getting-started-tutorial/02-model-training.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Part 2: Training an ML Model\n",
    "\n",
    "This part of the MLRun getting-started tutorial walks you through the steps for training a machine-learning (ML) model, including data exploration and model testing.\n",
    "\n",
    "The tutorial consists of the following steps:\n",
    "\n",
    "1. [Setup and Configuration](#gs-tutorial-2-step-setup)\n",
    "2. [Creating a training function](#gs-tutorial-2-step-create-a-training-function)\n",
    "3. [Exploring the data with an MLRun marketplace function](#gs-tutorial-2-step-explore-data-w-mlrun-func)\n",
    "4. [Testing your model](#gs-tutorial-2-step-test-model)\n",
    "\n",
    "By the end of this tutorial you'll learn how to\n",
    "\n",
    "- Create a training function, store models, and track experiments while running them.\n",
    "- Use artifacts as inputs to functions.\n",
    "- Leverage the MLRun functions marketplace.\n",
    "- View plot artifacts."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id=\"gs-tutorial-2-prerequisites\"></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Prerequisites\n",
    "\n",
    "The following steps are a continuation of the previous part of this getting-started tutorial and rely on the generated outputs.\n",
    "Therefore, make sure to first run [part 1](01-mlrun-basics.ipynb) of the tutorial."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id=\"gs-tutorial-2-step-setup\"></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 1: Setup and Configuration"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id=\"gs-tutorial-2-mlrun-import-libraries\"></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Importing Libraries\n",
    "\n",
    "Run the following code to import required libraries:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from os import path\n",
    "import mlrun"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id=\"gs-tutorial-2-mlrun-envr-init\"></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Initializing Your MLRun Environment\n",
    "\n",
    "Use the `set_environment` MLRun method to configure the working environment and default configuration.\n",
    "Set the `project` and `user_project` parameters to the same values that you used in the call to this method in the [Part 1: MLRun Basics](./01-mlrun-basics.ipynb#gs-tutorial-1-set-mlrun-envr) tutorial notebook."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Set the base project name\n",
    "project_name_base = 'getting-started-tutorial'\n",
    "# Initialize the MLRun environment and save the project name and artifacts path\n",
    "project_name, artifact_path = mlrun.set_environment(project=project_name_base,\n",
    "                                                    user_project=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id=\"gs-tutorial-2-mark-mlrun-code-start\"></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Marking The Beginning of Your Function Code\n",
    "\n",
    "The following code uses the `# nuclio: start-code` marker comment annotation to instruct MLRun to start processing code only from this location.\n",
    "\n",
    "> **Note:** You can add code to define function dependencies and perform additional configuration after the `# nuclio: start-code` marker and before [the `# nuclio: end-code` marker](#gs-tutorial-2-mark-mlrun-code-end)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# nuclio: start-code"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id=\"gs-tutorial-2-step-create-a-training-function\"></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 2: Creating a Training Function\n",
    "\n",
    "An essential component of artifact management and versioning is storing a model version.\n",
    "This allows users to experiment with different models and compare their performance without having to worry about losing previous results.\n",
    "\n",
    "The simplest way to store a model named `my_model`, for example, is with the following code:\n",
    "\n",
    "``` python\n",
    "from cloudpickle import dumps\n",
    "model_data = dumps(model)\n",
    "context.log_model(key='my_model', body=model_data, model_file='my_model.pkl')\n",
    "```\n",
    "\n",
    "You can also store any related metrics by providing a dictionary in the `metrics` parameter, such as `metrics={'accuracy': 0.9}`.\n",
    "Furthermore, you can use the `extra_data` parameter to pass any additional data that you wish to store along with the model;\n",
    "for example `extra_data={'confusion': confusion.target_path}`.\n",
    "\n",
    "You can use the `eval_model_v2` utility method (from `mlrun.utils`) to calculate mode metrics.\n",
    "\n",
    "The following example implements a simple model that's trained using scikit-learn;\n",
    "(in a real-world scenario, you would typically send the data as input to the function).\n",
    "The last two lines evaluate the model and log the model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn import linear_model\n",
    "from sklearn import datasets\n",
    "from sklearn.model_selection import train_test_split\n",
    "from cloudpickle import dumps\n",
    "import pandas as pd\n",
    "\n",
    "from mlrun.execution import MLClientCtx\n",
    "from mlrun.datastore import DataItem\n",
    "from mlrun.mlutils.data import get_sample\n",
    "from mlrun.mlutils.plots import eval_model_v2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "def train_iris(context: MLClientCtx,\n",
    "               dataset: DataItem,\n",
    "               label_column: str = \"labels\"):\n",
    "\n",
    "    raw, labels, header = get_sample(dataset, sample=-1, label=label_column)\n",
    "    \n",
    "    # Basic scikit-learn Iris data-set SVM model\n",
    "    X_train, X_test, y_train, y_test = train_test_split(\n",
    "        raw, labels, test_size=0.2, random_state=42)\n",
    "    \n",
    "    context.log_dataset('train_set', \n",
    "                        df=pd.concat([X_train, y_train.to_frame()], axis=1),\n",
    "                        format='csv', index=False, \n",
    "                        artifact_path=context.artifact_subpath('data'))\n",
    "\n",
    "    context.log_dataset('test_set', \n",
    "                        df=pd.concat([X_test, y_test.to_frame()], axis=1),\n",
    "                        format='csv', index=False, \n",
    "                        labels={\"data-type\": \"held-out\"},\n",
    "                        artifact_path=context.artifact_subpath('data'))\n",
    "    \n",
    "    model = linear_model.LogisticRegression(max_iter=10000)\n",
    "    model.fit(X_train, y_train)\n",
    "    \n",
    "    # Evaluate model results and get the evaluation metrics\n",
    "    eval_metrics = eval_model_v2(context, X_test, y_test, model)\n",
    "    \n",
    "    # Log model\n",
    "    context.log_model(\"model\",\n",
    "                      body=dumps(model),\n",
    "                      artifact_path=context.artifact_subpath(\"models\"),\n",
    "                      extra_data=eval_metrics, \n",
    "                      model_file=\"model.pkl\",\n",
