model/02_Naive_Bayes_oversampling_uni_bigrams.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[nltk_data] Downloading package punkt to\n",
      "[nltk_data]     C:\\Users\\Boss\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package punkt is already up-to-date!\n",
      "[nltk_data] Downloading package stopwords to\n",
      "[nltk_data]     C:\\Users\\Boss\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package stopwords is already up-to-date!\n"
     ]
    }
   ],
   "source": [
    "# Import dependencies\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "\n",
    "# Plot confusion matrices\n",
    "import matplotlib as mpl \n",
    "import matplotlib.cm as cm \n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# NLP libraries\n",
    "import re\n",
    "import string\n",
    "import unicodedata\n",
    "import nltk\n",
    "nltk.download('punkt')\n",
    "from nltk.tokenize import word_tokenize\n",
    "from nltk.corpus import stopwords\n",
    "nltk.download('stopwords')\n",
    "stop_words_nltk = set(stopwords.words('english'))\n",
    "from nltk.stem.porter import PorterStemmer\n",
    "stemmer = PorterStemmer()\n",
    "\n",
    "# Machine learning\n",
    "import sklearn\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "from sklearn.naive_bayes import MultinomialNB\n",
    "\n",
    "# Evaluate the classifiers\n",
    "from sklearn import metrics\n",
    "from sklearn.metrics import accuracy_score\n",
    "from sklearn.metrics import confusion_matrix \n",
    "\n",
    "from sklearn.utils import resample\n",
    "\n",
    "# Import time function from time module to track the training duration\n",
    "from time import time"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Connect to database"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# SQL Alchemy\n",
    "from sqlalchemy import create_engine"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create engine and connection\n",
    "engine = create_engine(\"sqlite:///../db.sqlite\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['cuisine_ingredients']"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Check for tables\n",
    "engine.table_names()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Read in the data table\n",
    "df = pd.read_sql_query('SELECT * FROM cuisine_ingredients', con=engine)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>id</th>\n",
       "      <th>cuisine</th>\n",
       "      <th>recipe</th>\n",
       "      <th>full_ingredients</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>3727</th>\n",
       "      <td>3728</td>\n",
       "      <td>Italian</td>\n",
       "      <td>Spicy fregola with scallops and crispy kale</td>\n",
       "      <td>['olive oil, for shallow and deep frying', '1 ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1923</th>\n",
       "      <td>1924</td>\n",
       "      <td>Chinese</td>\n",
       "      <td>Chunky bacon and cucumber salad</td>\n",
       "      <td>['1 tbsp groundnut oil', '6 long dried chillie...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3552</th>\n",
       "      <td>3553</td>\n",
       "      <td>Italian</td>\n",
       "      <td>Polenta pork</td>\n",
       "      <td>['2 tbsp sunflower oil ', '12 rashers thick ri...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1146</th>\n",
       "      <td>1147</td>\n",
       "      <td>British</td>\n",
       "      <td>Oat fig stuffing</td>\n",
       "      <td>['140g/5oz butter', '100g/3½oz jumbo oats', '1...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3195</th>\n",
       "      <td>3196</td>\n",
       "      <td>Italian</td>\n",
       "      <td>Bolognese with tagliatelle</td>\n",
       "      <td>['250g/9oz 00 flour', '3-4 medium free-range e...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1643</th>\n",
       "      <td>1644</td>\n",
       "      <td>British</td>\n",
       "      <td>Textured potato salad</td>\n",
       "      <td>['675g/1½lb floury potatoes, peeled and cut in...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3054</th>\n",
       "      <td>3055</td>\n",
       "      <td>Indian</td>\n",
       "      <td>Tandoori lamb wrap</td>\n",
       "      <td>['150ml/5fl oz Greek-style yoghurt ', '½ small...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>842</th>\n",
       "      <td>843</td>\n",
       "      <td>British</td>\n",
