diff --git a/class__11-Affinity Propagation Algorithm/Code/Affinity_Propagation.ipynb b/class__11-Affinity Propagation Algorithm/Code/Affinity_Propagation.ipynb
new file mode 100644
index 0000000..b77406a
--- /dev/null
+++ b/class__11-Affinity Propagation Algorithm/Code/Affinity_Propagation.ipynb	
@@ -0,0 +1,1045 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "cell_execution_strategy": "setup"
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": 127,
+      "metadata": {
+        "id": "pj-F8hmD3hIz"
+      },
+      "outputs": [],
+      "source": [
+        "from sklearn.datasets import make_blobs\n",
+        "from sklearn.cluster import AffinityPropagation"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df4, labels_true = make_blobs(n_samples=100, cluster_std = 1, random_state = 0)\n",
+        "df4\n"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "mdSR3L7l4RCc",
+        "outputId": "d82298f5-1659-4e03-e4f4-232a4f2b9e70"
+      },
+      "execution_count": 128,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "array([[ 2.63185834,  0.6893649 ],\n",
+              "       [ 0.08080352,  4.69068983],\n",
+              "       [ 3.00251949,  0.74265357],\n",
+              "       [-0.63762777,  4.09104705],\n",
+              "       [-0.07228289,  2.88376939],\n",
+              "       [ 0.62835793,  4.4601363 ],\n",
+              "       [-2.67437267,  2.48006222],\n",
+              "       [-0.57748321,  3.0054335 ],\n",
+              "       [ 2.72756228,  1.3051255 ],\n",
+              "       [ 0.34194798,  3.94104616],\n",
+              "       [ 1.70536064,  4.43277024],\n",
+              "       [ 2.20656076,  5.50616718],\n",
+              "       [ 2.52092996, -0.63858003],\n",
+              "       [ 2.50904929,  5.7731461 ],\n",
+              "       [-2.27165884,  2.09144372],\n",
+              "       [ 3.92282648,  1.80370832],\n",
+              "       [-1.62535654,  2.25440397],\n",
+              "       [ 0.1631238 ,  2.57750473],\n",
+              "       [-1.59514562,  4.63122498],\n",
+              "       [-2.63128735,  2.97004734],\n",
+              "       [-2.17052242,  0.69447911],\n",
+              "       [-1.56618683,  1.74978876],\n",
+              "       [-0.88677249,  1.30092622],\n",
+              "       [ 0.08848433,  2.32299086],\n",
+              "       [ 0.9845149 ,  1.95211539],\n",
+              "       [ 2.18217961,  1.29965302],\n",
+              "       [ 1.28535145,  1.43691285],\n",
+              "       [ 0.89011768,  1.79849015],\n",
+              "       [-1.89608585,  2.67850308],\n",
+              "       [-0.75511346,  3.74138642],\n",
+              "       [ 1.12031365,  5.75806083],\n",
+              "       [ 3.54351972,  2.79355284],\n",
+              "       [ 1.64164854,  0.15020885],\n",
+              "       [ 2.47034915,  4.09862906],\n",
+              "       [-1.98243652,  2.93536142],\n",
+              "       [ 0.85624076,  3.86236175],\n",
+              "       [ 0.87305123,  4.71438583],\n",
+              "       [ 1.38093486,  0.92949422],\n",
+              "       [ 2.41163392,  1.60423683],\n",
+              "       [-2.26646701,  4.46089686],\n",
+              "       [-0.40026809,  1.83795075],\n",
+              "       [ 2.45760916,  0.21285357],\n",
+              "       [ 2.3535057 ,  2.22404956],\n",
+              "       [-0.73000011,  6.25456272],\n",
+              "       [ 1.1312175 ,  4.68194985],\n",
+              "       [ 0.4666179 ,  3.86571303],\n",
+              "       [ 1.18447037,  0.318814  ],\n",
+              "       [ 1.36069966,  0.74802912],\n",
+              "       [-2.43972624,  4.03489855],\n",
+              "       [-1.00362735,  2.74633593],\n",
+              "       [ 0.63633194,  4.25441021],\n",
+              "       [ 1.41942144,  1.57409695],\n",
+              "       [ 0.06897171,  4.35573272],\n",
+              "       [ 2.2635425 ,  1.8743027 ],\n",
+              "       [-2.02493646,  4.84741432],\n",
+              "       [-0.6700734 ,  2.26685667],\n",
+              "       [ 3.23404709,  0.71773882],\n",
+              "       [ 2.06576754,  2.68353415],\n",
+              "       [ 1.0220286 ,  4.11660348],\n",
+              "       [ 3.93841822, -0.4500954 ],\n",
+              "       [ 0.78478252,  1.86706037],\n",
+              "       [-2.81976092,  3.18493313],\n",
+              "       [-2.33031368,  2.22833248],\n",
+              "       [-1.36023052,  3.5529137 ],\n",
+              "       [-3.01816161,  3.35727396],\n",
+              "       [ 1.65209057,  2.12010873],\n",
+              "       [ 1.7373078 ,  4.42546234],\n",
+              "       [-2.52711936,  1.37311116],\n",
+              "       [ 1.74371499,  0.953829  ],\n",
+              "       [ 1.9263585 ,  4.15243012],\n",
+              "       [-0.60604519,  3.23660991],\n",
+              "       [ 3.2460247 ,  2.84942165],\n",
+              "       [-1.57671974,  4.95740592],\n",
+              "       [ 3.97820955,  2.37817845],\n",
+              "       [ 1.19404184,  2.80772861],\n",
+              "       [ 2.11567076,  3.06896151],\n",
+              "       [ 1.15369622,  3.90200639],\n",
+              "       [ 0.30380963,  3.94423417],\n",
+              "       [-1.88089792,  1.54293097],\n",
+              "       [ 2.43169305, -0.20173713],\n",
+              "       [-0.27652528,  5.08127768],\n",
+              "       [ 1.0427873 ,  4.60625923],\n",
+              "       [ 1.78726415,  1.70012006],\n",
+              "       [-0.65392827,  4.76656958],\n",
+              "       [ 0.88214412,  2.84128485],\n",
+              "       [ 1.42013331,  4.63746165],\n",
+              "       [ 0.94808785,  4.7321192 ],\n",
+              "       [ 0.46546494,  3.12315514],\n",
+              "       [ 2.66934689,  1.81987033],\n",
+              "       [ 0.58894326,  4.00148458],\n",
+              "       [ 1.62011397,  2.74692739],\n",
+              "       [ 2.45127423, -0.19539785],\n",
+              "       [-0.42724442,  3.57314599],\n",
+              "       [-2.56114686,  3.59947678],\n",
