fake_news_classification_using_BERT.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "fake news classification using BERT.ipynb",
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "code",
      "metadata": {
        "id": "xSOLqxW65W_I",
        "colab_type": "code",
        "outputId": "32adcfee-07c5-4d66-c8e2-f0cc9a653264",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 196
        }
      },
      "source": [
        "#to access kaggle datasets\n",
        "!pip install kaggle"
      ],
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Requirement already satisfied: kaggle in /usr/local/lib/python3.6/dist-packages (1.5.6)\n",
            "Requirement already satisfied: tqdm in /usr/local/lib/python3.6/dist-packages (from kaggle) (4.41.1)\n",
            "Requirement already satisfied: python-dateutil in /usr/local/lib/python3.6/dist-packages (from kaggle) (2.8.1)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.6/dist-packages (from kaggle) (2.23.0)\n",
            "Requirement already satisfied: certifi in /usr/local/lib/python3.6/dist-packages (from kaggle) (2020.4.5.1)\n",
            "Requirement already satisfied: python-slugify in /usr/local/lib/python3.6/dist-packages (from kaggle) (4.0.0)\n",
            "Requirement already satisfied: six>=1.10 in /usr/local/lib/python3.6/dist-packages (from kaggle) (1.12.0)\n",
            "Requirement already satisfied: urllib3<1.25,>=1.21.1 in /usr/local/lib/python3.6/dist-packages (from kaggle) (1.24.3)\n",
            "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests->kaggle) (2.9)\n",
            "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests->kaggle) (3.0.4)\n",
            "Requirement already satisfied: text-unidecode>=1.3 in /usr/local/lib/python3.6/dist-packages (from python-slugify->kaggle) (1.3)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "a1vzZxMC5fQ0",
        "colab_type": "code",
        "outputId": "74a59cec-81f8-4dd6-f17c-19dd932602cd",
        "colab": {
          "resources": {
            "http://localhost:8080/nbextensions/google.colab/files.js": {
              "data": "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",
              "ok": true,
              "headers": [
                [
                  "content-type",
                  "application/javascript"
                ]
              ],
              "status": 200,
              "status_text": ""
            }
          },
          "base_uri": "https://localhost:8080/",
          "height": 88
        }
      },
      "source": [
        "# Colab's file access feature\n",
        "from google.colab import files\n",
        "\n",
        "#retrieve uploaded file\n",
        "uploaded = files.upload()\n",
        "\n",
        "#print results\n",
        "for fn in uploaded.keys():\n",
        "  print('User uploaded file \"{name}\" with length {length} bytes'.format(\n",
        "      name=fn, length=len(uploaded[fn])))\n",
        "  \n",
        "# Then move kaggle.json into the folder where the API expects to find it.\n",
        "!mkdir -p ~/.kaggle/ && mv kaggle.json ~/.kaggle/ && chmod 600 ~/.kaggle/kaggle.json"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "\n",
              "     <input type=\"file\" id=\"files-c990d73c-053f-44e1-872e-22cb2d73f173\" name=\"files[]\" multiple disabled />\n",
              "     <output id=\"result-c990d73c-053f-44e1-872e-22cb2d73f173\">\n",
              "      Upload widget is only available when the cell has been executed in the\n",
              "      current browser session. Please rerun this cell to enable.\n",
              "      </output>\n",
              "      <script src=\"/nbextensions/google.colab/files.js\"></script> "
            ],
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "Saving kaggle.json to kaggle.json\n",
            "User uploaded file \"kaggle.json\" with length 65 bytes\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Aa9E1RjH56Yf",
        "colab_type": "code",
        "outputId": "d32ef0fb-7716-49d3-e90a-2e00caecd04f",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 66
        }
      },
      "source": [
        "!kaggle datasets download -d sid321axn/fakernewsdata/download/fakernewsdata.zip/1"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Downloading fakernewsdata.zip to /content\n",
            " 80% 33.0M/41.0M [00:00<00:00, 29.5MB/s]\n",
            "100% 41.0M/41.0M [00:00<00:00, 44.4MB/s]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4KPwuypt6hl9",
        "colab_type": "code",
        "outputId": "56de5192-199d-4af4-aa13-deb2c70fc0ad",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 82
        }
      },
      "source": [
        "!ls\n",
        "!unzip fakernewsdata.zip\n",
        "!ls"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "fakernewsdata.zip  sample_data\n",
            "Archive:  fakernewsdata.zip\n",
            "  inflating: fake_news.csv           \n",
            "fake_news.csv  fakernewsdata.zip  sample_data\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "PLZBHQbr6-p-",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "import pandas as pd\n",
        "df = pd.read_csv('fake_news.csv')"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "K6qoFLOS7FQf",
        "colab_type": "code",
        "outputId": "249119a9-077f-4bc4-9bbd-a39dda1b4c1f",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 191
        }
      },
      "source": [
        "df.head()"
      ],
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Unnamed: 0</th>\n",
