Full Code of PacktPublishing/Mastering-Transformers for AI

Repository: PacktPublishing/Mastering-Transformers
Branch: main
Commit: f088d75fb24f
Files: 52
Total size: 69.9 MB

Directory structure:
gitextract_yqkst43d/

├── CH01/
│   └── CH01_Introduction.ipynb
├── CH02/
│   ├── CH02a_Working_with_Language_Models_and_Tokenizers.ipynb
│   ├── CH02b_Working_with_Datasets_Libary.ipynb
│   ├── CH02c_Speed_and_Memory_Benchmarking.ipynb
│   └── data/
│       ├── a.csv
│       ├── b.csv
│       └── c.csv
├── CH03/
│   ├── CH03a_BERT_As_one_of_Autoencoding_Language_Models.ipynb
│   ├── CH03b_Other_Autoencoding_Models.ipynb
│   ├── CH03c_Tokenization_Algorithms.ipynb
│   └── corpus.txt
├── CH04/
│   ├── .ipynb_checkpoints/
│   │   └── CH04b_machine_translation_fine_tuning_using_simpletransformers-checkpoint.ipynb
│   ├── CH04a_Summarization_with_BART.ipynb
│   ├── CH04b_Autoregressive_language_model_training.ipynb
│   ├── CH04c_machine_translation_fine_tuning_using_simpletransformers.ipynb
│   ├── TR2EN.txt
│   └── austen-emma.txt
├── CH05/
│   ├── CH05a_BERT_fine-tuning.ipynb
│   ├── CH05b_Training_with_Naitve_PyTorch.ipynb
│   ├── CH05c_Multi-class_Classification.ipynb
│   ├── CH05d_Sentence_Pair_Regression.ipynb
│   └── TTC4900.csv
├── CH06/
│   ├── CH06a_Fine_tuning_language_models_for_NER.ipynb
│   └── CH06b_Thinking_of_the_question_answering_problem_as_a_start_stop_token_classification.ipynb
├── CH07/
│   ├── CH07a_Benchmarking_sentence_similarity_models.ipynb
│   ├── CH07b_Using_BART_for_zero_shot_learning.ipynb
│   ├── CH07c_Semantic_similarity_experiment_with_FLAIR.ipynb
│   ├── CH07d_Text_clustering_with_Sentence-BERT.ipynb
│   └── CH07e_Semantic_Search_with_Sentence_BERT.ipynb
├── CH08/
│   ├── CH08a_Pruning_Quantization.ipynb
│   └── CH08b_Working_with_Efficient_Self-attention.ipynb
├── CH09/
│   ├── CH09a_XLM_and_multilingual_BERT.ipynb
│   ├── CH09b_Cross_lingual_text_similarity.ipynb
│   ├── CH09c_Visualizing_cross-lingual_textual_similarity.ipynb
│   ├── CH09d_Cross_lingual_classification.ipynb
│   ├── CH09e_Cross_lingual_zero_shot_learning.ipynb
│   └── CH09f_Fine-tuning_performance_of_multilingual_models.ipynb
├── CH10/
│   ├── CH10a_fastAPI_Transformer_model_serving/
│   │   └── main.py
│   ├── CH10b_Dockerizing_API/
│   │   ├── app/
│   │   │   └── main.py
│   │   └── dockerfile
│   ├── CH10c_Faster_Transformer_model_serving_using_Tensorflow_Extended/
│   │   ├── .ipynb_checkpoints/
│   │   │   └── saved_model-checkpoint.ipynb
│   │   ├── main.py
│   │   └── saved_model.ipynb
│   └── CH10d_Load_testing_using_Locust /
│       ├── docker/
│       │   ├── app/
│       │   │   └── main.py
│       │   └── dockerfile
│       ├── fastapi/
│       │   └── main.py
│       └── locust_file.py
├── CH11/
│   ├── CH11a_Visualization_with_BertViz.ipynb
│   ├── CH11b_Tracking_with_TensorBoard.ipynb
│   └── CH11c_Tracking_with_WandB.ipynb
├── LICENSE
└── README.md

================================================
FILE CONTENTS
================================================

================================================
FILE: CH01/CH01_Introduction.ipynb
================================================
{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.8.5"
    },
    "colab": {
      "name": "CH01 Introduction.ipynb",
      "provenance": [],
      "collapsed_sections": []
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "3HexS4eAsRQ1"
      },
      "source": [
        "# TF-IDF Vectorizer"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "QLrk1ZnKsRQ8",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 175
        },
        "outputId": "573b6379-aeea-4156-a09c-2230ef05424a"
      },
      "source": [
        "from sklearn.feature_extraction.text import TfidfVectorizer \n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "\n",
        "toy_corpus= [\"the fat cat sat on the mat\",\n",
        "             \"the big cat slept\",\n",
        "             \"the dog chased a cat\"]\n",
        "vectorizer=TfidfVectorizer(use_idf=True)\n",
        "\n",
        "corpus_tfidf=vectorizer.fit_transform(toy_corpus)\n",
        "\n",
        "print(f\"The vocabulary size is {len(vectorizer.vocabulary_.keys())} \")\n",
        "print(f\"The document-term matrix shape is {corpus_tfidf.shape}\")\n",
        "\n",
        "df=pd.DataFrame(np.round(corpus_tfidf.toarray(),2))\n",
        "df.columns=vectorizer.get_feature_names()\n",
        "df"
      ],
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "The vocabulary size is 10 \n",
            "The document-term matrix shape is (3, 10)\n"
          ],
          "name": "stdout"
        },
        {
          "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>big</th>\n",
