FYS-STK4155/doc/pub/DimRed/ipynb/.ipynb_checkpoints/DimRed-checkpoint.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<!-- dom:TITLE: Data Analysis and Machine Learning: Preprocessing and Dimensionality Reduction -->\n",
    "# Data Analysis and Machine Learning: Preprocessing and Dimensionality Reduction\n",
    "<!-- dom:AUTHOR: Morten Hjorth-Jensen at Department of Physics, University of Oslo & Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University -->\n",
    "<!-- Author: -->  \n",
    "**Morten Hjorth-Jensen**, Department of Physics, University of Oslo and Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University\n",
    "\n",
    "Date: **Oct 14, 2019**\n",
    "\n",
    "Copyright 1999-2019, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "## Reducing the number of degrees of freedom, overarching view\n",
    "\n",
    "Many Machine Learning problems involve thousands or even millions of features for each training\n",
    "instance. Not only does this make training extremely slow, it can also make it much harder to find a good\n",
    "solution, as we will see. This problem is often referred to as the curse of dimensionality.\n",
    "Fortunately, in real-world problems, it is often possible to reduce the number of features considerably,\n",
    "turning an intractable problem into a tractable one.\n",
    "\n",
    "Here we will discuss some of the most popular dimensionality\n",
    "reduction techniques: the principal component analysis PCA, Kernel PCA, and Locally Linear Embedding (LLE).\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "## Preprocessing our data\n",
    "\n",
    "Before we proceed however, we will discuss how to preprocess our\n",
    "data. Till now and in connection with our previous examples we have not met so many cases\n",
    "where we are too sensitive to the scaling of our data. Normally the\n",
    "data may need a rescaling and/or may be sensitive to extreme\n",
    "values. Scaling the data renders our inputs much more suitable for the\n",
    "algorithms we want to employ.\n",
    "\n",
    "**Scikit-Learn** has several functions which allow us to rescale the data, normally resulting in much better results in terms of various accuracy scores.  The **StandardScaler** function in **Scikit-Learn** ensures that for each feature/predictor we study the mean value is zero and the variance is zero (every column in the design/feature matrix).\n",
    "This scaling has the drawback that it does not ensure that we have a particular maximum or minumum in our data set. Another function included in **Scikit-Learn** is the **MinMaxScaler** which ensures that all features are exactly between $0$ and $1$. The **Normalizer** function scales each column of the design matrix by its Euclidean norm.\n",
    "\n",
    "\n",
    "\n",
    "## Simple preprocessing examples, Franke function and regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "MSE before scaling: 0.01\n",
      "R2 score before scaling 0.94\n",
      "Feature min values before scaling:\n",
      " [1.00000000e+00 3.65071692e-04 3.95817540e-04 1.33277341e-07\n",
      " 1.44501779e-07 1.56671525e-07 4.86557843e-11 5.27535091e-11\n",
      " 5.71963387e-11 6.20133374e-11 1.77628495e-14 1.92588128e-14\n",
      " 2.08807642e-14 2.26393141e-14 2.45459667e-14 6.48471354e-18\n",
      " 7.03084740e-18 7.62297591e-18 8.26497270e-18 8.96103759e-18\n",
      " 9.71572413e-18]\n",
      "Feature max values before scaling:\n",
      " [1.         0.99846102 0.99865465 0.99692442 0.99711774 0.99731111\n",
      " 0.99539017 0.9955832  0.99577627 0.99596937 0.99385829 0.99405102\n",
      " 0.99424379 0.9944366  0.99462944 0.99232877 0.9925212  0.99271367\n",
      " 0.99290618 0.99309873 0.99329132]\n",