       "      <td>Gammon and pease pudding</td>\n",
       "      <td>['300g/10oz dried yellow split peas', '50g/2oz...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>505</th>\n",
       "      <td>506</td>\n",
       "      <td>British</td>\n",
       "      <td>Braised shin of beef with parsnip purée</td>\n",
       "      <td>['4kg/9lb beef shin, on the bone', 'sea salt a...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2224</th>\n",
       "      <td>2225</td>\n",
       "      <td>French</td>\n",
       "      <td>Mary Berry's celeriac remoulade</td>\n",
       "      <td>['650g/1lb 7oz celeriac, peeled and sliced int...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        id  cuisine                                       recipe  \\\n",
       "3727  3728  Italian  Spicy fregola with scallops and crispy kale   \n",
       "1923  1924  Chinese              Chunky bacon and cucumber salad   \n",
       "3552  3553  Italian                                Polenta pork    \n",
       "1146  1147  British                             Oat fig stuffing   \n",
       "3195  3196  Italian                   Bolognese with tagliatelle   \n",
       "1643  1644  British                        Textured potato salad   \n",
       "3054  3055   Indian                           Tandoori lamb wrap   \n",
       "842    843  British                     Gammon and pease pudding   \n",
       "505    506  British      Braised shin of beef with parsnip purée   \n",
       "2224  2225   French              Mary Berry's celeriac remoulade   \n",
       "\n",
       "                                       full_ingredients  \n",
       "3727  ['olive oil, for shallow and deep frying', '1 ...  \n",
       "1923  ['1 tbsp groundnut oil', '6 long dried chillie...  \n",
       "3552  ['2 tbsp sunflower oil ', '12 rashers thick ri...  \n",
       "1146  ['140g/5oz butter', '100g/3½oz jumbo oats', '1...  \n",
       "3195  ['250g/9oz 00 flour', '3-4 medium free-range e...  \n",
       "1643  ['675g/1½lb floury potatoes, peeled and cut in...  \n",
       "3054  ['150ml/5fl oz Greek-style yoghurt ', '½ small...  \n",
       "842   ['300g/10oz dried yellow split peas', '50g/2oz...  \n",
       "505   ['4kg/9lb beef shin, on the bone', 'sea salt a...  \n",
       "2224  ['650g/1lb 7oz celeriac, peeled and sliced int...  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Overview of the data set\n",
    "df.sample(10, random_state=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['African',\n",
       " 'American',\n",
       " 'British',\n",
       " 'Caribbean',\n",
       " 'Chinese',\n",
       " 'East European',\n",
       " 'French',\n",
       " 'Greek',\n",
       " 'Indian',\n",
       " 'Irish',\n",
       " 'Italian',\n",
       " 'Japanese',\n",
       " 'Korean',\n",
       " 'Mexican',\n",
       " 'Nordic',\n",
       " 'North African',\n",
       " 'Pakistani',\n",
       " 'Portuguese',\n",
       " 'South American',\n",
       " 'Spanish',\n",
       " 'Thai and South-East Asian',\n",
       " 'Turkish and Middle Eastern']"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Get a list of unique cuisines in the dataset\n",
    "cuisine_list = df.cuisine.unique().tolist()\n",
    "cuisine_list"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Define text pre-processing function"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create a function to remove accented characters\n",
    "def remove_accented_chars(matchobj):\n",
    "    text = matchobj.group()\n",
    "    new_text = unicodedata.normalize('NFKD', text).encode('ascii', 'ignore').decode('utf-8', 'ignore')\n",
    "    return new_text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "words_to_remove = [\n",
    "    \"tbsp\", \"roughly\", \"chopped\", \"tsp\", \"finely\", \"oz\", \"plus\", \"optional\",\n",
    "    \"extra\", \"fresh\", \"freshly\", \"ground\", \"thinly\", \"sliced\", \"clove\", \"pint\",\n",
    "    \"cut\", \"kg\", \"lb\", \"cm\", \"ml\", \"mm\", \"small\", \"large\", \"medium\", \"diced\", \"slice\",\n",
    "    \"pinch\", \"peeled\", \"grated\", \"removed\", \"handful\", \"piece\", \"crushed\", \"red\", \"dried\",\n",
    "    \"drained\", \"rinsed\", \"halved\", \"trimmed\", \"deseeded\", \"x\", \"beaten\", \"available\", \"supermarket\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create a function to clean ingredient text\n",
