{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Classification with Hundred Hammers"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In this notebook we will explain how to use the HundredHammers library to perform a basic model selection and hyperparameter optimization for a classification problem. \n",
    "\n",
    "To do this, we will use one of the example datasets available in the scikit-learn library."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-09-22T19:36:12.600420200Z",
     "start_time": "2023-09-22T19:36:12.542559200Z"
    }
   },
   "outputs": [],
   "source": [
    "import logging\n",
    "\n",
    "import hundred_hammers as hh\n",
    "from hundred_hammers.model_zoo import (\n",
    "    DummyClassifier,\n",
    "    KNeighborsClassifier,\n",
    "    RidgeClassifier,\n",
    "    DecisionTreeClassifier,\n",
    ")\n",
    "\n",
    "from sklearn.datasets import load_iris"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "First we store the data in the X (input) and y (target) variables."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-09-22T19:36:12.602422Z",
     "start_time": "2023-09-22T19:36:12.544299900Z"
    }
   },
   "outputs": [],
   "source": [
    "data = load_iris()\n",
    "X = data.data\n",
    "y = data.target"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We are going to first train some models with their default configuration. If you don't specify the models that you want to use, some classifiers will be chosen for you.\n",
    "\n",
    "To see which models are chosen by default, you can check the ```DEFAULT_CLASSIFICATION_MODELS``` variable"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-09-22T19:36:12.603422100Z",
     "start_time": "2023-09-22T19:36:12.548085500Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('Dummy', DummyClassifier(strategy='most_frequent'), {}),\n",
       " ('Decision Tree', DecisionTreeClassifier(random_state=0), {}),\n",
       " ('SVC', SVC(gamma='auto'), {}),\n",
       " ('Linear SVC', LinearSVC(random_state=0, tol=1e-05), {}),\n",
       " ('Perceptron', Perceptron(), {}),\n",
       " ('Logistic Regression', LogisticRegression(random_state=0), {}),\n",
       " ('Ridge Classifier', RidgeClassifier(random_state=0), {}),\n",
       " ('SGD Classifier', SGDClassifier(random_state=0), {}),\n",
       " ('Passive Aggressive Classifier',\n",
       "  PassiveAggressiveClassifier(random_state=0),\n",
       "  {}),\n",
       " ('K Neighbors Classifier', KNeighborsClassifier(), {}),\n",
       " ('Neural Network Classifier', MLPClassifier(random_state=0), {}),\n",
       " ('Gaussian Process Classifier',\n",
       "  GaussianProcessClassifier(random_state=0),\n",
       "  {}),\n",
       " ('Random Forest Classifier', RandomForestClassifier(random_state=0), {}),\n",
       " ('AdaBoost Classifier', AdaBoostClassifier(random_state=0), {}),\n",
       " ('Gradient Boosting Classifier',\n",
       "  GradientBoostingClassifier(random_state=0),\n",
       "  {}),\n",
       " ('Extra Trees Classifier', ExtraTreesClassifier(random_state=0), {}),\n",
       " ('Bagging Classifier', BaggingClassifier(random_state=0), {})]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hh.model_zoo.DEFAULT_CLASSIFICATION_MODELS"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Notice that it is composed of a list of tuples. Each tuple contains the name we give to the classifier, an instance of the class that implements the classifier and a grid of hyperparameters (which now is empty, but will be explained later).\n",
    "\n",
    "Those are the models that we are going to use now."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Evaluation with default models"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "First create the HundredHammersClassifier object. We want to see the progress of the evaluation of the models, so we indicate it in the constructor of the class."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-09-22T19:36:12.612423400Z",
     "start_time": "2023-09-22T19:36:12.552876800Z"
    }
   },
   "outputs": [],
   "source": [
    "hh_models = hh.HundredHammersClassifier(show_progress_bar=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Then evaluate the models. Apart from the actual data (the variables X and y), you can pass other parameters. ```optim_hyper``` checks whether we want to optimize the hyperparameters of the models and n_grid_points controls how many values from each hyperparameter to check in the optimization.\n",
    "\n",
    "We will leave hyperparameter optimization for later, so for now ``optim_hyper`` is set as false."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-09-22T19:36:30.934986Z",
     "start_time": "2023-09-22T19:36:12.556410700Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Evaluating models...: 100%|██████████| 17/17 [00:40<00:00,  2.37s/it]\n"
     ]
    }
   ],
   "source": [
    "# configure the logger\n",
    "hh.hh_logger.setLevel(logging.WARNING)\n",
    "\n",
    "# Evaluate the models and store the results in a variable\n",
    "df_results = hh_models.evaluate(X, y, optim_hyper=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Notice the line above the evaluation of the models. This configures the logger to only show warnings (of which there should be none). The setting you most likely would want to use in an interactive enviroment would be ```logging.INFO```, since you get information about each model in \"real time\". \n",
    "\n",
    "If you want to see more detailed information, you can set the level to ```logging.DEBUG```. It outputs a lot of information, but it might be useful if you encounter a bug.\n",
    "\n",
    "For the purposes of this notebook, it will be kept to ```logging.WARNING``` but you are welcome to change it if you are running this notebook locally."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can now show the results of our execution"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-09-22T19:36:30.947815900Z",
     "start_time": "2023-09-22T19:36:30.935979800Z"
    }
   },
