customer churn(xgboost and random forest) this is better then the neural network you used.ipynb

{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"authorship_tag":"ABX9TyOS63F4W8gfE1PRdXSXAYmQ"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"}},"cells":[{"cell_type":"code","execution_count":2,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":206},"id":"O7Z2qshyRerM","executionInfo":{"status":"ok","timestamp":1723628845692,"user_tz":-330,"elapsed":470,"user":{"displayName":"Abhiram Vanama","userId":"15150483264437415347"}},"outputId":"0208455e-514b-4af7-ec96-af2b658d4fb5"},"outputs":[{"output_type":"execute_result","data":{"text/plain":["   RowNumber  CustomerId   Surname  CreditScore Geography  Gender  Age  \\\n","0          1    15634602  Hargrave          619    France  Female   42   \n","1          2    15647311      Hill          608     Spain  Female   41   \n","2          3    15619304      Onio          502    France  Female   42   \n","3          4    15701354      Boni          699    France  Female   39   \n","4          5    15737888  Mitchell          850     Spain  Female   43   \n","\n","   Tenure    Balance  NumOfProducts  HasCrCard  IsActiveMember  \\\n","0       2       0.00              1          1               1   \n","1       1   83807.86              1          0               1   \n","2       8  159660.80              3          1               0   \n","3       1       0.00              2          0               0   \n","4       2  125510.82              1          1               1   \n","\n","   EstimatedSalary  Exited  \n","0        101348.88       1  \n","1        112542.58       0  \n","2        113931.57       1  \n","3         93826.63       0  \n","4         79084.10       0  "],"text/html":["\n","  <div id=\"df-36922067-8891-4552-8c18-3a3313d87d61\" class=\"colab-df-container\">\n","    <div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>RowNumber</th>\n","      <th>CustomerId</th>\n","      <th>Surname</th>\n","      <th>CreditScore</th>\n","      <th>Geography</th>\n","      <th>Gender</th>\n","      <th>Age</th>\n","      <th>Tenure</th>\n","      <th>Balance</th>\n","      <th>NumOfProducts</th>\n","      <th>HasCrCard</th>\n","      <th>IsActiveMember</th>\n","      <th>EstimatedSalary</th>\n","      <th>Exited</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>1</td>\n","      <td>15634602</td>\n","      <td>Hargrave</td>\n","      <td>619</td>\n","      <td>France</td>\n","      <td>Female</td>\n","      <td>42</td>\n","      <td>2</td>\n","      <td>0.00</td>\n","      <td>1</td>\n","      <td>1</td>\n","      <td>1</td>\n","      <td>101348.88</td>\n","      <td>1</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>2</td>\n","      <td>15647311</td>\n","      <td>Hill</td>\n","      <td>608</td>\n","      <td>Spain</td>\n","      <td>Female</td>\n","      <td>41</td>\n","      <td>1</td>\n","      <td>83807.86</td>\n","      <td>1</td>\n","      <td>0</td>\n","      <td>1</td>\n","      <td>112542.58</td>\n","      <td>0</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>3</td>\n","      <td>15619304</td>\n","      <td>Onio</td>\n","      <td>502</td>\n","      <td>France</td>\n","      <td>Female</td>\n","      <td>42</td>\n","      <td>8</td>\n","      <td>159660.80</td>\n","      <td>3</td>\n","      <td>1</td>\n","      <td>0</td>\n","      <td>113931.57</td>\n","      <td>1</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>4</td>\n","      <td>15701354</td>\n","      <td>Boni</td>\n","      <td>699</td>\n","      <td>France</td>\n","      <td>Female</td>\n","      <td>39</td>\n","      <td>1</td>\n","      <td>0.00</td>\n","      <td>2</td>\n","      <td>0</td>\n","      <td>0</td>\n","      <td>93826.63</td>\n","      <td>0</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>5</td>\n","      <td>15737888</td>\n","      <td>Mitchell</td>\n","      <td>850</td>\n","      <td>Spain</td>\n","      <td>Female</td>\n","      <td>43</td>\n","      <td>2</td>\n","      <td>125510.82</td>\n","      <td>1</td>\n","      <td>1</td>\n","      <td>1</td>\n","      <td>79084.10</td>\n","      <td>0</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>\n","    <div class=\"colab-df-buttons\">\n","\n","  <div class=\"colab-df-container\">\n","    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-36922067-8891-4552-8c18-3a3313d87d61')\"\n","            title=\"Convert this dataframe to an interactive table.\"\n","            style=\"display:none;\">\n","\n","  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n","    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n","  </svg>\n","    </button>\n","\n","  <style>\n","    .colab-df-container {\n","      display:flex;\n","      gap: 12px;\n","    }\n","\n","    .colab-df-convert {\n","      background-color: #E8F0FE;\n","      border: none;\n","      border-radius: 50%;\n","      cursor: pointer;\n","      display: none;\n","      fill: #1967D2;\n","      height: 32px;\n","      padding: 0 0 0 0;\n","      width: 32px;\n","    }\n","\n","    .colab-df-convert:hover {\n","      background-color: #E2EBFA;\n","      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n","      fill: #174EA6;\n","    }\n","\n","    .colab-df-buttons div {\n","      margin-bottom: 4px;\n","    }\n","\n","    [theme=dark] .colab-df-convert {\n","      background-color: #3B4455;\n","      fill: #D2E3FC;\n","    }\n","\n","    [theme=dark] .colab-df-convert:hover {\n","      background-color: #434B5C;\n","      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n","      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n","      fill: #FFFFFF;\n","    }\n","  </style>\n","\n","    <script>\n","      const buttonEl =\n","        document.querySelector('#df-36922067-8891-4552-8c18-3a3313d87d61 button.colab-df-convert');\n","      buttonEl.style.display =\n","        google.colab.kernel.accessAllowed ? 'block' : 'none';\n","\n","      async function convertToInteractive(key) {\n","        const element = document.querySelector('#df-36922067-8891-4552-8c18-3a3313d87d61');\n","        const dataTable =\n","          await google.colab.kernel.invokeFunction('convertToInteractive',\n","                                                    [key], {});\n","        if (!dataTable) return;\n","\n","        const docLinkHtml = 'Like what you see? Visit the ' +\n","          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n","          + ' to learn more about interactive tables.';\n","        element.innerHTML = '';\n","        dataTable['output_type'] = 'display_data';\n","        await google.colab.output.renderOutput(dataTable, element);\n","        const docLink = document.createElement('div');\n","        docLink.innerHTML = docLinkHtml;\n","        element.appendChild(docLink);\n","      }\n","    </script>\n","  </div>\n","\n","\n","<div id=\"df-24efc1da-966d-4689-8e2a-62512c346c37\">\n","  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-24efc1da-966d-4689-8e2a-62512c346c37')\"\n","            title=\"Suggest charts\"\n","            style=\"display:none;\">\n","\n","<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n","     width=\"24px\">\n","    <g>\n","        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n","    </g>\n","</svg>\n","  </button>\n","\n","<style>\n","  .colab-df-quickchart {\n","      --bg-color: #E8F0FE;\n","      --fill-color: #1967D2;\n","      --hover-bg-color: #E2EBFA;\n","      --hover-fill-color: #174EA6;\n","      --disabled-fill-color: #AAA;\n","      --disabled-bg-color: #DDD;\n","  }\n","\n","  [theme=dark] .colab-df-quickchart {\n","      --bg-color: #3B4455;\n","      --fill-color: #D2E3FC;\n","      --hover-bg-color: #434B5C;\n","      --hover-fill-color: #FFFFFF;\n","      --disabled-bg-color: #3B4455;\n","      --disabled-fill-color: #666;\n","  }\n","\n","  .colab-df-quickchart {\n","    background-color: var(--bg-color);\n","    border: none;\n","    border-radius: 50%;\n","    cursor: pointer;\n","    display: none;\n","    fill: var(--fill-color);\n","    height: 32px;\n","    padding: 0;\n","    width: 32px;\n","  }\n","\n","  .colab-df-quickchart:hover {\n","    background-color: var(--hover-bg-color);\n","    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n","    fill: var(--button-hover-fill-color);\n","  }\n","\n","  .colab-df-quickchart-complete:disabled,\n","  .colab-df-quickchart-complete:disabled:hover {\n","    background-color: var(--disabled-bg-color);\n","    fill: var(--disabled-fill-color);\n","    box-shadow: none;\n","  }\n","\n","  .colab-df-spinner {\n","    border: 2px solid var(--fill-color);\n","    border-color: transparent;\n","    border-bottom-color: var(--fill-color);\n","    animation:\n","      spin 1s steps(1) infinite;\n","  }\n","\n","  @keyframes spin {\n","    0% {\n","      border-color: transparent;\n","      border-bottom-color: var(--fill-color);\n","      border-left-color: var(--fill-color);\n","    }\n","    20% {\n","      border-color: transparent;\n","      border-left-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","    }\n","    30% {\n","      border-color: transparent;\n","      border-left-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","      border-right-color: var(--fill-color);\n","    }\n","    40% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","    }\n","    60% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","    }\n","    80% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","      border-bottom-color: var(--fill-color);\n","    }\n","    90% {\n","      border-color: transparent;\n","      border-bottom-color: var(--fill-color);\n","    }\n","  }\n","</style>\n","\n","  <script>\n","    async function quickchart(key) {\n","      const quickchartButtonEl =\n","        document.querySelector('#' + key + ' button');\n","      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n","      quickchartButtonEl.classList.add('colab-df-spinner');\n","      try {\n","        const charts = await google.colab.kernel.invokeFunction(\n","            'suggestCharts', [key], {});\n","      } catch (error) {\n","        console.error('Error during call to suggestCharts:', error);\n","      }\n","      quickchartButtonEl.classList.remove('colab-df-spinner');\n","      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n","    }\n","    (() => {\n","      let quickchartButtonEl =\n","        document.querySelector('#df-24efc1da-966d-4689-8e2a-62512c346c37 button');\n","      quickchartButtonEl.style.display =\n","        google.colab.kernel.accessAllowed ? 'block' : 'none';\n","    })();\n","  </script>\n","</div>\n","\n","    </div>\n","  </div>\n"],"application/vnd.google.colaboratory.intrinsic+json":{"type":"dataframe","variable_name":"df","summary":"{\n  \"name\": \"df\",\n  \"rows\": 10000,\n  \"fields\": [\n    {\n      \"column\": \"RowNumber\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2886,\n        \"min\": 1,\n        \"max\": 10000,\n        \"num_unique_values\": 10000,\n        \"samples\": [\n          6253,\n          4685,\n          1732\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"CustomerId\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 71936,\n        \"min\": 15565701,\n        \"max\": 15815690,\n        \"num_unique_values\": 10000,\n        \"samples\": [\n          15687492,\n          15736963,\n          15721730\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Surname\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 2932,\n        \"samples\": [\n          \"McGuirk\",\n          \"Torkelson\",\n          \"Rapuluchukwu\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"CreditScore\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 96,\n        \"min\": 350,\n        \"max\": 850,\n        \"num_unique_values\": 460,\n        \"samples\": [\n          754,\n          533,\n          744\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Geography\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 3,\n        \"samples\": [\n          \"France\",\n          \"Spain\",\n          \"Germany\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Gender\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          \"Male\",\n          \"Female\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Age\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 10,\n        \"min\": 18,\n        \"max\": 92,\n        \"num_unique_values\": 70,\n        \"samples\": [\n          61,\n          42\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Tenure\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2,\n        \"min\": 0,\n        \"max\": 10,\n        \"num_unique_values\": 11,\n        \"samples\": [\n          6,\n          2\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Balance\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 62397.405202385955,\n        \"min\": 0.0,\n        \"max\": 250898.09,\n        \"num_unique_values\": 6382,\n        \"samples\": [\n          117707.18,\n          133050.97\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"NumOfProducts\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 1,\n        \"max\": 4,\n        \"num_unique_values\": 4,\n        \"samples\": [\n          3,\n          4\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"HasCrCard\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 1,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0,\n          1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"IsActiveMember\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 1,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0,\n          1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"EstimatedSalary\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 57510.49281769816,\n        \"min\": 11.58,\n        \"max\": 199992.48,\n        \"num_unique_values\": 9999,\n        \"samples\": [\n          100809.99,\n          95273.73\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Exited\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 1,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0,\n          1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"}},"metadata":{},"execution_count":2}],"source":["import pandas as pd\n","\n","# Load the dataset\n","df = pd.read_csv('/content/Churn_Modelling.csv')\n","\n","# Display the first few rows of the dataset to understand its structure\n","df.head()\n"]},{"cell_type":"code","source":["# One-hot encode the categorical variables\n","df = pd.get_dummies(df, columns=['Geography', 'Gender'], drop_first=True)\n","\n","# Drop unnecessary columns\n","X = df.drop(columns=['RowNumber', 'CustomerId', 'Surname', 'Exited'])\n","y = df['Exited']\n","\n","df.head()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":226},"id":"8JQXsRtXSQCK","executionInfo":{"status":"ok","timestamp":1723628866260,"user_tz":-330,"elapsed":479,"user":{"displayName":"Abhiram Vanama","userId":"15150483264437415347"}},"outputId":"89c094fa-65d3-475e-b844-cfec2316cc03"},"execution_count":3,"outputs":[{"output_type":"execute_result","data":{"text/plain":["   RowNumber  CustomerId   Surname  CreditScore  Age  Tenure    Balance  \\\n","0          1    15634602  Hargrave          619   42       2       0.00   \n","1          2    15647311      Hill          608   41       1   83807.86   \n","2          3    15619304      Onio          502   42       8  159660.80   \n","3          4    15701354      Boni          699   39       1       0.00   \n","4          5    15737888  Mitchell          850   43       2  125510.82   \n","\n","   NumOfProducts  HasCrCard  IsActiveMember  EstimatedSalary  Exited  \\\n","0              1          1               1        101348.88       1   \n","1              1          0               1        112542.58       0   \n","2              3          1               0        113931.57       1   \n","3              2          0               0         93826.63       0   \n","4              1          1               1         79084.10       0   \n","\n","   Geography_Germany  Geography_Spain  Gender_Male  \n","0              False            False        False  \n","1              False             True        False  \n","2              False            False        False  \n","3              False            False        False  \n","4              False             True        False  "],"text/html":["\n","  <div id=\"df-891f4a38-4882-4f32-a030-2f739063a962\" class=\"colab-df-container\">\n","    <div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>RowNumber</th>\n","      <th>CustomerId</th>\n","      <th>Surname</th>\n","      <th>CreditScore</th>\n","      <th>Age</th>\n","      <th>Tenure</th>\n","      <th>Balance</th>\n","      <th>NumOfProducts</th>\n","      <th>HasCrCard</th>\n","      <th>IsActiveMember</th>\n","      <th>EstimatedSalary</th>\n","      <th>Exited</th>\n","      <th>Geography_Germany</th>\n","      <th>Geography_Spain</th>\n","      <th>Gender_Male</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>1</td>\n","      <td>15634602</td>\n","      <td>Hargrave</td>\n","      <td>619</td>\n","      <td>42</td>\n","      <td>2</td>\n","      <td>0.00</td>\n","      <td>1</td>\n","      <td>1</td>\n","      <td>1</td>\n","      <td>101348.88</td>\n","      <td>1</td>\n","      <td>False</td>\n","      <td>False</td>\n","      <td>False</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>2</td>\n","      <td>15647311</td>\n","      <td>Hill</td>\n","      <td>608</td>\n","      <td>41</td>\n","      <td>1</td>\n","      <td>83807.86</td>\n","      <td>1</td>\n","      <td>0</td>\n","      <td>1</td>\n","      <td>112542.58</td>\n","      <td>0</td>\n","      <td>False</td>\n","      <td>True</td>\n","      <td>False</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>3</td>\n","      <td>15619304</td>\n","      <td>Onio</td>\n","      <td>502</td>\n","      <td>42</td>\n","      <td>8</td>\n","      <td>159660.80</td>\n","      <td>3</td>\n","      <td>1</td>\n","      <td>0</td>\n","      <td>113931.57</td>\n","      <td>1</td>\n","      <td>False</td>\n","      <td>False</td>\n","      <td>False</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>4</td>\n","      <td>15701354</td>\n","      <td>Boni</td>\n","      <td>699</td>\n","      <td>39</td>\n","      <td>1</td>\n","      <td>0.00</td>\n","      <td>2</td>\n","      <td>0</td>\n","      <td>0</td>\n","      <td>93826.63</td>\n","      <td>0</td>\n","      <td>False</td>\n","      <td>False</td>\n","      <td>False</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>5</td>\n","      <td>15737888</td>\n","      <td>Mitchell</td>\n","      <td>850</td>\n","      <td>43</td>\n","      <td>2</td>\n","      <td>125510.82</td>\n","      <td>1</td>\n","      <td>1</td>\n","      <td>1</td>\n","      <td>79084.10</td>\n","      <td>0</td>\n","      <td>False</td>\n","      <td>True</td>\n","      <td>False</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>\n","    <div class=\"colab-df-buttons\">\n","\n","  <div class=\"colab-df-container\">\n","    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-891f4a38-4882-4f32-a030-2f739063a962')\"\n","            title=\"Convert this dataframe to an interactive table.\"\n","            style=\"display:none;\">\n","\n","  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n","    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n","  </svg>\n","    </button>\n","\n","  <style>\n","    .colab-df-container {\n","      display:flex;\n","      gap: 12px;\n","    }\n","\n","    .colab-df-convert {\n","      background-color: #E8F0FE;\n","      border: none;\n","      border-radius: 50%;\n","      cursor: pointer;\n","      display: none;\n","      fill: #1967D2;\n","      height: 32px;\n","      padding: 0 0 0 0;\n","      width: 32px;\n","    }\n","\n","    .colab-df-convert:hover {\n","      background-color: #E2EBFA;\n","      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n","      fill: #174EA6;\n","    }\n","\n","    .colab-df-buttons div {\n","      margin-bottom: 4px;\n","    }\n","\n","    [theme=dark] .colab-df-convert {\n","      background-color: #3B4455;\n","      fill: #D2E3FC;\n","    }\n","\n","    [theme=dark] .colab-df-convert:hover {\n","      background-color: #434B5C;\n","      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n","      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n","      fill: #FFFFFF;\n","    }\n","  </style>\n","\n","    <script>\n","      const buttonEl =\n","        document.querySelector('#df-891f4a38-4882-4f32-a030-2f739063a962 button.colab-df-convert');\n","      buttonEl.style.display =\n","        google.colab.kernel.accessAllowed ? 'block' : 'none';\n","\n","      async function convertToInteractive(key) {\n","        const element = document.querySelector('#df-891f4a38-4882-4f32-a030-2f739063a962');\n","        const dataTable =\n","          await google.colab.kernel.invokeFunction('convertToInteractive',\n","                                                    [key], {});\n","        if (!dataTable) return;\n","\n","        const docLinkHtml = 'Like what you see? Visit the ' +\n","          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n","          + ' to learn more about interactive tables.';\n","        element.innerHTML = '';\n","        dataTable['output_type'] = 'display_data';\n","        await google.colab.output.renderOutput(dataTable, element);\n","        const docLink = document.createElement('div');\n","        docLink.innerHTML = docLinkHtml;\n","        element.appendChild(docLink);\n","      }\n","    </script>\n","  </div>\n","\n","\n","<div id=\"df-3b8d2f54-b519-4533-a1a2-e338c37ec564\">\n","  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-3b8d2f54-b519-4533-a1a2-e338c37ec564')\"\n","            title=\"Suggest charts\"\n","            style=\"display:none;\">\n","\n","<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n","     width=\"24px\">\n","    <g>\n","        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n","    </g>\n","</svg>\n","  </button>\n","\n","<style>\n","  .colab-df-quickchart {\n","      --bg-color: #E8F0FE;\n","      --fill-color: #1967D2;\n","      --hover-bg-color: #E2EBFA;\n","      --hover-fill-color: #174EA6;\n","      --disabled-fill-color: #AAA;\n","      --disabled-bg-color: #DDD;\n","  }\n","\n","  [theme=dark] .colab-df-quickchart {\n","      --bg-color: #3B4455;\n","      --fill-color: #D2E3FC;\n","      --hover-bg-color: #434B5C;\n","      --hover-fill-color: #FFFFFF;\n","      --disabled-bg-color: #3B4455;\n","      --disabled-fill-color: #666;\n","  }\n","\n","  .colab-df-quickchart {\n","    background-color: var(--bg-color);\n","    border: none;\n","    border-radius: 50%;\n","    cursor: pointer;\n","    display: none;\n","    fill: var(--fill-color);\n","    height: 32px;\n","    padding: 0;\n","    width: 32px;\n","  }\n","\n","  .colab-df-quickchart:hover {\n","    background-color: var(--hover-bg-color);\n","    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n","    fill: var(--button-hover-fill-color);\n","  }\n","\n","  .colab-df-quickchart-complete:disabled,\n","  .colab-df-quickchart-complete:disabled:hover {\n","    background-color: var(--disabled-bg-color);\n","    fill: var(--disabled-fill-color);\n","    box-shadow: none;\n","  }\n","\n","  .colab-df-spinner {\n","    border: 2px solid var(--fill-color);\n","    border-color: transparent;\n","    border-bottom-color: var(--fill-color);\n","    animation:\n","      spin 1s steps(1) infinite;\n","  }\n","\n","  @keyframes spin {\n","    0% {\n","      border-color: transparent;\n","      border-bottom-color: var(--fill-color);\n","      border-left-color: var(--fill-color);\n","    }\n","    20% {\n","      border-color: transparent;\n","      border-left-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","    }\n","    30% {\n","      border-color: transparent;\n","      border-left-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","      border-right-color: var(--fill-color);\n","    }\n","    40% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","    }\n","    60% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","    }\n","    80% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","      border-bottom-color: var(--fill-color);\n","    }\n","    90% {\n","      border-color: transparent;\n","      border-bottom-color: var(--fill-color);\n","    }\n","  }\n","</style>\n","\n","  <script>\n","    async function quickchart(key) {\n","      const quickchartButtonEl =\n","        document.querySelector('#' + key + ' button');\n","      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n","      quickchartButtonEl.classList.add('colab-df-spinner');\n","      try {\n","        const charts = await google.colab.kernel.invokeFunction(\n","            'suggestCharts', [key], {});\n","      } catch (error) {\n","        console.error('Error during call to suggestCharts:', error);\n","      }\n","      quickchartButtonEl.classList.remove('colab-df-spinner');\n","      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n","    }\n","    (() => {\n","      let quickchartButtonEl =\n","        document.querySelector('#df-3b8d2f54-b519-4533-a1a2-e338c37ec564 button');\n","      quickchartButtonEl.style.display =\n","        google.colab.kernel.accessAllowed ? 'block' : 'none';\n","    })();\n","  </script>\n","</div>\n","\n","    </div>\n","  </div>\n"],"application/vnd.google.colaboratory.intrinsic+json":{"type":"dataframe","variable_name":"df","summary":"{\n  \"name\": \"df\",\n  \"rows\": 10000,\n  \"fields\": [\n    {\n      \"column\": \"RowNumber\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2886,\n        \"min\": 1,\n        \"max\": 10000,\n        \"num_unique_values\": 10000,\n        \"samples\": [\n          6253,\n          4685,\n          1732\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"CustomerId\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 71936,\n        \"min\": 15565701,\n        \"max\": 15815690,\n        \"num_unique_values\": 10000,\n        \"samples\": [\n          15687492,\n          15736963,\n          15721730\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Surname\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 2932,\n        \"samples\": [\n          \"McGuirk\",\n          \"Torkelson\",\n          \"Rapuluchukwu\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"CreditScore\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 96,\n        \"min\": 350,\n        \"max\": 850,\n        \"num_unique_values\": 460,\n        \"samples\": [\n          754,\n          533,\n          744\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Age\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 10,\n        \"min\": 18,\n        \"max\": 92,\n        \"num_unique_values\": 70,\n        \"samples\": [\n          61,\n          42,\n          59\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Tenure\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2,\n        \"min\": 0,\n        \"max\": 10,\n        \"num_unique_values\": 11,\n        \"samples\": [\n          6,\n          2,\n          9\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Balance\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 62397.405202385955,\n        \"min\": 0.0,\n        \"max\": 250898.09,\n        \"num_unique_values\": 6382,\n        \"samples\": [\n          117707.18,\n          133050.97,\n          124271.26\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"NumOfProducts\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 1,\n        \"max\": 4,\n        \"num_unique_values\": 4,\n        \"samples\": [\n          3,\n          4,\n          1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"HasCrCard\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 1,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0,\n          1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"IsActiveMember\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 1,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0,\n          1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"EstimatedSalary\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 57510.49281769816,\n        \"min\": 11.58,\n        \"max\": 199992.48,\n        \"num_unique_values\": 9999,\n        \"samples\": [\n          100809.99,\n          95273.73\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Exited\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 1,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0,\n          1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Geography_Germany\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Geography_Spain\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Gender_Male\",\n      \"properties\": {\n        \"dtype\": \"boolean\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          true,\n          false\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"}},"metadata":{},"execution_count":3}]},{"cell_type":"code","source":["from sklearn.preprocessing import StandardScaler\n","from sklearn.model_selection import train_test_split\n","\n","# Initialize the scaler\n","scaler = StandardScaler()\n","\n","# Fit the scaler on the training data and transform both training and test data\n","X_scaled = scaler.fit_transform(X)\n","\n","# Split the data into training and testing sets\n","X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)\n"],"metadata":{"id":"mA24rSZlSMUr","executionInfo":{"status":"ok","timestamp":1723628881057,"user_tz":-330,"elapsed":1642,"user":{"displayName":"Abhiram Vanama","userId":"15150483264437415347"}}},"execution_count":4,"outputs":[]},{"cell_type":"code","source":["from sklearn.ensemble import RandomForestClassifier\n","from sklearn.metrics import accuracy_score\n","\n","# Initialize and train the Random Forest model\n","rf_model = RandomForestClassifier(n_estimators=100, random_state=42)\n","rf_model.fit(X_train, y_train)\n","\n","# Predict on the training and testing sets\n","rf_train_preds = rf_model.predict(X_train)\n","rf_test_preds = rf_model.predict(X_test)\n","\n","# Calculate training and testing accuracy\n","rf_train_accuracy = accuracy_score(y_train, rf_train_preds)\n","rf_test_accuracy = accuracy_score(y_test, rf_test_preds)\n","\n","print(f\"Random Forest Training Accuracy: {rf_train_accuracy:.4f}\")\n","print(f\"Random Forest Testing Accuracy: {rf_test_accuracy:.4f}\")\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"c2v74ZrmSYxe","executionInfo":{"status":"ok","timestamp":1723628894406,"user_tz":-330,"elapsed":4173,"user":{"displayName":"Abhiram Vanama","userId":"15150483264437415347"}},"outputId":"8b2d521f-addf-4459-c28d-70b9853d4f42"},"execution_count":5,"outputs":[{"output_type":"stream","name":"stdout","text":["Random Forest Training Accuracy: 1.0000\n","Random Forest Testing Accuracy: 0.8670\n"]}]},{"cell_type":"code","source":["from xgboost import XGBClassifier\n","\n","# Initialize and train the XGBoost model\n","xgb_model = XGBClassifier(use_label_encoder=False, eval_metric='logloss', random_state=42)\n","xgb_model.fit(X_train, y_train)\n","\n","# Predict on the training and testing sets\n","xgb_train_preds = xgb_model.predict(X_train)\n","xgb_test_preds = xgb_model.predict(X_test)\n","\n","# Calculate training and testing accuracy\n","xgb_train_accuracy = accuracy_score(y_train, xgb_train_preds)\n","xgb_test_accuracy = accuracy_score(y_test, xgb_test_preds)\n","\n","print(f\"XGBoost Training Accuracy: {xgb_train_accuracy:.4f}\")\n","print(f\"XGBoost Testing Accuracy: {xgb_test_accuracy:.4f}\")\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"eXnrCaUySeNw","executionInfo":{"status":"ok","timestamp":1723628920291,"user_tz":-330,"elapsed":1136,"user":{"displayName":"Abhiram Vanama","userId":"15150483264437415347"}},"outputId":"dec6756b-1ecd-4ca2-fe33-b46eb88dfa03"},"execution_count":6,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.10/dist-packages/xgboost/core.py:158: UserWarning: [09:48:39] WARNING: /workspace/src/learner.cc:740: \n","Parameters: { \"use_label_encoder\" } are not used.