01-09-2016-rrfd-scikit-learn-tutorial.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Just as an eample, ML looks at a lot of data and then tries to predict properties of unknown data.\n",
    "\n",
    "This is a supervised learning example.\n",
    "\n",
    "SML can be split into two categories: classifications (what something is) and regression (how much something is)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "from sklearn import datasets\n",
    "\n",
    "iris = datasets.load_iris()\n",
    "digits = datasets.load_digits()\n",
    "\n",
    "# Remember these are not Pandas datasets. So you cannot manipulate them yet."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# import pandas as pd\n",
    "# iris_df = pd.DataFrame(iris)\n",
    "# iris_df.head()\n",
    "\n",
    "# Did not work - > ValueError: arrays must all be same length"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[  0.   0.   5. ...,   0.   0.   0.]\n",
      " [  0.   0.   0. ...,  10.   0.   0.]\n",
      " [  0.   0.   0. ...,  16.   9.   0.]\n",
      " ..., \n",
      " [  0.   0.   1. ...,   6.   0.   0.]\n",
      " [  0.   0.   2. ...,  12.   0.   0.]\n",
      " [  0.   0.  10. ...,  12.   1.   0.]] \n",
      "[[ 5.1  3.5  1.4  0.2]\n",
      " [ 4.9  3.   1.4  0.2]\n",
      " [ 4.7  3.2  1.3  0.2]\n",
      " [ 4.6  3.1  1.5  0.2]\n",
      " [ 5.   3.6  1.4  0.2]\n",
      " [ 5.4  3.9  1.7  0.4]\n",
      " [ 4.6  3.4  1.4  0.3]\n",
      " [ 5.   3.4  1.5  0.2]\n",
      " [ 4.4  2.9  1.4  0.2]\n",
      " [ 4.9  3.1  1.5  0.1]\n",
      " [ 5.4  3.7  1.5  0.2]\n",
      " [ 4.8  3.4  1.6  0.2]\n",
      " [ 4.8  3.   1.4  0.1]\n",
      " [ 4.3  3.   1.1  0.1]\n",
      " [ 5.8  4.   1.2  0.2]\n",
      " [ 5.7  4.4  1.5  0.4]\n",
      " [ 5.4  3.9  1.3  0.4]\n",
      " [ 5.1  3.5  1.4  0.3]\n",
      " [ 5.7  3.8  1.7  0.3]\n",
      " [ 5.1  3.8  1.5  0.3]\n",
      " [ 5.4  3.4  1.7  0.2]\n",
      " [ 5.1  3.7  1.5  0.4]\n",
      " [ 4.6  3.6  1.   0.2]\n",
      " [ 5.1  3.3  1.7  0.5]\n",
      " [ 4.8  3.4  1.9  0.2]\n",
      " [ 5.   3.   1.6  0.2]\n",
      " [ 5.   3.4  1.6  0.4]\n",
      " [ 5.2  3.5  1.5  0.2]\n",
      " [ 5.2  3.4  1.4  0.2]\n",
      " [ 4.7  3.2  1.6  0.2]\n",
      " [ 4.8  3.1  1.6  0.2]\n",
      " [ 5.4  3.4  1.5  0.4]\n",
      " [ 5.2  4.1  1.5  0.1]\n",
      " [ 5.5  4.2  1.4  0.2]\n",
      " [ 4.9  3.1  1.5  0.1]\n",
      " [ 5.   3.2  1.2  0.2]\n",
      " [ 5.5  3.5  1.3  0.2]\n",
      " [ 4.9  3.1  1.5  0.1]\n",
      " [ 4.4  3.   1.3  0.2]\n",
      " [ 5.1  3.4  1.5  0.2]\n",
      " [ 5.   3.5  1.3  0.3]\n",
      " [ 4.5  2.3  1.3  0.3]\n",
      " [ 4.4  3.2  1.3  0.2]\n",
      " [ 5.   3.5  1.6  0.6]\n",
      " [ 5.1  3.8  1.9  0.4]\n",
      " [ 4.8  3.   1.4  0.3]\n",
      " [ 5.1  3.8  1.6  0.2]\n",
      " [ 4.6  3.2  1.4  0.2]\n",
      " [ 5.3  3.7  1.5  0.2]\n",
      " [ 5.   3.3  1.4  0.2]\n",