   "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>Model</th>\n",
       "      <th>Avg ACC (Validation Train)</th>\n",
       "      <th>Std ACC (Validation Train)</th>\n",
       "      <th>Avg ACC (Validation Test)</th>\n",
       "      <th>Std ACC (Validation Test)</th>\n",
       "      <th>Avg ACC (Train)</th>\n",
       "      <th>Std ACC (Train)</th>\n",
       "      <th>Avg ACC (Test)</th>\n",
       "      <th>Std ACC (Test)</th>\n",
       "      <th>Avg F1W (Validation Train)</th>\n",
       "      <th>Std F1W (Validation Train)</th>\n",
       "      <th>Avg F1W (Validation Test)</th>\n",
       "      <th>Std F1W (Validation Test)</th>\n",
       "      <th>Avg F1W (Train)</th>\n",
       "      <th>Std F1W (Train)</th>\n",
       "      <th>Avg F1W (Test)</th>\n",
       "      <th>Std F1W (Test)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Dummy</td>\n",
       "      <td>0.333333</td>\n",
       "      <td>5.551115e-17</td>\n",
       "      <td>0.333333</td>\n",
       "      <td>5.551115e-17</td>\n",
       "      <td>0.333333</td>\n",
       "      <td>5.551115e-17</td>\n",
       "      <td>0.333333</td>\n",
       "      <td>5.551115e-17</td>\n",
       "      <td>0.166667</td>\n",
       "      <td>2.775558e-17</td>\n",
       "      <td>0.166667</td>\n",
       "      <td>2.775558e-17</td>\n",
       "      <td>0.166667</td>\n",
       "      <td>2.775558e-17</td>\n",
       "      <td>0.166667</td>\n",
       "      <td>2.775558e-17</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Decision Tree</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.939167</td>\n",
       "      <td>3.556098e-02</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.966667</td>\n",
       "      <td>1.110223e-16</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.938725</td>\n",
       "      <td>3.602842e-02</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.966583</td>\n",
       "      <td>1.110223e-16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>SVC</td>\n",
       "      <td>0.963750</td>\n",
       "      <td>1.288302e-02</td>\n",
       "      <td>0.948333</td>\n",
       "      <td>4.213075e-02</td>\n",
       "      <td>0.966667</td>\n",
       "      <td>1.110223e-16</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.963732</td>\n",
       "      <td>1.289618e-02</td>\n",
       "      <td>0.947760</td>\n",
       "      <td>4.309094e-02</td>\n",
       "      <td>0.966667</td>\n",
       "      <td>1.110223e-16</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Linear SVC</td>\n",
       "      <td>0.966667</td>\n",
       "      <td>8.068715e-03</td>\n",
       "      <td>0.953333</td>\n",
       "      <td>3.876568e-02</td>\n",
       "      <td>0.968333</td>\n",
       "      <td>3.333333e-03</td>\n",
       "      <td>0.966667</td>\n",
       "      <td>1.110223e-16</td>\n",
       "      <td>0.966648</td>\n",
       "      <td>8.077152e-03</td>\n",
       "      <td>0.952942</td>\n",
       "      <td>3.920657e-02</td>\n",
       "      <td>0.968333</td>\n",
       "      <td>3.331771e-03</td>\n",
       "      <td>0.966583</td>\n",
       "      <td>1.110223e-16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Perceptron</td>\n",
       "      <td>0.715417</td>\n",
       "      <td>1.401023e-01</td>\n",
       "      <td>0.709167</td>\n",
       "      <td>1.526366e-01</td>\n",
       "      <td>0.675000</td>\n",
       "      <td>1.895902e-01</td>\n",
       "      <td>0.693333</td>\n",
       "      <td>2.015496e-01</td>\n",
       "      <td>0.640206</td>\n",
       "      <td>1.857964e-01</td>\n",
       "      <td>0.628819</td>\n",
       "      <td>1.991136e-01</td>\n",
       "      <td>0.612396</td>\n",
       "      <td>2.376406e-01</td>\n",
       "      <td>0.628800</td>\n",
       "      <td>2.560143e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Logistic Regression</td>\n",
       "      <td>0.960625</td>\n",
       "      <td>1.088330e-02</td>\n",
       "      <td>0.944167</td>\n",
       "      <td>4.049177e-02</td>\n",
       "      <td>0.966667</td>\n",
       "      <td>1.110223e-16</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.960613</td>\n",
       "      <td>1.088587e-02</td>\n",
       "      <td>0.943516</td>\n",
       "      <td>4.156557e-02</td>\n",
       "      <td>0.966646</td>\n",
       "      <td>1.110223e-16</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Ridge Classifier</td>\n",
       "      <td>0.873958</td>\n",
       "      <td>2.322239e-02</td>\n",
       "      <td>0.860000</td>\n",
       "      <td>6.601767e-02</td>\n",
       "      <td>0.875000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.833333</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.872920</td>\n",
       "      <td>2.371401e-02</td>\n",
       "      <td>0.856881</td>\n",
       "      <td>6.857956e-02</td>\n",
       "      <td>0.874036</td>\n",
       "      <td>1.110223e-16</td>\n",
       "      <td>0.829497</td>\n",
       "      <td>1.110223e-16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>SGD Classifier</td>\n",
       "      <td>0.803542</td>\n",
       "      <td>1.149994e-01</td>\n",
       "      <td>0.789167</td>\n",
       "      <td>1.158933e-01</td>\n",
       "      <td>0.846667</td>\n",
       "      <td>1.013246e-01</td>\n",
       "      <td>0.863333</td>\n",
       "      <td>1.058825e-01</td>\n",
       "      <td>0.760521</td>\n",
       "      <td>1.589352e-01</td>\n",
       "      <td>0.742811</td>\n",
       "      <td>1.569199e-01</td>\n",
       "      <td>0.819405</td>\n",
       "      <td>1.344465e-01</td>\n",
       "      <td>0.840678</td>\n",
       "      <td>1.381196e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Passive Aggressive Classifier</td>\n",
       "      <td>0.822083</td>\n",
       "      <td>9.702251e-02</td>\n",
       "      <td>0.814167</td>\n",
       "      <td>1.000729e-01</td>\n",
       "      <td>0.845000</td>\n",
       "      <td>9.137833e-02</td>\n",
       "      <td>0.866667</td>\n",