    "                      metrics=context.results,\n",
    "                      labels={\"class\": \"sklearn.linear_model.LogisticRegression\"})"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id=\"gs-tutorial-2-mark-mlrun-code-end\"></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Marking The End of Your Function Code\n",
    "\n",
    "The following code uses the `# nuclio: end-code` marker code annotation to mark the end of the code section that should be converted to your MLRun function (which began with [the `# nuclio: start-code` annotation](#gs-tutorial-2-mark-mlrun-code-start)) and instruct MLRun to stop parsing the notebook at this point.\n",
    "\n",
    "> **Important:** Don't remove the start-code and end-code annotation cells."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# nuclio: end-code"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Converting the Code to an MLRun Function\n",
    "\n",
    "Use the MLRun `code_to_function` method to convert the selected portions of your notebook code into an MLRun function in your project &mdash; a function object with embedded code, which can run on the cluster.\n",
    "\n",
    "The following code converts the code of your local `train_iris` function, which is defined within `# nuclio: start-code` and `# nuclio: end-code` annotations that mark the notebook code to convert (see the previous code cells), into into a `train_iris_func` MLRun function.\n",
    "Because the `project` parameter of the conversion method isn't set, the MLRun function is added to the default project that's configured for your environment (as stored in the `project_name` variable &mdash; see the `set_environment` call in the previous steps).\n",
    "The code sets the following `code_to_function` parameters:\n",
    "\n",
    "- `name` &mdash; the name of the new MLRun function (`train_iris`).\n",
    "- `handler` &mdash; the name of the function-handler method (`train_iris`; the default is `main`).\n",
    "- `kind` &mdash; the function's runtime type (`job` for a Python process).\n",
    "- `image` &mdash; the name of the container image to use for running the job &mdash; \"mlrun/ml-models\".\n",
    "    This image contains a wide variety of machine-learning Python packages (such as scikit-learn, TensorFlow, and PyTorch), saving you the time of creating your own image."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_iris_func = mlrun.code_to_function(name='train_iris',\n",
    "                                         handler='train_iris',\n",
    "                                         kind='job',\n",
    "                                         image='mlrun/ml-models')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id=\"gs-tutorial-2-persistent-volume-mount\"></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Mounting a Persistent Volume\n",
    "\n",
    "When running jobs in Kubernetes, to allow a job to read or write data you need to give it access to a **Persistent Volume (PV)**.\n",
    "This connects your function to your environment's shared file system and allows you to pass data from your environment to the function and get back the results (plots) directly into your notebook.\n",
    "\n",
    "A **Persistent Volume Claim (PVC)** is a request to access a PV.\n",
    "In MLRun, such requests can be issued by calling the `apply` function method and passing the mount method as input.\n",
    "`mount_v3io` creates a PVC to the Iguazio Data Science Platform's V3IO volume;\n",
    "`mount_pvc` is a generic mount function for other storage types (such as NFS).\n",
    "The tutorial example uses the `auto_mount` method to automatically select the appropriate mount method for the your environment.\n",
    "Calling `auto_mount` without any parameters accesses the Iguazio Data Science Platform's V3IO volume when the `V3IO_ACCESS_KEY` and `V3IO_USERNAME` environment variables are set;\n",
    "otherwise, the method attempts to access a Kubernetes PVC volume when an `MLRUN_PVC_MOUNT=<pvc-name>:<mount-path>` environment variable is set.\n",
    "You can also explicitly set the `pvc_name` and `volume_mount_path` parameters to a specific PVC name and volume mount path instead of relying on environment variables."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "from mlrun.platforms import auto_mount\n",
    "train_iris_func = train_iris_func.apply(auto_mount())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Running the Function on a Cluster\n",
    "\n",
    "Use the following code to run your function on a cluster."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'store://getting-started-tutorial-iguazio/prep_data_cleaned_data'"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset = f'store://{project_name}/prep_data_cleaned_data'\n",
    "dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "> 2021-01-25 08:37:23,350 [info] starting run train-iris-train_iris uid=151f5607321244799eb665a781970a2b DB=http://mlrun-api:8080\n",
      "> 2021-01-25 08:37:23,566 [info] Job is running in the background, pod: train-iris-train-iris-blw6w\n",
      "> 2021-01-25 08:37:28,682 [info] run executed, status=completed\n",
      "final state: completed\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<style>\n",
       ".dictlist {\n",
       "  background-color: #4EC64B;\n",
       "  text-align: center;\n",
       "  margin: 4px;\n",
       "  border-radius: 3px; padding: 0px 3px 1px 3px; display: inline-block;}\n",
       ".artifact {\n",
       "  cursor: pointer;\n",
       "  background-color: #4EC64B;\n",
       "  text-align: left;\n",
       "  margin: 4px; border-radius: 3px; padding: 0px 3px 1px 3px; display: inline-block;\n",
       "}\n",
       "div.block.hidden {\n",
       "  display: none;\n",
       "}\n",
       ".clickable {\n",
       "  cursor: pointer;\n",
       "}\n",
       ".ellipsis {\n",
       "  display: inline-block;\n",
       "  max-width: 60px;\n",
       "  white-space: nowrap;\n",
       "  overflow: hidden;\n",
       "  text-overflow: ellipsis;\n",
       "}\n",
       ".master-wrapper {\n",
       "  display: flex;\n",
       "  flex-flow: row nowrap;\n",
       "  justify-content: flex-start;\n",
       "  align-items: stretch;\n",
       "}\n",
       ".master-tbl {\n",
       "  flex: 3\n",
       "}\n",
       ".master-wrapper > div {\n",
       "  margin: 4px;\n",
       "  padding: 10px;\n",
       "}\n",
       "iframe.fileview {\n",
       "  border: 0 none;\n",
       "  height: 100%;\n",
       "  width: 100%;\n",
       "  white-space: pre-wrap;\n",
       "}\n",
       ".pane-header-title {\n",
       "  width: 80%;\n",
       "  font-weight: 500;\n",
       "}\n",
       ".pane-header {\n",
       "  line-height: 1;\n",
       "  background-color: #4EC64B;\n",
       "  padding: 3px;\n",
       "}\n",
       ".pane-header .close {\n",
       "  font-size: 20px;\n",
       "  font-weight: 700;\n",
       "  float: right;\n",
       "  margin-top: -5px;\n",
       "}\n",
       ".master-wrapper .right-pane {\n",
       "  border: 1px inset silver;\n",
       "  width: 40%;\n",
       "  min-height: 300px;\n",
       "  flex: 3\n",
       "  min-width: 500px;\n",