      " [ 7.   3.2  4.7  1.4]\n",
      " [ 6.4  3.2  4.5  1.5]\n",
      " [ 6.9  3.1  4.9  1.5]\n",
      " [ 5.5  2.3  4.   1.3]\n",
      " [ 6.5  2.8  4.6  1.5]\n",
      " [ 5.7  2.8  4.5  1.3]\n",
      " [ 6.3  3.3  4.7  1.6]\n",
      " [ 4.9  2.4  3.3  1. ]\n",
      " [ 6.6  2.9  4.6  1.3]\n",
      " [ 5.2  2.7  3.9  1.4]\n",
      " [ 5.   2.   3.5  1. ]\n",
      " [ 5.9  3.   4.2  1.5]\n",
      " [ 6.   2.2  4.   1. ]\n",
      " [ 6.1  2.9  4.7  1.4]\n",
      " [ 5.6  2.9  3.6  1.3]\n",
      " [ 6.7  3.1  4.4  1.4]\n",
      " [ 5.6  3.   4.5  1.5]\n",
      " [ 5.8  2.7  4.1  1. ]\n",
      " [ 6.2  2.2  4.5  1.5]\n",
      " [ 5.6  2.5  3.9  1.1]\n",
      " [ 5.9  3.2  4.8  1.8]\n",
      " [ 6.1  2.8  4.   1.3]\n",
      " [ 6.3  2.5  4.9  1.5]\n",
      " [ 6.1  2.8  4.7  1.2]\n",
      " [ 6.4  2.9  4.3  1.3]\n",
      " [ 6.6  3.   4.4  1.4]\n",
      " [ 6.8  2.8  4.8  1.4]\n",
      " [ 6.7  3.   5.   1.7]\n",
      " [ 6.   2.9  4.5  1.5]\n",
      " [ 5.7  2.6  3.5  1. ]\n",
      " [ 5.5  2.4  3.8  1.1]\n",
      " [ 5.5  2.4  3.7  1. ]\n",
      " [ 5.8  2.7  3.9  1.2]\n",
      " [ 6.   2.7  5.1  1.6]\n",
      " [ 5.4  3.   4.5  1.5]\n",
      " [ 6.   3.4  4.5  1.6]\n",
      " [ 6.7  3.1  4.7  1.5]\n",
      " [ 6.3  2.3  4.4  1.3]\n",
      " [ 5.6  3.   4.1  1.3]\n",
      " [ 5.5  2.5  4.   1.3]\n",
      " [ 5.5  2.6  4.4  1.2]\n",
      " [ 6.1  3.   4.6  1.4]\n",
      " [ 5.8  2.6  4.   1.2]\n",
      " [ 5.   2.3  3.3  1. ]\n",
      " [ 5.6  2.7  4.2  1.3]\n",
      " [ 5.7  3.   4.2  1.2]\n",
      " [ 5.7  2.9  4.2  1.3]\n",
      " [ 6.2  2.9  4.3  1.3]\n",
      " [ 5.1  2.5  3.   1.1]\n",
      " [ 5.7  2.8  4.1  1.3]\n",
      " [ 6.3  3.3  6.   2.5]\n",
      " [ 5.8  2.7  5.1  1.9]\n",
      " [ 7.1  3.   5.9  2.1]\n",
      " [ 6.3  2.9  5.6  1.8]\n",
      " [ 6.5  3.   5.8  2.2]\n",
      " [ 7.6  3.   6.6  2.1]\n",
      " [ 4.9  2.5  4.5  1.7]\n",
      " [ 7.3  2.9  6.3  1.8]\n",
      " [ 6.7  2.5  5.8  1.8]\n",
      " [ 7.2  3.6  6.1  2.5]\n",
      " [ 6.5  3.2  5.1  2. ]\n",
      " [ 6.4  2.7  5.3  1.9]\n",
      " [ 6.8  3.   5.5  2.1]\n",
      " [ 5.7  2.5  5.   2. ]\n",
      " [ 5.8  2.8  5.1  2.4]\n",
      " [ 6.4  3.2  5.3  2.3]\n",
      " [ 6.5  3.   5.5  1.8]\n",
      " [ 7.7  3.8  6.7  2.2]\n",
      " [ 7.7  2.6  6.9  2.3]\n",
      " [ 6.   2.2  5.   1.5]\n",
      " [ 6.9  3.2  5.7  2.3]\n",
      " [ 5.6  2.8  4.9  2. ]\n",
      " [ 7.7  2.8  6.7  2. ]\n",
      " [ 6.3  2.7  4.9  1.8]\n",
      " [ 6.7  3.3  5.7  2.1]\n",
      " [ 7.2  3.2  6.   1.8]\n",
      " [ 6.2  2.8  4.8  1.8]\n",
      " [ 6.1  3.   4.9  1.8]\n",
      " [ 6.4  2.8  5.6  2.1]\n",
      " [ 7.2  3.   5.8  1.6]\n",
      " [ 7.4  2.8  6.1  1.9]\n",
      " [ 7.9  3.8  6.4  2. ]\n",
      " [ 6.4  2.8  5.6  2.2]\n",
      " [ 6.3  2.8  5.1  1.5]\n",
      " [ 6.1  2.6  5.6  1.4]\n",
      " [ 7.7  3.   6.1  2.3]\n",