       "      <td>9.067647e-02</td>\n",
       "      <td>0.790508</td>\n",
       "      <td>1.306401e-01</td>\n",
       "      <td>0.778717</td>\n",
       "      <td>1.387220e-01</td>\n",
       "      <td>0.823307</td>\n",
       "      <td>1.176445e-01</td>\n",
       "      <td>0.851415</td>\n",
       "      <td>1.100022e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>K Neighbors Classifier</td>\n",
       "      <td>0.962708</td>\n",
       "      <td>1.251562e-02</td>\n",
       "      <td>0.942500</td>\n",
       "      <td>4.073116e-02</td>\n",
       "      <td>0.958333</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.962680</td>\n",
       "      <td>1.252658e-02</td>\n",
       "      <td>0.941871</td>\n",
       "      <td>4.140596e-02</td>\n",
       "      <td>0.958327</td>\n",
       "      <td>1.110223e-16</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Neural Network Classifier</td>\n",
       "      <td>0.969167</td>\n",
       "      <td>8.829008e-03</td>\n",
       "      <td>0.965833</td>\n",
       "      <td>3.404450e-02</td>\n",
       "      <td>0.970000</td>\n",
       "      <td>4.082483e-03</td>\n",
       "      <td>0.996667</td>\n",
       "      <td>1.000000e-02</td>\n",
       "      <td>0.969096</td>\n",
       "      <td>8.875182e-03</td>\n",
       "      <td>0.965445</td>\n",
       "      <td>3.464766e-02</td>\n",
       "      <td>0.969945</td>\n",
       "      <td>4.104926e-03</td>\n",
       "      <td>0.996658</td>\n",
       "      <td>1.002506e-02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Gaussian Process Classifier</td>\n",
       "      <td>0.957292</td>\n",
       "      <td>1.321727e-02</td>\n",
       "      <td>0.937500</td>\n",
       "      <td>4.583333e-02</td>\n",
       "      <td>0.950000</td>\n",
       "      <td>1.110223e-16</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.957271</td>\n",
       "      <td>1.323461e-02</td>\n",
       "      <td>0.936587</td>\n",
       "      <td>4.725891e-02</td>\n",
       "      <td>0.949969</td>\n",
       "      <td>1.110223e-16</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Random Forest Classifier</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.945000</td>\n",
       "      <td>4.034573e-02</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.953333</td>\n",
       "      <td>1.632993e-02</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.944500</td>\n",
       "      <td>4.096522e-02</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.953014</td>\n",
       "      <td>1.661890e-02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>AdaBoost Classifier</td>\n",
       "      <td>0.941458</td>\n",
       "      <td>7.079932e-02</td>\n",
       "      <td>0.920000</td>\n",
       "      <td>8.284859e-02</td>\n",
       "      <td>0.958333</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.933333</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.936119</td>\n",
       "      <td>8.755802e-02</td>\n",
       "      <td>0.912969</td>\n",
       "      <td>1.020773e-01</td>\n",
       "      <td>0.958327</td>\n",
       "      <td>1.110223e-16</td>\n",
       "      <td>0.932660</td>\n",
       "      <td>1.110223e-16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>Gradient Boosting Classifier</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.944167</td>\n",
       "      <td>4.049177e-02</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.966667</td>\n",
       "      <td>1.110223e-16</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.943731</td>\n",
       "      <td>4.094640e-02</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.966583</td>\n",
       "      <td>1.110223e-16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>Extra Trees Classifier</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.940000</td>\n",
       "      <td>4.262237e-02</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.986667</td>\n",
       "      <td>1.632993e-02</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.939543</td>\n",
       "      <td>4.294486e-02</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.986633</td>\n",
       "      <td>1.637086e-02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>Bagging Classifier</td>\n",
       "      <td>0.993333</td>\n",
       "      <td>8.003905e-03</td>\n",
       "      <td>0.945833</td>\n",
       "      <td>3.841477e-02</td>\n",
       "      <td>0.993333</td>\n",
       "      <td>6.236096e-03</td>\n",
       "      <td>0.956667</td>\n",
       "      <td>2.134375e-02</td>\n",
       "      <td>0.993331</td>\n",
       "      <td>8.006943e-03</td>\n",
       "      <td>0.945411</td>\n",
       "      <td>3.890909e-02</td>\n",
       "      <td>0.993332</td>\n",
       "      <td>6.237907e-03</td>\n",
       "      <td>0.956356</td>\n",
       "      <td>2.161894e-02</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                            Model  Avg ACC (Validation Train)  \\\n",
       "0                           Dummy                    0.333333   \n",
       "1                   Decision Tree                    1.000000   \n",
       "2                             SVC                    0.963750   \n",
       "3                      Linear SVC                    0.966667   \n",
       "4                      Perceptron                    0.715417   \n",
       "5             Logistic Regression                    0.960625   \n",
       "6                Ridge Classifier                    0.873958   \n",
       "7                  SGD Classifier                    0.803542   \n",
       "8   Passive Aggressive Classifier                    0.822083   \n",
       "9          K Neighbors Classifier                    0.962708   \n",
       "10      Neural Network Classifier                    0.969167   \n",
       "11    Gaussian Process Classifier                    0.957292   \n",
       "12       Random Forest Classifier                    1.000000   \n",
       "13            AdaBoost Classifier                    0.941458   \n",
