Yt//ud/zre//W3WrVvHX/7lX3LnnXfWuptyjtu8eTNf/vKXsaxydFrIeaXmAdLn8/H444+zfft2du3axe7du2vdJVmATnQffv/738fn8/H7v//7NeyhLBTH3otvvfUWP/jBD/jCF75Q667JAjLdn4mFQoFUKsU///M/85WvfIX//J//M3oSmMy16e7FLVu28LWvfY3t27fzta99jbvvvrvW3ZRz2DPPPENTUxOXXHJJrbsyb9Q8QBYlEgmuvvpqfvGLX9Dc3Ex/fz8A/f39musjZ0zlfQjw6KOP8uyzz/Kd73xHQwfljCrei93d3Rw4cIAbbriBrq4uent7ufHGGxkYGKh1F2UBqPwzMZlMsn79eowxXHrppViWxdDQUK27KAtE5b346KOP8slPfhKAT3/606qGy5z6zW9+w9NPP01XVxd33nknzz//PHfdddeCzis1DZCDg4OkUikAMpkMv/rVr1ixYgVdXV089thjADz22GN84hOfqGU35Rx3vPtwnAMx5gAAA5ZJREFUx44d/O3f/i3f//73iUQiNe6lLATT3YsXXXQRzz33HE8//TRPP/007e3t/PSnP6W1tbXGvZVz1fH+TPzd3/1dnn/+eQD27dvH5OQkjY2NteyqnOOOdy+2tbXx4osvAvD888+zfPnyGvZSznVf+tKX2LFjB08//TTf+973uOaaa/jOd76zoPNKTR/j0f//t3fHLI1EURiGv8iqhQRMEUVIYYpgp4KFlYWgMkiKQLAOKRS1shTLMGg6MT/BRgSxMZEYJWInWmihjSFY2YgYUGKRZCZbbLWwgQF3HWf2fcphinPgwvBx7r3z/Kz19XVZlqV2uy3DMDQ9Pa3x8XGtra3p4OBAQ0ND2tnZcbNM+FyndTg7O6tGo6F0Oi1JGhsbUyaTcbla+FmntQh8pU7rsNFoaGNjQ/F4XN3d3cpms+zMwD/VaS0Gg0Ftbm6q1Wqpt7eXbzNcsbS09N/mFVd/4wEAAAAA8I5vcwYSAAAAAPC9ESABAAAAAI4QIAEAAAAAjhAgAQAAAACOECABAAAAAI4QIAEAnnd6eqqRkRFVq1W3SwEAwNcIkAAAz8vn85qYmNDx8bHbpQAA4Gv8BxIA4Gn1el2GYWh3d1crKysqFouybVuZTEbX19eKRCKybVvJZFKGYeju7k7ZbFYfHx8KhULa2trSwMCA220AAOAJTCABAJ52dnamqakpRaNR9ff36/7+XqVSSU9PTzo6OpJpmrq9vZUkNZtNmaapXC6nw8NDJZNJbW9vu9wBAADe8cPtAgAA+IxCoaBUKiVJmp+fVz6fV6vVkmEY6urqUjgc1uTkpCTp8fFRDw8PSqfTkiTbthUOh12rHQAAryFAAgA8q1ar6fLyUpVKRYFAQJZlKRAIaGZm5o/vt9ttxWIx7e/vf3GlAAD4A1tYAQCedXJyokQiofPzc5XLZV1cXCgSiSgUCqlUKsm2bb28vOjq6kqSFI1G9fr6qpubG0m/trRWKhU3WwAAwFOYQAIAPKtQKGhxcfG3Z3Nzc6pWqxocHFQ8Htfw8LBGR0cVDAbV09OjXC4n0zT1/v4uy7KUSqUUi8Vc6gAAAG/hFlYAgC/V63X19fWpVqtpYWFBe3t7nHcEAOCTmEACAHxpeXlZb29vajabWl1dJTwCAPAXMIEEAAAAADjCJToAAAAAAEcIkAAAAAAARwiQAAAAAABHCJAAAAAAAEcIkAAAAAAARwiQAAAAAABHfgJf4L/vMEoS3QAAAABJRU5ErkJggg==\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"facet = sns.FacetGrid(train_data, hue='Survived', aspect=4)\nfacet.map(sns.kdeplot, 'Age', shade=True)\nfacet.set(xlim=(0, train_data['Age'].max()))\nfacet.add_legend()\nplt.xlim(40, 60)","execution_count":1011,"outputs":[{"output_type":"execute_result","execution_count":1011,"data":{"text/plain":"(40.0, 60.0)"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 915.875x216 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Binning\n# child = 0, young = 1, adult = 2, mid-age = 3, older = 4\ntrain_data['AgeGroup'] = pd.cut(train_data['Age'], bins=[0, 16, 26, 36, 62, 100], labels=False, precision=0)\ntest_data['AgeGroup'] = pd.cut(test_data['Age'], bins=[0, 16, 26, 36, 62, 100], labels=False, precision=0)\nbar_chart('AgeGroup')","execution_count":1012,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 720x360 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"bar_chart('Embarked')","execution_count":1013,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 720x360 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"pc1 = train_data[train_data[\"Pclass\"] == 1][\"Embarked\"].value_counts()\npc2 = train_data[train_data[\"Pclass\"] == 2][\"Embarked\"].value_counts()\npc3 = train_data[train_data[\"Pclass\"] == 3][\"Embarked\"].value_counts()\ndf = pd.DataFrame([pc1, pc2, pc3])\ndf.index = ['1st class', '2nd class', '3rd class']\ndf.plot(kind ='bar', stacked=True, figsize=(10, 5))","execution_count":1014,"outputs":[{"output_type":"execute_result","execution_count":1014,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fd51b687650>"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 720x360 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{},"cell_type":"markdown","source":"More than 50% of 1st class are from S embark\n\nMore than 50% of 2nd class are from S embark"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Preprocessing & Feature Engineering\n# Ordinal encoding of Embarked data\ntrain_data[\"Embarked\"].fillna('S', inplace=True)\ntest_data[\"Embarked\"].fillna('S', inplace = True)\n\nembarked_map = {\n    'S' : 0,\n    'C' : 1,\n    'Q' : 2\n}\n\n# replace data\ntrain_data['Embarked'] = train_data['Embarked'].map(embarked_map)\ntest_data['Embarked'] = test_data['Embarked'].map(embarked_map)\n\ntrain_data.head()","execution_count":1015,"outputs":[{"output_type":"execute_result","execution_count":1015,"data":{"text/plain":"   PassengerId  Survived  Pclass  Sex   Age  SibSp  Parch            Ticket  \\\n0            1         0       3    1  22.0      1      0         A/5 21171   \n1            2         1       1    0  38.0      1      0          PC 17599   \n2            3         1       3    0  26.0      0      0  STON/O2. 3101282   \n3            4         1       1    0  35.0      1      0            113803   \n4            5         0       3    1  35.0      0      0            373450   \n\n      Fare Cabin  Embarked  Title  AgeGroup  \n0   7.2500   NaN         0      0         1  \n1  71.2833   C85         1      2         3  \n2   7.9250   NaN         0      1         1  \n3  53.1000  C123         0      2         2  \n4   8.0500   NaN         0      0         2  ","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>PassengerId</th>\n      <th>Survived</th>\n      <th>Pclass</th>\n      <th>Sex</th>\n      <th>Age</th>\n      <th>SibSp</th>\n      <th>Parch</th>\n      <th>Ticket</th>\n      <th>Fare</th>\n      <th>Cabin</th>\n      <th>Embarked</th>\n      <th>Title</th>\n      <th>AgeGroup</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>0</td>\n      <td>3</td>\n      <td>1</td>\n      <td>22.0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>A/5 21171</td>\n      <td>7.2500</td>\n      <td>NaN</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>38.0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>PC 17599</td>\n      <td>71.2833</td>\n      <td>C85</td>\n      <td>1</td>\n      <td>2</td>\n      <td>3</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>3</td>\n      <td>1</td>\n      <td>3</td>\n      <td>0</td>\n      <td>26.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>STON/O2. 3101282</td>\n      <td>7.9250</td>\n      <td>NaN</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>35.0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>113803</td>\n      <td>53.1000</td>\n      <td>C123</td>\n      <td>0</td>\n      <td>2</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5</td>\n      <td>0</td>\n      <td>3</td>\n      <td>1</td>\n      <td>35.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>373450</td>\n      <td>8.0500</td>\n      <td>NaN</td>\n      <td>0</td>\n      <td>0</td>\n      <td>2</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Fare\n# fill missing Fare data with mean value\ntest_data['Fare'].fillna(test_data.groupby('Pclass').transform('median')['Fare'], inplace=True)\n\nsns.heatmap(test_data.isnull(), yticklabels=False, cbar=False, cmap='viridis')","execution_count":1016,"outputs":[{"output_type":"execute_result","execution_count":1016,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fd51ad75350>"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 432x288 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"facet = sns.FacetGrid(train_data, hue='Survived', aspect=4)\nfacet.map(sns.kdeplot, 'Fare', shade=True)\nfacet.set(xlim=(0, train_data['Fare'].max()))\nfacet.add_legend()\n\nplt.show()","execution_count":1017,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 915.875x216 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"facet = sns.FacetGrid(train_data, hue='Survived', aspect=4)\nfacet.map(sns.kdeplot, 'Fare', shade=True)\nfacet.set(xlim=(0, train_data['Fare'].max()))\nfacet.add_legend()\nplt.xlim(0, 20)","execution_count":1018,"outputs":[{"output_type":"execute_result","execution_count":1018,"data":{"text/plain":"(0.0, 20.0)"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 915.875x216 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"facet = sns.FacetGrid(train_data, hue='Survived', aspect=4)\nfacet.map(sns.kdeplot, 'Fare', shade=True)\nfacet.set(xlim=(0, train_data['Fare'].max()))\nfacet.add_legend()\nplt.xlim(0, 30)","execution_count":1019,"outputs":[{"output_type":"execute_result","execution_count":1019,"data":{"text/plain":"(0.0, 30.0)"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 