+              "       [-2.84281142,  2.45629766],\n",
+              "       [-0.33887422,  3.23482487],\n",
+              "       [ 1.28933778,  3.44969159],\n",
+              "       [ 1.84070628,  3.56162231],\n",
+              "       [-0.90167256,  1.31582461],\n",
+              "       [-2.75233953,  3.76224524]])"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 128
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ef0f70bf"
+      },
+      "source": [
+        "### 🇧🇷\n",
+        "\n",
+        "Este bloco de código recupera um segredo armazenado nas configurações do usuário do Colab chamado 'secretNew'. Isso é útil para acessar chaves de API ou outras informações confidenciais sem expô-las diretamente no código.\n",
+        "\n",
+        "\n",
+        "---\n",
+        "\n",
+        "### 🇬🇧\n",
+        "\n",
+        "This code block retrieves a secret stored in Colab's user data settings named 'secretNew'. This is useful for accessing API keys or other sensitive information without exposing them directly in the code."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 35
+        },
+        "id": "9b4eb56a",
+        "outputId": "76ee3635-5a5d-455c-d74c-7bed0dae2d59"
+      },
+      "source": [
+        "from google.colab import userdata\n",
+        "userdata.get('secretNew')"
+      ],
+      "execution_count": 129,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "'AIzaSyA5pD1qYZkX7cf8OS0H1rpCLnPg9jP7a18'"
+            ],
+            "application/vnd.google.colaboratory.intrinsic+json": {
+              "type": "string"
+            }
+          },
+          "metadata": {},
+          "execution_count": 129
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "3e51a343"
+      },
+      "source": [
+        "from sklearn.datasets import make_blobs\n",
+        "from sklearn.cluster import AffinityPropagation"
+      ],
+      "execution_count": 130,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cdae6309"
+      },
+      "source": [
+        "### 🇧🇷\n",
+        "\n",
+        "Este bloco de código utiliza a função `make_blobs` para criar um conjunto de dados artificial para clustering.\n",
+        "- `n_samples=100`: Gera 100 pontos de dados.\n",
+        "- `cluster_std=1`: Define o desvio padrão dos clusters, controlando quão espalhados eles estão.\n",
+        "- `random_state=0`: Garante que os dados gerados sejam os mesmos cada vez que o código é executado.\n",
+        "A função retorna os dados gerados (`df4`) e os rótulos verdadeiros para cada ponto (`labels_true`).\n",
+        "\n",
+        "---\n",
+        "\n",
+        "### 🇬🇧\n",
+        "\n",
+        "\n",
+        "This code block uses the `make_blobs` function to create an artificial dataset for clustering.\n",
+        "- `n_samples=100`: Generates 100 data points.\n",
+        "- `cluster_std=1`: Sets the standard deviation of the clusters, controlling how spread out they are.\n",
+        "- `random_state=0`: Ensures that the generated data is the same each time the code is run.\n",
+        "The function returns the generated data (`df4`) and the true labels for each point (`labels_true`)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "fc3da753",
+        "outputId": "794cbf9d-036a-4d16-b1c2-2da9d6cd3b7e"
+      },
+      "source": [
+        "df4, labels_true = make_blobs(n_samples=500, cluster_std = 1, random_state = 0)\n",
+        "df4"
+      ],
+      "execution_count": 131,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "array([[ 1.10318217,  4.70577669],\n",
+              "       [-1.93284574,  3.64225077],\n",
+              "       [-2.03442161,  1.86600216],\n",
+              "       [ 1.6164016 ,  2.68683128],\n",
+              "       [-0.96000973,  4.49256592],\n",
+              "       [ 0.94808785,  4.7321192 ],\n",
+              "       [ 0.33265168,  2.08038418],\n",
+              "       [-1.32893672,  3.99981748],\n",
+              "       [-1.29885069,  3.11936221],\n",
+              "       [ 1.72345841,  3.11484237],\n",
+              "       [-2.42430494,  4.23035263],\n",
+              "       [-1.54176172,  3.7392882 ],\n",
+              "       [-2.3858764 ,  2.0189401 ],\n",
+              "       [-0.44552798,  2.28650627],\n",
+              "       [-0.33963733,  3.84220272],\n",
+              "       [ 0.85810603,  3.62360912],\n",
+              "       [ 2.99831361, -1.84201351],\n",
+              "       [ 3.13950603,  5.64031528],\n",
+              "       [-1.02885161,  2.89169002],\n",
+              "       [ 0.91464368,  4.19648205],\n",
+              "       [ 2.39417165,  2.91870722],\n",
+              "       [ 1.02533224,  0.5477203 ],\n",
+              "       [ 1.96933675,  1.0919566 ],\n",
+              "       [-2.31557327,  4.01252064],\n",
+              "       [ 1.35269561,  3.20438654],\n",
+              "       [-0.96289548,  1.63332996],\n",
+              "       [ 1.14650428,  0.47334604],\n",
+              "       [-0.5859864 ,  3.32308634],\n",
+              "       [ 0.10547293,  3.72493766],\n",
+              "       [-0.99796039,  3.16403005],\n",
+              "       [-0.80692028,  1.81497605],\n",
+              "       [ 2.20656076,  5.50616718],\n",
+              "       [ 0.06344785,  5.42080362],\n",
+              "       [-1.68290216,  4.91010685],\n",
+              "       [ 1.6706221 ,  0.45382757],\n",
+              "       [-0.03933555,  1.02138557],\n",
+              "       [ 2.03958541,  1.05859183],\n",
+              "       [ 3.15161437,  0.66344786],\n",
+              "       [ 1.50095789,  0.427026  ],\n",
+              "       [ 0.05105181,  1.27454018],\n",
+              "       [-2.31919068,  2.38627635],\n",
+              "       [ 1.40252881,  4.98069536],\n",
+              "       [ 3.35941485,  5.24826681],\n",
+              "       [ 3.15555186,  2.19568563],\n",
+              "       [ 3.23664612,  0.2657599 ],\n",
+              "       [ 0.47823763,  6.23331938],\n",
+              "       [ 1.69057398,  1.05436752],\n",
+              "       [ 1.66608824,  5.60563356],\n",
+              "       [-1.72530291,  3.01207456],\n",
