examples/notebooks/hyper_parameter_tuning_nia_sample.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 445
    },
    "colab_type": "code",
    "id": "uVFd6ndPX_0J",
    "outputId": "518aa283-1769-4d7c-c5fa-d98e31adeec2"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: np in /Users/timzatko/.pyenv/versions/miniconda3-4.7.12/lib/python3.7/site-packages (1.0.2)\n",
      "Requirement already satisfied: sklearn in /Users/timzatko/.pyenv/versions/miniconda3-4.7.12/lib/python3.7/site-packages (0.0)\n",
      "Requirement already satisfied: scikit-learn in /Users/timzatko/.pyenv/versions/miniconda3-4.7.12/lib/python3.7/site-packages (from sklearn) (0.24.2)\n",
      "Requirement already satisfied: scipy>=0.19.1 in /Users/timzatko/.pyenv/versions/miniconda3-4.7.12/lib/python3.7/site-packages (from scikit-learn->sklearn) (1.7.0)\n",
      "Requirement already satisfied: threadpoolctl>=2.0.0 in /Users/timzatko/.pyenv/versions/miniconda3-4.7.12/lib/python3.7/site-packages (from scikit-learn->sklearn) (2.2.0)\n",
      "Requirement already satisfied: numpy>=1.13.3 in /Users/timzatko/.pyenv/versions/miniconda3-4.7.12/lib/python3.7/site-packages (from scikit-learn->sklearn) (1.21.1)\n",
      "Requirement already satisfied: joblib>=0.11 in /Users/timzatko/.pyenv/versions/miniconda3-4.7.12/lib/python3.7/site-packages (from scikit-learn->sklearn) (1.0.1)\n"
     ]
    }
   ],
   "source": [
    "! pip install np\n",
    "! pip install sklearn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "iRq7N9veX67Z"
   },
   "outputs": [],
   "source": [
    "from sklearn.metrics import classification_report"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "iAIzDA0bX67c"
   },
   "source": [
    "# Hyper-Parameter Tunning Using Nature Inspired Algorithms "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "ztnf-m7KZDUg"
   },
   "source": [
    "We will hyper-tune parameters of the RandomForestClassifier."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "p5oNj0hSaP8D"
   },
   "source": [
    "## Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 68
    },
    "colab_type": "code",
    "id": "_yRMWxuLX67d",
    "outputId": "81970368-2388-4576-f9b1-9fa32092bccc"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "train size - 120\n",
      "test size - 30\n"
     ]
    }
   ],
   "source": [
    "import random\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.datasets import load_iris\n",