       "}\n",
       ".master-wrapper * {\n",
       "  box-sizing: border-box;\n",
       "}\n",
       "</style><script>\n",
       "function copyToClipboard(fld) {\n",
       "    if (document.queryCommandSupported && document.queryCommandSupported('copy')) {\n",
       "        var textarea = document.createElement('textarea');\n",
       "        textarea.textContent = fld.innerHTML;\n",
       "        textarea.style.position = 'fixed';\n",
       "        document.body.appendChild(textarea);\n",
       "        textarea.select();\n",
       "\n",
       "        try {\n",
       "            return document.execCommand('copy'); // Security exception may be thrown by some browsers.\n",
       "        } catch (ex) {\n",
       "\n",
       "        } finally {\n",
       "            document.body.removeChild(textarea);\n",
       "        }\n",
       "    }\n",
       "}\n",
       "function expandPanel(el) {\n",
       "  const panelName = \"#\" + el.getAttribute('paneName');\n",
       "  console.log(el.title);\n",
       "\n",
       "  document.querySelector(panelName + \"-title\").innerHTML = el.title\n",
       "  iframe = document.querySelector(panelName + \"-body\");\n",
       "\n",
       "  const tblcss = `<style> body { font-family: Arial, Helvetica, sans-serif;}\n",
       "    #csv { margin-bottom: 15px; }\n",
       "    #csv table { border-collapse: collapse;}\n",
       "    #csv table td { padding: 4px 8px; border: 1px solid silver;} </style>`;\n",
       "\n",
       "  function csvToHtmlTable(str) {\n",
       "    return '<div id=\"csv\"><table><tr><td>' +  str.replace(/[\\n\\r]+$/g, '').replace(/[\\n\\r]+/g, '</td></tr><tr><td>')\n",
       "      .replace(/,/g, '</td><td>') + '</td></tr></table></div>';\n",
       "  }\n",
       "\n",
       "  function reqListener () {\n",
       "    if (el.title.endsWith(\".csv\")) {\n",
       "      iframe.setAttribute(\"srcdoc\", tblcss + csvToHtmlTable(this.responseText));\n",
       "    } else {\n",
       "      iframe.setAttribute(\"srcdoc\", this.responseText);\n",
       "    }\n",
       "    console.log(this.responseText);\n",
       "  }\n",
       "\n",
       "  const oReq = new XMLHttpRequest();\n",
       "  oReq.addEventListener(\"load\", reqListener);\n",
       "  oReq.open(\"GET\", el.title);\n",
       "  oReq.send();\n",
       "\n",
       "\n",
       "  //iframe.src = el.title;\n",
       "  const resultPane = document.querySelector(panelName + \"-pane\");\n",
       "  if (resultPane.classList.contains(\"hidden\")) {\n",
       "    resultPane.classList.remove(\"hidden\");\n",
       "  }\n",
       "}\n",
       "function closePanel(el) {\n",
       "  const panelName = \"#\" + el.getAttribute('paneName')\n",
       "  const resultPane = document.querySelector(panelName + \"-pane\");\n",
       "  if (!resultPane.classList.contains(\"hidden\")) {\n",
       "    resultPane.classList.add(\"hidden\");\n",
       "  }\n",
       "}\n",
       "\n",
       "</script>\n",
       "<div class=\"master-wrapper\">\n",
       "  <div class=\"block master-tbl\"><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>project</th>\n",
       "      <th>uid</th>\n",
       "      <th>iter</th>\n",
       "      <th>start</th>\n",
       "      <th>state</th>\n",
       "      <th>name</th>\n",
       "      <th>labels</th>\n",
       "      <th>inputs</th>\n",
       "      <th>parameters</th>\n",
       "      <th>results</th>\n",
       "      <th>artifacts</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>getting-started-tutorial-iguazio</td>\n",
       "      <td><div title=\"151f5607321244799eb665a781970a2b\"><a href=\"https://mlrun-ui.default-tenant.app.aefccdjffbit.iguazio-cd0.com/projects/getting-started-tutorial-iguazio/jobs/monitor/151f5607321244799eb665a781970a2b/info\" target=\"_blank\" >...81970a2b</a></div></td>\n",
       "      <td>0</td>\n",
       "      <td>Jan 25 08:37:27</td>\n",
       "      <td>completed</td>\n",
       "      <td>train-iris-train_iris</td>\n",
       "      <td><div class=\"dictlist\">v3io_user=iguazio</div><div class=\"dictlist\">kind=job</div><div class=\"dictlist\">owner=iguazio</div><div class=\"dictlist\">host=train-iris-train-iris-blw6w</div></td>\n",
       "      <td><div title=\"store://getting-started-tutorial-iguazio/prep_data_cleaned_data\">dataset</div></td>\n",
       "      <td><div class=\"dictlist\">label_column=label</div></td>\n",
       "      <td><div class=\"dictlist\">accuracy=1.0</div><div class=\"dictlist\">test-error=0.0</div><div class=\"dictlist\">auc-micro=1.0</div><div class=\"dictlist\">auc-weighted=1.0</div><div class=\"dictlist\">f1-score=1.0</div><div class=\"dictlist\">precision_score=1.0</div><div class=\"dictlist\">recall_score=1.0</div></td>\n",
       "      <td><div title=\"/v3io/projects/getting-started-tutorial-iguazio/artifacts/data/train_set.csv\">train_set</div><div title=\"/v3io/projects/getting-started-tutorial-iguazio/artifacts/data/test_set.csv\">test_set</div><div title=\"/v3io/projects/getting-started-tutorial-iguazio/artifacts/plots/confusion-matrix.html\">confusion-matrix</div><div title=\"/v3io/projects/getting-started-tutorial-iguazio/artifacts/plots/precision-recall-multiclass.html\">precision-recall-multiclass</div><div title=\"/v3io/projects/getting-started-tutorial-iguazio/artifacts/plots/roc-multiclass.html\">roc-multiclass</div><div title=\"/v3io/projects/getting-started-tutorial-iguazio/artifacts/models\">model</div></td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div></div>\n",
       "  <div id=\"result9afbd30b-pane\" class=\"right-pane block hidden\">\n",
       "    <div class=\"pane-header\">\n",
       "      <span id=\"result9afbd30b-title\" class=\"pane-header-title\">Title</span>\n",
       "      <span onclick=\"closePanel(this)\" paneName=\"result9afbd30b\" class=\"close clickable\">&times;</span>\n",
       "    </div>\n",
       "    <iframe class=\"fileview\" id=\"result9afbd30b-body\"></iframe>\n",
       "  </div>\n",
       "</div>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "to track results use .show() or .logs() or in CLI: \n",
      "!mlrun get run 151f5607321244799eb665a781970a2b --project getting-started-tutorial-iguazio , !mlrun logs 151f5607321244799eb665a781970a2b --project getting-started-tutorial-iguazio\n",
      "> 2021-01-25 08:37:29,709 [info] run executed, status=completed\n"
     ]
    }
   ],
   "source": [
    "train_run = train_iris_func.run(inputs={'dataset': dataset},\n",
    "                                params={'label_column': 'label'})"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id='gs-run-ingest-func'></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Reviewing the Run Output\n",
    "\n",
    "You can view extensive run information and artifacts from Jupyter Notebook and the MLRun dashboard, as well as browse the project artifacts from the dashboard.\n",
    "\n",
    "The following code extracts and displays the model from the training-job outputs."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "store://artifacts/getting-started-tutorial-iguazio/train-iris-train_iris_model:151f5607321244799eb665a781970a2b\n"
     ]
