{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "collapsed_sections": [
        "1SC43mfvTOaA",
        "rSgbzJWVGVmr",
        "CBWWfdG2JQjQ",
        "rSdQ0mQ7ga9j",
        "ahVziGA5gXll"
      ]
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU",
    "gpuClass": "standard"
  },
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "HeQKFpJZT8iY",
        "outputId": "97eb81bc-8151-49d3-9c03-0d10a1b90696"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Mounted at /content/drive\n"
          ]
        }
      ],
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/drive')"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "import time\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.metrics import accuracy_score\n",
        "from sklearn.metrics import classification_report\n",
        "import numpy as np\n",
        "from sklearn.metrics import roc_auc_score\n",
        "from sklearn.metrics import confusion_matrix\n",
        "from sklearn.model_selection import KFold, cross_val_score\n",
        "from sklearn.metrics import log_loss,cohen_kappa_score\n",
        "from imblearn.metrics import geometric_mean_score\n",
        "import matplotlib.pyplot as plt\n",
        "import numpy as np\n",
        "import seaborn as sns\n",
        "import warnings\n",
        "warnings.filterwarnings('ignore')\n",
        "import nltk\n",
        "nltk.download('stopwords')\n",
        "# !pip install vaderSentiment\n",
        "# !pip install afinn"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ovClcNbDULOm",
        "outputId": "adad522e-ab67-4e06-ad82-e9050d2a1b0e"
      },
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "[nltk_data] Downloading package stopwords to /root/nltk_data...\n",
            "[nltk_data]   Package stopwords is already up-to-date!\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "True"
            ]
          },
          "metadata": {},
          "execution_count": 1
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "import nltk\n",
        "from collections import Counter\n",
        "df = pd.read_csv(\"/content/data.csv\")\n",
        "# df=df.drop('Unnamed',axis=1)"
      ],
      "metadata": {
        "id": "2V5BhgPpULZ6"
      },
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df.info()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_FWfC_N7E7b2",
        "outputId": "42a18717-5b18-472a-978f-34bb721fc559"
      },
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 1000 entries, 0 to 999\n",
            "Data columns (total 7 columns):\n",
            " #   Column          Non-Null Count  Dtype  \n",
            "---  ------          --------------  -----  \n",
            " 0   UserID          1000 non-null   int64  \n",
            " 1   Age             1000 non-null   int64  \n",
            " 2   Gender          1000 non-null   object \n",
            " 3   VRHeadset       1000 non-null   object \n",
            " 4   Duration        1000 non-null   float64\n",
            " 5   MotionSickness  1000 non-null   int64  \n",
            " 6   ImmersionLevel  1000 non-null   int64  \n",
            "dtypes: float64(1), int64(4), object(2)\n",
            "memory usage: 54.8+ KB\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "70e1hvw6U4Cf",
        "outputId": "4182ccb9-0ff0-4f03-fd02-c300de3a8832"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   UserID  Age  Gender       VRHeadset   Duration  MotionSickness  \\\n",
              "0       1   40    Male        HTC Vive  13.598508               8   \n",
              "1       2   43  Female        HTC Vive  19.950815               2   \n",
              "2       3   27    Male  PlayStation VR  16.543387               4   \n",
              "3       4   33    Male        HTC Vive  42.574083               6   \n",
              "4       5   51    Male  PlayStation VR  22.452647               4   \n",
              "\n",
              "   ImmersionLevel  \n",
              "0               5  \n",
              "1               2  \n",
              "2               2  \n",
              "3               3  \n",
              "4               2  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-9951a2a7-5300-4e9f-89e0-4015d813ab9f\">\n",
              "    <div 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>UserID</th>\n",
              "      <th>Age</th>\n",
              "      <th>Gender</th>\n",
              "      <th>VRHeadset</th>\n",
              "      <th>Duration</th>\n",
              "      <th>MotionSickness</th>\n",
              "      <th>ImmersionLevel</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>40</td>\n",
              "      <td>Male</td>\n",
              "      <td>HTC Vive</td>\n",
              "      <td>13.598508</td>\n",
              "      <td>8</td>\n",
              "      <td>5</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>43</td>\n",
              "      <td>Female</td>\n",
              "      <td>HTC Vive</td>\n",
              "      <td>19.950815</td>\n",
              "      <td>2</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>27</td>\n",
              "      <td>Male</td>\n",
              "      <td>PlayStation VR</td>\n",
              "      <td>16.543387</td>\n",
              "      <td>4</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>4</td>\n",
              "      <td>33</td>\n",
              "      <td>Male</td>\n",
              "      <td>HTC Vive</td>\n",
              "      <td>42.574083</td>\n",
              "      <td>6</td>\n",
              "      <td>3</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>5</td>\n",
              "      <td>51</td>\n",
              "      <td>Male</td>\n",
              "      <td>PlayStation VR</td>\n",
              "      <td>22.452647</td>\n",
              "      <td>4</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-9951a2a7-5300-4e9f-89e0-4015d813ab9f')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-9951a2a7-5300-4e9f-89e0-4015d813ab9f 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-9951a2a7-5300-4e9f-89e0-4015d813ab9f');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn import preprocessing\n",
        "le = preprocessing.LabelEncoder()\n",
        "df['Gender']=le.fit_transform(df['Gender'])\n",
        "df['VRHeadset']=le.fit_transform(df['VRHeadset'])"
      ],
      "metadata": {
        "id": "T9zRV_tsNOLA"
      },
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df['ImmersionLevel'].value_counts()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "tA8AtMX6XXzA",
        "outputId": "16d484b4-ef60-4ac4-8073-9dff52038833"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "2    208\n",
              "4    206\n",
              "1    202\n",
              "3    193\n",
              "5    191\n",
              "Name: ImmersionLevel, dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Data analysis"
      ],
      "metadata": {
        "id": "1SC43mfvTOaA"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import matplotlib.pyplot as plt\n",
        "import numpy as np\n",
        "import seaborn as sns\n",
        "import matplotlib.ticker as tkr\n",
        "def func(x, pos):  # formatter function takes tick label and tick position\n",
