{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"intent_classification_airlines_ATIS.ipynb","provenance":[],"collapsed_sections":[]},"kernelspec":{"name":"python3","display_name":"Python 3"}},"cells":[{"cell_type":"markdown","metadata":{"id":"ZE4c3HMSkGGu"},"source":["![JohnSnowLabs](https://nlp.johnsnowlabs.com/assets/images/logo.png)\n","\n","\n","[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/JohnSnowLabs/nlu/blob/master/examples/colab/component_examples/classifiers/intent_classification_airlines_ATIS.ipynb)\n","\n","# Intent Classification with NLU\n","\n","|Type | \tDescription |\n","|------|--------------|\n"," | atis_airfare|air fares, like **500 $**\n"," | atis_ground_service|gorund services like, **Transporation**\n"," | atis_flight|aits flights like, **6B12**\n"," | atis_airline|atis airline like, **Emirates**\n"," | atis_abbreviation|atis abbreviations like,   **air fare q**\n","             \n","# What is the ATIS Dataset?\n","ATIS dataset provides large number of messages and their associated intents that can be used in training a classifier. Within a chatbot, intent refers to the goal the customer has in mind when typing in a question or comment. While entity refers to the modifier the customer uses to describe their issue, the intent is what they really mean. For example, a user says, ‘I need new shoes.’ The intent behind the message is to browse the footwear on offer. Understanding the intent of the customer is key to implementing a successful chatbot experience for end-user.\n","https://www.kaggle.com/hassanamin/atis-airlinetravelinformationsystem\n","\n"]},{"cell_type":"code","metadata":{"id":"SF5-Z-U4jukd","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1649990147602,"user_tz":-300,"elapsed":111768,"user":{"displayName":"Gammer Otaku","userId":"18042713576744284398"}},"outputId":"e2ab06a7-7811-4539-8212-41c21af55334"},"source":["!wget https://setup.johnsnowlabs.com/nlu/colab.sh -O - | bash\n","  \n","\n","import nlu"],"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["--2022-04-15 02:33:54--  https://setup.johnsnowlabs.com/nlu/colab.sh\n","Resolving setup.johnsnowlabs.com (setup.johnsnowlabs.com)... 51.158.130.125\n","Connecting to setup.johnsnowlabs.com (setup.johnsnowlabs.com)|51.158.130.125|:443... connected.\n","HTTP request sent, awaiting response... 302 Moved Temporarily\n","Location: https://raw.githubusercontent.com/JohnSnowLabs/nlu/master/scripts/colab_setup.sh [following]\n","--2022-04-15 02:33:54--  https://raw.githubusercontent.com/JohnSnowLabs/nlu/master/scripts/colab_setup.sh\n","Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...\n","Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.\n","HTTP request sent, awaiting response... 200 OK\n","Length: 1665 (1.6K) [text/plain]\n","Saving to: ‘STDOUT’\n","\n","-                   100%[===================>]   1.63K  --.-KB/s    in 0s      \n","\n","2022-04-15 02:33:55 (28.6 MB/s) - written to stdout [1665/1665]\n","\n","Installing  NLU 3.4.3rc2 with  PySpark 3.0.3 and Spark NLP 3.4.2 for Google Colab ...\n","Get:1 https://cloud.r-project.org/bin/linux/ubuntu bionic-cran40/ InRelease [3,626 B]\n","Ign:2 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64  InRelease\n","Ign:3 https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64  InRelease\n","Get:4 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64  Release [696 B]\n","Hit:5 https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64  Release\n","Get:6 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64  Release.gpg [836 B]\n","Get:7 http://ppa.launchpad.net/c2d4u.team/c2d4u4.0+/ubuntu bionic InRelease [15.9 kB]\n","Hit:8 http://archive.ubuntu.com/ubuntu bionic InRelease\n","Get:9 http://security.ubuntu.com/ubuntu bionic-security InRelease [88.7 kB]\n","Get:10 http://archive.ubuntu.com/ubuntu bionic-updates InRelease [88.7 kB]\n","Hit:11 http://ppa.launchpad.net/cran/libgit2/ubuntu bionic InRelease\n","Get:13 http://archive.ubuntu.com/ubuntu bionic-backports InRelease [74.6 kB]\n","Get:14 http://ppa.launchpad.net/deadsnakes/ppa/ubuntu bionic InRelease [15.9 kB]\n","Get:15 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64  Packages [953 kB]\n","Hit:16 http://ppa.launchpad.net/graphics-drivers/ppa/ubuntu bionic InRelease\n","Get:17 http://ppa.launchpad.net/c2d4u.team/c2d4u4.0+/ubuntu bionic/main Sources [1,947 kB]\n","Get:18 http://security.ubuntu.com/ubuntu bionic-security/universe amd64 Packages [1,490 kB]\n","Get:19 http://archive.ubuntu.com/ubuntu bionic-updates/main amd64 Packages [3,134 kB]\n","Get:20 http://security.ubuntu.com/ubuntu bionic-security/main amd64 Packages [2,695 kB]\n","Get:21 http://ppa.launchpad.net/c2d4u.team/c2d4u4.0+/ubuntu bionic/main amd64 Packages [996 kB]\n","Get:22 http://archive.ubuntu.com/ubuntu bionic-updates/universe amd64 Packages [2,268 kB]\n","Get:23 http://ppa.launchpad.net/deadsnakes/ppa/ubuntu bionic/main amd64 Packages [45.3 kB]\n","Fetched 13.8 MB in 4s (3,725 kB/s)\n","Reading package lists... Done\n","tar: spark-3.0.2-bin-hadoop2.7.tgz: Cannot open: No such file or directory\n","tar: Error is not recoverable: exiting now\n","\u001b[K     |████████████████████████████████| 209.1 MB 55 kB/s \n","\u001b[K     |████████████████████████████████| 142 kB 48.8 MB/s \n","\u001b[K     |████████████████████████████████| 505 kB 45.5 MB/s \n","\u001b[K     |████████████████████████████████| 198 kB 56.6 MB/s \n","\u001b[?25h  Building wheel for pyspark (setup.py) ... \u001b[?25l\u001b[?25hdone\n","Collecting nlu_tmp==3.4.3rc10\n","  Downloading nlu_tmp-3.4.3rc10-py3-none-any.whl (510 kB)\n","\u001b[K     |████████████████████████████████| 510 kB 5.0 MB/s \n","\u001b[?25hRequirement already satisfied: pandas>=1.3.5 in /usr/local/lib/python3.7/dist-packages (from nlu_tmp==3.4.3rc10) (1.3.5)\n","Requirement already satisfied: numpy in /usr/local/lib/python3.7/dist-packages (from nlu_tmp==3.4.3rc10) (1.21.5)\n","Requirement already satisfied: pyarrow>=0.16.0 in /usr/local/lib/python3.7/dist-packages (from nlu_tmp==3.4.3rc10) (6.0.1)\n","Requirement already satisfied: dataclasses in /usr/local/lib/python3.7/dist-packages (from nlu_tmp==3.4.3rc10) (0.6)\n","Requirement already satisfied: spark-nlp<3.5.0,>=3.4.2 in /usr/local/lib/python3.7/dist-packages (from nlu_tmp==3.4.3rc10) (3.4.2)\n","Requirement already satisfied: pytz>=2017.3 in /usr/local/lib/python3.7/dist-packages (from pandas>=1.3.5->nlu_tmp==3.4.3rc10) (2018.9)\n","Requirement already satisfied: python-dateutil>=2.7.3 in /usr/local/lib/python3.7/dist-packages (from pandas>=1.3.5->nlu_tmp==3.4.3rc10) (2.8.2)\n","Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.7/dist-packages (from python-dateutil>=2.7.3->pandas>=1.3.5->nlu_tmp==3.4.3rc10) (1.15.0)\n","Installing collected packages: nlu-tmp\n","Successfully installed nlu-tmp-3.4.3rc10\n"]}]},{"cell_type":"code","metadata":{"id":"51Zr-JvU4xEg","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1649990148234,"user_tz":-300,"elapsed":665,"user":{"displayName":"Gammer Otaku","userId":"18042713576744284398"}},"outputId":"9edca62f-a258-4563-fa37-791f1ce4b77e"},"source":["# Download the dataset \n","! wget http://ckl-it.de/wp-content/uploads/2021/01/atis_intents.csv\n"],"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["--2022-04-15 02:35:46--  http://ckl-it.de/wp-content/uploads/2021/01/atis_intents.csv\n","Resolving ckl-it.de (ckl-it.de)... 217.160.0.108, 2001:8d8:100f:f000::209\n","Connecting to ckl-it.de (ckl-it.de)|217.160.0.108|:80... connected.\n","HTTP request sent, awaiting response... 200 OK\n","Length: 391936 (383K) [text/csv]\n","Saving to: ‘atis_intents.csv’\n","\n","atis_intents.csv    100%[===================>] 382.75K   669KB/s    in 0.6s    \n","\n","2022-04-15 02:35:47 (669 KB/s) - ‘atis_intents.csv’ saved [391936/391936]\n","\n"]}]},{"cell_type":"markdown","metadata":{"id":"yZ7R8bho2kXI"},"source":["# Predict Intent of Airline messages"]},{"cell_type":"code","metadata":{"id":"7GJX5d6mjk5j","colab":{"base_uri":"https://localhost:8080/","height":580},"executionInfo":{"status":"ok","timestamp":1649990290799,"user_tz":-300,"elapsed":142581,"user":{"displayName":"Gammer Otaku","userId":"18042713576744284398"}},"outputId":"384404ea-9b81-48a3-eb65-024b784020c8"},"source":["import nlu \n","import pandas as pd\n","\n","df = pd.read_csv(\"atis_intents.csv\")\n","df.columns = [\"flight\",\"text\"]\n","\n","preds = nlu.load('en.classify.intent.airline').predict(df[\"text\"],output_level='sentence')\n","preds"],"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["classifierdl_use_atis download started this may take some time.\n","Approximate size to download 21.1 MB\n","[OK!]\n","tfhub_use download started this may take some time.