Release/530

examples/colab/component_examples/classifiers/Bart_Zero_Shot_Classifier.ipynb

@@ -0,0 +1,313 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "source": [
+        "![JohnSnowLabs](https://nlp.johnsnowlabs.com/assets/images/logo.png)"
+      ],
+      "metadata": {
+        "id": "7A9NQR0tVbWf"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/https://github.com/JohnSnowLabs/nlu/tree/master/examples/colab/component_examples/classifiers/Bart_Zero_Shot_Classifiers.ipynb)"
+      ],
+      "metadata": {
+        "id": "XCxDeiyZxNyV"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "### **Zero Shot Classifiers**"
+      ],
+      "metadata": {
+        "id": "ba7qk8Dwxc29"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "### Zero Shot Text Classification\n",
+        "\n",
+        "State-of-the-art NLP models for text classification without annotated data\n",
+        "\n",
+        "Natural language processing is a very exciting field right now. In recent years, the community has begun to figure out some pretty effective methods of learning from the enormous amounts of unlabeled data available on the internet. The success of transfer learning from unsupervised models has allowed us to surpass virtually all existing benchmarks on downstream supervised learning tasks. As we continue to develop new model architectures and unsupervised learning objectives, \"state of the art\" continues to be a rapidly moving target for many tasks where large amounts of labeled data are available.\n",
+        "\n",
+        "### Zero Shot learning\n",
+        "\n",
+        "Zero-shot Learning (ZSL) is one of the most recent advancements in Machine Learning aimed to train Deep Neural Network models to have higher generalisability on unseen data. One of the most prominent methods of training such models is to use text prompts that explain the task to be solved, along with all possible outputs.\n",
+        "\n",
+        "The primary aim of using ZSL over supervised learning is to address the following limitations of training traditional supervised learning models:\n",
+        "\n",
+        "1. Training supervised NLP models require substantial amount of training data.\n",
+        "2. Even with recent trend of fine-tuning large language models, the supervised approach of training or fine-tuning a model is basically to learn a very specific data distribution, which results in low performance when applied to diverse and unseen data.\n",
+        "3. The classical annotate-train-test cycle is highly demanding in terms of temporal and human resources."
+      ],
+      "metadata": {
+        "id": "VOktZCAgxffG"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "### Bart Zero Shot Classifier\n",
+        "\n",
+        "This model is intended to be used for zero-shot text classification, especially in English. It is fine-tuned on MNLI by using large BART model.\n",
+        "\n",
+        "BartForZeroShotClassification using a ModelForSequenceClassification trained on MNLI tasks. Equivalent of BartForSequenceClassification models, but these models don’t require a hardcoded number of potential classes, they can be chosen at runtime. It usually means it’s slower but it is much more flexible.\n",
+        "\n",
+        "We used TFBartForSequenceClassification to train this model and used BartForZeroShotClassification annotator in Spark NLP 🚀 for prediction at scale"
+      ],
+      "metadata": {
+        "id": "MvfFWlHrxmGQ"
+      }
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "8w2RtQGCU_Xg"
+      },
+      "outputs": [],
+      "source": [
+        "!pip install nlu\n",
+        "!pip install pyspark==3.4.1"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import nlu\n",
+        "import pandas as pd"
+      ],
+      "metadata": {
+        "id": "mU_7-Y4nVZXA"
+      },
+      "execution_count": 3,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "text = ['I have a problem with my hotel reservation that needs to be resolved asap!!']"