+              "       [-2.70453298,  1.77768596],\n",
+              "       [ 0.4666179 ,  3.86571303],\n",
+              "       [ 1.83310069,  3.65276173],\n",
+              "       [ 0.340424  ,  4.98022062],\n",
+              "       [ 0.59139027,  4.39813892],\n",
+              "       [-2.19461673,  4.599804  ],\n",
+              "       [-2.04848369,  1.73319567],\n",
+              "       [ 0.72305587, -1.07096103],\n",
+              "       [ 1.36796848,  0.78018911],\n",
+              "       [ 1.42013331,  4.63746165],\n",
+              "       [ 0.58988701,  1.30700386],\n",
+              "       [ 3.5685956 ,  1.45079572],\n",
+              "       [-0.12555918,  2.50750047],\n",
+              "       [ 1.39671455,  0.38342969],\n",
+              "       [ 1.06975678, -0.57417135],\n",
+              "       [ 2.33954719,  2.64033244],\n",
+              "       [-3.16986931,  2.51181047],\n",
+              "       [ 1.37531642,  1.53119457],\n",
+              "       [ 1.78753398, -0.23034767],\n",
+              "       [ 0.06586674,  2.65930963],\n",
+              "       [ 0.52073758,  4.32126649],\n",
+              "       [-1.17408741,  2.76510784],\n",
+              "       [ 0.08080352,  4.69068983],\n",
+              "       [ 0.11504439,  6.21385228],\n",
+              "       [-2.18483011,  3.8867649 ],\n",
+              "       [ 4.75149157,  0.82373899],\n",
+              "       [-1.23017084,  3.74786842],\n",
+              "       [ 2.1047625 ,  1.39150044],\n",
+              "       [ 1.53774848, -0.0811662 ],\n",
+              "       [ 1.13726275,  1.15016029],\n",
+              "       [ 3.23557903,  4.26153018],\n",
+              "       [ 2.07592967,  4.95905106],\n",
+              "       [ 0.84032038,  5.44067869],\n",
+              "       [-1.94921884,  3.02259629],\n",
+              "       [ 0.34818252,  3.82276021],\n",
+              "       [-3.15932732,  2.85074811],\n",
+              "       [ 2.33570923, -0.09545995],\n",
+              "       [-2.3300454 ,  2.45354457],\n",
+              "       [-1.29951124,  1.90114361],\n",
+              "       [-0.51506158,  2.25993122],\n",
+              "       [-2.37948986,  2.94084202],\n",
+              "       [ 0.17286041,  3.61423755],\n",
+              "       [ 1.33263648,  5.0103605 ],\n",
+              "       [ 3.78798871,  1.58216477],\n",
+              "       [-0.56452694,  4.36704932],\n",
+              "       [-0.37271998,  3.09038668],\n",
+              "       [ 2.93110028,  0.78255619],\n",
+              "       [-1.48713728,  1.35088755],\n",
+              "       [-0.11573195,  3.70368609],\n",
+              "       [-0.15591501,  2.40803902],\n",
+              "       [ 0.03182382,  3.89373763],\n",
+              "       [ 3.7941402 ,  1.89205805],\n",
+              "       [-2.28477487,  2.86779817],\n",
+              "       [-3.12874006,  2.03070132],\n",
+              "       [ 1.0220286 ,  4.11660348],\n",
+              "       [ 0.29225918,  5.96333812],\n",
+              "       [ 0.03886089,  0.35820903],\n",
+              "       [ 1.1312175 ,  4.68194985],\n",
+              "       [ 3.52184624,  1.7502156 ],\n",
+              "       [ 1.66780883,  4.99853647],\n",
+              "       [ 1.79362208,  0.71541888],\n",
+              "       [ 0.4334086 ,  4.71983737],\n",
+              "       [ 0.57682105,  4.67384322],\n",
+              "       [ 0.77557835,  0.31223246],\n",
+              "       [-0.14164247,  2.61478401],\n",
+              "       [-1.83888012,  2.07759187],\n",
+              "       [ 1.36742991, -0.31641374],\n",
+              "       [-1.47532907,  3.78515889],\n",
+              "       [ 2.6225578 ,  0.67498856],\n",
+              "       [ 1.58523464,  0.68093219],\n",
+              "       [-0.91497682,  1.57638554],\n",
+              "       [-1.87315346,  2.12324594],\n",
+              "       [ 3.2460247 ,  2.84942165],\n",
+              "       [-0.03754805,  3.43918601],\n",
+              "       [-2.53373577,  4.59945898],\n",
+              "       [-2.02592065,  2.93923349],\n",
+              "       [ 1.37861172,  3.61897724],\n",
+              "       [-1.49630219,  2.84824068],\n",
+              "       [ 1.5001611 ,  4.39220941],\n",
+              "       [-0.20044237,  1.95327584],\n",
+              "       [ 0.70826671,  5.10624372],\n",
+              "       [ 1.92516057,  0.99161689],\n",
+              "       [ 1.76259804,  3.83736823],\n",
+              "       [-2.17408545,  3.39012941],\n",
+              "       [ 1.86461403,  0.50281415],\n",
+              "       [-0.21258918,  3.79697097],\n",
+              "       [ 2.73172825,  0.5156547 ],\n",
+              "       [-2.37522454,  2.59221279],\n",
+              "       [-2.46478424,  3.35099021],\n",
+              "       [ 1.37724174,  2.19550945],\n",
+              "       [ 0.87781755,  3.64030904],\n",
+              "       [ 2.46452227,  6.1996765 ],\n",
+              "       [-0.55436822,  5.05175051],\n",
+              "       [-2.44601746,  3.11063611],\n",
+              "       [ 2.69858199, -0.67295975],\n",
+              "       [ 1.60150153,  2.70172967],\n",
+              "       [ 0.06897171,  4.35573272],\n",
+              "       [ 0.28170222,  4.15415279],\n",
+              "       [ 2.34217201, -1.42293062],\n",
+              "       [ 1.92421351,  2.03074354],\n",
+              "       [ 0.81860306,  6.56051082],\n",
+              "       [ 2.00956356,  1.11817132],\n",
+              "       [ 0.5626511 ,  3.55633252],\n",
+              "       [-0.33025677,  5.96191801],\n",
+              "       [ 1.88644899,  4.62100554],\n",
+              "       [ 2.91319145,  2.03876553],\n",
+              "       [ 0.86572942,  5.32396004],\n",
+              "       [-0.20188996,  3.12321483],\n",
+              "       [ 0.60873282,  1.69796161],\n",
+              "       [-0.59045829,  2.88278708],\n",
+              "       [ 0.93698726,  3.13569383],\n",
+              "       [ 2.43799995,  0.86342138],\n",
+              "       [ 0.87610959,  2.19909173],\n",