        "    s = '%d' % x\n",
        "    groups = []\n",
        "    while s and s[-1].isdigit():\n",
        "        groups.append(s[-3:])\n",
        "        s = s[:-3]\n",
        "    return s + ','.join(reversed(groups))\n",
        "\n",
        "y_format = tkr.FuncFormatter(func)  # make formatter\n",
        "plt.figure(figsize=(8,5), dpi = 200)\n",
        "p=sns.countplot(x='ImmersionLevel',data= df )\n",
        "p.yaxis.set_major_formatter(y_format)\n",
        "p.tick_params(labelsize=13)\n",
        "plt.xticks(rotation = 50)\n",
        "plt.xlabel(\"Immersion Level\",fontsize=12)\n",
        "plt.ylabel(\"Distribution Count\",fontsize=12)\n",
        "# plt.savefig('barchart.pdf',dpi=100,bbox_inches = 'tight')\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 778
        },
        "id": "h-hRO4ZvExuV",
        "outputId": "24234c8d-6ccf-4632-e804-36af424fd3d5"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1600x1000 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "x=df.drop(['ImmersionLevel'],axis=1)\n",
        "y=df['ImmersionLevel']\n",
        "X_train, X_test, Y_train, Y_test = train_test_split(x,y, test_size = 0.2,random_state=0,shuffle=True)"
      ],
      "metadata": {
        "id": "r1C-I0mUFFa1"
      },
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# results with origional features"
      ],
      "metadata": {
        "id": "rSgbzJWVGVmr"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.linear_model import LogisticRegression\n",
        "clf = LogisticRegression(random_state=0,max_iter=500,multi_class='auto',C=1.0)\n",
        "start = time.time()\n",
        "clf.fit(X_train, Y_train)\n",
        "stop = time.time()\n",
        "print(f\"Training time: {stop - start}s\")\n",
        "dtP3=clf.predict(X_test)\n",
        "print('accuracy score',accuracy_score(Y_test,dtP3))\n",
        "# print('error rate:',1-accuracy_score(Y_test,dtP3))\n",
        "print(classification_report(Y_test,dtP3))\n",
        "kf = KFold(n_splits=10, shuffle=True)\n",
        "clf = LogisticRegression(random_state=0, solver='lbfgs',max_iter=100,multi_class='auto',C=1.0)\n",
        "score = cross_val_score(clf, x, y, cv= kf, scoring=\"accuracy\")\n",
        "print(\"%0.4f accuracy with a standard deviation of %0.4f\" % (score.mean(), score.std()))\n",
        "# cf_matrix=confusion_matrix(Y_test,dtP3)\n",
        "# cf_matrix"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DDhztFg6FjCv",
        "outputId": "6abb3264-5bfc-4a2b-9e3d-476c493bd97b"
      },
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Training time: 0.2122478485107422s\n",
            "accuracy score 0.2\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "           1       0.24      0.41      0.30        37\n",
            "           2       0.19      0.28      0.23        39\n",
            "           3       0.10      0.11      0.11        35\n",
            "           4       0.25      0.21      0.23        48\n",
            "           5       0.00      0.00      0.00        41\n",
            "\n",
            "    accuracy                           0.20       200\n",
            "   macro avg       0.16      0.20      0.17       200\n",
            "weighted avg       0.16      0.20      0.17       200\n",
            "\n",
            "0.2070 accuracy with a standard deviation of 0.0195\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.svm import LinearSVC\n",
        "print(\"SVC\")\n",
        "clf = LinearSVC(random_state=0,max_iter=500)\n",
        "start = time.time()\n",
        "clf.fit(X_train, Y_train)\n",
        "stop = time.time()\n",
        "print(f\"Training time: {stop - start}s\")\n",
        "dtP3=clf.predict(X_test)\n",
        "print('accuracy score',accuracy_score(Y_test,dtP3))\n",
        "# print('error rate:',1-accuracy_score(Y_test,dtP3))\n",
        "print(classification_report(Y_test,dtP3))\n",
        "kf = KFold(n_splits=10, shuffle=True)\n",
        "clf = LinearSVC(random_state=0,max_iter=500)\n",
        "score = cross_val_score(clf, x, y, cv= kf, scoring=\"accuracy\")\n",
        "print(\"%0.4f accuracy with a standard deviation of %0.4f\" % (score.mean(), score.std()))\n",
        "# cf_matrix=confusion_matrix(Y_test,dtP3)\n",
        "# cf_matrix"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_2gBZ4LuFt0S",
        "outputId": "d8675cdd-a9b4-46da-b6da-035d0fb2eb83"
      },
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "SVC\n",
            "Training time: 0.11833071708679199s\n",
            "accuracy score 0.225\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "           1       0.50      0.03      0.05        37\n",
            "           2       0.19      0.13      0.15        39\n",
            "           3       0.00      0.00      0.00        35\n",
            "           4       0.26      0.73      0.38        48\n",
            "           5       0.12      0.10      0.11        41\n",
            "\n",
            "    accuracy                           0.23       200\n",
            "   macro avg       0.21      0.20      0.14       200\n",
            "weighted avg       0.21      0.23      0.15       200\n",
            "\n",
            "0.2300 accuracy with a standard deviation of 0.0332\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.ensemble import RandomForestClassifier\n",
        "print(\"RF\")\n",
        "clf = RandomForestClassifier(n_estimators=100,max_depth=100, random_state=0)\n",
        "start = time.time()\n",
        "clf.fit(X_train, Y_train)\n",
        "stop = time.time()\n",
        "print(f\"Training time: {stop - start}s\")\n",
        "dtP3=clf.predict(X_test)\n",
        "print('accuracy score',accuracy_score(Y_test,dtP3))\n",
        "# print('error rate:',1-accuracy_score(Y_test,dtP3))\n",
        "print(classification_report(Y_test,dtP3))\n",
        "kf = KFold(n_splits=10, shuffle=True)\n",
        "clf = RandomForestClassifier(n_estimators=100,max_depth=100, random_state=0)\n",
        "score = cross_val_score(clf, x, y, cv= kf, scoring=\"accuracy\")\n",
        "print(\"%0.4f accuracy with a standard deviation of %0.4f\" % (score.mean(), score.std()))\n",
        "# cf_matrix=confusion_matrix(Y_test,dtP3)\n",
        "# cf_matrix"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_wCokrupGBqz",
        "outputId": "a5b1545d-5ed1-482e-8bc6-68cd502e8530"
      },
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "RF\n",
            "Training time: 0.6832747459411621s\n",
            "accuracy score 0.16\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "           1       0.14      0.14      0.14        37\n",
            "           2       0.13      0.18      0.15        39\n",
            "           3       0.22      0.20      0.21        35\n",
            "           4       0.14      0.12      0.13        48\n",
            "           5       0.20      0.17      0.18        41\n",
            "\n",
            "    accuracy                           0.16       200\n",
            "   macro avg       0.17      0.16      0.16       200\n",
            "weighted avg       0.16      0.16      0.16       200\n",
            "\n",
            "0.1990 accuracy with a standard deviation of 0.0226\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Results with PCA"