      "Feature min values after scaling:\n",
      " [ 0.         -1.68592363 -1.680662   -1.10811004 -1.09082494 -1.07436341\n",
      " -0.87879986 -0.86810747 -0.85783478 -0.84797797 -0.74808585 -0.74211553\n",
      " -0.73635781 -0.73080352 -0.72544375 -0.6608814  -0.65780307 -0.65482349\n",
      " -0.65193637 -0.64913573 -0.64641588]\n",
      "Feature max values after scaling:\n",
      " [0.         1.72566977 1.72438202 2.24728818 2.21480932 2.18128191\n",
      " 2.66918481 2.62627499 2.5831825  2.53999114 3.03235352 2.9851254\n",
      " 2.93793971 2.89083203 2.84383422 3.35451279 3.30554819 3.25663591\n",
      " 3.20779653 3.15904953 3.11041347]\n",
      "MSE after  scaling: 0.00\n",
      "R2 score for  scaled data: 0.97\n"
     ]
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "\n",
    "# Common imports\n",
    "import os\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import sklearn.linear_model as skl\n",
    "from sklearn.metrics import mean_squared_error\n",
    "from sklearn.model_selection import  train_test_split\n",
    "from sklearn.preprocessing import MinMaxScaler, StandardScaler, Normalizer\n",
    "from sklearn.svm import SVR\n",
    "\n",
    "# Where to save the figures and data files\n",
    "PROJECT_ROOT_DIR = \"Results\"\n",
    "FIGURE_ID = \"Results/FigureFiles\"\n",
    "DATA_ID = \"DataFiles/\"\n",
    "\n",
    "if not os.path.exists(PROJECT_ROOT_DIR):\n",
    "    os.mkdir(PROJECT_ROOT_DIR)\n",
    "\n",
    "if not os.path.exists(FIGURE_ID):\n",
    "    os.makedirs(FIGURE_ID)\n",
    "\n",
    "if not os.path.exists(DATA_ID):\n",
    "    os.makedirs(DATA_ID)\n",
    "\n",
    "def image_path(fig_id):\n",
    "    return os.path.join(FIGURE_ID, fig_id)\n",
    "\n",
    "def data_path(dat_id):\n",
    "    return os.path.join(DATA_ID, dat_id)\n",
    "\n",
    "def save_fig(fig_id):\n",
    "    plt.savefig(image_path(fig_id) + \".png\", format='png')\n",
    "\n",
    "\n",
    "def FrankeFunction(x,y):\n",
    "\tterm1 = 0.75*np.exp(-(0.25*(9*x-2)**2) - 0.25*((9*y-2)**2))\n",
    "\tterm2 = 0.75*np.exp(-((9*x+1)**2)/49.0 - 0.1*(9*y+1))\n",
    "\tterm3 = 0.5*np.exp(-(9*x-7)**2/4.0 - 0.25*((9*y-3)**2))\n",
    "\tterm4 = -0.2*np.exp(-(9*x-4)**2 - (9*y-7)**2)\n",
    "\treturn term1 + term2 + term3 + term4\n",
    "\n",
    "\n",
    "def create_X(x, y, n ):\n",
    "\tif len(x.shape) > 1:\n",
    "\t\tx = np.ravel(x)\n",
    "\t\ty = np.ravel(y)\n",
    "\n",
    "\tN = len(x)\n",
    "\tl = int((n+1)*(n+2)/2)\t\t# Number of elements in beta\n",
    "\tX = np.ones((N,l))\n",
    "\n",
    "\tfor i in range(1,n+1):\n",
    "\t\tq = int((i)*(i+1)/2)\n",
    "\t\tfor k in range(i+1):\n",
    "\t\t\tX[:,q+k] = (x**(i-k))*(y**k)\n",
    "\n",
    "\treturn X\n",
    "\n",
    "\n",
    "# Making meshgrid of datapoints and compute Franke's function\n",
    "n = 5\n",
    "N = 1000\n",
    "x = np.sort(np.random.uniform(0, 1, N))\n",
    "y = np.sort(np.random.uniform(0, 1, N))\n",
    "z = FrankeFunction(x, y)\n",
    "X = create_X(x, y, n=n)    \n",
    "# split in training and test data\n",
    "X_train, X_test, y_train, y_test = train_test_split(X,z,test_size=0.2)\n",
    "\n",
    "\n",
    "svm = SVR(gamma='auto',C=10.0)\n",
    "svm.fit(X_train, y_train)\n",
    "\n",
    "# The mean squared error and R2 score\n",
    "print(\"MSE before scaling: {:.2f}\".format(mean_squared_error(svm.predict(X_test), y_test)))\n",
    "print(\"R2 score before scaling {:.2f}\".format(svm.score(X_test,y_test)))\n",
    "\n",
    "scaler = StandardScaler()\n",
    "scaler.fit(X_train)\n",
    "X_train_scaled = scaler.transform(X_train)\n",
    "X_test_scaled = scaler.transform(X_test)\n",
    "\n",
    "print(\"Feature min values before scaling:\\n {}\".format(X_train.min(axis=0)))\n",