              "      <th>title</th>\n",
              "      <th>text</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0</td>\n",
              "      <td>As U.S. budget fight looms, Republicans flip t...</td>\n",
              "      <td>WASHINGTON (Reuters) - The head of a conservat...</td>\n",
              "      <td>TRUE</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>U.S. military to accept transgender recruits o...</td>\n",
              "      <td>WASHINGTON (Reuters) - Transgender people will...</td>\n",
              "      <td>TRUE</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2</td>\n",
              "      <td>Senior U.S. Republican senator: 'Let Mr. Muell...</td>\n",
              "      <td>WASHINGTON (Reuters) - The special counsel inv...</td>\n",
              "      <td>TRUE</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>3</td>\n",
              "      <td>FBI Russia probe helped by Australian diplomat...</td>\n",
              "      <td>WASHINGTON (Reuters) - Trump campaign adviser ...</td>\n",
              "      <td>TRUE</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>4</td>\n",
              "      <td>Trump wants Postal Service to charge 'much mor...</td>\n",
              "      <td>SEATTLE/WASHINGTON (Reuters) - President Donal...</td>\n",
              "      <td>TRUE</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   Unnamed: 0  ... label\n",
              "0           0  ...  TRUE\n",
              "1           1  ...  TRUE\n",
              "2           2  ...  TRUE\n",
              "3           3  ...  TRUE\n",
              "4           4  ...  TRUE\n",
              "\n",
              "[5 rows x 4 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "XTlf_mvt7OCa",
        "colab_type": "code",
        "outputId": "4991a4a3-485b-4e7a-8bf2-19cd18dc2e52",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 191
        }
      },
      "source": [
        "import numpy as np\n",
        "df =df.reindex(np.random.permutation(df.index))\n",
        "df.head()"
      ],
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Unnamed: 0</th>\n",
              "      <th>title</th>\n",
              "      <th>text</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>40925</th>\n",
              "      <td>40925</td>\n",
              "      <td>WOW! JILL STEIN’S ‘FIRESIDE CHAT’ Exposes Her ...</td>\n",
              "      <td></td>\n",
              "      <td>FAKE</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>29304</th>\n",
              "      <td>29304</td>\n",
              "      <td>Donald Trump Just Said The DUMBEST Thing Abou...</td>\n",
              "      <td>Donald Trump made a pathetic appearance at Reg...</td>\n",
              "      <td>FAKE</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>16622</th>\n",
              "      <td>16622</td>\n",
              "      <td>EU's Tusk says 'good deal' or 'no deal' on Bre...</td>\n",
              "      <td>BRUSSELS (Reuters) - European Council Presiden...</td>\n",
              "      <td>TRUE</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>28554</th>\n",
              "      <td>28554</td>\n",
              "      <td>Rosie O’Donnell Writes Powerful Poem That Per...</td>\n",
              "      <td>If anyone knows what it s like to be attacked ...</td>\n",
              "      <td>FAKE</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>40764</th>\n",
              "      <td>40764</td>\n",
              "      <td>BOOM! Trump Drains Obama Swamp…Mandates All Am...</td>\n",
              "      <td>President-elect Donald J. Trump s transition s...</td>\n",
              "      <td>FAKE</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "       Unnamed: 0  ... label\n",
              "40925       40925  ...  FAKE\n",
              "29304       29304  ...  FAKE\n",
              "16622       16622  ...  TRUE\n",
              "28554       28554  ...  FAKE\n",
              "40764       40764  ...  FAKE\n",
              "\n",
              "[5 rows x 4 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "_yenFZgX7URF",
        "colab_type": "code",
        "outputId": "60553d5f-2ecf-4870-dc0d-dd1b36d8a0f9",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 191
        }
      },
      "source": [
        "df.drop(['Unnamed: 0'],axis=1, inplace=True)\n",
        "df[\"label\"] = df.label.apply(lambda  x:0 if x=='TRUE' else 1)\n",
        "df.head()\n"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>title</th>\n",
              "      <th>text</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>40925</th>\n",
              "      <td>WOW! JILL STEIN’S ‘FIRESIDE CHAT’ Exposes Her ...</td>\n",
              "      <td></td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>29304</th>\n",
              "      <td>Donald Trump Just Said The DUMBEST Thing Abou...</td>\n",
              "      <td>Donald Trump made a pathetic appearance at Reg...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>16622</th>\n",
              "      <td>EU's Tusk says 'good deal' or 'no deal' on Bre...</td>\n",
              "      <td>BRUSSELS (Reuters) - European Council Presiden...</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>28554</th>\n",
              "      <td>Rosie O’Donnell Writes Powerful Poem That Per...</td>\n",
              "      <td>If anyone knows what it s like to be attacked ...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>40764</th>\n",