      " [ 6.3  3.4  5.6  2.4]\n",
      " [ 6.4  3.1  5.5  1.8]\n",
      " [ 6.   3.   4.8  1.8]\n",
      " [ 6.9  3.1  5.4  2.1]\n",
      " [ 6.7  3.1  5.6  2.4]\n",
      " [ 6.9  3.1  5.1  2.3]\n",
      " [ 5.8  2.7  5.1  1.9]\n",
      " [ 6.8  3.2  5.9  2.3]\n",
      " [ 6.7  3.3  5.7  2.5]\n",
      " [ 6.7  3.   5.2  2.3]\n",
      " [ 6.3  2.5  5.   1.9]\n",
      " [ 6.5  3.   5.2  2. ]\n",
      " [ 6.2  3.4  5.4  2.3]\n",
      " [ 5.9  3.   5.1  1.8]]\n"
     ]
    }
   ],
   "source": [
    "# This shows the data in the dataset we're trying to look at\n",
    "print digits.data, \"\\n\", iris.data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[  0.,   0.,   5.,  13.,   9.,   1.,   0.,   0.],\n",
       "       [  0.,   0.,  13.,  15.,  10.,  15.,   5.,   0.],\n",
       "       [  0.,   3.,  15.,   2.,   0.,  11.,   8.,   0.],\n",
       "       [  0.,   4.,  12.,   0.,   0.,   8.,   8.,   0.],\n",
       "       [  0.,   5.,   8.,   0.,   0.,   9.,   8.,   0.],\n",
       "       [  0.,   4.,  11.,   0.,   1.,  12.,   7.,   0.],\n",
       "       [  0.,   2.,  14.,   5.,  10.,  12.,   0.,   0.],\n",
       "       [  0.,   0.,   6.,  13.,  10.,   0.,   0.,   0.]])"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "digits.images[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# So the first thing we're going to do is learn ... and then we PREDICT.\n",
    "# For that we use SVC. Same thing we used on the Titanic example\n",
    "\n",
    "from sklearn import svm\n",
    "\n",
    "# clf is the classifier, or the thing that is going to be doing the learning.\n",
    "clf = svm.SVC(gamma = 0.001, C=100)\n",
    "\n",
    "# Right now gamma is set manually, but we could use grid search or cross \n",
    "# validation to find the correct gamma.\n",
    "\n",
    "# More on the above here:\n",
    "# http://scikit-learn.org/stable/modules/grid_search.html#grid-search\n",
    "# http://scikit-learn.org/stable/modules/cross_validation.html#cross-validation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SVC(C=100, cache_size=200, class_weight=None, coef0=0.0,\n",
       "  decision_function_shape=None, degree=3, gamma=0.001, kernel='rbf',\n",
       "  max_iter=-1, probability=False, random_state=None, shrinking=True,\n",
       "  tol=0.001, verbose=False)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clf.fit(digits.data[:-1], digits.target[:-1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/robertdefilippi/miniconda2/lib/python2.7/site-packages/sklearn/utils/validation.py:386: DeprecationWarning: Passing 1d arrays as data is deprecated in 0.17 and willraise ValueError in 0.19. Reshape your data either using X.reshape(-1, 1) if your data has a single feature or X.reshape(1, -1) if it contains a single sample.\n",
      "  DeprecationWarning)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([8])"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Now we: have the model and fitted the model.\n",
