{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "# PyCaret in CoCalc\n",
    "\n",
    "https://pycaret.org/\n",
    "\n",
    "Kernel: Python 3 (system-wide) in Ubuntu 20.04\n",
    "\n",
    "Example: https://github.com/pycaret/pycaret/blob/master/examples/PyCaret%202%20Anomaly%20Detection.ipynb"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'2.1.2'"
      ]
     },
     "execution_count": 1,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from pycaret.utils import version\n",
    "version()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "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>Col1</th>\n",
       "      <th>Col2</th>\n",
       "      <th>Col3</th>\n",
       "      <th>Col4</th>\n",
       "      <th>Col5</th>\n",
       "      <th>Col6</th>\n",
       "      <th>Col7</th>\n",
       "      <th>Col8</th>\n",
       "      <th>Col9</th>\n",
       "      <th>Col10</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.263995</td>\n",
       "      <td>0.764929</td>\n",
       "      <td>0.138424</td>\n",
       "      <td>0.935242</td>\n",
       "      <td>0.605867</td>\n",
       "      <td>0.518790</td>\n",
       "      <td>0.912225</td>\n",
       "      <td>0.608234</td>\n",
       "      <td>0.723782</td>\n",
       "      <td>0.733591</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.546092</td>\n",
       "      <td>0.653975</td>\n",
       "      <td>0.065575</td>\n",
       "      <td>0.227772</td>\n",
       "      <td>0.845269</td>\n",
       "      <td>0.837066</td>\n",
       "      <td>0.272379</td>\n",
       "      <td>0.331679</td>\n",
       "      <td>0.429297</td>\n",
       "      <td>0.367422</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.336714</td>\n",
       "      <td>0.538842</td>\n",
       "      <td>0.192801</td>\n",
       "      <td>0.553563</td>\n",
       "      <td>0.074515</td>\n",
       "      <td>0.332993</td>\n",
       "      <td>0.365792</td>\n",
       "      <td>0.861309</td>\n",
       "      <td>0.899017</td>\n",
       "      <td>0.088600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.092108</td>\n",
       "      <td>0.995017</td>\n",
       "      <td>0.014465</td>\n",
       "      <td>0.176371</td>\n",
       "      <td>0.241530</td>\n",
       "      <td>0.514724</td>\n",
       "      <td>0.562208</td>\n",
       "      <td>0.158963</td>\n",
       "      <td>0.073715</td>\n",
       "      <td>0.208463</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.325261</td>\n",
       "      <td>0.805968</td>\n",
       "      <td>0.957033</td>\n",
       "      <td>0.331665</td>\n",
       "      <td>0.307923</td>\n",
       "      <td>0.355315</td>\n",
       "      <td>0.501899</td>\n",
       "      <td>0.558449</td>\n",
       "      <td>0.885169</td>\n",
       "      <td>0.182754</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Col1      Col2      Col3      Col4      Col5      Col6      Col7  \\\n",
       "0  0.263995  0.764929  0.138424  0.935242  0.605867  0.518790  0.912225   \n",
       "1  0.546092  0.653975  0.065575  0.227772  0.845269  0.837066  0.272379   \n",
       "2  0.336714  0.538842  0.192801  0.553563  0.074515  0.332993  0.365792   \n",
       "3  0.092108  0.995017  0.014465  0.176371  0.241530  0.514724  0.562208   \n",
       "4  0.325261  0.805968  0.957033  0.331665  0.307923  0.355315  0.501899   \n",
       "\n",
       "       Col8      Col9     Col10  \n",
       "0  0.608234  0.723782  0.733591  \n",
       "1  0.331679  0.429297  0.367422  \n",
       "2  0.861309  0.899017  0.088600  \n",
       "3  0.158963  0.073715  0.208463  \n",
       "4  0.558449  0.885169  0.182754  "
      ]
     },
     "execution_count": 2,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from pycaret.datasets import get_data\n",
    "data = get_data('anomaly')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "cocalc": {
     "outputs": {
      "5": {
       "name": "input",
       "opts": {
        "password": false,
        "prompt": ""
       },
       "output_type": "stream"
      }
     }
    },
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "af7d6d64a96b455ba125468d6c61d894",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "IntProgress(value=0, description='Processing: ', max=4)"
