{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "import transformers\n",
    "from transformers import BartTokenizer, BartForConditionalGeneration\n",
    "tr = BartTokenizer.from_pretrained('facebook/bart-large-cnn')\n",
    "mdl = BartForConditionalGeneration.from_pretrained('facebook/bart-large-cnn')\n",
    "torch_device = 'cpu'\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "def bart_summarize(text, num_beams=20, length_penalty=2, max_length=2048, min_length=56, no_repeat_ngram_size=2):\n",
    "\n",
    "      text = text.replace('\\n','')\n",
    "      text_input_ids = tr.batch_encode_plus([text], return_tensors='pt', max_length=1024)['input_ids'].to(torch_device)\n",
    "      summary_ids = mdl.generate(text_input_ids, num_beams=int(num_beams), length_penalty=float(length_penalty), max_length=int(max_length), min_length=int(min_length), no_repeat_ngram_size=int(no_repeat_ngram_size))\n",
    "      summary_txt = tr.decode(summary_ids.squeeze(), skip_special_tokens=True)\n",
    "      return summary_txt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from sentence_transformers import SentenceTransformer\n",
    "import scipy.spatial\n",
    "import pickle as pkl\n",
    "from sentence_transformers import SentenceTransformer, util\n",
    "import torch\n",
    "#import os\n",
    "\n",
    "\n",
    "df = pd.read_csv('combined_paris.csv')\n",
    "\n",
    "\n",
    "df_combined = df.sort_values(['Hotel']).groupby('Hotel', sort=False).review.apply(''.join).reset_index(name='all_review')\n",
    "\n",
    "import re\n",
    "\n",
    "df_combined['all_review'] = df_combined['all_review'].apply(lambda x: re.sub('[^a-zA-z0-9\\s]','',x))\n",
    "def lower_case(input_str):\n",
    "        input_str = input_str.lower()\n",
    "        return input_str"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_combined['all_review']= df_combined['all_review'].apply(lambda x: lower_case(x))\n",
    "\n",
    "df = df_combined\n",
    "\n",
    "df_sentences = df_combined.set_index(\"all_review\")\n",
    "\n",
    "df_sentences = df_sentences[\"Hotel\"].to_dict()\n",
    "df_sentences_list = list(df_sentences.keys())\n"
   ]
  },
  {
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Hotel</th>\n",
       "      <td>25hours Hotel Terminus Nord</td>\n",
       "      <td>Acacias Etoile Hotel</td>\n",
       "      <td>COQ Hotel Paris</td>\n",
       "      <td>Campanile Paris 14 - Maine Montparnasse</td>\n",
       "      <td>Cler Hotel</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>all_review</th>\n",
       "      <td>weve spent lots of time in paris and this was ...</td>\n",
       "      <td>the hotel is great for value the breakfast sel...</td>\n",
       "      <td>stayed for a short city break  the hotel is a ...</td>\n",
       "      <td>room was very clean  transportation is very ne...</td>\n",
       "      <td>we had the best stay at cler hotel  the locati...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                            0  \\\n",
       "Hotel                             25hours Hotel Terminus Nord   \n",
       "all_review  weve spent lots of time in paris and this was ...   \n",
       "\n",
       "                                                            1  \\\n",
       "Hotel                                    Acacias Etoile Hotel   \n",
       "all_review  the hotel is great for value the breakfast sel...   \n",
       "\n",
       "                                                            2  \\\n",
       "Hotel                                         COQ Hotel Paris   \n",
       "all_review  stayed for a short city break  the hotel is a ...   \n",
       "\n",
       "                                                            3  \\\n",
       "Hotel                 Campanile Paris 14 - Maine Montparnasse   \n",
       "all_review  room was very clean  transportation is very ne...   \n",
       "\n",
       "                                                            4  \n",
       "Hotel                                              Cler Hotel  \n",
       "all_review  we had the best stay at cler hotel  the locati...  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_combined.head().T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Truncation was not explicitly activated but `max_length` is provided a specific value, please use `truncation=True` to explicitly truncate examples to max length. Defaulting to 'longest_first' truncation strategy. If you encode pairs of sequences (GLUE-style) with the tokenizer you can select this strategy more precisely by providing a specific strategy to `truncation`.\n"
     ]
    }
   ],
   "source": [
    "long_summary = []\n",
    "\n",
    "for i in range(len(df_combined)):\n",
    "    t = bart_summarize(df_combined['all_review'][i])\n",
    "    long_summary.append(t)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_combined['summary'] = long_summary"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_combined.to_csv('df_combined_paris.csv',index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "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>Hotel</th>\n",
       "      <th>all_review</th>\n",
       "      <th>summary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>25hours Hotel Terminus Nord</td>\n",
       "      <td>weve spent lots of time in paris and this was ...</td>\n",
       "      <td>we were blown away by this excellent hotel we ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Acacias Etoile Hotel</td>\n",
       "      <td>the hotel is great for value the breakfast sel...</td>\n",