              "      <td>BOOM! Trump Drains Obama Swamp…Mandates All Am...</td>\n",
              "      <td>President-elect Donald J. Trump s transition s...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                   title  ... label\n",
              "40925  WOW! JILL STEIN’S ‘FIRESIDE CHAT’ Exposes Her ...  ...     1\n",
              "29304   Donald Trump Just Said The DUMBEST Thing Abou...  ...     1\n",
              "16622  EU's Tusk says 'good deal' or 'no deal' on Bre...  ...     0\n",
              "28554   Rosie O’Donnell Writes Powerful Poem That Per...  ...     1\n",
              "40764  BOOM! Trump Drains Obama Swamp…Mandates All Am...  ...     1\n",
              "\n",
              "[5 rows x 3 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "21OkqyyfceXd",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "spec_chars = [\"!\",'\"',\"#\",\"%\",\"&\",\"'\",\"(\",\")\",\n",
        "              \"*\",\"+\",\",\",\"-\",\".\",\"/\",\":\",\";\",\"<\",\n",
        "              \"=\",\">\",\"?\",\"@\",\"[\",\"\\\\\",\"]\",\"^\",\"_\",\n",
        "              \"`\",\"{\",\"|\",\"}\",\"~\",\"–\"]\n",
        "for char in spec_chars:\n",
        "    df['title'] = df['title'].str.replace(char, ' ')"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "QLo69CpIceks",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 191
        },
        "outputId": "f756b0c9-ca78-4b5c-d463-10acb34dde11"
      },
      "source": [
        "df['title']=df['title'].str.lower()\n",
        "df.head()"
      ],
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>title</th>\n",
              "      <th>text</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>40925</th>\n",
              "      <td>wow  jill stein’s ‘fireside chat’ exposes her ...</td>\n",
              "      <td></td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>29304</th>\n",
              "      <td>donald trump just said the dumbest thing abou...</td>\n",
              "      <td>Donald Trump made a pathetic appearance at Reg...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>16622</th>\n",
              "      <td>eu s tusk says  good deal  or  no deal  on bre...</td>\n",
              "      <td>BRUSSELS (Reuters) - European Council Presiden...</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>28554</th>\n",
              "      <td>rosie o’donnell writes powerful poem that per...</td>\n",
              "      <td>If anyone knows what it s like to be attacked ...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>40764</th>\n",
              "      <td>boom  trump drains obama swamp…mandates all am...</td>\n",
              "      <td>President-elect Donald J. Trump s transition s...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                   title  ... label\n",
              "40925  wow  jill stein’s ‘fireside chat’ exposes her ...  ...     1\n",
              "29304   donald trump just said the dumbest thing abou...  ...     1\n",
              "16622  eu s tusk says  good deal  or  no deal  on bre...  ...     0\n",
              "28554   rosie o’donnell writes powerful poem that per...  ...     1\n",
              "40764  boom  trump drains obama swamp…mandates all am...  ...     1\n",
              "\n",
              "[5 rows x 3 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "3_d9AXA3cer0",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "outputId": "d7ff5f77-0768-4088-c3d6-9bb39b1d83f5"
      },
      "source": [
        "!pip3 install ktrain"
      ],
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Collecting ktrain\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/5e/2e/1dc6da3e0f3006060dde122be4ab5d0bddc1cd248bcdb6c7311d146bdec2/ktrain-0.14.7.tar.gz (25.2MB)\n",
            "\u001b[K     |████████████████████████████████| 25.2MB 135kB/s \n",
            "\u001b[?25hCollecting tensorflow==2.1.0\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/85/d4/c0cd1057b331bc38b65478302114194bd8e1b9c2bbc06e300935c0e93d90/tensorflow-2.1.0-cp36-cp36m-manylinux2010_x86_64.whl (421.8MB)\n",
            "\u001b[K     |████████████████████████████████| 421.8MB 40kB/s \n",
            "\u001b[?25hRequirement already satisfied: scikit-learn>=0.21.3 in /usr/local/lib/python3.6/dist-packages (from ktrain) (0.22.2.post1)\n",
            "Requirement already satisfied: matplotlib>=3.0.0 in /usr/local/lib/python3.6/dist-packages (from ktrain) (3.2.1)\n",
            "Requirement already satisfied: pandas>=1.0.1 in /usr/local/lib/python3.6/dist-packages (from ktrain) (1.0.3)\n",
            "Requirement already satisfied: fastprogress>=0.1.21 in /usr/local/lib/python3.6/dist-packages (from ktrain) (0.2.3)\n",
            "Collecting keras_bert>=0.81.0\n",
            "  Downloading https://files.pythonhosted.org/packages/2c/0f/cdc886c1018943ea62d3209bc964413d5aa9d0eb7e493abd8545be679294/keras-bert-0.81.0.tar.gz\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.6/dist-packages (from ktrain) (2.23.0)\n",
            "Requirement already satisfied: joblib in /usr/local/lib/python3.6/dist-packages (from ktrain) (0.14.1)\n",
            "Collecting langdetect\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/56/a3/8407c1e62d5980188b4acc45ef3d94b933d14a2ebc9ef3505f22cf772570/langdetect-1.0.8.tar.gz (981kB)\n",
            "\u001b[K     |████████████████████████████████| 983kB 15.5MB/s \n",
            "\u001b[?25hRequirement already satisfied: jieba in /usr/local/lib/python3.6/dist-packages (from ktrain) (0.42.1)\n",
