{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "f:\\miniconda3\\envs\\btl\\Lib\\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 matplotlib.pyplot as plt\n",
    "import gradio as gd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running on local URL:  http://127.0.0.1:7860\n",
      "\n",
      "To create a public link, set `share=True` in `launch()`.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div><iframe src=\"http://127.0.0.1:7860/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": []
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import gradio as gr\n",
    "\n",
    "def greet(name, intensity):\n",
    "    return \"Hello, \" + name + \"!\" * int(intensity)\n",
    "\n",
    "demo = gr.Interface(\n",
    "    fn=greet,\n",
    "    inputs=[\"text\", \"slider\"],\n",
    "    outputs=[\"text\"],\n",
    ")\n",
    "\n",
    "demo.launch()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running on local URL:  http://127.0.0.1:7904\n",
      "\n",
      "Could not create share link. Missing file: f:\\miniconda3\\envs\\btl\\Lib\\site-packages\\gradio\\frpc_windows_amd64_v0.2. \n",
      "\n",
      "Please check your internet connection. This can happen if your antivirus software blocks the download of this file. You can install manually by following these steps: \n",
      "\n",
      "1. Download this file: https://cdn-media.huggingface.co/frpc-gradio-0.2/frpc_windows_amd64.exe\n",
      "2. Rename the downloaded file to: frpc_windows_amd64_v0.2\n",
      "3. Move the file to this location: f:\\miniconda3\\envs\\btl\\Lib\\site-packages\\gradio\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div><iframe src=\"http://127.0.0.1:7904/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": []
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# #setup\n",
    "# model_path = \"KAITANY/finetuned-roberta-base-sentiment\"\n",
    "\n",
    "# tokenizer = AutoTokenizer.from_pretrained(model_path)\n",
    "# #config = AutoConfig.from_pretrained(model_path)\n",
    "# model = AutoModelForSequenceClassification.from_pretrained(model_path)\n",
    "\n",
    "# def preprocess(text):\n",
    "#     # Preprocess text (username and link placeholders)\n",
    "#     new_text = []\n",
    "#     for t in text.split(\" \"):\n",
    "#         t = '@user' if t.startswith('@') and len(t) > 1 else t\n",
    "#         t = 'http' if t.startswith('http') else t\n",
    "#         new_text.append(t)\n",
    "#     return \" \".join(new_text)\n",
    "\n",
    "# def sentiment_analysis(text):\n",
    "    # text = preprocess(text)\n",
    "\n",
    "    # # Tokenize the text\n",
    "    # inputs = tokenizer(text, return_tensors=\"pt\", padding=True)\n",
    "\n",
    "    # # Make a prediction\n",
    "    # with torch.no_grad():\n",
    "    #     outputs = model(**inputs)\n",
    "\n",
    "    # # Get the predicted class probabilities\n",
    "    # scores = torch.softmax(outputs.logits, dim=1).tolist()[0]\n",
    "    # # Map the scores to labels\n",
    "    # labels = ['Negative', 'Neutral', 'Positive']\n",
    "    # scores_dict = {label: score for label, score in zip(labels, scores)}\n",
    "\n",
    "    # return scores_dict\n",
    "#demo\n",
    "aspects = ['General', 'Battery', 'Performance', 'Camera', 'Ser&Acc', 'Others', 'Design', 'Screen', 'Features', 'Price']\n",
    "aspects_ratio = (np.random.dirichlet(np.ones(10), size=1) * 100).flatten()\n",
    "\n",
    "sentiments_ratio = (np.random.dirichlet(np.ones(3), size=1) * 100).flatten()\n",
    "sentiments = ['Positive', 'Negative', 'Neutral']\n",
    "\n",
    "aspects_polarity = []\n",
    "aspects_polarity_ratio = (np.random.dirichlet(np.ones(30), size=1) * 100).flatten()\n",
    "for aspect in aspects:\n",
    "    for sentiment in sentiments:\n",
    "        aspects_polarity.append(aspect + '#' + sentiment)    \n",
    "\n",
    "def sentiment_analysis(text, aspect):\n",
    "\n",
    "    # Tạo biểu đồ cảm xúc theo aspect\n",
    "    pie_sentiments_of_an_aspect = draw_pie_sentiments_of_an_aspect(aspect)\n",
    "\n",
    "    #Biểu đồ aspect\n",
    "    pie_of_all_aspect = draw_pie_of_aspect()\n",
    "\n",
    "    #Biểu đồ aspect#polirity\n",
    "    pie_aspect_polarity = draw_pie_aspect_polarity()\n",
    "    # return [pie_aspect, pie_all_aspect, pie_aspect_polarity]\n",
    "    return pie_sentiments_of_an_aspect, pie_of_all_aspect, pie_aspect_polarity\n",
    "\n",
    "def draw_pie_sentiments_of_an_aspect(aspect):\n",
    "    sentiments_ratio = (np.random.dirichlet(np.ones(3), size=1) * 100).flatten()\n",