              "      <th>cat</th>\n",
              "      <th>chased</th>\n",
              "      <th>dog</th>\n",
              "      <th>fat</th>\n",
              "      <th>mat</th>\n",
              "      <th>on</th>\n",
              "      <th>sat</th>\n",
              "      <th>slept</th>\n",
              "      <th>the</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0.00</td>\n",
              "      <td>0.25</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.42</td>\n",
              "      <td>0.42</td>\n",
              "      <td>0.42</td>\n",
              "      <td>0.42</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.49</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0.61</td>\n",
              "      <td>0.36</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.61</td>\n",
              "      <td>0.36</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>0.00</td>\n",
              "      <td>0.36</td>\n",
              "      <td>0.61</td>\n",
              "      <td>0.61</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.36</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "    big   cat  chased   dog   fat   mat    on   sat  slept   the\n",
              "0  0.00  0.25    0.00  0.00  0.42  0.42  0.42  0.42   0.00  0.49\n",
              "1  0.61  0.36    0.00  0.00  0.00  0.00  0.00  0.00   0.61  0.36\n",
              "2  0.00  0.36    0.61  0.61  0.00  0.00  0.00  0.00   0.00  0.36"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 1
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "WQI1-eQDXuvZ"
      },
      "source": [
        ""
      ],
      "execution_count": 1,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "o7S1Wf2xWqH-"
      },
      "source": [
        "## Classification"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "iQ_wnwpCsRQ9",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "3988dbf1-9b29-4fd4-bf2a-7dcbb0e9f075"
      },
      "source": [
        "from sklearn.pipeline import make_pipeline\n",
        "from sklearn.svm import SVC\n",
        "labels= [0,1,0]\n",
        "clf =  SVC()\n",
        "clf.fit(df, labels)"
      ],
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "SVC(C=1.0, break_ties=False, cache_size=200, class_weight=None, coef0=0.0,\n",
              "    decision_function_shape='ovr', degree=3, gamma='scale', kernel='rbf',\n",
              "    max_iter=-1, probability=False, random_state=None, shrinking=True,\n",
              "    tol=0.001, verbose=False)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 2
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "P1UfliHPXotq",
        "outputId": "11971404-077e-4681-be5d-e8a3aa95eebe"
      },
      "source": [
        "clf.predict(df)"
      ],
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([0, 1, 0])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 3
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "M7Xp7alkCb0L"
      },
      "source": [
        ""
      ],
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "rIpBd5b_sRQ_"
      },
      "source": [
        "# Building a LM Model \n",
        "Once we prepared our corpus above, we are ready to start training Maximum Likelihood Estimator (MLE) as a Language Model."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "nUGnkes_sRRA"
      },
      "source": [
        "## Training a bigram LM"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "gLP2eGrBmJTz",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "55c36aca-dfd1-4f05-9584-53900abb6310"
      },
      "source": [
        "!pip install nltk==3.5.0"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Collecting nltk==3.5.0\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/92/75/ce35194d8e3022203cca0d2f896dbb88689f9b3fce8e9f9cff942913519d/nltk-3.5.zip (1.4MB)\n",
            "\r\u001b[K     |▎                               | 10kB 15.0MB/s eta 0:00:01\r\u001b[K     |▌                               | 20kB 20.8MB/s eta 0:00:01\r\u001b[K     |▊                               | 30kB 24.9MB/s eta 0:00:01\r\u001b[K     |█                               | 40kB 22.1MB/s eta 0:00:01\r\u001b[K     |█▏                              | 51kB 24.1MB/s eta 0:00:01\r\u001b[K     |█▍                              | 61kB 21.6MB/s eta 0:00:01\r\u001b[K     |█▋                              | 71kB 18.8MB/s eta 0:00:01\r\u001b[K     |█▉                              | 81kB 19.0MB/s eta 0:00:01\r\u001b[K     |██                              | 92kB 18.2MB/s eta 0:00:01\r\u001b[K     |██▎                             | 102kB 18.6MB/s eta 0:00:01\r\u001b[K     |██▌                             | 112kB 18.6MB/s eta 0:00:01\r\u001b[K     |██▊                             | 122kB 18.6MB/s