{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "a17d07c8",
   "metadata": {},
   "source": [
    "### This notebook shows how to compare models, how to move these from one stage to another and to make predictions"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6aa96e7f",
   "metadata": {},
   "source": [
    "<b>Notebook setup</b>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "7fb2f7d7",
   "metadata": {},
   "outputs": [],
   "source": [
    "# import libraries and setup connection\n",
    "import mlflow\n",
    "from mlflow import MlflowClient\n",
    "client = MlflowClient()\n",
    "\n",
    "from sklearn import datasets\n",
    "from sklearn.model_selection import train_test_split\n",
    "from pprint import pprint\n",
    "import pandas as pd\n",
    "\n",
    "tracking_uri = 'https://dev-orch-mlflow-service.dev.theorchard.io'\n",
    "mlflow.set_tracking_uri(tracking_uri)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "2329f602",
   "metadata": {},
   "outputs": [],
   "source": [
    "iris = datasets.load_iris()\n",
    "x = iris.data[:, 2:]\n",
    "y = iris.target\n",
    "X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=7)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "1f4cc17a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "list existing experiments:\n",
      "Name: test-experiment-776. Id: 29\n",
      "Name: Default. Id: 0\n",
      "Name: post_release_consumption/spotify_audio_subscriptions. Id: 4\n",
      "Name: AD_SIMILARITY_BENCHMARK. Id: 6\n",
      "Name: data-platform/debut-forecasting/US/348. Id: 16\n",
      "Name: data-platform/debut-forecasting/US/286. Id: 17\n",
      "Name: data-platform/debut-forecasting/US/1. Id: 18\n",
      "Name: data-platform/debut-forecasting/US/187. Id: 19\n",
      "Name: track-similarity-experiment. Id: 22\n",
      "Name: S3 bucket test2. Id: 24\n"
     ]
    }
   ],
   "source": [
    "# Find the experiment created in the \"model_logging\" notebook\n",
    "\n",
    "print('list existing experiments:')\n",
    "experiments = mlflow.search_experiments()\n",
    "for e in experiments:\n",
    "    print(f'Name: {e.name}. Id: {e.experiment_id}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "50ae5fd3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Experiment: artifact_location='s3://dev-cucumbers/mlflow_artifacts/29', creation_time=1692608042577, experiment_id='29', last_update_time=1692608042577, lifecycle_stage='active', name='test-experiment-776', tags={}>"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Set experiment\n",
    "experiment = 'test-experiment-776'\n",
    "mlflow.set_experiment(experiment)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5934eb60",
   "metadata": {},
   "source": [
    "<b>List runs under this experiment</b><br>\n",
    "We can see that manually logged model has some value missing and metrics are called differently. <br>\n",
    "That may be one reason why to consider autologging always."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "08b303dd",
   "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>run_id</th>\n",
       "      <th>metrics.training_r2_score</th>\n",
       "      <th>tags.estimator_name</th>\n",
       "      <th>metrics.r2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>02846082c8734079a01e2cc72eab5b1e</td>\n",
       "      <td>NaN</td>\n",
       "      <td>None</td>\n",
       "      <td>0.770992</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>6fcf30790c04412f8d178b38003a8bcd</td>\n",
       "      <td>NaN</td>\n",
       "      <td>DecisionTreeClassifier</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>50bcc4b8c86340469749be68d6672362</td>\n",
       "      <td>NaN</td>\n",
       "      <td>DecisionTreeClassifier</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>46587177d3ba4c8bba9d614df60600f7</td>\n",
       "      <td>0.996450</td>\n",
       "      <td>RandomForestRegressor</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>2695c2d819bc413a8ac3582a474cc95f</td>\n",
       "      <td>0.996646</td>\n",
       "      <td>RandomForestRegressor</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>97fbd3d67e1344d49a7bdfb9f883ccaa</td>\n",
       "      <td>0.996494</td>\n",
       "      <td>RandomForestRegressor</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                             run_id  metrics.training_r2_score   \n",