    "def clean(doc):\n",
    "    doc = doc.str.lower()\n",
    "    doc = doc.str.replace(r'\\w*[\\d¼½¾⅓⅔⅛⅜⅝]\\w*', '')\n",
    "    doc = doc.str.translate(str.maketrans('', '', string.punctuation))\n",
    "    doc = doc.str.replace(r'[£×–‘’“”⁄]', '')\n",
    "    doc = doc.apply(lambda x: re.sub(r'[âãäçèéêîïñóôûüōưấớ]', remove_accented_chars, x))\n",
    "    doc = doc.apply(lambda x: word_tokenize(x))\n",
    "    doc = doc.apply(lambda x: [word for word in x if not word in stop_words_nltk])\n",
    "    doc = doc.apply(lambda x: [word for word in x if not word in words_to_remove])\n",
    "    doc = doc.apply(lambda x: [stemmer.stem(word) for word in x])\n",
    "    processed_doc = doc.apply(lambda x: ' '.join([word for word in x]))\n",
    "\n",
    "    return processed_doc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Add a new column to the dataframe with the cleaned text\n",
    "df[\"ingredients_processed\"] = clean(df.full_ingredients)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "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>id</th>\n",
       "      <th>cuisine</th>\n",
       "      <th>recipe</th>\n",
       "      <th>full_ingredients</th>\n",
       "      <th>ingredients_processed</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>3727</th>\n",
       "      <td>3728</td>\n",
       "      <td>Italian</td>\n",
       "      <td>Spicy fregola with scallops and crispy kale</td>\n",
       "      <td>['olive oil, for shallow and deep frying', '1 ...</td>\n",
       "      <td>oliv oil shallow deep fri shallot garlic chill...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1923</th>\n",
       "      <td>1924</td>\n",
       "      <td>Chinese</td>\n",
       "      <td>Chunky bacon and cucumber salad</td>\n",
       "      <td>['1 tbsp groundnut oil', '6 long dried chillie...</td>\n",
       "      <td>groundnut oil long chilli sichuan peppercorn w...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3552</th>\n",
       "      <td>3553</td>\n",
       "      <td>Italian</td>\n",
       "      <td>Polenta pork</td>\n",
       "      <td>['2 tbsp sunflower oil ', '12 rashers thick ri...</td>\n",
       "      <td>sunflow oil rasher thick rindless smoke streak...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1146</th>\n",
       "      <td>1147</td>\n",
       "      <td>British</td>\n",
       "      <td>Oat fig stuffing</td>\n",
       "      <td>['140g/5oz butter', '100g/3½oz jumbo oats', '1...</td>\n",
       "      <td>butter jumbo oat roll oat onion pistachio fig ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3195</th>\n",
       "      <td>3196</td>\n",
       "      <td>Italian</td>\n",
       "      <td>Bolognese with tagliatelle</td>\n",
       "      <td>['250g/9oz 00 flour', '3-4 medium free-range e...</td>\n",
       "      <td>flour freerang egg prefer bright yellow yolk f...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1643</th>\n",
       "      <td>1644</td>\n",
       "      <td>British</td>\n",
       "      <td>Textured potato salad</td>\n",
       "      <td>['675g/1½lb floury potatoes, peeled and cut in...</td>\n",
       "      <td>flouri potato cube rasher smoke streaki bacon ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3054</th>\n",
       "      <td>3055</td>\n",
       "      <td>Indian</td>\n",
       "      <td>Tandoori lamb wrap</td>\n",
       "      <td>['150ml/5fl oz Greek-style yoghurt ', '½ small...</td>\n",
       "      <td>greekstyl yoghurt onion garlic ginger garam ma...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>842</th>\n",
       "      <td>843</td>\n",
       "      <td>British</td>\n",
       "      <td>Gammon and pease pudding</td>\n",
       "      <td>['300g/10oz dried yellow split peas', '50g/2oz...</td>\n",
       "      <td>yellow split pea butter onion thyme bay leaf s...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>505</th>\n",
       "      <td>506</td>\n",
       "      <td>British</td>\n",
       "      <td>Braised shin of beef with parsnip purée</td>\n",
       "      <td>['4kg/9lb beef shin, on the bone', 'sea salt a...</td>\n",
       "      <td>beef shin bone sea salt black pepper oliv oil ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2224</th>\n",
       "      <td>2225</td>\n",
       "      <td>French</td>\n",
       "      <td>Mary Berry's celeriac remoulade</td>\n",