    "    pie_sentiments_of_an_aspect = plt.figure(figsize=(5,5))\n",
    "    plt.pie(sentiments_ratio, labels=sentiments, autopct='%1.1f%%', startangle=140)\n",
    "    return pie_sentiments_of_an_aspect\n",
    "\n",
    "def draw_pie_of_aspect():\n",
    "    pie_aspect = plt.figure(figsize=(5,5))\n",
    "    plt.pie(aspects_ratio, labels=aspects, autopct='%1.1f%%', startangle=140)\n",
    "    return pie_aspect\n",
    "\n",
    "def draw_pie_aspect_polarity():\n",
    "    pie_aspect_polarity = plt.figure(figsize=(20, 10))\n",
    "    plt.pie(aspects_polarity_ratio, labels=aspects_polarity, autopct='%1.1f%%', startangle=140)\n",
    "    plt.legend(aspects_polarity, loc='upper right', bbox_to_anchor=(1.5, 1.))\n",
    "    return pie_aspect_polarity\n",
    "\n",
    "def submit(comment, aspect):\n",
    "    return sentiment_analysis(comment, aspect)\n",
    "    \n",
    "title = \"Sentiment Analysis Application\\n\\n\\nThis application assesses if a twitter post relating to vaccination is positive,neutral or negative\"\n",
    "with gr.Blocks() as demo:\n",
    "    with gr.Row():\n",
    "        text_box = gr.Textbox(placeholder=\"Write your comment here...\", visible=True, label=\"Comment\")\n",
    "        submit_btn = gr.Button(\"Submit\")\n",
    "    with gr.Row():\n",
    "        with gr.Column():\n",
    "            choose_aspect_dropdown = gr.Dropdown(\n",
    "                choices=['General', 'Battery', 'Performance', 'Camera', 'Ser&Acc', 'Others', 'Design', 'Screen', 'Features', 'Price'], \n",
    "                label=\"Choose Aspect\",\n",
    "                value='General'\n",
    "                )\n",
    "            pie_sentiment = gr.Plot()\n",
    "        pie_all_aspect = gr.Plot()\n",
    "        pie_aspect_polarity = gr.Plot(min_width=2000)\n",
    "    # demo.fn(draw_pie_aspect(choose_aspect_dropdown))\n",
    "\n",
    "    choose_aspect_dropdown.select(\n",
    "            fn = draw_pie_sentiments_of_an_aspect,\n",
    "            inputs = [choose_aspect_dropdown],\n",
    "            outputs = [pie_sentiment],\n",
    "        )\n",
    "\n",
    "    submit_btn.click(\n",
    "    fn = submit,\n",
    "    inputs = [text_box, choose_aspect_dropdown],\n",
    "    outputs = [pie_sentiment, pie_all_aspect, pie_aspect_polarity],\n",
    ")\n",
    "\n",
    "\n",
    "# demo = gr.Interface(\n",
    "#     fn=sentiment_analysis,\n",
    "#     inputs=gr.Textbox(placeholder=\"Write your tweet here...\"),\n",
    "#     outputs=gr.Plot(),\n",
    "#     examples=[[\"The Vaccine is harmful!\"],[\"I cant believe people don't vaccinate their kids\"],[\"FDA think just not worth the AE unfortunately\"],[\"For a vaccine given to healthy\"]],\n",
    "#     title=title\n",
    "# )\n",
    "\n",
    "demo.launch(share=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running on local URL:  http://127.0.0.1:7881\n",
      "\n",
      "To create a public link, set `share=True` in `launch()`.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div><iframe src=\"http://127.0.0.1:7881/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": []
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import gradio as gr\n",
    "\n",
    "with gr.Blocks() as demo:\n",
    "    error_box = gr.Textbox(label=\"Error\", visible=False)\n",
    "\n",
    "    name_box = gr.Textbox(label=\"Name\")\n",
    "    age_box = gr.Number(label=\"Age\", minimum=0, maximum=100)\n",
    "    symptoms_box = gr.CheckboxGroup([\"Cough\", \"Fever\", \"Runny Nose\"])\n",
    "    submit_btn = gr.Button(\"Submit\")\n",
    "\n",
    "    with gr.Column(visible=False) as output_col:\n",
    "        diagnosis_box = gr.Textbox(label=\"Diagnosis\")\n",
    "        patient_summary_box = gr.Textbox(label=\"Patient Summary\")\n",
    "\n",
    "    def submit(name, age, symptoms):\n",
    "        if len(name) == 0:\n",
    "            return {error_box: gr.Textbox(value=\"Enter name\", visible=True)}\n",
    "        return {\n",
    "            output_col: gr.Column(visible=True),\n",
    "            diagnosis_box: \"covid\" if \"Cough\" in symptoms else \"flu\",\n",
    "            patient_summary_box: f\"{name}, {age} y/o\",\n",
    "        }\n",
    "\n",
    "    submit_btn.click(\n",
    "        submit,\n",
    "        [name_box, age_box, symptoms_box],\n",
    "        [error_box, diagnosis_box, patient_summary_box, output_col],\n",
    "    )\n",
    "\n",
    "demo.launch()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "btl",
   "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": 2
}