       "14   Gradient Boosting Classifier                    1.000000   \n",
       "15         Extra Trees Classifier                    1.000000   \n",
       "16             Bagging Classifier                    0.993333   \n",
       "\n",
       "    Std ACC (Validation Train)  Avg ACC (Validation Test)  \\\n",
       "0                 5.551115e-17                   0.333333   \n",
       "1                 0.000000e+00                   0.939167   \n",
       "2                 1.288302e-02                   0.948333   \n",
       "3                 8.068715e-03                   0.953333   \n",
       "4                 1.401023e-01                   0.709167   \n",
       "5                 1.088330e-02                   0.944167   \n",
       "6                 2.322239e-02                   0.860000   \n",
       "7                 1.149994e-01                   0.789167   \n",
       "8                 9.702251e-02                   0.814167   \n",
       "9                 1.251562e-02                   0.942500   \n",
       "10                8.829008e-03                   0.965833   \n",
       "11                1.321727e-02                   0.937500   \n",
       "12                0.000000e+00                   0.945000   \n",
       "13                7.079932e-02                   0.920000   \n",
       "14                0.000000e+00                   0.944167   \n",
       "15                0.000000e+00                   0.940000   \n",
       "16                8.003905e-03                   0.945833   \n",
       "\n",
       "    Std ACC (Validation Test)  Avg ACC (Train)  Std ACC (Train)  \\\n",
       "0                5.551115e-17         0.333333     5.551115e-17   \n",
       "1                3.556098e-02         1.000000     0.000000e+00   \n",
       "2                4.213075e-02         0.966667     1.110223e-16   \n",
       "3                3.876568e-02         0.968333     3.333333e-03   \n",
       "4                1.526366e-01         0.675000     1.895902e-01   \n",
       "5                4.049177e-02         0.966667     1.110223e-16   \n",
       "6                6.601767e-02         0.875000     0.000000e+00   \n",
       "7                1.158933e-01         0.846667     1.013246e-01   \n",
       "8                1.000729e-01         0.845000     9.137833e-02   \n",
       "9                4.073116e-02         0.958333     0.000000e+00   \n",
       "10               3.404450e-02         0.970000     4.082483e-03   \n",
       "11               4.583333e-02         0.950000     1.110223e-16   \n",
       "12               4.034573e-02         1.000000     0.000000e+00   \n",
       "13               8.284859e-02         0.958333     0.000000e+00   \n",
       "14               4.049177e-02         1.000000     0.000000e+00   \n",
       "15               4.262237e-02         1.000000     0.000000e+00   \n",
       "16               3.841477e-02         0.993333     6.236096e-03   \n",
       "\n",
       "    Avg ACC (Test)  Std ACC (Test)  Avg F1W (Validation Train)  \\\n",
       "0         0.333333    5.551115e-17                    0.166667   \n",
       "1         0.966667    1.110223e-16                    1.000000   \n",
       "2         1.000000    0.000000e+00                    0.963732   \n",
       "3         0.966667    1.110223e-16                    0.966648   \n",
       "4         0.693333    2.015496e-01                    0.640206   \n",
       "5         1.000000    0.000000e+00                    0.960613   \n",
       "6         0.833333    0.000000e+00                    0.872920   \n",
       "7         0.863333    1.058825e-01                    0.760521   \n",
       "8         0.866667    9.067647e-02                    0.790508   \n",
       "9         1.000000    0.000000e+00                    0.962680   \n",
       "10        0.996667    1.000000e-02                    0.969096   \n",
       "11        1.000000    0.000000e+00                    0.957271   \n",
       "12        0.953333    1.632993e-02                    1.000000   \n",
       "13        0.933333    0.000000e+00                    0.936119   \n",
       "14        0.966667    1.110223e-16                    1.000000   \n",
       "15        0.986667    1.632993e-02                    1.000000   \n",
       "16        0.956667    2.134375e-02                    0.993331   \n",
       "\n",
       "    Std F1W (Validation Train)  Avg F1W (Validation Test)  \\\n",
       "0                 2.775558e-17                   0.166667   \n",
       "1                 0.000000e+00                   0.938725   \n",
       "2                 1.289618e-02                   0.947760   \n",
       "3                 8.077152e-03                   0.952942   \n",
       "4                 1.857964e-01                   0.628819   \n",
       "5                 1.088587e-02                   0.943516   \n",
       "6                 2.371401e-02                   0.856881   \n",
       "7                 1.589352e-01                   0.742811   \n",
       "8                 1.306401e-01                   0.778717   \n",
       "9                 1.252658e-02                   0.941871   \n",
       "10                8.875182e-03                   0.965445   \n",
       "11                1.323461e-02                   0.936587   \n",
       "12                0.000000e+00                   0.944500   \n",
       "13                8.755802e-02                   0.912969   \n",
       "14                0.000000e+00                   0.943731   \n",
       "15                0.000000e+00                   0.939543   \n",
       "16                8.006943e-03                   0.945411   \n",
       "\n",
       "    Std F1W (Validation Test)  Avg F1W (Train)  Std F1W (Train)  \\\n",
       "0                2.775558e-17         0.166667     2.775558e-17   \n",
       "1                3.602842e-02         1.000000     0.000000e+00   \n",
       "2                4.309094e-02         0.966667     1.110223e-16   \n",
