{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 78,
   "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>name</th>\n",
       "      <th>description</th>\n",
       "      <th>year</th>\n",
       "      <th>target</th>\n",
       "      <th>size</th>\n",
       "      <th>stage</th>\n",
       "      <th>raised</th>\n",
       "      <th>tags</th>\n",
       "      <th>text_vector_</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.10 of a Second</td>\n",
       "      <td>Smart Indicators for Connected Vehicles</td>\n",
       "      <td>2019.0</td>\n",
       "      <td>B2B</td>\n",
       "      <td>1-10</td>\n",
       "      <td>Pre-Funding</td>\n",
       "      <td>Undisclosed</td>\n",
       "      <td>[connected-vehicles, adas, autonomous-vehicles...</td>\n",
       "      <td>[-0.031224824488162994, -0.06342269480228424, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>12trix</td>\n",
       "      <td>Math Lessons for Young Kids</td>\n",
       "      <td>2012.0</td>\n",
       "      <td>B2B, B2C</td>\n",
       "      <td>1-10</td>\n",
       "      <td>Pre-Funding</td>\n",
       "      <td>Undisclosed</td>\n",
       "      <td>[sdg, schools, pre-k, serious-games, games, mo...</td>\n",
       "      <td>[-0.038649097084999084, 0.028091922402381897, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1E Therapeutics</td>\n",
       "      <td>Novel RNA-targeting Drugs</td>\n",
       "      <td>2021.0</td>\n",
       "      <td>B2B</td>\n",
       "      <td>51-200</td>\n",
       "      <td>Seed</td>\n",
       "      <td>$120M</td>\n",
       "      <td>[pharmaceuticals, chronic-disease, immunology,...</td>\n",
       "      <td>[0.04561534896492958, -0.017776092514395714, 0...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1MRobotics</td>\n",
       "      <td>Retail Automation Solutions with Nano Fulfillment</td>\n",
       "      <td>2021.0</td>\n",
       "      <td>B2B</td>\n",
       "      <td>11-50</td>\n",
       "      <td>A</td>\n",
       "      <td>$25M</td>\n",
       "      <td>[omni-channel, ecommerce, climate-tech, artifi...</td>\n",
       "      <td>[0.0024080690927803516, -0.03042100928723812, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1touch.io</td>\n",
       "      <td>Personal Data Flow Tracking and Data Cataloging</td>\n",
       "      <td>2017.0</td>\n",
       "      <td>B2B</td>\n",
       "      <td>51-200</td>\n",
       "      <td>A</td>\n",
       "      <td>$16.1M</td>\n",
       "      <td>[enterprise-solutions, data-protection, cyber-...</td>\n",
       "      <td>[-0.01007091999053955, 0.10431888699531555, -0...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4981</th>\n",
       "      <td>YOW HR</td>\n",
       "      <td>Human Resources Engagement and Optimization Pl...</td>\n",
       "      <td>2020.0</td>\n",
       "      <td>B2B, B2B2C</td>\n",
       "      <td>1-10</td>\n",
       "      <td>Pre-Funding</td>\n",
       "      <td>Undisclosed</td>\n",
       "      <td>[content-creators, e-learning, software-applic...</td>\n",
       "      <td>[0.026961881667375565, 0.002459645736962557, -...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4982</th>\n",
       "      <td>Yummi Home Food</td>\n",
       "      <td>Marketplace for Homemade Food</td>\n",
       "      <td>2012.0</td>\n",
       "      <td>B2C</td>\n",
       "      <td>11-50</td>\n",
       "      <td>Pre-Funding</td>\n",
       "      <td>Undisclosed</td>\n",
       "      <td>[ecommerce, p2p, delivery, online-shopping, ma...</td>\n",
       "      <td>[0.0036857957020401955, 0.03582162782549858, -...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4983</th>\n",
       "      <td>Yung-Etgar</td>\n",
       "      <td>Custom Mechanized Harvesting Systems</td>\n",
       "      <td>1982.0</td>\n",
       "      <td>B2B</td>\n",
       "      <td>51-200</td>\n",
       "      <td>Mature</td>\n",
       "      <td>Undisclosed</td>\n",
       "      <td>[crops, agtech, harvesting, machinery, sdg, cl...</td>\n",
       "      <td>[0.027293115854263306, 0.010461761616170406, 0...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4984</th>\n",
       "      <td>YuviTal</td>\n",
       "      <td>Digital Health and Fitness Solutions for Organ...</td>\n",
       "      <td>2017.0</td>\n",
       "      <td>B2B, B2C, B2G</td>\n",
       "      <td>11-50</td>\n",
       "      <td>Pre-Funding</td>\n",
       "      <td>Undisclosed</td>\n",
       "      <td>[fitness, digital-wallet, discount, mobile-app...</td>\n",
       "      <td>[0.02851911261677742, 0.05474231392145157, -0....</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4985</th>\n",
       "      <td>Z-square</td>\n",