915.875x216 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"facet = sns.FacetGrid(train_data, hue='Survived', aspect=4)\nfacet.map(sns.kdeplot, 'Fare', shade=True)\nfacet.set(xlim=(0, train_data['Fare'].max()))\nfacet.add_legend()\nplt.xlim(30, 100)","execution_count":1020,"outputs":[{"output_type":"execute_result","execution_count":1020,"data":{"text/plain":"(30.0, 100.0)"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 915.875x216 with 1 Axes>","image/png":"iVBORw0KGgoAAAANSUhEUgAAA5AAAADQCAYAAABx/I7VAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjEsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+j8jraAAAgAElEQVR4nO3de3Rc1WH+/WefMzPS6GZZwpLwJQZfoLzGwfxaAiQGJwqKiYWDFjY/Ypq8b5O4tDSEFJKsQEhdcGInq0lZTbqyskJZJdAkbmsgNkE4cRFgUWhCmmKrIRAXiBpjLAl8k3WdmXP2+8eZqy7W2JY81vD9rOU157LPmX28dXtm732OsdZaAQAAAAAwAafQFQAAAAAATA8ESAAAAABAXgiQAAAAAIC8ECABAAAAAHkhQAIAAAAA8hIqdAXG4nm+Dh3qL3Q1MEkqKkrU1zdc6GpgktCexYX2LC60Z3GhPYsL7VlcZs2qLHQVCuaM7IE0xhS6CphEoZBb6CpgEtGexYX2LC60Z3GhPYsL7YlicUYGSAAAAADAmYcACQAAAADICwESAAAAAJAXAiQAAAAAIC8ESAAAAABAXgiQAAAAAIC8ECABAAAAAHkhQAIAAAAA8kKABAAAAADkhQAJAAAAAMgLARIAAAAAkBcCJAAAAAAgLwRIAAAAAEBeQvkUam9v16ZNm+T7vq6//nrddNNNOfuttdq0aZN27dql0tJSff3rX9eSJUskSY2NjSovL5fjOHJdV48++ujkXwUAAAAAYMpNGCA9z9PGjRv1wAMPqL6+XmvXrlVjY6MWLVqULtPe3q7Ozk7t3LlTe/bs0d13362tW7em9z/44IOqqamZmisAAAAAAJwWEw5h7ejo0Pz58zVv3jxFIhE1Nzerra0tp0xbW5taWlpkjNGyZcvU29urnp6eKas0AAAAAOD0m7AHsru7Ww0NDen1+vp6dXR0HLdMQ0ODuru7VVdXJ0n61Kc+JWOMbrjhBt1www0TVsoYqbq6LO+LwJnNdR3as4jQnsWF9iwutGdxoT2LC+2JYjFhgLTWjtpmjMm7zJYtW1RfX6+DBw/qE5/4hBYsWKBLLrlkgveUjhwZmKhqmCaqq8tozyJCexYX2rO40J7FhfYsLrRncZk1q7LQVSiYCYewNjQ0qKurK72e3bM4Xpmurq50mfr6eklSbW2tmpqaRvVeAgAAAACmhwkD5NKlS9XZ2al9+/YpFouptbVVjY2NOWUaGxu1bds2WWu1e/duVVZWqq6uTgMDA+rr65MkDQwM6LnnntPixYun5koAAAAAAFNqwiGsoVBIGzZs0Pr16+V5ntasWaPFixdry5YtkqR169ZpxYoV2rVrl5qamhSNRrV582ZJ0sGDB/XpT39aUnA312uuuUZXXnnlFF4OAAAAAGCqGDvWBMYC832rgwf7Cl0NTBLG/BcX2rO40J7FhfYsLrRncaE9iwtzIAEAAAAAmAABEgAAAACQFwIkAAAAACAvBEgAAAAAQF4IkAAAAACAvBAgAQAAAAB5IUACAAAAAPJCgAQAAAAA5IUACQAAAADICwESAAAAAJAXAiQAAAAAIC8ESAAAAABAXgiQAAAAAIC8ECABAAAAAHkhQAIAAAAA8kKABAAAAADkhQAJAAAAAMgLARIAAAAAkBcCJAAAAAAgLwRIAAAAAEBe8gqQ7e3tWrlypZqamnTfffeN2m+t1Ve/+lU1NTVp9erVeumll3L2e56nlpYW/dmf/dnk1BoAAAAAcNpNGCA9z9PGjRt1//33q7W1VY8//rheffXVnDLt7e3q7OzUzp079ZWvfEV33313zv6HHnpICxcunNSKAwAAAABOrwkDZEdHh+bPn6958+YpEomoublZbW1tOWXa2trU0tIiY4yWLVum3t5e9fT0SJK6urr0zDPPaO3atVNzBQAAAACA0yI0UYHu7m41NDSk1+vr69XR0XHcMg0NDeru7lZdXZ02b96sL3zhC+rv78+7UsZI1dVleZfHmc11HdqziNCexYX2LC60Z3GhPYsL7YliMWGAtNaO2maMyavM008/rZqaGl144YX6xS9+kXelrJWOHBnIuzzObNXVZbRnEaE9iwvtWVxoz+JCexYX2rO4zJpVWegqFMyEAbKhoUFdXV3p9VTP4vHKdHV1qa6uTj/72c/01FNPqb29XcPDw+rr69PnP/95ffOb35zESwAAAAAAnA4TzoFcunSpOjs7tW/fPsViMbW2tqqxsTGnTGNjo7Zt2yZrrXbv3q3KykrV1dXpc5/7nNrb2/XUU0/p3nvv1WWXXUZ4BAAAAIBpasIeyFAopA0bNmj9+vXyPE9r1qzR4sWLtWXLFknSunXrtGLFCu3atUtNTU2KRqPavHnzlFccAAAAAHB6GTvWBMYC832rgwf7Cl0NTBLG/BcX2rO40J7FhfYsLrRncaE9i8s7eQ7khENYAQAAAACQCJAAAAAAgDwRIAEAAAAAeSFAAgAAAADyQoAEAAAAAOSFAAkAAAAAyAsBEgAAAACQFwIkAAAAACAvBEgAAAAAQF4IkAAAAACAvBAgAQAAAAB5IUACAAAAAPJCgAQAAAAA5IUACQAAAADICwESAAAAAJAXAiQAAAAAIC8ESAAAAABAXgiQAAAAAIC8ECABAAAAAHkhQAIAAAAA8pJXgGxvb9fKlSvV1NSk++67b9R+a62++tWvqqmpSatXr9ZLL70kSRoeHtbatWv1kY98RM3Nzfr2t789ubUHAAAAAJw2oYkKeJ6njRs36oEHHlB9fb3Wrl2rxsZGLVq0KF2mvb1dnZ2d2rlzp/bs2aO7775bW7duVSQS0YMPPqjy8nLF43HdeOONuvLKK7Vs2bIpvSgAAAAAwOSbsAeyo6ND8+fP17x58xSJRNTc3Ky2tracMm1tbWppaZExRsuWLVNvb696enpkjFF5ebkkKZFIKJFIyBgzNVcCAAAAAJhSE/ZAdnd3q6GhIb1eX1+vjo6O45ZpaGhQd3e36urq5HmerrvuOv3+97/XjTfeqIsuumjCShkjVVeXnch14Azmug7tWURoz+JCexYX2rO40J7FhfZEsZgwQFprR20b2Yt4vDKu62r79u3q7e3Vpz/9ae3du1fnnXfeBO8pHTkyMFHVME1UV5fRnkWE9iwutGdxoT2LC+1ZXGjP4jJrVmWhq1AwEw5hbWhoUFdXV3o91bN4vDJdXV2jylRVVenSSy/Vs88+e6p1BgAAAIBp47vf/a6am5u1evVqXXvttdqzZ88pn7OtrW3MG5yejIsvvjjvshMGyKVLl6qzs1P79u1TLBZTa2urGhsbc8o0NjZq27ZtstZq9+7dqqysVF1dnQ4dOqTe3l5J0tDQkJ5//nktWLDgBC8HAAAAAKanF198Uc8884x+/OMf6yc/+YkeeOCBnOl/x5NIJMbd98EPflA33XTTZFUzbxMOYQ2FQtqwYYPWr18vz/O0Zs0aLV68WFu2bJEkrVu3TitWrNCuXbvU1NSkaDSqzZs3S5J6enp0xx13yPM8WWt19dVX6wMf+MDUXhEAAAAAnCHeeustzZw5U5FIRJJUU1MjKeiEe/jhh1VTU6P//u//1t/8zd/on/7pn/T3f//36unp0f79+zVz5kz9/ve/1+bNm7V48WJJ0sc//nF98Ytf1N69e/XrX/9at912m6699lo9+eSTchxHg4ODuvrqq/Xkk0/qwIEDuueee3T48GGVlpbqK1/5ihYuXKh9+/bp85//vBKJhK644ooTup4JA6QkrVixQitWrMjZtm7duvSyMUZ//dd/Peq4P/iDP9C2bdtOqEIAAAAAUCze97736Tvf+Y5Wrlypyy+/XKtWrdJ73vOe4x7z0ksv6Uc/+pFKS0v1/e9/Xzt27NDixYvV09Ojnp4eXXjhhdq7d68kqbKyUueff75eeOEFXXbZZXr66ae1fPlyhcNh/dVf/ZXuuecenXPOOdqzZ4/uuecePfTQQ9q0aZPWrVunlpYW/fCHPzyh65lwCCsAAAAA4OSUl5fr0Ucf1caNG1VTU6PbbrtNjz766HGPaWxsVGlpqSTpwx/+sH76059Kknbs2KGrr756VPlVq1bpiSeekCS1trZq1apV6u/v14svvqjPfvazuvbaa7Vhwwa99dZbkoJhtc3NzZKka6+99oSuJ68eSAAAAADAyXFdV5deeqkuvfRSnXfeedq2bZtc100/zWJ4eDinfDQaTS/X19erurpar7zyinbs2KF77rln1PkbGxt177336siRI3rppZd02WWXaXBwUFVVVdq+ffuYdRr5ZI180QMJAAAAAFPk9ddfV2dnZ3r95Zdf1uzZszVnzhz9+te/liTt3LnzuOdobm7W/fffr2PHjun8888ftb+8vFxLly7Vpk2b9P73v1+u66qiokJz587Vjh07JAWPXnzllVckBXddbW1tlSQ99thjJ3Q9BEgAAAAAmCIDAwO64447tGrVKq1evVqvvfaabrnlFt1yyy3avHmzbrzxRrmue9xzrFy5Uk888YQ+/OEPj1tm1apVeuyxx7Rq1ar0tm984xt6+OGH9ZGPfETNzc168sknJUl33XWXfvSjH2nNmjXq6+s7oesxNtVvegbxfauDB0/sQnDm4sG5xYX2LC60Z3GhPYsL7VlcaM/iMmtWZaGrUDD0QAIAAAAA8kKABAAAAADkhQAJAAAAAMgLARIAAAAAkBcCJAAAAAAgLwRIAAAAAEBeCJAAAAAAUOTa29u1cuVKNTU16b777jvp8xAgAQAAAKCIeZ6njRs36v7771dra6sef/xxvfrqqyd1LgIkAAAAABSxjo4OzZ8/X/PmzVMkElFzc7Pa2tpO6lyhSa4bAAAAAGAMj/zqDf3rf+6b1HP+3z+apzV/OPe4Zbq7u9XQ0JBer6+vV0dHx0m9Hz2QAAAAAFDErLWjthljTupc9EACAAAAwGmw5g/nTthbOBUaGhrU1dWVXu/u7lZdXd1JnYseSAAAAAAoYkuXLlVnZ6f27dunWCym1tZWNTY2ntS56IEEAAAAgCIWCoW0YcMGrV+/Xp7nac2aNVq8ePHJnWuS6wYAAAAAOMOsWLFCK1asOOXz5DWEdaKHTlpr9dWvflVNTU1avXq1XnrpJUnSgQMH9PGPf1wf/vCH1dzcrAcffPCUKwwAAAAAKIwJeyBTD5184IEHVF9fr7Vr16qxsVGLFi1Kl2lvb1dnZ6d27typPXv26O6779bWrVvluq7uuOMOLVmyRH19fVqzZo3e97735RwLAAAAAJgeJuyBzOehk21tbWppaZExRsuWLVNvb696enpUV1enJUuWSJIqKiq0YMECdXd3T82VAAAAAACm1IQBcqyHTo4MgSPLNDQ0jCrzxhtv6OWXX9ZFF110qnUGAAAAABTAhENY83no5ERl+vv7deutt+pLX/qSKioqJqyUMVJ1ddmE5TA9uK5DexYR2rO40J7FhfYsLrRncaE9USwmDJD5PHRyZJmurq50mXg8rltvvVWrV6/Whz70obwqZa105MhAXmVx5quuLqM9iwjtWVxoz+JCexYX2rO40J7FZdasykJXoWAmHMKaz0MnGxsbtW3bNllrtXv3blVWVqqurk7WWt11111asGCBPvGJT0zZRQAAAAAAxnbnnXfq8ssv1zXXXHPK55qwB3K8h05u2bJFkrRu3TqtWLFCu3btUlNTk6LRqDZv3ixJ+tWvfqXt27frvPPO07XXXitJuv322yfl+SMAAAAAgIldd911+tjHPqYvfvGLp3wuY8eawFhgvm918GBfoauBScKQjeJCexYX2rO40J7FhfYsLrRncZmOQ1jfeOMN/fmf/7kef/zxUzrPhD2QAAAAAIBJsHuL9OIPJvecF39MWrZucs95HBPOgQQAAAAAQKIHEgAAAABOj2XrTmtv4VSgBxIAAAAAkBcCJAAAAAAUsdtvv10f/ehH9bvf/U5XXnmltm7detLnYggrAAAAABSxe++9d9LORQ8kAAAAACAvBEgAAAAAQF4IkAAAAACAvBAgAQAAAAB5IUACAAAAAPJCgAQAAAAA5IUACQAAAADICwESAAAAAJAXAiQAAAAAIC9nZIA0w0flHn5N8uKFrgoAAAAAIClU6AqMxRz+nWp+9H5Z48qvepe8mQvlVS9QYsYCeTMXyKteIL+sXjKm0FUFAAAAgHeMMzJA2qq5GvjDW+T2HZDbf0Du4dcU3tcu48UyZcLl8qoXBOFyxjlBuKw+V96Mc2VLqwtYewAAAAAoTmdkgOyORfRieLmWLTaKhpK9jNaXGTwkt+9NOf1dcvsOyOk/oPD+nyvyP4/JWD99vF9aE4TJ6iBUJmYskDfjXHkzzpEi5YW5KAAAAACY5s7IAPnWgNXNz/hyjfT/1Eh/OMvo/9QZXXxWrSrrzpL07twDvLicgW45fV1yB7rl9B2Q29+lyP8+LeeVrTlF/fL6IExWL5RXfY4SM5JBs+pdUqj09F0kAAAAAEwzeQXI9vZ2bdq0Sb7v6/rrr9dNN92Us99aq02bNmnXrl0qLS3V17/+dS1ZskSSdOedd+qZZ55RbW2tHn/88bwqdW6V9KWLYnrlqKOXjzj6wW+Nvv+KkZF0/kzpj5KB8pI6o8qIkdyw/Mq58ivnKjHyZImhZI9ll5yB7mTPZZcir7XKGT6SuQYZ+ZWzk8Hy3GSP5bnBcuU8yQ3nVXcAAAAAKFYTBkjP87Rx40Y98MADqq+v19q1a9XY2KhFixaly7S3t6uzs1M7d+7Unj17dPfdd2vr1qDn77rrrtPHPvYxffGLX8y7Uo6RltX6WlYbDEuNedLeXke/PeLoN0cc/eurRj/Ya+QaadlZ0vLZjpafbbRohmRG3lgnVCp/xjnyZ5wz+o3iA+mhsG5/pucy3PUrmXh/uph1QvIr5wU38JlxbqbXcsa58itnS+aMvJktAAAAAEyqCQNkR0eH5s+fr3nz5kmSmpub1dbWlhMg29ra1NLSImOMli1bpt7eXvX09Kiurk6XXHKJ3njjjVOqZMSVLpzp68KZvtZIivvSq71Gew65evGgq2/t8fWtPVJ9VFp+ttH7ZhtdWm9UHp7gLq3hsuAmPDMXKueBIdbKxI6lA6XT3xXczOfI7xTe95yMN5Qp6pbImzFffvUCJVI9l6lwWVbHnWIBAAAAFI0JA2R3d7caGhrS6/X19ero6DhumYaGBnV3d6uurm4Sq5oRdqQLqq0uqE7oowsSOjQs7TnkavdBVzt+b/TI60YhI/2fWUbLZxstP9vo3KoxeifHY4xsSZW8kip5tefn7rNWZuhweihsEDAPyH37Nwp3tsn4mSga3Ck2EyoTqSGx1QtkS2dO4v8IAAAAAEy9CQOktXbUtpFBLJ8yJ8JIikYjeZefE5XmVEurFkhx3+qVw1a/6jH61dvSvbut7t0tzakwWjHP1fvnhXTZ2a7KJuqdPJ7KqDRrds4mK8nzPWngLZneA9KxN2WOHZBz7IDcnl9Jrz0hY71M+dJq2ZqFUs1C2ZoFsjULk+sLpJKqk6/bGch1HVVXlxW6GpgktGdxoT2LC+1ZXGjP4kJ7olhMGCAbGhrU1dWVXh+rZ3Fkma6urlPqfbSSBgdjE5Ybz6IyadE50g3nSG8PSbsPunrxkKtH9/r60csJRRzpj+qM3nd20EM5v3Iyh5lWS1