            "Collecting cchardet==2.1.5\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/fa/4e/847feebfc3e71c773b23ee06c74687b8c50a5a6d6aaff452a0a4f4eb9a32/cchardet-2.1.5-cp36-cp36m-manylinux1_x86_64.whl (241kB)\n",
            "\u001b[K     |████████████████████████████████| 245kB 39.4MB/s \n",
            "\u001b[?25hRequirement already satisfied: networkx>=2.3 in /usr/local/lib/python3.6/dist-packages (from ktrain) (2.4)\n",
            "Requirement already satisfied: bokeh in /usr/local/lib/python3.6/dist-packages (from ktrain) (1.4.0)\n",
            "Collecting seqeval\n",
            "  Downloading https://files.pythonhosted.org/packages/34/91/068aca8d60ce56dd9ba4506850e876aba5e66a6f2f29aa223224b50df0de/seqeval-0.0.12.tar.gz\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.6/dist-packages (from ktrain) (20.3)\n",
            "Requirement already satisfied: tensorflow_datasets in /usr/local/lib/python3.6/dist-packages (from ktrain) (2.1.0)\n",
            "Collecting transformers>=2.7.0\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/cd/38/c9527aa055241c66c4d785381eaf6f80a28c224cae97daa1f8b183b5fabb/transformers-2.9.0-py3-none-any.whl (635kB)\n",
            "\u001b[K     |████████████████████████████████| 645kB 30.8MB/s \n",
            "\u001b[?25hRequirement already satisfied: ipython in /usr/local/lib/python3.6/dist-packages (from ktrain) (5.5.0)\n",
            "Collecting syntok\n",
            "  Downloading https://files.pythonhosted.org/packages/8c/76/a49e73a04b3e3a14ce232e8e28a1587f8108baa665644fe8c40e307e792e/syntok-1.3.1.tar.gz\n",
            "Collecting whoosh\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/ba/19/24d0f1f454a2c1eb689ca28d2f178db81e5024f42d82729a4ff6771155cf/Whoosh-2.7.4-py2.py3-none-any.whl (468kB)\n",
            "\u001b[K     |████████████████████████████████| 471kB 31.9MB/s \n",
            "\u001b[?25hRequirement already satisfied: six>=1.12.0 in /usr/local/lib/python3.6/dist-packages (from tensorflow==2.1.0->ktrain) (1.12.0)\n",
            "Requirement already satisfied: protobuf>=3.8.0 in /usr/local/lib/python3.6/dist-packages (from tensorflow==2.1.0->ktrain) (3.10.0)\n",
            "Requirement already satisfied: google-pasta>=0.1.6 in /usr/local/lib/python3.6/dist-packages (from tensorflow==2.1.0->ktrain) (0.2.0)\n",
            "Requirement already satisfied: wheel>=0.26; python_version >= \"3\" in /usr/local/lib/python3.6/dist-packages (from tensorflow==2.1.0->ktrain) (0.34.2)\n",
            "Requirement already satisfied: keras-applications>=1.0.8 in /usr/local/lib/python3.6/dist-packages (from tensorflow==2.1.0->ktrain) (1.0.8)\n",
            "Requirement already satisfied: opt-einsum>=2.3.2 in /usr/local/lib/python3.6/dist-packages (from tensorflow==2.1.0->ktrain) (3.2.1)\n",
            "Requirement already satisfied: astor>=0.6.0 in /usr/local/lib/python3.6/dist-packages (from tensorflow==2.1.0->ktrain) (0.8.1)\n",
            "Requirement already satisfied: wrapt>=1.11.1 in /usr/local/lib/python3.6/dist-packages (from tensorflow==2.1.0->ktrain) (1.12.1)\n",
            "Requirement already satisfied: grpcio>=1.8.6 in /usr/local/lib/python3.6/dist-packages (from tensorflow==2.1.0->ktrain) (1.28.1)\n",
            "Collecting tensorflow-estimator<2.2.0,>=2.1.0rc0\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/18/90/b77c328a1304437ab1310b463e533fa7689f4bfc41549593056d812fab8e/tensorflow_estimator-2.1.0-py2.py3-none-any.whl (448kB)\n",
            "\u001b[K     |████████████████████████████████| 450kB 38.0MB/s \n",
            "\u001b[?25hRequirement already satisfied: scipy==1.4.1; python_version >= \"3\" in /usr/local/lib/python3.6/dist-packages (from tensorflow==2.1.0->ktrain) (1.4.1)\n",
            "Collecting tensorboard<2.2.0,>=2.1.0\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/d9/41/bbf49b61370e4f4d245d4c6051dfb6db80cec672605c91b1652ac8cc3d38/tensorboard-2.1.1-py3-none-any.whl (3.8MB)\n",
            "\u001b[K     |████████████████████████████████| 3.9MB 18.9MB/s \n",
            "\u001b[?25hRequirement already satisfied: keras-preprocessing>=1.1.0 in /usr/local/lib/python3.6/dist-packages (from tensorflow==2.1.0->ktrain) (1.1.0)\n",
            "Requirement already satisfied: termcolor>=1.1.0 in /usr/local/lib/python3.6/dist-packages (from tensorflow==2.1.0->ktrain) (1.1.0)\n",
            "Requirement already satisfied: absl-py>=0.7.0 in /usr/local/lib/python3.6/dist-packages (from tensorflow==2.1.0->ktrain) (0.9.0)\n",
            "Collecting gast==0.2.2\n",
            "  Downloading https://files.pythonhosted.org/packages/4e/35/11749bf99b2d4e3cceb4d55ca22590b0d7c2c62b9de38ac4a4a7f4687421/gast-0.2.2.tar.gz\n",
            "Requirement already satisfied: numpy<2.0,>=1.16.0 in /usr/local/lib/python3.6/dist-packages (from tensorflow==2.1.0->ktrain) (1.18.4)\n",
            "Requirement already satisfied: python-dateutil>=2.1 in /usr/local/lib/python3.6/dist-packages (from matplotlib>=3.0.0->ktrain) (2.8.1)\n",
            "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.6/dist-packages (from matplotlib>=3.0.0->ktrain) (1.2.0)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.6/dist-packages (from matplotlib>=3.0.0->ktrain) (0.10.0)\n",
            "Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.1 in /usr/local/lib/python3.6/dist-packages (from matplotlib>=3.0.0->ktrain) (2.4.7)\n",
            "Requirement already satisfied: pytz>=2017.2 in /usr/local/lib/python3.6/dist-packages (from pandas>=1.0.1->ktrain) (2018.9)\n",