       "      <td>Microendoscope for Minimally Invasive Imaging ...</td>\n",
       "      <td>2013.0</td>\n",
       "      <td>B2B</td>\n",
       "      <td>11-50</td>\n",
       "      <td>Seed</td>\n",
       "      <td>$10M</td>\n",
       "      <td>[endoscopy, medical-devices, minimally-invasiv...</td>\n",
       "      <td>[0.012587728910148144, -0.07959864288568497, -...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4986 rows × 9 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                  name                                        description  \\\n",
       "0     0.10 of a Second           Smart Indicators for Connected Vehicles    \n",
       "1               12trix                        Math Lessons for Young Kids   \n",
       "2      1E Therapeutics                          Novel RNA-targeting Drugs   \n",
       "3           1MRobotics  Retail Automation Solutions with Nano Fulfillment   \n",
       "4            1touch.io    Personal Data Flow Tracking and Data Cataloging   \n",
       "...                ...                                                ...   \n",
       "4981            YOW HR  Human Resources Engagement and Optimization Pl...   \n",
       "4982   Yummi Home Food                      Marketplace for Homemade Food   \n",
       "4983        Yung-Etgar               Custom Mechanized Harvesting Systems   \n",
       "4984           YuviTal  Digital Health and Fitness Solutions for Organ...   \n",
       "4985          Z-square  Microendoscope for Minimally Invasive Imaging ...   \n",
       "\n",
       "        year         target    size        stage       raised  \\\n",
       "0     2019.0            B2B    1-10  Pre-Funding  Undisclosed   \n",
       "1     2012.0       B2B, B2C    1-10  Pre-Funding  Undisclosed   \n",
       "2     2021.0            B2B  51-200         Seed        $120M   \n",
       "3     2021.0            B2B   11-50            A         $25M   \n",
       "4     2017.0            B2B  51-200            A       $16.1M   \n",
       "...      ...            ...     ...          ...          ...   \n",
       "4981  2020.0     B2B, B2B2C    1-10  Pre-Funding  Undisclosed   \n",
       "4982  2012.0            B2C   11-50  Pre-Funding  Undisclosed   \n",
       "4983  1982.0            B2B  51-200       Mature  Undisclosed   \n",
       "4984  2017.0  B2B, B2C, B2G   11-50  Pre-Funding  Undisclosed   \n",
       "4985  2013.0            B2B   11-50         Seed         $10M   \n",
       "\n",
       "                                                   tags  \\\n",
       "0     [connected-vehicles, adas, autonomous-vehicles...   \n",
       "1     [sdg, schools, pre-k, serious-games, games, mo...   \n",
       "2     [pharmaceuticals, chronic-disease, immunology,...   \n",
       "3     [omni-channel, ecommerce, climate-tech, artifi...   \n",
       "4     [enterprise-solutions, data-protection, cyber-...   \n",
       "...                                                 ...   \n",
       "4981  [content-creators, e-learning, software-applic...   \n",
       "4982  [ecommerce, p2p, delivery, online-shopping, ma...   \n",
       "4983  [crops, agtech, harvesting, machinery, sdg, cl...   \n",
       "4984  [fitness, digital-wallet, discount, mobile-app...   \n",
       "4985  [endoscopy, medical-devices, minimally-invasiv...   \n",
       "\n",
       "                                           text_vector_  \n",
       "0     [-0.031224824488162994, -0.06342269480228424, ...  \n",
       "1     [-0.038649097084999084, 0.028091922402381897, ...  \n",
       "2     [0.04561534896492958, -0.017776092514395714, 0...  \n",
       "3     [0.0024080690927803516, -0.03042100928723812, ...  \n",
       "4     [-0.01007091999053955, 0.10431888699531555, -0...  \n",
       "...                                                 ...  \n",
       "4981  [0.026961881667375565, 0.002459645736962557, -...  \n",
       "4982  [0.0036857957020401955, 0.03582162782549858, -...  \n",
       "4983  [0.027293115854263306, 0.010461761616170406, 0...  \n",
       "4984  [0.02851911261677742, 0.05474231392145157, -0....  \n",
       "4985  [0.012587728910148144, -0.07959864288568497, -...  \n",
       "\n",
       "[4986 rows x 9 columns]"
      ]
     },
     "execution_count": 78,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "df = pd.read_parquet('df_encoded.parquet')\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "os.system('pip install openpyxl')\n",
    "os.system('pip install sentence-transformers')\n",
    "import pandas as pd\n",
    "import gradio as gr\n",
    "from sentence_transformers import SentenceTransformer\n",
    "\n",
    "model = SentenceTransformer('all-mpnet-base-v2') #all-MiniLM-L6-v2 #all-mpnet-base-v2\n",