\n","\n","  warnings.warn(smsg, UserWarning)\n"]},{"output_type":"stream","name":"stdout","text":["XGBoost Training Accuracy: 0.9585\n","XGBoost Testing Accuracy: 0.8640\n"]}]},{"cell_type":"code","source":["\n","###even if you tune your hyper parameters manually it still shows the same\n","\n","\n","from xgboost import XGBClassifier\n","\n","# Initialize and train the XGBoost model with regularization and early stopping\n","xgb_model1 = XGBClassifier(use_label_encoder=False, eval_metric='logloss', random_state=42,\n","                          reg_lambda=2.0, reg_alpha=1.0, max_depth=2, min_child_weight=10,\n","                          subsample=0.8, colsample_bytree=0.8, learning_rate=0.01, n_estimators=500)\n","\n","xgb_model1.fit(X_train, y_train, eval_set=[(X_test, y_test)], verbose=True)\n","\n","\n","\n","\n","\n","# Predict on the training and testing sets\n","xgb_train_preds1 = xgb_model.predict(X_train)\n","xgb_test_preds1 = xgb_model.predict(X_test)\n","\n","# Calculate training and testing accuracy\n","xgb_train_accuracy = accuracy_score(y_train, xgb_train_preds1)\n","xgb_test_accuracy = accuracy_score(y_test, xgb_test_preds1)\n","\n","print(f\"XGBoost Training Accuracy: {xgb_train_accuracy:.4f}\")\n","print(f\"XGBoost Testing Accuracy: {xgb_test_accuracy:.4f}\")\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"collapsed":true,"id":"moqSurULSjPP","executionInfo":{"status":"ok","timestamp":1723629602908,"user_tz":-330,"elapsed":3613,"user":{"displayName":"Abhiram Vanama","userId":"15150483264437415347"}},"outputId":"3301e26a-1ca4-4f66-efdc-0149843bb752"},"execution_count":10,"outputs":[{"output_type":"stream","name":"stdout","text":["[0]\tvalidation_0-logloss:0.49801\n","[1]\tvalidation_0-logloss:0.49672\n","[2]\tvalidation_0-logloss:0.49542\n","[3]\tvalidation_0-logloss:0.49415\n","[4]\tvalidation_0-logloss:0.49228\n","[5]\tvalidation_0-logloss:0.49076\n","[6]\tvalidation_0-logloss:0.48905\n","[7]\tvalidation_0-logloss:0.48740\n","[8]\tvalidation_0-logloss:0.48622\n","[9]\tvalidation_0-logloss:0.48468\n","[10]\tvalidation_0-logloss:0.48307\n","[11]\tvalidation_0-logloss:0.48170\n","[12]\tvalidation_0-logloss:0.48018\n","[13]\tvalidation_0-logloss:0.47868\n","[14]\tvalidation_0-logloss:0.47762\n","[15]\tvalidation_0-logloss:0.47658\n","[16]\tvalidation_0-logloss:0.47530\n","[17]\tvalidation_0-logloss:0.47400\n","[18]\tvalidation_0-logloss:0.47277\n","[19]\tvalidation_0-logloss:0.47160\n","[20]\tvalidation_0-logloss:0.47060\n","[21]\tvalidation_0-logloss:0.46938\n","[22]\tvalidation_0-logloss:0.46820\n","[23]\tvalidation_0-logloss:0.46726\n","[24]\tvalidation_0-logloss:0.46597\n","[25]\tvalidation_0-logloss:0.46484\n","[26]\tvalidation_0-logloss:0.46392\n","[27]\tvalidation_0-logloss:0.46276\n","[28]\tvalidation_0-logloss:0.46186\n","[29]\tvalidation_0-logloss:0.46098\n","[30]\tvalidation_0-logloss:0.46013\n","[31]\tvalidation_0-logloss:0.45929\n","[32]\tvalidation_0-logloss:0.45845\n","[33]\tvalidation_0-logloss:0.45737\n","[34]\tvalidation_0-logloss:0.45623\n","[35]\tvalidation_0-logloss:0.45517\n","[36]\tvalidation_0-logloss:0.45438\n","[37]\tvalidation_0-logloss:0.45336\n","[38]\tvalidation_0-logloss:0.45227\n","[39]\tvalidation_0-logloss:0.45143\n","[40]\tvalidation_0-logloss:0.45039\n","[41]\tvalidation_0-logloss:0.44995\n"]},{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.10/dist-packages/xgboost/core.py:158: UserWarning: [09:59:59] WARNING: /workspace/src/learner.cc:740: \n","Parameters: { \"use_label_encoder\" } are not used.\n","\n","  warnings.warn(smsg, UserWarning)\n"]},{"output_type":"stream","name":"stdout","text":["[42]\tvalidation_0-logloss:0.44893\n","[43]\tvalidation_0-logloss:0.44790\n","[44]\tvalidation_0-logloss:0.44690\n","[45]\tvalidation_0-logloss:0.44647\n","[46]\tvalidation_0-logloss:0.44561\n","[47]\tvalidation_0-logloss:0.44518\n","[48]\tvalidation_0-logloss:0.44429\n","[49]\tvalidation_0-logloss:0.44333\n","[50]\tvalidation_0-logloss:0.44256\n","[51]\tvalidation_0-logloss:0.44167\n","[52]\tvalidation_0-logloss:0.44095\n","[53]\tvalidation_0-logloss:0.44025\n","[54]\tvalidation_0-logloss:0.43935\n","[55]\tvalidation_0-logloss:0.43850\n","[56]\tvalidation_0-logloss:0.43783\n","[57]\tvalidation_0-logloss:0.43716\n","[58]\tvalidation_0-logloss:0.43643\n","[59]\tvalidation_0-logloss:0.43575\n","[60]\tvalidation_0-logloss:0.43494\n","[61]\tvalidation_0-logloss:0.43430\n","[62]\tvalidation_0-logloss:0.43361\n","[63]\tvalidation_0-logloss:0.43295\n","[64]\tvalidation_0-logloss:0.43229\n","[65]\tvalidation_0-logloss:0.43160\n","[66]\tvalidation_0-logloss:0.43088\n","[67]\tvalidation_0-logloss:0.43018\n","[68]\tvalidation_0-logloss:0.42950\n","[69]\tvalidation_0-logloss:0.42887\n","[70]\tvalidation_0-logloss:0.42814\n","[71]\tvalidation_0-logloss:0.42747\n","[72]\tvalidation_0-logloss:0.42686\n","[73]\tvalidation_0-logloss:0.42626\n","[74]\tvalidation_0-logloss:0.42569\n","[75]\tvalidation_0-logloss:0.42512\n","[76]\tvalidation_0-logloss:0.42445\n","[77]\tvalidation_0-logloss:0.42380\n","[78]\tvalidation_0-logloss:0.42324\n","[79]\tvalidation_0-logloss:0.42268\n","[80]\tvalidation_0-logloss:0.42212\n","[81]\tvalidation_0-logloss:0.42177\n","[82]\tvalidation_0-logloss:0.42120\n","[83]\tvalidation_0-logloss:0.42061\n","[84]\tvalidation_0-logloss:0.42008\n","[85]\tvalidation_0-logloss:0.41950\n","[86]\tvalidation_0-logloss:0.41898\n","[87]\tvalidation_0-logloss:0.41849\n","[88]\tvalidation_0-logloss:0.41802\n","[89]\tvalidation_0-logloss:0.41752\n","[90]\tvalidation_0-logloss:0.41701\n","[91]\tvalidation_0-logloss:0.41650\n","[92]\tvalidation_0-logloss:0.41595\n","[93]\tvalidation_0-logloss:0.41540\n","[94]\tvalidation_0-logloss:0.41485\n","[95]\tvalidation_0-logloss:0.41433\n","[96]\tvalidation_0-logloss:0.41386\n","[97]\tvalidation_0-logloss:0.41335\n","[98]\tvalidation_0-logloss:0.41282\n","[99]\tvalidation_0-logloss:0.41233\n","[100]\tvalidation_0-logloss:0.41180\n","[101]\tvalidation_0-logloss:0.41147\n","[102]\tvalidation_0-logloss:0.41097\n","[103]\tvalidation_0-logloss:0.41053\n","[104]\tvalidation_0-logloss:0.41002\n","[105]\tvalidation_0-logloss:0.40953\n","[106]\tvalidation_0-logloss:0.40922\n","[107]\tvalidation_0-logloss:0.40882\n","[108]\tvalidation_0-logloss:0.40835\n","[109]\tvalidation_0-logloss:0.40793\n","[110]\tvalidation_0-logloss:0.40753\n","[111]\tvalidation_0-logloss:0.40710\n","[112]\tvalidation_0-logloss:0.40650\n","[113]\tvalidation_0-logloss:0.40603\n","[114]\tvalidation_0-logloss:0.40558\n","[115]\tvalidation_0-logloss:0.40517\n","[116]\tvalidation_0-logloss:0.40480\n","[117]\tvalidation_0-logloss:0.40437\n","[118]\tvalidation_0-logloss:0.40395\n","[119]\tvalidation_0-logloss:0.40355\n","[120]\tvalidation_0-logloss:0.40311\n","[121]\tvalidation_0-logloss:0.40269\n","[122]\tvalidation_0-logloss:0.40232\n","[123]\tvalidation_0-logloss:0.40195\n","[124]\tvalidation_0-logloss:0.40167\n","[125]\tvalidation_0-logloss:0.40132\n","[126]\tvalidation_0-logloss:0.40093\n","[127]\tvalidation_0-logloss:0.40