       "      <td>['650g/1lb 7oz celeriac, peeled and sliced int...</td>\n",
       "      <td>celeriac thin matchstick see tip lemon juic li...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        id  cuisine                                       recipe  \\\n",
       "3727  3728  Italian  Spicy fregola with scallops and crispy kale   \n",
       "1923  1924  Chinese              Chunky bacon and cucumber salad   \n",
       "3552  3553  Italian                                Polenta pork    \n",
       "1146  1147  British                             Oat fig stuffing   \n",
       "3195  3196  Italian                   Bolognese with tagliatelle   \n",
       "1643  1644  British                        Textured potato salad   \n",
       "3054  3055   Indian                           Tandoori lamb wrap   \n",
       "842    843  British                     Gammon and pease pudding   \n",
       "505    506  British      Braised shin of beef with parsnip purée   \n",
       "2224  2225   French              Mary Berry's celeriac remoulade   \n",
       "\n",
       "                                       full_ingredients  \\\n",
       "3727  ['olive oil, for shallow and deep frying', '1 ...   \n",
       "1923  ['1 tbsp groundnut oil', '6 long dried chillie...   \n",
       "3552  ['2 tbsp sunflower oil ', '12 rashers thick ri...   \n",
       "1146  ['140g/5oz butter', '100g/3½oz jumbo oats', '1...   \n",
       "3195  ['250g/9oz 00 flour', '3-4 medium free-range e...   \n",
       "1643  ['675g/1½lb floury potatoes, peeled and cut in...   \n",
       "3054  ['150ml/5fl oz Greek-style yoghurt ', '½ small...   \n",
       "842   ['300g/10oz dried yellow split peas', '50g/2oz...   \n",
       "505   ['4kg/9lb beef shin, on the bone', 'sea salt a...   \n",
       "2224  ['650g/1lb 7oz celeriac, peeled and sliced int...   \n",
       "\n",
       "                                  ingredients_processed  \n",
       "3727  oliv oil shallow deep fri shallot garlic chill...  \n",
       "1923  groundnut oil long chilli sichuan peppercorn w...  \n",
       "3552  sunflow oil rasher thick rindless smoke streak...  \n",
       "1146  butter jumbo oat roll oat onion pistachio fig ...  \n",
       "3195  flour freerang egg prefer bright yellow yolk f...  \n",
       "1643  flouri potato cube rasher smoke streaki bacon ...  \n",
       "3054  greekstyl yoghurt onion garlic ginger garam ma...  \n",
       "842   yellow split pea butter onion thyme bay leaf s...  \n",
       "505   beef shin bone sea salt black pepper oliv oil ...  \n",
       "2224  celeriac thin matchstick see tip lemon juic li...  "
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Overview of the dataset\n",
    "df.sample(10, random_state=2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Modeling"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Split the data into training and test sets (75% train, 25% test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(4724,) (4724,)\n"
     ]
    }
   ],
   "source": [
    "# The column contains textual data to extract features from.\n",
    "X = df.ingredients_processed\n",
    "\n",
    "# The column we're learning to predict.\n",
    "y = df.cuisine \n",
    "print(X.shape, y.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(3543,) (3543,)\n",
      "(1181,) (1181,)\n"
     ]
    }
   ],
   "source": [
    "# Split X and y into training and testing sets. By default, it splits 75% training and 25% test\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=1, stratify=y)\n",
    "print(X_train.shape, y_train.shape)\n",
    "print(X_test.shape, y_test.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Resampling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(3543, 2)"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Concatenate our training data back together\n",
    "X_y_train = pd.concat([X_train, y_train], axis=1)\n",
    "X_y_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "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>ingredients_processed</th>\n",
       "      <th>cuisine</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1948</th>\n",
       "      <td>white fish fillet sole plaic cornflour dust gr...</td>\n",
       "      <td>Chinese</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>921</th>\n",
       "      <td>oliv oil goodqual pork sausag shallot rosemari...</td>\n",