      ],
      "metadata": {
        "id": "CBWWfdG2JQjQ"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.decomposition import PCA\n",
        "pca=PCA(n_components=3)\n",
        "x_pca=pca.fit_transform(x)"
      ],
      "metadata": {
        "id": "YlBqhCAQJPtQ"
      },
      "execution_count": 19,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "X_train, X_test, Y_train, Y_test = train_test_split(x_pca,y, test_size = 0.2,random_state=0,shuffle=True)"
      ],
      "metadata": {
        "id": "GhaLxn8EKDK2"
      },
      "execution_count": 20,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.linear_model import LogisticRegression\n",
        "clf = LogisticRegression(random_state=0,max_iter=100,multi_class='auto',C=1.0)\n",
        "start = time.time()\n",
        "clf.fit(X_train, Y_train)\n",
        "stop = time.time()\n",
        "print(f\"Training time: {stop - start}s\")\n",
        "dtP3=clf.predict(X_test)\n",
        "print('accuracy score',accuracy_score(Y_test,dtP3))\n",
        "# print('error rate:',1-accuracy_score(Y_test,dtP3))\n",
        "print(classification_report(Y_test,dtP3))\n",
        "kf = KFold(n_splits=10, shuffle=True)\n",
        "clf = LogisticRegression(random_state=0, solver='lbfgs',max_iter=100,multi_class='auto',C=1.0)\n",
        "score = cross_val_score(clf, x_pca, y, cv= kf, scoring=\"accuracy\")\n",
        "print(\"%0.4f accuracy with a standard deviation of %0.4f\" % (score.mean(), score.std()))\n",
        "# cf_matrix=confusion_matrix(Y_test,dtP3)\n",
        "# cf_matrix"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ItH3lHaoKGwN",
        "outputId": "bd21ec25-09d9-4581-9c60-8e6d48a88445"
      },
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Training time: 0.12718510627746582s\n",
            "accuracy score 0.2\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "           1       0.27      0.35      0.31        37\n",
            "           2       0.16      0.26      0.20        39\n",
            "           3       0.17      0.20      0.18        35\n",
            "           4       0.21      0.21      0.21        48\n",
            "           5       0.00      0.00      0.00        41\n",
            "\n",
            "    accuracy                           0.20       200\n",
            "   macro avg       0.16      0.20      0.18       200\n",
            "weighted avg       0.16      0.20      0.18       200\n",
            "\n",
            "0.2120 accuracy with a standard deviation of 0.0477\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.svm import LinearSVC\n",
        "print(\"SVC\")\n",
        "clf = LinearSVC(random_state=0,max_iter=500)\n",
        "start = time.time()\n",
        "clf.fit(X_train, Y_train)\n",
        "stop = time.time()\n",
        "print(f\"Training time: {stop - start}s\")\n",
        "dtP3=clf.predict(X_test)\n",
        "print('accuracy score',accuracy_score(Y_test,dtP3))\n",
        "# print('error rate:',1-accuracy_score(Y_test,dtP3))\n",
        "print(classification_report(Y_test,dtP3))\n",
        "kf = KFold(n_splits=10, shuffle=True)\n",
        "clf = LinearSVC(random_state=0,max_iter=500)\n",
        "score = cross_val_score(clf, x_pca, y, cv= kf, scoring=\"accuracy\")\n",
        "print(\"%0.4f accuracy with a standard deviation of %0.4f\" % (score.mean(), score.std()))\n",
        "# cf_matrix=confusion_matrix(Y_test,dtP3)\n",
        "# cf_matrix"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ptZw4js7KZar",
        "outputId": "e9d0e1f2-9819-48bc-aec9-f5558ce8d379"
      },
      "execution_count": 25,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "SVC\n",
            "Training time: 0.09511661529541016s\n",
            "accuracy score 0.21\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "           1       0.21      0.51      0.29        37\n",
            "           2       0.14      0.10      0.12        39\n",
            "           3       0.23      0.43      0.30        35\n",
            "           4       0.30      0.06      0.10        48\n",
            "           5       0.20      0.02      0.04        41\n",
            "\n",
            "    accuracy                           0.21       200\n",
            "   macro avg       0.22      0.23      0.17       200\n",
            "weighted avg       0.22      0.21      0.16       200\n",
            "\n",
            "0.1980 accuracy with a standard deviation of 0.0451\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.ensemble import RandomForestClassifier\n",
        "print(\"RF\")\n",
        "clf = RandomForestClassifier(n_estimators=100,max_depth=100, random_state=0)\n",
        "start = time.time()\n",
        "clf.fit(X_train, Y_train)\n",
        "stop = time.time()\n",
        "print(f\"Training time: {stop - start}s\")\n",
        "dtP3=clf.predict(X_test)\n",
        "print('accuracy score',accuracy_score(Y_test,dtP3))\n",
        "# print('error rate:',1-accuracy_score(Y_test,dtP3))\n",
        "print(classification_report(Y_test,dtP3))\n",
        "kf = KFold(n_splits=10, shuffle=True)\n",
        "clf = RandomForestClassifier(n_estimators=100,max_depth=100, random_state=0)\n",
        "score = cross_val_score(clf, x_pca, y, cv= kf, scoring=\"accuracy\")\n",
        "print(\"%0.4f accuracy with a standard deviation of %0.4f\" % (score.mean(), score.std()))\n",
        "# cf_matrix=confusion_matrix(Y_test,dtP3)\n",
        "# cf_matrix"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "-IVT_a8pKZL1",
        "outputId": "252e9f35-2304-4925-d04b-c4df513d7c01"
      },
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "RF\n",
            "Training time: 0.44127869606018066s\n",
            "accuracy score 0.225\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "           1       0.23      0.27      0.25        37\n",
            "           2       0.21      0.23      0.22        39\n",
            "           3       0.22      0.26      0.24        35\n",
            "           4       0.26      0.25      0.26        48\n",
            "           5       0.18      0.12      0.14        41\n",
            "\n",
            "    accuracy                           0.23       200\n",
            "   macro avg       0.22      0.23      0.22       200\n",
            "weighted avg       0.22      0.23      0.22       200\n",
            "\n",
            "0.1930 accuracy with a standard deviation of 0.0492\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Transfer learning"
      ],
      "metadata": {
        "id": "pGxG0grWJ0RT"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "x=df.drop(['ImmersionLevel'],axis=1)\n",
        "y=df['ImmersionLevel']"
      ],
      "metadata": {
        "id": "ZopeP2W7XpMG"
      },
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "from sklearn.preprocessing import PolynomialFeatures\n",
        "# Create polynomial features\n",
        "poly = PolynomialFeatures(degree=1,include_bias=False)\n",
        "X_train_poly = poly.fit_transform(x)\n",
        "pl=pd.DataFrame(X_train_poly)\n",
        "\n",
        "from sklearn.ensemble import RandomForestClassifier\n",
        "print(\"RF\")\n",
        "RF=RandomForestClassifier(n_estimators=20,max_depth=12, random_state=0)\n",