XVUtUFuZv9hJz+nsx8y9SjSF5/Wu6v/zW3aLRWfuVceZVzgteK2fIq58qvnCOvcq5sSfW0GhpbXV2mI0cGCl0NTBLas7jQnsWF9iwutGdxoT2Ly6xZlYWuQsFMGCCXLl2qzs5O7du3T/X19WptbdXf/u3f5pRpbGzUD37wAzU3N2vPnj2qrKycsuGrJ+qsUumqOZ6umuMp7ksvH3G0+5CrFw86er7L6BsvSvMqpCtmO3rf2cEjQ0pDUxDOnJD8ytnyK2ePcafYYTn93Zn5lgPdMgNvK9TTIaezTcYbziluQ2XBHWPTIXOOvIrU61z55fXcNRYAAADApJswQIZCIW3YsEHr16+X53las2aNFi9erC1btkiS1q1bpxUrVmjXrl1qampSNBrV5s2b08fffvvteuGFF3T48GFdeeWV+sxnPqPrr79+6q7oOMKO9O4aX++u8fX/LpK6B412HwwC5cOvWv1or1GJK72nPpg3ufxsozkVp6GnL1Qif8a75M941+h9qRv6DL4tZ+BtOUMHg9fBt+Ue269Q9+6cx5FIkjWO/PIG+Vnh0qucIz/1WjlXNlIx9dcFAAAAoKgYO9YExgIbOHZEv/6PttP6njFPeumIoz2HXP3X2466BoPgeG6VdGm9o4tnScvOMqovOwOHjiaG5QweDELm4NuZ5YG35Qy8JTPwVs78S0nyS6qSz85M9lpWzpZXMVde5exge9msSXs8CUM2igvtWVxoz+JCexYX2rO40J7FhSGsUMSVLq71dXGtr/9vkXRg0Gj3QVe7Dzna9rrVP/9PEBxnl0sXn2V08SyjZbOMFlRJTqHnI4ZK0sNjx2R9maEjuQFz4C05gwflHvofhd94Pue5l5JknbD8itnyq0YGzFSv5mwpVHoaLg4AAADAmYIAOQZjpNllVrPLElo1T0r40v/2Gf32qKvfHnX0/AGj1v8NQmNVJOiZvHiW0bKzjJbUSBH3DOulNI5stEZetEaezhu7THwgPTR2ZC9m5OBemcGDMsrtrPajZwVhsmpuMDx2mt/sBwAAAMDxESDzEHKkhVVWC6uCQGltMH/ylaOOfpv81/5mEJQijrSkRrp4VhAqLzrLqCoyDUJUuGz8eZhScBfZwUMyWQHTHXw7uNlP9x45v3ty3Jv9mJnvUmVJnfxojWxpjbzSGtlorfzSmfKjtbLRGtlwBWETAAAAOMMRIE+CMVJDmVVDmaf3nx3MLeyNSa8cdbT3qKtXjho9+IrRP75sZCQtmiFdPMvRsrOCYHl2+TQMSk5IfnmdVF4nb6z9x7nZT6h3vyL9e2SGe2X8+Jint05YNlojv7QmeI3WBsulM+VFa2VLU9tmpsvJzf9ZoQAAAABOHQFyklRFpPfM8vWeWb4kadiTXu11tPeoo1eOOnq80+pfXw2CY0OZ0kNeL55ltLBKcp1pGCqzGSNbUiWvpEpe9YKcXRUVperrGwq6bhNDcmK9MrFjQaCM9cmJB8tO7FiwffCQQkf/N7mtd9y39CMV6WCZCpWpXk6/tFZ+diAtrZEtqZq0GwMBAAAA70QEyClS4kpLZvpaMjMIlL6Vft9ngiGvvY5e6HK0IzmPsiIczKO8sEY6p8ronCqj+ZVSdCqeR1lIxkjhqPxwVCqvz+8Y35OJ98kMH5OJ9coZPiYTTwbPdAg9Jvfo/yrU0yEzfFTGi415Kmtc2dKZQciMZgXM0kz49FO9ncl1bhQEAAAAZBAgTxPHSOdUWp1T6WmlPFkrvTVk9MpRo71HXb181NFzBySrTGhsKJPOrTI6t8ronErpnKogYM4qlcw7Zb6g48qWzJAtmSFJYw+fHSkxHITNrIDpxPsyy8ntoWP7k9t6Zaw/5qlsqEx+dKZs9Kxkb+bMTO9mpFI2VCYbLpNCUdlwsJzaFixHJbeE+Z0AAAAoCgTIAjFGqota1UWtrmwIwkvMk7oGjfYPGB0YcPTmgNGbA0YvvmU05GUCSHkoEybPrTTBcqXRvEqp5Ey7A2whhEpkQ7Pklc3Kr7z1ZeL9ub2csV6Z+Ihezr79MgdfDno5E4N5V8caRwqVyYajueEyXJbcngqd0czyuIE0d1mhUsIpAAAAThsC5Bkk4krvqrB6V4WVlOkRs1Y6HJP29ydD5WDw+kKXUWtnJjw4kmZXKKvHMhMwZ5a8g3otT5RxZCOVspFKSbPz6+X0YjKJQZnEsOQNySSGg7vQJoZl/OHk9mCb8YaT+4eC/d5wMBd04K1MucRQsD8+OOpxKcdjZZK9n9GcgKmRgXO8gDpGb6l1QpITlnXDkhOSdSKSG2xjDikAAMA7GwFyGjBGqimRakp8La2RsgdyDnnSgYHcXss3jjn6RZcU8zOBsSqidKg8p9JoVlSaFZXOihrVRaXKMAHzhLgRWTciWzLJ57VW8uMyiaFksAyC58hAmtmXvT6UCbFDh+X0HchsTwxJiSEZm1c8Hr96xpXckM4y2QEzHIRLNxk2U9vcSDqMyg1ngml6PZxcD0nZ53LDsiazPX1+JyzrhiQndd6QrBu83+jzhtKvckJBvR1HMqEgBPO1DgAAcFIIkNNcqSudW2l1bmVur6VvpbeHgiGwBwYcvTlotL/f6N/fNHpsePQfzyWuNKtUyWBpkv+UCZqlwXoFQXNqGZMOp5JOoC8yD9ZKfiLdA5oOn6nlxLBkE5Lvy9iE5HuSTcj4XnCc9STrKeJaxYdjyW2pcskyfiKzHO+XsV6wLXu770l+PLhBkk1IXiL5PonJvNrj/1cYRzKu5LiScUevJ18z25wgtJoRy2Psk+PKmlAysLpBgJUz7rnHf28nHX5tclnJsja1P/l+kiOber90GSe9LGOS75V1XGp5uFxuXyyr7iP2GycZwF1J2ecxOe9HKAcA4J2BAFmknKw5lstqc28QM+RJR4aNDg1Lh2NGR2JO8DosHRo2eumQ0aEhadAb/QdhqRsEyrpk72WwbHRWTviUysP8MXnGMSbooXPDUqTipMNpqKJUg31Dk1o1SUHAtV46kGYHz2DZywTNUWX8ZHhNBmA/Llk/KG/95HLwLwjCfvDs0vTyWPuPsy0Zgo0/nAzc4x8bbPeDa8t6NX52WS9TrgBqJuEcVmaCUJtZtlllguBsgpBtkudIn8skl01wTPZ7ZJdJlsspkzxu5Dltahj2qHM4yesYox4ysia7TrnvK+Mkr99k9o/xP5TXNptvudGbjKyckpAqhrM+jMn3fHnX5UTK5vlTJu9rzq+cGfNtx6uLkTXK/ZpR7tde5msw096Zr6/UsiQ5uWXS59Ko49JfZ9KIr+3c9zVlJSodTIw4r0bUccTXqBMOPuhJj8YIZY3UcDMjP0woOXIknPzwKjgudTwAjIcA+Q5U6koNZVYNZVLwS3XsP1oHE0HAPDxsdDgmHR52dCSWWjbqeDsIocNjBM2ykHRWVKqOSDVlgyp3fVWFjWZErKpKjKrCUpzzWAsAABXhSURBVFWJVBUxmhGRZkSkyogUnu7Pw8TJMyb4g8YJfixl/7k3qT2xZzJr8wy0vqTUus3abrO2+2Nst6O2l5a6GhqM5RxnssuljpMdFcZT5zMjzm1kR5Txxjg++z1s8pjgfY77mvrgQH7yCyP1apPXGZQ7/vmSP/NGvJqc9fGOD97PZP2/BPUaUUZj/SwbY9uYP/LyPXbsbaUjg9aYvcOnUr+xd9jTcX151uWEesRHtXd2+2bvl3K/7jL7T2Tu+omqnLIzj8/KZKYApAPoyDCatd1kT0UYI7Ca450rlBNercnsS09NcEuCOfpuiWyoJDlSpySzPZTaH0nO1+dvCWAqESAxrmhIioasZpelfjGODprWSoNeECgPDxsdiklHYo6OJENnX9zojV7pWMyqLy71J4yOFwfKQsF8zaqINCNikq+pbSZrnzSjxKgyLM0oCY5z+IWB6S41LFSZT/9PoV8nLyUVpYpPRY8yCqKiolR9tGdhpAKolPXhxDgfYmjkBxYas1x5WUT9/cNZoxMyH5hkzpX74YhJTyvw0lMP5KdGPiSnE1gvUy71QVVqNEfOSJCsKQqpD7OSo0Byz+3JxAfSx2SfIzg2eVzONIms80xmM8gEd2N3IsGrG0mGzNLkcmlOCE0H01QADaWCaUR+1v5UUE2fz43IuqW57+FmjqUXF8WMAIlTYkwQ3spCVnPKxw6a0WhEg4OxYI+V+hNBsEy99iWk/rhRf8KoL2HUH5f6EkZ9Mal7wKgvLh2LS3H/+AEx7ARzOUvcoJc1+7UkZDLLrlTqGpW4NrnNpLeXuFJpaGS5zLlCqdFvJvOZtxmxntqf3qfcD0NNVhkzYj17v1XwN4Gf/H9L/f/lLCvT+ZFeTu5LH5/cpzHOZRUMtjNGck0w9Nk1x1/3wlYDMTvmfubHAnjHMlk/0fO4Y3VeHwSVl8raoeIehZEejTAybHrpOfjyY0H49Ua8+vFgyoIfT26Py6TLxjP7s4+L98kMH5HxYsH+ZDl58eS22KRMJ0jfTM7NhFUnEtVME06G2RIpVCobKpXcEvmh0mA9GXYVKpV1ksE3XS57ORWKk4E4uRzMl+d3MaYWARKnlWOCO75WhlO/DvP/tRjzpL5U6EyGzIGEUV/caNgP7jo77ElxX4r5UswzyVdpIB7sT60PJ19jnuSPP0YLY+ofd49R0MZOVrhMLUecIISnAno0K9SXhqRSRyoNpYK9yQny0VD2BwJmxHpmP73QQP58a5Xwg5+Z2a+J5IdS2d/LI7+f0x8eKXc7HyLhhGWPvHAjZ8b0hdQ8dy95wzg/lgyn8cxrKnzaRDKEJsum9ycyITV1nOPLDidvXBfrywRWL56803oseD2Fm8pZ42QFzZLc5VA002uaFT6DbZnl1D5lrStnXyb8psrxmK93FgIkpo2IK9W4Uk3JiYfP8VgreVbpYJkdMmPJUBrzpJgNAqmXmgaTGqU0ohbZU4+Ss8aOW3bkL8rs41M9lKlpoUFPoc3p8UwvZ607yTtIjHl89rEmtx6pnspUL2ewzeT0YvpWckOuYnF/RLmRx5v0srXBg2cS6fBuFPekwbh0dChYzw71w56UsCf3R2jECcJkWUgqD0vlIaksbNLL5WGj8pBVWdgEZUJSWVa5inDmWIZFY6pZazXkSf1xaSCR/BeX+hNWA4lgHnp/PPmasBpIGMU9GwQ9qzHDn28GNBz3FbdZgdDPXU4k9/l24jqeqLE+RMoeweAod3vISGE3+N6NuFLEMSPWU6NLTLDs2mBfVrns8mEne9mkzxFxpRJHKgklX13JZc49xuMk75IdKpU0eUG2oqJU/fkMMbd+0Fua7iWNJXtR4+ntqdCaG3KDMmOVlxeTifXK8Q5KqfWc1+FTmss7Vo9rMCQ4NXQ4OeTXjQRB1UkNLS4Jbu7nZsr57sghxrnnTQ1RHj0UmTmwpwsBEu9oqT9gQk4QGEb/mijqgUMnJRp1NTg4tY/c8FK9yH5wk6bsUJ9aH/aDYc3ZwX/YMxrypaFEcBfhoYR0cFDa32c0mPwDfTCRf69zdETILM8Ko5mgabL2J7eHkuWyAmnEoXdmuov7VgPJsNef/FoaiNv08siwNxC3mbLJcgNZ5QYS+f+ECTvBkPuIE/y8co3kOlLYSK6x6W2RkFGZa+Um10MmWA4ly4eUOj5zjGuythnJdYIPqlIfBKU/RMr6YGnkh0ejP4Qacew4y56V4takQ+5QQuqLBd/TqW3ZYTjup6YznPrP5pCTCZM50xhcKZI1CiI1eqIkOfWhJLkcSZfNPi6Y+hANSdHU6IrkKz8DkDfjZIa36jT9JZJ81FcqsGZ6R0eG0VRwzbyarN7XnB5XP2t4cGJIjn9wxNDieLp3V15sUm5GZWUyj0MbJ8Sml0OluWF3ZFBN3iAq/UxrJ5R8HnXyJlKzPjoJ//HTEwESwBnHdaSoI0UlTXaot8ke50FPGkoYDXrBH/NDXrA85Jnk9tR6JowOxKVDg5ljBhNBD2pe12RyA+WokBkyKg/bMQNpap5uuifFzfSohN0gHPCHaS7Pt4r54/fuDWRvT1gNxI0GEpmQlw5/WeXieU6LMrKKJoND6rXUtSp3pdqIzYQK1yrqKjlsOwiI0dT2kNLbsudfTyR7znmxsjbTi5odKlPbMttNOnwG24IPmuKpkSbJ0RAxP2vqQ3JfX0w6PJQZhRL3s6Y+nGSANcoKlMlQmQmZJr0v2GYUDVlVRWMyvp/8usgOpCb99TXya42fBTgpyUd9yQ3LhstO/8fn6Ud5JbJ6VccYMpwaHjzmMOJge+q4zBzZrHN6gzKxY7nhNuc1GZbzcRkBEgDeEYzJ9DQocuqzbTw/FTKlwUQmhGbCaPA64JmgXCqsnmLvaLbUHNMSN3MzqVTQDEKmyQmdQRANtpWXDsvxPEVcE8xh04gbOo0cLi2NHkKd9X+bvV0jj0su+zbzR3vcy/yBH0sOzwz+sLfpP+rTr+k5zsl9yT/+U8Ojs8ufyPDMsGPTf8inAlxpSKotkeaWZUJcOvCFrEqTPYLRUG7wS/U0MTpy6hgT9LyGc0L1WA0+NX8C26xQmg6iI6Y+DKeG5fsmGDWRHqZvMsP1U8P3k72uw17muOHkh1e+PbEPA7JDaipcZgJpZj0TOs2oEBqUCQJtdvloKPg/J6BiSmQ9yuu09ryOJdUbO+JOxJn14A7CVYWq3xmAAAkAp8B1pHIn6C3M/Lo7uV974/WOjuxJiSeH98XSr8EwwMz+3H0DMeloVo9MzMs+l69Y6ja9BeYaq3ByiGY4OewynFp2guGYqX0lrhQOB+EvNZQzlDo2q1xpVu9eEPRyg9+J9O4BUvB3biT5gUy5pKmc+hAuiehofywIlsnh+0Ne7lD+dPBMhtPcIBosD8SkQ0NBYB3yUueY+O7mIzkmN1AeP4Qme0pD+R/DaAqcEVK9sQozsWkceQXI9vZ2bdq0Sb7v6/rrr9dNN92Us99aq02bNmnXrl0qLS3V17/+dS1ZsiSvYwEAgcnuHc1HNBpR/0AsuAFL8q2yb/iUfbOn7Bs9TVjWKv1g+ezjrIJekrBjs4Jh8EqvHZArNT9/9Bz9yfmZ4PmZHs/h5CiJIKRmwmgsK5wOpYJrVvlhXzo6LPUMmHTPaerVO8Ebohkp58ZHYSd3uH726InsGyZF0jdMsiPWR96kKXgN5vqa9Dzg1M+g1Nzi7PXs19RcYm6whne6CQOk53nauHGjHnjgAdXX12vt2rVqbGzUokWL0mXa29vV2dmpnTt3as+ePbr77ru1devWvI4FABSWk+xRmXx8VgucyVxHKhvzJnKT872bSPaYpkOpp5ze0iEvNaw3OdfUJkdKZM9lHbGtN5E1x9XXqH8nO0f1RKTuJDxewMzebrLKus6AjPXlOCZ9R+Jx71g8zp2Lg/0muT/5TOZxz2Uy53BGP3Zn1LOcJ9qf9V6p/weTs25y7g6fes50attY68o658ipEhOZrBifugnYyLvSj/X87OznbF85Se8/HU0YIDs6OjR//nzNmzdPktTc3Ky2tracENjW1qaWlhYZY7Rs2TL19vaqp6dH+/fvn/DYMSsVCqu2fu6pXBfOICUlIZUNT+1dO3H60J7FhfYsLrRncaE9T5xNP9/UJofr2+TNkjLrnh/caMtL3gnYs1aeb5QYtS1YTqSOUerYYH/CZpZztvvBMVbBtnTokFHC82UV3AjKt1bWN/KtzTwOK7k9d12yyfdOncuzVr6fWs49JvWIMj7Em1qdVxW6BoUzYYDs7u5WQ0NDer2+vl4dHR3HLdPQ0KDu7u68jh1LJFquhRddmtcFAAAAAABOjwlvHWDt6E8vRk5wHq9MPscCAAAAAKaHCXsgGxoa1NXVlV7v7u5WXV3dcct0dXWprq5O8Xh8wmMBAAAAANPDhD2QS5cuVWdnp/bt26dYLKbW1lY1NjbmlGlsbNS2bdtkrdXu3btVWVmpurq6vI4FAAAAAEwPE/ZAhkIhbdiwQevXr5fneVqzZo0WL16sLVu2SJLWrVunFStWaNeuXWpqalI0GtXmzZuPeywAAAAAYPoxdqyJigAAAAAAjDDhEFYAAAAAACQCJAAAAAAgTxPOgZxKw8PD+uM//mPFYjF5nqeVK1fq1ltv1ZEjR3Tbbbdp//79mjNnjv7u7/5OM2bMKGRVcQJS813r6+v1ve99j/acxhobG1VeXi7HceS6rh599FHacxrr7e3Vl7/8Ze3du1fGGG3evFnnnnsu7TkNvf7667rtttvS6/v27dOtt96qlpYW2nOa+v73v6+tW7fKGKPzzjtPX/va1zQ4OEh7TlMPPvigtm7dKmutrr/+ev3Jn/wJvz+nkTvvvFPPPPOMamtr9fjjj0vScdvve9/7nh5++GE5jqMvf/nLuuKKKwpZ/SlX0B7ISCSiBx98UI899pi2bdumZ599Vrt379Z9992nyy+/XDt37tTll1+u++67r5DVxAl66KGHtHDhwvQ67Tm9Pfjgg9q+fbseffRRSbTndLZp0yZdccUV+ulPf6rt27dr4cKFtOc0tWDBAm3fvj39vRmNRtXU1ER7TlPd3d166KGH9Mgjj+jxxx+X53lqbW2lPaepvXv3auvWrdq6dau2b9+uZ555Rp2dnbTnNHLdddfp/vvvz9k2Xvu9+uqram1tVWtrq+6//37dc8898jyvENU+bQoaII0xKi8vlyQlEgklEgkZY9TW1qaWlhZJUktLi5588slCVhMnoKurS88884zWrl2b3kZ7Fhfac3rq6+vTL3/5y/T3ZiQSUVVVFe1ZBP7jP/5D8+bN05w5c2jPaczzPA0NDSmRSGhoaEh1dXW05zT12muv6aKLLlI0GlUoFNIll1yif/u3f6M9p5FLLrlkVO/weO3X1tam5uZmRSIRzZs3T/Pnz1dHR8dpr/PpVPA5kJ7n6dprr9V73/tevfe979VFF12kgwcPqq6uTpJUV1enQ4cOFbiWyNfmzZv1hS98QY6T+dKiPae3T33qU7ruuuv0L//yL5Joz+lq3759qqmp0Z133qmWlhbdddddGhgYoD2LQGtrq6655hpJfH9OV/X19frkJz+pD3zgA1q+fLkqKiq0fPly2nOaOu+88/Sf//mfOnz4sAYHB9Xe3q6uri7ac5obr/26u7vV0NCQLldfX6/u7u6C1PF0KXiAdF1X27dv165du9TR0aG9e/cWuko4SU8//bRqamp04YUXFroqmCRbtmzRj3/8Y/3DP/yDfvjDH+qXv/xloauEk5RIJPSb3/xG69at07Zt2xSNRhk+VQRisZieeuopXX311YWuCk7B0aNH1dbWpra2Nj377LMaHBzU9u3bC10tnKSFCxdq/fr1+uQnP6n169fr/PPPl+u6ha4WpshYT0Q0xhSgJqdPwQNkSlVVlS699FI9++yzqq2tVU9PjySpp6dHNTU1Ba4d8vFf//Vfeuqpp9TY2Kjbb79dP//5z/X5z3+e9pzG6uvrJUm1tbVqampSR0cH7TlNNTQ0qKGhQRdddJEk6eqrr9ZvfvMb2nOaa29v15IlS3TWWWdJEu05TT3//POaO3euampqFA6H9aEPfUgvvvgi7TmNXX/99frxj3+sH/7wh6qurtb8+fNpz2luvPZraGhQV1dXulx3d3e6p7JYFTRAHjp0SL29vZKkoaEhPf/881qwYIEaGxu1bds2SdK2bdv0wQ9+sJDVRJ4+97nPqb29XU899ZTuvfdeXXbZZfrmN79Je05TAwMD6uvrSy8/99xzWrx4Me05Tc2aNUsNDQ16/fXXJQXz5hYuXEh7TnOtra1qbm5Or9Oe09Ps2bO1Z88eDQ4OylrL92cROHjwoCTpzTff1M6dO3XNNdfQntPceO3X2Nio1tZWxWIx7du3T52dnXr3u99dyKpOOWPH6nc9TV555RXdcccd8jxP1lpdffXVuuWWW3T48GH95V/+pQ4cOKCzzz5b3/rWt1RdXV2oauIk/OIXv9A//uM/6nvf+x7tOU3t27dPn/70pyUFc5WvueYa3XzzzbTnNPbyyy/rrrvuUjwe17x58/S1r31Nvu/TntPU4OCg3v/+9+vJJ59UZWWlJPH9OY19+9vf1hNPPKFQKKQLLrhAmzZtUn9/P+05Td144406cuSIQqGQ7rzzTl1++eV8f04jt99+u1544QUdPnxYtbW1+sxnPqOrrrpq3Pb77ne/q0ceeUSu6+pLX/qSVqxYUeArmFoFDZAAAAAAgOnjjJkDCQAAAAA4sxEgAQAAAAB5IUACAAAAAPJCgAQAAAAA5IUACQAAAADIS6jQFQAA4GRdcMEFOu+889Lr3/nOdzR37twC1ggAgOJGgAQATFulpaXavn37CR1jrZW1Vo7DIBwAAE4UARIAUDT6+/v1F3/xF+rt7VUikdBnP/tZXXXVVXrjjTf0p3/6p7r00ku1e/dufec739GOHTu0Y8cOxWIxNTU16dZbby109QEAOOMZa60tdCUAADgZ2UNY586dq29961saGhpSRUWFDh06pBtuuEE7d+7U/v37ddVVV+mf//mftWzZMv37v/+7fvazn2njxo2y1urmm2/W+vXrdckllxT4igAAOLPRAwkAmLZGDmGNx+O699579ctf/lKO46i7u1tvv/22JGn27NlatmyZJOm5557Tc889p5aWFknSwMCAOjs7CZAAAEyAAAkAKBo/+clPdOjQIT366KMKh8NqbGzU8PCwJKmsrCxdzlqrm266SR/96EcLVVUAAKYl7iAAACgax44dU21trcLhsH7+859r//79Y5Zbvny5HnnkEfX390uSuru7dfDgwdNZVQAApiV6IAEARWP16tW6+eabdd111+mCCy7QggULxiy3fPlyvfbaa+keyLKyMn3jG99QbW3t6awuAADTDjfRAQAAAADkhSGsAAAAAIC8ECABAAAAAHkhQAIAAAAA8kKABAAAAADkhQAJAAAAAMgLARIAAAAAkBcCJAAAAAAgL/8/TGrdDPtYUFUAAAAASUVORK5CYII=\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"facet = sns.FacetGrid(train_data, hue='Survived', aspect=4)\nfacet.map(sns.kdeplot, 'Fare', shade=True)\nfacet.set(xlim=(0, train_data['Fare'].max()))\nfacet.add_legend()\nplt.xlim(100, 600)","execution_count":1021,"outputs":[{"output_type":"execute_result","execution_count":1021,"data":{"text/plain":"(100.0, 600.0)"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 915.875x216 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Binning\n# child = 0, young = 1, adult = 2, mid-age = 3, older = 4\ntrain_data['FareGroup'] = pd.cut(train_data['Fare'], bins=[-1, 17, 30, 100, 1000], labels=False, precision=0)\ntest_data['FareGroup'] = pd.cut(test_data['Fare'], bins=[-1, 17, 30, 100, 1000], labels=False, precision=0)\nbar_chart('FareGroup')","execution_count":1022,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 720x360 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.drop(['Age', 'Fare'], axis=1, inplace=True)\ntest_data.drop(['Age', 'Fare'], axis=1, inplace=True)","execution_count":1024,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Preprocessing\n# Impute age column in train dataset with LinearRegression using other columns\n\"\"\"from sklearn.ensemble import RandomForestClassifier\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.linear_model import LinearRegression\n\n# replace age\ndef ageRegression(data):\n    age_data = data.drop([\"Ticket\", \"Cabin\"], axis=1)\n\n    test_age_data = age_data[age_data['Age'].isna()].drop(['Age'], axis=1)\n\n    train_age_data = age_data[~age_data['Age'].isna()]\n    train_age = train_age_data[\"Age\"]\n    train_age_data_no_age = train_age_data.drop(['Age'], axis=1)\n\n    # Run Model to find \n    model = LinearRegression()\n    model.fit(train_age_data_no_age, train_age)\n    \n    # update test part\n    test_age_data['Age'] = np.abs(np.ceil(model.predict(test_age_data)))\n    # merge with train part and return\n    out = pd.concat([train_age_data, test_age_data], axis=0)\n    out[\"Ticket\"] = data[\"Ticket\"]\n    out[\"Cabin\"] = data[\"Cabin\"]\n    return out\n\ntrain_data_new = ageRegression(train_data)\ntest_data_new = ageRegression(test_data)\n\ndisplay(train_data_new.head())\ndisplay(test_data_new.head())\n\nsns.heatmap(train_data_new.isnull(), yticklabels=False, cbar=False, cmap='viridis')\"\"\"","execution_count":967,"outputs":[{"output_type":"execute_result","execution_count":967,"data":{"text/plain":"'from sklearn.ensemble import RandomForestClassifier\\nfrom sklearn.linear_model import LogisticRegression\\nfrom sklearn.linear_model import LinearRegression\\n\\n# replace age\\ndef ageRegression(data):\\n    age_data = data.drop([\"Ticket\", \"Cabin\"], axis=1)\\n\\n    test_age_data = age_data[age_data[\\'Age\\'].isna()].drop([\\'Age\\'], axis=1)\\n\\n    train_age_data = age_data[~age_data[\\'Age\\'].isna()]\\n    train_age = train_age_data[\"Age\"]\\n    train_age_data_no_age = train_age_data.drop([\\'Age\\'], axis=1)\\n\\n    # Run Model to find \\n    model = LinearRegression()\\n    model.fit(train_age_data_no_age, train_age)\\n    \\n    # update test part\\n    test_age_data[\\'Age\\'] = np.abs(np.ceil(model.predict(test_age_data)))\\n    # merge with train part and return\\n    out = pd.concat([train_age_data, test_age_data], axis=0)\\n    out[\"Ticket\"] = data[\"Ticket\"]\\n    out[\"Cabin\"] = data[\"Cabin\"]\\n    return out\\n\\ntrain_data_new = ageRegression(train_data)\\ntest_data_new = ageRegression(test_data)\\n\\ndisplay(train_data_new.head())\\ndisplay(test_data_new.head())\\n\\nsns.heatmap(train_data_new.isnull(), yticklabels=False, cbar=False, cmap=\\'viridis\\')'"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"#!pip install datawig\n#import datawig","execution_count":968,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Feature Engineering\n# Use only first character of Cabin for simplicity\ntrain_data['Cabin'] = train_data['Cabin'].str[:1]\ntest_data['Cabin'] = test_data['Cabin'].str[:1]\n\ntrain_data.head()","execution_count":1025,"outputs":[{"output_type":"execute_result","execution_count":1025,"data":{"text/plain":"   PassengerId  Survived  Pclass  Sex  SibSp  Parch            Ticket Cabin  \\\n0            1         0       3    1      1      0         A/5 21171   NaN   \n1            2         1       1    0      1      0          PC 17599     C   \n2            3         1       3    0      0      0  STON/O2. 3101282   NaN   \n3            4         1       1    0      1      0            113803     C   \n4            5         0       3    1      0      0            373450   NaN   \n\n   Embarked  Title  AgeGroup  FareGroup  \n0         0      0         1          0  \n1         1      2         3          2  \n2         0      1         1          0  \n3         0      2         2          2  \n4         0      0         2          0  ","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>PassengerId</th>\n      <th>Survived</th>\n      <th>Pclass</th>\n      <th>Sex</th>\n      <th>SibSp</th>\n      <th>Parch</th>\n      <th>Ticket</th>\n      <th>Cabin</th>\n      <th>Embarked</th>\n      <th>Title</th>\n      <th>AgeGroup</th>\n      <th>FareGroup</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>0</td>\n      <td>3</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>A/5 21171</td>\n      <td>NaN</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>PC 17599</td>\n      <td>C</td>\n      <td>1</td>\n      <td>2</td>\n      <td>3</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>3</td>\n      <td>1</td>\n      <td>3</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>STON/O2. 