+              "       [-1.91377486,  2.40758952],\n",
+              "       [-1.45231761,  1.84078319],\n",
+              "       [-1.53804963,  2.92938116],\n",
+              "       [ 2.92423101,  1.17453557],\n",
+              "       [ 0.30380963,  3.94423417],\n",
+              "       [ 2.59857941,  1.33670662],\n",
+              "       [-0.31658683,  4.5708382 ],\n",
+              "       [ 2.40704763,  1.27689919],\n",
+              "       [-1.16242276,  4.38920422],\n",
+              "       [-2.46588559,  3.93490325],\n",
+              "       [ 2.89689879,  0.64820508],\n",
+              "       [ 1.47001186,  4.18768339],\n",
+              "       [ 1.74806063,  5.12729148],\n",
+              "       [-0.77150832,  3.78528967],\n",
+              "       [-1.64167934,  3.2266335 ],\n",
+              "       [ 1.83100859,  0.59541393],\n",
+              "       [ 1.57561171,  1.51802196],\n",
+              "       [ 1.50955555, -0.98692219],\n",
+              "       [ 2.42609252,  1.03972547],\n",
+              "       [ 1.61434489,  0.61730816],\n",
+              "       [-1.58225656,  2.65394491],\n",
+              "       [-1.89195923,  1.12655471],\n",
+              "       [ 1.32622286,  1.09422106],\n",
+              "       [ 1.96488551,  2.2652609 ],\n",
+              "       [ 0.95924966,  4.68293906],\n",
+              "       [ 2.95052779,  2.27262773],\n",
+              "       [ 0.08848433,  2.32299086],\n",
+              "       [-2.29260621,  3.47366923],\n",
+              "       [-1.58549056,  2.60033917],\n",
+              "       [ 0.02032508,  3.95780555],\n",
+              "       [ 1.60146348,  1.3009282 ],\n",
+              "       [ 3.28013809,  0.96251977],\n",
+              "       [ 0.87305123,  4.71438583],\n",
+              "       [-2.45969305,  4.16120165],\n",
+              "       [ 1.98799191, -0.42073221],\n",
+              "       [-0.17119857,  3.86596728],\n",
+              "       [-1.01966506,  2.80165256],\n",
+              "       [ 1.58842198, -0.51924245],\n",
+              "       [-1.25130334,  4.35293165],\n",
+              "       [ 3.3744044 ,  0.01524484],\n",
+              "       [ 1.74952306,  3.11990669],\n",
+              "       [-0.06898329,  5.51493262],\n",
+              "       [-2.32632641,  3.15866977],\n",
+              "       [-0.20029671, -0.12484318],\n",
+              "       [ 0.7073421 ,  0.13609027],\n",
+              "       [-0.3089063 ,  0.91799784],\n",
+              "       [-3.21513404,  2.80541628],\n",
+              "       [-2.36458206,  2.32669916],\n",
+              "       [ 1.5528609 ,  4.09548857],\n",
+              "       [ 0.31291132, -0.40557909],\n",
+              "       [ 0.37404931,  0.0086923 ],\n",
+              "       [-1.58437353,  2.52666521],\n",
+              "       [-0.59649552,  2.74256586],\n",
+              "       [ 1.67004323,  4.14421389],\n",
+              "       [-2.34439711,  1.51653497],\n",
+              "       [ 2.89921211,  5.78430212],\n",
+              "       [-2.28901853,  2.03010212],\n",
+              "       [-0.85633356,  2.21037656],\n",
+              "       [ 2.25456772,  0.84706012],\n",
+              "       [-1.48177   ,  5.25750707],\n",
+              "       [ 1.81324769,  2.41592483],\n",
+              "       [ 1.66287852, -2.14847939],\n",
+              "       [ 2.84382904,  5.20983199],\n",
+              "       [ 2.12860164,  5.38340592],\n",
+              "       [ 0.62835793,  4.4601363 ],\n",
+              "       [ 3.08420301,  0.82537665],\n",
+              "       [-1.60157199,  3.1765987 ],\n",
+              "       [ 0.28422023,  5.84016438],\n",
+              "       [-0.18108518,  3.99149508],\n",
+              "       [-2.67451496,  2.55976819],\n",
+              "       [ 0.22808214,  2.78489384],\n",
+              "       [ 2.09389807, -0.75905144],\n",
+              "       [-1.51467203,  4.48714188],\n",
+              "       [-1.28732125,  2.5480811 ],\n",
+              "       [ 1.37227679,  3.21072582],\n",
+              "       [ 1.70183577, -0.71881053],\n",
+              "       [ 1.49733495,  3.72799936],\n",
+              "       [ 1.84070628,  3.56162231],\n",
+              "       [-0.19685333,  6.24740851],\n",
+              "       [ 2.06389542,  1.42466787],\n",
+              "       [ 1.40297392,  0.37647435],\n",
+              "       [ 1.83266184, -0.01541556],\n",
+              "       [ 1.92352205,  4.14877723],\n",
+              "       [-2.75352567,  3.88532841],\n",
+              "       [-1.12048852,  2.72470556],\n",
+              "       [-1.05647087,  3.22932933],\n",
+              "       [-1.50584199,  3.01733672],\n",
+              "       [-1.74938102,  2.05896235],\n",
+              "       [ 1.60710216,  0.24832573],\n",
+              "       [-2.23182537,  3.59785711],\n",
+              "       [-0.80380352,  2.94249439],\n",
+              "       [ 0.33883305,  3.90651551],\n",
+              "       [-0.71422997,  3.50514164],\n",
+              "       [-2.47439261,  3.16232572],\n",
+              "       [-0.29421492,  5.27318404],\n",
+              "       [ 2.51268313, -0.06694835],\n",
+              "       [-2.05939393,  3.56293753],\n",
+              "       [ 0.28672907,  1.25314545],\n",
+              "       [ 2.51839785,  1.17675942],\n",
+              "       [ 0.23151526,  3.47734879],\n",
+              "       [ 0.34194798,  3.94104616],\n",
+              "       [ 1.92335888,  1.30242547],\n",
+              "       [ 1.48595547,  1.16756801],\n",
+              "       [ 0.37895401,  4.0658656 ],\n",
+              "       [-0.26182618,  3.12937927],\n",
+              "       [ 3.70340245,  1.06189142],\n",
+              "       [-1.21857277,  1.53979879],\n",
+              "       [ 2.75372467,  0.90143455],\n",
+              "       [ 2.03184442,  1.97685839],\n",
+              "       [-2.97184421,  1.70733927],\n",
+              "       [ 2.64514734,  0.53380485],\n",
+              "       [ 1.11822324,  3.98445891],\n",
+              "       [-0.35798839,  2.95706982],\n",