    }
   ],
   "source": [
    "print (train_run.outputs['model'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Your project's artifacts directory contains the results for the executed training job.\n",
    "The **plots** subdirectory has HTML output artifacts for the selected run iteration;\n",
    "(the **data** subdirectory contains the artifacts for the test data set).\n",
    "\n",
    "Use the following code to extract and display information from the run object &mdash; the accuracy that was achieved with the model, and the `confusion` and `roc` HTML output artifacts for the optimal run iteration."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 1.0\n"
     ]
    }
   ],
   "source": [
    "print(f'Accuracy: {train_run.outputs[\"accuracy\"]}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<h3 style=\"text-align:center\">Confusion Matrix - Normalized Plot</h3>\n",
       "<img title=\"confusion-matrix\" src=\"data:image/png;base64,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\">"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Display HTML output artifacts\n",
    "from IPython.display import display, HTML\n",
    "display(HTML(mlrun.get_dataitem(train_run.outputs['confusion-matrix']).get().decode('utf-8')))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<h3 style=\"text-align:center\">Multiclass ROC Curve</h3>\n",
       "<img title=\"roc-multiclass\" src=\"data:image/png;base64,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\">"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "display(HTML(mlrun.get_dataitem(train_run.outputs['roc-multiclass']).get().decode('utf-8')))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id=\"gs-explore-data-w-pandas-df\"></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Exploring the Data with pandas DataFrames\n",
    "\n",
    "Run the following code to use pandas DataFrames to read your data set, extract some basic statistics, and display them."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Read your data set\n",
    "df = mlrun.get_dataitem(train_run.outputs['test_set']).as_df()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "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>sepal length (cm)</th>\n",
       "      <th>sepal width (cm)</th>\n",
       "      <th>petal length (cm)</th>\n",
       "      <th>petal width (cm)</th>\n",
       "      <th>label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6.1</td>\n",
       "      <td>2.8</td>\n",
       "      <td>4.7</td>\n",
       "      <td>1.2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5.7</td>\n",
       "      <td>3.8</td>\n",
       "      <td>1.7</td>\n",
       "      <td>0.3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7.7</td>\n",
       "      <td>3.8</td>\n",
       "      <td>6.7</td>\n",
       "      <td>2.2</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>6.0</td>\n",
       "      <td>2.9</td>\n",
       "      <td>4.5</td>\n",
       "      <td>1.5</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6.8</td>\n",
       "      <td>2.8</td>\n",
       "      <td>4.8</td>\n",
       "      <td>1.4</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)  \\\n",
       "0                6.1               2.8                4.7               1.2   \n",
       "1                5.7               3.8                1.7               0.3   \n",
       "2                7.7               3.8                6.7               2.2   \n",
       "3                6.0               2.9                4.5               1.5   \n",
       "4                6.8               2.8                4.8               1.4   \n",
       "\n",
       "   label  \n",
       "0      1  \n",
       "1      0  \n",
       "2      2  \n",
       "3      1  \n",
       "4      1  "
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Display a portion of the read data\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total number of rows: 30\n"
     ]
    }
   ],
   "source": [
    "# Calculate and display the number of data-set items\n",
    "print(f'Total number of rows: {len(df)}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr:last-of-type th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th colspan=\"8\" halign=\"left\">sepal length (cm)</th>\n",
       "      <th colspan=\"2\" halign=\"left\">sepal width (cm)</th>\n",
       "      <th>...</th>\n",
       "      <th colspan=\"2\" halign=\"left\">petal length (cm)</th>\n",
       "      <th colspan=\"8\" halign=\"left\">petal width (cm)</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>...</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "      <th>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>label</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>10.0</td>\n",
       "      <td>5.070000</td>\n",
       "      <td>0.346570</td>\n",
       "      <td>4.7</td>\n",
       "      <td>4.8</td>\n",
       "      <td>4.95</td>\n",
       "      <td>5.325</td>\n",
       "      <td>5.7</td>\n",
       "      <td>10.0</td>\n",
       "      <td>3.330000</td>\n",
       "      <td>...</td>\n",
       "      <td>1.6</td>\n",
       "      <td>1.7</td>\n",
       "      <td>10.0</td>\n",
       "      <td>0.250000</td>\n",
       "      <td>0.108012</td>\n",
       "      <td>0.1</td>\n",
       "      <td>0.20</td>\n",
       "      <td>0.25</td>\n",
       "      <td>0.3</td>\n",
       "      <td>0.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>9.0</td>\n",
       "      <td>6.011111</td>\n",
       "      <td>0.391933</td>\n",
       "      <td>5.6</td>\n",
       "      <td>5.7</td>\n",
       "      <td>6.00</td>\n",
       "      <td>6.200</td>\n",
       "      <td>6.8</td>\n",
       "      <td>9.0</td>\n",
       "      <td>2.766667</td>\n",
       "      <td>...</td>\n",
       "      <td>4.7</td>\n",
       "      <td>4.8</td>\n",
       "      <td>9.0</td>\n",
       "      <td>1.344444</td>\n",
       "      <td>0.166667</td>\n",
       "      <td>1.1</td>\n",
       "      <td>1.20</td>\n",
       "      <td>1.30</td>\n",
       "      <td>1.5</td>\n",
       "      <td>1.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>11.0</td>\n",
       "      <td>6.690909</td>\n",
       "      <td>0.656437</td>\n",
       "      <td>5.8</td>\n",
       "      <td>6.3</td>\n",
       "      <td>6.50</td>\n",
       "      <td>6.950</td>\n",
       "      <td>7.9</td>\n",
       "      <td>11.0</td>\n",
       "      <td>3.218182</td>\n",
       "      <td>...</td>\n",
       "      <td>5.9</td>\n",
       "      <td>6.7</td>\n",
       "      <td>11.0</td>\n",
       "      <td>2.145455</td>\n",
       "      <td>0.269680</td>\n",
       "      <td>1.8</td>\n",
       "      <td>1.95</td>\n",
       "      <td>2.10</td>\n",
       "      <td>2.4</td>\n",
       "      <td>2.5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3 rows × 32 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      sepal length (cm)                                                  \\\n",
       "                  count      mean       std  min  25%   50%    75%  max   \n",
       "label                                                                     \n",