        "rfPre1=RF.fit(x, y).predict_proba(x)\n",
        "rf=pd.DataFrame(rfPre1)\n",
        "\n",
        "result = pd.concat([pl,rf], axis=1).reindex(pl.index)\n",
        "from sklearn.model_selection import train_test_split\n",
        "X_train, X_test, Y_train, Y_test = train_test_split(result,y,test_size = 0.2,random_state=0,shuffle=True)"
      ],
      "metadata": {
        "id": "KYg9tnxNLdUs",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "f38a8a20-d35f-4582-ebd4-bd94d94c517c"
      },
      "execution_count": 54,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "RF\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "result.to_csv('hybridfeatureselpsy-up.csv',index=False)\n",
        "# df1=pd.read_csv('/content/hybridfeatureselpsy.csv')\n",
        "# # x=df.drop(['y'],axis=1)\n",
        "# y=df['y']\n",
        "# X_train, X_test, Y_train, Y_test = train_test_split(df1,y, test_size = 0.2,random_state=0,shuffle=True)"
      ],
      "metadata": {
        "id": "t2-SqMbIc6dG"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## ML"
      ],
      "metadata": {
        "id": "rSdQ0mQ7ga9j"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.linear_model import LogisticRegression\n",
        "clf = LogisticRegression(random_state=0,max_iter=500,multi_class='auto',C=1.0)\n",
        "start = time.time()\n",
        "clf.fit(X_train, Y_train)\n",
        "stop = time.time()\n",
        "print(f\"Training time: {stop - start}s\")\n",
        "dtP3=clf.predict(X_test)\n",
        "print('accuracy score',accuracy_score(Y_test,dtP3))\n",
        "print('error rate:',1-accuracy_score(Y_test,dtP3))\n",
        "print(classification_report(Y_test,dtP3))\n",
        "kf = KFold(n_splits=10, shuffle=True)\n",
        "clf = LogisticRegression(random_state=0,max_iter=500,multi_class='auto',C=1.0)\n",
        "score = cross_val_score(clf, result, y, cv= kf, scoring=\"accuracy\")\n",
        "print(\"%0.4f accuracy with a standard deviation of %0.4f\" % (score.mean(), score.std()))\n",
        "cf_matrix=confusion_matrix(Y_test,dtP3)\n",
        "cf_matrix"
      ],
      "metadata": {
        "id": "ka0UDjEfMvDl",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "0ac94147-4ae8-4abb-8c40-db452b291ac8"
      },
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Training time: 0.3015613555908203s\n",
            "accuracy score 0.975\n",
            "error rate: 0.025000000000000022\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "           1       1.00      1.00      1.00        37\n",
            "           2       1.00      0.92      0.96        39\n",
            "           3       0.92      1.00      0.96        35\n",
            "           4       0.98      0.98      0.98        48\n",
            "           5       0.98      0.98      0.98        41\n",
            "\n",
            "    accuracy                           0.97       200\n",
            "   macro avg       0.98      0.98      0.97       200\n",
            "weighted avg       0.98      0.97      0.98       200\n",
            "\n",
            "0.9700 accuracy with a standard deviation of 0.0214\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[37,  0,  0,  0,  0],\n",
              "       [ 0, 36,  2,  1,  0],\n",
              "       [ 0,  0, 35,  0,  0],\n",
              "       [ 0,  0,  0, 47,  1],\n",
              "       [ 0,  0,  1,  0, 40]])"
            ]
          },
          "metadata": {},
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.svm import LinearSVC\n",
        "print(\"SVC\")\n",
        "clf = LinearSVC(random_state=0,max_iter=1000)\n",
        "start = time.time()\n",
        "clf.fit(X_train, Y_train)\n",
        "stop = time.time()\n",
        "print(f\"Training time: {stop - start}s\")\n",
        "dtP3=clf.predict(X_test)\n",
        "print('accuracy score',accuracy_score(Y_test,dtP3))\n",
        "print('error rate:',1-accuracy_score(Y_test,dtP3))\n",
        "print(classification_report(Y_test,dtP3))\n",
        "kf = KFold(n_splits=10, shuffle=True)\n",
        "clf = LinearSVC(random_state=0,max_iter=1000)\n",
        "score = cross_val_score(clf, result, y, cv= kf, scoring=\"accuracy\")\n",
        "print(\"%0.4f accuracy with a standard deviation of %0.4f\" % (score.mean(), score.std()))\n",
        "cf_matrix=confusion_matrix(Y_test,dtP3)\n",
        "cf_matrix"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xetWPws8aHFO",
        "outputId": "34603b78-8b26-4420-fab5-a8f74eb7f82f"
      },
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "SVC\n",
            "Training time: 0.2347567081451416s\n",
            "accuracy score 0.255\n",
            "error rate: 0.745\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "           1       1.00      0.16      0.28        37\n",
            "           2       0.21      1.00      0.34        39\n",
            "           3       1.00      0.06      0.11        35\n",
            "           4       1.00      0.08      0.15        48\n",
            "           5       0.00      0.00      0.00        41\n",
            "\n",
            "    accuracy                           0.26       200\n",
            "   macro avg       0.64      0.26      0.18       200\n",
            "weighted avg       0.64      0.26      0.17       200\n",
            "\n",
            "0.6440 accuracy with a standard deviation of 0.1796\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[ 6, 31,  0,  0,  0],\n",
              "       [ 0, 39,  0,  0,  0],\n",
              "       [ 0, 33,  2,  0,  0],\n",
              "       [ 0, 44,  0,  4,  0],\n",
              "       [ 0, 41,  0,  0,  0]])"
            ]
          },
          "metadata": {},
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.ensemble import RandomForestClassifier\n",
        "print(\"RF\")\n",
        "clf = RandomForestClassifier(n_estimators=300,max_depth=300, random_state=0)\n",
        "start = time.time()\n",
        "clf.fit(X_train, Y_train)\n",
        "stop = time.time()\n",
        "print(f\"Training time: {stop - start}s\")\n",
        "dtP3=clf.predict(X_test)\n",
        "print('accuracy score',accuracy_score(Y_test,dtP3))\n",
        "print('error rate:',1-accuracy_score(Y_test,dtP3))\n",
        "print(classification_report(Y_test,dtP3))\n",
        "kf = KFold(n_splits=10, shuffle=True)\n",
        "clf = RandomForestClassifier(n_estimators=300,max_depth=300, random_state=0)\n",
        "score = cross_val_score(clf, result, y, cv= kf, scoring=\"accuracy\")\n",
        "print(\"%0.4f accuracy with a standard deviation of %0.4f\" % (score.mean(), score.std()))\n",
        "cf_matrix=confusion_matrix(Y_test,dtP3)\n",
        "cf_matrix"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "lZycB2r5aUDU",
        "outputId": "2a80ae6a-6309-4d7b-cb71-608e504d2097"
      },
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "RF\n",
            "Training time: 1.0338032245635986s\n",
            "accuracy score 0.985\n",
            "error rate: 0.015000000000000013\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "           1       1.00      1.00      1.00        37\n",
            "           2       1.00      0.95      0.97        39\n",