       "3                3.920657e-02         0.968333     3.331771e-03   \n",
       "4                1.991136e-01         0.612396     2.376406e-01   \n",
       "5                4.156557e-02         0.966646     1.110223e-16   \n",
       "6                6.857956e-02         0.874036     1.110223e-16   \n",
       "7                1.569199e-01         0.819405     1.344465e-01   \n",
       "8                1.387220e-01         0.823307     1.176445e-01   \n",
       "9                4.140596e-02         0.958327     1.110223e-16   \n",
       "10               3.464766e-02         0.969945     4.104926e-03   \n",
       "11               4.725891e-02         0.949969     1.110223e-16   \n",
       "12               4.096522e-02         1.000000     0.000000e+00   \n",
       "13               1.020773e-01         0.958327     1.110223e-16   \n",
       "14               4.094640e-02         1.000000     0.000000e+00   \n",
       "15               4.294486e-02         1.000000     0.000000e+00   \n",
       "16               3.890909e-02         0.993332     6.237907e-03   \n",
       "\n",
       "    Avg F1W (Test)  Std F1W (Test)  \n",
       "0         0.166667    2.775558e-17  \n",
       "1         0.966583    1.110223e-16  \n",
       "2         1.000000    0.000000e+00  \n",
       "3         0.966583    1.110223e-16  \n",
       "4         0.628800    2.560143e-01  \n",
       "5         1.000000    0.000000e+00  \n",
       "6         0.829497    1.110223e-16  \n",
       "7         0.840678    1.381196e-01  \n",
       "8         0.851415    1.100022e-01  \n",
       "9         1.000000    0.000000e+00  \n",
       "10        0.996658    1.002506e-02  \n",
       "11        1.000000    0.000000e+00  \n",
       "12        0.953014    1.661890e-02  \n",
       "13        0.932660    1.110223e-16  \n",
       "14        0.966583    1.110223e-16  \n",
       "15        0.986633    1.637086e-02  \n",
       "16        0.956356    2.161894e-02  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_results"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "That's an ok way of displaying the result, but tables can sometimes be hard to read, this is why we also implement a couple of functions to display the information of the table in a more readable format."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-09-22T19:36:31.737892300Z",
     "start_time": "2023-09-22T19:36:30.944815200Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 600x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "hh.plot_batch_results(df_results, metric_name=\"ACC\", title=\"Iris Dataset\", display=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-09-22T19:36:32.066701900Z",
     "start_time": "2023-09-22T19:36:31.738892100Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x1000 with 4 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "hh.plot_confusion_matrix(\n",
    "    X,\n",
    "    y,\n",
    "    class_dict={0: \"Setosa\", 1: \"Versicolor\", 2: \"Virginica\"},\n",
    "    model=KNeighborsClassifier(),\n",
    "    title=\"Iris Dataset\",\n",
    "    display=False,\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In case we needed to use one of the trained models, we can take it from the ```trained_models``` attribute from the ```HundredHammersClassifier``` class. This value will consist on a list with tuples containing the name of the model and the trained model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-09-22T19:36:32.067702500Z",
     "start_time": "2023-09-22T19:36:32.055481700Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('Dummy', DummyClassifier(random_state=9, strategy='most_frequent'), {}),\n",
       " ('Decision Tree', DecisionTreeClassifier(random_state=9), {}),\n",
       " ('SVC', SVC(gamma='auto', random_state=9), {}),\n",
       " ('Linear SVC', LinearSVC(random_state=9, tol=1e-05), {}),\n",
       " ('Perceptron', Perceptron(random_state=9), {}),\n",
       " ('Logistic Regression', LogisticRegression(random_state=9), {}),\n",
       " ('Ridge Classifier', RidgeClassifier(random_state=9), {}),\n",
       " ('SGD Classifier', SGDClassifier(random_state=9), {}),\n",
       " ('Passive Aggressive Classifier',\n",
       "  PassiveAggressiveClassifier(random_state=9),\n",
       "  {}),\n",
       " ('K Neighbors Classifier', KNeighborsClassifier(), {}),\n",
       " ('Neural Network Classifier', MLPClassifier(random_state=9), {}),\n",
       " ('Gaussian Process Classifier',\n",
       "  GaussianProcessClassifier(random_state=9),\n",
       "  {}),\n",
       " ('Random Forest Classifier', RandomForestClassifier(random_state=9), {}),\n",
       " ('AdaBoost Classifier', AdaBoostClassifier(random_state=9), {}),\n",
       " ('Gradient Boosting Classifier',\n",
       "  GradientBoostingClassifier(random_state=9),\n",
       "  {}),\n",
       " ('Extra Trees Classifier', ExtraTreesClassifier(random_state=9), {}),\n",
       " ('Bagging Classifier', BaggingClassifier(random_state=9), {})]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hh_models.trained_models"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Automatic optimization of hyperparameters"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now, let us take a look at how the hyperparameter optimization works. Let us assume that we do not want to use every model that we saw earlier, but only a select few: in this case we need to create a model list and pass it to the ```HundredHammersClassifier``` class.\n",
    "\n",
    "For this example, we will use four simple classifier models."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-09-22T19:36:32.067702500Z",
     "start_time": "2023-09-22T19:36:32.060252900Z"
    }
   },
   "outputs": [],
   "source": [
    "models_to_check = [\n",
    "    (\"Dummy\", DummyClassifier(), None),\n",
    "    (\"Decision Tree\", DecisionTreeClassifier(random_state=0), None),\n",
    "    (\"Ridge Classifer\", RidgeClassifier(random_state=0), None),\n",
    "    (\"KNN\", KNeighborsClassifier(), None),\n",