+      ],
+      "metadata": {
+        "id": "Bn1xHZfGVqJA"
+      },
+      "execution_count": 4,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "bart_zero_shot = nlu.load('en.bart.zero_shot_classifier')"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "29Q7-Riqw74U",
+        "outputId": "e7ed4737-efbb-48cc-fbdd-40d01545cb27"
+      },
+      "execution_count": 5,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Warning::Spark Session already created, some configs may not take.\n",
+            "bart_large_zero_shot_classifier_mnli download started this may take some time.\n",
+            "Approximate size to download 445.4 MB\n",
+            "[OK!]\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "results = bart_zero_shot.predict(text, output_level = 'document')"
+      ],
+      "metadata": {
+        "id": "34efPvSQw9cl"
+      },
+      "execution_count": 8,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "results"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 81
+        },
+        "id": "s75RpDk6w-5f",
+        "outputId": "8cd5cdf1-2982-478b-a05e-819c0bd4b2d2"
+      },
+      "execution_count": 9,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "  classified_sequence classified_sequence_confidence  \\\n",
+              "0            [travel]                   [0.12591693]   \n",
+              "\n",
+              "                                            document  \n",
+              "0  I have a problem with my hotel reservation tha...  "
+            ],
+            "text/html": [
+              "\n",
+              "  <div id=\"df-69db0df6-4398-4d2e-8abe-7b957daed517\" class=\"colab-df-container\">\n",
+              "    <div>\n",
+              "<style scoped>\n",
+              "    .dataframe tbody tr th:only-of-type {\n",
+              "        vertical-align: middle;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe tbody tr th {\n",
+              "        vertical-align: top;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe thead th {\n",
+              "        text-align: right;\n",
+              "    }\n",
+              "</style>\n",
+              "<table border=\"1\" class=\"dataframe\">\n",
+              "  <thead>\n",
+              "    <tr style=\"text-align: right;\">\n",
+              "      <th></th>\n",
+              "      <th>classified_sequence</th>\n",
+              "      <th>classified_sequence_confidence</th>\n",
+              "      <th>document</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>[travel]</td>\n",
+              "      <td>[0.12591693]</td>\n",
+              "      <td>I have a problem with my hotel reservation tha...</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>\n",
+              "    <div class=\"colab-df-buttons\">\n",
+              "\n",
+              "  <div class=\"colab-df-container\">\n",
+              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-69db0df6-4398-4d2e-8abe-7b957daed517')\"\n",
+              "            title=\"Convert this dataframe to an interactive table.\"\n",
+              "            style=\"display:none;\">\n",
+              "\n",
+              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
+              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
+              "  </svg>\n",
+              "    </button>\n",
+              "\n",
+              "  <style>\n",
+              "    .colab-df-container {\n",
+              "      display:flex;\n",
+              "      gap: 12px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert {\n",
+              "      background-color: #E8F0FE;\n",
+              "      border: none;\n",
+              "      border-radius: 50%;\n",
+              "      cursor: pointer;\n",
+              "      display: none;\n",
+              "      fill: #1967D2;\n",
+              "      height: 32px;\n",
+              "      padding: 0 0 0 0;\n",
+              "      width: 32px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert:hover {\n",
+              "      background-color: #E2EBFA;\n",
+              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+              "      fill: #174EA6;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-buttons div {\n",
+              "      margin-bottom: 4px;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert {\n",
+              "      background-color: #3B4455;\n",
+              "      fill: #D2E3FC;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert:hover {\n",
+              "      background-color: #434B5C;\n",
+              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
+              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
+              "      fill: #FFFFFF;\n",
+              "    }\n",
+              "  </style>\n",
+              "\n",
+              "    <script>\n",
+              "      const buttonEl =\n",
+              "        document.querySelector('#df-69db0df6-4398-4d2e-8abe-7b957daed517 button.colab-df-convert');\n",
+              "      buttonEl.style.display =\n",
+              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "\n",
+              "      async function convertToInteractive(key) {\n",
+              "        const element = document.querySelector('#df-69db0df6-4398-4d2e-8abe-7b957daed517');\n",
+              "        const dataTable =\n",
+              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
+              "                                                    [key], {});\n",
+              "        if (!dataTable) return;\n",
+              "\n",
+              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
+              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
+              "          + ' to learn more about interactive tables.';\n",
+              "        element.innerHTML = '';\n",
+              "        dataTable['output_type'] = 'display_data';\n",
+              "        await google.colab.output.renderOutput(dataTable, element);\n",
+              "        const docLink = document.createElement('div');\n",
+              "        docLink.innerHTML = docLinkHtml;\n",
+              "        element.appendChild(docLink);\n",
+              "      }\n",
+              "    </script>\n",
+              "  </div>\n",
+              "\n",
+              "    </div>\n",
+              "  </div>\n"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 9
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "UgFt5oRbogZw"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}