            "Requirement already satisfied: Keras in /usr/local/lib/python3.6/dist-packages (from keras_bert>=0.81.0->ktrain) (2.3.1)\n",
            "Collecting keras-transformer>=0.30.0\n",
            "  Downloading https://files.pythonhosted.org/packages/22/b9/9040ec948ef895e71df6bee505a1f7e1c99ffedb409cb6eb329f04ece6e0/keras-transformer-0.33.0.tar.gz\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.6/dist-packages (from requests->ktrain) (2020.4.5.1)\n",
            "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.6/dist-packages (from requests->ktrain) (1.24.3)\n",
            "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests->ktrain) (2.9)\n",
            "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests->ktrain) (3.0.4)\n",
            "Requirement already satisfied: decorator>=4.3.0 in /usr/local/lib/python3.6/dist-packages (from networkx>=2.3->ktrain) (4.4.2)\n",
            "Requirement already satisfied: pillow>=4.0 in /usr/local/lib/python3.6/dist-packages (from bokeh->ktrain) (7.0.0)\n",
            "Requirement already satisfied: Jinja2>=2.7 in /usr/local/lib/python3.6/dist-packages (from bokeh->ktrain) (2.11.2)\n",
            "Requirement already satisfied: PyYAML>=3.10 in /usr/local/lib/python3.6/dist-packages (from bokeh->ktrain) (3.13)\n",
            "Requirement already satisfied: tornado>=4.3 in /usr/local/lib/python3.6/dist-packages (from bokeh->ktrain) (4.5.3)\n",
            "Requirement already satisfied: future in /usr/local/lib/python3.6/dist-packages (from tensorflow_datasets->ktrain) (0.16.0)\n",
            "Requirement already satisfied: tensorflow-metadata in /usr/local/lib/python3.6/dist-packages (from tensorflow_datasets->ktrain) (0.21.2)\n",
            "Requirement already satisfied: dill in /usr/local/lib/python3.6/dist-packages (from tensorflow_datasets->ktrain) (0.3.1.1)\n",
            "Requirement already satisfied: promise in /usr/local/lib/python3.6/dist-packages (from tensorflow_datasets->ktrain) (2.3)\n",
            "Requirement already satisfied: tqdm in /usr/local/lib/python3.6/dist-packages (from tensorflow_datasets->ktrain) (4.41.1)\n",
            "Requirement already satisfied: attrs>=18.1.0 in /usr/local/lib/python3.6/dist-packages (from tensorflow_datasets->ktrain) (19.3.0)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.6/dist-packages (from transformers>=2.7.0->ktrain) (2019.12.20)\n",
            "Collecting sentencepiece\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/98/2c/8df20f3ac6c22ac224fff307ebc102818206c53fc454ecd37d8ac2060df5/sentencepiece-0.1.86-cp36-cp36m-manylinux1_x86_64.whl (1.0MB)\n",
            "\u001b[K     |████████████████████████████████| 1.0MB 30.0MB/s \n",
            "\u001b[?25hCollecting sacremoses\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/7d/34/09d19aff26edcc8eb2a01bed8e98f13a1537005d31e95233fd48216eed10/sacremoses-0.0.43.tar.gz (883kB)\n",
            "\u001b[K     |████████████████████████████████| 890kB 36.7MB/s \n",
            "\u001b[?25hRequirement already satisfied: filelock in /usr/local/lib/python3.6/dist-packages (from transformers>=2.7.0->ktrain) (3.0.12)\n",
            "Collecting tokenizers==0.7.0\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/14/e5/a26eb4716523808bb0a799fcfdceb6ebf77a18169d9591b2f46a9adb87d9/tokenizers-0.7.0-cp36-cp36m-manylinux1_x86_64.whl (3.8MB)\n",
            "\u001b[K     |████████████████████████████████| 3.8MB 35.4MB/s \n",
            "\u001b[?25hRequirement already satisfied: dataclasses; python_version < \"3.7\" in /usr/local/lib/python3.6/dist-packages (from transformers>=2.7.0->ktrain) (0.7)\n",
            "Requirement already satisfied: simplegeneric>0.8 in /usr/local/lib/python3.6/dist-packages (from ipython->ktrain) (0.8.1)\n",
            "Requirement already satisfied: setuptools>=18.5 in /usr/local/lib/python3.6/dist-packages (from ipython->ktrain) (46.1.3)\n",
            "Requirement already satisfied: pickleshare in /usr/local/lib/python3.6/dist-packages (from ipython->ktrain) (0.7.5)\n",
            "Requirement already satisfied: prompt-toolkit<2.0.0,>=1.0.4 in /usr/local/lib/python3.6/dist-packages (from ipython->ktrain) (1.0.18)\n",
            "Requirement already satisfied: pexpect; sys_platform != \"win32\" in /usr/local/lib/python3.6/dist-packages (from ipython->ktrain) (4.8.0)\n",
            "Requirement already satisfied: pygments in /usr/local/lib/python3.6/dist-packages (from ipython->ktrain) (2.1.3)\n",
            "Requirement already satisfied: traitlets>=4.2 in /usr/local/lib/python3.6/dist-packages (from ipython->ktrain) (4.3.3)\n",
            "Requirement already satisfied: h5py in /usr/local/lib/python3.6/dist-packages (from keras-applications>=1.0.8->tensorflow==2.1.0->ktrain) (2.10.0)\n",
            "Requirement already satisfied: google-auth-oauthlib<0.5,>=0.4.1 in /usr/local/lib/python3.6/dist-packages (from tensorboard<2.2.0,>=2.1.0->tensorflow==2.1.0->ktrain) (0.4.1)\n",
            "Requirement already satisfied: werkzeug>=0.11.15 in /usr/local/lib/python3.6/dist-packages (from tensorboard<2.2.0,>=2.1.0->tensorflow==2.1.0->ktrain) (1.0.1)\n",
            "Requirement already satisfied: google-auth<2,>=1.6.3 in /usr/local/lib/python3.6/dist-packages (from tensorboard<2.2.0,>=2.1.0->tensorflow==2.1.0->ktrain) (1.7.2)\n",
            "Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.6/dist-packages (from tensorboard<2.2.0,>=2.1.0->tensorflow==2.1.0->ktrain) (3.2.1)\n",
            "Collecting keras-pos-embd>=0.10.0\n",