+              "       [ 2.8219307 ,  1.25395648],\n",
+              "       [ 2.15504965,  4.12386249],\n",
+              "       [ 2.9871159 ,  1.23762864],\n",
+              "       [ 0.50483818,  1.31498248],\n",
+              "       [ 1.03722565,  0.8198089 ],\n",
+              "       [ 0.10956444, -0.01511983],\n",
+              "       [-3.02930058,  1.14021531],\n",
+              "       [ 3.57526238,  2.61725297],\n",
+              "       [ 0.60708824,  4.06440815],\n",
+              "       [ 2.102906  ,  3.22385582],\n",
+              "       [ 0.90802847,  6.01713005],\n",
+              "       [-0.60666832,  4.91416671],\n",
+              "       [-0.82752353,  1.85665997],\n",
+              "       [-1.62860129,  2.93716165],\n",
+              "       [-0.23335252,  1.14914807],\n",
+              "       [ 3.08967741, -0.09854898],\n",
+              "       [-1.95156732,  2.08791766],\n",
+              "       [-1.05000564,  3.06633184],\n",
+              "       [ 0.9867701 ,  6.08965782],\n",
+              "       [ 0.2506727 ,  2.92042337],\n",
+              "       [ 2.63378902,  1.24731812],\n",
+              "       [-2.27659436,  2.95069101],\n",
+              "       [ 1.70536064,  4.43277024],\n",
+              "       [-1.08587111,  3.09667513],\n",
+              "       [ 1.84836385,  1.77784257],\n",
+              "       [ 2.93218239,  4.69388065],\n",
+              "       [ 2.52143395,  0.52742122],\n",
+              "       [-0.59050547,  2.39224167],\n",
+              "       [ 3.34125153, -0.60933474],\n",
+              "       [-0.12811326,  4.35595241],\n",
+              "       [-1.15935912,  3.10819382],\n",
+              "       [-0.24916544,  5.1481503 ],\n",
+              "       [ 1.74615308,  0.664197  ],\n",
+              "       [ 1.59034945,  5.225994  ],\n",
+              "       [-1.30132235,  4.30702758],\n",
+              "       [ 0.83732901,  0.59270002],\n",
+              "       [-0.77116372,  2.37874962],\n",
+              "       [-1.56267209,  5.29862761],\n",
+              "       [ 2.50904929,  5.7731461 ],\n",
+              "       [-0.44779083,  3.81046744],\n",
+              "       [ 1.7373078 ,  4.42546234],\n",
+              "       [ 2.27911108,  1.22728664],\n",
+              "       [-2.05960681,  4.008632  ],\n",
+              "       [-1.80333686,  2.65830528],\n",
+              "       [ 0.25666569,  3.49079434],\n",
+              "       [ 0.95194395,  3.56575642],\n",
+              "       [ 1.68456352, -0.04795214],\n",
+              "       [ 0.48715614,  2.61111649],\n",
+              "       [ 1.45661358, -0.21823333],\n",
+              "       [ 1.12031365,  5.75806083],\n",
+              "       [-0.73000011,  6.25456272],\n",
+              "       [ 1.55245082,  3.31011734],\n",
+              "       [ 2.86978734,  0.95658925],\n",
+              "       [ 0.3238615 ,  3.91283395],\n",
+              "       [-2.03226233,  2.10209072],\n",
+              "       [ 2.99200998,  2.30999137],\n",
+              "       [ 2.85942078,  2.95602827],\n",
+              "       [ 1.12511102,  0.71907457],\n",
+              "       [-0.66338435,  2.11312852],\n",
+              "       [ 1.76343016,  0.13617145],\n",
+              "       [ 0.21219797,  0.41968966],\n",
+              "       [-0.17991235,  5.08498543],\n",
+              "       [-0.50511343,  2.36534159],\n",
+              "       [-0.07228289,  2.88376939],\n",
+              "       [-0.97094133,  3.81035615],\n",
+              "       [ 1.08416295,  1.21248086],\n",
+              "       [-1.23778351,  3.33075308],\n",
+              "       [ 2.98477263,  1.47988825],\n",
+              "       [ 1.44193252,  2.76754364],\n",
+              "       [ 1.07399505,  4.88674101],\n",
+              "       [ 1.25619468,  4.20563694],\n",
+              "       [ 1.00063906,  1.7179115 ],\n",
+              "       [ 0.30193742,  4.33561789],\n",
+              "       [-0.63762777,  4.09104705],\n",
+              "       [-2.88668474,  2.87648145],\n",
+              "       [ 1.616078  ,  1.07900209],\n",
+              "       [ 0.23670708,  5.84680192],\n",
+              "       [-3.35116067,  3.22148617],\n",
+              "       [-1.16739961,  2.77331544],\n",
+              "       [-1.88850329,  3.9824674 ],\n",
+              "       [ 2.47075462,  2.2338023 ],\n",
+              "       [ 3.18386159,  1.39366461],\n",
+              "       [ 1.2911236 , -0.54012781],\n",
+              "       [ 1.94477812, -0.76303615],\n",
+              "       [-1.29208249,  5.05003567],\n",
+              "       [ 0.37995604,  4.25122003],\n",
+              "       [ 2.29738548,  0.0089434 ],\n",
+              "       [-2.1946243 ,  3.24484486],\n",
+              "       [-0.65392827,  4.76656958],\n",
+              "       [ 0.5126741 ,  4.7852688 ],\n",
+              "       [ 1.13277662,  4.53596836],\n",
+              "       [ 0.81974302,  1.63872115],\n",
+              "       [ 2.16429987,  4.62072994],\n",
+              "       [-1.30739446,  3.3109452 ],\n",
+              "       [ 1.92569089,  4.39133857],\n",
+              "       [-1.46700933,  2.70535922],\n",
+              "       [-2.94882388,  4.91583834],\n",
+              "       [ 2.47034915,  4.09862906],\n",
+              "       [-2.06217418,  2.94328747],\n",
+              "       [-1.7682418 ,  2.03969192],\n",
+              "       [-0.10392052,  3.31396885],\n",
+              "       [-1.2020344 ,  3.91500024],\n",
+              "       [ 1.83572649, -0.18637296],\n",
+              "       [ 1.6801204 , -0.32853253],\n",
+              "       [-1.6312475 ,  1.92988032],\n",
+              "       [ 2.09227324,  1.66556607],\n",
+              "       [-1.04578889,  5.67723738],\n",
+              "       [-2.02300635,  2.84307728],\n",
+              "       [-1.1968689 ,  5.14382659],\n",
+              "       [-1.8924551 ,  3.8559748 ],\n",
+              "       [ 1.64265316,  3.84306754],\n",
+              "       [ 0.84256852,  5.38153113],\n",
