comparison notebooks/sensitivity_experiment.ipynb @ 47:081ff4ea7da7 branch-tests

sensitivity experiment split

 {
  "cells": [
   {
    "cell_type": "code",
    "execution_count": 15,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
      "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": [

       "60 44 44 44 60\n",
       "file 38 of 5037\n",
       "loading speech/music segments...\n",
       "extracting onset patterns and mfccs...\n",
       "extracting chroma...\n",
-      "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs/PB-melodia/\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs/PB-melodia/\n",
       "(45, 240)\n",
       "60 44 44 44 45\n",
       "file 39 of 5037\n",
       "loading speech/music segments...\n",
       "extracting onset patterns and mfccs...\n",

       "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs/PB-melodia/\n",
       "(45, 240)\n",
       "60 44 44 44 45\n",
       "file 77 of 5037\n",
       "loading speech/music segments...\n",
-      "extracting onset patterns and mfccs...\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "extracting onset patterns and mfccs...\n",
       "extracting chroma...\n",
       "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs_BL_old/PB-melodia/\n",
       "(60, 240)\n",
       "60 44 44 44 60\n",
       "file 78 of 5037\n",

       "60 44 44 44 45\n",
       "file 115 of 5037\n",
       "loading speech/music segments...\n",
       "extracting onset patterns and mfccs...\n",
       "extracting chroma...\n",
-      "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs/PB-melodia/\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs/PB-melodia/\n",
       "(45, 240)\n",
       "60 44 44 44 45\n",
       "file 116 of 5037\n",
       "loading speech/music segments...\n",
       "extracting onset patterns and mfccs...\n",

       "extracting chroma...\n",
       "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs/PB-melodia/\n",
       "(45, 240)\n",
       "60 44 44 44 45\n",
       "file 154 of 5037\n",
-      "loading speech/music segments...\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "loading speech/music segments...\n",
       "extracting onset patterns and mfccs...\n",
       "extracting chroma...\n",
       "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs/PB-melodia/\n",
       "(45, 240)\n",
       "60 44 44 44 45\n",

       "60 44 44 44 45\n",
       "file 192 of 5037\n",
       "loading speech/music segments...\n",
       "extracting onset patterns and mfccs...\n",
       "extracting chroma...\n",
-      "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs_BL_old/PB-melodia/\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs_BL_old/PB-melodia/\n",
       "(60, 240)\n",
       "60 44 44 44 60\n",
       "file 193 of 5037\n",
       "loading speech/music segments...\n",
       "extracting onset patterns and mfccs...\n",

       "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs/PB-melodia/\n",
       "(45, 240)\n",
       "60 44 44 44 45\n",
       "file 232 of 5037\n",
       "loading speech/music segments...\n",
-      "extracting onset patterns and mfccs...\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "extracting onset patterns and mfccs...\n",
       "extracting chroma...\n",
       "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs/PB-melodia/\n",
       "(45, 240)\n",
       "60 44 44 44 45\n",
       "file 233 of 5037\n",

       "60 44 44 44 45\n",
       "file 270 of 5037\n",
       "loading speech/music segments...\n",
       "extracting onset patterns and mfccs...\n",
       "extracting chroma...\n",
-      "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs/PB-melodia/\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs/PB-melodia/\n",
       "(45, 240)\n",
       "60 44 44 44 45\n",
       "file 271 of 5037\n",
       "loading speech/music segments...\n",
       "extracting onset patterns and mfccs...\n",

       "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs_BL_old/PB-melodia/\n",
       "(60, 240)\n",
       "60 44 44 44 60\n",
       "file 309 of 5037\n",
       "loading speech/music segments...\n",
-      "extracting onset patterns and mfccs...\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "extracting onset patterns and mfccs...\n",
       "extracting chroma...\n",
       "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs/PB-melodia/\n",
       "(45, 240)\n",
       "60 44 44 44 45\n",
       "file 310 of 5037\n",

       "60 44 44 44 45\n",
       "file 347 of 5037\n",
       "loading speech/music segments...\n",
       "extracting onset patterns and mfccs...\n",
       "extracting chroma...\n",
-      "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs/PB-melodia/\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs/PB-melodia/\n",
       "(45, 240)\n",
       "60 44 44 44 45\n",
       "file 348 of 5037\n",
       "loading speech/music segments...\n",
       "extracting onset patterns and mfccs...\n",

