Volume analisys.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('photo_recognition_results.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "EXCLUDE_ALIASES = [\n",
    "    'COURVOISIER VS',\n",
    "    'COURVOISIER VSOP',\n",
    "    'COURVOISIER XO +',\n",
    "    'A.D FUSSIGNY',\n",
    "    'CAMUS',\n",
    "    'MARTELL',\n",
    "    'REMY MARTIN',\n",
    "    'HENNESSY',\n",
    "]\n",
    "\n",
    "REFERENCE_ALIASES = [\n",
    "    'AUCHENTOSHAN 18YO',\n",
    "    \"McCLELLAND'S HIGHLAND\",\n",
    "    \"McCLELLAND'S LOWLAND\",\n",
    "    'AUCHENTOSHAN 12YO',\n",
    "    \"McCLELLAND'S SPEYSIDE\",\n",
    "    'JIM BEAM RED STAG BLACK CHERRY',\n",
    "    'JIM BEAM APPLE',\n",
    "    'AUCHENTOSHAN AMERICAN OAK',\n",
    "    'AUCHENTOSHAN 3 WOOD',\n",
    "    'BOWMORE 12YO',\n",
    "    \"McCLELLAND'S ISLAY\",\n",
    "    'KILBEGGAN',\n",
    "    'JIM BEAM HONEY',\n",
    "    'MACALLAN 12YO DOUBLE CASK',\n",
    "    'MACALLAN 12YO TRIPLE CASK',\n",
    "    'MACALLAN 15YO TRIPLE CASK',\n",
    "    'MACALLAN 18YO TRIPLE CASK',\n",
    "    'MACALLAN RARE CASK',\n",
    "    'MACALLAN SHERRY OAK 12YO',\n",
    "    'MACALLAN SHERRY OAK 18YO',\n",
    "    'HIGHLAND PARK 10YO',\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>call_id</th>\n",
       "      <th>photo_id</th>\n",
       "      <th>recognition_alias</th>\n",
       "      <th>count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>452592</td>\n",
       "      <td>1317053</td>\n",
       "      <td>JOHNNIE WALKER</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>452592</td>\n",
       "      <td>1317053</td>\n",
       "      <td>other</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>452592</td>\n",
       "      <td>1317053</td>\n",
       "      <td>AUCHENTOSHAN AMERICAN OAK</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>452592</td>\n",
       "      <td>1317053</td>\n",
       "      <td>GLENFIDDICH</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>452592</td>\n",
       "      <td>1317053</td>\n",
       "      <td>MARTELL</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   call_id  photo_id          recognition_alias  count\n",
       "0   452592   1317053             JOHNNIE WALKER      1\n",
       "1   452592   1317053                      other     16\n",
       "2   452592   1317053  AUCHENTOSHAN AMERICAN OAK      1\n",
       "3   452592   1317053                GLENFIDDICH      2\n",
       "4   452592   1317053                    MARTELL      1"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "photos = dict()\n",
    "for _, row in df.iterrows():\n",
    "    if row['recognition_alias'] == 'other':\n",
    "        continue\n",
    "    if row['photo_id'] not in photos:\n",
    "        photos[row['photo_id']] = [row['recognition_alias']]\n",
    "    else:\n",
    "        photos[row['photo_id']].append(row['recognition_alias'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1073"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "without_ref_count = 0\n",
    "reference_set = set(REFERENCE_ALIASES)\n",
    "exclude_set = set(EXCLUDE_ALIASES)\n",
    "for k, v in photos.items():\n",
    "    aliases = set(v)\n",
    "    if not reference_set.intersection(aliases) and not aliases.issubset(exclude_set):\n",
    "        without_ref_count += 1\n",
    "\n",
    "without_ref_count"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.3757002801120448"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "without_ref_count / len(photos.keys())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}