{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "27b0322e-d6a8-4202-9f78-8d2754ebdd97",
   "metadata": {},
   "outputs": [],
   "source": [
    "#!pip list | grep hugging"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "da82a90f-7098-4d0c-9fe8-3e0cfc39671d",
   "metadata": {},
   "outputs": [],
   "source": [
    "#!pip install transformers datasets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "829575c2-c292-4455-8cc6-48764e64c4b0",
   "metadata": {},
   "outputs": [],
   "source": [
    "#!pip install torch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "ba0ced0b-35cd-40fd-934f-1013d4a1364d",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/milindchawre/.pyenv/versions/3.12.2/envs/hugging-face/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "import transformers\n",
    "import datasets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "d196c435-fa5a-4c3b-bec4-0181aa00e8bb",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'4.44.0'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "transformers.__version__"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "55ddfdaa-3a22-4eab-ad36-24355cbb7fee",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'2.21.0'"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "datasets.__version__"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "13b8669b-5cc5-40b8-bd22-a7ff44fa43f3",
   "metadata": {},
   "outputs": [],
   "source": [
    "from datasets import load_dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "a722a796-84b7-4c45-a104-3d863d52cbb5",
   "metadata": {},
   "outputs": [],
   "source": [
    "reviews = load_dataset('rotten_tomatoes')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "607c352e-70c8-4697-b9a1-a4c68e55d502",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "datasets.dataset_dict.DatasetDict"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(reviews)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "e0637ff3-90b9-41cf-bdd0-ba3dbe185225",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "DatasetDict({\n",
      "    train: Dataset({\n",
      "        features: ['text', 'label'],\n",
      "        num_rows: 8530\n",
      "    })\n",
      "    validation: Dataset({\n",
      "        features: ['text', 'label'],\n",
      "        num_rows: 1066\n",
      "    })\n",
      "    test: Dataset({\n",
      "        features: ['text', 'label'],\n",
      "        num_rows: 1066\n",
      "    })\n",
      "})\n"
     ]
    }
   ],
   "source": [
    "print(reviews)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "79f60106-7628-4605-920f-6bb8375e6cb5",
   "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>text</th>\n",
       "      <th>label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>the rock is destined to be the 21st century's ...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>the gorgeously elaborate continuation of \" the...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>effective but too-tepid biopic</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>if you sometimes like to go to the movies to h...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>emerges as something rare , an issue movie tha...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8525</th>\n",
       "      <td>any enjoyment will be hinge from a personal th...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8526</th>\n",
       "      <td>if legendary shlockmeister ed wood had ever ma...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8527</th>\n",
       "      <td>hardly a nuanced portrait of a young woman's b...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8528</th>\n",
       "      <td>interminably bleak , to say nothing of boring .</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8529</th>\n",
       "      <td>things really get weird , though not particula...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8530 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                   text  label\n",
       "0     the rock is destined to be the 21st century's ...      1\n",
       "1     the gorgeously elaborate continuation of \" the...      1\n",
       "2                        effective but too-tepid biopic      1\n",
       "3     if you sometimes like to go to the movies to h...      1\n",
       "4     emerges as something rare , an issue movie tha...      1\n",
       "...                                                 ...    ...\n",
       "8525  any enjoyment will be hinge from a personal th...      0\n",
       "8526  if legendary shlockmeister ed wood had ever ma...      0\n",
       "8527  hardly a nuanced portrait of a young woman's b...      0\n",
       "8528    interminably bleak , to say nothing of boring .      0\n",
       "8529  things really get weird , though not particula...      0\n",
       "\n",
       "[8530 rows x 2 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reviews['train'].to_pandas()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "8971be5a-f5ba-4cb9-be88-7fa509b201ef",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'the rock is destined to be the 21st century\\'s new \" conan \" and that he\\'s going to make a splash even greater than arnold schwarzenegger , jean-claud van damme or steven segal .'"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reviews['train'].to_pandas()['text'][0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "74db724b-063c-4c91-9681-37231a5a09fd",
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import pipeline\n",
    "import torch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "4a22ba6c-2db8-4dff-9abd-037f1a08fc7a",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "No model was supplied, defaulted to distilbert/distilbert-base-uncased-finetuned-sst-2-english and revision af0f99b (https://huggingface.co/distilbert/distilbert-base-uncased-finetuned-sst-2-english).\n",
      "Using a pipeline without specifying a model name and revision in production is not recommended.\n",