       "      <td>British</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4215</th>\n",
       "      <td>veget oil onion garlic root ginger tomato chil...</td>\n",
       "      <td>Pakistani</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2601</th>\n",
       "      <td>sirloin steak salt black pepper oliv oil butte...</td>\n",
       "      <td>French</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3770</th>\n",
       "      <td>type pasta flour bake section deli dust salt b...</td>\n",
       "      <td>Italian</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                  ingredients_processed    cuisine\n",
       "1948  white fish fillet sole plaic cornflour dust gr...    Chinese\n",
       "921   oliv oil goodqual pork sausag shallot rosemari...    British\n",
       "4215  veget oil onion garlic root ginger tomato chil...  Pakistani\n",
       "2601  sirloin steak salt black pepper oliv oil butte...     French\n",
       "3770  type pasta flour bake section deli dust salt b...    Italian"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Overview of the training set\n",
    "X_y_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Separate minority and majority classes\n",
    "british_cuisines_df = X_y_train[X_y_train.cuisine==\"British\"]\n",
    "other_cuisines_df = X_y_train[X_y_train.cuisine!=\"British\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "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>ingredients_processed</th>\n",
       "      <th>cuisine</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1948</th>\n",
       "      <td>white fish fillet sole plaic cornflour dust gr...</td>\n",
       "      <td>Chinese</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4215</th>\n",
       "      <td>veget oil onion garlic root ginger tomato chil...</td>\n",
       "      <td>Pakistani</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2601</th>\n",
       "      <td>sirloin steak salt black pepper oliv oil butte...</td>\n",
       "      <td>French</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3770</th>\n",
       "      <td>type pasta flour bake section deli dust salt b...</td>\n",
       "      <td>Italian</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3737</th>\n",
       "      <td>tagliatel broccoli floret hand pea frozen oliv...</td>\n",
       "      <td>Italian</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                  ingredients_processed    cuisine\n",
       "1948  white fish fillet sole plaic cornflour dust gr...    Chinese\n",
       "4215  veget oil onion garlic root ginger tomato chil...  Pakistani\n",
       "2601  sirloin steak salt black pepper oliv oil butte...     French\n",
       "3770  type pasta flour bake section deli dust salt b...    Italian\n",
       "3737  tagliatel broccoli floret hand pea frozen oliv...    Italian"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "other_cuisines_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Chinese',\n",
       " 'Pakistani',\n",
       " 'French',\n",
       " 'Italian',\n",
       " 'Japanese',\n",
       " 'Indian',\n",
       " 'Mexican',\n",
       " 'American',\n",
       " 'Nordic',\n",
       " 'Turkish and Middle Eastern',\n",
       " 'Caribbean',\n",
       " 'Thai and South-East Asian',\n",
       " 'North African',\n",
       " 'East European',\n",
       " 'Irish',\n",
       " 'Portuguese',\n",
       " 'Greek',\n",
       " 'South American',\n",
       " 'Spanish',\n",
       " 'Korean',\n",
       " 'African']"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Get a list of minority cuisines\n",
    "other_cuisines = other_cuisines_df.cuisine.unique().tolist()\n",
    "other_cuisines"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "other_cuisines_upsampled = list()\n",
    "\n",
    "# Upsample the minorities\n",
    "\n",
    "for cuisine in other_cuisines:\n",
    "    cuisine_df = X_y_train[X_y_train.cuisine==cuisine]\n",
    "    cuisine_upsampled = resample(cuisine_df,\n",
    "                                 replace=True, # sample with replacement\n",
    "                                 n_samples=len(british_cuisines_df), # match number of recipes in British cuisine\n",
    "                                 random_state=1)\n",