       "0                  10.0  5.070000  0.346570  4.7  4.8  4.95  5.325  5.7   \n",
       "1                   9.0  6.011111  0.391933  5.6  5.7  6.00  6.200  6.8   \n",
       "2                  11.0  6.690909  0.656437  5.8  6.3  6.50  6.950  7.9   \n",
       "\n",
       "      sepal width (cm)            ... petal length (cm)      petal width (cm)  \\\n",
       "                 count      mean  ...               75%  max            count   \n",
       "label                             ...                                           \n",
       "0                 10.0  3.330000  ...               1.6  1.7             10.0   \n",
       "1                  9.0  2.766667  ...               4.7  4.8              9.0   \n",
       "2                 11.0  3.218182  ...               5.9  6.7             11.0   \n",
       "\n",
       "                                                      \n",
       "           mean       std  min   25%   50%  75%  max  \n",
       "label                                                 \n",
       "0      0.250000  0.108012  0.1  0.20  0.25  0.3  0.4  \n",
       "1      1.344444  0.166667  1.1  1.20  1.30  1.5  1.6  \n",
       "2      2.145455  0.269680  1.8  1.95  2.10  2.4  2.5  \n",
       "\n",
       "[3 rows x 32 columns]"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Display statistics grouped by label\n",
    "df.groupby(['label']).describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id=\"gs-tutorial-2-step-explore-data-w-mlrun-func\"></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 3: Exploring the Data with an MLRun Marketplace Function\n",
    "\n",
    "You can perform further data exploration by leveraging **the MLRun functions marketplace** (a.k.a. \"the MLRun functions hub\").\n",
    "This marketplace is a centralized location for open-source contributions of function components that are commonly used in machine-learning development.\n",
    "The location of the marketplace is configured via the `hub_url` MLRun configuration.\n",
    "By default, it points to the [mlrun/functions](https://github.com/mlrun/functions/) GitHub repository.\n",
    "> **Note:** `hub_url` points to the raw GitHub URL, and can be defined with `{name}` and `{tag}` annotations, as done in the default value &mdash;\n",
    "> `https://raw.githubusercontent.com/mlrun/functions/{tag}/{name}/function.yaml`.\n",
    "\n",
    "This step uses the [`describe` marketplace function](https://github.com/mlrun/functions/tree/master/describe), which performs data exploration on a provided data set.\n",
    "The function is used to extract information from your data set, analyze it, and visualize relevant information in different ways."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Adding an Exploration Function\n",
    "\n",
    "Use the `import_function` MLRun method, which adds or updates a function object in a project, to load the `describe` MLRun marketplace function into a new `describe` project function. \n",
    "The tutorial code sets the first `import_function` parameter &mdash; `url` &mdash; which identities the function to load.\n",
    "\n",
    "> **Note:** MLRun supports multiple types of URL formats.\n",
    "> The example uses the `hub://<function name>` format to point to the `describe` function-code directory in the MLRun functions marketplace (`'hub://describe'`).\n",
    "> You can add `:<tag>` to this syntax to load a specific function tag &mdash; `hub://<function_name>:<tag>`; replace the `<function name>` and `<tag>` placeholders with the desired function name and tag."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "describe = mlrun.import_function('hub://describe').apply(auto_mount())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id=\"gs-tutorial-2-view-func-doc\"></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Viewing the Function Documentation\n",
    "\n",
    "Use the `doc` method to view the embedded documentation of the `describe` function."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "function: describe\n",
      "describe and visualizes dataset stats\n",
      "default handler: summarize\n",
      "entry points:\n",
      "  summarize: Summarize a table\n",
      "    context(MLClientCtx)  - the function context, default=\n",
      "    table(DataItem)  - MLRun input pointing to pandas dataframe (csv/parquet file path), default=\n",
      "    label_column(str)  - ground truth column label, default=None\n",
      "    class_labels(List[str])  - label for each class in tables and plots, default=[]\n",
      "    plot_hist(bool)  - (True) set this to False for large tables, default=True\n",
      "    plots_dest(str)  - destination folder of summary plots (relative to artifact_path), default=plots\n",
      "    update_dataset  - when the table is a registered dataset update the charts in-place, default=False\n"
     ]
    }
   ],
   "source": [
    "describe.doc()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Running the Exploration Function\n",
    "\n",
    "Run the following code to execute the `describe` project function as a Kubernetes job by using the MLRun `run` method.\n",
    "The returned run object is stored in a `describe_run` variable.\n",
    "\n",
    "The location of the data set is the only input that you need to provide.\n",
    "This information is provided as a `table` input artifact that points to the `table_set` output artifact of the `train_run` job that you ran in the previous step."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "> 2021-01-25 08:37:29,984 [info] starting run describe-summarize uid=aa1a8315f0fa4e70be7dc8a8071f7c80 DB=http://mlrun-api:8080\n",
      "> 2021-01-25 08:37:30,129 [info] Job is running in the background, pod: describe-summarize-s2kxq\n",
      "> 2021-01-25 08:37:38,744 [info] run executed, status=completed\n",
      "final state: completed\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<style>\n",
       ".dictlist {\n",
       "  background-color: #4EC64B;\n",
       "  text-align: center;\n",
       "  margin: 4px;\n",
       "  border-radius: 3px; padding: 0px 3px 1px 3px; display: inline-block;}\n",
       ".artifact {\n",
       "  cursor: pointer;\n",
       "  background-color: #4EC64B;\n",
       "  text-align: left;\n",
       "  margin: 4px; border-radius: 3px; padding: 0px 3px 1px 3px; display: inline-block;\n",
       "}\n",
       "div.block.hidden {\n",
       "  display: none;\n",
       "}\n",
       ".clickable {\n",
       "  cursor: pointer;\n",
       "}\n",
       ".ellipsis {\n",
       "  display: inline-block;\n",
       "  max-width: 60px;\n",
       "  white-space: nowrap;\n",
       "  overflow: hidden;\n",
       "  text-overflow: ellipsis;\n",
       "}\n",
       ".master-wrapper {\n",
       "  display: flex;\n",
       "  flex-flow: row nowrap;\n",
       "  justify-content: flex-start;\n",
       "  align-items: stretch;\n",
       "}\n",
       ".master-tbl {\n",
       "  flex: 3\n",
       "}\n",
       ".master-wrapper > div {\n",
       "  margin: 4px;\n",
       "  padding: 10px;\n",
       "}\n",
       "iframe.fileview {\n",
       "  border: 0 none;\n",
