comparison notebooks/sensitivity_experiment.ipynb @ 73:92a5e280946d branch-tests

?

 {
  "cells": [
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 5,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
        "(8396, 108)"

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 48,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 52,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 56,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
        "array([ 59,   1,   1,   1,   1, 733, 733, 733, 733, 733, 733, 733, 733,\n",

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 8,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
       "text/html": [
        "<div>\n",

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 47,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 59,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 21,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [

       "13          Germany  0.040000        100           4\n",
       "31      Afghanistan  0.041667         24           1\n",
       "105           Sudan  0.045455         66           3\n",
       "120      Kazakhstan  0.045455         88           4\n",
       "writing file\n",
-      "iteration 7\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "iteration 7\n",
       "classifying...\n",
       "/import/c4dm-04/mariap/train_data_melodia_8_7.pickle\n",
       "0.179777654473\n",
       "detecting outliers...\n",
       "most outliers \n",

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 52,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [

       "13          Germany  0.040000        100           4\n",
       "31      Afghanistan  0.041667         24           1\n",
       "105           Sudan  0.045455         66           3\n",
       "120      Kazakhstan  0.045455         88           4\n",
       "writing file\n",
-      "iteration 7\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "iteration 7\n",
       "(8048, 381) (8048,)\n",
       "detecting outliers...\n",
       "most outliers \n",
       "         Country  Outliers  N_Country  N_Outliers\n",
       "136     Botswana  0.636364         88          56\n",

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 67,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [

       "109  Democratic Republic of the Congo  0.052632         38           2\n",
       "51                            Finland  0.052632         19           1\n",
       "105                             Sudan  0.055556         54           3\n",
       "writing file\n",
       "iteration 6\n",
-      "/import/c4dm-04/mariap/lda_data_melodia_8.pickle\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "/import/c4dm-04/mariap/lda_data_melodia_8.pickle\n",
       "(6560, 380) (6560,)\n",
       "detecting outliers...\n",
       "most outliers \n",
       "           Country  Outliers  N_Country  N_Outliers\n",
       "60            Chad  0.666667          9           6\n",

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 69,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
        "(137, 10)"

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 70,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 71,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "from scipy.stats import kendalltau\n",
     "r_, p_ = [], []\n",
     "ranked_countries_arr = ranked_countries.get_values()\n",

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 72,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 80,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 81,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 76,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
        "{'Chad', 'French Guiana', 'Gambia'}"

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 97,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "# majority voting + precision at K (top5?)\n",
     "from collections import Counter\n",
     "K_vote = 10\n",

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 98,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
       "text/html": [
        "<div>\n",

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 99,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
       "text/html": [
        "<div>\n",

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 102,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
        "0.51000000000000001"

    "file_extension": ".py",
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython2",
-   "version": "2.7.12"
+   "version": "2.7.11"
   }
  },
  "nbformat": 4,
  "nbformat_minor": 1
 }