    "# We can now LEARN from the model.\n",
    "\n",
    "clf.predict(digits.data[-1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Lets take a look at k-means clustering.\n",
    "\n",
    "from sklearn import cluster, datasets\n",
    "iris = datasets.load_iris()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'DESCR': 'Iris Plants Database\\n\\nNotes\\n-----\\nData Set Characteristics:\\n    :Number of Instances: 150 (50 in each of three classes)\\n    :Number of Attributes: 4 numeric, predictive attributes and the class\\n    :Attribute Information:\\n        - sepal length in cm\\n        - sepal width in cm\\n        - petal length in cm\\n        - petal width in cm\\n        - class:\\n                - Iris-Setosa\\n                - Iris-Versicolour\\n                - Iris-Virginica\\n    :Summary Statistics:\\n\\n    ============== ==== ==== ======= ===== ====================\\n                    Min  Max   Mean    SD   Class Correlation\\n    ============== ==== ==== ======= ===== ====================\\n    sepal length:   4.3  7.9   5.84   0.83    0.7826\\n    sepal width:    2.0  4.4   3.05   0.43   -0.4194\\n    petal length:   1.0  6.9   3.76   1.76    0.9490  (high!)\\n    petal width:    0.1  2.5   1.20  0.76     0.9565  (high!)\\n    ============== ==== ==== ======= ===== ====================\\n\\n    :Missing Attribute Values: None\\n    :Class Distribution: 33.3% for each of 3 classes.\\n    :Creator: R.A. Fisher\\n    :Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)\\n    :Date: July, 1988\\n\\nThis is a copy of UCI ML iris datasets.\\nhttp://archive.ics.uci.edu/ml/datasets/Iris\\n\\nThe famous Iris database, first used by Sir R.A Fisher\\n\\nThis is perhaps the best known database to be found in the\\npattern recognition literature.  Fisher\\'s paper is a classic in the field and\\nis referenced frequently to this day.  (See Duda & Hart, for example.)  The\\ndata set contains 3 classes of 50 instances each, where each class refers to a\\ntype of iris plant.  One class is linearly separable from the other 2; the\\nlatter are NOT linearly separable from each other.\\n\\nReferences\\n----------\\n   - Fisher,R.A. \"The use of multiple measurements in taxonomic problems\"\\n     Annual Eugenics, 7, Part II, 179-188 (1936); also in \"Contributions to\\n     Mathematical Statistics\" (John Wiley, NY, 1950).\\n   - Duda,R.O., & Hart,P.E. (1973) Pattern Classification and Scene Analysis.\\n     (Q327.D83) John Wiley & Sons.  ISBN 0-471-22361-1.  See page 218.\\n   - Dasarathy, B.V. (1980) \"Nosing Around the Neighborhood: A New System\\n     Structure and Classification Rule for Recognition in Partially Exposed\\n     Environments\".  IEEE Transactions on Pattern Analysis and Machine\\n     Intelligence, Vol. PAMI-2, No. 1, 67-71.\\n   - Gates, G.W. (1972) \"The Reduced Nearest Neighbor Rule\".  IEEE Transactions\\n     on Information Theory, May 1972, 431-433.\\n   - See also: 1988 MLC Proceedings, 54-64.  Cheeseman et al\"s AUTOCLASS II\\n     conceptual clustering system finds 3 classes in the data.\\n   - Many, many more ...\\n',\n",