       "  height: 100%;\n",
       "  width: 100%;\n",
       "  white-space: pre-wrap;\n",
       "}\n",
       ".pane-header-title {\n",
       "  width: 80%;\n",
       "  font-weight: 500;\n",
       "}\n",
       ".pane-header {\n",
       "  line-height: 1;\n",
       "  background-color: #4EC64B;\n",
       "  padding: 3px;\n",
       "}\n",
       ".pane-header .close {\n",
       "  font-size: 20px;\n",
       "  font-weight: 700;\n",
       "  float: right;\n",
       "  margin-top: -5px;\n",
       "}\n",
       ".master-wrapper .right-pane {\n",
       "  border: 1px inset silver;\n",
       "  width: 40%;\n",
       "  min-height: 300px;\n",
       "  flex: 3\n",
       "  min-width: 500px;\n",
       "}\n",
       ".master-wrapper * {\n",
       "  box-sizing: border-box;\n",
       "}\n",
       "</style><script>\n",
       "function copyToClipboard(fld) {\n",
       "    if (document.queryCommandSupported && document.queryCommandSupported('copy')) {\n",
       "        var textarea = document.createElement('textarea');\n",
       "        textarea.textContent = fld.innerHTML;\n",
       "        textarea.style.position = 'fixed';\n",
       "        document.body.appendChild(textarea);\n",
       "        textarea.select();\n",
       "\n",
       "        try {\n",
       "            return document.execCommand('copy'); // Security exception may be thrown by some browsers.\n",
       "        } catch (ex) {\n",
       "\n",
       "        } finally {\n",
       "            document.body.removeChild(textarea);\n",
       "        }\n",
       "    }\n",
       "}\n",
       "function expandPanel(el) {\n",
       "  const panelName = \"#\" + el.getAttribute('paneName');\n",
       "  console.log(el.title);\n",
       "\n",
       "  document.querySelector(panelName + \"-title\").innerHTML = el.title\n",
       "  iframe = document.querySelector(panelName + \"-body\");\n",
       "\n",
       "  const tblcss = `<style> body { font-family: Arial, Helvetica, sans-serif;}\n",
       "    #csv { margin-bottom: 15px; }\n",
       "    #csv table { border-collapse: collapse;}\n",
       "    #csv table td { padding: 4px 8px; border: 1px solid silver;} </style>`;\n",
       "\n",
       "  function csvToHtmlTable(str) {\n",
       "    return '<div id=\"csv\"><table><tr><td>' +  str.replace(/[\\n\\r]+$/g, '').replace(/[\\n\\r]+/g, '</td></tr><tr><td>')\n",
       "      .replace(/,/g, '</td><td>') + '</td></tr></table></div>';\n",
       "  }\n",
       "\n",
       "  function reqListener () {\n",
       "    if (el.title.endsWith(\".csv\")) {\n",
       "      iframe.setAttribute(\"srcdoc\", tblcss + csvToHtmlTable(this.responseText));\n",
       "    } else {\n",
       "      iframe.setAttribute(\"srcdoc\", this.responseText);\n",
       "    }\n",
       "    console.log(this.responseText);\n",
       "  }\n",
       "\n",
       "  const oReq = new XMLHttpRequest();\n",
       "  oReq.addEventListener(\"load\", reqListener);\n",
       "  oReq.open(\"GET\", el.title);\n",
       "  oReq.send();\n",
       "\n",
       "\n",
       "  //iframe.src = el.title;\n",
       "  const resultPane = document.querySelector(panelName + \"-pane\");\n",
       "  if (resultPane.classList.contains(\"hidden\")) {\n",
       "    resultPane.classList.remove(\"hidden\");\n",
       "  }\n",
       "}\n",
       "function closePanel(el) {\n",
       "  const panelName = \"#\" + el.getAttribute('paneName')\n",
       "  const resultPane = document.querySelector(panelName + \"-pane\");\n",
       "  if (!resultPane.classList.contains(\"hidden\")) {\n",
       "    resultPane.classList.add(\"hidden\");\n",
       "  }\n",
       "}\n",
       "\n",
       "</script>\n",
       "<div class=\"master-wrapper\">\n",
       "  <div class=\"block master-tbl\"><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>project</th>\n",
       "      <th>uid</th>\n",
       "      <th>iter</th>\n",
       "      <th>start</th>\n",
       "      <th>state</th>\n",
       "      <th>name</th>\n",
       "      <th>labels</th>\n",
       "      <th>inputs</th>\n",
       "      <th>parameters</th>\n",
       "      <th>results</th>\n",
       "      <th>artifacts</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>getting-started-tutorial-iguazio</td>\n",
       "      <td><div title=\"aa1a8315f0fa4e70be7dc8a8071f7c80\"><a href=\"https://mlrun-ui.default-tenant.app.aefccdjffbit.iguazio-cd0.com/projects/getting-started-tutorial-iguazio/jobs/monitor/aa1a8315f0fa4e70be7dc8a8071f7c80/info\" target=\"_blank\" >...071f7c80</a></div></td>\n",
       "      <td>0</td>\n",
       "      <td>Jan 25 08:37:34</td>\n",
       "      <td>completed</td>\n",
       "      <td>describe-summarize</td>\n",
       "      <td><div class=\"dictlist\">v3io_user=iguazio</div><div class=\"dictlist\">kind=job</div><div class=\"dictlist\">owner=iguazio</div><div class=\"dictlist\">host=describe-summarize-s2kxq</div></td>\n",
       "      <td><div title=\"store://artifacts/getting-started-tutorial-iguazio/train-iris-train_iris_test_set:151f5607321244799eb665a781970a2b\">table</div></td>\n",
       "      <td><div class=\"dictlist\">label_column=label</div></td>\n",
       "      <td></td>\n",
       "      <td><div title=\"/v3io/projects/getting-started-tutorial-iguazio/artifacts/plots/hist.html\">histograms</div><div title=\"/v3io/projects/getting-started-tutorial-iguazio/artifacts/plots/violin.html\">violin</div><div title=\"/v3io/projects/getting-started-tutorial-iguazio/artifacts/plots/imbalance.html\">imbalance</div><div title=\"/v3io/projects/getting-started-tutorial-iguazio/artifacts/plots/imbalance-weights-vec.csv\">imbalance-weights-vec</div><div title=\"/v3io/projects/getting-started-tutorial-iguazio/artifacts/plots/correlation-matrix.csv\">correlation-matrix</div><div title=\"/v3io/projects/getting-started-tutorial-iguazio/artifacts/plots/corr.html\">correlation</div></td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div></div>\n",
       "  <div id=\"result9eb7fb6a-pane\" class=\"right-pane block hidden\">\n",
       "    <div class=\"pane-header\">\n",
       "      <span id=\"result9eb7fb6a-title\" class=\"pane-header-title\">Title</span>\n",
       "      <span onclick=\"closePanel(this)\" paneName=\"result9eb7fb6a\" class=\"close clickable\">&times;</span>\n",
       "    </div>\n",
       "    <iframe class=\"fileview\" id=\"result9eb7fb6a-body\"></iframe>\n",
       "  </div>\n",
       "</div>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "to track results use .show() or .logs() or in CLI: \n",
      "!mlrun get run aa1a8315f0fa4e70be7dc8a8071f7c80 --project getting-started-tutorial-iguazio , !mlrun logs aa1a8315f0fa4e70be7dc8a8071f7c80 --project getting-started-tutorial-iguazio\n",
      "> 2021-01-25 08:37:39,317 [info] run executed, status=completed\n"
     ]
    }
   ],
   "source": [
    "describe_run = describe.run(params={'label_column': 'label'},\n",
    "                            inputs={\"table\":\n",
    "                                    train_run.outputs['test_set']})"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Reviewing the Run Output\n",
    "\n",