    "\n",
    "X, y = load_iris(return_X_y=True, as_frame=False)\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
    "\n",
    "print(f'train size - {len(X_train)}\\ntest size - {len(X_test)}')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "pTiifVL_X67f"
   },
   "source": [
    "## Hyper-parameters\n",
    "\n",
    "Now, we will define the `param_grid` which we will be optimizing. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "UiHVmD2PX67g"
   },
   "outputs": [],
   "source": [
    "param_grid = { \n",
    "    'n_estimators': range(20, 100, 2), \n",
    "    'max_depth': range(5, 100, 20),\n",
    "    'min_samples_split': range(2, 10, 5),\n",
    "    'max_features': [\"auto\"],\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "EOe-mgdIlMOj",
    "outputId": "b2ba3de0-b311-4b0d-e38c-c797e548a6cd"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "This is 400 combinations in total.\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "\n",
    "print(f'This is {np.multiply.reduce([len(param) for param in param_grid.values()])} combinations in total.')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "-dgwoKDQX68v"
   },
   "source": [
    "### Optimization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "EWF9kIikghxo"
   },
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 51
    },
    "colab_type": "code",
    "id": "GSg2ett_X68v",
    "outputId": "4358806b-e098-40d5-fd6a-eb1c7e17e691"
   },
   "outputs": [],
   "source": [
    "import sys\n",
    "sys.path.append('../..')\n",
    "\n",
    "from sklearn_nature_inspired_algorithms.model_selection.nature_inspired_search_cv import NatureInspiredSearchCV\n",
    "from sklearn_nature_inspired_algorithms.helpers import score_by_generation_lineplot"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "uYPjHAq-bTAX"
   },
   "source": [
    "### Bat Algorithm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 68
    },
    "colab_type": "code",
    "id": "fHaK7n49X69g",
    "outputId": "4464a87d-dce2-4c0f-f0bb-117d342730a0"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting 5 folds for some of the 400 candidates, which might total in 2000 fits\n",
      "Optimization finished, 244 candidates were fitted (totalling 1220 fits)\n",
      "CPU times: user 3.7 s, sys: 212 ms, total: 3.91 s\n",