       " 'data': array([[ 5.1,  3.5,  1.4,  0.2],\n",
       "        [ 4.9,  3. ,  1.4,  0.2],\n",
       "        [ 4.7,  3.2,  1.3,  0.2],\n",
       "        [ 4.6,  3.1,  1.5,  0.2],\n",
       "        [ 5. ,  3.6,  1.4,  0.2],\n",
       "        [ 5.4,  3.9,  1.7,  0.4],\n",
       "        [ 4.6,  3.4,  1.4,  0.3],\n",
       "        [ 5. ,  3.4,  1.5,  0.2],\n",
       "        [ 4.4,  2.9,  1.4,  0.2],\n",
       "        [ 4.9,  3.1,  1.5,  0.1],\n",
       "        [ 5.4,  3.7,  1.5,  0.2],\n",
       "        [ 4.8,  3.4,  1.6,  0.2],\n",
       "        [ 4.8,  3. ,  1.4,  0.1],\n",
       "        [ 4.3,  3. ,  1.1,  0.1],\n",
       "        [ 5.8,  4. ,  1.2,  0.2],\n",
       "        [ 5.7,  4.4,  1.5,  0.4],\n",
       "        [ 5.4,  3.9,  1.3,  0.4],\n",
       "        [ 5.1,  3.5,  1.4,  0.3],\n",
       "        [ 5.7,  3.8,  1.7,  0.3],\n",
       "        [ 5.1,  3.8,  1.5,  0.3],\n",
       "        [ 5.4,  3.4,  1.7,  0.2],\n",
       "        [ 5.1,  3.7,  1.5,  0.4],\n",
       "        [ 4.6,  3.6,  1. ,  0.2],\n",
       "        [ 5.1,  3.3,  1.7,  0.5],\n",
       "        [ 4.8,  3.4,  1.9,  0.2],\n",
       "        [ 5. ,  3. ,  1.6,  0.2],\n",
       "        [ 5. ,  3.4,  1.6,  0.4],\n",
       "        [ 5.2,  3.5,  1.5,  0.2],\n",
       "        [ 5.2,  3.4,  1.4,  0.2],\n",
       "        [ 4.7,  3.2,  1.6,  0.2],\n",
       "        [ 4.8,  3.1,  1.6,  0.2],\n",
       "        [ 5.4,  3.4,  1.5,  0.4],\n",
       "        [ 5.2,  4.1,  1.5,  0.1],\n",
       "        [ 5.5,  4.2,  1.4,  0.2],\n",
       "        [ 4.9,  3.1,  1.5,  0.1],\n",
       "        [ 5. ,  3.2,  1.2,  0.2],\n",
       "        [ 5.5,  3.5,  1.3,  0.2],\n",
       "        [ 4.9,  3.1,  1.5,  0.1],\n",
       "        [ 4.4,  3. ,  1.3,  0.2],\n",
       "        [ 5.1,  3.4,  1.5,  0.2],\n",
       "        [ 5. ,  3.5,  1.3,  0.3],\n",
       "        [ 4.5,  2.3,  1.3,  0.3],\n",
       "        [ 4.4,  3.2,  1.3,  0.2],\n",
       "        [ 5. ,  3.5,  1.6,  0.6],\n",
       "        [ 5.1,  3.8,  1.9,  0.4],\n",
       "        [ 4.8,  3. ,  1.4,  0.3],\n",
       "        [ 5.1,  3.8,  1.6,  0.2],\n",
       "        [ 4.6,  3.2,  1.4,  0.2],\n",
       "        [ 5.3,  3.7,  1.5,  0.2],\n",
       "        [ 5. ,  3.3,  1.4,  0.2],\n",
       "        [ 7. ,  3.2,  4.7,  1.4],\n",
       "        [ 6.4,  3.2,  4.5,  1.5],\n",
       "        [ 6.9,  3.1,  4.9,  1.5],\n",
       "        [ 5.5,  2.3,  4. ,  1.3],\n",
       "        [ 6.5,  2.8,  4.6,  1.5],\n",
       "        [ 5.7,  2.8,  4.5,  1.3],\n",
       "        [ 6.3,  3.3,  4.7,  1.6],\n",
       "        [ 4.9,  2.4,  3.3,  1. ],\n",
