diff notebooks/sensitivity_experiment.ipynb @ 82:4395037087b6 branch-tests

notebooks
author mpanteli <m.x.panteli@gmail.com>
date Tue, 26 Sep 2017 21:18:26 +0100
parents 92a5e280946d
children e279ccea5f9b
line wrap: on
line diff
--- a/notebooks/sensitivity_experiment.ipynb	Tue Sep 26 14:37:28 2017 +0100
+++ b/notebooks/sensitivity_experiment.ipynb	Tue Sep 26 21:18:26 2017 +0100
@@ -3,11 +3,16 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ERROR! Session/line number was not unique in database. History logging moved to new session 32\n"
+     ]
+    },
+    {
      "name": "stderr",
      "output_type": "stream",
      "text": [
@@ -37,9 +42,7 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "OUTPUT_FILES = load_dataset.OUTPUT_FILES\n",
@@ -49,9 +52,7 @@
   {
    "cell_type": "code",
    "execution_count": 5,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -72,9 +73,7 @@
   {
    "cell_type": "code",
    "execution_count": 48,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -284,9 +283,7 @@
   {
    "cell_type": "code",
    "execution_count": 52,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -455,9 +452,7 @@
   {
    "cell_type": "code",
    "execution_count": 56,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -480,9 +475,7 @@
   {
    "cell_type": "code",
    "execution_count": 8,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -741,9 +734,7 @@
   {
    "cell_type": "code",
    "execution_count": 47,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -842,9 +833,7 @@
   {
    "cell_type": "code",
    "execution_count": 59,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -4591,9 +4580,7 @@
   {
    "cell_type": "code",
    "execution_count": 21,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -4943,9 +4930,7 @@
   {
    "cell_type": "code",
    "execution_count": 52,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -5271,9 +5256,7 @@
   {
    "cell_type": "code",
    "execution_count": 67,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -5613,7 +5596,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 68,
+   "execution_count": 7,
    "metadata": {
     "collapsed": true
    },
@@ -5630,10 +5613,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 69,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 8,
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -5641,7 +5622,7 @@
        "(137, 10)"
       ]
      },
-     "execution_count": 69,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -5659,10 +5640,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 70,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 9,
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -5702,6 +5681,7 @@
     "first_zero_idx = np.min(zero_idx)\n",
     "ranked_countries = ranked_countries.iloc[:first_zero_idx, :]\n",
     "ranked_outliers = ranked_outliers.iloc[:first_zero_idx, :]\n",
+    "ranked_countries_arr = ranked_countries.get_values()\n",
     "\n",
     "print ranked_countries.head()\n",
     "print ranked_outliers.head()"
@@ -5737,9 +5717,7 @@
   {
    "cell_type": "code",
    "execution_count": 72,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -5756,9 +5734,7 @@
   {
    "cell_type": "code",
    "execution_count": 80,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -5787,9 +5763,7 @@
   {
    "cell_type": "code",
    "execution_count": 81,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -5824,9 +5798,7 @@
   {
    "cell_type": "code",
    "execution_count": 76,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -5844,11 +5816,16 @@
    ]
   },
   {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Try precision at K"
+   ]
+  },
+  {
    "cell_type": "code",
-   "execution_count": 97,
-   "metadata": {
-    "collapsed": true
-   },
+   "execution_count": 10,
+   "metadata": {},
    "outputs": [],
    "source": [
     "# majority voting + precision at K (top5?)\n",
@@ -5859,10 +5836,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 98,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 11,
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -5915,7 +5890,7 @@
        "4   Bhutan   7"
       ]
      },
-     "execution_count": 98,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -5927,10 +5902,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 99,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 12,
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -6067,7 +6040,7 @@
        "9           Malta   1"
       ]
      },
-     "execution_count": 99,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -6078,20 +6051,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 102,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 14,
+   "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "0.51000000000000001"
-      ]
-     },
-     "execution_count": 102,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.51 0.0830662386292\n"
+     ]
     }
    ],
    "source": [
@@ -6104,7 +6072,27 @@
     "for j in range(ranked_countries_arr.shape[1]):\n",
     "    p_.append(precision_at_k(ranked_countries_arr[:, j], ground_truth, k))\n",
     "p_ = np.array(p_)\n",
-    "np.mean(p_)"
+    "print np.mean(p_), np.std(p_)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([ 0.6,  0.5,  0.5,  0.5,  0.5,  0.5,  0.5,  0.4,  0.7,  0.4])"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "p_"
    ]
   },
   {
@@ -6133,7 +6121,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython2",
-   "version": "2.7.11"
+   "version": "2.7.12"
   }
  },
  "nbformat": 4,