\n","Approximate size to download 923.7 MB\n","[OK!]\n","sentence_detector_dl download started this may take some time.\n","Approximate size to download 354.6 KB\n","[OK!]\n"]},{"output_type":"execute_result","data":{"text/plain":["            intent intent_confidence_confidence  \\\n","0      atis_flight                     0.999994   \n","1      atis_flight                     0.999997   \n","2     atis_airfare                     0.997928   \n","3     atis_airfare                          1.0   \n","4      atis_flight                     0.999996   \n","...            ...                          ...   \n","4972  atis_airfare                     0.999503   \n","4973   atis_flight                     0.999994   \n","4974  atis_airline                          1.0   \n","4975   atis_flight                     0.994565   \n","4976   atis_flight                     0.999779   \n","\n","                                               sentence  \\\n","0     what flights are available from pittsburgh to ...   \n","1     what is the arrival time in san francisco for ...   \n","2               cheapest airfare from tacoma to orlando   \n","3     round trip fares from pittsburgh to philadelph...   \n","4     i need a flight tomorrow from columbus to minn...   \n","...                                                 ...   \n","4972  what is the airfare for flights from denver to...   \n","4973  do you have any flights from denver to baltimo...   \n","4974          which airlines fly into and out of denver   \n","4975  does continental fly from boston to san franci...   \n","4976  is there a delta flight from denver to san fra...   \n","\n","                                 sentence_embedding_use  \n","0     [0.037106938660144806, 0.0727505013346672, -0....  \n","1     [0.020266082137823105, 0.044293809682130814, -...  \n","2     [0.05529679358005524, 0.0694049745798111, -0.0...  \n","3     [0.044724948704242706, 0.07032939791679382, -0...  \n","4     [-0.0009330636239610612, 0.0720256119966507, -...  \n","...                                                 ...  \n","4972  [0.015531656332314014, 0.06927467882633209, -0...  \n","4973  [0.03598876670002937, 0.06490834802389145, -0....  \n","4974  [0.0314473956823349, 0.0699605792760849, -0.06...  \n","4975  [0.01851840876042843, 0.07567648589611053, -0....  \n","4976  [0.026785779744386673, 0.06964033842086792, -0...  \n","\n","[4977 rows x 4 columns]"],"text/html":["\n","  <div id=\"df-36540a2c-fbfb-4edd-9f49-f629b9e642ea\">\n","    <div class=\"colab-df-container\">\n","      <div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>intent</th>\n","      <th>intent_confidence_confidence</th>\n","      <th>sentence</th>\n","      <th>sentence_embedding_use</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>atis_flight</td>\n","      <td>0.999994</td>\n","      <td>what flights are available from pittsburgh to ...</td>\n","      <td>[0.037106938660144806, 0.0727505013346672, -0....</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>atis_flight</td>\n","      <td>0.999997</td>\n","      <td>what is the arrival time in san francisco for ...</td>\n","      <td>[0.020266082137823105, 0.044293809682130814, -...</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>atis_airfare</td>\n","      <td>0.997928</td>\n","      <td>cheapest airfare from tacoma to orlando</td>\n","      <td>[0.05529679358005524, 0.0694049745798111, -0.0...</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>atis_airfare</td>\n","      <td>1.0</td>\n","      <td>round trip fares from pittsburgh to philadelph...</td>\n","      <td>[0.044724948704242706, 0.07032939791679382, -0...</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>atis_flight</td>\n","      <td>0.999996</td>\n","      <td>i need a flight tomorrow from columbus to minn...</td>\n","      <td>[-0.0009330636239610612, 0.0720256119966507, -...</td>\n","    </tr>\n","    <tr>\n","      <th>...</th>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","    </tr>\n","    <tr>\n","      <th>4972</th>\n","      <td>atis_airfare</td>\n","      <td>0.999503</td>\n","      <td>what is the airfare for flights from denver to...</td>\n","      <td>[0.015531656332314014, 0.06927467882633209, -0...</td>\n","    </tr>\n","    <tr>\n","      <th>4973</th>\n","      <td>atis_flight</td>\n","      <td>0.999994</td>\n","      <td>do you have any flights from denver to baltimo...