    "The output cell for your code execution contains a run-information table.\n",
    "You can also view run information in the MLRun dashboard; see the output-review information in Step 2, only this time look for the `describe-summarize` job and related artifacts.\n",
    "\n",
    "The `describe` function generates three HTML output artifacts, which provide visual insights for your data set &mdash; `histograms`, `imbalance`, and `correlation`.\n",
    "The artifacts are stored as HTML files in your project's artifacts directory, under **&lt;project artifacts path&gt;/jobs/plots/**.\n",
    "The following code displays the artifact files in the notebook."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<h3 style=\"text-align:center\">histograms</h3>\n",
       "<img title=\"histograms\" src=\"data:image/png;base64,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\">"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Display the `histograms` artifact\n",
    "display(HTML(mlrun.get_dataitem(describe_run.outputs['histograms']).get().decode('utf-8')))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<h3 style=\"text-align:center\">imbalance</h3>\n",
       "<img title=\"imbalance\" src=\"data:image/png;base64,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\">"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Display the `imbalance` artifact\n",
    "display(HTML(mlrun.get_dataitem(describe_run.outputs['imbalance']).get().decode('utf-8')))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<h3 style=\"text-align:center\">Correlation Matrix</h3>\n",
       "<img title=\"correlation\" src=\"data:image/png;base64,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\">"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Display the `correlation` artifact\n",
    "display(HTML(mlrun.get_dataitem(describe_run.outputs['correlation']).get().decode('utf-8')))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id=\"gs-tutorial-2-step-test-model\"></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 4: Testing Your Model\n",
    "\n",
    "Now that you have a trained model, you can test it:\n",
    "run a task that uses the [`test_classifier` marketplace function](https://github.com/mlrun/functions/tree/master/test_classifier) to run the selected trained model against the test data set, as returned for the training task (`train`) in the previous step."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id=\"gs-tutorial-2-add-test-function\"></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Adding a Test Function\n",
    "\n",
    "Run the following code to add to your project a `test` function that uses the `test_classifier` marketplace function code, and create a related `test` function object."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "test = mlrun.import_function('hub://test_classifier').apply(auto_mount())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id=\"gs-tutorial-2-run-model-testing-job\"></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Running a Model-Testing Job\n",
    "\n",
    "Configure parameters for the test function (`params`), and provide the selected trained model from the `train_run` job as an input artifact (`inputs`)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "> 2021-01-25 08:37:39,556 [info] starting run test uid=38900a3da1f247b8bb309529fe1593fe DB=http://mlrun-api:8080\n",
      "> 2021-01-25 08:37:39,728 [info] Job is running in the background, pod: test-wkdgh\n",
      "> 2021-01-25 08:37:44,922 [info] run executed, status=completed\n",
      "final state: completed\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<style>\n",
       ".dictlist {\n",
       "  background-color: #4EC64B;\n",
       "  text-align: center;\n",
       "  margin: 4px;\n",
       "  border-radius: 3px; padding: 0px 3px 1px 3px; display: inline-block;}\n",
       ".artifact {\n",
       "  cursor: pointer;\n",
       "  background-color: #4EC64B;\n",
       "  text-align: left;\n",
       "  margin: 4px; border-radius: 3px; padding: 0px 3px 1px 3px; display: inline-block;\n",
       "}\n",
       "div.block.hidden {\n",
       "  display: none;\n",
       "}\n",
       ".clickable {\n",
       "  cursor: pointer;\n",
       "}\n",
       ".ellipsis {\n",
       "  display: inline-block;\n",
       "  max-width: 60px;\n",
       "  white-space: nowrap;\n",
       "  overflow: hidden;\n",
       "  text-overflow: ellipsis;\n",
       "}\n",
       ".master-wrapper {\n",
       "  display: flex;\n",
       "  flex-flow: row nowrap;\n",
       "  justify-content: flex-start;\n",
       "  align-items: stretch;\n",
       "}\n",
       ".master-tbl {\n",
       "  flex: 3\n",
       "}\n",
       ".master-wrapper > div {\n",
       "  margin: 4px;\n",
       "  padding: 10px;\n",
       "}\n",
       "iframe.fileview {\n",
       "  border: 0 none;\n",
       "  height: 100%;\n",
       "  width: 100%;\n",
       "  white-space: pre-wrap;\n",
       "}\n",
       ".pane-header-title {\n",
       "  width: 80%;\n",
       "  font-weight: 500;\n",
       "}\n",
       ".pane-header {\n",
       "  line-height: 1;\n",
       "  background-color: #4EC64B;\n",
       "  padding: 3px;\n",
       "}\n",
       ".pane-header .close {\n",
       "  font-size: 20px;\n",
       "  font-weight: 700;\n",
       "  float: right;\n",
       "  margin-top: -5px;\n",
       "}\n",
       ".master-wrapper .right-pane {\n",
       "  border: 1px inset silver;\n",
       "  width: 40%;\n",
       "  min-height: 300px;\n",
       "  flex: 3\n",
       "  min-width: 500px;\n",
       "}\n",
       ".master-wrapper * {\n",
       "  box-sizing: border-box;\n",
       "}\n",
       "</style><script>\n",
       "function copyToClipboard(fld) {\n",
       "    if (document.queryCommandSupported && document.queryCommandSupported('copy')) {\n",
       "        var textarea = document.createElement('textarea');\n",
       "        textarea.textContent = fld.innerHTML;\n",
       "        textarea.style.position = 'fixed';\n",
       "        document.body.appendChild(textarea);\n",
       "        textarea.select();\n",
       "\n",
       "        try {\n",
       "            return document.execCommand('copy'); // Security exception may be thrown by some browsers.\n",
       "        } catch (ex) {\n",
       "\n",
       "        } finally {\n",
       "            document.body.removeChild(textarea);\n",
       "        }\n",
       "    }\n",
       "}\n",
       "function expandPanel(el) {\n",
       "  const panelName = \"#\" + el.getAttribute('paneName');\n",
       "  console.log(el.title);\n",
       "\n",
       "  document.querySelector(panelName + \"-title\").innerHTML = el.title\n",
       "  iframe = document.querySelector(panelName + \"-body\");\n",
       "\n",
       "  const tblcss = `<style> body { font-family: Arial, Helvetica, sans-serif;}\n",
       "    #csv { margin-bottom: 15px; }\n",
       "    #csv table { border-collapse: collapse;}\n",
       "    #csv table td { padding: 4px 8px; border: 1px solid silver;} </style>`;\n",
       "\n",
       "  function csvToHtmlTable(str) {\n",