      "/Users/milindchawre/.pyenv/versions/3.12.2/envs/hugging-face/lib/python3.12/site-packages/transformers/tokenization_utils_base.py:1601: FutureWarning: `clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be depracted in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "classifier = pipeline(\"sentiment-analysis\", device=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "2d64c34d-c2d8-4cda-9c04-91e5497304a9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[{'label': 'POSITIVE', 'score': 0.9998668432235718}]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "classifier(\"This was great movie!\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "fc11b406-3770-44ea-9654-4ec2e2e1081b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[{'label': 'POSITIVE', 'score': 0.9998465776443481}]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "classifier(\"This was great ok!\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "682a57fc-d2f6-4ad5-b05c-ad4a311216fa",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[{'label': 'NEGATIVE', 'score': 0.9997976422309875}]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "classifier(\"This was not that good movie!\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "3e790b3e-cb65-46a8-9bcb-74503742fcb6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[{'label': 'NEGATIVE', 'score': 0.9997455477714539}]"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "classifier(\"This was worst movie!\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "56f1f502-f683-4c3a-924d-9a16e5d6c55c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[{'label': 'NEGATIVE', 'score': 0.9991676807403564}]"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "classifier(\"In the movie, the acting was fine, but the story was bad, while the costume was good but the daigloues are boring!\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "a8755bd0-5c4b-4da7-84d5-fb1986188d4e",
   "metadata": {},
   "outputs": [],
   "source": [
    "def score(review_text):\n",
    "    return classifier(review_text)[0]['label']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "1de830b3-bb2d-42ce-90b6-b2868017d499",
   "metadata": {},
   "outputs": [],
   "source": [
    "test_df = reviews['test'].to_pandas()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "0b0004ea-562c-493b-8a0c-125dd20a185f",
   "metadata": {},
   "outputs": [],
   "source": [
    "test_df['model_prediction'] = test_df['text'].apply(score)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "21715d4f-51f2-4118-b5d8-23b5d432d3b6",
   "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>text</th>\n",
       "      <th>label</th>\n",
       "      <th>model_prediction</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>lovingly photographed in the manner of a golde...</td>\n",
       "      <td>1</td>\n",
       "      <td>POSITIVE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>consistently clever and suspenseful .</td>\n",
       "      <td>1</td>\n",
       "      <td>POSITIVE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>it's like a \" big chill \" reunion of the baade...</td>\n",
       "      <td>1</td>\n",
       "      <td>NEGATIVE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>the story gives ample opportunity for large-sc...</td>\n",
       "      <td>1</td>\n",
       "      <td>POSITIVE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>red dragon \" never cuts corners .</td>\n",
       "      <td>1</td>\n",
       "      <td>POSITIVE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1061</th>\n",
       "      <td>a terrible movie that some people will neverth...</td>\n",
       "      <td>0</td>\n",
       "      <td>NEGATIVE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1062</th>\n",
       "      <td>there are many definitions of 'time waster' bu...</td>\n",
       "      <td>0</td>\n",
       "      <td>NEGATIVE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1063</th>\n",
       "      <td>as it stands , crocodile hunter has the hurrie...</td>\n",
       "      <td>0</td>\n",
       "      <td>NEGATIVE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1064</th>\n",
       "      <td>the thing looks like a made-for-home-video qui...</td>\n",
       "      <td>0</td>\n",
       "      <td>NEGATIVE</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1065</th>\n",
       "      <td>enigma is well-made , but it's just too dry an...</td>\n",
       "      <td>0</td>\n",
       "      <td>NEGATIVE</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1066 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                   text  label  \\\n",
       "0     lovingly photographed in the manner of a golde...      1   \n",
       "1                 consistently clever and suspenseful .      1   \n",
       "2     it's like a \" big chill \" reunion of the baade...      1   \n",
       "3     the story gives ample opportunity for large-sc...      1   \n",
       "4                     red dragon \" never cuts corners .      1   \n",
       "...                                                 ...    ...   \n",
       "1061  a terrible movie that some people will neverth...      0   \n",
       "1062  there are many definitions of 'time waster' bu...      0   \n",
       "1063  as it stands , crocodile hunter has the hurrie...      0   \n",
       "1064  the thing looks like a made-for-home-video qui...      0   \n",
       "1065  enigma is well-made , but it's just too dry an...      0   \n",
       "\n",
       "     model_prediction  \n",
       "0            POSITIVE  \n",
       "1            POSITIVE  \n",
       "2            NEGATIVE  \n",
       "3            POSITIVE  \n",
       "4            POSITIVE  \n",
       "...               ...  \n",
       "1061         NEGATIVE  \n",
       "1062         NEGATIVE  \n",
       "1063         NEGATIVE  \n",
       "1064         NEGATIVE  \n",
       "1065         NEGATIVE  \n",
       "\n",
       "[1066 rows x 3 columns]"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3c916443-92ad-4dc6-a5bf-10aad52d8b4c",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "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": "3.12.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}