057\n","[128]\tvalidation_0-logloss:0.40027\n","[129]\tvalidation_0-logloss:0.39995\n","[130]\tvalidation_0-logloss:0.39959\n","[131]\tvalidation_0-logloss:0.39923\n","[132]\tvalidation_0-logloss:0.39884\n","[133]\tvalidation_0-logloss:0.39851\n","[134]\tvalidation_0-logloss:0.39821\n","[135]\tvalidation_0-logloss:0.39787\n","[136]\tvalidation_0-logloss:0.39734\n","[137]\tvalidation_0-logloss:0.39704\n","[138]\tvalidation_0-logloss:0.39669\n","[139]\tvalidation_0-logloss:0.39630\n","[140]\tvalidation_0-logloss:0.39590\n","[141]\tvalidation_0-logloss:0.39555\n","[142]\tvalidation_0-logloss:0.39525\n","[143]\tvalidation_0-logloss:0.39475\n","[144]\tvalidation_0-logloss:0.39448\n","[145]\tvalidation_0-logloss:0.39416\n","[146]\tvalidation_0-logloss:0.39386\n","[147]\tvalidation_0-logloss:0.39369\n","[148]\tvalidation_0-logloss:0.39333\n","[149]\tvalidation_0-logloss:0.39305\n","[150]\tvalidation_0-logloss:0.39282\n","[151]\tvalidation_0-logloss:0.39245\n","[152]\tvalidation_0-logloss:0.39228\n","[153]\tvalidation_0-logloss:0.39192\n","[154]\tvalidation_0-logloss:0.39156\n","[155]\tvalidation_0-logloss:0.39123\n","[156]\tvalidation_0-logloss:0.39095\n","[157]\tvalidation_0-logloss:0.39065\n","[158]\tvalidation_0-logloss:0.39020\n","[159]\tvalidation_0-logloss:0.38990\n","[160]\tvalidation_0-logloss:0.38958\n","[161]\tvalidation_0-logloss:0.38930\n","[162]\tvalidation_0-logloss:0.38903\n","[163]\tvalidation_0-logloss:0.38871\n","[164]\tvalidation_0-logloss:0.38843\n","[165]\tvalidation_0-logloss:0.38816\n","[166]\tvalidation_0-logloss:0.38791\n","[167]\tvalidation_0-logloss:0.38764\n","[168]\tvalidation_0-logloss:0.38734\n","[169]\tvalidation_0-logloss:0.38711\n","[170]\tvalidation_0-logloss:0.38680\n","[171]\tvalidation_0-logloss:0.38652\n","[172]\tvalidation_0-logloss:0.38625\n","[173]\tvalidation_0-logloss:0.38602\n","[174]\tvalidation_0-logloss:0.38576\n","[175]\tvalidation_0-logloss:0.38547\n","[176]\tvalidation_0-logloss:0.38517\n","[177]\tvalidation_0-logloss:0.38494\n","[178]\tvalidation_0-logloss:0.38471\n","[179]\tvalidation_0-logloss:0.38448\n","[180]\tvalidation_0-logloss:0.38428\n","[181]\tvalidation_0-logloss:0.38405\n","[182]\tvalidation_0-logloss:0.38380\n","[183]\tvalidation_0-logloss:0.38352\n","[184]\tvalidation_0-logloss:0.38332\n","[185]\tvalidation_0-logloss:0.38304\n","[186]\tvalidation_0-logloss:0.38284\n","[187]\tvalidation_0-logloss:0.38263\n","[188]\tvalidation_0-logloss:0.38235\n","[189]\tvalidation_0-logloss:0.38209\n","[190]\tvalidation_0-logloss:0.38183\n","[191]\tvalidation_0-logloss:0.38161\n","[192]\tvalidation_0-logloss:0.38134\n","[193]\tvalidation_0-logloss:0.38099\n","[194]\tvalidation_0-logloss:0.38065\n","[195]\tvalidation_0-logloss:0.38045\n","[196]\tvalidation_0-logloss:0.38019\n","[197]\tvalidation_0-logloss:0.37996\n","[198]\tvalidation_0-logloss:0.37972\n","[199]\tvalidation_0-logloss:0.37947\n","[200]\tvalidation_0-logloss:0.37924\n","[201]\tvalidation_0-logloss:0.37902\n","[202]\tvalidation_0-logloss:0.37884\n","[203]\tvalidation_0-logloss:0.37862\n","[204]\tvalidation_0-logloss:0.37843\n","[205]\tvalidation_0-logloss:0.37819\n","[206]\tvalidation_0-logloss:0.37800\n","[207]\tvalidation_0-logloss:0.37779\n","[208]\tvalidation_0-logloss:0.37759\n","[209]\tvalidation_0-logloss:0.37737\n","[210]\tvalidation_0-logloss:0.37721\n","[211]\tvalidation_0-logloss:0.37701\n","[212]\tvalidation_0-logloss:0.37679\n","[213]\tvalidation_0-logloss:0.37659\n","[214]\tvalidation_0-logloss:0.37639\n","[215]\tvalidation_0-logloss:0.37616\n","[216]\tvalidation_0-logloss:0.37596\n","[217]\tvalidation_0-logloss:0.37579\n","[218]\tvalidation_0-logloss:0.37559\n","[219]\tvalidation_0-logloss:0.37543\n","[220]\tvalidation_0-logloss:0.37525\n","[221]\tvalidation_0-logloss:0.37504\n","[222]\tvalidation_0-logloss:0.37487\n","[223]\tvalidation_0-logloss:0.37471\n","[224]\tvalidation_0-logloss:0.37450\n","[225]\tvalidation_0-logloss:0.37430\n","[226]\tvalidation_0-logloss:0.37413\n","[227]\tvalidation_0-logloss:0.37394\n","[228]\tvalidation_0-logloss:0.37379\n","[229]\tvalidation_0-logloss:0.37361\n","[230]\tvalidation_0-logloss:0.37339\n","[231]\tvalidation_0-logloss:0.37318\n","[232]\tvalidation_0-logloss:0.37300\n","[233]\tvalidation_0-logloss:0.37285\n","[234]\tvalidation_0-logloss:0.37265\n","[235]\tvalidation_0-logloss:0.37251\n","[236]\tvalidation_0-logloss:0.37234\n","[237]\tvalidation_0-logloss:0.37216\n","[238]\tvalidation_0-logloss:0.37193\n","[239]\tvalidation_0-logloss:0.37174\n","[240]\tvalidation_0-logloss:0.37155\n","[241]\tvalidation_0-logloss:0.37136\n","[242]\tvalidation_0-logloss:0.37115\n","[243]\tvalidation_0-logloss:0.37100\n","[244]\tvalidation_0-logloss:0.37086\n","[245]\tvalidation_0-logloss:0.37069\n","[246]\tvalidation_0-logloss:0.37051\n","[247]\tvalidation_0-logloss:0.37038\n","[248]\tvalidation_0-logloss:0.37019\n","[249]\tvalidation_0-logloss:0.37005\n","[250]\tvalidation_0-logloss:0.36987\n","[251]\tvalidation_0-logloss:0.36970\n","[252]\tvalidation_0-logloss:0.36957\n","[253]\tvalidation_0-logloss:0.36941\n","[254]\tvalidation_0-logloss:0.36924\n","[255]\tvalidation_0-logloss:0.36911\n","[256]\tvalidation_0-logloss:0.36895\n","[257]\tvalidation_0-logloss:0.36874\n","[258]\tvalidation_0-logloss:0.36851\n","[259]\tvalidation_0-logloss:0.36830\n","[260]\tvalidation_0-logloss:0.36818\n","[261]\tvalidation_0-logloss:0.36797\n","[262]\tvalidation_0-logloss:0.36780\n","[263]\tvalidation_0-logloss:0.36764\n","[264]\tvalidation_0-logloss:0.36748\n","[265]\tvalidation_0-logloss:0.36735\n","[266]\tvalidation_0-logloss:0.36719\n","[267]\tvalidation_0-logloss:0.36703\n","[268]\tvalidation_0-logloss:0.36687\n","[269]\tvalidation_0-logloss:0.36672\n","[270]\tvalidation_0-logloss:0.36657\n","[271]\tvalidation_0-logloss:0.36642\n","[272]\tvalidation_0-logloss:0.36629\n","[273]\tvalidation_0-logloss:0.36616\n","[274]\tvalidation_0-logloss:0.36603\n","[275]\tvalidation_0-logloss:0.36589\n","[276]\tvalidation_0-logloss:0.36576\n","[277]\tvalidation_0-logloss:0.36563\n","[278]\tvalidation_0-logloss:0.36553\n","[279]\tvalidation_0-logloss:0.36539\n","[280]\tvalidation_0-logloss:0.36525\n","[281]\tvalidation_0-logloss:0.36508\n","[282]\tvalidation_0-logloss:0.36497\n","[283]\tvalidation_0-logloss:0.36482\n","[284]\tvalidation_0-logloss:0.36470\n","[285]\tvalidation_0-logloss:0.36456\n","[286]\tvalidation_0-logloss:0.36444\n","[287]\tvalidation_0-logloss:0.36434\n","[288]\tvalidation_0-logloss:0.36421\n","[289]\tvalidation_0-logloss:0.36405\n","[290]\tvalidation_0-logloss:0.36385\n","[291]\tvalidation_0-logloss:0.36374\n","[292]\tvalidation_0-logloss:0.36360\n","[293]\tvalidation_0-logloss:0.36346\n","[294]\tvalidation_0-logloss:0.36338\n","[295]\tvalidation_0-logloss:0.36325\n","[296]\tvalidation_0-logloss:0.36315\n","[297]\tvalidation_0-logloss:0.36303\n","[298]\tvalidation_0-logloss:0.36293\n","[299]\tvalidation_0-logloss:0.36279\n","[300]\tvalidation_0-logloss:0.36266\n","[301]\tvalidation_0-logloss:0.36249\n","[302]\tvalidation_0-logloss:0.36236\n","[303]\tvalidation_0-logloss:0.36224\n","[304]\tvalidation_0-logloss:0.36207\n","[305]\tvalidation_0-logloss:0.36189\n","[306]\tvalidation_0-logloss:0.36180\n","[307]\tvalidation_0-logloss:0.36170\n","[308]\tvalidation_0-logloss:0.36154\n","[309]\tvalidation_0-logloss:0.36144\n","[310]\tvalidation_0-logloss:0.36134\n","[311]\tvalidation_0-logloss:0.36122\n","[312]\tvalidation_0-logloss:0.36110\n","[313]\tvalidation_0-logloss:0.36099\n","[314]\tvalidation_0-logloss:0.36091\n","[315]\tvalidation_0-logloss:0.36080\n","[316]\tvalidation_0-logloss:0.36067\n","[317]\tvalidation_0-logloss:0.36058\n","[318]\tvalidation_0-logloss:0.36045\n","[319]\tvalidation_0-logloss:0.36034\n","[320]\tvalidation_0-logloss:0.36026\n","[321]\tvalidation_0-logloss:0.36013\n","[322]\tvalidation_0-logloss:0.36004\n","[323]\tvalidation_0-logloss:0.35995\n","[324]