{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Build Classification Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.model_selection import train_test_split, cross_val_score\n",
    "from sklearn.metrics import accuracy_score,precision_score,confusion_matrix,classification_report, precision_recall_curve\n",
    "from sklearn.svm import SVC\n",
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "   Unnamed: 0 cuisine  almond  angelica  anise  anise_seed  apple  \\\n",
       "0           0  indian       0         0      0           0      0   \n",
       "1           1  indian       1         0      0           0      0   \n",
       "2           2  indian       0         0      0           0      0   \n",
       "3           3  indian       0         0      0           0      0   \n",
       "4           4  indian       0         0      0           0      0   \n",
       "\n",
       "   apple_brandy  apricot  armagnac  ...  whiskey  white_bread  white_wine  \\\n",
       "0             0        0         0  ...        0            0           0   \n",
       "1             0        0         0  ...        0            0           0   \n",
       "2             0        0         0  ...        0            0           0   \n",
       "3             0        0         0  ...        0            0           0   \n",
       "4             0        0         0  ...        0            0           0   \n",
       "\n",
       "   whole_grain_wheat_flour  wine  wood  yam  yeast  yogurt  zucchini  \n",
       "0                        0     0     0    0      0       0         0  \n",
       "1                        0     0     0    0      0       0         0  \n",
       "2                        0     0     0    0      0       0         0  \n",
       "3                        0     0     0    0      0       0         0  \n",
       "4                        0     0     0    0      0       1         0  \n",
       "\n",
       "[5 rows x 382 columns]"
      ],
      "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>Unnamed: 0</th>\n      <th>cuisine</th>\n      <th>almond</th>\n      <th>angelica</th>\n      <th>anise</th>\n      <th>anise_seed</th>\n      <th>apple</th>\n      <th>apple_brandy</th>\n      <th>apricot</th>\n      <th>armagnac</th>\n      <th>...</th>\n      <th>whiskey</th>\n      <th>white_bread</th>\n      <th>white_wine</th>\n      <th>whole_grain_wheat_flour</th>\n      <th>wine</th>\n      <th>wood</th>\n      <th>yam</th>\n      <th>yeast</th>\n      <th>yogurt</th>\n      <th>zucchini</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>0</td>\n      <td>indian</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>...</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>1</td>\n      <td>indian</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>...</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2</td>\n      <td>indian</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>...</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>3</td>\n      <td>indian</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>...</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>4</td>\n      <td>indian</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>...</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n<p>5 rows × 382 columns</p>\n</div>"
     },
     "metadata": {},
     "execution_count": 26
    }
   ],
   "source": [
    "recipes_df = pd.read_csv(\"../../data/cleaned_cuisine.csv\")\n",
    "recipes_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "0    indian\n",
       "1    indian\n",
       "2    indian\n",
       "3    indian\n",
       "4    indian\n",
       "Name: cuisine, dtype: object"
      ]
     },
     "metadata": {},
     "execution_count": 27
    }
   ],
   "source": [
    "recipes_label_df = recipes_df['cuisine']\n",
    "recipes_label_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "   almond  angelica  anise  anise_seed  apple  apple_brandy  apricot  \\\n",
       "0       0         0      0           0      0             0        0   \n",
       "1       1         0      0           0      0             0        0   \n",
       "2       0         0      0           0      0             0        0   \n",
       "3       0         0      0           0      0             0        0   \n",
       "4       0         0      0           0      0             0        0   \n",
       "\n",
       "   armagnac  artemisia  artichoke  ...  whiskey  white_bread  white_wine  \\\n",
       "0         0          0          0  ...        0            0           0   \n",
       "1         0          0          0  ...        0            0           0   \n",
       "2         0          0          0  ...        0            0           0   \n",
       "3         0          0          0  ...        0            0           0   \n",
       "4         0          0          0  ...        0            0           0   \n",
       "\n",
       "   whole_grain_wheat_flour  wine  wood  yam  yeast  yogurt  zucchini  \n",
       "0                        0     0     0    0      0       0         0  \n",
       "1                        0     0     0    0      0       0         0  \n",
       "2                        0     0     0    0      0       0         0  \n",
       "3                        0     0     0    0      0       0         0  \n",
       "4                        0     0     0    0      0       1         0  \n",
       "\n",
       "[5 rows x 380 columns]"
      ],