+              "       [ 0.1631238 ,  2.57750473],\n",
+              "       [ 2.91786353, -1.75795543],\n",
+              "       [-0.83647499,  3.71455437],\n",
+              "       [ 0.16290582,  2.837363  ],\n",
+              "       [ 0.3571617 ,  1.28494414],\n",
+              "       [ 1.64856484,  4.71124916],\n",
+              "       [ 2.85583232,  0.97592384],\n",
+              "       [ 0.54111653,  6.15305106],\n",
+              "       [ 2.5539578 ,  1.94563582],\n",
+              "       [-1.5165547 ,  3.63791602],\n",
+              "       [-2.82559074,  4.19395761],\n",
+              "       [ 1.28933778,  3.44969159],\n",
+              "       [ 1.06752057,  2.51384997],\n",
+              "       [ 2.28087618,  1.34737576],\n",
+              "       [ 0.62227617,  2.92883603],\n",
+              "       [ 1.87021385,  0.09001517],\n",
+              "       [-0.49646575,  0.87055865],\n",
+              "       [-2.22323067,  2.62748516],\n",
+              "       [ 2.11567076,  3.06896151],\n",
+              "       [ 3.12377692,  0.44427786],\n",
+              "       [-4.10970065,  1.7639319 ],\n",
+              "       [ 2.21919609,  0.99398502],\n",
+              "       [-0.19912132,  2.81660078],\n",
+              "       [-0.05797276,  4.98538185],\n",
+              "       [-0.7796205 ,  4.75472179],\n",
+              "       [-1.57671974,  4.95740592],\n",
+              "       [ 1.66003854, -0.26175686],\n",
+              "       [ 0.97029638,  0.67256061],\n",
+              "       [ 0.2715698 ,  5.24704805],\n",
+              "       [-0.18887976,  5.20461381],\n",
+              "       [ 1.70781687,  0.31639518],\n",
+              "       [-2.55954712,  2.48113392],\n",
+              "       [-0.75420918,  1.25628397],\n",
+              "       [ 0.66538391,  4.40118749],\n",
+              "       [-1.97820705,  3.18357024],\n",
+              "       [ 3.41979937,  0.20821448],\n",
+              "       [ 1.0427873 ,  4.60625923],\n",
+              "       [-2.18336769,  0.08332776],\n",
+              "       [ 0.8433895 ,  4.00599645],\n",
+              "       [ 2.23860672,  2.56860669],\n",
+              "       [-0.15055573,  3.57310957],\n",
+              "       [-2.897664  ,  3.78353518],\n",
+              "       [ 0.57309313,  5.5262324 ],\n",
+              "       [ 1.27450825,  5.63017322],\n",
+              "       [ 1.12252661, -0.36540469],\n",
+              "       [ 1.25078644,  3.41287224],\n",
+              "       [ 1.26261377,  4.91263116],\n",
+              "       [ 1.15369622,  3.90200639],\n",
+              "       [ 0.206354  ,  4.84303652],\n",
+              "       [ 1.85237068,  0.78778088],\n",
+              "       [ 1.8971289 ,  4.62251498],\n",
+              "       [ 0.422633  , -0.67010406],\n",
+              "       [-2.38345332,  1.37629486],\n",
+              "       [ 1.58640333, -1.30377763],\n",
+              "       [-0.31431938,  1.76171596],\n",
+              "       [-1.05441439,  6.36828019],\n",
+              "       [-1.47594974,  1.12365299],\n",
+              "       [ 2.99773564,  0.63006891],\n",
+              "       [-1.19632726,  3.86712873],\n",
+              "       [ 2.41002521,  1.51455021],\n",
+              "       [-1.87486587,  1.5644934 ],\n",
+              "       [ 2.17041539,  0.5185161 ],\n",
+              "       [ 1.14294357,  4.93881876],\n",
+              "       [-1.25573383,  2.11638538],\n",
+              "       [ 4.0665242 ,  0.85306823],\n",
+              "       [ 2.25033722, -0.8838992 ],\n",
+              "       [ 1.45460996,  2.44990684],\n",
+              "       [ 0.91546507,  1.68262118],\n",
+              "       [ 1.83831795,  1.34305691],\n",
+              "       [ 0.46546494,  3.12315514],\n",
+              "       [-1.05851878,  4.65376126],\n",
+              "       [ 2.87685323,  0.90295631],\n",
+              "       [-1.34297852,  2.5323925 ],\n",
+              "       [ 0.93409863,  4.01690014],\n",
+              "       [ 1.18454506,  5.28042636],\n",
+              "       [ 1.09476314,  0.1045463 ],\n",
+              "       [-1.07870873,  4.61406383],\n",
+              "       [-2.9886367 ,  2.23444249],\n",
+              "       [-0.02394527,  2.75901623],\n",
+              "       [-1.67048352,  2.53585681],\n",
+              "       [ 3.13346483, -1.66152101],\n",
+              "       [ 0.66725711,  2.62778352],\n",
+              "       [-0.27652528,  5.08127768],\n",
+              "       [ 2.37242815,  1.41770427],\n",
+              "       [ 0.64930461,  0.30760601],\n",
+              "       [ 0.32268723,  2.70371561],\n",
+              "       [ 1.9991345 ,  0.89627862],\n",
+              "       [-2.11830668,  4.04230145],\n",
+              "       [ 2.26874757, -0.31090999],\n",
+              "       [ 1.77959699,  0.18793569],\n",
+              "       [-0.18433654,  1.29916272],\n",
+              "       [ 2.50904943, -0.93207675],\n",
+              "       [-0.56621061,  4.24694511],\n",
+              "       [ 0.58894326,  4.00148458],\n",
+              "       [ 1.24964101, -0.22064826],\n",
+              "       [ 0.10346342,  0.23777193],\n",
+              "       [-0.51498751,  4.74317903],\n",
+              "       [ 1.27263837,  0.78727436],\n",
+              "       [-0.99785877,  3.34051088],\n",
+              "       [-1.16105523,  4.21570753],\n",
+              "       [ 1.9263585 ,  4.15243012],\n",
+              "       [ 1.3952112 ,  1.07348261],\n",
+              "       [ 1.11089903,  1.13576681],\n",
+              "       [-1.93320714,  2.05383727],\n",
+              "       [ 1.49954674,  4.132241  ],\n",
+              "       [-2.37863321,  4.74060586],\n",
+              "       [ 0.66471755,  4.35995267],\n",
+              "       [ 3.28018678,  3.2437715 ],\n",
+              "       [ 2.66038761,  1.79321965],\n",
+              "       [ 2.87558932,  2.2576122 ],\n",
+              "       [ 2.82667347,  1.92710249],\n",
+              "       [-0.09448254,  5.35823905],\n",
+              "       [ 2.50775661,  0.99555981]])"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 131