       "    return '<div id=\"csv\"><table><tr><td>' +  str.replace(/[\\n\\r]+$/g, '').replace(/[\\n\\r]+/g, '</td></tr><tr><td>')\n",
       "      .replace(/,/g, '</td><td>') + '</td></tr></table></div>';\n",
       "  }\n",
       "\n",
       "  function reqListener () {\n",
       "    if (el.title.endsWith(\".csv\")) {\n",
       "      iframe.setAttribute(\"srcdoc\", tblcss + csvToHtmlTable(this.responseText));\n",
       "    } else {\n",
       "      iframe.setAttribute(\"srcdoc\", this.responseText);\n",
       "    }\n",
       "    console.log(this.responseText);\n",
       "  }\n",
       "\n",
       "  const oReq = new XMLHttpRequest();\n",
       "  oReq.addEventListener(\"load\", reqListener);\n",
       "  oReq.open(\"GET\", el.title);\n",
       "  oReq.send();\n",
       "\n",
       "\n",
       "  //iframe.src = el.title;\n",
       "  const resultPane = document.querySelector(panelName + \"-pane\");\n",
       "  if (resultPane.classList.contains(\"hidden\")) {\n",
       "    resultPane.classList.remove(\"hidden\");\n",
       "  }\n",
       "}\n",
       "function closePanel(el) {\n",
       "  const panelName = \"#\" + el.getAttribute('paneName')\n",
       "  const resultPane = document.querySelector(panelName + \"-pane\");\n",
       "  if (!resultPane.classList.contains(\"hidden\")) {\n",
       "    resultPane.classList.add(\"hidden\");\n",
       "  }\n",
       "}\n",
       "\n",
       "</script>\n",
       "<div class=\"master-wrapper\">\n",
       "  <div class=\"block master-tbl\"><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>project</th>\n",
       "      <th>uid</th>\n",
       "      <th>iter</th>\n",
       "      <th>start</th>\n",
       "      <th>state</th>\n",
       "      <th>name</th>\n",
       "      <th>labels</th>\n",
       "      <th>inputs</th>\n",
       "      <th>parameters</th>\n",
       "      <th>results</th>\n",
       "      <th>artifacts</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>getting-started-tutorial-iguazio</td>\n",
       "      <td><div title=\"38900a3da1f247b8bb309529fe1593fe\"><a href=\"https://mlrun-ui.default-tenant.app.aefccdjffbit.iguazio-cd0.com/projects/getting-started-tutorial-iguazio/jobs/monitor/38900a3da1f247b8bb309529fe1593fe/info\" target=\"_blank\" >...fe1593fe</a></div></td>\n",
       "      <td>0</td>\n",
       "      <td>Jan 25 08:37:44</td>\n",
       "      <td>completed</td>\n",
       "      <td>test</td>\n",
       "      <td><div class=\"dictlist\">v3io_user=iguazio</div><div class=\"dictlist\">kind=job</div><div class=\"dictlist\">owner=iguazio</div><div class=\"dictlist\">host=test-wkdgh</div></td>\n",
       "      <td><div title=\"store://artifacts/getting-started-tutorial-iguazio/train-iris-train_iris_model:151f5607321244799eb665a781970a2b\">models_path</div><div title=\"store://artifacts/getting-started-tutorial-iguazio/train-iris-train_iris_test_set:151f5607321244799eb665a781970a2b\">test_set</div></td>\n",
       "      <td><div class=\"dictlist\">label_column=label</div><div class=\"dictlist\">plots_dest=plots/test</div></td>\n",
       "      <td><div class=\"dictlist\">accuracy=1.0</div><div class=\"dictlist\">test-error=0.0</div><div class=\"dictlist\">auc-micro=1.0</div><div class=\"dictlist\">auc-weighted=1.0</div><div class=\"dictlist\">f1-score=1.0</div><div class=\"dictlist\">precision_score=1.0</div><div class=\"dictlist\">recall_score=1.0</div></td>\n",
       "      <td><div title=\"/v3io/projects/getting-started-tutorial-iguazio/artifacts/plots/confusion-matrix.html\">confusion-matrix</div><div title=\"/v3io/projects/getting-started-tutorial-iguazio/artifacts/plots/precision-recall-multiclass.html\">precision-recall-multiclass</div><div title=\"/v3io/projects/getting-started-tutorial-iguazio/artifacts/plots/roc-multiclass.html\">roc-multiclass</div><div title=\"/v3io/projects/getting-started-tutorial-iguazio/artifacts/test_set_preds.parquet\">test_set_preds</div></td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div></div>\n",
       "  <div id=\"result5199a9c7-pane\" class=\"right-pane block hidden\">\n",
       "    <div class=\"pane-header\">\n",
       "      <span id=\"result5199a9c7-title\" class=\"pane-header-title\">Title</span>\n",
       "      <span onclick=\"closePanel(this)\" paneName=\"result5199a9c7\" class=\"close clickable\">&times;</span>\n",
       "    </div>\n",
       "    <iframe class=\"fileview\" id=\"result5199a9c7-body\"></iframe>\n",
       "  </div>\n",
       "</div>\n"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "to track results use .show() or .logs() or in CLI: \n",
      "!mlrun get run 38900a3da1f247b8bb309529fe1593fe --project getting-started-tutorial-iguazio , !mlrun logs 38900a3da1f247b8bb309529fe1593fe --project getting-started-tutorial-iguazio\n",
      "> 2021-01-25 08:37:45,856 [info] run executed, status=completed\n"
     ]
    }
   ],
   "source": [
    "test_run = test.run(name=\"test\",\n",
    "                    params={\"label_column\": \"label\",\n",
    "                            \"plots_dest\": path.join(\"plots\", \"test\")},\n",
    "                    inputs={\"models_path\": train_run.outputs['model'],\n",
    "                            \"test_set\": train_run.outputs['test_set']})"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id=\"gs-test-model-run-output-review\"></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Reviewing the Run Output\n",
    "\n",
    "Check the output information for your run in Jupyter Notebook and on the MLRun dashboard.\n",
    "\n",
    "Use the following code to display information from the run object &mdash; the accuracy of the model, and the `confusion` and `roc` HTML output artifacts."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Test Accuracy: 1.0\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<h3 style=\"text-align:center\">Confusion Matrix - Normalized Plot</h3>\n",
       "<img title=\"confusion-matrix\" src=\"data:image/png;base64,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\">"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<h3 style=\"text-align:center\">Multiclass ROC Curve</h3>\n",
       "<img title=\"roc-multiclass\" src=\"data:image/png;base64,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\">"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Display the model accuracy\n",
    "print(f'Test Accuracy: {test_run.outputs[\"accuracy\"]}')\n",
    "\n",
    "# Display HTML output artifacts\n",
    "display(HTML(mlrun.get_dataitem(test_run.outputs['confusion-matrix']).get().decode('utf-8')))\n",
    "display(HTML(mlrun.get_dataitem(test_run.outputs['roc-multiclass']).get().decode('utf-8')))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id=\"gs-tutorial-2-done\"></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Done!\n",
    "\n",
    "Congratulation! You've completed Part 2 of the MLRun getting-started tutorial.\n",
    "Proceed to [Part 3](03-model-serving.ipynb) to learn how to deploy and server your model using a serverless function."
   ]
  }
 ],
 "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": "3.7.6"
  },
  "toc-showcode": false,
  "toc-showmarkdowntxt": false
 },
 "nbformat": 4,
 "nbformat_minor": 4
}