      "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>almond</th>\n      <th>angelica</th>\n      <th>anise</th>\n      <th>anise_seed</th>\n      <th>apple</th>\n      <th>apple_brandy</th>\n      <th>apricot</th>\n      <th>armagnac</th>\n      <th>artemisia</th>\n      <th>artichoke</th>\n      <th>...</th>\n      <th>whiskey</th>\n      <th>white_bread</th>\n      <th>white_wine</th>\n      <th>whole_grain_wheat_flour</th>\n      <th>wine</th>\n      <th>wood</th>\n      <th>yam</th>\n      <th>yeast</th>\n      <th>yogurt</th>\n      <th>zucchini</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>...</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>...</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>...</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>...</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>...</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n<p>5 rows × 380 columns</p>\n</div>"
     },
     "metadata": {},
     "execution_count": 28
    }
   ],
   "source": [
    "recipes_feature_df = recipes_df.drop(['Unnamed: 0', 'cuisine'], axis=1)\n",
    "recipes_feature_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(recipes_feature_df, recipes_label_df, test_size=0.3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Accuracy is 0.810675562969141\n"
     ]
    }
   ],
   "source": [
    "lr = LogisticRegression(multi_class='ovr',solver='lbfgs')\n",
    "model = lr.fit(X_train, np.ravel(y_train))\n",
    "\n",
    "accuracy = model.score(X_test, y_test)\n",
    "print (\"Accuracy is {}\".format(accuracy))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "ingredients: Index(['bean', 'coriander', 'cumin', 'fenugreek', 'pepper', 'turmeric',\n       'vegetable_oil'],\n      dtype='object')\ncusine: thai\n"
     ]
    }
   ],
   "source": [
    "# test an item\n",
    "print(f'ingredients: {X_test.iloc[20][X_test.iloc[20]!=0].keys()}')\n",
    "print(f'cuisine: {y_test.iloc[20]}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "                 0\n",
       "indian    0.530435\n",
       "thai      0.344293\n",
       "japanese  0.108792\n",
       "chinese   0.015001\n",
       "korean    0.001480"
      ],
      "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>0</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>indian</th>\n      <td>0.530435</td>\n    </tr>\n    <tr>\n      <th>thai</th>\n      <td>0.344293</td>\n    </tr>\n    <tr>\n      <th>japanese</th>\n      <td>0.108792</td>\n    </tr>\n    <tr>\n      <th>chinese</th>\n      <td>0.015001</td>\n    </tr>\n    <tr>\n      <th>korean</th>\n      <td>0.001480</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
     },
     "metadata": {},
     "execution_count": 32
    }
   ],
   "source": [
    "#rehsape to 2d array and transpose\r\n",
    "test= X_test.iloc[20].values.reshape(-1, 1).T\r\n",
    "# predict with score\r\n",
    "proba = model.predict_proba(test)\r\n",
    "classes = model.classes_\r\n",
    "# create df with classes and scores\r\n",
    "resultdf = pd.DataFrame(data=proba, columns=classes)\r\n",
    "\r\n",
    "# create df to show results\r\n",
    "topPrediction = resultdf.T.sort_values(by=[0], ascending = [False])\r\n",
    "topPrediction.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "              precision    recall  f1-score   support\n\n     chinese       0.75      0.67      0.70       231\n      indian       0.91      0.90      0.90       255\n    japanese       0.77      0.82      0.79       260\n      korean       0.83      0.83      0.83       220\n        thai       0.79      0.83      0.81       233\n\n    accuracy                           0.81      1199\n   macro avg       0.81      0.81      0.81      1199\nweighted avg       0.81      0.81      0.81      1199\n\n"
     ]
    }
   ],
   "source": [
    "y_pred = model.predict(X_test)\r\n",
    "print(classification_report(y_test,y_pred))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Try different classifiers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "\r\n",
    "C = 10\r\n",
    "# Create different classifiers.\r\n",
    "classifiers = {\r\n",
    "    'L1 logistic': LogisticRegression(C=C, penalty='l1',\r\n",
    "                                      solver='saga',\r\n",
    "                                      multi_class='multinomial',\r\n",
    "                                      max_iter=10000),\r\n",
    "    'L2 logistic (Multinomial)': LogisticRegression(C=C, penalty='l2',\r\n",
    "                                                    solver='saga',\r\n",
    "                                                    multi_class='multinomial',\r\n",
    "                                                    max_iter=10000),\r\n",
    "    'L2 logistic (OvR)': LogisticRegression(C=C, penalty='l2',\r\n",
    "                                            solver='saga',\r\n",
    "                                            multi_class='ovr',\r\n",
    "                                            max_iter=10000),\r\n",
    "    'Linear SVC': SVC(kernel='linear', C=C, probability=True,\r\n",
    "                      random_state=0)\r\n",
    "}\r\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Accuracy (train) for L1 logistic: 79.4% \n",
      "Accuracy (train) for L2 logistic (Multinomial): 79.2% \n",
      "Accuracy (train) for L2 logistic (OvR): 80.2% \n",
      "Accuracy (train) for Linear SVC: 79.1% \n"
     ]
    }
   ],
   "source": [
    "n_classifiers = len(classifiers)\r\n",
    "\r\n",
    "for index, (name, classifier) in enumerate(classifiers.items()):\r\n",
    "    classifier.fit(X_train, np.ravel(y_train))\r\n",
    "\r\n",
    "    y_pred = classifier.predict(X_test)\r\n",
    "    accuracy = accuracy_score(y_test, y_pred)\r\n",
    "    print(\"Accuracy (train) for %s: %0.1f%% \" % (name, accuracy * 100))\r\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "dd61f40108e2a19f4ef0d3ebbc6b6eea57ab3c4bc13b15fe6f390d3d86442534"
  },
  "kernelspec": {
   "name": "python37364bit8d3b438fb5fc4430a93ac2cb74d693a7",
   "display_name": "Python 3.7.0 64-bit ('3.7')"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.0"
  },
  "metadata": {
   "interpreter": {
    "hash": "70b38d7a306a849643e446cd70466270a13445e5987dfa1344ef2b127438fa4d"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}