       "        [ 6.6,  2.9,  4.6,  1.3],\n",
       "        [ 5.2,  2.7,  3.9,  1.4],\n",
       "        [ 5. ,  2. ,  3.5,  1. ],\n",
       "        [ 5.9,  3. ,  4.2,  1.5],\n",
       "        [ 6. ,  2.2,  4. ,  1. ],\n",
       "        [ 6.1,  2.9,  4.7,  1.4],\n",
       "        [ 5.6,  2.9,  3.6,  1.3],\n",
       "        [ 6.7,  3.1,  4.4,  1.4],\n",
       "        [ 5.6,  3. ,  4.5,  1.5],\n",
       "        [ 5.8,  2.7,  4.1,  1. ],\n",
       "        [ 6.2,  2.2,  4.5,  1.5],\n",
       "        [ 5.6,  2.5,  3.9,  1.1],\n",
       "        [ 5.9,  3.2,  4.8,  1.8],\n",
       "        [ 6.1,  2.8,  4. ,  1.3],\n",
       "        [ 6.3,  2.5,  4.9,  1.5],\n",
       "        [ 6.1,  2.8,  4.7,  1.2],\n",
       "        [ 6.4,  2.9,  4.3,  1.3],\n",
       "        [ 6.6,  3. ,  4.4,  1.4],\n",
       "        [ 6.8,  2.8,  4.8,  1.4],\n",
       "        [ 6.7,  3. ,  5. ,  1.7],\n",
       "        [ 6. ,  2.9,  4.5,  1.5],\n",
       "        [ 5.7,  2.6,  3.5,  1. ],\n",
       "        [ 5.5,  2.4,  3.8,  1.1],\n",
       "        [ 5.5,  2.4,  3.7,  1. ],\n",
       "        [ 5.8,  2.7,  3.9,  1.2],\n",
       "        [ 6. ,  2.7,  5.1,  1.6],\n",
       "        [ 5.4,  3. ,  4.5,  1.5],\n",
       "        [ 6. ,  3.4,  4.5,  1.6],\n",
       "        [ 6.7,  3.1,  4.7,  1.5],\n",
       "        [ 6.3,  2.3,  4.4,  1.3],\n",
       "        [ 5.6,  3. ,  4.1,  1.3],\n",
       "        [ 5.5,  2.5,  4. ,  1.3],\n",
       "        [ 5.5,  2.6,  4.4,  1.2],\n",
       "        [ 6.1,  3. ,  4.6,  1.4],\n",
       "        [ 5.8,  2.6,  4. ,  1.2],\n",
       "        [ 5. ,  2.3,  3.3,  1. ],\n",
       "        [ 5.6,  2.7,  4.2,  1.3],\n",
       "        [ 5.7,  3. ,  4.2,  1.2],\n",
       "        [ 5.7,  2.9,  4.2,  1.3],\n",
       "        [ 6.2,  2.9,  4.3,  1.3],\n",
       "        [ 5.1,  2.5,  3. ,  1.1],\n",
       "        [ 5.7,  2.8,  4.1,  1.3],\n",
       "        [ 6.3,  3.3,  6. ,  2.5],\n",
       "        [ 5.8,  2.7,  5.1,  1.9],\n",
       "        [ 7.1,  3. ,  5.9,  2.1],\n",
       "        [ 6.3,  2.9,  5.6,  1.8],\n",
       "        [ 6.5,  3. ,  5.8,  2.2],\n",
       "        [ 7.6,  3. ,  6.6,  2.1],\n",
       "        [ 4.9,  2.5,  4.5,  1.7],\n",
       "        [ 7.3,  2.9,  6.3,  1.8],\n",
       "        [ 6.7,  2.5,  5.8,  1.8],\n",
       "        [ 7.2,  3.6,  6.1,  2.5],\n",
       "        [ 6.5,  3.2,  5.1,  2. ],\n",
       "        [ 6.4,  2.7,  5.3,  1.9],\n",
       "        [ 6.8,  3. ,  5.5,  2.1],\n",
       "        [ 5.7,  2.5,  5. ,  2. ],\n",
       "        [ 5.8,  2.8,  5.1,  2.4],\n",
       "        [ 6.4,  3.2,  5.3,  2.3],\n",
       "        [ 6.5,  3. ,  5.5,  1.8],\n",
       "        [ 7.7,  3.8,  6.7,  2.2],\n",
       "        [ 7.7,  2.6,  6.9,  2.3],\n",
       "        [ 6. ,  2.2,  5. ,  1.5],\n",
       "        [ 6.9,  3.2,  5.7,  2.3],\n",
