diff notebooks/sensitivity_experiment.ipynb @ 15:9847b954c217 branch-tests

added sensitivity experiment

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/notebooks/sensitivity_experiment.ipynb	Tue Sep 12 19:03:48 2017 +0100
@@ -0,0 +1,143 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/mariapanteli/anaconda/lib/python2.7/site-packages/librosa/core/audio.py:33: UserWarning: Could not import scikits.samplerate. Falling back to scipy.signal\n",
+      "  warnings.warn('Could not import scikits.samplerate. '\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "\n",
+    "%matplotlib inline\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "%load_ext autoreload\n",
+    "%autoreload 2\n",
+    "\n",
+    "import sys\n",
+    "sys.path.append('../')\n",
+    "import scripts.load_dataset as load_dataset\n",
+    "import scripts.map_and_average as mapper\n",
+    "import scripts.results_classification as results_class\n",
+    "import scripts.results as results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "OUTPUT_FILES = ['/import/c4dm-04/mariap/train_data_melodia_'+str(WIN_SIZE)+'.pickle', \n",
+    "                '/import/c4dm-04/mariap/val_data_melodia_'+str(WIN_SIZE)+'.pickle', \n",
+    "                '/import/c4dm-04/mariap/test_data_melodia_'+str(WIN_SIZE)+'.pickle']\n",
+    "n_iters = 10"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "ename": "IOError",
+     "evalue": "File data/metadata_BLSM_language_all.csv does not exist",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mIOError\u001b[0m                                   Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-5-8d1030af886f>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mn\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mn_iters\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m     \u001b[0mdf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_dataset\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msample_dataset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcsv_file\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mload_dataset\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mMETADATA_FILE\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      3\u001b[0m     load_dataset.OUTPUT_FILES = [output_file.split('.pickle')[0]+'_'+str(n)+'.pickle' for \n\u001b[1;32m      4\u001b[0m                                  output_file in load_dataset.OUTPUT_FILES]\n\u001b[1;32m      5\u001b[0m     \u001b[0mload_dataset\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfeatures_for_train_test_sets\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwrite_output\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/Users/mariapanteli/Documents/QMUL/Code/MyPythonCode/plosone_underreview/scripts/load_dataset.py\u001b[0m in \u001b[0;36msample_dataset\u001b[0;34m(csv_file)\u001b[0m\n\u001b[1;32m    130\u001b[0m         \u001b[0mThe\u001b[0m \u001b[0mmetadata\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mthe\u001b[0m \u001b[0mselected\u001b[0m \u001b[0msubset\u001b[0m \u001b[0mof\u001b[0m \u001b[0mtracks\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    131\u001b[0m     \"\"\"\n\u001b[0;32m--> 132\u001b[0;31m     \u001b[0mdf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread_csv\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcsv_file\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    133\u001b[0m     \u001b[0mdf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mutil_filter_dataset\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mremove_missing_data\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    134\u001b[0m     \u001b[0msubset_idx\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msubset_labels\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Country'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_values\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/Users/mariapanteli/anaconda/lib/python2.7/site-packages/pandas/io/parsers.pyc\u001b[0m in \u001b[0;36mparser_f\u001b[0;34m(filepath_or_buffer, sep, dialect, compression, doublequote, escapechar, quotechar, quoting, skipinitialspace, lineterminator, header, index_col, names, prefix, skiprows, skipfooter, skip_footer, na_values, na_fvalues, true_values, false_values, delimiter, converters, dtype, usecols, engine, delim_whitespace, as_recarray, na_filter, compact_ints, use_unsigned, low_memory, buffer_lines, warn_bad_lines, error_bad_lines, keep_default_na, thousands, comment, decimal, parse_dates, keep_date_col, dayfirst, date_parser, memory_map, float_precision, nrows, iterator, chunksize, verbose, encoding, squeeze, mangle_dupe_cols, tupleize_cols, infer_datetime_format, skip_blank_lines)\u001b[0m\n\u001b[1;32m    463\u001b[0m                     skip_blank_lines=skip_blank_lines)\n\u001b[1;32m    464\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 465\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0m_read\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    466\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    467\u001b[0m     \u001b[0mparser_f\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__name__\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/Users/mariapanteli/anaconda/lib/python2.7/site-packages/pandas/io/parsers.pyc\u001b[0m in \u001b[0;36m_read\u001b[0;34m(filepath_or_buffer, kwds)\u001b[0m\n\u001b[1;32m    239\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    240\u001b[0m     \u001b[0;31m# Create the parser.