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "4c032fef"
+      },
+      "source": [
+        "### 🇧🇷\n",
+        "\n",
+        "Este bloco de código utiliza a função `make_blobs` para criar um conjunto de dados artificial para clustering.\n",
+        "- `n_samples=100`: Gera 100 pontos de dados.\n",
+        "- `cluster_std=1`: Define o desvio padrão dos clusters, controlando quão espalhados eles estão.\n",
+        "- `random_state=0`: Garante que os dados gerados sejam os mesmos cada vez que o código é executado.\n",
+        "A função retorna os dados gerados (`df4`) e os rótulos verdadeiros para cada ponto (`labels_true`).\n",
+        "\n",
+        "* * *\n",
+        "\n",
+        "### 🇬🇧\n",
+        "\n",
+        "This code block uses the `make_blobs` function to create an artificial dataset for clustering.\n",
+        "- `n_samples=100`: Generates 100 data points.\n",
+        "- `cluster_std=1`: Sets the standard deviation of the clusters, controlling how spread out they are.\n",
+        "- `random_state=0`: Ensures that the generated data is the same each time the code is run.\n",
+        "The function returns the generated data (`df4`) and the true labels for each point (`labels_true`)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "\"\"\"\n",
+        "Este bloco de código aplica o algoritmo Affinity Propagation aos dados gerados.\n",
+        "- `preference=-30`: Define o parâmetro de preferência, que influencia o número de clusters encontrados. Valores menores levam a menos clusters.\n",
+        "- `.fit(df4)`: Executa o algoritmo de clustering nos dados armazenados em `df4`.\n",
+        "\n",
+        "As variáveis `cluster_centers_indices` e `labels` são armazenadas para uso posterior.\n",
+        "\n",
+        "This code block applies the Affinity Propagation algorithm to the generated data.\n",
+        "- `preference=-30`: Sets the preference parameter, which influences the number of clusters found. Lower values lead to fewer clusters.\n",
+        "- `.fit(df4)`: Executes the clustering algorithm on the data stored in `df4`.\n",
+        "\n",
+        "The variables `cluster_centers_indices` and `labels` are stored for later use.\n",
+        "\"\"\"\n",
+        "af = AffinityPropagation (preference = -30, random_state = 0). fit(df4)\n",
+        "cluster_centers_indices = af.cluster_centers_indices_\n",
+        "labels = af.labels_"
+      ],
+      "metadata": {
+        "id": "eev4QeZi38Wt"
+      },
+      "execution_count": 132,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "\"\"\"\n",
+        "Este bloco de código avalia o desempenho do clustering usando várias métricas do scikit-learn.\n",
+        "- `n_clusters_`: Calcula o número estimado de clusters encontrados.\n",
+        "- `mt.homogeneity_score`, `mt.completeness_score`, `mt.v_measure_score`, `mt.adjusted_rand_score`, `mt.adjusted_mutual_info_score`: Calculam diferentes métricas que comparam os rótulos do cluster encontrados com os rótulos verdadeiros.\n",
+        "- `mt.silhouette_score`: Calcula o coeficiente de silhueta, que mede quão bem cada ponto de dados se encaixa em seu próprio cluster em comparação com outros clusters.\n",
+        "\n",
+        "This code block evaluates the clustering performance using various scikit-learn metrics.\n",
+        "- `n_clusters_`: Calculates the estimated number of clusters found.\n",
+        "- `mt.homogeneity_score`, `mt.completeness_score`, `mt.v_measure_score`, `mt.adjusted_rand_score`, `mt.adjusted_mutual_info_score`: Calculate different metrics that compare the found cluster labels with the true labels.\n",
+        "- `mt.silhouette_score`: Calculates the silhouette coefficient, which measures how well each data point fits into its own cluster compared to other clusters.\n",
+        "\"\"\"\n",
+        "import sklearn.metrics as mt\n",
+        "n_clusters_ = len(cluster_centers_indices)\n",
+        "print (\"Número estimado de clusters: %d\" % n_clusters_)\n",
+        "print (\"Homogeneidade: %0.3f\" % mt.homogeneity_score(labels_true, labels))\n",
+        "print (\"Completude: %0.3f\" % mt.completeness_score(labels_true, labels))\n",
+        "print (\"Medida-V: %0.3f\" % mt.v_measure_score(labels_true, labels))\n",
+        "print(\"Índice Rand Ajustado: %0.3f\" % mt.adjusted_rand_score(labels_true, labels))\n",
+        "print (\"Informação Mútua Ajustada: %0.3f\" % mt.adjusted_mutual_info_score(labels_true, labels))\n",
+        "print (\"Coeficiente de Silhueta: %0.3f\" % mt.silhouette_score(df4, labels, metric=\"sqeuclidean\"))"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "i_5lfTUM4Vtm",
+        "outputId": "4d6e77d0-1989-4a5e-a1f2-f7e00f274428"
+      },
+      "execution_count": 133,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Número estimado de clusters: 12\n",
+            "Homogeneidade: 0.782\n",
+            "Completude: 0.354\n",
+            "Medida-V: 0.488\n",
+            "Índice Rand Ajustado: 0.267\n",
+            "Informação Mútua Ajustada: 0.481\n",
+            "Coeficiente de Silhueta: 0.482\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "\"\"\"\n",
+        "Este bloco de código configura o ambiente de plotagem usando Matplotlib.\n",
+        "- `import matplotlib.pyplot as plt`: Importa a biblioteca Matplotlib para criação de gráficos.\n",
+        "- `plt.style.use('seaborn-v0_8-darkgrid')`: Aplica um estilo de gráfico com grade escura.\n",
+        "- `plt.close(\"all\")`: Fecha todas as figuras de plotagem abertas anteriormente.\n",
+        "- `plt.figure(1)`: Cria uma nova figura.\n",
+        "- `plt.clf()`: Limpa a figura atual.\n",
+        "\n",
+        "This code block sets up the plotting environment using Matplotlib.\n",
+        "- `import matplotlib.pyplot as plt`: Imports the Matplotlib library for creating plots.\n",
+        "- `plt.style.use('seaborn-v0_8-darkgrid')`: Applies a dark grid plot style.\n",
+        "- `plt.close(\"all\")`: Closes all previously opened plot figures.\n",
+        "- `plt.figure(1)`: Creates a new figure.\n",
+        "- `plt.clf()`: Clears the current figure.\n",
