{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "## **Implementing Agglomerative Hierarchical Clustering**"
      ],
      "metadata": {
        "id": "ELerDrAkAZlq"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "import pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "from sklearn.datasets import load_digits\n",
        "from sklearn.preprocessing import StandardScaler\n",
        "from sklearn.cluster import AgglomerativeClustering\n",
        "from sklearn.metrics import silhouette_score\n",
        "from scipy.cluster.hierarchy import dendrogram, linkage"
      ],
      "metadata": {
        "id": "2YV9k59VAX8f"
      },
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "digits = load_digits()\n",
        "X = digits.data\n"
      ],
      "metadata": {
        "id": "MHk6eEIaOXmH"
      },
      "execution_count": 4,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "scaler = StandardScaler()\n",
        "X_scaled = scaler.fit_transform(X)\n"
      ],
      "metadata": {
        "id": "VKAwR4crOXou"
      },
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "linked = linkage(X_scaled, method='ward')\n",
        "\n",
        "plt.figure(figsize=(12, 6))\n",
        "dendrogram(\n",
        "    linked,\n",
        "    truncate_mode='lastp',\n",
        "    p=30\n",
        ")\n",
        "plt.title(\"Hierarchical Clustering Dendrogram\")\n",
        "plt.xlabel(\"Cluster Size\")\n",
        "plt.ylabel(\"Distance\")\n",
        "plt.show()\n",
        "\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 587
        },
        "id": "1e2VjKCYOXrP",
        "outputId": "534d316c-8fa3-4261-9de1-b144250a655a"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1200x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "hc_model = AgglomerativeClustering(\n",
        "    n_clusters=10,\n",
        "    linkage='ward'\n",
        ")\n"
      ],
      "metadata": {
        "id": "D3j3NqBNOXtX"
      },
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "cluster_labels = hc_model.fit_predict(X_scaled)\n"
      ],
      "metadata": {
        "id": "Qbe_HCybOXvw"
      },
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "pd.Series(cluster_labels).value_counts()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 398
        },
        "id": "0p5tiARoOXyH",
        "outputId": "ae2cdaf8-a676-487e-d0ee-abe34d8b275b"
      },
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1    388\n",
              "4    319\n",
              "3    195\n",
              "6    182\n",
              "5    178\n",
              "0    175\n",
              "8    167\n",
              "9    151\n",
              "7     40\n",
              "2      2\n",
              "Name: count, dtype: int64"
            ],
            "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>count</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>388</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>319</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>195</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>182</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>178</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>175</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>8</th>\n",
              "      <td>167</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9</th>\n",
              "      <td>151</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>40</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div><br><label><b>dtype:</b> int64</label>"
            ]
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "sil_score = silhouette_score(X_scaled, cluster_labels)\n",
        "print(\"Score :\", round(sil_score, 2))\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "bGNjH_ykS9hQ",
        "outputId": "337c8e0a-766d-4ed4-aa0a-38d1b256a444"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Score : 0.13\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## **Implementing Divisive Hierarchical Clustering**"
      ],
      "metadata": {
        "id": "Y-AHF-MKAt6u"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.datasets import load_digits\n",
        "from sklearn.preprocessing import StandardScaler\n",
        "from sklearn.cluster import KMeans\n",
        "from sklearn.metrics import silhouette_score\n",
        "import numpy as np"
      ],
      "metadata": {
        "id": "zFPYmkRqS9j9"
      },
      "execution_count": 11,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "digits = load_digits()\n",
        "X = digits.data"
      ],
      "metadata": {
        "id": "Oqs7jYedS9mb"
      },
      "execution_count": 12,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "scaler = StandardScaler()\n",
        "X_scaled = scaler.fit_transform(X)"
      ],
      "metadata": {
        "id": "wmckC3ZxA2iQ"
      },
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.cluster import KMeans\n",
        "\n",
        "def divisive_clustering(X, depth=0, max_depth=3, min_size=50):\n",
        "\n",
        "    if depth == max_depth or len(X) <= min_size:\n",
        "        return [X]\n",
        "\n",
        "\n",
        "    kmeans = KMeans(n_clusters=2, random_state=42)\n",
        "    labels = kmeans.fit_predict(X)\n",
        "\n",
        "    cluster_1 = X[labels == 0]\n",
        "    cluster_2 = X[labels == 1]\n",
        "\n",
        "\n",
        "    return (\n",
        "        divisive_clustering(cluster_1, depth + 1, max_depth, min_size) +\n",
        "        divisive_clustering(cluster_2, depth + 1, max_depth, min_size)\n",
        "    )\n"
      ],
      "metadata": {
        "id": "YRLDayqOA2lH"
      },
      "execution_count": 14,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "final_clusters = divisive_clustering(\n",
        "    X_scaled,\n",
        "    max_depth=4,\n",
        "    min_size=50\n",
        ")"
      ],
      "metadata": {
        "id": "W78bk7UFA2oo"
      },