            "  Downloading https://files.pythonhosted.org/packages/09/70/b63ed8fc660da2bb6ae29b9895401c628da5740c048c190b5d7107cadd02/keras-pos-embd-0.11.0.tar.gz\n",
            "Collecting keras-multi-head>=0.22.0\n",
            "  Downloading https://files.pythonhosted.org/packages/40/3e/d0a64bb2ac5217928effe4507c26bbd19b86145d16a1948bc2d4f4c6338a/keras-multi-head-0.22.0.tar.gz\n",
            "Collecting keras-layer-normalization>=0.12.0\n",
            "  Downloading https://files.pythonhosted.org/packages/a4/0e/d1078df0494bac9ce1a67954e5380b6e7569668f0f3b50a9531c62c1fc4a/keras-layer-normalization-0.14.0.tar.gz\n",
            "Collecting keras-position-wise-feed-forward>=0.5.0\n",
            "  Downloading https://files.pythonhosted.org/packages/e3/59/f0faa1037c033059e7e9e7758e6c23b4d1c0772cd48de14c4b6fd4033ad5/keras-position-wise-feed-forward-0.6.0.tar.gz\n",
            "Collecting keras-embed-sim>=0.7.0\n",
            "  Downloading https://files.pythonhosted.org/packages/bc/20/735fd53f6896e2af63af47e212601c1b8a7a80d00b6126c388c9d1233892/keras-embed-sim-0.7.0.tar.gz\n",
            "Requirement already satisfied: MarkupSafe>=0.23 in /usr/local/lib/python3.6/dist-packages (from Jinja2>=2.7->bokeh->ktrain) (1.1.1)\n",
            "Requirement already satisfied: googleapis-common-protos in /usr/local/lib/python3.6/dist-packages (from tensorflow-metadata->tensorflow_datasets->ktrain) (1.51.0)\n",
            "Requirement already satisfied: click in /usr/local/lib/python3.6/dist-packages (from sacremoses->transformers>=2.7.0->ktrain) (7.1.2)\n",
            "Requirement already satisfied: wcwidth in /usr/local/lib/python3.6/dist-packages (from prompt-toolkit<2.0.0,>=1.0.4->ipython->ktrain) (0.1.9)\n",
            "Requirement already satisfied: ptyprocess>=0.5 in /usr/local/lib/python3.6/dist-packages (from pexpect; sys_platform != \"win32\"->ipython->ktrain) (0.6.0)\n",
            "Requirement already satisfied: ipython-genutils in /usr/local/lib/python3.6/dist-packages (from traitlets>=4.2->ipython->ktrain) (0.2.0)\n",
            "Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.6/dist-packages (from google-auth-oauthlib<0.5,>=0.4.1->tensorboard<2.2.0,>=2.1.0->tensorflow==2.1.0->ktrain) (1.3.0)\n",
            "Requirement already satisfied: rsa<4.1,>=3.1.4 in /usr/local/lib/python3.6/dist-packages (from google-auth<2,>=1.6.3->tensorboard<2.2.0,>=2.1.0->tensorflow==2.1.0->ktrain) (4.0)\n",
            "Requirement already satisfied: cachetools<3.2,>=2.0.0 in /usr/local/lib/python3.6/dist-packages (from google-auth<2,>=1.6.3->tensorboard<2.2.0,>=2.1.0->tensorflow==2.1.0->ktrain) (3.1.1)\n",
            "Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.6/dist-packages (from google-auth<2,>=1.6.3->tensorboard<2.2.0,>=2.1.0->tensorflow==2.1.0->ktrain) (0.2.8)\n",
            "Collecting keras-self-attention==0.41.0\n",
            "  Downloading https://files.pythonhosted.org/packages/1b/1c/01599219bef7266fa43b3316e4f55bcb487734d3bafdc60ffd564f3cfe29/keras-self-attention-0.41.0.tar.gz\n",
            "Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.6/dist-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tensorboard<2.2.0,>=2.1.0->tensorflow==2.1.0->ktrain) (3.1.0)\n",
            "Requirement already satisfied: pyasn1>=0.1.3 in /usr/local/lib/python3.6/dist-packages (from rsa<4.1,>=3.1.4->google-auth<2,>=1.6.3->tensorboard<2.2.0,>=2.1.0->tensorflow==2.1.0->ktrain) (0.4.8)\n",
            "Building wheels for collected packages: ktrain, keras-bert, langdetect, seqeval, syntok, gast, keras-transformer, sacremoses, keras-pos-embd, keras-multi-head, keras-layer-normalization, keras-position-wise-feed-forward, keras-embed-sim, keras-self-attention\n",
            "  Building wheel for ktrain (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for ktrain: filename=ktrain-0.14.7-cp36-none-any.whl size=25240969 sha256=e0806742c0019120bfdc63cc5d10e72116751adc6d4c0f32ba93dfd4137ea3eb\n",
            "  Stored in directory: /root/.cache/pip/wheels/d6/99/6b/4fc1aad36f8231465508e10579ccf401b80ef0e5eb2ab9a17d\n",
            "  Building wheel for keras-bert (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for keras-bert: filename=keras_bert-0.81.0-cp36-none-any.whl size=37913 sha256=6d4245caad8e7a1b4196bbc7d7fa004c686b7e1be7e4f064671e447a8ba2885e\n",
            "  Stored in directory: /root/.cache/pip/wheels/bd/27/da/ffc2d573aa48b87440ec4f98bc7c992e3a2d899edb2d22ef9e\n",
            "  Building wheel for langdetect (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for langdetect: filename=langdetect-1.0.8-cp36-none-any.whl size=993193 sha256=4adaef96a3e7093c856a1e681251305dfd96b351acbdc19d0fda97ef5a516617\n",
            "  Stored in directory: /root/.cache/pip/wheels/8d/b3/aa/6d99de9f3841d7d3d40a60ea06e6d669e8e5012e6c8b947a57\n",
            "  Building wheel for seqeval (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for seqeval: filename=seqeval-0.0.12-cp36-none-any.whl size=7424 sha256=bd15554afc737b5f7e604546d66f4f0f480e55014a20e5a0207505d4a24ff5b7\n",
            "  Stored in directory: /root/.cache/pip/wheels/4f/32/0a/df3b340a82583566975377d65e724895b3fad101a3fb729f68\n",
            "  Building wheel for syntok (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for syntok: filename=syntok-1.3.1-cp36-none-any.whl size=20918 sha256=a74e6dfb05da54a1f666c298111001132e733cdd3f1c3c42b5bec8c1bacc489c\n",
            "  Stored in directory: /root/.cache/pip/wheels/51/c6/a4/be1920586c49469846bcd2888200bdecfe109ec421dab9be2d\n",