      "Wall time: 1min 25s\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "NatureInspiredSearchCV(algorithm='ba', cv=5,\n",
       "                       estimator=RandomForestClassifier(random_state=42),\n",
       "                       max_n_gen=20, max_stagnating_gen=5, n_jobs=-1,\n",
       "                       param_grid={'max_depth': range(5, 100, 20),\n",
       "                                   'max_features': ['auto'],\n",
       "                                   'min_samples_split': range(2, 10, 5),\n",
       "                                   'n_estimators': range(20, 100, 2)},\n",
       "                       population_size=10, random_state=42, runs=5,\n",
       "                       scoring='f1_macro')"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%%time\n",
    "\n",
    "clf = RandomForestClassifier(random_state=42)\n",
    "\n",
    "nia_search = NatureInspiredSearchCV(\n",
    "    clf,\n",
    "    param_grid,\n",
    "    cv=5,\n",
    "    verbose=0,\n",
    "    algorithm='ba',\n",
    "    population_size=10,\n",
    "    max_n_gen=20,\n",
    "    max_stagnating_gen=5,\n",
    "    runs=5,\n",
    "    n_jobs=-1,\n",
    "    scoring='f1_macro',\n",
    "    random_state=42)\n",
    "\n",
    "nia_search.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 296
    },
    "colab_type": "code",
    "id": "1VTiD3A_dEqP",
    "outputId": "e36f05eb-9e41-4c68-c4fb-c9b04a6e8c6a"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='generation', ylabel='max score'>"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYgAAAEICAYAAABF82P+AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8rg+JYAAAACXBIWXMAAAsTAAALEwEAmpwYAAAZkklEQVR4nO3dfZBV9Z3n8feHByUKFspTERoBgzE0FEFpER+iODUmwLgqkHEkOoqaZbfUGMtyNlqZHXdIuZqM7mrUyg4TSQadQBnUhCDBUCJlNGalkQcFFiGCoVtKOyiJxJBg890/zgGvzQGO9D19m3s/r6pbnMff/R4t+Nzf+Z0HRQRmZmZtdal0AWZm1jk5IMzMLJMDwszMMjkgzMwskwPCzMwyOSDMzCxTYQEhaY6kdyS9dpD1kvRdSZslrZV0Rsm6ayRtSj/XFFWjmZkdnIq6D0LS+cAuYG5EjMpYPxn4GjAZOAt4ICLOknQS0Ag0AAGsBMZGxHuH+r6+ffvG0KFDy3sQZmZVbuXKlb+LiH5Z67oV9aUR8bykoYfY5FKS8Ajg15J6SxoITACWRsS7AJKWAhOBeYf6vqFDh9LY2FiW2s3MaoWkNw+2rpJjEIOAbSXzTemygy03M7MOdFQPUkuaKalRUmNLS0ulyzEzqyqVDIhmYHDJfF267GDLDxARsyOiISIa+vXLPIVmZmZHqLAxiBwWAjdJmk8ySP37iNgu6Rngf0o6Md3ui8AdlSrSzOxw9uzZQ1NTE7t37650KQfVo0cP6urq6N69e+59CgsISfNIBpz7SmoC7gS6A0TE/wEWk1zBtBn4ALg2XfeupG8BK9KmZu0bsDYz64yampro1asXQ4cORVKlyzlARLBjxw6ampoYNmxY7v2KvIpp+mHWB3DjQdbNAeYUUZeZWbnt3r2704YDgCT69OnDJx2rPaoHqc3MOovOGg77HEl9DggzM8vkgDAz6wQigr1791a6jI9xQJiZVcjWrVs57bTTuPrqqxk1ahRdu3bdv27BggXMmDEDgBkzZnDzzTdzzjnncMopp7BgwYIOqc8BYWZWQZs2beKGG25g3bp1HH/88Qfdbvv27bzwwgssWrSI22+/vUNqc0CYmVXQkCFDGD9+/GG3u+yyy+jSpQv19fW8/fbbHVCZA8LMrKJKew2lVxq1venu2GOP3T9d1FO423JAmJl1EgMGDGDDhg3s3buXp556qtLlOCDMzDqLe+65h4svvphzzjmHgQMHVrqc4l4Y1NEaGhrC74Mws0rYsGEDI0aMqHQZh5VVp6SVEdGQtb17EGZmlskBYWZmmRwQZmaWyQFhZmaZHBBmZpbJAWFmZpkcEGZmVWDJkiWcdtppDB8+nHvuuacsbTogzMyOcq2trdx44438/Oc/Z/369cybN4/169e3u10HhJnZUe7ll19m+PDhnHLKKRxzzDFcccUV/PSnP213uw4IM7OjXHNzM4MHD94/X1dXR3Nzc7vb7dbuFszMbL8/vvVbWv/0QVnb7Pqp4zj+0yeXtc083IMwMzvKDRo0iG3btu2fb2pqYtCgQe1u1z0IM7MyqsQv/TPPPJNNmzaxZcsWBg0axPz58/nRj37U7nYdEGZmR7lu3brx0EMP8aUvfYnW1lauu+46Ro4c2f52y1CbmZlV2OTJk5k8eXJZ2/QYhJmZZXJAmJlZJgeEmZllckCYmVkmB4SZmWVyQJiZWSYHhJlZFbjuuuvo378/o0aNKlubDggzsyowY8YMlixZUtY2Cw0ISRMlbZS0WdLtGeuHSHpW0lpJyyXVlaz7jqR1kjZI+q4kFVmrmdnR7Pzzz+ekk04qa5uFBYSkrsDDwCSgHpguqb7NZvcCcyNiNDALuDvd9xzgXGA0MAo4E7igqFrNzOxART5qYxywOSLeAJA0H7gUKH3NUT1wazr9HPCTdDqAHsAxgIDuwNsF1mpmVhbbf/UKu3e8V9Y2e/Q5kYHnnFHWNvMo8hTTIGBbyXxTuqzUGmBqOj0F6CWpT0S8RBIY29PPMxGxocBazcysjUo/rO824CFJM4DngWagVdJwYASwb0xiqaQvRMQvS3eWNBOYCXDyyR3/iF0zs7Yq8Uu/KEX2IJqBwSXzdemy/SLirYiYGhGnA99Ml+0k6U38OiJ2RcQu4OfA2W2/ICJmR0RDRDT069evoMMwM+v8pk+fztlnn83GjRupq6vjkUceaXebRfYgVgCnShpGEgxXAF8p3UBSX+DdiNgL3AHMSVf9FvjPku4mGYO4ALi/wFrNzI5q8+bNK3ubhfUgIuJD4CbgGWAD8HhErJM0S9Il6WYTgI2SXgcGAHelyxcAvwFeJRmnWBMRPyuqVjMzO1ChYxARsRhY3GbZP5VMLyAJg7b7tQL/pcjazMzs0HwntZmZZXJAmJlZJgeEmZllckCYmVkmB4SZWRXYtm0bF154IfX19YwcOZIHHnig3W1W+k5qMzMrg27dunHfffdxxhln8P777zN27Fguuugi6uvbPiM1P/cgzMyqwMCBAznjjOQxH7169WLEiBE0NzcfZq9Dc0CYmVWZrVu3smrVKs4666x2teNTTGZmZbTq8eXs3NZS1jZ7D+7H6ZdPyLXtrl27mDZtGvfffz8nnHBCu77XPQgzsyqxZ88epk2bxpVXXsnUqVMPv8NhuAdhZlZGeX/pl1tEcP311zNixAhuvfXWw++Qg3sQZmZV4MUXX+TRRx9l2bJljBkzhjFjxrB48eLD73gI7kGYmVWB8847j4goa5vuQZiZWSYHhJmZZXJAmJlZJgeEmZllckCYmVkmB4SZmWVyQJiZVYHdu3czbtw4Pv/5zzNy5EjuvPPOdrfp+yDMzKrAsccey7Jly+jZsyd79uzhvPPOY9KkSYwfP/6I23QPwsysCkiiZ8+eQPJMpj179iCpXW06IMzMqkRraytjxoyhf//+XHTRRX7ct5lZZ/LEg0/RtLl9L+ppq274IKZ9bcpht+vatSurV69m586dTJkyhddee41Ro0Yd8fe6B2FmVmV69+7NhRdeyJIlS9rVjnsQZmZllOeXfhFaWlro3r07vXv35k9/+hNLly7lG9/4RrvadECYmVWB7du3c80119Da2srevXu5/PLLufjii9vVpgPCzKwKjB49mlWrVpW1TY9BmJlZJgeEmZllckCYmVkmB4SZmWVyQJiZWaZCA0LSREkbJW2WdHvG+iGSnpW0VtJySXUl606W9AtJGyStlzS0yFrNzOzjCgsISV2Bh4FJQD0wXVJ9m83uBeZGxGhgFnB3ybq5wL9ExAhgHPBOUbWamVWD1tZWTj/99Hbf/7DPYQNC0mfTX/mvpfOjJf1jjrbHAZsj4o2I+AswH7i0zTb1wLJ0+rl969Mg6RYRSwEiYldEfJDriMzMatQDDzzAiBEjytZenh7EvwF3AHsAImItcEWO/QYB20rmm9JlpdYAU9PpKUAvSX2AzwI7JT0paZWkf0l7JB8jaaakRkmNLS0tOUoyM6tOTU1NPP3003z1q18tW5t5AuK4iHi5zbIPy/T9twEXSFoFXAA0A60kd3h/IV1/JnAKMKPtzhExOyIaIqKhX79+ZSrJzOzoc8stt/Cd73yHLl3KN3KQ51Ebv5P0GSAAJH0Z2J5jv2ZgcMl8Xbpsv4h4i7QHIaknMC0idkpqAlZHxBvpup8A44FHcnyvmVnFfPufH2Tj+s1lbfO0+uF8486vHXT9okWL6N+/P2PHjmX58uVl+948AXEjMBv4nKRmYAtwZY79VgCnShpGEgxXAF8p3UBSX+DdiNhLchprTsm+vSX1i4gW4K+AxhzfaWZWc1588UUWLlzI4sWL2b17N3/4wx+46qqreOyxx9rVriLi4CuT8/7fjojbJB0PdImI93M3Lk0G7ge6AnMi4i5Js4DGiFiY9kbuJumdPA/cGBF/Tve9CLgPELASmJkOdmdqaGiIxkZniJl1vA0bNpR1cLg9li9fzr333suiRYsOWJdVp6SVEdGQ1dYhexAR0SrpvHT6j5+00IhYDCxus+yfSqYXAAsOsu9SYPQn/U4zMyuPPKeYVklaCPwY2B8SEfFkYVWZmdkRmTBhAhMmTChLW3kCogewg2QcYJ8AHBBmZlXssAEREdd2RCFmZta55LmTuk7SU5LeST9PlD4zyczMqlOeOyp+ACwEPp1+fpYuMzOz1KGuCO0MjqS+PAHRLyJ+EBEfpp8fAr5t2cws1aNHD3bs2NFpQyIi2LFjBz169PhE++UZpN4h6SpgXjo/nWTQ2szMgLq6OpqamujMz4Tr0aMHdXWfbHQgT0BcBzwI/G+Sq5d+BXjg2sws1b17d4YNG1bpMsouz1VMbwKXdEAtZmbWieS5iunfJfUumT9R0pxD7GJmZlUgzyD16IjYuW8mIt4DTi+sIjMz6xTyBEQXSSfum5F0EvnGLszM7CiW5x/6+4CXJP2Y5MmqXwbuKrQqMzOruDyD1HMlNfLRs5imRsT6YssyM7NKO2xApG+T+01ErJc0AfhrSW+VjkuYmVn1yTMG8QTQKmk48K8krxH9UaFVmZlZxeUZg9gbER9Kmgo8FBEPSlpVdGEdafq5V/P2e+9VugwzsyMy4MQTmffi3LK3m6cHsUfSdOBqYN877LqXvRIzM+tU8vQgrgX+K3BXRGyRNAx4tNiyOlYRyWtmdrTLcxXTeuDmkvktwLeLLMrMzCovzykmMzOrQQ4IMzPLlOdhfQe8YUJS32LKMTOzziJPD2KFpPH7ZiRNI3knhJmZVbE8VzF9BZgjaTnJO6n78NFjN8zMrErluYrpVUl3kVza+j5wfkQ0FV6ZmZlVVJ5nMT0CfAYYDXwWWCTpwYh4uOjizMyscvKMQbwKXBgRWyLiGeAs4IxiyzIzs0rLc4rp/jbzvweuL6ogMzPrHPKcYjoVuBuoB/Zf8hoRpxRYl5mZVVieU0w/AL4HfAhcCMwFHiuyKDMzq7w8AfGpiHgWUES8GRH/A/ibYssyM7NKyxMQf5bUBdgk6SZJU4CeeRqXNFHSRkmbJd2esX6IpGclrZW0XFJdm/UnSGqS9FCuozEzs7LJExBfB44jeaLrWODvgWsOt5OkrsDDwCSS8YvpkurbbHYvMDciRgOzSMY6Sn0LeD5HjWZmVmZ5rmJakU7uInk3RF7jgM0R8QaApPnApcD6km3qgVvT6eeAn+xbIWksMABYAjR8gu81M7MyyPOwvgZJT0l6JT0VtFbS2hxtDwK2lcw3pctKrQGmptNTgF6S+qSntO4DbsvxPWZmVoA8z2L6D+AfSG6Y21vm778NeEjSDJJTSc1AK3ADsDgimiQddGdJM4GZACeffHKZSzMzq215AqIlIhYeQdvNwOCS+bp02X4R8RZpD0JST2BaROyUdDbwBUk3kAyIHyNpV0Tc3mb/2cBsgIaGhjiCGs3M7CDyBMSdkr4PPAv8ed/CiHjyMPutAE5N32HdDFxB8mTY/dL3SrwbEXuBO4A5adtXlmwzA2hoGw5mZlasPAFxLfA5oDsfnWIK4JABEREfSroJeAboCsyJiHWSZgGNaa9kAnC3pCA5xXTjER2FmZmVnSIOfWZG0saIOK2D6jliDQ0N0djYWOkyzMyOKpJWRkTmlaJ57oP4Vcb9C2ZmVuXynGIaD6yWtIVkDEJApDe3mZlZlcoTEBMLr8LMzDqdPHdSv9kRhZiZWeeSZwzCzMxqkAPCzMwyOSDMzCyTA8LMzDI5IMzMLJMDwszMMjkgzMwskwPCzMwyOSDMzCyTA8LMzDI5IMzMLJMDwszMMjkgzMwskwPCzMwyOSDMzCyTA8LMzDI5IMzMLJMDwszMMjkgzMwskwPCzMwyOSDMzCyTA8LMzDI5IMzMLJMDwszMMjkgzMwskwPCzMwyOSDMzCyTA8LMzDI5IMzMLFOhASFpoqSNkjZLuj1j/RBJz0paK2m5pLp0+RhJL0lal677uyLrNDOzAxUWEJK6Ag8Dk4B6YLqk+jab3QvMjYjRwCzg7nT5B8DVETESmAjcL6l3UbWamdmBiuxBjAM2R8QbEfEXYD5waZtt6oFl6fRz+9ZHxOsRsSmdfgt4B+hXYK1mZtZGkQExCNhWMt+ULiu1BpiaTk8BeknqU7qBpHHAMcBvCqrTzMwyVHqQ+jbgAkmrgAuAZqB130pJA4FHgWsjYm/bnSXNlNQoqbGlpaWjajYzqwlFBkQzMLhkvi5dtl9EvBURUyPidOCb6bKdAJJOAJ4GvhkRv876goiYHRENEdHQr5/PQJmZlVORAbECOFXSMEnHAFcAC0s3kNRX0r4a7gDmpMuPAZ4iGcBeUGCNZmZ2EIUFRER8CNwEPANsAB6PiHWSZkm6JN1sArBR0uvAAOCudPnlwPnADEmr08+Yomo1M7MDKSIqXUNZNDQ0RGNjY6XLMDM7qkhaGRENWesqPUhtZmadlAPCzMwyOSDMzCyTA8LMzDI5IMzMLJMDwszMMjkgzMwskwPCzMwyOSDMzCyTA8LMzDI5IMzMLJMDwszMMjkgzMwskwPCzMwyOSDMzCyTA8LMzDI5IMzMLJMDwszMMjkgzMwskwPCzMwyOSDMzCyTA8LMzDI5IMzMLJMDwszMMjkgzMwskwPCzMwyOSDMzCyTA8LMzDI5IMzMLJMDwszMMjkgzMwskwPCzMwyFRoQkiZK2ihps6TbM9YPkfSspLWSlkuqK1l3jaRN6eeaIus0M7MDFRYQkroCDwOTgHpguqT6NpvdC8yNiNHALODudN+TgDuBs4BxwJ2STiyqVjMzO1CRPYhxwOaIeCMi/gLMBy5ts009sCydfq5k/ZeApRHxbkS8BywFJhZYq5mZtVFkQAwCtpXMN6XLSq0BpqbTU4Bekvrk3NfMzApU6UHq24ALJK0CLgCagda8O0uaKalRUmNLS0tRNZqZ1aQiA6IZGFwyX5cu2y8i3oqIqRFxOvDNdNnOPPum286OiIaIaOjXr1+Zyzczq21FBsQK4FRJwyQdA1wBLCzdQFJfSftquAOYk04/A3xR0onp4PQX02VmZtZBCguIiPgQuInkH/YNwOMRsU7SLEmXpJtNADZKeh0YANyV7vsu8C2SkFkBzEqXmZlZB1FEVLqGsmhoaIjGxsZKl2FmdlSRtDIiGrLWVXqQ2szMOikHhJmZZaqaU0ySWoA329FEX+B3ZSrnaFFrx1xrxws+5lrRnmMeEhGZl4FWTUC0l6TGg52Hq1a1dsy1drzgY64VRR2zTzGZmVkmB4SZmWVyQHxkdqULqIBaO+ZaO17wMdeKQo7ZYxBmZpbJPQgzM8tU8wFxuLfeVRtJcyS9I+m1StfSUSQNlvScpPWS1kn6eqVrKpqkHpJelrQmPeZ/rnRNHUFSV0mrJC2qdC0dRdJWSa9KWi2prI+TqOlTTOlb714HLiJ558QKYHpErK9oYQWSdD6wi+RNfqMqXU9HkDQQGBgRr0jqBawELqvy/88Cjo+IXZK6Ay8AX4+IX1e4tEJJuhVoAE6IiIsrXU9HkLQVaIiIst/7Ues9iDxvvasqEfE8UFMPPoyI7RHxSjr9PsnDI6v6BVSR2JXOdk8/Vf1rMH2n/d8A3690LdWi1gPCb66rMZKGAqcD/7fCpRQuPd2yGniH5BW+1X7M9wP/Ddhb4To6WgC/kLRS0sxyNlzrAWE1RFJP4Angloj4Q6XrKVpEtEbEGJIXbo2TVLWnFCVdDLwTESsrXUsFnBcRZwCTgBvT08hlUesBkevNdXb0S8/DPwH8R0Q8Wel6OlL6lsbngIkVLqVI5wKXpOfj5wN/JemxypbUMSKiOf3zHeApklPnZVHrAXHYt97Z0S8dsH0E2BAR/6vS9XQESf0k9U6nP0VyIcb/q2hRBYqIOyKiLiKGkvw9XhYRV1W4rMJJOj698AJJx5O8fbNsVyjWdEAc7K13la2qWJLmAS8Bp0lqknR9pWvqAOcCf0/yq3J1+plc6aIKNhB4TtJakh9CSyOiZi79rCEDgBckrQFeBp6OiCXlarymL3M1M7ODq+kehJmZHZwDwszMMjkgzMwskwPCzMwyOSDMzCyTA8KsE5B0i6TjSuYX77uPwaxSfJmrWQdIb9ZTRGQ+J6jIJ3KaHSn3IKymSfrv6ftAXpA0T9Jtkj4jaUn68LNfSvpcuu0PJX1X0q8kvSHpyyXt/IOkFZLW7nv