{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b24465d0",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import sklearn as sk"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "094df92b",
   "metadata": {},
   "outputs": [],
   "source": [
    "pingvinek = sns.load_dataset('penguins')\n",
    "pingvinek"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a4253344",
   "metadata": {},
   "outputs": [],
   "source": [
    "pingvinek = pingvinek[['species', 'bill_length_mm', 'bill_depth_mm', 'flipper_length_mm', 'body_mass_g']]\n",
    "pingvinek = pingvinek[\n",
    "    pingvinek['species'].notna() &\n",
    "    pingvinek['bill_length_mm'].notna() &\n",
    "    pingvinek['bill_depth_mm'].notna() &\n",
    "    pingvinek['flipper_length_mm'].notna() &\n",
    "    pingvinek['body_mass_g'].notna()\n",
    "]\n",
    "pingvinek"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c5dd2925",
   "metadata": {},
   "outputs": [],
   "source": [
    "pingvinek['species'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "238d9a13",
   "metadata": {},
   "outputs": [],
   "source": [
    "g = sns.pairplot(pingvinek, hue='species')\n",
    "g.map_lower(sns.kdeplot)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "dd1fab07",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "pingvinek_jellemzők = pingvinek.drop('species', axis=1)\n",
    "pingvinek_cél = pingvinek['species']\n",
    "(\n",
    "    pingvinek_jellemzők_tanuló, \n",
    "    pingvinek_jellemzők_teszt, \n",
    "    pingvinek_cél_tanuló, \n",
    "    pingvinek_cél_teszt,\n",
    ") = train_test_split(\n",
    "    pingvinek_jellemzők, \n",
    "    pingvinek_cél,\n",
    "    test_size=1/3,\n",
    "    random_state=12345,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "073c42a2",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "modell = KNeighborsClassifier()\n",
    "modell.fit(pingvinek_jellemzők_tanuló, pingvinek_cél_tanuló)\n",
    "pingvinek_cél_jósolt = modell.predict(pingvinek_jellemzők_teszt)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e6dbe94e",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn import metrics\n",
    "print(f'{100*metrics.accuracy_score(pingvinek_cél_teszt, pingvinek_cél_jósolt):.1f}%')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f5b38f79",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import confusion_matrix\n",
    "metrics.ConfusionMatrixDisplay(\n",
    "    confusion_matrix = confusion_matrix(pingvinek_cél_teszt, pingvinek_cél_jósolt), \n",
    "    display_labels = modell.classes_\n",
    ").plot()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "78c51a1f",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import StratifiedKFold\n",
    "from sklearn.model_selection import cross_val_score\n",
    "k_szoros = StratifiedKFold(n_splits=10, random_state=54321, shuffle=True)\n",
    "cross_val_score(modell, pingvinek_jellemzők, pingvinek_cél, cv=k_szoros, scoring='accuracy')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bfb5d58e",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "from sklearn.svm import SVC\n",
    "from sklearn.model_selection import StratifiedKFold\n",
    "from sklearn.model_selection import cross_val_score\n",
    "\n",
    "for név, modell in [\n",
    "    ('Logistic Regression', LogisticRegression(solver='liblinear')),\n",
    "    ('Linear Discriminant Analysis', LinearDiscriminantAnalysis()),\n",
    "    ('K-Neighbors Classifier', KNeighborsClassifier()),\n",
    "    ('Decision Tree Classifier', DecisionTreeClassifier()),\n",
    "    ('Gaussian Naive Bayes', GaussianNB()),\n",
    "    ('C-Support Vector Classification', SVC()),\n",
    "]:\n",
    "    k_szoros_ellenőrzés = StratifiedKFold(n_splits=10, random_state=11111, shuffle=True)\n",
    "    eredmények = cross_val_score(modell, pingvinek_jellemzők, pingvinek_cél, cv=k_szoros_ellenőrzés, scoring='accuracy')\n",
    "    print(f'{név}: {100*eredmények.mean():.2f}%')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "53925de3",
   "metadata": {},
   "outputs": [],
   "source": [
    "modell = LogisticRegression(solver='liblinear')\n",
    "modell.fit(pingvinek_jellemzők_tanuló, pingvinek_cél_tanuló)\n",
    "pingvinek_cél_jósolt = modell.predict(pingvinek_jellemzők_teszt)\n",
    "metrics.ConfusionMatrixDisplay(\n",
    "    confusion_matrix = confusion_matrix(pingvinek_cél_teszt, pingvinek_cél_jósolt), \n",
    "    display_labels = modell.classes_\n",
    ").plot()\n",
    "plt.show()"
   ]
  }
 ],
 "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": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}