            "  Building wheel for gast (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for gast: filename=gast-0.2.2-cp36-none-any.whl size=7540 sha256=232e798b47c6fc10f8c5be31738d7da13b2ae8644fe19434fa06443f52d7f118\n",
            "  Stored in directory: /root/.cache/pip/wheels/5c/2e/7e/a1d4d4fcebe6c381f378ce7743a3ced3699feb89bcfbdadadd\n",
            "  Building wheel for keras-transformer (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for keras-transformer: filename=keras_transformer-0.33.0-cp36-none-any.whl size=13260 sha256=11c9aba79818304c616585d95937867519870c86bf2e18c1f5168ffd2c0f8ff1\n",
            "  Stored in directory: /root/.cache/pip/wheels/26/98/13/a28402939e1d48edd8704e6b02f223795af4a706815f4bf6d8\n",
            "  Building wheel for sacremoses (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for sacremoses: filename=sacremoses-0.0.43-cp36-none-any.whl size=893260 sha256=90e9c7eda5faf1e22b4bdf89567eba2de8b9b25b30acd301dfd25a2dd6d1c530\n",
            "  Stored in directory: /root/.cache/pip/wheels/29/3c/fd/7ce5c3f0666dab31a50123635e6fb5e19ceb42ce38d4e58f45\n",
            "  Building wheel for keras-pos-embd (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for keras-pos-embd: filename=keras_pos_embd-0.11.0-cp36-none-any.whl size=7554 sha256=96a3faf8ca4e6694269ada1ddb6bf9b980ba11538bbc6c135576a596faadda95\n",
            "  Stored in directory: /root/.cache/pip/wheels/5b/a1/a0/ce6b1d49ba1a9a76f592e70cf297b05c96bc9f418146761032\n",
            "  Building wheel for keras-multi-head (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for keras-multi-head: filename=keras_multi_head-0.22.0-cp36-none-any.whl size=15371 sha256=e75faec7ad44a8bee19c41d59bfa4936e56a8e4542bb51195b1895145ef04a80\n",
            "  Stored in directory: /root/.cache/pip/wheels/bb/df/3f/81b36f41b66e6a9cd69224c70a737de2bb6b2f7feb3272c25e\n",
            "  Building wheel for keras-layer-normalization (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for keras-layer-normalization: filename=keras_layer_normalization-0.14.0-cp36-none-any.whl size=5268 sha256=388fbc71e8b467eb61c8a6b12dc706db42f1f4103e19c2f4635f178da263c0d4\n",
            "  Stored in directory: /root/.cache/pip/wheels/54/80/22/a638a7d406fd155e507aa33d703e3fa2612b9eb7bb4f4fe667\n",
            "  Building wheel for keras-position-wise-feed-forward (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for keras-position-wise-feed-forward: filename=keras_position_wise_feed_forward-0.6.0-cp36-none-any.whl size=5623 sha256=6de462e742155e76c130e8294cff83502fc7b7d4e965df8af968a5051fa1b77e\n",
            "  Stored in directory: /root/.cache/pip/wheels/39/e2/e2/3514fef126a00574b13bc0b9e23891800158df3a3c19c96e3b\n",
            "  Building wheel for keras-embed-sim (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for keras-embed-sim: filename=keras_embed_sim-0.7.0-cp36-none-any.whl size=4676 sha256=bbc4e699af9a929fc66472df399e02b821b92bdb12f35f380fed64f25292427a\n",
            "  Stored in directory: /root/.cache/pip/wheels/d1/bc/b1/b0c45cee4ca2e6c86586b0218ffafe7f0703c6d07fdf049866\n",
            "  Building wheel for keras-self-attention (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for keras-self-attention: filename=keras_self_attention-0.41.0-cp36-none-any.whl size=17288 sha256=34224cf64eef97b5fdb3171f678ab453bbc2ef2ca019a7fb72611540b6cbf1c9\n",
            "  Stored in directory: /root/.cache/pip/wheels/cc/dc/17/84258b27a04cd38ac91998abe148203720ca696186635db694\n",
            "Successfully built ktrain keras-bert langdetect seqeval syntok gast keras-transformer sacremoses keras-pos-embd keras-multi-head keras-layer-normalization keras-position-wise-feed-forward keras-embed-sim keras-self-attention\n",
            "\u001b[31mERROR: tensorflow-probability 0.10.0rc0 has requirement gast>=0.3.2, but you'll have gast 0.2.2 which is incompatible.\u001b[0m\n",
            "Installing collected packages: tensorflow-estimator, tensorboard, gast, tensorflow, keras-pos-embd, keras-self-attention, keras-multi-head, keras-layer-normalization, keras-position-wise-feed-forward, keras-embed-sim, keras-transformer, keras-bert, langdetect, cchardet, seqeval, sentencepiece, sacremoses, tokenizers, transformers, syntok, whoosh, ktrain\n",
            "  Found existing installation: tensorflow-estimator 2.2.0\n",
            "    Uninstalling tensorflow-estimator-2.2.0:\n",
            "      Successfully uninstalled tensorflow-estimator-2.2.0\n",
            "  Found existing installation: tensorboard 2.2.1\n",
            "    Uninstalling tensorboard-2.2.1:\n",
            "      Successfully uninstalled tensorboard-2.2.1\n",
            "  Found existing installation: gast 0.3.3\n",
            "    Uninstalling gast-0.3.3:\n",
            "      Successfully uninstalled gast-0.3.3\n",
            "  Found existing installation: tensorflow 2.2.0rc4\n",
            "    Uninstalling tensorflow-2.2.0rc4:\n",
            "      Successfully uninstalled tensorflow-2.2.0rc4\n",
            "Successfully installed cchardet-2.1.5 gast-0.2.2 keras-bert-0.81.0 keras-embed-sim-0.7.0 keras-layer-normalization-0.14.0 keras-multi-head-0.22.0 keras-pos-embd-0.11.0 keras-position-wise-feed-forward-0.6.0 keras-self-attention-0.41.0 keras-transformer-0.33.0 ktrain-0.14.7 langdetect-1.0.8 sacremoses-0.0.43 sentencepiece-0.1.86 seqeval-0.0.12 syntok-1.3.1 tensorboard-2.1.1 tensorflow-2.1.0 tensorflow-estimator-2.1.0 tokenizers-0.7.0 transformers-2.9.0 whoosh-2.7.4\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Uw3TT4MScepI",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "import ktrain\n",