    "print(\"Feature max values before scaling:\\n {}\".format(X_train.max(axis=0)))\n",
    "\n",
    "print(\"Feature min values after scaling:\\n {}\".format(X_train_scaled.min(axis=0)))\n",
    "print(\"Feature max values after scaling:\\n {}\".format(X_train_scaled.max(axis=0)))\n",
    "\n",
    "svm = SVR(gamma='auto',C=10.0)\n",
    "svm.fit(X_train_scaled, y_train)\n",
    "\n",
    "print(\"MSE after  scaling: {:.2f}\".format(mean_squared_error(svm.predict(X_test_scaled), y_test)))\n",
    "print(\"R2 score for  scaled data: {:.2f}\".format(svm.score(X_test_scaled,y_test)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Simple preprocessing examples, breast cancer data and classification\n",
    "\n",
    "We show here how we can use a simple regression case on the breast cancer data using support vector machine as algorithm for classification"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(426, 30)\n",
      "(143, 30)\n",
      "Test set accuracy: 0.63\n",
      "Feature min values before scaling:\n",
      " [6.981e+00 9.710e+00 4.379e+01 1.435e+02 5.263e-02 1.938e-02 0.000e+00\n",
      " 0.000e+00 1.060e-01 4.996e-02 1.115e-01 3.628e-01 7.570e-01 7.228e+00\n",
      " 1.713e-03 2.252e-03 0.000e+00 0.000e+00 7.882e-03 8.948e-04 7.930e+00\n",
      " 1.202e+01 5.041e+01 1.852e+02 7.117e-02 2.729e-02 0.000e+00 0.000e+00\n",
      " 1.565e-01 5.504e-02]\n",
      "Feature max values before scaling:\n",
      " [2.811e+01 3.381e+01 1.885e+02 2.501e+03 1.447e-01 3.114e-01 4.268e-01\n",
      " 2.012e-01 3.040e-01 9.744e-02 2.873e+00 4.885e+00 2.198e+01 5.422e+02\n",
      " 2.333e-02 1.064e-01 3.960e-01 5.279e-02 6.146e-02 2.984e-02 3.604e+01\n",
      " 4.954e+01 2.512e+02 4.254e+03 2.226e-01 1.058e+00 1.252e+00 2.903e-01\n",
      " 6.638e-01 2.075e-01]\n",
      "Feature min values before scaling:\n",
      " [0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n",
      " 0. 0. 0. 0. 0. 0.]\n",
      "Feature max values before scaling:\n",
      " [1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1. 1.\n",
      " 1. 1. 1. 1. 1. 1.]\n",
      "Test set accuracy scaled data: 0.97\n",
      "Test set accuracy scaled data: 0.96\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.7/site-packages/sklearn/svm/base.py:196: FutureWarning: The default value of gamma will change from 'auto' to 'scale' in version 0.22 to account better for unscaled features. Set gamma explicitly to 'auto' or 'scale' to avoid this warning.\n",
      "  \"avoid this warning.\", FutureWarning)\n",
      "/usr/local/lib/python3.7/site-packages/sklearn/svm/base.py:196: FutureWarning: The default value of gamma will change from 'auto' to 'scale' in version 0.22 to account better for unscaled features. Set gamma explicitly to 'auto' or 'scale' to avoid this warning.\n",
      "  \"avoid this warning.\", FutureWarning)\n"
     ]
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "from sklearn.model_selection import  train_test_split \n",
    "from sklearn.datasets import load_breast_cancer\n",
    "from sklearn.svm import SVC\n",
    "cancer = load_breast_cancer()\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(cancer.data,cancer.target,random_state=0)\n",
    "print(X_train.shape)\n",
    "print(X_test.shape)\n",
    "\n",
    "svm = SVC(C=100)\n",
    "svm.fit(X_train, y_train)\n",
    "print(\"Test set accuracy: {:.2f}\".format(svm.score(X_test,y_test)))\n",
    "\n",
    "from sklearn.preprocessing import MinMaxScaler, StandardScaler\n",
    "\n",
    "scaler = MinMaxScaler()\n",
    "scaler.fit(X_train)\n",
    "X_train_scaled = scaler.transform(X_train)\n",
    "X_test_scaled = scaler.transform(X_test)\n",
    "\n",
    "print(\"Feature min values before scaling:\\n {}\".format(X_train.min(axis=0)))\n",