eta 0:00:01\r\u001b[K     |███                             | 133kB 18.6MB/s eta 0:00:01\r\u001b[K     |███▏                            | 143kB 18.6MB/s eta 0:00:01\r\u001b[K     |███▍                            | 153kB 18.6MB/s eta 0:00:01\r\u001b[K     |███▋                            | 163kB 18.6MB/s eta 0:00:01\r\u001b[K     |███▉                            | 174kB 18.6MB/s eta 0:00:01\r\u001b[K     |████▏                           | 184kB 18.6MB/s eta 0:00:01\r\u001b[K     |████▍                           | 194kB 18.6MB/s eta 0:00:01\r\u001b[K     |████▋                           | 204kB 18.6MB/s eta 0:00:01\r\u001b[K     |████▉                           | 215kB 18.6MB/s eta 0:00:01\r\u001b[K     |█████                           | 225kB 18.6MB/s eta 0:00:01\r\u001b[K     |█████▎                          | 235kB 18.6MB/s eta 0:00:01\r\u001b[K     |█████▌                          | 245kB 18.6MB/s eta 0:00:01\r\u001b[K     |█████▊                          | 256kB 18.6MB/s eta 0:00:01\r\u001b[K     |██████                          | 266kB 18.6MB/s eta 0:00:01\r\u001b[K     |██████▏                         | 276kB 18.6MB/s eta 0:00:01\r\u001b[K     |██████▍                         | 286kB 18.6MB/s eta 0:00:01\r\u001b[K     |██████▋                         | 296kB 18.6MB/s eta 0:00:01\r\u001b[K     |██████▉                         | 307kB 18.6MB/s eta 0:00:01\r\u001b[K     |███████                         | 317kB 18.6MB/s eta 0:00:01\r\u001b[K     |███████▎                        | 327kB 18.6MB/s eta 0:00:01\r\u001b[K     |███████▌                        | 337kB 18.6MB/s eta 0:00:01\r\u001b[K     |███████▊                        | 348kB 18.6MB/s eta 0:00:01\r\u001b[K     |████████                        | 358kB 18.6MB/s eta 0:00:01\r\u001b[K     |████████▎                       | 368kB 18.6MB/s eta 0:00:01\r\u001b[K     |████████▌                       | 378kB 18.6MB/s eta 0:00:01\r\u001b[K     |████████▊                       | 389kB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████                       | 399kB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████▏                      | 409kB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████▍                      | 419kB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████▋                      | 430kB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████▉                      | 440kB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████                      | 450kB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████▎                     | 460kB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████▌                     | 471kB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████▊                     | 481kB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████                     | 491kB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████▏                    | 501kB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████▍                    | 512kB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████▋                    | 522kB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████▉                    | 532kB 18.6MB/s eta 0:00:01\r\u001b[K     |████████████▏                   | 542kB 18.6MB/s eta 0:00:01\r\u001b[K     |████████████▍                   | 552kB 18.6MB/s eta 0:00:01\r\u001b[K     |████████████▋                   | 563kB 18.6MB/s eta 0:00:01\r\u001b[K     |████████████▉                   | 573kB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████████                   | 583kB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████████▎                  | 593kB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████████▌                  | 604kB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████████▊                  | 614kB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████                  | 624kB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████▏                 | 634kB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████▍                 | 645kB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████▋                 | 655kB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████▉                 | 665kB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████████                 | 675kB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████████▎                | 686kB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████████▌                | 696kB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████████▊                | 706kB 18.6MB/s eta 0:00:01\r\u001b[K     |████████████████                | 716kB 18.6MB/s eta 0:00:01\r\u001b[K     |████████████████▎               | 727kB 18.6MB/s eta 