        "from ktrain import text\n",
        "import numpy as np # linear algebra\n",
        "from sklearn.model_selection import train_test_split\n",
        "# fetch the dataset using scikit-learn\n",
        "categories = ['TRUE', 'FAKE']\n",
        "\n",
        "y = df['label'].values\n",
        "X = df['title']\n",
        "\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y,stratify=y,test_size=0.30, random_state=0)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "dPsV2m5pdc02",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 131
        },
        "outputId": "0ccf6738-943a-4751-c7c9-c19cc90ec7c8"
      },
      "source": [
        "(x_train,  y_train), (x_test, y_test), preproc = text.texts_from_array(x_train=X_train, y_train=y_train,\n",
        "                                                                       x_test=X_test, y_test=y_test,\n",
        "                                                                       class_names=categories,\n",
        "                                                                       preprocess_mode='bert',\n",
        "                                                                       maxlen=350, \n",
        "                                                                       max_features=35000)"
      ],
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "task: text classification\n",
            "preprocessing train...\n",
            "language: en\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "done."
            ],
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "preprocessing test...\n",
            "language: en\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "done."
            ],
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "uGhwQBQ-djau",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 66
        },
        "outputId": "23ae6d1c-acb1-452b-f89b-a498410e76cb"
      },
      "source": [
        "# you can disregard the deprecation warnings arising from using Keras 2.2.4 with TensorFlow 1.14.\n",
        "model = text.text_classifier('bert', train_data=(x_train, y_train), preproc=preproc)\n",
        "learner = ktrain.get_learner(model, train_data=(x_train, y_train), batch_size=6)"
      ],
      "execution_count": 19,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Is Multi-Label? False\n",
            "maxlen is 350\n",
            "done.\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "78oetXwpdsoy",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 115
        },
        "outputId": "882a3b6b-31c5-4d31-cc27-6b70adef9990"
      },
      "source": [
        "learner.fit_onecycle(2e-5, 1)"
      ],
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "\n",
            "\n",
            "begin training using onecycle policy with max lr of 2e-05...\n",
            "Train on 31428 samples\n",
            "31428/31428 [==============================] - 2782s 89ms/sample - loss: 0.1111 - accuracy: 0.9570\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<tensorflow.python.keras.callbacks.History at 0x7f3e0c1a5d68>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "j8tGt5p9feiu",
        "colab_type": "text"
      },
      "source": [
        "We can use the learner.validate method to test our model against the Test set."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "HyxcvUSjdxp4",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 196
        },
        "outputId": "4d5caf67-3ccd-46ba-c8a9-2efd63de8381"
      },
      "source": [
        "learner.validate(val_data=(x_test, y_test), class_names=categories)"
      ],
      "execution_count": 21,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "              precision    recall  f1-score   support\n",
            "\n",
            "        TRUE       0.98      0.99      0.98      6425\n",
            "        FAKE       0.99      0.98      0.98      7045\n",
            "\n",
            "    accuracy                           0.98     13470\n",
            "   macro avg       0.98      0.98      0.98     13470\n",
            "weighted avg       0.98      0.98      0.98     13470\n",
            "\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[6356,   69],\n",
              "       [ 143, 6902]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 21
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "U9vGoVRbf6JN",
        "colab_type": "text"
      },
      "source": [
        "## How to Use Our Trained BERT Model\n",
        "We can call the learner.get_predictor method to obtain a Predictor object capable of making predictions on new raw data."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "7b2hqIn1f9Cq",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "predictor = ktrain.get_predictor(learner.model, preproc)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "e8zqbeglgAVA",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        },
        "outputId": "a8426dd7-40ee-4014-c8db-4381af25a6a8"
      },
      "source": [
        "predictor.get_classes()"
      ],
      "execution_count": 23,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['TRUE', 'FAKE']"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 23
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "q_VLMUfVdfI4",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        ""
      ],
      "execution_count": 0,
      "outputs": []
    }
  ]
}