       "      <td>The hotel is great for value the breakfast sel...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>COQ Hotel Paris</td>\n",
       "      <td>stayed for a short city break  the hotel is a ...</td>\n",
       "      <td>stayed for a short city break  the hotel is a ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Campanile Paris 14 - Maine Montparnasse</td>\n",
       "      <td>room was very clean  transportation is very ne...</td>\n",
       "      <td>hotel turned out to be perfect for our short ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Cler Hotel</td>\n",
       "      <td>we had the best stay at cler hotel  the locati...</td>\n",
       "      <td>we had the best stay at cler hotel  the locati...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                     Hotel  \\\n",
       "0              25hours Hotel Terminus Nord   \n",
       "1                     Acacias Etoile Hotel   \n",
       "2                          COQ Hotel Paris   \n",
       "3  Campanile Paris 14 - Maine Montparnasse   \n",
       "4                               Cler Hotel   \n",
       "\n",
       "                                          all_review  \\\n",
       "0  weve spent lots of time in paris and this was ...   \n",
       "1  the hotel is great for value the breakfast sel...   \n",
       "2  stayed for a short city break  the hotel is a ...   \n",
       "3  room was very clean  transportation is very ne...   \n",
       "4  we had the best stay at cler hotel  the locati...   \n",
       "\n",
       "                                             summary  \n",
       "0  we were blown away by this excellent hotel we ...  \n",
       "1  The hotel is great for value the breakfast sel...  \n",
       "2  stayed for a short city break  the hotel is a ...  \n",
       "3   hotel turned out to be perfect for our short ...  \n",
       "4  we had the best stay at cler hotel  the locati...  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_combined.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Dockerfile                            df_combined.csv\n",
      "Hotel New York Combined.csv           en_core_web_sm-3.2.0-py3-none-any.whl\n",
      "README.md                             query_generator.ipynb\n",
      "Untitled.ipynb                        requirements.txt\n",
      "app.py                                summary.ipynb\n",
      "app.yaml\n"
     ]
    }
   ],
   "source": [
    "!ls"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/aimzlicious/miniforge3/envs/tf_m1/lib/python3.8/site-packages/huggingface_hub/snapshot_download.py:6: FutureWarning: snapshot_download.py has been made private and will no longer be available from version 0.11. Please use `from huggingface_hub import snapshot_download` to import the only public function in this module. Other members of the file may be changed without a deprecation notice.\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "from sentence_transformers import SentenceTransformer\n",
    "import scipy.spatial\n",
    "import pickle as pkl\n",
    "from sentence_transformers import SentenceTransformer, util\n",
    "import torch\n",
    "df_combined_paris_summary = pd.read_csv('df_combined_paris.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>Hotel</th>\n",
       "      <th>all_review</th>\n",
       "      <th>summary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>25hours Hotel Terminus Nord</td>\n",
       "      <td>weve spent lots of time in paris and this was ...</td>\n",
       "      <td>we were blown away by this excellent hotel we ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Acacias Etoile Hotel</td>\n",
       "      <td>the hotel is great for value the breakfast sel...</td>\n",
       "      <td>The hotel is great for value the breakfast sel...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>COQ Hotel Paris</td>\n",
       "      <td>stayed for a short city break  the hotel is a ...</td>\n",
       "      <td>stayed for a short city break  the hotel is a ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Campanile Paris 14 - Maine Montparnasse</td>\n",
       "      <td>room was very clean  transportation is very ne...</td>\n",
       "      <td>hotel turned out to be perfect for our short ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Cler Hotel</td>\n",
       "      <td>we had the best stay at cler hotel  the locati...</td>\n",
       "      <td>we had the best stay at cler hotel  the locati...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                     Hotel  \\\n",
       "0              25hours Hotel Terminus Nord   \n",
       "1                     Acacias Etoile Hotel   \n",
       "2                          COQ Hotel Paris   \n",
       "3  Campanile Paris 14 - Maine Montparnasse   \n",
       "4                               Cler Hotel   \n",
       "\n",
       "                                          all_review  \\\n",
       "0  weve spent lots of time in paris and this was ...   \n",
       "1  the hotel is great for value the breakfast sel...   \n",
       "2  stayed for a short city break  the hotel is a ...   \n",
       "3  room was very clean  transportation is very ne...   \n",
       "4  we had the best stay at cler hotel  the locati...   \n",
       "\n",
       "                                             summary  \n",
       "0  we were blown away by this excellent hotel we ...  \n",
       "1  The hotel is great for value the breakfast sel...  \n",
       "2  stayed for a short city break  the hotel is a ...  \n",
       "3   hotel turned out to be perfect for our short ...  \n",