      "execution_count": 15,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "cluster_sizes = [len(cluster) for cluster in final_clusters]\n",
        "cluster_sizes"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5qeKfWeSB8-h",
        "outputId": "82ff6a5e-5c8d-42f5-a5f5-dcad97f3c957"
      },
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[39, 211, 357, 428, 215, 179, 190, 90, 88]"
            ]
          },
          "metadata": {},
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "labels = np.empty(X_scaled.shape[0], dtype=int)\n",
        "\n",
        "start = 0\n",
        "for i, cluster in enumerate(final_clusters):\n",
        "    size = len(cluster)\n",
        "    labels[start:start + size] = i\n",
        "    start += size"
      ],
      "metadata": {
        "id": "x0MHuG1wB9BL"
      },
      "execution_count": 17,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "sil_score = silhouette_score(X_scaled, labels)\n",
        "print(\"Score :\", round(sil_score, 2))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "zCgeckEsCD7D",
        "outputId": "785308fe-46cc-4e6d-c294-bffece90c42c"
      },
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Score : -0.04\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### **Visualizing the divisive graph**"
      ],
      "metadata": {
        "id": "nJ9pvICgxDiX"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "def build_tree(X, depth=0, max_depth=3, min_size=50, node_name=\"Root\"):\n",
        "\n",
        "    if depth == max_depth or len(X) <= min_size:\n",
        "        return {\n",
        "            \"name\": f\"{node_name}\\n(size={len(X)})\",\n",
        "            \"children\": []\n",
        "        }\n",
        "\n",
        "    kmeans = KMeans(n_clusters=2, random_state=42)\n",
        "    labels = kmeans.fit_predict(X)\n",
        "\n",
        "    cluster_1 = X[labels == 0]\n",
        "    cluster_2 = X[labels == 1]\n",
        "\n",
        "    return {\n",
        "        \"name\": f\"{node_name}\\n(size={len(X)})\",\n",
        "        \"children\": [\n",
        "            build_tree(cluster_1, depth + 1, max_depth, min_size, node_name + \" → C1\"),\n",
        "            build_tree(cluster_2, depth + 1, max_depth, min_size, node_name + \" → C2\")\n",
        "        ]\n",
        "    }\n"
      ],
      "metadata": {
        "id": "-gAbaxa1CD-M"
      },
      "execution_count": 19,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "tree = build_tree(X_scaled, max_depth=3, min_size=50)"
      ],
      "metadata": {
        "id": "CtAw0-F-vmHL"
      },
      "execution_count": 20,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "def compute_positions(node, depth=0, x=0, positions=None, width=8):\n",
        "\n",
        "    if positions is None:\n",
        "        positions = {}\n",
        "\n",
        "    positions[node[\"name\"]] = (x, -depth)\n",
        "\n",
        "    children = node[\"children\"]\n",
        "    if children:\n",
        "        dx = width / len(children)\n",
        "        start_x = x - width/2 + dx/2\n",
        "\n",
        "        for i, child in enumerate(children):\n",
        "            compute_positions(child,\n",
        "                              depth + 1,\n",
        "                              start_x + i * dx,\n",
        "                              positions,\n",
        "                              width / 2)\n",
        "    return positions\n"
      ],
      "metadata": {
        "id": "LO0EWJFtvmKW"
      },
      "execution_count": 21,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "def extract_edges(node, edges=None):\n",
        "\n",
        "    if edges is None:\n",
        "        edges = []\n",
        "\n",
        "    for child in node[\"children\"]:\n",
        "        edges.append((node[\"name\"], child[\"name\"]))\n",
        "        extract_edges(child, edges)\n",
        "\n",
        "    return edges\n"
      ],
      "metadata": {
        "id": "cniOv_UivmPW"
      },
      "execution_count": 22,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "def plot_tree(tree):\n",
        "\n",
        "    positions = compute_positions(tree)\n",
        "    edges = extract_edges(tree)\n",
        "\n",
        "    fig, ax = plt.subplots(figsize=(12, 6))\n",
        "    ax.axis('off')\n",
        "\n",
        "\n",
        "    for parent, child in edges:\n",
        "        x1, y1 = positions[parent]\n",
        "        x2, y2 = positions[child]\n",
        "        ax.plot([x1, x2], [y1, y2], 'k-')\n",
        "\n",
        "\n",
        "    for node, (x, y) in positions.items():\n",
        "\n",
        "        if \"Root\" in node:\n",
        "            color = \"lightblue\"\n",
        "        elif \"C1\" in node or \"C2\" in node:\n",
        "            color = \"lightgreen\"\n",
        "        else:\n",
        "            color = \"lightyellow\"\n",
        "\n",
        "        ax.text(x, y, node,\n",
        "                ha='center',\n",
        "                va='center',\n",
        "                bbox=dict(boxstyle=\"round\",\n",
        "                          facecolor=color,\n",
        "                          edgecolor=\"black\"))\n",
        "\n",
        "    plt.title(\"Divisive Hierarchical Clustering Tree\", fontsize=14)\n",
        "    plt.tight_layout()\n",
        "    plt.show()\n"
      ],
      "metadata": {
        "id": "sDkNT6RyvmTe"
      },
      "execution_count": 23,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "plot_tree(tree)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 607
        },
        "id": "gdvWZ0l6wAHE",
        "outputId": "d3b2aef8-f629-42dc-b55e-9a8275d0add2"
      },
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1200x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "3vNEDbO2wAKy"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "SSx_7OlICEBH"
      },
      "execution_count": 21,
      "outputs": []
    }
  ]
}