clustering_exps_mnist_PCA.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "clustering-exps-mnist-PCA.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "toc_visible": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "KMVxeD4vXAZB",
        "outputId": "bc8a9ef9-f51e-44b6-ec31-c5a08951b1cb"
      },
      "source": [
        "#@title Don't forget to upload usps.h5\n",
        "\n",
        "import numpy as np\n",
        "from sklearn import metrics\n",
        "\n",
        "def purity_score(y_true, y_pred): # from https://stackoverflow.com/a/51672699/7947996; in [0,1]; 0-bad,1-good\n",
        "    # compute contingency matrix (also called confusion matrix)\n",
        "    contingency_matrix = metrics.cluster.contingency_matrix(y_true, y_pred)\n",
        "    # return purity\n",
        "    return np.sum(np.amax(contingency_matrix, axis=0)) / np.sum(contingency_matrix) \n",
        "\n",
        "from sklearn.metrics.cluster import adjusted_rand_score # in [0,1]; 0-bad,1-good\n",
        "from sklearn.metrics.cluster import normalized_mutual_info_score # in [0,1]; 0-bad,1-good\n",
        "\n",
        "!pip install coclust\n",
        "from coclust.evaluation.external import accuracy # in [0,1]; 0-bad,1-good\n",
        "\n",
        "def get_data_20news():\n",
        "  import tensorflow as tf\n",
        "  from sklearn.datasets import fetch_20newsgroups\n",
        "  from sklearn.feature_extraction.text import TfidfVectorizer\n",
        "\n",
        "  _20news = fetch_20newsgroups(subset=\"all\")\n",
        "  data = _20news.data\n",
        "  target = _20news.target\n",
        "\n",
        "  vectorizer = TfidfVectorizer(max_features=2000)\n",
        "  data = vectorizer.fit_transform(data)\n",
        "  data = data.toarray()\n",
        "\n",
        "  return data, target\n",
        "\n",
        "\n",
        "def get_data_mnist():\n",
        "  import tensorflow as tf\n",
        "  mnist = tf.keras.datasets.mnist\n",
        "  (x_train, y_train),(x_test, y_test) = mnist.load_data()\n",
        "\n",
        "  x_train = np.concatenate((x_train,x_test))\n",
        "  y_train = np.concatenate((y_train,y_test))\n",
        "\n",
        "  real_labels = y_train\n",
        "\n",
        "  # # indices = np.isin(y_train,range(number_of_dist))\n",
        "  # x_train = x_train[indices]\n",
        "  # y_train = y_train[indices]\n",
        "\n",
        "  samples = (x_train.reshape((x_train.shape[0],-1))/255.).astype(np.float32)\n",
        "  \n",
        "  return samples, real_labels\n",
        "\n",
        "\n",
        "\n",
        "def get_data_usps():\n",
        "  import h5py\n",
        "  path = \"./usps.h5\"\n",
        "  with h5py.File(path, 'r') as hf:\n",
        "    train = hf.get('train')\n",
        "    X_tr = train.get('data')[:]\n",
        "    y_tr = train.get('target')[:]\n",
        "    test = hf.get('test')\n",
        "    X_te = test.get('data')[:]\n",
        "    y_te = test.get('target')[:]\n",
        "\n",
        "  samples = np.concatenate((X_tr,X_te))\n",
        "  real_labels = np.concatenate((y_tr,y_te))\n",
        "  return samples, real_labels\n",
        "\n",
        "original_data_name = \"mnist\" # @param [\"mnist\", \"20news\", \"usps\"]\n",
        "\n",
        "if original_data_name == \"mnist\":\n",
        "    samples, real_labels = get_data_mnist()\n",
        "elif original_data_name == \"20news\":\n",
        "    samples, real_labels = get_data_20news()\n",
        "elif original_data_name == \"usps\":\n",
        "    samples, real_labels = get_data_usps()\n",
        "  \n",
        "k = len(np.unique(real_labels))\n",
        "n_init = 10\n",
        "dim_pca = 100\n",
        "\n",
        "if dim_pca is not None:\n",
        "    import numpy as np\n",
        "    from sklearn.decomposition import PCA\n",
        "    X = samples\n",
        "    pca = PCA(n_components=dim_pca)\n",
        "    samples = pca.fit_transform(X)"
      ],
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Collecting coclust\n",
            "  Downloading https://files.pythonhosted.org/packages/5d/44/ad5a69c7187c2b7bcf2c45596e9052811a3be52f4fcaa6709937c5146ee2/coclust-0.2.1.tar.gz\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.7/dist-packages (from coclust) (1.19.5)\n",
            "Requirement already satisfied: scipy in /usr/local/lib/python3.7/dist-packages (from coclust) (1.4.1)\n",
            "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.7/dist-packages (from coclust) (0.22.2.post1)\n",
            "Requirement already satisfied: joblib>=0.11 in /usr/local/lib/python3.7/dist-packages (from scikit-learn->coclust) (1.0.1)\n",