       "0  02846082c8734079a01e2cc72eab5b1e                        NaN  \\\n",
       "1  6fcf30790c04412f8d178b38003a8bcd                        NaN   \n",
       "2  50bcc4b8c86340469749be68d6672362                        NaN   \n",
       "4  46587177d3ba4c8bba9d614df60600f7                   0.996450   \n",
       "5  2695c2d819bc413a8ac3582a474cc95f                   0.996646   \n",
       "6  97fbd3d67e1344d49a7bdfb9f883ccaa                   0.996494   \n",
       "\n",
       "      tags.estimator_name  metrics.r2  \n",
       "0                    None    0.770992  \n",
       "1  DecisionTreeClassifier         NaN  \n",
       "2  DecisionTreeClassifier         NaN  \n",
       "4   RandomForestRegressor         NaN  \n",
       "5   RandomForestRegressor         NaN  \n",
       "6   RandomForestRegressor         NaN  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "current_experiment=dict(mlflow.get_experiment_by_name(experiment))\n",
    "experiment_id=current_experiment['experiment_id']\n",
    "df = mlflow.search_runs(experiment_ids=[experiment_id])\n",
    "cols = ['run_id', 'metrics.training_r2_score', 'tags.estimator_name', 'metrics.r2']\n",
    "df[df['tags.mlflow.log-model.history'].notna()][cols]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "071341c4",
   "metadata": {},
   "source": [
    "Let's predict using some run_ids:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "3b47d6be",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[2. 1. 0.]\n"
     ]
    }
   ],
   "source": [
    "model = mlflow.sklearn.load_model(\"runs:/97fbd3d67e1344d49a7bdfb9f883ccaa/model\")\n",
    "predictions = model.predict(X_test[:3])\n",
    "print(predictions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "0013299d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[2 1 0 1]\n"
     ]
    }
   ],
   "source": [
    "model = mlflow.sklearn.load_model(\"runs:/50bcc4b8c86340469749be68d6672362/model\")\n",
    "predictions = model.predict(X_test[:4])\n",
    "print(predictions)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1e89056b",
   "metadata": {},
   "source": [
    "<b>Let's register one of the models in the Model Registry:</b>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "bd2d6f19",
   "metadata": {},
   "outputs": [],
   "source": [
    "best_model_run = '2695c2d819bc413a8ac3582a474cc95f'\n",
    "best_model_name = 'sk-learn-random-forest-reg'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "f0c93ded",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Successfully registered model 'sk-learn-random-forest-reg'.\n",
      "2023/08/21 09:26:45 INFO mlflow.tracking._model_registry.client: Waiting up to 300 seconds for model version to finish creation. Model name: sk-learn-random-forest-reg, version 1\n",
      "Created version '1' of model 'sk-learn-random-forest-reg'.\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<ModelVersion: aliases=[], creation_timestamp=1692610005333, current_stage='None', description='', last_updated_timestamp=1692610005333, name='sk-learn-random-forest-reg', run_id='2695c2d819bc413a8ac3582a474cc95f', run_link='', source='s3://dev-cucumbers/mlflow_artifacts/29/2695c2d819bc413a8ac3582a474cc95f/artifacts/model', status='READY', status_message='', tags={}, user_id='', version='1'>"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mlflow.register_model(\n",
    "    f'runs:/{best_model_run}/model', f'{best_model_name}')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f3af49b5",
   "metadata": {},
   "source": [
    "<b>Transition this model to production</b>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "59dff509",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<ModelVersion: aliases=[], creation_timestamp=1692610005333, current_stage='Production', description='', last_updated_timestamp=1692610009069, name='sk-learn-random-forest-reg', run_id='2695c2d819bc413a8ac3582a474cc95f', run_link='', source='s3://dev-cucumbers/mlflow_artifacts/29/2695c2d819bc413a8ac3582a474cc95f/artifacts/model', status='READY', status_message='', tags={}, user_id='', version='1'>"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "client.transition_model_version_stage(\n",
    "    name=f'{best_model_name}', version=1, stage=\"Production\"\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4784d3b1",
   "metadata": {},
   "source": [