       "        [ 5.6,  2.8,  4.9,  2. ],\n",
       "        [ 7.7,  2.8,  6.7,  2. ],\n",
       "        [ 6.3,  2.7,  4.9,  1.8],\n",
       "        [ 6.7,  3.3,  5.7,  2.1],\n",
       "        [ 7.2,  3.2,  6. ,  1.8],\n",
       "        [ 6.2,  2.8,  4.8,  1.8],\n",
       "        [ 6.1,  3. ,  4.9,  1.8],\n",
       "        [ 6.4,  2.8,  5.6,  2.1],\n",
       "        [ 7.2,  3. ,  5.8,  1.6],\n",
       "        [ 7.4,  2.8,  6.1,  1.9],\n",
       "        [ 7.9,  3.8,  6.4,  2. ],\n",
       "        [ 6.4,  2.8,  5.6,  2.2],\n",
       "        [ 6.3,  2.8,  5.1,  1.5],\n",
       "        [ 6.1,  2.6,  5.6,  1.4],\n",
       "        [ 7.7,  3. ,  6.1,  2.3],\n",
       "        [ 6.3,  3.4,  5.6,  2.4],\n",
       "        [ 6.4,  3.1,  5.5,  1.8],\n",
       "        [ 6. ,  3. ,  4.8,  1.8],\n",
       "        [ 6.9,  3.1,  5.4,  2.1],\n",
       "        [ 6.7,  3.1,  5.6,  2.4],\n",
       "        [ 6.9,  3.1,  5.1,  2.3],\n",
       "        [ 5.8,  2.7,  5.1,  1.9],\n",
       "        [ 6.8,  3.2,  5.9,  2.3],\n",
       "        [ 6.7,  3.3,  5.7,  2.5],\n",
       "        [ 6.7,  3. ,  5.2,  2.3],\n",
       "        [ 6.3,  2.5,  5. ,  1.9],\n",
       "        [ 6.5,  3. ,  5.2,  2. ],\n",
       "        [ 6.2,  3.4,  5.4,  2.3],\n",
       "        [ 5.9,  3. ,  5.1,  1.8]]),\n",
       " 'feature_names': ['sepal length (cm)',\n",
       "  'sepal width (cm)',\n",
       "  'petal length (cm)',\n",
       "  'petal width (cm)'],\n",
       " 'target': array([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, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "        0, 0, 0, 0, 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, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "        1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\n",
       "        2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\n",
       "        2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2]),\n",
       " 'target_names': array(['setosa', 'versicolor', 'virginica'], \n",
       "       dtype='|S10')}"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "iris"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "X_iris = iris.data\n",
    "y_iris = iris.target\n",
    "\n",
    "# print X_iris, \"\\n\", y_iris"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "KMeans(copy_x=True, init='k-means++', max_iter=300, n_clusters=3, n_init=10,\n",
       "    n_jobs=1, precompute_distances='auto', random_state=None, tol=0.0001,\n",
       "    verbose=0)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Now we are going to find some clusters\n",
    "# You can get the KMeans function from cluster\n",
    "k_means = cluster.KMeans(n_clusters = 3)\n",
    "\n",
    "# Fit it to our data\n",
    "k_means.fit(X_iris)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0 0 0 0 0 1 1 1 1 1 2 2 2 2 2]\n"
     ]
    }
   ],
   "source": [
    "# Now lets compare\n",