3gqShadtzSe5uHSzpe5IaS9/RIOlm4NMkN7Y9ly7bKqlvOn2rpNfSzy0lbW+Q9G9pW79I75g2K5+I8MefmvwAZwKrgR5AL2ATcBvwLHBqus1ZJI9tAPgh8GOSH1b1JI+Kh+TxBrMBpesWAecDQ0meLDq+5DtPSv/sCiwHRqfzW4G+JdttBfoCY4FXgeOBnsA6kqfRDgU+BMak2z8OXFXp/6b+VNenW5lyxuxodC7w04jYDeyW9DOSsDgH+HFyVgiAY0v2+Ukkp4nWSxqQLvti+lmVzvcETgV+C7wZH39Jz+XpI5m7kTwOox5Ye4gazwOeiog/Akh6EvgCyTPDtkTE6nS7lSShYVY2Dgizj+sC7IzkMdlZ/lwyrZI/746Ify3dMH33xB9L5oeR9FDOjIj3JP2QJJCOVGktrYBPMVlZeQzCatmLwH9K39/cE7gY+ADYIulvIRlclvT5w7TzDHBd2gaSBknqn7HdCSSB8fu09zGpZN37JKe52volcJmk49KndU5Jl5kVzj0Iq1kRsULSQpJTPG+TnOv/PXAl8D1J/0jyqs75wJpDtPMLSSOAl9LTUruAq0h+1Zdut0bSKpLHbm8jCah9ZgNLJL0VEReW7PNK2tN4OV30/YhYlfZOzArly1ytpknqGRG70nsQngdmRvr+arNa5x6E1brZkupJxgL+3eFg9hH3IMzMLJMHqc3MLJMDwszMMjkgzMwskwPCzMwyOSDMzCyTA8LMzDL9f8xWWPudd8b6AAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "score_by_generation_lineplot(nia_search)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 85
    },
    "colab_type": "code",
    "id": "g9qTA5QzX69l",
    "outputId": "171692fe-668f-46c5-bc33-a0c813b5722f"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'n_estimators': 80,\n",
       " 'max_depth': 45,\n",
       " 'min_samples_split': 7,\n",
       " 'max_features': 'auto'}"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "nia_search.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 255
    },
    "colab_type": "code",
    "id": "akeXCPiGX69q",
    "outputId": "bf97c4fc-ad82-4a81-a68a-75fc03b2fca2"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0     1.0000    1.0000    1.0000        10\n",
      "           1     1.0000    1.0000    1.0000         9\n",
      "           2     1.0000    1.0000    1.0000        11\n",
      "\n",
      "    accuracy                         1.0000        30\n",
      "   macro avg     1.0000    1.0000    1.0000        30\n",
      "weighted avg     1.0000    1.0000    1.0000        30\n",
      "\n"
     ]
    }
   ],
   "source": [
    "clf = RandomForestClassifier(**nia_search.best_params_, random_state=42)\n",
    "\n",
    "clf.fit(X_train, y_train)\n",
    "\n",
    "y_pred = clf.predict(X_test)\n",
    "\n",
    "print(classification_report(y_test, y_pred, digits=4))"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Copy of hyper_parameter_tuning_nia_comparison.ipynb",
   "provenance": []
  },
  "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": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}