    "<b>Predict using Staged model:</b>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "9adeb812",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([2., 1., 0., 1.])"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_version_uri = f'models:/{best_model_name}/Production'\n",
    "current_model = mlflow.pyfunc.load_model(model_version_uri)\n",
    "current_model.predict(X_test[:4])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a1eb75d2",
   "metadata": {},
   "source": [
    "<b>Apply alias to model:</b>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f259bcbc",
   "metadata": {},
   "outputs": [],
   "source": [
    "client.set_registered_model_alias(f'{best_model_name}', \"Champion\", '1')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "b554f098",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([2., 1., 0., 1.])"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_version_uri = f'models:/{best_model_name}@Champion'\n",
    "champion_version = mlflow.pyfunc.load_model(model_version_uri)\n",
    "champion_version.predict(X_test[:4])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "af50f973",
   "metadata": {},
   "source": [
    "<b>Manually creating input for prediction:</b>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "6d884f57",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([2., 1., 0., 1.])"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data ={\n",
    "  \"inputs\": [\n",
    "    [\n",
    "      5.1, 1.8\n",
    "    ],\n",
    "    [\n",
    "      4.5, 1.5\n",
    "    ],\n",
    "    [\n",
    "      1.3, 0.3\n",
    "    ],\n",
    "    [\n",
    "      4.5, 1.5\n",
    "    ]\n",
    "  ]\n",
    "}\n",
    "champion_version.predict(pd.DataFrame(data))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "abfd2d9f",
   "metadata": {},
   "source": [
    "List all models available in the MLflow:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "eed9b1bb",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{   'aliases': {},\n",
      "    'creation_timestamp': 1691565300553,\n",
      "    'description': '',\n",
      "    'last_updated_timestamp': 1691565300851,\n",
      "    'latest_versions': [   <ModelVersion: aliases=[], creation_timestamp=1691565300851, current_stage='None', description='', last_updated_timestamp=1691565300851, name='ElasticnetWineModel', run_id='0cdebea1d7644865a6a6471a7fbedabd', run_link='', source='s3://dev-cucumbers/mlflow_artifacts/24/0cdebea1d7644865a6a6471a7fbedabd/artifacts/model', status='READY', status_message='', tags={}, user_id='', version='1'>],\n",
      "    'name': 'ElasticnetWineModel',\n",
      "    'tags': {}}\n",
      "{   'aliases': {'Champion': '1'},\n",
      "    'creation_timestamp': 1692610005196,\n",
      "    'description': '',\n",
      "    'last_updated_timestamp': 1692610009069,\n",
      "    'latest_versions': [   <ModelVersion: aliases=[], creation_timestamp=1692610005333, current_stage='Production', description='', last_updated_timestamp=1692610009069, name='sk-learn-random-forest-reg', run_id='2695c2d819bc413a8ac3582a474cc95f', run_link='', source='s3://dev-cucumbers/mlflow_artifacts/29/2695c2d819bc413a8ac3582a474cc95f/artifacts/model', status='READY', status_message='', tags={}, user_id='', version='1'>],\n",
      "    'name': 'sk-learn-random-forest-reg',\n",
      "    'tags': {}}\n"
     ]
    }
   ],
   "source": [
    "# list existing models\n",
    "client = MlflowClient()\n",
    "for rm in client.search_registered_models():\n",
    "    pprint(dict(rm), indent=4)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8ebbac65",
   "metadata": {},
   "source": [
    "<b>To conclude then from UI we can see champion model:</b>"
   ]
  },
  {
   "attachments": {
    "versioned_model.png": {
     "image/png": "iVBORw0KGgoAAAANSUhEUgAACE4AAAEqCAYAAAABe4egAAAMPWlDQ1BJQ0MgUHJvZmlsZQAASImV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\nAAAAAElFTkSuQmCC\n"
    }
   },
   "cell_type": "markdown",
   "id": "c07afef1",
   "metadata": {},
   "source": [
    "![versioned_model.png](attachment:versioned_model.png)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6655ac4a",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "conda_python3",
   "language": "python",
   "name": "conda_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": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}