      ]
     },
     "execution_count": 3,
     "metadata": {
     },
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Initiated</th>\n",
       "      <td>. . . . . . . . . . . . . . . . . .</td>\n",
       "      <td>10:22:36</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Status</th>\n",
       "      <td>. . . . . . . . . . . . . . . . . .</td>\n",
       "      <td>Loading Dependencies</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                                    \n",
       "                                                                    \n",
       "Initiated  . . . . . . . . . . . . . . . . . .              10:22:36\n",
       "Status     . . . . . . . . . . . . . . . . . .  Loading Dependencies"
      ]
     },
     "execution_count": 3,
     "metadata": {
     },
     "output_type": "execute_result",
     "transient": {
      "display_id": "monitor"
     }
    },
    {
     "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></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Initiated</th>\n",
       "      <td>. . . . . . . . . . . . . . . . . .</td>\n",
       "      <td>10:22:36</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Status</th>\n",
       "      <td>. . . . . . . . . . . . . . . . . .</td>\n",
       "      <td>Preparing Data for Modeling</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                                           \n",
       "                                                                           \n",
       "Initiated  . . . . . . . . . . . . . . . . . .                     10:22:36\n",
       "Status     . . . . . . . . . . . . . . . . . .  Preparing Data for Modeling"
      ]
     },
     "execution_count": 3,
     "metadata": {
     },
     "output_type": "execute_result",
     "transient": {
      "display_id": "monitor"
     }
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "067b8230d9754542b66a1853f3870452",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Text(value=\"Following data types have been inferred automatically, if they are correct press enter to continue…"
      ]
     },
     "execution_count": 3,
     "metadata": {
     },
     "output_type": "execute_result"
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Data Type</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Col1</th>\n",
       "      <td>Numeric</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Col2</th>\n",
       "      <td>Numeric</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Col3</th>\n",
       "      <td>Numeric</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Col4</th>\n",
       "      <td>Numeric</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Col5</th>\n",
       "      <td>Numeric</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Col6</th>\n",
       "      <td>Numeric</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Col7</th>\n",
       "      <td>Numeric</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Col8</th>\n",
       "      <td>Numeric</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Col9</th>\n",
       "      <td>Numeric</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Col10</th>\n",
       "      <td>Numeric</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Data Type\n",
       "Col1    Numeric\n",
       "Col2    Numeric\n",
       "Col3    Numeric\n",
       "Col4    Numeric\n",
       "Col5    Numeric\n",
       "Col6    Numeric\n",
       "Col7    Numeric\n",
       "Col8    Numeric\n",
       "Col9    Numeric\n",
       "Col10   Numeric"
      ]
     },
     "execution_count": 3,
     "metadata": {
     },
     "output_type": "execute_result"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": " "
    }
   ],
   "source": [
    "from pycaret.anomaly import *\n",
    "ano1 = setup(data, session_id=123, log_experiment=True, experiment_name='anomaly1')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "models()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "iforest = create_model('iforest')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "knn = create_model('knn', fraction = 0.1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
    "iforest_results = assign_model(iforest)\n",