3101282</td>\n      <td>NaN</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>113803</td>\n      <td>C</td>\n      <td>0</td>\n      <td>2</td>\n      <td>2</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5</td>\n      <td>0</td>\n      <td>3</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>373450</td>\n      <td>NaN</td>\n      <td>0</td>\n      <td>0</td>\n      <td>2</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"pc1 = train_data[train_data[\"Pclass\"] == 1][\"Cabin\"].value_counts()\npc2 = train_data[train_data[\"Pclass\"] == 2][\"Cabin\"].value_counts()\npc3 = train_data[train_data[\"Pclass\"] == 3][\"Cabin\"].value_counts()\ndf = pd.DataFrame([pc1, pc2, pc3])\ndf.index = ['1st class', '2nd class', '3rd class']\ndf.plot(kind ='bar', stacked=True, figsize=(10, 5))","execution_count":1026,"outputs":[{"output_type":"execute_result","execution_count":1026,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fd51954ca10>"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 720x360 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Feature Scaling\n# Ordinal encoding of Cabin data\ncabin_map = {\n    'A' : 0.0,\n    'B' : 0.4,\n    'C' : 0.8,\n    'D' : 1.2,\n    'E' : 1.6,\n    'F' : 2.0,\n    'G' : 2.4,\n    'T' : 2.8\n}\n\n# replace data\ntrain_data['Cabin'] = train_data['Cabin'].map(cabin_map)\ntest_data['Cabin'] = test_data['Cabin'].map(cabin_map)\n\ntrain_data.head()","execution_count":1027,"outputs":[{"output_type":"execute_result","execution_count":1027,"data":{"text/plain":"   PassengerId  Survived  Pclass  Sex  SibSp  Parch            Ticket  Cabin  \\\n0            1         0       3    1      1      0         A/5 21171    NaN   \n1            2         1       1    0      1      0          PC 17599    0.8   \n2            3         1       3    0      0      0  STON/O2. 3101282    NaN   \n3            4         1       1    0      1      0            113803    0.8   \n4            5         0       3    1      0      0            373450    NaN   \n\n   Embarked  Title  AgeGroup  FareGroup  \n0         0      0         1          0  \n1         1      2         3          2  \n2         0      1         1          0  \n3         0      2         2          2  \n4         0      0         2          0  ","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>PassengerId</th>\n      <th>Survived</th>\n      <th>Pclass</th>\n      <th>Sex</th>\n      <th>SibSp</th>\n      <th>Parch</th>\n      <th>Ticket</th>\n      <th>Cabin</th>\n      <th>Embarked</th>\n      <th>Title</th>\n      <th>AgeGroup</th>\n      <th>FareGroup</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>0</td>\n      <td>3</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>A/5 21171</td>\n      <td>NaN</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>PC 17599</td>\n      <td>0.8</td>\n      <td>1</td>\n      <td>2</td>\n      <td>3</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>3</td>\n      <td>1</td>\n      <td>3</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>STON/O2. 3101282</td>\n      <td>NaN</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>113803</td>\n      <td>0.8</td>\n      <td>0</td>\n      <td>2</td>\n      <td>2</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5</td>\n      <td>0</td>\n      <td>3</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>373450</td>\n      <td>NaN</td>\n      <td>0</td>\n      <td>0</td>\n      <td>2</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# fill missing Cabin data with mean value\ntrain_data['Cabin'].fillna(train_data.groupby('Pclass')['Cabin'].transform('median'), inplace=True)\ntest_data['Cabin'].fillna(test_data.groupby('Pclass')['Cabin'].transform('median'), inplace=True)\n\ntrain_data.head()","execution_count":1028,"outputs":[{"output_type":"execute_result","execution_count":1028,"data":{"text/plain":"   PassengerId  Survived  Pclass  Sex  SibSp  Parch            Ticket  Cabin  \\\n0            1         0       3    1      1      0         A/5 21171    2.0   \n1            2         1       1    0      1      0          PC 17599    0.8   \n2            3         1       3    0      0      0  STON/O2. 3101282    2.0   \n3            4         1       1    0      1      0            113803    0.8   \n4            5         0       3    1      0      0            373450    2.0   \n\n   Embarked  Title  AgeGroup  FareGroup  \n0         0      0         1          0  \n1         1      2         3          2  \n2         0      1         1          0  \n3         0      2         2          2  \n4         0      0         2          0  ","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>PassengerId</th>\n      <th>Survived</th>\n      <th>Pclass</th>\n      <th>Sex</th>\n      <th>SibSp</th>\n      <th>Parch</th>\n      <th>Ticket</th>\n      <th>Cabin</th>\n      <th>Embarked</th>\n      <th>Title</th>\n      <th>AgeGroup</th>\n      <th>FareGroup</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>0</td>\n      <td>3</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>A/5 21171</td>\n      <td>2.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>PC 17599</td>\n      <td>0.8</td>\n      <td>1</td>\n      <td>2</td>\n      <td>3</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>3</td>\n      <td>1</td>\n      <td>3</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>STON/O2. 3101282</td>\n      <td>2.0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>113803</td>\n      <td>0.8</td>\n      <td>0</td>\n      <td>2</td>\n      <td>2</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5</td>\n      <td>0</td>\n      <td>3</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>373450</td>\n      <td>2.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>2</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Preprocessing & Feature Engineering\n\n# add additional feature from: Parch & SibSp\ndef process_family(data):\n    data['Family'] = data['Parch'] + data['SibSp'] + 1 \n    return data\n\ntrain_data = process_family(train_data)\ntest_data = process_family(test_data)\n\ntrain_data.head()","execution_count":1029,"outputs":[{"output_type":"execute_result","execution_count":1029,"data":{"text/plain":"   PassengerId  Survived  Pclass  Sex  SibSp  Parch            Ticket  Cabin  \\\n0            1         0       3    1      1      0         A/5 21171    2.0   \n1            2         1       1    0      1      0          PC 17599    0.8   \n2            3         1       3    0      0      0  STON/O2. 3101282    2.0   \n3            4         1       1    0      1      0            113803    0.8   \n4            5         0       3    1      0      0            373450    2.0   \n\n   Embarked  Title  AgeGroup  FareGroup  Family  \n0         0      0         1          0       2  \n1         1      2         3          2       2  \n2         0      1         1          0       1  \n3         0      2         2          2       2  \n4         0      0         2          0       1  ","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>PassengerId</th>\n      <th>Survived</th>\n      <th>Pclass</th>\n      <th>Sex</th>\n      <th>SibSp</th>\n      <th>Parch</th>\n      <th>Ticket</th>\n      <th>Cabin</th>\n      <th>Embarked</th>\n      <th>Title</th>\n      <th>AgeGroup</th>\n      <th>FareGroup</th>\n      <th>Family</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>0</td>\n      <td>3</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>A/5 21171</td>\n      <td>2.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>PC 17599</td>\n      <td>0.8</td>\n      <td>1</td>\n      <td>2</td>\n      <td>3</td>\n      <td>2</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>3</td>\n      <td>1</td>\n      <td>3</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>STON/O2. 