{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## RCV1-v2 Dataset [source here](http://www.jmlr.org/papers/volume5/lewis04a/lyrl2004_rcv1v2_README.htm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import logging\n",
    "\n",
    "from sklearn.datasets import fetch_rcv1\n",
    "from sklearn.multiclass import OneVsRestClassifier\n",
    "from sklearn.metrics import f1_score, precision_score, recall_score\n",
    "from sklearn.pipeline import Pipeline\n",
    "from sklearn import svm\n",
    "\n",
    "logging.basicConfig()\n",
    "rcv1 = fetch_rcv1()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "training_samples = 23149\n",
    "\n",
    "X_train = rcv1.data[:training_samples]\n",
    "X_test = rcv1.data[training_samples:]\n",
    "\n",
    "y_train = rcv1.target[:training_samples]\n",
    "y_test = rcv1.target[training_samples:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "clf = OneVsRestClassifier(svm.LinearSVC(penalty='l1',tol=0.01,multi_class='crammer_singer',dual=False))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/felipe/venv2/local/lib/python2.7/site-packages/sklearn/multiclass.py:70: UserWarning: Label not 49 is present in all training examples.\n",
      "  str(classes[c]))\n",
      "/home/felipe/venv2/local/lib/python2.7/site-packages/sklearn/multiclass.py:70: UserWarning: Label not 80 is present in all training examples.\n",
      "  str(classes[c]))\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "OneVsRestClassifier(estimator=LinearSVC(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
       "     intercept_scaling=1, loss='squared_hinge', max_iter=1000,\n",
       "     multi_class='crammer_singer', penalty='l1', random_state=None,\n",
       "     tol=0.01, verbose=0),\n",
       "          n_jobs=1)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clf.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "y_pred = clf.predict(X_test)\n",
    "\n",
    "current_score = f1_score(y_test,y_pred,average='micro')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.80843419139591599"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "current_score"
   ]
  }
 ],
 "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": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}