            "           3       0.97      1.00      0.99        35\n",
            "           4       0.98      0.98      0.98        48\n",
            "           5       0.98      1.00      0.99        41\n",
            "\n",
            "    accuracy                           0.98       200\n",
            "   macro avg       0.99      0.99      0.99       200\n",
            "weighted avg       0.99      0.98      0.98       200\n",
            "\n",
            "0.9790 accuracy with a standard deviation of 0.0130\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[37,  0,  0,  0,  0],\n",
              "       [ 0, 37,  1,  1,  0],\n",
              "       [ 0,  0, 35,  0,  0],\n",
              "       [ 0,  0,  0, 47,  1],\n",
              "       [ 0,  0,  0,  0, 41]])"
            ]
          },
          "metadata": {},
          "execution_count": 24
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "array1=[[37,  0,  0,  0,  0],\n",
        "       [ 0, 36,  2,  1,  0],\n",
        "       [ 0,  0, 35,  0,  0],\n",
        "       [ 0,  0,  0, 47,  1],\n",
        "       [ 0,  0,  1,  0, 40]]\n",
        "\n",
        "array2=[[37,  0,  0,  0,  0],\n",
        "       [ 0, 37,  1,  1,  0],\n",
        "       [ 0,  0, 35,  0,  0],\n",
        "       [ 0,  0,  0, 47,  1],\n",
        "       [ 0,  0,  0,  0, 41]]\n",
        "\n",
        "array3=[[ 6, 31,  0,  0,  0],\n",
        "       [ 0, 39,  0,  0,  0],\n",
        "       [ 0, 33,  2,  0,  0],\n",
        "       [ 0, 44,  0,  4,  0],\n",
        "       [ 0, 41,  0,  0,  0]]\n",
        "\n",
        "array4=[[36,  1,  0,  0,  0],\n",
        "       [ 1, 36,  1,  1,  0],\n",
        "       [ 0,  0, 35,  0,  0],\n",
        "       [ 0,  0,  0, 47,  1],\n",
        "       [ 4,  0,  0,  2, 35]]\n"
      ],
      "metadata": {
        "id": "1q9LIlsCotuj"
      },
      "execution_count": 30,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Create a figure with 8 subplots\n",
        "fig, axes = plt.subplots(nrows=2, ncols=2, figsize=(7, 5),dpi=200)\n",
        "\n",
        "# Set title for the whole figure\n",
        "# fig.suptitle('Confusion matrices', fontsize=16)\n",
        "\n",
        "# Create a list of confusion matrices and corresponding titles\n",
        "cms =    [array1, array2, array3, array4]\n",
        "titles = ['LR'  ,'RF',   'SVM',  'GRU',]\n",
        "\n",
        "# Plot each confusion matrix as a heatmap on a subplot\n",
        "for ax, cm, title in zip(axes.flat, cms, titles):\n",
        "    sns.heatmap(cm, annot=True, cmap='Blues', ax=ax,fmt='g')\n",
        "    ax.set_title(title)\n",
        "    ax.set_xlabel('Predicted label')\n",
        "    ax.set_ylabel('True label')\n",
        "# Adjust spacing between subplots\n",
        "plt.subplots_adjust(hspace=0.4, wspace=0.4)\n",
        "\n",
        "# Display the figure\n",
        "plt.savefig('froncm.pdf')\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 927
        },
        "id": "F3QY4hcuWV5S",
        "outputId": "c3c0d221-e52e-49db-e27d-9093d12b1ba3"
      },
      "execution_count": 36,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1400x1000 with 8 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## GRU"
      ],
      "metadata": {
        "id": "ahVziGA5gXll"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "result = pd.concat([pl,rf], axis=1).reindex(pl.index)\n",
        "from sklearn.model_selection import train_test_split\n",
        "df['ImmersionLevel'] = df['ImmersionLevel'].map({1:0,\n",
        "                 2: 1,\n",
        "                 3: 2,\n",
        "                 4:3,\n",
        "                 5:4})\n",
        "y=df['ImmersionLevel']\n",
        "X_train, X_test, Y_train, Y_test = train_test_split(result,y,test_size = 0.2,random_state=0,shuffle=True)"
      ],
      "metadata": {
        "id": "9ok3s8lrY8HE"
      },
      "execution_count": 26,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from keras.models import Sequential\n",
        "from tensorflow.keras.utils import to_categorical\n",
        "from keras.layers import Dense, LSTM,GRU,Dropout\n",
        "# Build the LSTM model\n",
        "model = Sequential()\n",
        "model.add(GRU(64, input_shape= (X_train.shape[1], 1)))\n",
        "model.add(Dense(32,activation='relu'))\n",
        "model.add(Dropout(0.02))\n",
        "model.add(Dense(5,activation='softmax'))\n",
        "model.compile(loss = 'categorical_crossentropy',optimizer = 'adam' ,metrics=['accuracy'])\n",
        "print(model.summary())\n",
        "start = time.time()\n",
        "history=model.fit(X_train, to_categorical(Y_train, num_classes=5), validation_split=0.1, epochs=10)\n",
        "stop = time.time()\n",
        "print(f\"Training time: {stop - start}s\")\n",
        "\n",
        "import matplotlib.ticker as mticker\n",
        "import matplotlib.pyplot as plt\n",
        "plt.figure(figsize = (6, 3.5), dpi = 200)\n",
        "plt.plot(history.history['loss'], label='train loss')\n",
        "plt.plot(history.history['val_loss'], label='val loss')\n",
        "plt.plot(history.history['accuracy'], label='train accuracy')\n",
        "plt.plot(history.history['val_accuracy'], label='val accuracy')\n",
        "plt.gca().xaxis.set_major_locator(mticker.MultipleLocator(1))\n",
        "plt.xlabel(\"Epoch\")\n",
        "plt.ylabel(\"Score\")\n",
        "plt.legend()\n",
        "plt.show()\n",
        "\n",
        "scores = model.predict(X_test)\n",
        "print('accuracy score',accuracy_score(Y_test,scores.argmax(axis=1)))\n",
        "print('error rate:',1-accuracy_score(Y_test,scores.argmax(axis=1)))\n",
        "print(classification_report(Y_test,scores.argmax(axis=1)))\n",
        "cf_matrix=confusion_matrix(Y_test,scores.argmax(axis=1))\n",
        "cf_matrix"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "60n2EEkJdqjH",
        "outputId": "feca14bb-9fe0-42d4-c065-c8f5031dd5e6"
      },
      "execution_count": 28,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Model: \"sequential_2\"\n",
            "_________________________________________________________________\n",
            " Layer (type)                Output Shape              Param #   \n",
            "=================================================================\n",
            " gru (GRU)                   (None, 64)                12864     \n",
            "                                                                 \n",
            " dense_4 (Dense)             (None, 32)                2080      \n",
            "                                                                 \n",
            " dropout_2 (Dropout)         (None, 32)                0         \n",
            "                                                                 \n",
            " dense_5 (Dense)             (None, 5)                 165       \n",
            "                                                                 \n",
            "=================================================================\n",
            "Total params: 15,109\n",
            "Trainable params: 15,109\n",
            "Non-trainable params: 0\n",
            "_________________________________________________________________\n",
            "None\n",