3101282</td>\n      <td>2.0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>113803</td>\n      <td>0.8</td>\n      <td>0</td>\n      <td>2</td>\n      <td>2</td>\n      <td>2</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5</td>\n      <td>0</td>\n      <td>3</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>373450</td>\n      <td>2.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>2</td>\n      <td>0</td>\n      <td>1</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"facet = sns.FacetGrid(train_data, hue='Survived', aspect=4)\nfacet.map(sns.kdeplot, 'Family', shade=True)\nfacet.set(xlim=(0, train_data['Family'].max()))\nfacet.add_legend()\n\nplt.show()","execution_count":1030,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 915.875x216 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Ordinal encoding of Family data\nfamily_map = { 1:0, 2:0.4, 3:0.8, 4:1.2, 5:1.6, 6:2, 7:2.4, 8:2.8, 9:3.2, 10:3.6, 11:4 }\n\n# replace data\ntrain_data['Family'] = train_data['Family'].map(family_map)\ntest_data['Family'] = test_data['Family'].map(family_map)\n\ntrain_data.head()","execution_count":1031,"outputs":[{"output_type":"execute_result","execution_count":1031,"data":{"text/plain":"   PassengerId  Survived  Pclass  Sex  SibSp  Parch            Ticket  Cabin  \\\n0            1         0       3    1      1      0         A/5 21171    2.0   \n1            2         1       1    0      1      0          PC 17599    0.8   \n2            3         1       3    0      0      0  STON/O2. 3101282    2.0   \n3            4         1       1    0      1      0            113803    0.8   \n4            5         0       3    1      0      0            373450    2.0   \n\n   Embarked  Title  AgeGroup  FareGroup  Family  \n0         0      0         1          0     0.4  \n1         1      2         3          2     0.4  \n2         0      1         1          0     0.0  \n3         0      2         2          2     0.4  \n4         0      0         2          0     0.0  ","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>PassengerId</th>\n      <th>Survived</th>\n      <th>Pclass</th>\n      <th>Sex</th>\n      <th>SibSp</th>\n      <th>Parch</th>\n      <th>Ticket</th>\n      <th>Cabin</th>\n      <th>Embarked</th>\n      <th>Title</th>\n      <th>AgeGroup</th>\n      <th>FareGroup</th>\n      <th>Family</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>0</td>\n      <td>3</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>A/5 21171</td>\n      <td>2.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0.4</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>PC 17599</td>\n      <td>0.8</td>\n      <td>1</td>\n      <td>2</td>\n      <td>3</td>\n      <td>2</td>\n      <td>0.4</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>3</td>\n      <td>1</td>\n      <td>3</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>STON/O2. 3101282</td>\n      <td>2.0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0.0</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>113803</td>\n      <td>0.8</td>\n      <td>0</td>\n      <td>2</td>\n      <td>2</td>\n      <td>2</td>\n      <td>0.4</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5</td>\n      <td>0</td>\n      <td>3</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>373450</td>\n      <td>2.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>2</td>\n      <td>0</td>\n      <td>0.0</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.drop(['Parch', 'SibSp'], axis=1, inplace=True)\ntest_data.drop(['Parch', 'SibSp'], axis=1, inplace=True)\n\ntrain_data.head()","execution_count":1032,"outputs":[{"output_type":"execute_result","execution_count":1032,"data":{"text/plain":"   PassengerId  Survived  Pclass  Sex            Ticket  Cabin  Embarked  \\\n0            1         0       3    1         A/5 21171    2.0         0   \n1            2         1       1    0          PC 17599    0.8         1   \n2            3         1       3    0  STON/O2. 3101282    2.0         0   \n3            4         1       1    0            113803    0.8         0   \n4            5         0       3    1            373450    2.0         0   \n\n   Title  AgeGroup  FareGroup  Family  \n0      0         1          0     0.4  \n1      2         3          2     0.4  \n2      1         1          0     0.0  \n3      2         2          2     0.4  \n4      0         2          0     0.0  ","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>PassengerId</th>\n      <th>Survived</th>\n      <th>Pclass</th>\n      <th>Sex</th>\n      <th>Ticket</th>\n      <th>Cabin</th>\n      <th>Embarked</th>\n      <th>Title</th>\n      <th>AgeGroup</th>\n      <th>FareGroup</th>\n      <th>Family</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>0</td>\n      <td>3</td>\n      <td>1</td>\n      <td>A/5 21171</td>\n      <td>2.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0.4</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>PC 17599</td>\n      <td>0.8</td>\n      <td>1</td>\n      <td>2</td>\n      <td>3</td>\n      <td>2</td>\n      <td>0.4</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>3</td>\n      <td>1</td>\n      <td>3</td>\n      <td>0</td>\n      <td>STON/O2. 3101282</td>\n      <td>2.0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0.0</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>113803</td>\n      <td>0.8</td>\n      <td>0</td>\n      <td>2</td>\n      <td>2</td>\n      <td>2</td>\n      <td>0.4</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5</td>\n      <td>0</td>\n      <td>3</td>\n      <td>1</td>\n      <td>373450</td>\n      <td>2.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>2</td>\n      <td>0</td>\n      <td>0.0</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"\"\"\"df_train, df_test = datawig.utils.random_split(train_data_new)\n\n# Initialize a SimpleImputer model\nimputer = datawig.SimpleImputer(\n    input_columns=['Survived','Pclass','Name','Age','SibSp','Parch','Fare','Sex_male','Embarked_Q','Embarked_S','Family'], # column(s) containing information about the column we want to impute\n    output_column= 'Cabin', # the column we'd like to impute values for\n    output_path = 'imputer_model' # stores model data and metrics\n    )\n\n# Fit an imputer model on the train data\nimputer.fit(train_df=df_train, num_epochs=10)\n\n# Impute missing train Cabin values and return original dataframe with predictions\nimputed_train = imputer.predict(train_data_new)\n\n# Impute missing test Cabin values\ndf_train, df_test = datawig.utils.random_split(test_data_new)\nimputer = datawig.SimpleImputer(\n    input_columns=['Pclass','Name','Age','SibSp','Parch','Fare','Sex_male','Embarked_Q','Embarked_S','Family'], # column(s) containing information about the column we want to impute\n    output_column= 'Cabin', # the column we'd like to impute values for\n    output_path = 'imputer_model' # stores model data and metrics\n    )\nimputer.fit(train_df=df_train, num_epochs=10)\nimputed_test = imputer.predict(test_data_new)\"\"\"","execution_count":977,"outputs":[{"output_type":"execute_result","execution_count":977,"data":{"text/plain":"\"df_train, df_test = datawig.utils.random_split(train_data_new)\\n\\n# Initialize a SimpleImputer model\\nimputer = datawig.SimpleImputer(\\n    input_columns=['Survived','Pclass','Name','Age','SibSp','Parch','Fare','Sex_male','Embarked_Q','Embarked_S','Family'], # column(s) containing information about the column we want to impute\\n    output_column= 'Cabin', # the column we'd like to impute values for\\n    output_path = 'imputer_model' # stores model data and metrics\\n    )\\n\\n# Fit an imputer model on the train data\\nimputer.fit(train_df=df_train, num_epochs=10)\\n\\n# Impute missing train Cabin values and return original dataframe with predictions\\nimputed_train = imputer.predict(train_data_new)\\n\\n# Impute missing test Cabin values\\ndf_train, df_test = datawig.utils.random_split(test_data_new)\\nimputer = datawig.SimpleImputer(\\n    