    "]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Each model has a name and an object that implements it. The third position in the tuple represents the user-specified grid of hyperparameters, however, we will let them be automatially generated.\n",
    "\n",
    "This will only happen for already configured models, if you want automatic generation of hyperparameters for a model that is not already added, check the \"example_add_model.ipynb\" notebook.\n",
    "\n",
    "We can now proceed passing these models to the ```HundredHammersClassifier``` class."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-09-22T19:36:32.067702500Z",
     "start_time": "2023-09-22T19:36:32.063128800Z"
    }
   },
   "outputs": [],
   "source": [
    "hh_models = hh.HundredHammersClassifier(models=models_to_check, show_progress_bar=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This time, since we want to optimize the hyperparameters of our models, we set the appropriate parameter to ```True```.\n",
    "\n",
    "We can configure how many parameters to check in the GridSearch step, ```n_grid_points``` will indicate how many values each of the hyperparameters will take. In this case, we will take 8 values for each one.\n",
    "\n",
    "(In the case of categorical values, if there are less than 8 values, only those will be taken.)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-09-22T19:36:35.540738700Z",
     "start_time": "2023-09-22T19:36:32.065701600Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Evaluating models...: 100%|██████████| 4/4 [00:00<00:00,  4.65it/s]         \n"
     ]
    }
   ],
   "source": [
    "df_results = hh_models.evaluate(X, y, optim_hyper=True, n_grid_points=8)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-09-22T19:36:35.548267700Z",
     "start_time": "2023-09-22T19:36:35.537746100Z"
    }
   },
   "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>Model</th>\n",
       "      <th>Avg ACC (Validation Train)</th>\n",
       "      <th>Std ACC (Validation Train)</th>\n",
       "      <th>Avg ACC (Validation Test)</th>\n",
       "      <th>Std ACC (Validation Test)</th>\n",
       "      <th>Avg ACC (Train)</th>\n",
       "      <th>Std ACC (Train)</th>\n",
       "      <th>Avg ACC (Test)</th>\n",
       "      <th>Std ACC (Test)</th>\n",
       "      <th>Avg F1W (Validation Train)</th>\n",
       "      <th>Std F1W (Validation Train)</th>\n",
       "      <th>Avg F1W (Validation Test)</th>\n",
       "      <th>Std F1W (Validation Test)</th>\n",
       "      <th>Avg F1W (Train)</th>\n",
       "      <th>Std F1W (Train)</th>\n",
       "      <th>Avg F1W (Test)</th>\n",
       "      <th>Std F1W (Test)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Dummy</td>\n",
       "      <td>0.337083</td>\n",
       "      <td>0.046991</td>\n",
       "      <td>0.344167</td>\n",
       "      <td>0.098886</td>\n",
       "      <td>0.3375</td>\n",
       "      <td>0.056673</td>\n",
       "      <td>0.290000</td>\n",
       "      <td>9.315459e-02</td>\n",
       "      <td>0.334173</td>\n",
       "      <td>0.048363</td>\n",
       "      <td>0.335000</td>\n",
       "      <td>0.099751</td>\n",
       "      <td>0.336118</td>\n",
       "      <td>5.640639e-02</td>\n",
       "      <td>0.281269</td>\n",
       "      <td>9.491669e-02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Decision Tree</td>\n",
       "      <td>0.997917</td>\n",
       "      <td>0.004167</td>\n",
       "      <td>0.938333</td>\n",
       "      <td>0.039299</td>\n",
       "      <td>1.0000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.966667</td>\n",
       "      <td>1.110223e-16</td>\n",
       "      <td>0.997916</td>\n",
       "      <td>0.004168</td>\n",
       "      <td>0.937882</td>\n",
       "      <td>0.039750</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.966583</td>\n",
       "      <td>1.110223e-16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Ridge Classifer</td>\n",
       "      <td>0.872083</td>\n",
       "      <td>0.018286</td>\n",
       "      <td>0.863333</td>\n",
       "      <td>0.061260</td>\n",
       "      <td>0.8750</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.800000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.871381</td>\n",
       "      <td>0.018568</td>\n",
       "      <td>0.861076</td>\n",
       "      <td>0.063023</td>\n",
       "      <td>0.874510</td>\n",
       "      <td>1.110223e-16</td>\n",
       "      <td>0.797980</td>\n",
       "      <td>1.110223e-16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>KNN</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.967500</td>\n",
       "      <td>0.026732</td>\n",
       "      <td>1.0000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.966667</td>\n",
       "      <td>1.110223e-16</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.967359</td>\n",
       "      <td>0.026863</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.966583</td>\n",
       "      <td>1.110223e-16</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Model  Avg ACC (Validation Train)  Std ACC (Validation Train)  \\\n",
       "0            Dummy                    0.337083                    0.046991   \n",
       "1    Decision Tree                    0.997917                    0.004167   \n",
       "2  Ridge Classifer                    0.872083                    0.018286   \n",
       "3              KNN                    1.000000                    0.000000   \n",
       "\n",
       "   Avg ACC (Validation Test)  Std ACC (Validation Test)  Avg ACC (Train)  \\\n",
       "0                   0.344167                   0.098886           0.3375   \n",
       "1                   0.938333                   0.039299           1.0000   \n",
       "2                   0.863333                   0.061260           0.8750   \n",
       "3                   0.967500                   0.026732           1.0000   \n",
       "\n",
       "   Std ACC (Train)  Avg ACC (Test)  Std ACC (Test)  \\\n",
       "0         0.056673        0.290000    9.315459e-02   \n",