    "iforest_results.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "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>Col1</th>\n",
       "      <th>Col2</th>\n",
       "      <th>Col3</th>\n",
       "      <th>Col4</th>\n",
       "      <th>Col5</th>\n",
       "      <th>Col6</th>\n",
       "      <th>Col7</th>\n",
       "      <th>Col8</th>\n",
       "      <th>Col9</th>\n",
       "      <th>Col10</th>\n",
       "      <th>Label</th>\n",
       "      <th>Score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.263995</td>\n",
       "      <td>0.764929</td>\n",
       "      <td>0.138424</td>\n",
       "      <td>0.935242</td>\n",
       "      <td>0.605867</td>\n",
       "      <td>0.518790</td>\n",
       "      <td>0.912225</td>\n",
       "      <td>0.608234</td>\n",
       "      <td>0.723782</td>\n",
       "      <td>0.733591</td>\n",
       "      <td>0</td>\n",
       "      <td>-0.035865</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.546092</td>\n",
       "      <td>0.653975</td>\n",
       "      <td>0.065575</td>\n",
       "      <td>0.227772</td>\n",
       "      <td>0.845269</td>\n",
       "      <td>0.837066</td>\n",
       "      <td>0.272379</td>\n",
       "      <td>0.331679</td>\n",
       "      <td>0.429297</td>\n",
       "      <td>0.367422</td>\n",
       "      <td>0</td>\n",
       "      <td>-0.084927</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.336714</td>\n",
       "      <td>0.538842</td>\n",
       "      <td>0.192801</td>\n",
       "      <td>0.553563</td>\n",
       "      <td>0.074515</td>\n",
       "      <td>0.332993</td>\n",
       "      <td>0.365792</td>\n",
       "      <td>0.861309</td>\n",
       "      <td>0.899017</td>\n",
       "      <td>0.088600</td>\n",
       "      <td>1</td>\n",
       "      <td>0.025356</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.092108</td>\n",
       "      <td>0.995017</td>\n",
       "      <td>0.014465</td>\n",
       "      <td>0.176371</td>\n",
       "      <td>0.241530</td>\n",
       "      <td>0.514724</td>\n",
       "      <td>0.562208</td>\n",
       "      <td>0.158963</td>\n",
       "      <td>0.073715</td>\n",
       "      <td>0.208463</td>\n",
       "      <td>1</td>\n",
       "      <td>0.042415</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.325261</td>\n",
       "      <td>0.805968</td>\n",
       "      <td>0.957033</td>\n",
       "      <td>0.331665</td>\n",
       "      <td>0.307923</td>\n",
       "      <td>0.355315</td>\n",
       "      <td>0.501899</td>\n",
       "      <td>0.558449</td>\n",
       "      <td>0.885169</td>\n",
       "      <td>0.182754</td>\n",
       "      <td>0</td>\n",
       "      <td>-0.023408</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       Col1      Col2      Col3      Col4      Col5      Col6      Col7  \\\n",
       "0  0.263995  0.764929  0.138424  0.935242  0.605867  0.518790  0.912225   \n",
       "1  0.546092  0.653975  0.065575  0.227772  0.845269  0.837066  0.272379   \n",
       "2  0.336714  0.538842  0.192801  0.553563  0.074515  0.332993  0.365792   \n",
       "3  0.092108  0.995017  0.014465  0.176371  0.241530  0.514724  0.562208   \n",
       "4  0.325261  0.805968  0.957033  0.331665  0.307923  0.355315  0.501899   \n",
       "\n",
       "       Col8      Col9     Col10  Label     Score  \n",
       "0  0.608234  0.723782  0.733591      0 -0.035865  \n",
       "1  0.331679  0.429297  0.367422      0 -0.084927  \n",
       "2  0.861309  0.899017  0.088600      1  0.025356  \n",
       "3  0.158963  0.073715  0.208463      1  0.042415  \n",
       "4  0.558449  0.885169  0.182754      0 -0.023408  "
      ]
     },
     "execution_count": 11,
     "metadata": {
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pred_new = predict_model(iforest, data=data)\n",
    "pred_new.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
   ],
   "source": [
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (system-wide)",
   "language": "python",
   "metadata": {
    "cocalc": {
     "description": "Python 3 programming language",
     "priority": 100,
     "url": "https://www.python.org/"
    }
   },
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}