0:00:01\r\u001b[K     |████████████████▌               | 737kB 18.6MB/s eta 0:00:01\r\u001b[K     |████████████████▊               | 747kB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████████████               | 757kB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████████████▏              | 768kB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████████████▍              | 778kB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████████████▋              | 788kB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████████████▉              | 798kB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████████              | 808kB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████████▎             | 819kB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████████▌             | 829kB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████████▊             | 839kB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████████████             | 849kB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████████████▏            | 860kB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████████████▍            | 870kB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████████████▋            | 880kB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████████████▉            | 890kB 18.6MB/s eta 0:00:01\r\u001b[K     |████████████████████▏           | 901kB 18.6MB/s eta 0:00:01\r\u001b[K     |████████████████████▍           | 911kB 18.6MB/s eta 0:00:01\r\u001b[K     |████████████████████▋           | 921kB 18.6MB/s eta 0:00:01\r\u001b[K     |████████████████████▉           | 931kB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████████████████           | 942kB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████████████████▎          | 952kB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████████████████▌          | 962kB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████████████████▊          | 972kB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████████████          | 983kB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████████████▏         | 993kB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████████████▍         | 1.0MB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████████████▋         | 1.0MB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████████████▉         | 1.0MB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████████████████         | 1.0MB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████████████████▎        | 1.0MB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████████████████▌        | 1.1MB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████████████████▊        | 1.1MB 18.6MB/s eta 0:00:01\r\u001b[K     |████████████████████████        | 1.1MB 18.6MB/s eta 0:00:01\r\u001b[K     |████████████████████████▎       | 1.1MB 18.6MB/s eta 0:00:01\r\u001b[K     |████████████████████████▌       | 1.1MB 18.6MB/s eta 0:00:01\r\u001b[K     |████████████████████████▊       | 1.1MB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████████████████████       | 1.1MB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████████████████████▏      | 1.1MB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████████████████████▍      | 1.1MB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████████████████████▋      | 1.1MB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████████████████████▉      | 1.2MB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████████████████      | 1.2MB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████████████████▎     | 1.2MB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████████████████▌     | 1.2MB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████████████████▊     | 1.2MB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████████████████████     | 1.2MB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████████████████████▏    | 1.2MB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████████████████████▍    | 1.2MB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████████████████████▋    | 1.2MB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████████████████████▉    | 1.2MB 18.6MB/s eta 0:00:01\r\u001b[K     |████████████████████████████▏   | 1.3MB 18.6MB/s eta 0:00:01\r\u001b[K     |████████████████████████████▍   | 1.3MB 18.6MB/s eta 0:00:01\r\u001b[K     |████████████████████████████▋   | 1.3MB 18.6MB/s eta 0:00:01\r\u001b[K     |████████████████████████████▉   | 1.3MB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████████████████████████   | 1.3MB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████████████████████████▎  | 