+        "\"\"\"\n",
+        "import matplotlib.pyplot as plt\n",
+        "\n",
+        "plt.style.use('seaborn-v0_8-darkgrid') # Use a dark grid style\n",
+        "plt.close(\"all\")\n",
+        "plt.figure(1)\n",
+        "plt.clf()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 34
+        },
+        "id": "FG8jStv66RTX",
+        "outputId": "c5c5ba31-4b6b-496f-e3ad-f46a01d581c3"
+      },
+      "execution_count": 134,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 0 Axes>"
+            ]
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "\"\"\"\n",
+        "Este bloco de código define um esquema de cores aproximado de \"hexachrome\" para uso na plotagem.\n",
+        "- `hexachrome_colors`: Uma lista de códigos hexadecimais que representam cores que se assemelham a um esquema hexachrome.\n",
+        "- `plt.cycler(color=hexachrome_colors)`: Cria um ciclo de cores a partir da lista definida, que será usado para colorir os diferentes clusters no gráfico.\n",
+        "\n",
+        "This code block defines an approximate \"hexachrome\" color scheme for use in plotting.\n",
+        "- `hexachrome_colors`: A list of hexadecimal codes representing colors that resemble a hexachrome scheme.\n",
+        "- `plt.cycler(color=hexachrome_colors)`: Creates a color cycle from the defined list, which will be used to color the different clusters in the plot.\n",
+        "\"\"\"\n",
+        "# Approximate hexachrome colors\n",
+        "hexachrome_colors = [\n",
+        "    '#000000',  # Black\n",
+        "    '#FFFFFF',  # White\n",
+        "    '#FF0000',  # Red\n",
+        "    '#00FF00',  # Green\n",
+        "    '#0000FF',  # Blue\n",
+        "    '#FFFF00',  # Yellow\n",
+        "]\n",
+        "colors = plt.cycler(color=hexachrome_colors)"
+      ],
+      "metadata": {
+        "id": "o3-BtzNu6ull"
+      },
+      "execution_count": 135,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "\"\"\"\n",
+        "Este bloco de código gera o gráfico de dispersão dos clusters e seus centros, conectando cada ponto de dados ao centro do seu cluster.\n",
+        "- O loop itera sobre cada cluster (`k`) e sua cor correspondente (`col`).\n",
+        "- `class_members`: Seleciona os pontos de dados que pertencem ao cluster atual.\n",
+        "- `cluster_center`: Obtém as coordenadas do centro do cluster atual.\n",
+        "- `plt.scatter(df4[class_members, 0], df4[class_members, 1], ...)`: Plota os pontos de dados do cluster.\n",
+        "- `plt.scatter(cluster_center[0], cluster_center[1], ...)`: Plota o centro do cluster.\n",
+        "- O loop interno itera sobre cada ponto de dados no cluster e plota uma linha conectando-o ao centro do cluster.\n",
+        "\n",
+        "This code block generates the scatter plot of the clusters and their centers, connecting each data point to its cluster center.\n",
+        "- The loop iterates through each cluster (`k`) and its corresponding color (`col`).\n",
+        "- `class_members`: Selects the data points that belong to the current cluster.\n",
+        "- `cluster_center`: Gets the coordinates of the current cluster center.\n",
+        "- `plt.scatter(df4[class_members, 0], df4[class_members, 1], ...)`: Plots the data points for the cluster.\n",
+        "- `plt.scatter(cluster_center[0], cluster_center[1], ...)`: Plots the cluster center.\n",
+        "- The inner loop iterates through each data point in the cluster and plots a line connecting it to the cluster center.\n",
+        "\"\"\"\n",
+        "for k, col in zip(range(n_clusters_), colors):\n",
+        "    class_members = labels == k\n",
+        "    cluster_center = df4[cluster_centers_indices[k]]\n",
+        "    plt.scatter(\n",
+        "        df4[class_members, 0], df4[class_members, 1], color=col[\"color\"], marker=\".\"\n",
+        "    )\n",
+        "    plt.scatter(\n",
+        "        cluster_center[0], cluster_center[1], s=14, color=col[\"color\"], marker=\"o\"\n",
+        "    )\n",
+        "    for x in df4[class_members]:\n",
+        "        plt.plot(\n",
+        "            [cluster_center[0], x[0]], [cluster_center[1], x[1]], color=col[\"color\"]\n",
+        "        )"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 425
+        },
+        "id": "PIh5BeqZ63Us",
+        "outputId": "a692b198-13c6-46da-dd06-3ddc3096cc0c"
+      },
+      "execution_count": 136,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "Preference = [-200, -150, -100, -50, -10, 0]\n",
+        "silhouette_scores = []\n",
+        "for preference in Preference:\n",
+        "    # Added max_iter and damping to help with convergence\n",
+        "    model = AffinityPropagation(preference=preference, random_state=42, max_iter=10000, damping=0.9)\n",
+        "    model.fit(df4)\n",
+        "    # Evaluate only if more than one cluster is found\n",
+        "    if len(np.unique(model.labels_)) > 1 and len(np.unique(model.labels_)) < len(df4):\n",
+        "        score = mt.silhouette_score(df4, model.labels_)\n",
+        "        silhouette_scores.append(score)\n",
+        "    else:\n",
+        "        silhouette_scores.append(np.nan)\n",
+        "\n",
+        "plt.plot(Preference, silhouette_scores, marker='o')\n",
+        "plt.title('Preference vs Silhouette Score')\n",
+        "plt.xlabel('Preference')\n",
+        "plt.ylabel('Silhouette Score')\n",
+        "plt.grid()\n",
+        "plt.show()"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 465
+        },
+        "id": "8Uc1bc0c-r_C",
+        "outputId": "3cf83b8e-ebdb-440d-f7ad-532fce5dc07b"
+      },
+      "execution_count": 137,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<Figure size 640x480 with 1 Axes>"
+            ],
+            "image/png": "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\n"
+          },
+          "metadata": {}
+        }
+      ]
+    }
+  ]
+}
\ No newline at end of file
diff --git a/class__11-Affinity Propagation Algorithm/IMG_4558.JPG b/class__11-Affinity Propagation Algorithm/IMG_4558.JPG
new file mode 100644
index 0000000..09e70e0
Binary files /dev/null and b/class__11-Affinity Propagation Algorithm/IMG_4558.JPG differ