    "print(\"Feature max values before scaling:\\n {}\".format(X_train.max(axis=0)))\n",
    "\n",
    "print(\"Feature min values before scaling:\\n {}\".format(X_train_scaled.min(axis=0)))\n",
    "print(\"Feature max values before scaling:\\n {}\".format(X_train_scaled.max(axis=0)))\n",
    "\n",
    "\n",
    "svm.fit(X_train_scaled, y_train)\n",
    "print(\"Test set accuracy scaled data: {:.2f}\".format(svm.score(X_test_scaled,y_test)))\n",
    "\n",
    "scaler = StandardScaler()\n",
    "scaler.fit(X_train)\n",
    "X_train_scaled = scaler.transform(X_train)\n",
    "X_test_scaled = scaler.transform(X_test)\n",
    "\n",
    "svm.fit(X_train_scaled, y_train)\n",
    "print(\"Test set accuracy scaled data: {:.2f}\".format(svm.score(X_test_scaled,y_test)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## More on Cancer Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x1440 with 30 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(426, 30)\n",
      "(143, 30)\n",
      "Test set accuracy: 0.96\n",
      "Test set accuracy scaled data: 0.96\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.\n",
      "  FutureWarning)\n",
      "/usr/local/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.\n",
      "  FutureWarning)\n"
     ]
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "from sklearn.model_selection import  train_test_split \n",
    "from sklearn.datasets import load_breast_cancer\n",
    "from sklearn.svm import SVC\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "cancer = load_breast_cancer()\n",
    "\n",
    "fig, axes = plt.subplots(15,2,figsize=(10,20))\n",
    "male = cancer.data[cancer.target == 0]\n",
    "bene = cancer.data[cancer.target == 1]\n",
    "ax = axes.ravel()\n",
    "\n",
    "for i in range(30):\n",
    "    _, bins = np.histogram(cancer.data[:,i], bins =50)\n",
    "    ax[i].hist(male[:,i], bins = bins, alpha = 0.5)\n",
    "    ax[i].hist(bene[:,i], bins = bins, alpha = 0.5)\n",
    "    ax[i].set_title(cancer.feature_names[i])\n",
    "    ax[i].set_yticks(())\n",
    "ax[0].set_xlabel(\"Feature magnitude\")\n",
    "ax[0].set_ylabel(\"Frequency\")\n",
    "ax[0].legend([\"Male\", \"Bene\"], loc =\"best\")\n",
    "fig.tight_layout()\n",
    "plt.show()\n",
    "X_train, X_test, y_train, y_test = train_test_split(cancer.data,cancer.target,random_state=0)\n",
    "print(X_train.shape)\n",
    "print(X_test.shape)\n",
    "\n",
    "logreg = LogisticRegression()\n",
    "logreg.fit(X_train, y_train)\n",
    "\n",
    "print(\"Test set accuracy: {:.2f}\".format(logreg.score(X_test,y_test)))\n",
    "\n",
    "from sklearn.preprocessing import MinMaxScaler, StandardScaler\n",
    "\n",
    "\n",
    "scaler = StandardScaler()\n",
    "scaler.fit(X_train)\n",
    "X_train_scaled = scaler.transform(X_train)\n",
    "X_test_scaled = scaler.transform(X_test)\n",
    "logreg.fit(X_train_scaled, y_train)\n",
    "#svm.fit(X_train_scaled, y_train)\n",
    "print(\"Test set accuracy scaled data: {:.2f}\".format(logreg.score(X_test_scaled,y_test)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Principal Component Analysis\n",
    "Principal Component Analysis (PCA) is by far the most popular dimensionality reduction algorithm.\n",
    "First it identifies the hyperplane that lies closest to the data, and then it projects the data onto it.\n",
    "\n",
    "The following Python code uses NumPy’s **svd()** function to obtain all the principal components of the\n",
    "training set, then extracts the first two principal components"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_centered = X - X.mean(axis=0)\n",
    "U, s, V = np.linalg.svd(X_centered)\n",
    "c1 = V.T[:, 0]\n",
    "c2 = V.T[:, 1]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "PCA assumes that the dataset is centered around the origin. Scikit-Learn’s PCA classes take care of centering\n",