    "    other_cuisines_upsampled.append(cuisine_upsampled)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "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>ingredients_processed</th>\n",
       "      <th>cuisine</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1909</th>\n",
       "      <td>veget oil shallow fri firm tofu pat dri kitche...</td>\n",
       "      <td>Chinese</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2041</th>\n",
       "      <td>firm white fish fillet cod sole skin whole fis...</td>\n",
       "      <td>Chinese</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2019</th>\n",
       "      <td>shaox rice wine dri sherri light soy sauc clea...</td>\n",
       "      <td>Chinese</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1980</th>\n",
       "      <td>lobster sesam oil root ginger spring onion pak...</td>\n",
       "      <td>Chinese</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1999</th>\n",
       "      <td>pork minc ginger garlic spring onion soy sauc ...</td>\n",
       "      <td>Chinese</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                  ingredients_processed  cuisine\n",
       "1909  veget oil shallow fri firm tofu pat dri kitche...  Chinese\n",
       "2041  firm white fish fillet cod sole skin whole fis...  Chinese\n",
       "2019  shaox rice wine dri sherri light soy sauc clea...  Chinese\n",
       "1980  lobster sesam oil root ginger spring onion pak...  Chinese\n",
       "1999  pork minc ginger garlic spring onion soy sauc ...  Chinese"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Create a new resampled data set for minority cuisines\n",
    "other_cuisines_upsampled = pd.concat(other_cuisines_upsampled)\n",
    "other_cuisines_upsampled.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Combine the majority and the upsampled minority\n",
    "upsampled = pd.concat([british_cuisines_df, other_cuisines_upsampled])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "British                       1098\n",
       "Portuguese                    1098\n",
       "Chinese                       1098\n",
       "Irish                         1098\n",
       "South American                1098\n",
       "African                       1098\n",
       "Greek                         1098\n",
       "Mexican                       1098\n",
       "Thai and South-East Asian     1098\n",
       "Spanish                       1098\n",
       "Turkish and Middle Eastern    1098\n",
       "Korean                        1098\n",
       "Caribbean                     1098\n",
       "Indian                        1098\n",
       "Nordic                        1098\n",
       "Pakistani                     1098\n",
       "North African                 1098\n",
       "Japanese                      1098\n",
       "American                      1098\n",
       "East European                 1098\n",
       "Italian                       1098\n",
       "French                        1098\n",
       "Name: cuisine, dtype: int64"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# check new class counts\n",
    "upsampled.cuisine.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "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>ingredients_processed</th>\n",
       "      <th>cuisine</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4133</th>\n",
       "      <td>oliv oil fri chicken thigh onion garlic clove ...</td>\n",
       "      <td>North African</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3773</th>\n",
       "      <td>flour freerang italian yellow golden egg durum...</td>\n",
       "      <td>Italian</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2592</th>\n",
       "      <td>salt butter room temperatur caster sugar star ...</td>\n",
       "      <td>French</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4159</th>\n",
       "      <td>chicken joint piec oliv oil preserv lemon wash...</td>\n",
       "      <td>North African</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4204</th>\n",
       "      <td>ghee clarifi butter onion root ginger garlic c...</td>\n",
       "      <td>Pakistani</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3943</th>\n",
       "      <td>fillet beef garlic clove root ginger slice oni...</td>\n",
       "      <td>Korean</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4287</th>\n",
       "      <td>whole king prawn around oliv oil garlic clove ...</td>\n",