    "\n",
    "df = pd.read_parquet('df_encoded.parquet')\n",
    "df['tags'] = df['tags'].apply(lambda x : str(x))\n",
    "def parse_raised(x):\n",
    "    if x == 'Undisclosed':\n",
    "        return 0\n",
    "    else: \n",
    "        quantifier = x[-1]\n",
    "        x = float(x[1:-1])\n",
    "        if quantifier == 'K':\n",
    "            return x/1000\n",
    "        elif quantifier == 'M':\n",
    "            return x\n",
    "df['raised'] = df['raised'].apply(lambda x : parse_raised(x))\n",
    "df = df.reset_index(drop=True)\n",
    "\n",
    "from sklearn.neighbors import NearestNeighbors\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sentence_transformers import SentenceTransformer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\ardit\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\gradio\\deprecation.py:43: UserWarning: You have unused kwarg parameters in Radio, please remove them: {'multiselect': False}\n",
      "  warnings.warn(\n",
      "c:\\Users\\ardit\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\gradio\\deprecation.py:43: UserWarning: You have unused kwarg parameters in Slider, please remove them: {'step_size': 1}\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running on local URL:  http://127.0.0.1:7896\n",
      "\n",
      "To create a public link, set `share=True` in `launch()`.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div><iframe src=\"http://127.0.0.1:7896/\" 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": 92,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "a\n"
     ]
    }
   ],
   "source": [
    "def filter_df(df, column_name, filter_type, filter_value):\n",
    "    if filter_type == '==':\n",
    "        df_filtered = df[df[column_name]==filter_value]\n",
    "    elif filter_type == '>=':\n",
    "        df_filtered = df[df[column_name]>=filter_value]\n",
    "    elif filter_type == '<=':\n",
    "        df_filtered = df[df[column_name]<=filter_value]\n",
    "    elif filter_type == 'contains':\n",
    "        df_filtered = df[df['target'].str.contains(filter_value)]\n",
    "    return df_filtered\n",
    "\n",
    "def search(df, query):\n",
    "    product = model.encode(query).tolist()\n",
    "    # product = df.iloc[0]['text_vector_'] #use one of the products as sample\n",
    "\n",
    "    #prepare model\n",
    "    nbrs = NearestNeighbors(n_neighbors=20, algorithm='ball_tree').fit(df['text_vector_'].values.tolist())\n",
    "\n",
    "    distances, indices = nbrs.kneighbors([product]) #input the vector of the reference object\n",
    "\n",
    "    #print out the description of every recommended product\n",
    "    return df.iloc[list(indices)[0]][['name', 'description', 'raised', 'year', 'target', 'size', 'stage', 'tags']]\n",
    "\n",
    "#the first module becomes text1, the second module file1\n",
    "def greet(size, target, raised, query): \n",
    "    df_size = filter_df(df, 'size', '==', size)\n",
    "    df_target = filter_df(df_size, 'target', 'contains', target)\n",
    "    def raised_zero(x):\n",
    "        if x == 0:\n",
    "            return 'Undisclosed'\n",
    "        else:\n",
    "            return x\n",
    "    print('a')\n",
    "    df_raised = df_target[(df_target['raised'] >= raised) | (df_target['raised'] == 0)]\n",
    "    df_knn = search(df_raised, query)\n",
    "    #we live the sorting for last\n",
    "    df_knn = df_knn.sort_values('raised', ascending=False)\n",
    "    df_knn['raised'] = df_knn['raised'].apply(lambda x : raised_zero(x))\n",
    "\n",
    "    return df_knn\n",
    "\n",
    "with gr.Blocks(theme=gr.themes.Soft(primary_hue='amber', secondary_hue='gray', neutral_hue='amber')) as demo:\n",
    "    gr.Markdown(\n",
    "    \"\"\"\n",
    "    # Gradio with History\n",
    "    \"\"\"\n",
    "    )\n",
    "    size = gr.Radio(['1-10', '11-50', '51-200', '201-500', '500+'], multiselect=False, value='11-50', label='size')\n",
    "    target = gr.Radio(['B2B', 'B2C', 'B2G', 'B2B2C'], value='B2B', multiselect=False, label='target')\n",
    "    raised = gr.Slider(0, 20, value=5, step_size=1, label=\"Minimum raising (in Millions)\")\n",
    "    query = gr.Textbox(label='Describe the Startup you are searching for', value='age reversing')\n",
    "    btn = gr.Button(value=\"Search for a Startup\")\n",
    "    output1 = gr.DataFrame(label='value')\n",
    "    # btn.click(greet, inputs='text', outputs=['dataframe'])\n",
    "    btn.click(greet, [size, target, raised, query], [output1])\n",
    "demo.launch(share=False)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.9.13"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}