\tvalidation_0-logloss:0.35984\n","[325]\tvalidation_0-logloss:0.35974\n","[326]\tvalidation_0-logloss:0.35963\n","[327]\tvalidation_0-logloss:0.35954\n","[328]\tvalidation_0-logloss:0.35943\n","[329]\tvalidation_0-logloss:0.35934\n","[330]\tvalidation_0-logloss:0.35924\n","[331]\tvalidation_0-logloss:0.35913\n","[332]\tvalidation_0-logloss:0.35903\n","[333]\tvalidation_0-logloss:0.35893\n","[334]\tvalidation_0-logloss:0.35879\n","[335]\tvalidation_0-logloss:0.35871\n","[336]\tvalidation_0-logloss:0.35861\n","[337]\tvalidation_0-logloss:0.35848\n","[338]\tvalidation_0-logloss:0.35840\n","[339]\tvalidation_0-logloss:0.35832\n","[340]\tvalidation_0-logloss:0.35820\n","[341]\tvalidation_0-logloss:0.35811\n","[342]\tvalidation_0-logloss:0.35797\n","[343]\tvalidation_0-logloss:0.35790\n","[344]\tvalidation_0-logloss:0.35780\n","[345]\tvalidation_0-logloss:0.35772\n","[346]\tvalidation_0-logloss:0.35759\n","[347]\tvalidation_0-logloss:0.35750\n","[348]\tvalidation_0-logloss:0.35741\n","[349]\tvalidation_0-logloss:0.35727\n","[350]\tvalidation_0-logloss:0.35718\n","[351]\tvalidation_0-logloss:0.35711\n","[352]\tvalidation_0-logloss:0.35700\n","[353]\tvalidation_0-logloss:0.35691\n","[354]\tvalidation_0-logloss:0.35683\n","[355]\tvalidation_0-logloss:0.35669\n","[356]\tvalidation_0-logloss:0.35656\n","[357]\tvalidation_0-logloss:0.35649\n","[358]\tvalidation_0-logloss:0.35640\n","[359]\tvalidation_0-logloss:0.35627\n","[360]\tvalidation_0-logloss:0.35619\n","[361]\tvalidation_0-logloss:0.35611\n","[362]\tvalidation_0-logloss:0.35602\n","[363]\tvalidation_0-logloss:0.35589\n","[364]\tvalidation_0-logloss:0.35580\n","[365]\tvalidation_0-logloss:0.35568\n","[366]\tvalidation_0-logloss:0.35559\n","[367]\tvalidation_0-logloss:0.35550\n","[368]\tvalidation_0-logloss:0.35534\n","[369]\tvalidation_0-logloss:0.35524\n","[370]\tvalidation_0-logloss:0.35517\n","[371]\tvalidation_0-logloss:0.35501\n","[372]\tvalidation_0-logloss:0.35493\n","[373]\tvalidation_0-logloss:0.35484\n","[374]\tvalidation_0-logloss:0.35470\n","[375]\tvalidation_0-logloss:0.35460\n","[376]\tvalidation_0-logloss:0.35453\n","[377]\tvalidation_0-logloss:0.35445\n","[378]\tvalidation_0-logloss:0.35440\n","[379]\tvalidation_0-logloss:0.35431\n","[380]\tvalidation_0-logloss:0.35420\n","[381]\tvalidation_0-logloss:0.35412\n","[382]\tvalidation_0-logloss:0.35400\n","[383]\tvalidation_0-logloss:0.35384\n","[384]\tvalidation_0-logloss:0.35378\n","[385]\tvalidation_0-logloss:0.35367\n","[386]\tvalidation_0-logloss:0.35356\n","[387]\tvalidation_0-logloss:0.35348\n","[388]\tvalidation_0-logloss:0.35343\n","[389]\tvalidation_0-logloss:0.35338\n","[390]\tvalidation_0-logloss:0.35333\n","[391]\tvalidation_0-logloss:0.35323\n","[392]\tvalidation_0-logloss:0.35312\n","[393]\tvalidation_0-logloss:0.35307\n","[394]\tvalidation_0-logloss:0.35295\n","[395]\tvalidation_0-logloss:0.35289\n","[396]\tvalidation_0-logloss:0.35282\n","[397]\tvalidation_0-logloss:0.35276\n","[398]\tvalidation_0-logloss:0.35270\n","[399]\tvalidation_0-logloss:0.35262\n","[400]\tvalidation_0-logloss:0.35253\n","[401]\tvalidation_0-logloss:0.35246\n","[402]\tvalidation_0-logloss:0.35240\n","[403]\tvalidation_0-logloss:0.35229\n","[404]\tvalidation_0-logloss:0.35222\n","[405]\tvalidation_0-logloss:0.35215\n","[406]\tvalidation_0-logloss:0.35209\n","[407]\tvalidation_0-logloss:0.35202\n","[408]\tvalidation_0-logloss:0.35197\n","[409]\tvalidation_0-logloss:0.35187\n","[410]\tvalidation_0-logloss:0.35181\n","[411]\tvalidation_0-logloss:0.35173\n","[412]\tvalidation_0-logloss:0.35163\n","[413]\tvalidation_0-logloss:0.35153\n","[414]\tvalidation_0-logloss:0.35147\n","[415]\tvalidation_0-logloss:0.35141\n","[416]\tvalidation_0-logloss:0.35131\n","[417]\tvalidation_0-logloss:0.35124\n","[418]\tvalidation_0-logloss:0.35117\n","[419]\tvalidation_0-logloss:0.35110\n","[420]\tvalidation_0-logloss:0.35105\n","[421]\tvalidation_0-logloss:0.35101\n","[422]\tvalidation_0-logloss:0.35090\n","[423]\tvalidation_0-logloss:0.35084\n","[424]\tvalidation_0-logloss:0.35077\n","[425]\tvalidation_0-logloss:0.35071\n","[426]\tvalidation_0-logloss:0.35064\n","[427]\tvalidation_0-logloss:0.35058\n","[428]\tvalidation_0-logloss:0.35052\n","[429]\tvalidation_0-logloss:0.35046\n","[430]\tvalidation_0-logloss:0.35040\n","[431]\tvalidation_0-logloss:0.35034\n","[432]\tvalidation_0-logloss:0.35029\n","[433]\tvalidation_0-logloss:0.35018\n","[434]\tvalidation_0-logloss:0.35009\n","[435]\tvalidation_0-logloss:0.35003\n","[436]\tvalidation_0-logloss:0.34997\n","[437]\tvalidation_0-logloss:0.34988\n","[438]\tvalidation_0-logloss:0.34978\n","[439]\tvalidation_0-logloss:0.34969\n","[440]\tvalidation_0-logloss:0.34962\n","[441]\tvalidation_0-logloss:0.34956\n","[442]\tvalidation_0-logloss:0.34950\n","[443]\tvalidation_0-logloss:0.34944\n","[444]\tvalidation_0-logloss:0.34941\n","[445]\tvalidation_0-logloss:0.34935\n","[446]\tvalidation_0-logloss:0.34931\n","[447]\tvalidation_0-logloss:0.34927\n","[448]\tvalidation_0-logloss:0.34923\n","[449]\tvalidation_0-logloss:0.34920\n","[450]\tvalidation_0-logloss:0.34915\n","[451]\tvalidation_0-logloss:0.34909\n","[452]\tvalidation_0-logloss:0.34904\n","[453]\tvalidation_0-logloss:0.34898\n","[454]\tvalidation_0-logloss:0.34893\n","[455]\tvalidation_0-logloss:0.34885\n","[456]\tvalidation_0-logloss:0.34881\n","[457]\tvalidation_0-logloss:0.34875\n","[458]\tvalidation_0-logloss:0.34870\n","[459]\tvalidation_0-logloss:0.34863\n","[460]\tvalidation_0-logloss:0.34858\n","[461]\tvalidation_0-logloss:0.34849\n","[462]\tvalidation_0-logloss:0.34843\n","[463]\tvalidation_0-logloss:0.34838\n","[464]\tvalidation_0-logloss:0.34832\n","[465]\tvalidation_0-logloss:0.34827\n","[466]\tvalidation_0-logloss:0.34817\n","[467]\tvalidation_0-logloss:0.34815\n","[468]\tvalidation_0-logloss:0.34810\n","[469]\tvalidation_0-logloss:0.34796\n","[470]\tvalidation_0-logloss:0.34793\n","[471]\tvalidation_0-logloss:0.34788\n","[472]\tvalidation_0-logloss:0.34783\n","[473]\tvalidation_0-logloss:0.34772\n","[474]\tvalidation_0-logloss:0.34766\n","[475]\tvalidation_0-logloss:0.34761\n","[476]\tvalidation_0-logloss:0.34757\n","[477]\tvalidation_0-logloss:0.34752\n","[478]\tvalidation_0-logloss:0.34743\n","[479]\tvalidation_0-logloss:0.34739\n","[480]\tvalidation_0-logloss:0.34737\n","[481]\tvalidation_0-logloss:0.34735\n","[482]\tvalidation_0-logloss:0.34730\n","[483]\tvalidation_0-logloss:0.34725\n","[484]\tvalidation_0-logloss:0.34720\n","[485]\tvalidation_0-logloss:0.34712\n","[486]\tvalidation_0-logloss:0.34702\n","[487]\tvalidation_0-logloss:0.34698\n","[488]\tvalidation_0-logloss:0.34695\n","[489]\tvalidation_0-logloss:0.34692\n","[490]\tvalidation_0-logloss:0.34684\n","[491]\tvalidation_0-logloss:0.34682\n","[492]\tvalidation_0-logloss:0.34677\n","[493]\tvalidation_0-logloss:0.34667\n","[494]\tvalidation_0-logloss:0.34663\n","[495]\tvalidation_0-logloss:0.34656\n","[496]\tvalidation_0-logloss:0.34653\n","[497]\tvalidation_0-logloss:0.34645\n","[498]\tvalidation_0-logloss:0.34639\n","[499]\tvalidation_0-logloss:0.34635\n","XGBoost Training Accuracy: 0.9585\n","XGBoost Testing Accuracy: 0.8640\n"]}]},{"cell_type":"code","source":["from sklearn.model_selection import GridSearchCV\n","from xgboost import XGBClassifier\n","\n","# Define the parameter grid to search\n","param_grid = {\n","    'max_depth': [2, 3, 4],\n","    'min_child_weight': [1, 5, 10],\n","    'reg_lambda': [1.0, 2.0, 3.0],\n","    'reg_alpha': [0.0, 0.5, 1.0],\n","    'learning_rate': [0.01, 0.1],\n","    'n_estimators': [100, 200, 500],\n","    'subsample': [0.8, 1.0],\n","    'colsample_bytree': [0.8, 1.0]\n","}\n","\n","# Initialize the XGBoost model\n","xgb_model2 = XGBClassifier(use_label_encoder=False, eval_metric='logloss', random_state=42)\n","\n","# Set up Grid Search with 5-fold cross-validation\n","grid_search = GridSearchCV(estimator=xgb_model, param_grid=param_grid,\n","                           cv=5, scoring='accuracy', verbose=1, n_jobs=-1)\n","\n","# Fit the model\n","grid_search.fit(X_train, y_train)\n","\n","# Best parameters found by Grid Search\n","print(\"Best Hyperparameters:\", grid_search.best_params_)\n","\n","# Predict using the best model from grid search\n","best_xgb_model = grid_search.best_estimator_\n","best_xgb_train_preds = best_xgb_model.predict(X_train)\n","best_xgb_test_preds = best_xgb_model.predict(X_test)\n","\n","# Calculate training and testing accuracy\n","best_xgb_train_accuracy = accuracy_score(y_train, best_xgb_train_preds)\n","best_xgb_test_accuracy = accuracy_score(y_test, best_xgb_test_preds)\n","\n","print(f\"Best XGBoost Training Accuracy: {best_xgb_train_accuracy:.4f}\")\n","print(f\"Best XGBoost Testing Accuracy: {best_xgb_test_accuracy:.4f}\")\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":373},"id":"skcZw-vPV6C2","executionInfo":{"status":"error","timestamp":1723630501643,"user_tz":-330,"elapsed":673918,"user":{"displayName":"Abhiram Vanama","userId":"15150483264437415347"}},"outputId":"cfafa12d-f7c9-45a8-d7ea-b21fe2aee5a6"},"execution_count":11,"outputs":[{"output_type":"stream","name":"stdout","text":["Fitting 5 folds for each of 1944 candidates, totalling 9720 fits\n"]},{"output_type":"error","ename":"KeyboardInterrupt","evalue":"","traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)","\u001b[0;32m<ipython-input-11-c0544b869ec9>\u001b[0m in \u001b[0;36m<cell line: 24>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     22\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     23\u001b[0m \u001b[0;31m# Fit the model\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 24\u001b[0;31m \u001b[0mgrid_search\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_train\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_train\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     25\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     26\u001b[0m \u001b[0;31m# Best parameters found by Grid Search\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/sklearn/base.py\u001b[0m in \u001b[0;36mwrapper\u001b[0;34m(estimator, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1150\u001b[0m                 )\n\u001b[1;32m   1151\u001b[0m             ):\n\u001b[0;32m-> 1152\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mfit_method\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mestimator\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1153\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1154\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mwrapper\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/sklearn/model_selection/_search.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, X, y, groups, **fit_params)\u001b[0m\n\u001b[1;32m    896\u001b[0m                 \u001b[0;32mreturn\u001b[0m \u001b[0mresults\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    897\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 898\u001b[0;31m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_run_search\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mevaluate_candidates\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    899\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    900\u001b[0m             \u001b[0;31m# multimetric is determined here because in the case of a callable\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/sklearn/model_selection/_search.py\u001b[0m in \u001b[0;36m_run_search\u001b[0;34m(self, evaluate_candidates)\u001b[0m\n\u001b[1;32m   1420\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_run_search\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mevaluate_candidates\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1421\u001b[0m         \u001b[0;34m\"\"\"Search all candidates in param_grid\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1422\u001b[0;31m         \u001b[0mevaluate_candidates\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mParameterGrid\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mparam_grid\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1423\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1424\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/sklearn/model_selection/_search.py\u001b[0m in \u001b[0;36mevaluate_candidates\u001b[0;34m(candidate_params, cv, more_results)\u001b[0m\n\u001b[1;32m    843\u001b[0m                     )\n\u001b[1;32m    844\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 845\u001b[0;31m                 out = parallel(\n\u001b[0m\u001b[1;32m    846\u001b[0m                     delayed(_fit_and_score)(\n\u001b[1;32m    847\u001b[0m                         \u001b[0mclone\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbase_estimator\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/sklearn/utils/parallel.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, iterable)\u001b[0m\n\u001b[1;32m     63\u001b[0m             \u001b[0;32mfor\u001b[0m \u001b[0mdelayed_func\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwargs\u001b[0m \u001b[0;32min\u001b[0m \u001b[0miterable\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     64\u001b[0m         )\n\u001b[0;32m---> 65\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0msuper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__call__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0miterable_with_config\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     66\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     67\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/joblib/parallel.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, iterable)\u001b[0m\n\u001b[1;32m   2005\u001b[0m         \u001b[0mnext\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moutput\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2006\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2007\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0moutput\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreturn_generator\u001b[0m \u001b[0;32melse\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moutput\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2008\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2009\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m__repr__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/joblib/parallel.py\u001b[0m in \u001b[0;36m_get_outputs\u001b[0;34m(self, iterator, pre_dispatch)\u001b[0m\n\u001b[1;32m   1648\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1649\u001b[0m             \u001b[0;32mwith\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_backend\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mretrieval_context\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1650\u001b[0;31m                 \u001b[0;32myield\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_retrieve\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1651\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1652\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mGeneratorExit\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/joblib/parallel.py\u001b[0m in \u001b[0;36m_retrieve\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m   1760\u001b[0m                 (self._jobs[0].get_status(\n\u001b[1;32m   1761\u001b[0m                     timeout=self.timeout) == TASK_PENDING)):\n\u001b[0;32m-> 1762\u001b[0;31m                 \u001b[0mtime\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msleep\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0.01\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1763\u001b[0m                 \u001b[0;32mcontinue\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1764\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;31mKeyboardInterrupt\u001b[0m: "]}]}]}