{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Matching a target sample to a database"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sppysound.database import AudioDatabase, Matcher\n",
    "import matching_config"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "source_dir = \"./ExampleDatabase\"\n",
    "target_dir = \"./ExampleTarget\"\n",
    "output_dir = \"./ExampleOutput\"\n",
    "analysis_list = [\"rms\", \"f0\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Load source and target databases for matching..."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "source_database = AudioDatabase(\n",
    "    source_dir, \n",
    "    analysis_list=analysis_list, \n",
    "    config=matching_config\n",
    ")\n",
    "source_database.load_database(reanalyse=True)\n",
    "target_database = AudioDatabase(\n",
    "    target_dir, \n",
    "    analysis_list=analysis_list, \n",
    "    config=matching_config\n",
    ")\n",
    "target_database.load_database(reanalyse=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "An output database must also be defined. This is to store matching results and synthesis results generated later.\n",
    "Note that an analysis list was not defined for this as it will not be analysed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "output_database = AudioDatabase(output_dir, config=matching_config)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The database must still be loaded to check for previous HDF5 files to use for results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "output_database.load_database(reanalyse=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "A matcher object is then created using the loaded databases, ready to perform matching. The rematch argument can be set to discard any previously found matches from pre-existing HDF5 files, otherwise previously found matches will cause the program to terminate for their preservation."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "matcher = Matcher(\n",
    "    source_database,\n",
    "    target_database,\n",
    "    output_db=output_database,\n",
    "    config=matching_config,\n",
    "    rematch=True\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The matching is then run using the brute force matcher method. Other methods are not currently available.\n",
    "\n",
    "Warnings may be produced during this process. These will be silenced in a future revision but do not affect results."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "matcher.match(\n",
    "    matcher.kdtree_matcher,\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The output database will now contain a HDF5 file containing matching data for the two databases. This can be used to synthesize results."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The matching_config file for this demo is:\n",
    "\n",
    "~~~python\n",
    "rms = {\n",
    "    \"window_size\": 100,\n",
    "    \"overlap\": 2,\n",
    "}\n",
    "\n",
    "analysis_dict = {\n",
    "    \"f0\": \"log2_median\",\n",
    "    \"rms\": \"mean\"\n",
    "}\n",
    "\n",
    "matcher_weightings = {\n",
    "    \"f0\" : 1.,\n",
    "    \"rms\": 1.\n",
    "}\n",
    "\n",
    "analysis = {\n",
    "    \"reanalyse\": False\n",
    "}\n",
    "\n",
    "matcher = {\n",
    "    \"rematch\": False,\n",
    "    \"grain_size\": 100,\n",
    "    \"overlap\": 2,\n",
    "    # Defines the number of matches to keep for synthesis.\n",
    "    \"match_quantity\": 20\n",
    "}\n",
    "\n",
    "output_file = {\n",
    "    \"samplerate\": 44100,\n",
    "    \"format\": 131075,\n",
    "    \"channels\": 1\n",
    "}\n",
    "~~~"
   ]
  }
 ],
 "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": "2.7.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}