       "1         0.000000        0.966667    1.110223e-16   \n",
       "2         0.000000        0.800000    0.000000e+00   \n",
       "3         0.000000        0.966667    1.110223e-16   \n",
       "\n",
       "   Avg F1W (Validation Train)  Std F1W (Validation Train)  \\\n",
       "0                    0.334173                    0.048363   \n",
       "1                    0.997916                    0.004168   \n",
       "2                    0.871381                    0.018568   \n",
       "3                    1.000000                    0.000000   \n",
       "\n",
       "   Avg F1W (Validation Test)  Std F1W (Validation Test)  Avg F1W (Train)  \\\n",
       "0                   0.335000                   0.099751         0.336118   \n",
       "1                   0.937882                   0.039750         1.000000   \n",
       "2                   0.861076                   0.063023         0.874510   \n",
       "3                   0.967359                   0.026863         1.000000   \n",
       "\n",
       "   Std F1W (Train)  Avg F1W (Test)  Std F1W (Test)  \n",
       "0     5.640639e-02        0.281269    9.491669e-02  \n",
       "1     0.000000e+00        0.966583    1.110223e-16  \n",
       "2     1.110223e-16        0.797980    1.110223e-16  \n",
       "3     0.000000e+00        0.966583    1.110223e-16  "
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_results"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now that we have optimized the hyperparameters of the models, we can check which hyperparameters were chosen for each. This is done by checking the ```best_params``` attribute."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-09-22T19:36:35.549267400Z",
     "start_time": "2023-09-22T19:36:35.546266700Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('Dummy', {'strategy': 'stratified'}),\n",
       " ('Decision Tree', {'criterion': 'entropy', 'max_depth': 6}),\n",
       " ('Ridge Classifer', {'alpha': 1e-10}),\n",
       " ('KNN', {'metric': 'cosine', 'n_neighbors': 1})]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hh_models.best_params"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "If we use the in-built visualizations to compare the models:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-09-22T19:36:35.717435600Z",
     "start_time": "2023-09-22T19:36:35.549267400Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 600x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "hh.plot_batch_results(df_results, metric_name=\"ACC\", title=\"Iris Dataset\", display=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Optimization of hyperparameters with custom parameter grids"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For this example, we will use four simple classifier models with grids of hyperparameters. \n",
    "\n",
    "These grid will contain all the parameters that the gridsearch optimization will use."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-09-22T19:36:35.717435600Z",
     "start_time": "2023-09-22T19:36:35.714716500Z"
    }
   },
   "outputs": [],
   "source": [
    "models_to_check = [\n",
    "    (\"Dummy\", DummyClassifier(), {\"strategy\": [\"most_frequent\"]}),\n",
    "    (\n",
    "        \"Decision Tree\",\n",
    "        DecisionTreeClassifier(random_state=0),\n",
    "        {\n",
    "            \"criterion\": [\"gini\", \"entropy\", \"log_loss\"],\n",
    "            \"max_depth\": [1, 2, 3, 4, 5, 6, 7],\n",
    "        },\n",
    "    ),\n",
    "    (\n",
    "        \"Ridge Classifer\",\n",
    "        RidgeClassifier(random_state=0),\n",
    "        {\"alpha\": [1e-4, 1e-3, 1e-2, 0.1, 1, 10]},\n",
    "    ),\n",
    "    (\n",
    "        \"KNN\",\n",
    "        KNeighborsClassifier(),\n",
    "        {\"n_neighbors\": [1, 3, 5, 7, 9, 11], \"metric\": [\"manhattan\", \"euclidean\"]},\n",
    "    ),\n",
    "]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can now proceed passing these models to the ```HundredHammersClassifier``` class."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-09-22T19:36:35.723441Z",
     "start_time": "2023-09-22T19:36:35.717435600Z"
    }
   },
   "outputs": [],
   "source": [
    "hh_models = hh.HundredHammersClassifier(models=models_to_check, show_progress_bar=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Since we want to optimize the hyperparameters of our models, we set the appropiate parameter to ```True```. \n",
    "\n",
    "We don't need to set the ```n_grid_points``` parameter since we have already chosen which parameters to take in the GridSearch step."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-09-22T19:36:36.441664200Z",
     "start_time": "2023-09-22T19:36:35.720439900Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Evaluating models...: 100%|██████████| 4/4 [00:00<00:00,  5.08it/s]         \n"
     ]
    }
   ],
   "source": [
    "df_results = hh_models.evaluate(X, y, optim_hyper=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-09-22T19:36:36.447323200Z",
     "start_time": "2023-09-22T19:36:36.437663400Z"
    }
   },
   "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>Model</th>\n",
       "      <th>Avg ACC (Validation Train)</th>\n",
       "      <th>Std ACC (Validation Train)</th>\n",
       "      <th>Avg ACC (Validation Test)</th>\n",
       "      <th>Std ACC (Validation Test)</th>\n",
       "      <th>Avg ACC (Train)</th>\n",
       "      <th>Std ACC (Train)</th>\n",
       "      <th>Avg ACC (Test)</th>\n",
       "      <th>Std ACC (Test)</th>\n",
       "      <th>Avg F1W (Validation Train)</th>\n",
       "      <th>Std F1W (Validation Train)</th>\n",
       "      <th>Avg F1W (Validation Test)</th>\n",
       "      <th>Std F1W (Validation Test)</th>\n",
       "      <th>Avg F1W (Train)</th>\n",
       "      <th>Std F1W (Train)</th>\n",
       "      <th>Avg F1W (Test)</th>\n",
       "      <th>Std F1W (Test)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Dummy</td>\n",
       "      <td>0.333333</td>\n",
       "      <td>5.551115e-17</td>\n",