       "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs/PB-melodia/\n",
       "(45, 240)\n",
       "60 44 44 44 45\n",
       "file 386 of 5037\n",
       "loading speech/music segments...\n",
-      "extracting onset patterns and mfccs...\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "extracting onset patterns and mfccs...\n",
       "extracting chroma...\n",
       "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs/PB-melodia/\n",
       "(45, 240)\n",
       "60 44 44 44 45\n",
       "file 387 of 5037\n",

       "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs/PB-melodia/\n",
       "(45, 240)\n",
       "60 44 44 44 45\n",
       "file 425 of 5037\n",
       "loading speech/music segments...\n",
-      "extracting onset patterns and mfccs...\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "extracting onset patterns and mfccs...\n",
       "extracting chroma...\n",
       "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs/PB-melodia/\n",
       "(45, 240)\n",
       "60 44 44 44 45\n",
       "file 426 of 5037\n",

       "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs/PB-melodia/\n",
       "(45, 240)\n",
       "60 44 44 44 45\n",
       "file 464 of 5037\n",
       "loading speech/music segments...\n",
-      "extracting onset patterns and mfccs...\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "extracting onset patterns and mfccs...\n",
       "extracting chroma...\n",
       "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs/PB-melodia/\n",
       "(45, 240)\n",
       "60 44 44 44 45\n",
       "file 465 of 5037\n",

       "60 44 44 44 60\n",
       "file 502 of 5037\n",
       "loading speech/music segments...\n",
       "extracting onset patterns and mfccs...\n",
       "extracting chroma...\n",
-      "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs_BL_old/PB-melodia/\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
+      "load precomputed pitch bihist /import/c4dm-04/mariap/FeatureCsvs_BL_old/PB-melodia/\n",
       "(60, 240)\n",
       "60 44 44 44 60\n",
       "file 503 of 5037\n",
       "loading speech/music segments...\n",
       "extracting onset patterns and mfccs...\n",

     "    load_dataset.features_for_train_test_sets(df, write_output=True)"
    ]
   },
   {
    "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "MAPPER_OUTPUT_FILES = mapper.OUTPUT_FILES"
+   ]
+  },
+  {
+   "cell_type": "code",
    "execution_count": 3,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [

     "    print \"iteration %d\" % n\n",
     "    \n",
     "    print \"mapping...\"\n",
     "    mapper.INPUT_FILES = [output_file.split('.pickle')[0]+'_'+str(n)+'.pickle' for \n",
     "                                 output_file in OUTPUT_FILES]\n",
+    "    mapper.OUTPUT_FILES = [output_file.split('.pickle')[0]+'_'+str(n)+'.pickle' for \n",
+    "                                 output_file in MAPPER_OUTPUT_FILES]\n",
     "    _, _, ldadata_list, _, _, Y, Yaudio = mapper.lda_map_and_average_frames(min_variance=0.99)\n",
+    "    mapper.write_output([], [], ldadata_list, [], [], Y, Yaudio)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "CLASS_INPUT_FILES = [output_file.split('.pickle')[0]+'_'+str(n)+'.pickle' for \n",
+    "                                 output_file in mapper.OUTPUT_FILES]\n",
+    "mapper.OUTPUT_FILES = CLASS_INPUT_FILES\n",
+    "mapper.INPUT_FILES = OUTPUT_FILES\n",
+    "for n in range(n_iters):\n",
+    "    print \"iteration %d\" % n\n",
+    "    ldadata_list, Y, Yaudio = classification.load_data_from_pickle(CLASS_INPUT_FILES[2])\n",
     "    X = np.concatenate(ldadata_list, axis=1)\n",
-    "    \n",
     "    # classification and confusion\n",
     "    print \"classifying...\"\n",
-    "    traininds, testinds = classification.get_train_test_indices()\n",
+    "    traininds, testinds = classification.get_train_test_indices(Yaudio)\n",
     "    X_train, Y_train, X_test, Y_test = classification.get_train_test_sets(X, Y, traininds, testinds)\n",
     "    accuracy, _ = classification.confusion_matrix(X_train, Y_train, X_test, Y_test, saveCF=False, plots=False)\n",
     "    print accuracy\n",
     "    \n",
     "    # outliers\n",

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 5,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
        "(8089, 381)"

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 10,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 13,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 33,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [

    ]
   },
   {
    "cell_type": "code",
    "execution_count": 34,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
        "SpearmanrResult(correlation=1.0, pvalue=0.0)"