       "4  we had the best stay at cler hotel  the locati...  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_combined_paris.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_paris = pd.read_csv('paris_clean_newer.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "hotel=pd.DataFrame(df_paris['Hotel'].drop_duplicates())"
   ]
  },
  {
   "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>Hotel</th>\n",
       "      <th>all_review</th>\n",
       "      <th>summary</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>25hours Hotel Terminus Nord</td>\n",
       "      <td>weve spent lots of time in paris and this was ...</td>\n",
       "      <td>we were blown away by this excellent hotel we ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Acacias Etoile Hotel</td>\n",
       "      <td>the hotel is great for value the breakfast sel...</td>\n",
       "      <td>The hotel is great for value the breakfast sel...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>COQ Hotel Paris</td>\n",
       "      <td>stayed for a short city break  the hotel is a ...</td>\n",
       "      <td>stayed for a short city break  the hotel is a ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Campanile Paris 14 - Maine Montparnasse</td>\n",
       "      <td>room was very clean  transportation is very ne...</td>\n",
       "      <td>hotel turned out to be perfect for our short ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Cler Hotel</td>\n",
       "      <td>we had the best stay at cler hotel  the locati...</td>\n",
       "      <td>we had the best stay at cler hotel  the locati...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>89</th>\n",
       "      <td>Sofitel Paris Le Faubourg</td>\n",
       "      <td>4 years ago i was the last time at sofitel le ...</td>\n",
       "      <td>4 years ago i was the last time at sofitel le ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>90</th>\n",
       "      <td>St Christopher's Gare du Nord Paris</td>\n",
       "      <td>when arriving to the area it felt a little dan...</td>\n",
       "      <td>Barry is the best bartender in paris cheers gr...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>91</th>\n",
       "      <td>St Christopher's Inn Canal Paris</td>\n",
       "      <td>ive stayed at st christopher inn canal in pari...</td>\n",
       "      <td>ive stayed at st christopher inn canal in pari...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>92</th>\n",
       "      <td>Touring Hotel</td>\n",
       "      <td>hotel is in a great location  minutes walk fro...</td>\n",
       "      <td>Hotel is in a great location  minutes walk fro...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>93</th>\n",
       "      <td>Warwick Paris</td>\n",
       "      <td>if i know of anybody heading to paris i will r...</td>\n",
       "      <td>warwick hotel in paris is a good hotel to stay...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>94 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                      Hotel  \\\n",
       "0               25hours Hotel Terminus Nord   \n",
       "1                      Acacias Etoile Hotel   \n",
       "2                           COQ Hotel Paris   \n",
       "3   Campanile Paris 14 - Maine Montparnasse   \n",
       "4                                Cler Hotel   \n",
       "..                                      ...   \n",
       "89                Sofitel Paris Le Faubourg   \n",
       "90      St Christopher's Gare du Nord Paris   \n",
       "91         St Christopher's Inn Canal Paris   \n",
       "92                            Touring Hotel   \n",
       "93                            Warwick Paris   \n",
       "\n",
       "                                           all_review  \\\n",
       "0   weve spent lots of time in paris and this was ...   \n",
       "1   the hotel is great for value the breakfast sel...   \n",
       "2   stayed for a short city break  the hotel is a ...   \n",
       "3   room was very clean  transportation is very ne...   \n",
       "4   we had the best stay at cler hotel  the locati...   \n",
       "..                                                ...   \n",
       "89  4 years ago i was the last time at sofitel le ...   \n",
       "90  when arriving to the area it felt a little dan...   \n",
       "91  ive stayed at st christopher inn canal in pari...   \n",
       "92  hotel is in a great location  minutes walk fro...   \n",
       "93  if i know of anybody heading to paris i will r...   \n",
       "\n",
       "                                              summary  \n",
       "0   we were blown away by this excellent hotel we ...  \n",
       "1   The hotel is great for value the breakfast sel...  \n",
       "2   stayed for a short city break  the hotel is a ...  \n",
       "3    hotel turned out to be perfect for our short ...  \n",
       "4   we had the best stay at cler hotel  the locati...  \n",
       "..                                                ...  \n",
       "89  4 years ago i was the last time at sofitel le ...  \n",
       "90  Barry is the best bartender in paris cheers gr...  \n",
       "91  ive stayed at st christopher inn canal in pari...  \n",
       "92  Hotel is in a great location  minutes walk fro...  \n",
       "93  warwick hotel in paris is a good hotel to stay...  \n",
       "\n",
       "[94 rows x 3 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_combined_paris.merge(hotel,how='left')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "4bd624a0593993fe43ac4046b27b898fb2ef75c21c08f81e89e64ea0f51df676"
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.8.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}