Part 0.4: LanguageDetection.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/gulabpatel/NLP_Basics/blob/main/Part%200.4%3A%20LanguageDetection.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Language Detection\n",
        "\n",
        "Download the Dataset from https://www.kaggle.com/datasets/basilb2s/language-detection, then extract it and upload the csv file to this Notebook."
      ],
      "metadata": {
        "id": "ip4Ozho_eq5q"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "import re\n",
        "import seaborn as sns\n",
        "import matplotlib.pyplot as plt\n",
        "import pickle\n",
        "\n",
        "import warnings\n",
        "warnings.simplefilter(\"ignore\")"
      ],
      "metadata": {
        "id": "_wfbMocKOdDU"
      },
      "execution_count": 1,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Loading the dataset\n",
        "data = pd.read_csv(\"Language Detection.csv\")"
      ],
      "metadata": {
        "id": "1num6DmROi3v"
      },
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "data.head()"
      ],
      "metadata": {
        "id": "ew65hwK2OmbV",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "outputId": "8726f13b-8b02-4091-d95c-127d4da9e12f"
      },
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                                                Text Language\n",
              "0   Nature, in the broadest sense, is the natural...  English\n",
              "1  \"Nature\" can refer to the phenomena of the phy...  English\n",
              "2  The study of nature is a large, if not the onl...  English\n",
              "3  Although humans are part of nature, human acti...  English\n",
              "4  [1] The word nature is borrowed from the Old F...  English"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-6f902fe7-190a-4585-adf0-af6410cafbe8\">\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>Text</th>\n",
              "      <th>Language</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Nature, in the broadest sense, is the natural...</td>\n",
              "      <td>English</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>\"Nature\" can refer to the phenomena of the phy...</td>\n",
              "      <td>English</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>The study of nature is a large, if not the onl...</td>\n",
              "      <td>English</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Although humans are part of nature, human acti...</td>\n",
              "      <td>English</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>[1] The word nature is borrowed from the Old F...</td>\n",
              "      <td>English</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-6f902fe7-190a-4585-adf0-af6410cafbe8')\"\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-6f902fe7-190a-4585-adf0-af6410cafbe8 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-6f902fe7-190a-4585-adf0-af6410cafbe8');\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": 3
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "X = data[\"Text\"]\n",
        "y = data[\"Language\"]"
      ],
      "metadata": {
        "id": "UNLDZdv8Oqc6"
      },
      "execution_count": 4,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.preprocessing import LabelEncoder\n",
        "le = LabelEncoder()\n",
        "y = le.fit_transform(y)"
      ],
      "metadata": {
        "id": "oFKJwjL4OtFa"
      },
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "le.classes_"
      ],
      "metadata": {
        "id": "JBlI5__q-kAQ",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "72772d73-dbd4-48c8-a951-981065cbe310"
      },
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array(['Arabic', 'Danish', 'Dutch', 'English', 'French', 'German',\n",
              "       'Greek', 'Hindi', 'Italian', 'Kannada', 'Malayalam', 'Portugeese',\n",
              "       'Russian', 'Spanish', 'Sweedish', 'Tamil', 'Turkish'], dtype=object)"
            ]
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data_list = []\n",
        "for text in X:\n",
        "    text = re.sub(r'[!@#$(),\\n\"%^*?\\:;~`0-9]', ' ', text)\n",
        "    text = re.sub(r'[[]]', ' ', text)\n",
        "    text = text.lower()\n",
        "    data_list.append(text)"
      ],
      "metadata": {
        "id": "h7UAAGSKOwgk"
      },
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20)"
      ],
      "metadata": {
        "id": "yLBQzzU9O4AT"
      },
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# creating bag of words using countvectorizer\n",
        "\n",
        "from sklearn.feature_extraction.text import CountVectorizer\n",
        "cv = CountVectorizer()\n",
        "cv.fit(X_train)\n",
        "\n",
        "x_train = cv.transform(X_train).toarray()\n",
        "x_test  = cv.transform(X_test).toarray()"
      ],
      "metadata": {
        "id": "DO93yCpmSoNq"
      },
      "execution_count": 14,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.naive_bayes import MultinomialNB\n",
        "\n",
        "model = MultinomialNB()\n",
        "model.fit(x_train, y_train)"
      ],
      "metadata": {
        "id": "Ogytx3MZO6A_",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "c737f69c-f1d2-4342-c96e-25cf04ddf630"
      },
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "MultinomialNB()"
            ]
          },
          "metadata": {},
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_pred = model.predict(x_test)"
      ],
      "metadata": {
        "id": "seUa1oA3O8OB"
      },
      "execution_count": 16,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.metrics import accuracy_score, confusion_matrix, classification_report\n",
        "\n",
        "ac = accuracy_score(y_test, y_pred)\n",
        "cm = confusion_matrix(y_test, y_pred)\n",
        "cr = classification_report(y_test, y_pred)"
      ],
      "metadata": {
        "id": "YxyjIx1wPGjT"
      },
      "execution_count": 17,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "print(\"Accuracy is :\",ac)"
      ],
      "metadata": {
        "id": "yyswupfjPKGJ",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "f09e59ed-057e-4b6c-bbb2-1597d01fb15f"
      },
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Accuracy is : 0.9743713733075435\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.pipeline import Pipeline\n",
        "\n",
        "pipe = Pipeline([('vectorizer', cv), ('multinomialNB', model)])\n",
        "pipe.fit(X_train, y_train)"
      ],
      "metadata": {
        "id": "T4s4eisKRd24",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "aaed1daa-109e-4ce5-ed0f-4c6d9766fddd"
      },
      "execution_count": 19,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Pipeline(steps=[('vectorizer', CountVectorizer()),\n",
              "                ('multinomialNB', MultinomialNB())])"
            ]
          },
          "metadata": {},
          "execution_count": 19
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_pred2 = pipe.predict(X_test)\n",
        "ac2 = accuracy_score(y_test, y_pred2)\n",
        "print(\"Accuracy is :\",ac2)"
      ],
      "metadata": {
        "id": "3mTMZe4ru7P1",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "de8e3623-27ef-4c21-adaf-fcf0e39336c1"
      },
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Accuracy is : 0.9743713733075435\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "with open('trained_pipeline-0.1.0.pkl','wb') as f:\n",
        "    pickle.dump(pipe, f)"
      ],
      "metadata": {
        "id": "9fbk1qsyUfQf"
      },
      "execution_count": 21,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# If you need to zip and download a folder, you can do it with this command:\n",
        "\n",
        "# !zip -r ./trained_pipeline-0.1.0.pkl.zip ./trained_pipeline-0.1.0.pkl"
      ],
      "metadata": {
        "id": "nxoraEL8VLrr"
      },
      "execution_count": 22,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "text = \"Ciao, come stai?\"\n",
        "y = pipe.predict([text])\n",
        "le.classes_[y[0]], y"
      ],
      "metadata": {
        "id": "2RwoxtHHSIwL",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "6da0f7d1-3551-4633-87c7-89d4d87a60b6"
      },
      "execution_count": 23,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "('Italian', array([8]))"
            ]
          },
          "metadata": {},
          "execution_count": 23
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "text = \"Hello, how are you?\"\n",
        "y = pipe.predict([text])\n",
        "le.classes_[y[0]], y"
      ],
      "metadata": {
        "id": "VFmNG8LkwT7V",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "24c303ca-0d7d-479c-a1cf-cbdde3214f2f"
      },
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "('English', array([3]))"
            ]
          },
          "metadata": {},
          "execution_count": 24
        }
      ]
    }
  ]
}