            "Epoch 1/10\n",
            "23/23 [==============================] - 4s 24ms/step - loss: 1.6065 - accuracy: 0.2139 - val_loss: 1.6142 - val_accuracy: 0.1625\n",
            "Epoch 2/10\n",
            "23/23 [==============================] - 0s 6ms/step - loss: 1.5929 - accuracy: 0.2264 - val_loss: 1.6005 - val_accuracy: 0.1500\n",
            "Epoch 3/10\n",
            "23/23 [==============================] - 0s 6ms/step - loss: 1.5726 - accuracy: 0.2667 - val_loss: 1.5795 - val_accuracy: 0.2625\n",
            "Epoch 4/10\n",
            "23/23 [==============================] - 0s 6ms/step - loss: 1.5385 - accuracy: 0.3361 - val_loss: 1.5402 - val_accuracy: 0.2750\n",
            "Epoch 5/10\n",
            "23/23 [==============================] - 0s 6ms/step - loss: 1.4621 - accuracy: 0.3847 - val_loss: 1.4449 - val_accuracy: 0.2750\n",
            "Epoch 6/10\n",
            "23/23 [==============================] - 0s 6ms/step - loss: 1.2878 - accuracy: 0.4847 - val_loss: 1.2164 - val_accuracy: 0.4375\n",
            "Epoch 7/10\n",
            "23/23 [==============================] - 0s 6ms/step - loss: 1.0502 - accuracy: 0.6319 - val_loss: 1.0285 - val_accuracy: 0.6125\n",
            "Epoch 8/10\n",
            "23/23 [==============================] - 0s 5ms/step - loss: 0.8082 - accuracy: 0.8056 - val_loss: 0.6676 - val_accuracy: 0.8750\n",
            "Epoch 9/10\n",
            "23/23 [==============================] - 0s 6ms/step - loss: 0.5649 - accuracy: 0.8861 - val_loss: 0.4411 - val_accuracy: 0.9375\n",
            "Epoch 10/10\n",
            "23/23 [==============================] - 0s 5ms/step - loss: 0.4069 - accuracy: 0.9125 - val_loss: 0.2982 - val_accuracy: 0.9375\n",
            "Training time: 5.316595792770386s\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1200x700 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "7/7 [==============================] - 0s 3ms/step\n",
            "accuracy score 0.945\n",
            "error rate: 0.05500000000000005\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       0.88      0.97      0.92        37\n",
            "           1       0.97      0.92      0.95        39\n",
            "           2       0.97      1.00      0.99        35\n",
            "           3       0.94      0.98      0.96        48\n",
            "           4       0.97      0.85      0.91        41\n",
            "\n",
            "    accuracy                           0.94       200\n",
            "   macro avg       0.95      0.95      0.94       200\n",
            "weighted avg       0.95      0.94      0.94       200\n",
            "\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[36,  1,  0,  0,  0],\n",
              "       [ 1, 36,  1,  1,  0],\n",
              "       [ 0,  0, 35,  0,  0],\n",
              "       [ 0,  0,  0, 47,  1],\n",
              "       [ 4,  0,  0,  2, 35]])"
            ]
          },
          "metadata": {},
          "execution_count": 28
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from tensorflow.keras.wrappers.scikit_learn import KerasClassifier\n",
        "from sklearn.model_selection import cross_val_score\n",
        "\n",
        "def create_model():\n",
        "  model = Sequential()\n",
        "  model.add(GRU(64, input_shape= (X_train.shape[1], 1)))\n",
        "  model.add(Dense(32,activation='relu'))\n",
        "  model.add(Dropout(0.02))\n",
        "  model.add(Dense(5,activation='softmax'))\n",
        "  model.compile(loss = 'categorical_crossentropy',optimizer = 'adam' ,metrics=['accuracy'])\n",
        "  return model\n",
        "\n",
        "estimator = KerasClassifier(\n",
        "    build_fn=create_model,\n",
        "    epochs = 10,\n",
        "    verbose=1\n",
        ")\n",
        "cv_scores = cross_val_score(estimator,\n",
        "                            result,to_categorical(y, num_classes=5),\n",
        "                            cv=10\n",
        "                           )\n",
        "# cv_scores.mean()\n",
        "print(\"%0.4f accuracy with a standard deviation of %0.4f\" % (cv_scores.mean(), cv_scores.std()))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "J_yiiw5LfSx6",
        "outputId": "108ae15b-e6e3-4f9e-cf39-9cf8488411b1"
      },
      "execution_count": 29,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/10\n",
            "29/29 [==============================] - 3s 6ms/step - loss: 1.6042 - accuracy: 0.2322\n",
            "Epoch 2/10\n",
            "29/29 [==============================] - 0s 5ms/step - loss: 1.5889 - accuracy: 0.3422\n",
            "Epoch 3/10\n",
            "29/29 [==============================] - 0s 6ms/step - loss: 1.5625 - accuracy: 0.3367\n",
            "Epoch 4/10\n",
            "29/29 [==============================] - 0s 6ms/step - loss: 1.5005 - accuracy: 0.4589\n",
            "Epoch 5/10\n",
            "29/29 [==============================] - 0s 6ms/step - loss: 1.3441 - accuracy: 0.5556\n",
            "Epoch 6/10\n",
            "29/29 [==============================] - 0s 6ms/step - loss: 1.0094 - accuracy: 0.6656\n",
            "Epoch 7/10\n",
            "29/29 [==============================] - 0s 7ms/step - loss: 0.6810 - accuracy: 0.7822\n",
            "Epoch 8/10\n",
            "29/29 [==============================] - 0s 6ms/step - loss: 0.5092 - accuracy: 0.8444\n",
            "Epoch 9/10\n",
            "29/29 [==============================] - 0s 7ms/step - loss: 0.3711 - accuracy: 0.9000\n",
            "Epoch 10/10\n",
            "29/29 [==============================] - 0s 6ms/step - loss: 0.2805 - accuracy: 0.9322\n",
            "4/4 [==============================] - 0s 4ms/step - loss: 0.2165 - accuracy: 0.9100\n",
            "Epoch 1/10\n",
            "29/29 [==============================] - 4s 7ms/step - loss: 1.6066 - accuracy: 0.2367\n",
            "Epoch 2/10\n",
            "29/29 [==============================] - 0s 8ms/step - loss: 1.5873 - accuracy: 0.3022\n",
            "Epoch 3/10\n",
            "29/29 [==============================] - 0s 6ms/step - loss: 1.5516 - accuracy: 0.3800\n",
            "Epoch 4/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.4627 - accuracy: 0.4456\n",
            "Epoch 5/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.2694 - accuracy: 0.5456\n",
            "Epoch 6/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.0000 - accuracy: 0.6689\n",
            "Epoch 7/10\n",
            "29/29 [==============================] - 0s 8ms/step - loss: 0.6953 - accuracy: 0.8456\n",
            "Epoch 8/10\n",
            "29/29 [==============================] - 0s 9ms/step - loss: 0.4517 - accuracy: 0.9044\n",
            "Epoch 9/10\n",
            "29/29 [==============================] - 0s 6ms/step - loss: 0.3025 - accuracy: 0.9267\n",
            "Epoch 10/10\n",
            "29/29 [==============================] - 0s 7ms/step - loss: 0.2355 - accuracy: 0.9322\n",
            "4/4 [==============================] - 0s 5ms/step - loss: 0.2824 - accuracy: 0.9100\n",
            "Epoch 1/10\n",
            "29/29 [==============================] - 3s 5ms/step - loss: 1.6016 - accuracy: 0.1800\n",