1.3MB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████████████████████████▌  | 1.3MB 18.6MB/s eta 0:00:01\r\u001b[K     |█████████████████████████████▊  | 1.3MB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████████████████████  | 1.3MB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████████████████████▏ | 1.4MB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████████████████████▍ | 1.4MB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████████████████████▋ | 1.4MB 18.6MB/s eta 0:00:01\r\u001b[K     |██████████████████████████████▉ | 1.4MB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████████████████████████ | 1.4MB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████████████████████████▎| 1.4MB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████████████████████████▌| 1.4MB 18.6MB/s eta 0:00:01\r\u001b[K     |███████████████████████████████▊| 1.4MB 18.6MB/s eta 0:00:01\r\u001b[K     |████████████████████████████████| 1.4MB 18.6MB/s \n",
            "\u001b[?25hRequirement already satisfied: click in /usr/local/lib/python3.7/dist-packages (from nltk==3.5.0) (7.1.2)\n",
            "Requirement already satisfied: joblib in /usr/local/lib/python3.7/dist-packages (from nltk==3.5.0) (1.0.1)\n",
            "Requirement already satisfied: regex in /usr/local/lib/python3.7/dist-packages (from nltk==3.5.0) (2019.12.20)\n",
            "Requirement already satisfied: tqdm in /usr/local/lib/python3.7/dist-packages (from nltk==3.5.0) (4.41.1)\n",
            "Building wheels for collected packages: nltk\n",
            "  Building wheel for nltk (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for nltk: filename=nltk-3.5-cp37-none-any.whl size=1434676 sha256=b026191697fc0f1fd3d3503c277bd8b8b393a3d83015818aa19b9b5545d68fcb\n",
            "  Stored in directory: /root/.cache/pip/wheels/ae/8c/3f/b1fe0ba04555b08b57ab52ab7f86023639a526d8bc8d384306\n",
            "Successfully built nltk\n",
            "Installing collected packages: nltk\n",
            "  Found existing installation: nltk 3.2.5\n",
            "    Uninstalling nltk-3.2.5:\n",
            "      Successfully uninstalled nltk-3.2.5\n",
            "Successfully installed nltk-3.5\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DXhFj8Bk9hNI",
        "outputId": "cb579144-cbf8-4335-de75-f58cdce4e19a"
      },
      "source": [
        "import nltk\n",
        "from nltk.corpus import gutenberg\n",
        "from nltk.lm import MLE\n",
        "from nltk.lm.preprocessing import padded_everygram_pipeline\n",
        "\n",
        "nltk.download('gutenberg')\n",
        "nltk.download('punkt')\n",
        "macbeth = gutenberg.sents('shakespeare-macbeth.txt')\n",
        "\n",
        "model, vocab = padded_everygram_pipeline(2, macbeth)\n",
        "lm=MLE(2)\n",
        "lm.fit(model,vocab)\n",
        "print(list(lm.vocab)[:40])\n",
        "print(f\"The number of words is {len(lm.vocab)}\")\n"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[nltk_data] Downloading package gutenberg to /root/nltk_data...\n",
            "[nltk_data]   Unzipping corpora/gutenberg.zip.\n",
            "[nltk_data] Downloading package punkt to /root/nltk_data...\n",
            "[nltk_data]   Unzipping tokenizers/punkt.zip.\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "['<s>', '[', 'The', 'Tragedie', 'of', 'Macbeth', 'by', 'William', 'Shakespeare', '1603', ']', '</s>', 'Actus', 'Primus', '.', 'Scoena', 'Prima', 'Thunder', 'and', 'Lightning', 'Enter', 'three', 'Witches', '1', 'When', 'shall', 'we', 'meet', 'againe', '?', 'In', ',', 'or', 'in', 'Raine', '2', 'the', 'Hurley', '-', 'burley']\n",
            "The number of words is 4020\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "J7r_k7HsEIl5",
        "outputId": "77a4b812-aadb-467a-c839-fbe8bf3639e4"
      },
      "source": [
        "print(macbeth[42])"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "['So', 'well', 'thy', 'words', 'become', 'thee', ',', 'as', 'thy', 'wounds', ',', 'They', 'smack', 'of', 'Honor', 'both', ':', 'Goe', 'get', 'him', 'Surgeons', '.']\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "XAmNlJAusRRC"
      },
      "source": [
        "## See what LM learned"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "6-9V4zpqsRRC"
      },
      "source": [
        "Here is a list of what the language model learded so far"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Imi-8nJBsRRC",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "998fe046-ae85-499d-eb88-62a616d8373f"
      },
      "source": [
        "print(f\"The frequency of the term 'Macbeth' is {lm.counts['Macbeth']}\")\n",
        "print(f\"The language model probability score of 'Macbeth' is {lm.score('Macbeth')}\")\n",