</td>\n","      <td>[0.03598876670002937, 0.06490834802389145, -0....</td>\n","    </tr>\n","    <tr>\n","      <th>4974</th>\n","      <td>atis_airline</td>\n","      <td>1.0</td>\n","      <td>which airlines fly into and out of denver</td>\n","      <td>[0.0314473956823349, 0.0699605792760849, -0.06...</td>\n","    </tr>\n","    <tr>\n","      <th>4975</th>\n","      <td>atis_flight</td>\n","      <td>0.994565</td>\n","      <td>does continental fly from boston to san franci...</td>\n","      <td>[0.01851840876042843, 0.07567648589611053, -0....</td>\n","    </tr>\n","    <tr>\n","      <th>4976</th>\n","      <td>atis_flight</td>\n","      <td>0.999779</td>\n","      <td>is there a delta flight from denver to san fra...</td>\n","      <td>[0.026785779744386673, 0.06964033842086792, -0...</td>\n","    </tr>\n","  </tbody>\n","</table>\n","<p>4977 rows × 4 columns</p>\n","</div>\n","      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-36540a2c-fbfb-4edd-9f49-f629b9e642ea')\"\n","              title=\"Convert this dataframe to an interactive table.\"\n","              style=\"display:none;\">\n","        \n","  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n","       width=\"24px\">\n","    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n","    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n","  </svg>\n","      </button>\n","      \n","  <style>\n","    .colab-df-container {\n","      display:flex;\n","      flex-wrap:wrap;\n","      gap: 12px;\n","    }\n","\n","    .colab-df-convert {\n","      background-color: #E8F0FE;\n","      border: none;\n","      border-radius: 50%;\n","      cursor: pointer;\n","      display: none;\n","      fill: #1967D2;\n","      height: 32px;\n","      padding: 0 0 0 0;\n","      width: 32px;\n","    }\n","\n","    .colab-df-convert:hover {\n","      background-color: #E2EBFA;\n","      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n","      fill: #174EA6;\n","    }\n","\n","    [theme=dark] .colab-df-convert {\n","      background-color: #3B4455;\n","      fill: #D2E3FC;\n","    }\n","\n","    [theme=dark] .colab-df-convert:hover {\n","      background-color: #434B5C;\n","      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n","      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n","      fill: #FFFFFF;\n","    }\n","  </style>\n","\n","      <script>\n","        const buttonEl =\n","          document.querySelector('#df-36540a2c-fbfb-4edd-9f49-f629b9e642ea 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-36540a2c-fbfb-4edd-9f49-f629b9e642ea');\n","          const dataTable =\n","            await google.colab.kernel.invokeFunction('convertToInteractive',\n","                                                     [key], {});\n","          if (!dataTable) return;\n","\n","          const docLinkHtml = 'Like what you see? Visit the ' +\n","            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n","            + ' to learn more about interactive tables.';\n","          element.innerHTML = '';\n","          dataTable['output_type'] = 'display_data';\n","          await google.colab.output.renderOutput(dataTable, element);\n","          const docLink = document.createElement('div');\n","          docLink.innerHTML = docLinkHtml;\n","          element.appendChild(docLink);\n","        }\n","      </script>\n","    </div>\n","  </div>\n","  "]},"metadata":{},"execution_count":3}]},{"cell_type":"markdown","metadata":{"id":"HH6KBffB2pY_"},"source":["# Plot Distribution of Intent in Messages"]},{"cell_type":"code","metadata":{"id":"WdnY9n1LTmed","colab":{"base_uri":"https://localhost:8080/","height":388},"executionInfo":{"status":"ok","timestamp":1649990290804,"user_tz":-300,"elapsed":22,"user":{"displayName":"Gammer Otaku","userId":"18042713576744284398"}},"outputId":"36c79ee1-9285-4d11-a8ab-ff030e1e1710"},"source":["preds.intent.value_counts().plot.bar(title='Distribution of message intents')"],"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["<matplotlib.axes._subplots.AxesSubplot at 0x7fefb5071710>"]},"metadata":{},"execution_count":4},{"output_type":"display_data","data":{"text/plain":["<Figure size 432x288 with 1 Axes>"],"image/png":"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\n"},"metadata":{"needs_background":"light"}}]}]}