            "Epoch 2/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.5826 - accuracy: 0.3844\n",
            "Epoch 3/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.5427 - accuracy: 0.4156\n",
            "Epoch 4/10\n",
            "29/29 [==============================] - 0s 6ms/step - loss: 1.4543 - accuracy: 0.4511\n",
            "Epoch 5/10\n",
            "29/29 [==============================] - 0s 6ms/step - loss: 1.2623 - accuracy: 0.5989\n",
            "Epoch 6/10\n",
            "29/29 [==============================] - 0s 7ms/step - loss: 0.9622 - accuracy: 0.6711\n",
            "Epoch 7/10\n",
            "29/29 [==============================] - 0s 6ms/step - loss: 0.6611 - accuracy: 0.8267\n",
            "Epoch 8/10\n",
            "29/29 [==============================] - 0s 6ms/step - loss: 0.4281 - accuracy: 0.8967\n",
            "Epoch 9/10\n",
            "29/29 [==============================] - 0s 6ms/step - loss: 0.2956 - accuracy: 0.9211\n",
            "Epoch 10/10\n",
            "29/29 [==============================] - 0s 6ms/step - loss: 0.2372 - accuracy: 0.9322\n",
            "4/4 [==============================] - 1s 8ms/step - loss: 0.2821 - accuracy: 0.9100\n",
            "Epoch 1/10\n",
            "29/29 [==============================] - 2s 5ms/step - loss: 1.6081 - accuracy: 0.2022\n",
            "Epoch 2/10\n",
            "29/29 [==============================] - 0s 5ms/step - loss: 1.5979 - accuracy: 0.2144\n",
            "Epoch 3/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.5796 - accuracy: 0.2722\n",
            "Epoch 4/10\n",
            "29/29 [==============================] - 0s 5ms/step - loss: 1.5435 - accuracy: 0.3544\n",
            "Epoch 5/10\n",
            "29/29 [==============================] - 0s 5ms/step - loss: 1.4623 - accuracy: 0.4122\n",
            "Epoch 6/10\n",
            "29/29 [==============================] - 0s 5ms/step - loss: 1.2393 - accuracy: 0.5622\n",
            "Epoch 7/10\n",
            "29/29 [==============================] - 0s 5ms/step - loss: 0.9222 - accuracy: 0.6778\n",
            "Epoch 8/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 0.6409 - accuracy: 0.8300\n",
            "Epoch 9/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 0.4274 - accuracy: 0.8911\n",
            "Epoch 10/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 0.3066 - accuracy: 0.9289\n",
            "4/4 [==============================] - 0s 5ms/step - loss: 0.2795 - accuracy: 0.9100\n",
            "Epoch 1/10\n",
            "29/29 [==============================] - 2s 5ms/step - loss: 1.5986 - accuracy: 0.2744\n",
            "Epoch 2/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.5738 - accuracy: 0.2933\n",
            "Epoch 3/10\n",
            "29/29 [==============================] - 0s 5ms/step - loss: 1.5361 - accuracy: 0.4222\n",
            "Epoch 4/10\n",
            "29/29 [==============================] - 0s 5ms/step - loss: 1.4529 - accuracy: 0.4422\n",
            "Epoch 5/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.2831 - accuracy: 0.5422\n",
            "Epoch 6/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.0120 - accuracy: 0.6356\n",
            "Epoch 7/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 0.6861 - accuracy: 0.8356\n",
            "Epoch 8/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 0.4933 - accuracy: 0.8756\n",
            "Epoch 9/10\n",
            "29/29 [==============================] - 0s 5ms/step - loss: 0.3366 - accuracy: 0.9167\n",
            "Epoch 10/10\n",
            "29/29 [==============================] - 0s 5ms/step - loss: 0.2903 - accuracy: 0.9200\n",
            "4/4 [==============================] - 0s 5ms/step - loss: 0.2823 - accuracy: 0.9100\n",
            "Epoch 1/10\n",
            "29/29 [==============================] - 3s 4ms/step - loss: 1.6072 - accuracy: 0.2078\n",
            "Epoch 2/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.5867 - accuracy: 0.2478\n",
            "Epoch 3/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.5523 - accuracy: 0.3422\n",
            "Epoch 4/10\n",
            "29/29 [==============================] - 0s 5ms/step - loss: 1.4874 - accuracy: 0.4300\n",
            "Epoch 5/10\n",
            "29/29 [==============================] - 0s 5ms/step - loss: 1.2678 - accuracy: 0.6111\n",
            "Epoch 6/10\n",
            "29/29 [==============================] - 0s 5ms/step - loss: 0.8259 - accuracy: 0.7278\n",
            "Epoch 7/10\n",
            "29/29 [==============================] - 0s 5ms/step - loss: 0.5089 - accuracy: 0.8767\n",
            "Epoch 8/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 0.3388 - accuracy: 0.9089\n",
            "Epoch 9/10\n",
            "29/29 [==============================] - 0s 5ms/step - loss: 0.3101 - accuracy: 0.9056\n",
            "Epoch 10/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 0.2406 - accuracy: 0.9289\n",
            "4/4 [==============================] - 0s 5ms/step - loss: 0.2556 - accuracy: 0.9600\n",
            "Epoch 1/10\n",
            "29/29 [==============================] - 3s 5ms/step - loss: 1.6080 - accuracy: 0.2189\n",
            "Epoch 2/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.5858 - accuracy: 0.3144\n",
            "Epoch 3/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.5534 - accuracy: 0.3756\n",
            "Epoch 4/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.4901 - accuracy: 0.4367\n",
            "Epoch 5/10\n",
            "29/29 [==============================] - 0s 5ms/step - loss: 1.3224 - accuracy: 0.5922\n",
            "Epoch 6/10\n",
            "29/29 [==============================] - 0s 5ms/step - loss: 1.0145 - accuracy: 0.6878\n",
            "Epoch 7/10\n",
            "29/29 [==============================] - 0s 5ms/step - loss: 0.6386 - accuracy: 0.8478\n",
            "Epoch 8/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 0.4605 - accuracy: 0.8522\n",
            "Epoch 9/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 0.3269 - accuracy: 0.9067\n",
            "Epoch 10/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 0.3145 - accuracy: 0.9022\n",
            "4/4 [==============================] - 0s 5ms/step - loss: 0.3591 - accuracy: 0.9000\n",
            "Epoch 1/10\n",
            "29/29 [==============================] - 3s 6ms/step - loss: 1.6082 - accuracy: 0.1844\n",
            "Epoch 2/10\n",
            "29/29 [==============================] - 0s 7ms/step - loss: 1.5962 - accuracy: 0.2211\n",
            "Epoch 3/10\n",
            "29/29 [==============================] - 0s 6ms/step - loss: 1.5759 - accuracy: 0.3278\n",
            "Epoch 4/10\n",
            "29/29 [==============================] - 0s 6ms/step - loss: 1.5366 - accuracy: 0.3378\n",
            "Epoch 5/10\n",
            "29/29 [==============================] - 0s 6ms/step - loss: 1.4501 - accuracy: 0.4033\n",
            "Epoch 6/10\n",
            "29/29 [==============================] - 0s 6ms/step - loss: 1.2206 - accuracy: 0.5978\n",
            "Epoch 7/10\n",
            "29/29 [==============================] - 0s 6ms/step - loss: 0.8242 - accuracy: 0.7911\n",