    "the data for you. However, if you implement PCA yourself (as in the preceding example), or if you use other libraries, don’t\n",
    "forget to center the data first.\n",
    "\n",
    "Once you have identified all the principal components, you can reduce the dimensionality of the dataset\n",
    "down to $d$ dimensions by projecting it onto the hyperplane defined by the first $d$ principal components.\n",
    "Selecting this hyperplane ensures that the projection will preserve as much variance as possible."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "W2 = V.T[:, :2]\n",
    "X2D = X_centered.dot(W2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<!-- !split  -->\n",
    "## PCA and scikit-learn\n",
    "\n",
    "Scikit-Learn’s PCA class implements PCA using SVD decomposition just like we did before. The\n",
    "following code applies PCA to reduce the dimensionality of the dataset down to two dimensions (note\n",
    "that it automatically takes care of centering the data):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.decomposition import PCA\n",
    "pca = PCA(n_components = 2)\n",
    "X2D = pca.fit_transform(X)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "After fitting the PCA transformer to the dataset, you can access the principal components using the\n",
    "components variable (note that it contains the PCs as horizontal vectors, so, for example, the first\n",
    "principal component is equal to"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "pca.components_.T[:, 0])."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Another very useful piece of information is the explained variance ratio of each principal component,\n",
    "available via the $explained\\_variance\\_ratio$ variable. It indicates the proportion of the dataset’s\n",
    "variance that lies along the axis of each principal component. \n",
    "More material to come here.\n",
    "\n",
    "## More on the PCA\n",
    "Instead of arbitrarily choosing the number of dimensions to reduce down to, it is generally preferable to\n",
    "choose the number of dimensions that add up to a sufficiently large portion of the variance (e.g., 95%).\n",
    "Unless, of course, you are reducing dimensionality for data visualization — in that case you will\n",
    "generally want to reduce the dimensionality down to 2 or 3.\n",
    "The following code computes PCA without reducing dimensionality, then computes the minimum number\n",
    "of dimensions required to preserve 95% of the training set’s variance:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "pca = PCA()\n",
    "pca.fit(X)\n",
    "cumsum = np.cumsum(pca.explained_variance_ratio_)\n",
    "d = np.argmax(cumsum >= 0.95) + 1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "You could then set $n\\_components=d$ and run PCA again. However, there is a much better option: instead\n",
    "of specifying the number of principal components you want to preserve, you can set $n\\_components$ to be\n",
    "a float between 0.0 and 1.0, indicating the ratio of variance you wish to preserve:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "pca = PCA(n_components=0.95)\n",
    "X_reduced = pca.fit_transform(X)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Incremental PCA\n",
    "One problem with the preceding implementation of PCA is that it requires the whole training set to fit in\n",
    "memory in order for the SVD algorithm to run. Fortunately, Incremental PCA (IPCA) algorithms have\n",
    "been developed: you can split the training set into mini-batches and feed an IPCA algorithm one minibatch\n",
    "at a time. This is useful for large training sets, and also to apply PCA online (i.e., on the fly, as new\n",