input_columns=['Pclass','Name','Age','SibSp','Parch','Fare','Sex_male','Embarked_Q','Embarked_S','Family'], # column(s) containing information about the column we want to impute\\n    output_column= 'Cabin', # the column we'd like to impute values for\\n    output_path = 'imputer_model' # stores model data and metrics\\n    )\\nimputer.fit(train_df=df_train, num_epochs=10)\\nimputed_test = imputer.predict(test_data_new)\""},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"\"\"\"# Cabin imputation using deep learning (Datawig)\ntrain_data_new['Cabin'].fillna(imputed_train['Cabin_imputed'], inplace=True)\ntest_data_new['Cabin'].fillna(imputed_test['Cabin_imputed'], inplace=True)\"\"\"","execution_count":978,"outputs":[{"output_type":"execute_result","execution_count":978,"data":{"text/plain":"\"# Cabin imputation using deep learning (Datawig)\\ntrain_data_new['Cabin'].fillna(imputed_train['Cabin_imputed'], inplace=True)\\ntest_data_new['Cabin'].fillna(imputed_test['Cabin_imputed'], inplace=True)\""},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"\"\"\"# Preprocessing\n\n# Apply one hot encoding with k-1 columns\ntrain_data_Cabin = pd.get_dummies(train_data_new['Cabin'].str[0], drop_first=True, prefix='Cabin')\ntest_data_Cabin = pd.get_dummies(test_data_new['Cabin'].str[0], drop_first=True, prefix='Cabin')\n\n# Concat new columns to old datasets\ntrain_data_new = pd.concat([train_data_new.drop(['Cabin'], axis=1), train_data_Cabin], axis=1)\ntest_data_new = pd.concat([test_data_new.drop(['Cabin'], axis=1), test_data_Cabin], axis=1)\n\ndisplay(train_data_new.head())\n\ndisplay(test_data_new.head())\"\"\"","execution_count":979,"outputs":[{"output_type":"execute_result","execution_count":979,"data":{"text/plain":"\"# Preprocessing\\n\\n# Apply one hot encoding with k-1 columns\\ntrain_data_Cabin = pd.get_dummies(train_data_new['Cabin'].str[0], drop_first=True, prefix='Cabin')\\ntest_data_Cabin = pd.get_dummies(test_data_new['Cabin'].str[0], drop_first=True, prefix='Cabin')\\n\\n# Concat new columns to old datasets\\ntrain_data_new = pd.concat([train_data_new.drop(['Cabin'], axis=1), train_data_Cabin], axis=1)\\ntest_data_new = pd.concat([test_data_new.drop(['Cabin'], axis=1), test_data_Cabin], axis=1)\\n\\ndisplay(train_data_new.head())\\n\\ndisplay(test_data_new.head())\""},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"\"\"\"# Additional column to keep consistency\ntest_data_new['Cabin_T'] = 0\"\"\"","execution_count":980,"outputs":[{"output_type":"execute_result","execution_count":980,"data":{"text/plain":"\"# Additional column to keep consistency\\ntest_data_new['Cabin_T'] = 0\""},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Preprocessing\n# Tag passsengers having special ticket numbers\ntrain_data['Special'] = train_data['Ticket'].apply(lambda x: 0 if x.split(' ')[0].isnumeric() else 1 )\ntest_data['Special'] = train_data['Ticket'].apply(lambda x: 0 if x.split(' ')[0].isnumeric() else 1 )\n\nbar_chart('Special')","execution_count":1033,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 720x360 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Extract first two digits of ticket data (Replace LINE with 0)\ntrain_data['Ticket'] = train_data['Ticket'].apply(lambda x: x.split(' ')[len(x.split(' ')) - 1]).apply(lambda x: 0 if x == \"LINE\" else x).apply(lambda x: str(x)[:2]).apply(lambda x: float(x)/100)\ntest_data['Ticket'] = test_data['Ticket'].apply(lambda x: x.split(' ')[len(x.split(' ')) - 1]).apply(lambda x: str(x)[:2]).apply(lambda x: float(x)/100)\n\n#train_data[~train_data['Ticket'].apply(lambda x: str(x).isnumeric())]\ntrain_data.head()","execution_count":1034,"outputs":[{"output_type":"execute_result","execution_count":1034,"data":{"text/plain":"   PassengerId  Survived  Pclass  Sex  Ticket  Cabin  Embarked  Title  \\\n0            1         0       3    1    0.21    2.0         0      0   \n1            2         1       1    0    0.17    0.8         1      2   \n2            3         1       3    0    0.31    2.0         0      1   \n3            4         1       1    0    0.11    0.8         0      2   \n4            5         0       3    1    0.37    2.0         0      0   \n\n   AgeGroup  FareGroup  Family  Special  \n0         1          0     0.4        1  \n1         3          2     0.4        1  \n2         1          0     0.0        1  \n3         2          2     0.4        0  \n4         2          0     0.0        0  ","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>PassengerId</th>\n      <th>Survived</th>\n      <th>Pclass</th>\n      <th>Sex</th>\n      <th>Ticket</th>\n      <th>Cabin</th>\n      <th>Embarked</th>\n      <th>Title</th>\n      <th>AgeGroup</th>\n      <th>FareGroup</th>\n      <th>Family</th>\n      <th>Special</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>0</td>\n      <td>3</td>\n      <td>1</td>\n      <td>0.21</td>\n      <td>2.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0.4</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0.17</td>\n      <td>0.8</td>\n      <td>1</td>\n      <td>2</td>\n      <td>3</td>\n      <td>2</td>\n      <td>0.4</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>3</td>\n      <td>1</td>\n      <td>3</td>\n      <td>0</td>\n      <td>0.31</td>\n      <td>2.0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0.0</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0.11</td>\n      <td>0.8</td>\n      <td>0</td>\n      <td>2</td>\n      <td>2</td>\n      <td>2</td>\n      <td>0.4</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5</td>\n      <td>0</td>\n      <td>3</td>\n      <td>1</td>\n      <td>0.37</td>\n      <td>2.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>2</td>\n      <td>0</td>\n      <td>0.0</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"facet = sns.FacetGrid(train_data, hue='Survived', aspect=4)\nfacet.map(sns.kdeplot, 'Ticket', shade=True)\nfacet.set(xlim=(0, train_data['Ticket'].max()))\nfacet.add_legend()\n\nplt.show()","execution_count":1035,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 915.875x216 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# binning\ntrain_data['TicketGroup'] = pd.cut(train_data['Ticket'], bins=[-1, 0.42, 0.84, 1], labels=False, precision=0)\ntest_data['TicketGroup'] = pd.cut(test_data['Ticket'], bins=[-1, 0.42, 0.84, 1], labels=False, precision=0)\n\nbar_chart('TicketGroup')","execution_count":1036,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 720x360 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"passengerId = test_data['PassengerId']","execution_count":1039,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.drop(['Ticket', 'PassengerId'], axis=1, inplace=True)\ntest_data.drop(['Ticket', 'PassengerId'], axis=1, inplace=True)\n\ntrain_data.head()","execution_count":1040,"outputs":[{"output_type":"execute_result","execution_count":1040,"data":{"text/plain":"   Survived  Pclass  Sex  Cabin  Embarked  Title  AgeGroup  FareGroup  Family  \\\n0         0       3    1    2.0         0      0         1          0     0.4   \n1         1       1    0    0.8         1      2         3          2     0.4   \n2         1       3    0    2.0         0      1         1          0     0.0   \n3         1       1    0    0.8         0      2         2          2     0.4   \n4         0       3    1    2.0         0      0         2          0     0.0   \n\n   Special  TicketGroup  \n0        1            0  \n1        1            0  \n2        1            0  \n3        0            0  \n4        0            0  ","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>Survived</th>\n      <th>Pclass</th>\n      <th>Sex</th>\n      <th>Cabin</th>\n      <th>Embarked</th>\n      <th>Title</th>\n      <th>AgeGroup</th>\n      <th>FareGroup</th>\n      <th>Family</th>\n      <th>Special</th>\n      <th>TicketGroup</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>0</td>\n      <td>3</td>\n      <td>1</td>\n      <td>2.