       "      <td>0.333333</td>\n",
       "      <td>5.551115e-17</td>\n",
       "      <td>0.333333</td>\n",
       "      <td>5.551115e-17</td>\n",
       "      <td>0.333333</td>\n",
       "      <td>5.551115e-17</td>\n",
       "      <td>0.166667</td>\n",
       "      <td>2.775558e-17</td>\n",
       "      <td>0.166667</td>\n",
       "      <td>2.775558e-17</td>\n",
       "      <td>0.166667</td>\n",
       "      <td>2.775558e-17</td>\n",
       "      <td>0.166667</td>\n",
       "      <td>2.775558e-17</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Decision Tree</td>\n",
       "      <td>0.968125</td>\n",
       "      <td>8.692769e-03</td>\n",
       "      <td>0.958333</td>\n",
       "      <td>3.632416e-02</td>\n",
       "      <td>0.966667</td>\n",
       "      <td>1.110223e-16</td>\n",
       "      <td>0.933333</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.968099</td>\n",
       "      <td>8.705309e-03</td>\n",
       "      <td>0.958156</td>\n",
       "      <td>3.648369e-02</td>\n",
       "      <td>0.966646</td>\n",
       "      <td>1.110223e-16</td>\n",
       "      <td>0.932660</td>\n",
       "      <td>1.110223e-16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Ridge Classifer</td>\n",
       "      <td>0.872083</td>\n",
       "      <td>1.828592e-02</td>\n",
       "      <td>0.863333</td>\n",
       "      <td>6.125992e-02</td>\n",
       "      <td>0.875000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.800000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.871381</td>\n",
       "      <td>1.856780e-02</td>\n",
       "      <td>0.861076</td>\n",
       "      <td>6.302271e-02</td>\n",
       "      <td>0.874510</td>\n",
       "      <td>1.110223e-16</td>\n",
       "      <td>0.797980</td>\n",
       "      <td>1.110223e-16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>KNN</td>\n",
       "      <td>0.963542</td>\n",
       "      <td>1.201309e-02</td>\n",
       "      <td>0.946667</td>\n",
       "      <td>4.333333e-02</td>\n",
       "      <td>0.966667</td>\n",
       "      <td>1.110223e-16</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.963528</td>\n",
       "      <td>1.202337e-02</td>\n",
       "      <td>0.946001</td>\n",
       "      <td>4.432124e-02</td>\n",
       "      <td>0.966667</td>\n",
       "      <td>1.110223e-16</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Model  Avg ACC (Validation Train)  Std ACC (Validation Train)  \\\n",
       "0            Dummy                    0.333333                5.551115e-17   \n",
       "1    Decision Tree                    0.968125                8.692769e-03   \n",
       "2  Ridge Classifer                    0.872083                1.828592e-02   \n",
       "3              KNN                    0.963542                1.201309e-02   \n",
       "\n",
       "   Avg ACC (Validation Test)  Std ACC (Validation Test)  Avg ACC (Train)  \\\n",
       "0                   0.333333               5.551115e-17         0.333333   \n",
       "1                   0.958333               3.632416e-02         0.966667   \n",
       "2                   0.863333               6.125992e-02         0.875000   \n",
       "3                   0.946667               4.333333e-02         0.966667   \n",
       "\n",
       "   Std ACC (Train)  Avg ACC (Test)  Std ACC (Test)  \\\n",
       "0     5.551115e-17        0.333333    5.551115e-17   \n",
       "1     1.110223e-16        0.933333    0.000000e+00   \n",
       "2     0.000000e+00        0.800000    0.000000e+00   \n",
       "3     1.110223e-16        1.000000    0.000000e+00   \n",
       "\n",
       "   Avg F1W (Validation Train)  Std F1W (Validation Train)  \\\n",
       "0                    0.166667                2.775558e-17   \n",
       "1                    0.968099                8.705309e-03   \n",
       "2                    0.871381                1.856780e-02   \n",
       "3                    0.963528                1.202337e-02   \n",
       "\n",
       "   Avg F1W (Validation Test)  Std F1W (Validation Test)  Avg F1W (Train)  \\\n",
       "0                   0.166667               2.775558e-17         0.166667   \n",
       "1                   0.958156               3.648369e-02         0.966646   \n",
       "2                   0.861076               6.302271e-02         0.874510   \n",
       "3                   0.946001               4.432124e-02         0.966667   \n",
       "\n",
       "   Std F1W (Train)  Avg F1W (Test)  Std F1W (Test)  \n",
       "0     2.775558e-17        0.166667    2.775558e-17  \n",
       "1     1.110223e-16        0.932660    1.110223e-16  \n",
       "2     1.110223e-16        0.797980    1.110223e-16  \n",
       "3     1.110223e-16        1.000000    0.000000e+00  "
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_results"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now that we have optimized the hyperparameters of the models, we can check which hyperparameters were chosen for each. This is done by checking the ```best_params``` attribute."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-09-22T19:36:36.448323300Z",
     "start_time": "2023-09-22T19:36:36.444258700Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('Dummy', {'strategy': 'most_frequent'}),\n",
       " ('Decision Tree', {'criterion': 'gini', 'max_depth': 2}),\n",
       " ('Ridge Classifer', {'alpha': 0.0001}),\n",
       " ('KNN', {'metric': 'euclidean', 'n_neighbors': 11})]"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "hh_models.best_params"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can also show the plots like last time."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-09-22T19:36:36.606759600Z",
     "start_time": "2023-09-22T19:36:36.447323200Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 600x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "hh.plot_batch_results(df_results, metric_name=\"ACC\", title=\"Iris Dataset\", display=False)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}