{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a706a220",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "from matplotlib import pyplot as plt\n",
    "from sklearn.cluster import KMeans"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "94b5261d",
   "metadata": {},
   "outputs": [],
   "source": [
    "file='Pizza.csv'\n",
    "df=pd.read_csv(file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "97efa4e7",
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.scatter(df['fat'], df['ash'])\n",
    "plt.title('Pizzas')\n",
    "plt.xlabel('queimadas')\n",
    "plt.ylabel('gordas')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7790593f",
   "metadata": {},
   "outputs": [],
   "source": [
    "df1=df[['fat','ash']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7361d5a9",
   "metadata": {},
   "outputs": [],
   "source": [
    "wcss = []\n",
    "for i in range(1, 11):\n",
    "    model = KMeans(n_clusters=i, init='k-means++', max_iter=300, n_init=10, random_state=0)\n",
    "    model.fit(df1)\n",
    "    wcss.append(model.inertia_)\n",
    "plt.plot(range(1, 11), wcss)\n",
    "plt.title('Elbow Method')\n",
    "plt.xlabel('Number of clusters')\n",
    "plt.ylabel('WCSS')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "eae22195",
   "metadata": {},
   "outputs": [],
   "source": [
    "model1 = KMeans(n_clusters=3, init='k-means++', max_iter=400, n_init=10, random_state=0)\n",
    "model1.fit(df1)\n",
    "plt.scatter(df1[\"fat\"], df1[\"ash\"])\n",
    "plt.scatter(model1.cluster_centers_[:, 0], model1.cluster_centers_[:, 1], s=300, c='red')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6751d41b",
   "metadata": {},
   "outputs": [],
   "source": [
    "model1.predict(df1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "eb0009ff",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['group']=model1.predict(df1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a98e9fdb",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import silhouette_score\n",
    "score = silhouette_score(df1, model1.predict(df1), metric='euclidean')\n",
    "score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "427be794",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a01a598d",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}