            "Building wheels for collected packages: coclust\n",
            "  Building wheel for coclust (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for coclust: filename=coclust-0.2.1-cp37-none-any.whl size=29871 sha256=2f43c00bf83ba2454649375b5e5f733554806f09c5c08443bf740bc59e9cd891\n",
            "  Stored in directory: /root/.cache/pip/wheels/cd/d7/68/df601d0b5f8b934cf890dc626c2271df381fb0c3e910b0a34e\n",
            "Successfully built coclust\n",
            "Installing collected packages: coclust\n",
            "Successfully installed coclust-0.2.1\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/linear_assignment_.py:22: FutureWarning: The linear_assignment_ module is deprecated in 0.21 and will be removed from 0.23. Use scipy.optimize.linear_sum_assignment instead.\n",
            "  FutureWarning)\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz\n",
            "11493376/11490434 [==============================] - 0s 0us/step\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "UM2n39n8x0fE"
      },
      "source": [
        "### Random"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ExRzemEgvWeb",
        "outputId": "518ff445-63bd-40c5-de6c-2a4ca9c8175e"
      },
      "source": [
        "predicted_random = np.random.randint(k,size=len(real_labels))\n",
        "\n",
        "print(purity_score(real_labels,predicted_random))\n",
        "print(adjusted_rand_score(real_labels,predicted_random))\n",
        "print(normalized_mutual_info_score(real_labels,predicted_random))\n",
        "print(accuracy(real_labels,predicted_random))"
      ],
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "0.1132\n",
            "4.58439653291007e-07\n",
            "0.0002499611721435298\n",
            "0.10485714285714286\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/linear_assignment_.py:128: FutureWarning: The linear_assignment function is deprecated in 0.21 and will be removed from 0.23. Use scipy.optimize.linear_sum_assignment instead.\n",
            "  FutureWarning)\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "vE1OLiiGx3Tl"
      },
      "source": [
        "### k-means"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "3fSvnYVhb930",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "e2022d3d-6ae4-4af6-86a3-2485b64dc241"
      },
      "source": [
        "from sklearn.cluster import KMeans\n",
        "import numpy as np\n",
        "X = samples\n",
        "kmeans = KMeans(n_clusters=k,n_init=n_init).fit(X)\n",
        "predicted_km = kmeans.predict(X)\n",
        "\n",
        "print(purity_score(real_labels,predicted_km))\n",
        "print(adjusted_rand_score(real_labels,predicted_km))\n",
        "print(normalized_mutual_info_score(real_labels,predicted_km))\n",
        "print(accuracy(real_labels,predicted_km))"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "0.5807428571428571\n",
            "0.3618526197607881\n",
            "0.4831502081740063\n",
            "0.5432714285714285\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/linear_assignment_.py:128: FutureWarning: The linear_assignment function is deprecated in 0.21 and will be removed from 0.23. Use scipy.optimize.linear_sum_assignment instead.\n",
            "  FutureWarning)\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "57lT0F8Mx4Fh"
      },
      "source": [
        "### GMM"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "xxjlKBYscsE8",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "d9cac2a3-daa3-4d3c-d9fc-3e334641f11a"
      },
      "source": [
        "import numpy as np\n",
        "from sklearn.mixture import GaussianMixture\n",
        "X = samples\n",
        "gm = GaussianMixture(n_components=k,n_init=n_init).fit(X)\n",
        "predicted_gmm = gm.predict(X)\n",
        "\n",
        "print(purity_score(real_labels,predicted_gmm))\n",
        "print(adjusted_rand_score(real_labels,predicted_gmm))\n",
        "print(normalized_mutual_info_score(real_labels,predicted_gmm))\n",
        "print(accuracy(real_labels,predicted_gmm))"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "0.5799857142857143\n",
            "0.34492250716722755\n",
            "0.5322247859315703\n",
            "0.5371\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/linear_assignment_.py:128: FutureWarning: The linear_assignment function is deprecated in 0.21 and will be removed from 0.23. Use scipy.optimize.linear_sum_assignment instead.\n",
            "  FutureWarning)\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "UOjm81-zyy3q"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}