    "print(k_means.labels_[::10])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0 0 0 0 0 1 1 1 1 1 2 2 2 2 2]\n"
     ]
    }
   ],
   "source": [
    "print(y_iris[::10])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "The same as the titanic problem, we can use a confusion matrix to see how good our predictions were."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "True \n",
      "\n",
      "[[50  0  0]\n",
      " [ 0 50  0]\n",
      " [ 0  0 50]]\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "X, y = iris.data, iris.target\n",
    "clf = KNeighborsClassifier(n_neighbors=1)\n",
    "clf.fit(X, y)\n",
    "y_pred = clf.predict(X)\n",
    "\n",
    "print(np.all(y == y_pred)), \"\\n\"\n",
    "\n",
    "from sklearn.metrics import confusion_matrix\n",
    "\n",
    "print(confusion_matrix(y, y_pred))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The output of the matrix above is actual on the left, and predicted on the top. So with this model there was PERFECT prediction. But remember, this is not correct as we need to split things between trianing and testing."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[ 8  0  0]\n",
      " [ 0 11  1]\n",
      " [ 0  0 18]]\n"
     ]
    }
   ],
   "source": [
    "from sklearn.cross_validation import train_test_split\n",
    "\n",
    "Xtrain, Xtest, ytrain, ytest = train_test_split(X, y)\n",
    "clf.fit(Xtrain, ytrain)\n",
    "ypred = clf.predict(Xtest)\n",
    "\n",
    "print(confusion_matrix(ytest, ypred))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Ohhh ... not as good, eh?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "==========\n",
      "Libsvm GUI\n",
      "==========\n",
      "\n",
      "A simple graphical frontend for Libsvm mainly intended for didactic\n",
      "purposes. You can create data points by point and click and visualize\n",
      "the decision region induced by different kernels and parameter settings.\n",
      "\n",
      "To create positive examples click the left mouse button; to create\n",
      "negative examples click the right button.\n",
      "\n",
      "If all examples are from the same class, it uses a one-class SVM.\n",
      "\n",
      "\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n",
      "fit the model\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Exception in Tkinter callback\n",
      "Traceback (most recent call last):\n",
      "  File \"/Users/robertdefilippi/miniconda2/lib/python2.7/lib-tk/Tkinter.py\", line 1536, in __call__\n",
      "    return self.func(*args)\n",
      "  File \"/Users/robertdefilippi/Google Drive/Programming/data-science-ipython-notebooks/fig_code/svm_gui.py\", line 87, in fit\n",
      "    X = train[:, 0:2]\n",
      "IndexError: too many indices for array\n"
     ]
    }
   ],
   "source": [
    "%run fig_code/svm_gui.py"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}