        "print(f\"The number of times 'Macbeth' follows 'Enter' is {lm.counts[['Enter']]['Macbeth']} \")\n",
        "print(f\"P(Macbeth | Enter) is {lm.score('Macbeth', ['Enter'])}\")\n",
        "print(f\"P(shaking | for) is {lm.score('shaking', ['for'])}\")"
      ],
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "The frequency of the term 'Macbeth' is 61\n",
            "The language model probability score of 'Macbeth' is 0.0022631149365585812\n",
            "The number of times 'Macbeth' follows 'Enter' is 15 \n",
            "P(Macbeth | Enter) is 0.1875\n",
            "P(shaking | for) is 0.012195121951219513\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "oauTwshSsRRD"
      },
      "source": [
        "## Language Generation with LM"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "cVxMOl7csRRD"
      },
      "source": [
        "To generate one word"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "zhpjmp1_sRRD",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        },
        "outputId": "c2f8ce54-2df2-4e66-b85f-411b2c3f1424"
      },
      "source": [
        "lm.generate(1, random_seed=42)"
      ],
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            },
            "text/plain": [
              "'done'"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "h8NjYNyXsRRE"
      },
      "source": [
        "To generate a sentence of 7 words length"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "jq7dnLXQsRRE",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "1cfc5080-03ea-4ccb-aaec-f251c550d509"
      },
      "source": [
        "print(lm.generate(7, random_seed=42))"
      ],
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "['done', ',', 'Not', 'for', 'thee', 'in', 'this']\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "NK3EDt-_sRRE"
      },
      "source": [
        "To generate 10 words starting with \\<s>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "inFO4hKqsRRF",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "1e1f8861-ff67-4787-dfb8-9522b48ff04b"
      },
      "source": [
        " lm.generate(10, text_seed=['<s>'], random_seed=42)"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['My', 'Bosome', 'franchis', \"'\", 's', 'of', 'time', ',', 'We', 'are']"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "aUqLMMuPJjOj"
      },
      "source": [
        ""
      ],
      "execution_count": 10,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "CsT0yIeFJuu3"
      },
      "source": [
        "# Word Embeddings Training"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "QSXGUZAdKhFt",
        "outputId": "7733b901-7e9e-4d39-ded4-619c874bc81e"
      },
      "source": [
        "!pip install gensim==3.8.3"
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Collecting gensim==3.8.3\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/5c/4e/afe2315e08a38967f8a3036bbe7e38b428e9b7a90e823a83d0d49df1adf5/gensim-3.8.3-cp37-cp37m-manylinux1_x86_64.whl (24.2MB)\n",
            "\u001b[K     |████████████████████████████████| 24.2MB 2.3MB/s \n",
            "\u001b[?25hRequirement already satisfied: scipy>=0.18.1 in /usr/local/lib/python3.7/dist-packages (from gensim==3.8.3) (1.4.1)\n",
            "Requirement already satisfied: six>=1.5.0 in /usr/local/lib/python3.7/dist-packages (from gensim==3.8.3) (1.15.0)\n",
            "Requirement already satisfied: numpy>=1.11.3 in /usr/local/lib/python3.7/dist-packages (from gensim==3.8.3) (1.19.5)\n",
            "Requirement already satisfied: smart-open>=1.8.1 in /usr/local/lib/python3.7/dist-packages (from gensim==3.8.3) (5.0.0)\n",
            "Installing collected packages: gensim\n",
            "  Found existing installation: gensim 3.6.0\n",
            "    Uninstalling gensim-3.6.0:\n",
            "      Successfully uninstalled gensim-3.6.0\n",
            "Successfully installed gensim-3.8.3\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "hwIt376DJxEK"
      },
      "source": [
        "from gensim.models import Word2Vec\n",
        "model = Word2Vec(sentences=macbeth, size=100, window= 4, min_count=10, workers=4, iter=10)"
      ],
      "execution_count": 12,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "x1N8FgE0KKyu",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "aab62da2-9e3f-46aa-b84a-be0fedd5d26b"
      },
      "source": [
        "model.wv.similar_by_word('then',10)"
      ],
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[('did', 0.9997876286506653),\n",
              " ('were', 0.9997825026512146),\n",
              " ('feare', 0.9997712969779968),\n",
              " ('To', 0.9997696876525879),\n",
              " ('can', 0.9997659921646118),\n",
              " ('be', 0.9997646808624268),\n",