            "Epoch 8/10\n",
            "29/29 [==============================] - 0s 6ms/step - loss: 0.4637 - accuracy: 0.8978\n",
            "Epoch 9/10\n",
            "29/29 [==============================] - 0s 6ms/step - loss: 0.2631 - accuracy: 0.9378\n",
            "Epoch 10/10\n",
            "29/29 [==============================] - 0s 6ms/step - loss: 0.1831 - accuracy: 0.9578\n",
            "4/4 [==============================] - 1s 5ms/step - loss: 0.1726 - accuracy: 0.9600\n",
            "Epoch 1/10\n",
            "29/29 [==============================] - 2s 5ms/step - loss: 1.6035 - accuracy: 0.2422\n",
            "Epoch 2/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.5867 - accuracy: 0.3444\n",
            "Epoch 3/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.5548 - accuracy: 0.4489\n",
            "Epoch 4/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.4915 - accuracy: 0.4611\n",
            "Epoch 5/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.3189 - accuracy: 0.5011\n",
            "Epoch 6/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.0280 - accuracy: 0.6678\n",
            "Epoch 7/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 0.7415 - accuracy: 0.7933\n",
            "Epoch 8/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 0.5471 - accuracy: 0.8456\n",
            "Epoch 9/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 0.3716 - accuracy: 0.9167\n",
            "Epoch 10/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 0.3027 - accuracy: 0.9267\n",
            "4/4 [==============================] - 0s 5ms/step - loss: 0.2245 - accuracy: 0.9500\n",
            "Epoch 1/10\n",
            "29/29 [==============================] - 3s 4ms/step - loss: 1.5942 - accuracy: 0.2944\n",
            "Epoch 2/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.5648 - accuracy: 0.3856\n",
            "Epoch 3/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.5158 - accuracy: 0.3667\n",
            "Epoch 4/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.4304 - accuracy: 0.4367\n",
            "Epoch 5/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.2712 - accuracy: 0.5367\n",
            "Epoch 6/10\n",
            "29/29 [==============================] - 0s 4ms/step - loss: 1.0128 - accuracy: 0.6844\n",
            "Epoch 7/10\n",
            "29/29 [==============================] - 0s 5ms/step - loss: 0.7310 - accuracy: 0.7989\n",
            "Epoch 8/10\n",
            "29/29 [==============================] - 0s 5ms/step - loss: 0.4814 - accuracy: 0.8933\n",
            "Epoch 9/10\n",
            "29/29 [==============================] - 0s 5ms/step - loss: 0.3378 - accuracy: 0.9233\n",
            "Epoch 10/10\n",
            "29/29 [==============================] - 0s 5ms/step - loss: 0.2438 - accuracy: 0.9367\n",
            "4/4 [==============================] - 0s 7ms/step - loss: 0.0893 - accuracy: 0.9900\n",
            "0.9310 accuracy with a standard deviation of 0.0295\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Explainable AI"
      ],
      "metadata": {
        "id": "CTIHUu9KMk5n"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "pip install shap"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "mQMu6_pANBAY",
        "outputId": "325f28dd-2034-4fbc-ab4b-e66ee7052f8c"
      },
      "execution_count": 37,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting shap\n",
            "  Downloading shap-0.41.0-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (572 kB)\n",
            "\u001b[?25l     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/572.6 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K     \u001b[91m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[90m╺\u001b[0m \u001b[32m563.2/572.6 kB\u001b[0m \u001b[31m22.8 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m572.6/572.6 kB\u001b[0m \u001b[31m15.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from shap) (1.22.4)\n",
            "Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from shap) (1.10.1)\n",
            "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (from shap) (1.2.2)\n",
            "Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from shap) (1.5.3)\n",
            "Requirement already satisfied: tqdm>4.25.0 in /usr/local/lib/python3.10/dist-packages (from shap) (4.65.0)\n",
            "Requirement already satisfied: packaging>20.9 in /usr/local/lib/python3.10/dist-packages (from shap) (23.1)\n",
            "Collecting slicer==0.0.7 (from shap)\n",
            "  Downloading slicer-0.0.7-py3-none-any.whl (14 kB)\n",
            "Requirement already satisfied: numba in /usr/local/lib/python3.10/dist-packages (from shap) (0.56.4)\n",
            "Requirement already satisfied: cloudpickle in /usr/local/lib/python3.10/dist-packages (from shap) (2.2.1)\n",
            "Requirement already satisfied: llvmlite<0.40,>=0.39.0dev0 in /usr/local/lib/python3.10/dist-packages (from numba->shap) (0.39.1)\n",
            "Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from numba->shap) (67.7.2)\n",
            "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->shap) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->shap) (2022.7.1)\n",
            "Requirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->shap) (1.2.0)\n",
            "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->shap) (3.1.0)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas->shap) (1.16.0)\n",
            "Installing collected packages: slicer, shap\n",
            "Successfully installed shap-0.41.0 slicer-0.0.7\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "result.columns = ['f1', 'f2', 'f3','f4','f5','f6', 'f7', 'f8','f9','f10','f11']"
      ],
      "metadata": {
        "id": "G0gExPoSPhT8"
      },
      "execution_count": 40,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "X_train, X_test, Y_train, Y_test = train_test_split(result,y, test_size = 0.2,random_state=0,shuffle=True)"
      ],
      "metadata": {
        "id": "8zKaHWDpNn6O"
      },
      "execution_count": 41,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# import necessary libraries\n",
        "import pandas as pd\n",
        "import numpy as np\n",
        "from sklearn.ensemble import RandomForestClassifier\n",
        "import shap\n",
        "\n",
        "\n",
        "\n",
        "rf = RandomForestClassifier(n_estimators=300,max_depth=300, random_state=0)\n",
        "rf.fit(X_train, Y_train)\n",
        "\n",
        "\n",
        "# # calculate SHAP values\n",
        "explainer = shap.TreeExplainer(rf)\n",
        "shap_values = explainer.shap_values(X_test)\n",
        "\n",
        "# visualize feature importance using SHAP summary plot\n",
        "shap.summary_plot(shap_values[1], X_test)\n",
        "\n",
        "# shap.initjs()\n",
        "# shap.force_plot(explainer.expected_value[1], shap_values[1], X_test)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 596
        },
        "id": "hdmnyNV5NDrv",
        "outputId": "ee1c0e76-b225-42a6-9713-bd3145adf4d5"
      },
      "execution_count": 42,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x590 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    }
  ]
}