    "instances arrive).\n",
    "\n",
    "## Randomized PCA\n",
    "\n",
    "Scikit-Learn offers yet another option to perform PCA, called Randomized PCA. This is a stochastic\n",
    "algorithm that quickly finds an approximation of the first d principal components. Its computational\n",
    "complexity is $O(m \\times d^2)+O(d^3)$, instead of $O(m \\times n^2) + O(n^3)$, so it is dramatically faster than the\n",
    "previous algorithms when $d$ is much smaller than $n$.\n",
    "\n",
    "\n",
    "\n",
    "\n",
    "## Kernel PCA\n",
    "\n",
    "The kernel trick is a mathematical technique that implicitly maps instances into a\n",
    "very high-dimensional space (called the feature space), enabling nonlinear classification and regression\n",
    "with Support Vector Machines. Recall that a linear decision boundary in the high-dimensional feature\n",
    "space corresponds to a complex nonlinear decision boundary in the original space.\n",
    "It turns out that the same trick can be applied to PCA, making it possible to perform complex nonlinear\n",
    "projections for dimensionality reduction. This is called Kernel PCA (kPCA). It is often good at\n",
    "preserving clusters of instances after projection, or sometimes even unrolling datasets that lie close to a\n",
    "twisted manifold.\n",
    "For example, the following code uses Scikit-Learn’s KernelPCA class to perform kPCA with an"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.decomposition import KernelPCA\n",
    "rbf_pca = KernelPCA(n_components = 2, kernel=\"rbf\", gamma=0.04)\n",
    "X_reduced = rbf_pca.fit_transform(X)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## LLE\n",
    "\n",
    "Locally Linear Embedding (LLE) is another very powerful nonlinear dimensionality reduction\n",
    "(NLDR) technique. It is a Manifold Learning technique that does not rely on projections like the previous\n",
    "algorithms. In a nutshell, LLE works by first measuring how each training instance linearly relates to its\n",
    "closest neighbors (c.n.), and then looking for a low-dimensional representation of the training set where\n",
    "these local relationships are best preserved (more details shortly). \n",
    "\n",
    "\n",
    "\n",
    "## Other techniques\n",
    "\n",
    "\n",
    "There are many other dimensionality reduction techniques, several of which are available in Scikit-Learn.\n",
    "\n",
    "Here are some of the most popular:\n",
    "* **Multidimensional Scaling (MDS)** reduces dimensionality while trying to preserve the distances between the instances.\n",
    "\n",
    "* **Isomap** creates a graph by connecting each instance to its nearest neighbors, then reduces dimensionality while trying to preserve the geodesic distances between the instances.\n",
    "\n",
    "* **t-Distributed Stochastic Neighbor Embedding** (t-SNE) reduces dimensionality while trying to keep similar instances close and dissimilar instances apart. It is mostly used for visualization, in particular to visualize clusters of instances in high-dimensional space (e.g., to visualize the MNIST images in 2D).\n",
    "\n",
    "* Linear Discriminant Analysis (LDA) is actually a classification algorithm, but during training it learns the most discriminative axes between the classes, and these axes can then be used to define a hyperplane onto which to project the data. The benefit is that the projection will keep classes as far apart as possible, so LDA is a good technique to reduce dimensionality before running another classification algorithm such as a Support Vector Machine (SVM) classifier discussed in the SVM lectures."
   ]
  }
 ],
 "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": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}