public-engines/iris-h2o-automl/notebooks/.ipynb_checkpoints/sample-checkpoint.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Iris H2O Example"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Acquisitor and Cleaner"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "marvin_cell": "acquisitor"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from marvin_python_toolbox.common.data import MarvinData\n",
    "\n",
    "file_path = MarvinData.download_file(url=\"https://s3.amazonaws.com/marvin-engines-data/Iris.csv\")\n",
    "\n",
    "iris = pd.read_csv(file_path)\n",
    "\n",
    "marvin_initial_dataset = iris"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Training Preparator"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "marvin_cell": "tpreparator"
   },
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn import model_selection\n",
    "\n",
    "X_train, X_test= train_test_split(marvin_initial_dataset, random_state=1,test_size=0.3)\n",
    "\n",
    "marvin_dataset = {'train_X': X_train,  'test_X': X_test}\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Trainer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "marvin_cell": "trainer",
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Checking whether there is an H2O instance running at http://localhost:54321 . connected.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div style=\"overflow:auto\"><table style=\"width:50%\"><tr><td>H2O cluster uptime:</td>\n",
       "<td>1 day 0 hours 48 mins</td></tr>\n",
       "<tr><td>H2O cluster timezone:</td>\n",
       "<td>America/Sao_Paulo</td></tr>\n",
       "<tr><td>H2O data parsing timezone:</td>\n",
       "<td>UTC</td></tr>\n",
       "<tr><td>H2O cluster version:</td>\n",
       "<td>3.26.0.3</td></tr>\n",
       "<tr><td>H2O cluster version age:</td>\n",
       "<td>20 days </td></tr>\n",
       "<tr><td>H2O cluster name:</td>\n",
       "<td>H2O_from_python_fernandozagatti_7kn410</td></tr>\n",
       "<tr><td>H2O cluster total nodes:</td>\n",
       "<td>1</td></tr>\n",
       "<tr><td>H2O cluster free memory:</td>\n",
       "<td>3.791 Gb</td></tr>\n",
       "<tr><td>H2O cluster total cores:</td>\n",
       "<td>4</td></tr>\n",
       "<tr><td>H2O cluster allowed cores:</td>\n",
       "<td>4</td></tr>\n",
       "<tr><td>H2O cluster status:</td>\n",
       "<td>locked, healthy</td></tr>\n",
       "<tr><td>H2O connection url:</td>\n",
       "<td>http://localhost:54321</td></tr>\n",
       "<tr><td>H2O connection proxy:</td>\n",
       "<td>None</td></tr>\n",
       "<tr><td>H2O internal security:</td>\n",
       "<td>False</td></tr>\n",
       "<tr><td>H2O API Extensions:</td>\n",
       "<td>Amazon S3, XGBoost, Algos, AutoML, Core V3, Core V4</td></tr>\n",
       "<tr><td>Python version:</td>\n",
       "<td>3.7.3 final</td></tr></table></div>"
      ],
      "text/plain": [
       "--------------------------  ---------------------------------------------------\n",
       "H2O cluster uptime:         1 day 0 hours 48 mins\n",
       "H2O cluster timezone:       America/Sao_Paulo\n",
       "H2O data parsing timezone:  UTC\n",
       "H2O cluster version:        3.26.0.3\n",
       "H2O cluster version age:    20 days\n",
       "H2O cluster name:           H2O_from_python_fernandozagatti_7kn410\n",
       "H2O cluster total nodes:    1\n",
       "H2O cluster free memory:    3.791 Gb\n",
       "H2O cluster total cores:    4\n",
       "H2O cluster allowed cores:  4\n",
       "H2O cluster status:         locked, healthy\n",
       "H2O connection url:         http://localhost:54321\n",
       "H2O connection proxy:\n",
       "H2O internal security:      False\n",
       "H2O API Extensions:         Amazon S3, XGBoost, Algos, AutoML, Core V3, Core V4\n",
       "Python version:             3.7.3 final\n",
       "--------------------------  ---------------------------------------------------"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Parse progress: |█████████████████████████████████████████████████████████| 100%\n",
      "Parse progress: |█████████████████████████████████████████████████████████| 100%\n",
      "AutoML progress: |████████████████████████████████████████████████████████| 100%\n"
     ]
    }
   ],
   "source": [
    "import h2o\n",
    "from h2o.automl import H2OAutoML\n",
    "\n",
    "h2o.init()\n",
    "\n",
    "train_X_frame = h2o.H2OFrame.from_python(marvin_dataset['train_X'])\n",
    "test_X_frame = h2o.H2OFrame.from_python(marvin_dataset['test_X'])\n",
    "\n",
    "x = train_X_frame.columns\n",
    "y = 'Species'\n",
    "x.remove(y)\n",
    "\n",
    "automl = H2OAutoML(max_models=20, seed=1)\n",
    "automl.train(x=x, \n",
    "             y=y, \n",
    "             training_frame=train_X_frame)\n",
    "\n",
    "marvin_model = automl"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Metrics Evaluator"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "marvin_cell": "evaluator",
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/fernandozagatti/.virtualenvs/iris-h2o-automl-env/lib/python3.7/site-packages/pandas/core/frame.py:4102: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  errors=errors,\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Parse progress: |█████████████████████████████████████████████████████████| 100%\n",
      "gbm prediction progress: |████████████████████████████████████████████████| 100%\n"
     ]
    }
   ],
   "source": [
    "import h2o\n",
    "from sklearn import metrics\n",
    "\n",
    "#h2o.init()\n",
    "\n",
    "y_test = marvin_dataset['test_X']['Species']\n",
    "marvin_dataset['test_X'].drop(columns='Species',inplace= True)\n",
    "\n",
    "teste = h2o.H2OFrame.from_python(marvin_dataset['test_X'])\n",
    "preds = marvin_model.predict(teste).as_data_frame()['predict'].values\n",
    "marvin_metrics = metrics.accuracy_score(y_test, preds)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Prediction Preparator"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "marvin_cell": "ppreparator",
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Parse progress: |█████████████████████████████████████████████████████████| 100%\n"
     ]
    }
   ],
   "source": [
    "import h2o\n",
    "import pandas as pd\n",
    "\n",
    "input_message = {'SepalLengthCm': [input_message[0]], 'SepalWidthCm': [input_message[1]],\n",
    "                 'PetalLengthCm': [input_message[2]], 'PetalWidthCm': [input_message[3]]}\n",
    "input_message = pd.DataFrame(data=input_message)\n",
    "input_message = h2o.H2OFrame.from_python(input_message)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Predictor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "marvin_cell": "predictor"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "gbm prediction progress: |████████████████████████████████████████████████| 100%\n"
     ]
    }
   ],
   "source": [
    "final_prediction = marvin_model.predict(input_message).as_data_frame().values[0][0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Iris-versicolor\n"
     ]
    }
   ],
   "source": [
    "print(final_prediction)"
   ]
  }
 ],
 "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}