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 241\u001b[0;31m     \u001b[0mparser\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mTextFileReader\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    242\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    243\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mnrows\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mNone\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mchunksize\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/Users/mariapanteli/anaconda/lib/python2.7/site-packages/pandas/io/parsers.pyc\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, f, engine, **kwds)\u001b[0m\n\u001b[1;32m    555\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moptions\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'has_index_names'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mkwds\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'has_index_names'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    556\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 557\u001b[0;31m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_make_engine\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mengine\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    558\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    559\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_get_options_with_defaults\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mengine\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/Users/mariapanteli/anaconda/lib/python2.7/site-packages/pandas/io/parsers.pyc\u001b[0m in \u001b[0;36m_make_engine\u001b[0;34m(self, engine)\u001b[0m\n\u001b[1;32m    692\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_make_engine\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mengine\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'c'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    693\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mengine\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;34m'c'\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 694\u001b[0;31m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mCParserWrapper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mf\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moptions\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    695\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    696\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mengine\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;34m'python'\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/Users/mariapanteli/anaconda/lib/python2.7/site-packages/pandas/io/parsers.pyc\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, src, **kwds)\u001b[0m\n\u001b[1;32m   1059\u001b[0m         \u001b[0mkwds\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'allow_leading_cols'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mindex_col\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mFalse\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1060\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1061\u001b[0;31m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_reader\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_parser\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTextReader\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msrc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1062\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1063\u001b[0m         \u001b[0;31m# XXX\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32mpandas/parser.pyx\u001b[0m in \u001b[0;36mpandas.parser.TextReader.__cinit__ (pandas/parser.c:3163)\u001b[0;34m()\u001b[0m\n",
+      "\u001b[0;32mpandas/parser.pyx\u001b[0m in \u001b[0;36mpandas.parser.TextReader._setup_parser_source (pandas/parser.c:5779)\u001b[0;34m()\u001b[0m\n",
+      "\u001b[0;31mIOError\u001b[0m: File data/metadata_BLSM_language_all.csv does not exist"
+     ]
+    }
+   ],
+   "source": [
+    "for n in range(n_iters):\n",
+    "    print \"iteration %d\" % n\n",
+    "    df = load_dataset.sample_dataset(csv_file=load_dataset.METADATA_FILE)\n",
+    "    load_dataset.OUTPUT_FILES = [output_file.split('.pickle')[0]+'_'+str(n)+'.pickle' for \n",
+    "                                 output_file in OUTPUT_FILES]\n",
+    "    load_dataset.features_for_train_test_sets(df, write_output=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "for n in range(n_iters):\n",
+    "    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",
+    "    _, _, ldadata_list, _, _, Y, Yaudio = mapper.lda_map_and_average_frames(min_variance=0.99)\n",
+    "    X = np.concatenate(ldadata_list)\n",
+    "    \n",
+    "    # classification and confusion\n",
+    "    print \"classifying...\"\n",
+    "    traininds, testinds = results_class.get_train_test_indices()\n",
+    "    X_train, Y_train, X_test, Y_test = results_class.get_train_test_sets(X, Y, traininds, testinds)\n",
+    "    accuracy, _ = results_class.confusion_matrix(X_train, Y_train, X_test, Y_test, saveCF=False, plots=False)\n",
+    "    print accuracy\n",
+    "    \n",
+    "    # outliers\n",
+    "    print \"detecting outliers...\"\n",
+    "    ddf = results.load_metadata(Yaudio, metadata_file=load_dataset.METADATA_FILE)\n",
+    "    df_global, threshold, MD = get_outliers_df(X, Y, chi2thr=0.999)\n",
+    "    print_most_least_outliers_topN(df_global, N=10)\n",
+    "    \n",
+    "    # write output\n",
+    "    print \"writing file\"\n",
+    "    df_global.to_csv('../data/outliers_'+str(n)+'.csv', index=False)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 2",
+   "language": "python",
+   "name": "python2"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}