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0.4</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0.8</td>\n      <td>1</td>\n      <td>2</td>\n      <td>3</td>\n      <td>2</td>\n      <td>0.4</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>1</td>\n      <td>3</td>\n      <td>0</td>\n      <td>2.0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0.0</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0.8</td>\n      <td>0</td>\n      <td>2</td>\n      <td>2</td>\n      <td>2</td>\n      <td>0.4</td>\n      <td>0</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>0</td>\n      <td>3</td>\n      <td>1</td>\n      <td>2.0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>2</td>\n      <td>0</td>\n      <td>0.0</td>\n      <td>0</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.info()","execution_count":1041,"outputs":[{"output_type":"stream","text":"<class 'pandas.core.frame.DataFrame'>\nRangeIndex: 891 entries, 0 to 890\nData columns (total 11 columns):\n #   Column       Non-Null Count  Dtype  \n---  ------       --------------  -----  \n 0   Survived     891 non-null    int64  \n 1   Pclass       891 non-null    int64  \n 2   Sex          891 non-null    int64  \n 3   Cabin        891 non-null    float64\n 4   Embarked     891 non-null    int64  \n 5   Title        891 non-null    int64  \n 6   AgeGroup     891 non-null    int64  \n 7   FareGroup    891 non-null    int64  \n 8   Family       891 non-null    float64\n 9   Special      891 non-null    int64  \n 10  TicketGroup  891 non-null    int64  \ndtypes: float64(2), int64(9)\nmemory usage: 76.7 KB\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# install packages uninstalled during datawig install\n\"\"\"!pip install 'scikit-learn==0.22.2.post1'\n!pip install 'typing==3.7.4.1'\n!pip install 'pandas==1.0.3'\n!pip install 'mxnet==1.6.0'\"\"\"\n","execution_count":459,"outputs":[{"output_type":"execute_result","execution_count":459,"data":{"text/plain":"\"!pip install 'scikit-learn==0.22.2.post1'\\n!pip install 'typing==3.7.4.1'\\n!pip install 'pandas==1.0.3'\\n!pip install 'mxnet==1.6.0'\""},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.neighbors import KNeighborsClassifier\nfrom sklearn.tree import DecisionTreeClassifier\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.naive_bayes import GaussianNB\nfrom sklearn.svm import SVC\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.ensemble import GradientBoostingClassifier","execution_count":1047,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# **Cross Validation (K-fold)**"},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import KFold\nfrom sklearn.model_selection import cross_val_score\nk_fold = KFold(n_splits=10, shuffle=True, random_state=0)","execution_count":1052,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Logistic Regression"},{"metadata":{"trusted":true},"cell_type":"code","source":"# LogisticRegression\nclf = LogisticRegression(max_iter=1000)\nscoring = 'accuracy'\nscore = cross_val_score(clf, X_train, y_train, cv=k_fold, n_jobs=1, scoring=scoring)\nprint(score)\n\n# LogisticRegression Score\nprint(round(np.mean(score)*100, 2))","execution_count":1063,"outputs":[{"output_type":"stream","text":"[0.8        0.78651685 0.79775281 0.78651685 0.80898876 0.82022472\n 0.82022472 0.84269663 0.82022472 0.85393258]\n81.37\n","name":"stdout"}]},{"metadata":{},"cell_type":"markdown","source":"# kNN"},{"metadata":{"trusted":true},"cell_type":"code","source":"# kNN\nclf = KNeighborsClassifier(n_neighbors = 13)\nscoring = 'accuracy'\nscore = cross_val_score(clf, X_train, y_train, cv=k_fold, n_jobs=1, scoring=scoring)\nprint(score)\n\n# kNN Score\nprint(round(np.mean(score)*100, 2))","execution_count":1057,"outputs":[{"output_type":"stream","text":"[0.81111111 0.76404494 0.84269663 0.83146067 0.83146067 0.83146067\n 0.80898876 0.76404494 0.83146067 0.83146067]\n81.48\n","name":"stdout"}]},{"metadata":{},"cell_type":"markdown","source":"# Decision Tree"},{"metadata":{"trusted":true},"cell_type":"code","source":"# DecisionTreeClassifier\nclf = DecisionTreeClassifier()\nscoring = 'accuracy'\nscore = cross_val_score(clf, X_train, y_train, cv=k_fold, n_jobs=1, scoring=scoring)\nprint(score)\n\n# DecisionTreeClassifier Score\nprint(round(np.mean(score)*100, 2))","execution_count":1058,"outputs":[{"output_type":"stream","text":"[0.82222222 0.82022472 0.78651685 0.76404494 0.83146067 0.7752809\n 0.85393258 0.82022472 0.73033708 0.82022472]\n80.24\n","name":"stdout"}]},{"metadata":{},"cell_type":"markdown","source":"# Random Forest"},{"metadata":{"trusted":true},"cell_type":"code","source":"# RandomForestClassifier\nclf = RandomForestClassifier(n_estimators=13)\nscoring = 'accuracy'\nscore = cross_val_score(clf, X_train, y_train, cv=k_fold, n_jobs=1, scoring=scoring)\nprint(score)\n\n# RandomForestClassifier Score\nprint(round(np.mean(score)*100, 2))","execution_count":1059,"outputs":[{"output_type":"stream","text":"[0.83333333 0.80898876 0.84269663 0.78651685 0.85393258 0.79775281\n 0.85393258 0.80898876 0.76404494 0.82022472]\n81.7\n","name":"stdout"}]},{"metadata":{},"cell_type":"markdown","source":"# Gradient Boosting"},{"metadata":{"trusted":true},"cell_type":"code","source":"# GradientBoostingClassifier\nclf = GradientBoostingClassifier(learning_rate = 0.1, \n                    max_depth = 2,\n                    min_samples_split = 10,\n                    n_estimators = 200,\n                    subsample = 0.6)\nscoring = 'accuracy'\nscore = cross_val_score(clf, X_train, y_train, cv=k_fold, n_jobs=1, scoring=scoring)\nprint(score)\n\n# GradientBoostingClassifier Score\nprint(round(np.mean(score)*100, 2))","execution_count":1060,"outputs":[{"output_type":"stream","text":"[0.86666667 0.87640449 0.83146067 0.80898876 0.83146067 0.83146067\n 0.82022472 0.82022472 0.80898876 0.85393258]\n83.5\n","name":"stdout"}]},{"metadata":{},"cell_type":"markdown","source":"# Naive Bayes"},{"metadata":{"trusted":true},"cell_type":"code","source":"# GaussianNB\nclf = GaussianNB()\nscoring = 'accuracy'\nscore = cross_val_score(clf, X_train, y_train, cv=k_fold, n_jobs=1, scoring=scoring)\nprint(score)\n\n# GaussianNB Score\nprint(round(np.mean(score)*100, 2))","execution_count":1061,"outputs":[{"output_type":"stream","text":"[0.86666667 0.75280899 0.75280899 0.75280899 0.71910112 0.82022472\n 0.76404494 0.78651685 0.86516854 0.84269663]\n79.23\n","name":"stdout"}]},{"metadata":{},"cell_type":"markdown","source":"# SVM"},{"metadata":{"trusted":true},"cell_type":"code","source":"# SVC\nclf = SVC()\nscoring = 'accuracy'\nscore = cross_val_score(clf, X_train, y_train, cv=k_fold, n_jobs=1, scoring=scoring)\nprint(score)\n\n# GaussianNB Score\nprint(round(np.mean(score)*100, 2))","execution_count":1062,"outputs":[{"output_type":"stream","text":"[0.83333333 0.79775281 0.80898876 0.82022472 0.84269663 0.82022472\n 0.84269663 0.84269663 0.84269663 0.85393258]\n83.05\n","name":"stdout"}]},{"metadata":{},"cell_type":"markdown","source":"# Testing"},{"metadata":{"trusted":true},"cell_type":"code","source":"clf = SVC()\nclf.fit(X_train, y_train)\npredictions = clf.predict(X_test)","execution_count":1068,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"output = pd.DataFrame({'PassengerId': passengerId, 'Survived': predictions})\noutput.to_csv('submission_svm.csv', index=False)\nprint(\"Submission data successfully saved!\")\n\nprint(\"Train accuracy: {}\".format(round(model.score(X_train, y_train), 4)))\n\noutput.head()","execution_count":1069,"outputs":[{"output_type":"stream","text":"Submission data successfully saved!\nTrain accuracy: 0.8204\n","name":"stdout"},{"output_type":"execute_result","execution_count":1069,"data":{"text/plain":"   PassengerId  Survived\n0          892         0\n1          893         1\n2          894         0\n3          895         0\n4          896         1","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>PassengerId</th>\n      <th>Survived</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>892</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>893</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>894</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>895</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>896</td>\n      <td>1</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}
\ No newline at end of file