       "      <td>Spanish</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4046</th>\n",
       "      <td>oliv oil greas beef minc onion garlic clove ch...</td>\n",
       "      <td>Mexican</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2145</th>\n",
       "      <td>salmon fillet skin longgrain rice butter greas...</td>\n",
       "      <td>East European</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4413</th>\n",
       "      <td>duck breast skin veget oil dark soy sauc clear...</td>\n",
       "      <td>Thai and South-East Asian</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                  ingredients_processed  \\\n",
       "4133  oliv oil fri chicken thigh onion garlic clove ...   \n",
       "3773  flour freerang italian yellow golden egg durum...   \n",
       "2592  salt butter room temperatur caster sugar star ...   \n",
       "4159  chicken joint piec oliv oil preserv lemon wash...   \n",
       "4204  ghee clarifi butter onion root ginger garlic c...   \n",
       "3943  fillet beef garlic clove root ginger slice oni...   \n",
       "4287  whole king prawn around oliv oil garlic clove ...   \n",
       "4046  oliv oil greas beef minc onion garlic clove ch...   \n",
       "2145  salmon fillet skin longgrain rice butter greas...   \n",
       "4413  duck breast skin veget oil dark soy sauc clear...   \n",
       "\n",
       "                        cuisine  \n",
       "4133              North African  \n",
       "3773                    Italian  \n",
       "2592                     French  \n",
       "4159              North African  \n",
       "4204                  Pakistani  \n",
       "3943                     Korean  \n",
       "4287                    Spanish  \n",
       "4046                    Mexican  \n",
       "2145              East European  \n",
       "4413  Thai and South-East Asian  "
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Overview of the upsampled dataset\n",
    "upsampled.sample(10, random_state=2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Feature engineering using TF-IDF"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In bag of words and bag of n-grams approaches, all words in a corpus are treated equally important. TF-IDF, meanwhile, emphasizes that some words in a document are more important than others. This time, I'll try TF-IDF with unigram and bigrams."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "tfidf = TfidfVectorizer(ngram_range=(1,2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train_new = upsampled.ingredients_processed\n",
    "y_train_new = upsampled.cuisine"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(24156, 37955) (1181, 37955)\n"
     ]
    }
   ],
   "source": [
    "# Vectorize train and test data\n",
    "X_train_transformed = tfidf.fit_transform(X_train_new)\n",
    "X_test_transformed = tfidf.transform(X_test)\n",
    "print(X_train_transformed.shape, X_test_transformed.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Train the model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Wall time: 213 ms\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "MultinomialNB()"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Instantiate a Multinomial Naive Bayes model\n",
    "model = MultinomialNB()\n",
    "\n",
    "# Train the model\n",
    "%time model.fit(X_train_transformed, y_train_new)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Make class predictions for X_test_transformed\n",
    "y_predicted = model.predict(X_test_transformed)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Evaluate the model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy:  0.5901778154106689\n"
     ]
    }
   ],
   "source": [
    "#Print accuracy:\n",
    "print(\"Accuracy: \", accuracy_score(y_test, y_predicted))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Function to plot confusion matrix. \n",
    "# Ref: http://scikit-learn.org/stable/auto_examples/model_selection/plot_confusion_matrix.html\n",
    "import itertools\n",
    "from sklearn.metrics import roc_auc_score\n",
    "\n",
    "def plot_confusion_matrix(cm, classes,\n",
    "                          normalize=False,\n",
    "                          title='Confusion matrix',\n",
    "                          cmap=plt.cm.Blues):\n",
    "    \"\"\"\n",