              " ('me', 0.9997618198394775),\n",
              " ('(', 0.9997608661651611),\n",
              " ('for', 0.9997595548629761),\n",
              " ('So', 0.9997578859329224)]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Zfg_9ct1LVxK",
        "outputId": "941c99d1-f3f1-4104-f77e-70850f109233"
      },
      "source": [
        "model.wv['did'] # get numpy vector of word 'Macbeth'"
      ],
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([-3.57733190e-01,  1.31498814e-01, -3.64811748e-01, -3.19560729e-02,\n",
              "        2.22593561e-01,  1.39860272e-01,  2.89195538e-01,  1.13173693e-01,\n",
              "       -2.03456119e-01,  2.30740398e-01,  3.21552157e-01, -1.94947589e-02,\n",
              "        1.77455410e-01, -9.79656428e-02,  1.09568939e-01, -4.42196071e-01,\n",
              "       -3.71391594e-01,  3.15961063e-01,  4.32639867e-01,  4.01205927e-01,\n",
              "        4.15760688e-02,  2.13130236e-01, -1.46004602e-01,  3.42006655e-03,\n",
              "        1.51956335e-01,  2.29435697e-01,  8.56862292e-02, -1.36864200e-01,\n",
              "       -9.34164152e-02,  1.80605486e-01,  3.20621699e-01, -1.87747627e-01,\n",
              "       -1.36048272e-01,  3.84179175e-01,  3.72940242e-01,  2.36134127e-01,\n",
              "       -1.64353684e-01, -1.98470294e-01, -2.08301283e-03,  1.82027549e-01,\n",
              "       -2.48176172e-01,  3.47447805e-02,  1.55179739e-01,  1.77648738e-02,\n",
              "        3.28741083e-03,  4.83679831e-01,  6.38111308e-02,  2.69058108e-01,\n",
              "       -2.61533726e-02,  2.02223346e-01, -6.04587682e-02, -4.09872234e-02,\n",
              "       -1.39776707e-01,  2.51090005e-02,  6.56492822e-03, -1.89400643e-01,\n",
              "        1.36186212e-01, -4.85080406e-02, -2.54259855e-01,  1.95626095e-02,\n",
              "       -3.55173997e-03,  2.73116797e-01,  1.03901327e-01, -6.32568002e-02,\n",
              "        4.42321412e-04,  1.59238294e-01, -1.51489750e-01,  5.62172905e-02,\n",
              "       -1.15971854e-02,  9.89768729e-02, -4.28050384e-03,  1.83302804e-03,\n",
              "       -5.19516841e-02, -1.14471994e-01, -2.93976292e-02,  1.35174096e-01,\n",
              "        1.87644631e-01, -4.22828734e-01,  3.18877995e-01, -2.19833672e-01,\n",
              "        1.62515473e-02,  1.92310899e-01, -3.00093107e-02,  3.59999657e-01,\n",
              "        1.42292053e-01,  2.96746582e-01,  5.73777407e-02,  2.11292300e-02,\n",
              "        4.44845157e-03,  2.87942439e-02,  3.11298162e-01, -5.50519675e-03,\n",
              "       -8.33123475e-02,  2.27168053e-02,  5.33080921e-02, -7.58990739e-03,\n",
              "        2.14043647e-01,  1.00844651e-01,  9.25303325e-02, -3.15953307e-02],\n",
              "      dtype=float32)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 575
        },
        "id": "OPmlCHpEOviN",
        "outputId": "096f03cd-882d-4366-81b9-1b05546802d8"
      },
      "source": [
        "import matplotlib.pyplot as plt\n",
        "from sklearn.decomposition import PCA\n",
        "import random\n",
        "import numpy as np\n",
        "\n",
        "np.random.seed(42)\n",
        "words=list([e for e in model.wv.vocab if len(e)>4]) # plot words longer than 4\n",
        "random.shuffle(words)\n",
        "words3d = PCA(n_components=3, random_state=42).fit_transform(model.wv[words[:100]])\n",
        "\n",
        "def plotWords3D(vecs, words, title):\n",
        "    \"\"\"\n",
        "        Parameters\n",
        "        ----------\n",
        "        vecs : numpy-array\n",
        "            Transformed 3D array either by PCA or other techniques\n",
        "        words: a list of word\n",
        "            the word list to be mapped\n",
        "        title: str\n",
        "            The title of plot     \n",
        "        \"\"\"\n",
        "    fig = plt.figure(figsize=(14,10))\n",
        "    ax = fig.gca(projection='3d')\n",
        "    for w, vec in zip(words, vecs):\n",
        "        ax.text(vec[0],vec[1],vec[2], w, color=np.random.rand(3,))\n",
        "    ax.set_xlim(min(vecs[:,0]), max(vecs[:,0]))\n",
        "    ax.set_ylim(min(vecs[:,1]), max(vecs[:,1]))\n",
        "    ax.set_zlim(min(vecs[:,2]), max(vecs[:,2]))\n",
        "    ax.set_xlabel('DIM-1')\n",
        "    ax.set_ylabel('DIM-2')\n",
        "    ax.set_zlabel('DIM-3')\n",
        "    plt.title(title)\n",
        "    plt.show()\n",
        "plotWords3D(words3d, words, \"Visualizing Word2Vec Word Embeddings using PCA\")"
      ],
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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