{
 "cells": [
  {
   "cell_type": "heading",
   "metadata": {},
   "level": 1,
   "source": [
    "Loading an example dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "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"
     ]
    }
   ],
   "source": [
    "from sklearn import datasets\n",
    "iris = datasets.load_iris()\n",
    "digits = datasets.load_digits()\n",
    "\n",
    "print(digits.data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 1, 2, ..., 8, 9, 8])"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "digits.target"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "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": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "digits.images[0]"
   ]
  },
  {
   "cell_type": "heading",
   "metadata": {},
   "level": 1,
   "source": [
    "Learning and predicting"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SVC(C=100.0, 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": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn import svm\n",
    "clf = svm.SVC(gamma = 0.001,C=100.)\n",
    "clf.fit(digits.data[:-1],digits.target[:-1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([8])"
      ]
     },
     "execution_count": 98,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clf.predict(digits.data[-1:])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,\n  decision_function_shape=None, degree=3, gamma='auto', kernel='rbf',\n  max_iter=-1, probability=False, random_state=None, shrinking=True,\n  tol=0.001, verbose=False)\n0\n"
     ]
    }
   ],
   "source": [
    "from sklearn import svm\n",
    "from sklearn import datasets\n",
    "clf = svm.SVC()\n",
    "iris = datasets.load_iris()\n",
    "X,y = iris.data,iris.target\n",
    "print(clf.fit(X,y))\n",
    "\n",
    "import pickle\n",
    "s = pickle.dumps(clf)\n",
    "clf2 = pickle.loads(s)\n",
    "clf2.predict(X[0:1])\n",
    "print(y[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['data/filename.pkl']"
      ]
     },
     "execution_count": 100,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.externals import joblib\n",
    "joblib.dump(clf,'data/filename.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,\n  decision_function_shape=None, degree=3, gamma='auto', kernel='rbf',\n  max_iter=-1, probability=False, random_state=None, shrinking=True,\n  tol=0.001, verbose=False)\n"
     ]
    }
   ],
   "source": [
    "clf = joblib.load('data/filename.pkl')\n",
    "print(clf)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "float32\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "float64\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "from sklearn import random_projection\n",
    "rng = np.random.RandomState(0)\n",
    "X = rng.rand(10,2000)\n",
    "X = np.array(X,dtype='float32')\n",
    "X.dtype\n",
    "print(X.dtype)\n",
    "\n",
    "transformer = random_projection.GaussianRandomProjection()\n",
    "X_new = transformer.fit_transform(X)\n",
    "X_new.dtype\n",
    "print(X_new.dtype)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,\n  decision_function_shape=None, degree=3, gamma='auto', kernel='rbf',\n  max_iter=-1, probability=False, random_state=None, shrinking=True,\n  tol=0.001, verbose=False)"
      ]
     },
     "execution_count": 103,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn import datasets\n",
    "from sklearn.svm import SVC\n",
    "iris = datasets.load_iris()\n",
    "clf = SVC()\n",
    "clf.fit(iris.data,iris.target)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0, 0, 0]"
      ]
     },
     "execution_count": 104,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list(clf.predict(iris.data[:3]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,\n  decision_function_shape=None, degree=3, gamma='auto', kernel='rbf',\n  max_iter=-1, probability=False, random_state=None, shrinking=True,\n  tol=0.001, verbose=False)"
      ]
     },
     "execution_count": 105,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clf.fit(iris.data,iris.target_names[iris.target])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['setosa', 'setosa', 'setosa']"
      ]
     },
     "execution_count": 106,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list(clf.predict(iris.data[:3]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,\n  decision_function_shape=None, degree=3, gamma='auto', kernel='linear',\n  max_iter=-1, probability=False, random_state=None, shrinking=True,\n  tol=0.001, verbose=False)"
      ]
     },
     "execution_count": 107,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import numpy as np\n",
    "from sklearn.svm import SVC\n",
    "\n",
    "rng = np.random.RandomState(0)\n",
    "X = rng.rand(100, 10)\n",
    "y = rng.binomial(1, 0.5, 100)\n",
    "X_test = rng.rand(5, 10)\n",
    "clf = SVC()\n",
    "clf.set_params(kernel='linear').fit(X,y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 0, 1, 1, 0])"
      ]
     },
     "execution_count": 108,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clf.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,\n  decision_function_shape=None, degree=3, gamma='auto', kernel='rbf',\n  max_iter=-1, probability=False, random_state=None, shrinking=True,\n  tol=0.001, verbose=False)"
      ]
     },
     "execution_count": 109,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clf.set_params(kernel='rbf').fit(X,y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 0, 1, 0])"
      ]
     },
     "execution_count": 110,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clf.predict(X_test)"
   ]
  },
  {
   "cell_type": "heading",
   "metadata": {},
   "level": 1,
   "source": [
    "Muliclass vs. multilabel fitting"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 1, 1, 2])"
      ]
     },
     "execution_count": 111,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.svm import SVC\n",
    "from sklearn.multiclass import OneVsRestClassifier\n",
    "from sklearn.preprocessing import LabelBinarizer\n",
    "X = [[1,2],[2,4],[4,5],[3,2],[3,1]]\n",
    "y = [0,0,1,1,2]\n",
    "classif = OneVsRestClassifier(estimator=SVC(random_state=0))\n",
    "classif.fit(X,y).predict(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1, 0, 0],\n       [1, 0, 0],\n       [0, 1, 0],\n       [0, 0, 0],\n       [0, 0, 0]])"
      ]
     },
     "execution_count": 112,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y = LabelBinarizer().fit_transform(y)\n",
    "classif.fit(X,y).predict(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1, 1, 0, 0, 0],\n       [1, 0, 1, 0, 0],\n       [0, 1, 0, 1, 0],\n       [1, 0, 1, 0, 0],\n       [1, 0, 1, 0, 0]])"
      ]
     },
     "execution_count": 113,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.preprocessing import MultiLabelBinarizer\n",
    "y =[ [0,1],[0,2],[1,3],[0,2,3],[2,4]]\n",
    "y = MultiLabelBinarizer().fit_transform(y)\n",
    "classif.fit(X,y).predict(X)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2.0
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}