    "    This function prints and plots the confusion matrix.\n",
    "    Normalization can be applied by setting `normalize=True`.\n",
    "    \"\"\"\n",
    "    if normalize:\n",
    "        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]\n",
    "\n",
    "    plt.imshow(cm, interpolation='nearest', cmap=cmap)\n",
    "    plt.title(title)\n",
    "    plt.colorbar()\n",
    "    tick_marks = np.arange(len(classes))\n",
    "    plt.xticks(tick_marks, classes, rotation=90)\n",
    "    plt.yticks(tick_marks, classes)\n",
    "\n",
    "    fmt = '.2f' if normalize else 'd'\n",
    "    thresh = cm.max() / 2.\n",
    "    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):\n",
    "        plt.text(j, i, format(cm[i, j], fmt),\n",
    "                 horizontalalignment=\"center\",\n",
    "                 color=\"white\" if cm[i, j] > thresh else \"black\")\n",
    "\n",
    "    plt.tight_layout()\n",
    "    plt.ylabel('True label',fontsize=15)\n",
    "    plt.xlabel('Predicted label',fontsize=15)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1152x864 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# print the confusion matrix\n",
    "cnf_matrix = confusion_matrix(y_test, y_predicted)\n",
    "plt.figure(figsize=(16, 12))\n",
    "plot_confusion_matrix(cnf_matrix, classes=cuisine_list, normalize=True,\n",
    "                      title='Confusion matrix with all features - Naive Bayes - oversampling - uni and bi-grams')\n",
    "plt.savefig(\"../static/images/cfm_nb_oversampling_uni_bi.png\", bbox_inches='tight')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The model performs much better than without oversampling. It predicts very well in Chinese, Indian, Japanese, Mexican, North African, Spanish, Thai and South-East Asian cuisines. It only misses out completely on Portuguese cuisine."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                            precision    recall  f1-score   support\n",
      "\n",
      "                   African       0.20      0.33      0.25         6\n",
      "                  American       0.44      0.55      0.49        78\n",
      "                   British       0.80      0.42      0.55       366\n",
      "                 Caribbean       0.38      0.75      0.51        20\n",
      "                   Chinese       0.85      0.88      0.86        50\n",
      "             East European       0.30      0.42      0.35        19\n",
      "                    French       0.39      0.48      0.43       122\n",
      "                     Greek       0.40      0.53      0.46        15\n",
      "                    Indian       0.83      0.85      0.84        98\n",
      "                     Irish       0.14      0.25      0.18         8\n",
      "                   Italian       0.77      0.69      0.73       178\n",
      "                  Japanese       0.89      0.81      0.85        21\n",
      "                    Korean       0.40      0.40      0.40         5\n",
      "                   Mexican       0.59      0.84      0.69        31\n",
      "                    Nordic       0.13      0.55      0.21        11\n",
      "             North African       0.42      0.74      0.54        19\n",
      "                 Pakistani       0.25      0.25      0.25         8\n",
      "                Portuguese       0.00      0.00      0.00         4\n",
      "            South American       1.00      0.40      0.57         5\n",
      "                   Spanish       0.29      0.78      0.42        27\n",
      " Thai and South-East Asian       0.83      0.88      0.85        56\n",
      "Turkish and Middle Eastern       0.65      0.50      0.57        34\n",
      "\n",
      "                  accuracy                           0.59      1181\n",
      "                 macro avg       0.50      0.56      0.50      1181\n",
      "              weighted avg       0.67      0.59      0.60      1181\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Calculate classification report\n",
    "from sklearn.metrics import classification_report\n",
    "\n",
    "print(classification_report(y_test, y_predicted,\n",
    "                            target_names=cuisine_list))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:PythonAdv] *",
   "language": "python",
   "name": "conda-env-PythonAdv-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}