Doctor_Fees.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import re\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.neighbors import KNeighborsRegressor\n",
    "from sklearn.preprocessing import PolynomialFeatures\n",
    "from sklearn.metrics import mean_squared_error, r2_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "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>Qualification</th>\n",
       "      <th>Experience</th>\n",
       "      <th>Rating</th>\n",
       "      <th>Place</th>\n",
       "      <th>Profile</th>\n",
       "      <th>Miscellaneous_Info</th>\n",
       "      <th>Fees</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>BHMS, MD - Homeopathy</td>\n",
       "      <td>24 years experience</td>\n",
       "      <td>100%</td>\n",
       "      <td>Kakkanad, Ernakulam</td>\n",
       "      <td>Homeopath</td>\n",
       "      <td>100% 16 Feedback Kakkanad, Ernakulam</td>\n",
       "      <td>100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>BAMS, MD - Ayurveda Medicine</td>\n",
       "      <td>12 years experience</td>\n",
       "      <td>98%</td>\n",
       "      <td>Whitefield, Bangalore</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>98% 76 Feedback Whitefield, Bangalore</td>\n",
       "      <td>350</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>MBBS, MS - Otorhinolaryngology</td>\n",
       "      <td>9 years experience</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Mathikere - BEL, Bangalore</td>\n",
       "      <td>ENT Specialist</td>\n",
       "      <td>NaN</td>\n",
       "      <td>300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>BSc - Zoology, BAMS</td>\n",
       "      <td>12 years experience</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Bannerghatta Road, Bangalore</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>Bannerghatta Road, Bangalore ₹250 Available on...</td>\n",
       "      <td>250</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>BAMS</td>\n",
       "      <td>20 years experience</td>\n",
       "      <td>100%</td>\n",
       "      <td>Keelkattalai, Chennai</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>100% 4 Feedback Keelkattalai, Chennai</td>\n",
       "      <td>250</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                    Qualification           Experience Rating  \\\n",
       "0           BHMS, MD - Homeopathy  24 years experience   100%   \n",
       "1    BAMS, MD - Ayurveda Medicine  12 years experience    98%   \n",
       "2  MBBS, MS - Otorhinolaryngology   9 years experience    NaN   \n",
       "3             BSc - Zoology, BAMS  12 years experience    NaN   \n",
       "4                            BAMS  20 years experience   100%   \n",
       "\n",
       "                          Place         Profile  \\\n",
       "0           Kakkanad, Ernakulam       Homeopath   \n",
       "1         Whitefield, Bangalore        Ayurveda   \n",
       "2    Mathikere - BEL, Bangalore  ENT Specialist   \n",
       "3  Bannerghatta Road, Bangalore        Ayurveda   \n",
       "4         Keelkattalai, Chennai        Ayurveda   \n",
       "\n",
       "                                  Miscellaneous_Info  Fees  \n",
       "0               100% 16 Feedback Kakkanad, Ernakulam   100  \n",
       "1              98% 76 Feedback Whitefield, Bangalore   350  \n",
       "2                                                NaN   300  \n",
       "3  Bannerghatta Road, Bangalore ₹250 Available on...   250  \n",
       "4              100% 4 Feedback Keelkattalai, Chennai   250  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train = pd.read_excel('Final_Train.xlsx')\n",
    "df_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5961, 7)"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.shape(df_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1987, 6)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_test = pd.read_excel('Final_Test.xlsx')\n",
    "np.shape(df_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# df_test['Len']  = df_test['Qualification'].apply(lambda x : len(x))\n",
    "# result = df_test.sort_values(['Len'], ascending = False)\n",
    "# result.iloc[0]['Qualification']"
   ]
  },
  {
   "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>Qualification</th>\n",
       "      <th>Experience</th>\n",
       "      <th>Rating</th>\n",
       "      <th>Place</th>\n",
       "      <th>Profile</th>\n",
       "      <th>Miscellaneous_Info</th>\n",
       "      <th>Fees</th>\n",
       "      <th>City</th>\n",
       "      <th>Area</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>BHMS, MD - Homeopathy</td>\n",
       "      <td>24 years experience</td>\n",
       "      <td>100%</td>\n",
       "      <td>Kakkanad, Ernakulam</td>\n",
       "      <td>Homeopath</td>\n",
       "      <td>100% 16 Feedback Kakkanad, Ernakulam</td>\n",
       "      <td>100</td>\n",
       "      <td>Ernakulam</td>\n",
       "      <td>Kakkanad</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>BAMS, MD - Ayurveda Medicine</td>\n",
       "      <td>12 years experience</td>\n",
       "      <td>98%</td>\n",
       "      <td>Whitefield, Bangalore</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>98% 76 Feedback Whitefield, Bangalore</td>\n",
       "      <td>350</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Whitefield</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>MBBS, MS - Otorhinolaryngology</td>\n",
       "      <td>9 years experience</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Mathikere - BEL, Bangalore</td>\n",
       "      <td>ENT Specialist</td>\n",
       "      <td>NaN</td>\n",
       "      <td>300</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Mathikere - BEL</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>BSc - Zoology, BAMS</td>\n",
       "      <td>12 years experience</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Bannerghatta Road, Bangalore</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>Bannerghatta Road, Bangalore ₹250 Available on...</td>\n",
       "      <td>250</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Bannerghatta Road</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>BAMS</td>\n",
       "      <td>20 years experience</td>\n",
       "      <td>100%</td>\n",
       "      <td>Keelkattalai, Chennai</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>100% 4 Feedback Keelkattalai, Chennai</td>\n",
       "      <td>250</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>Keelkattalai</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                    Qualification           Experience Rating  \\\n",
       "0           BHMS, MD - Homeopathy  24 years experience   100%   \n",
       "1    BAMS, MD - Ayurveda Medicine  12 years experience    98%   \n",
       "2  MBBS, MS - Otorhinolaryngology   9 years experience    NaN   \n",
       "3             BSc - Zoology, BAMS  12 years experience    NaN   \n",
       "4                            BAMS  20 years experience   100%   \n",
       "\n",
       "                          Place         Profile  \\\n",
       "0           Kakkanad, Ernakulam       Homeopath   \n",
       "1         Whitefield, Bangalore        Ayurveda   \n",
       "2    Mathikere - BEL, Bangalore  ENT Specialist   \n",
       "3  Bannerghatta Road, Bangalore        Ayurveda   \n",
       "4         Keelkattalai, Chennai        Ayurveda   \n",
       "\n",
       "                                  Miscellaneous_Info  Fees       City  \\\n",
       "0               100% 16 Feedback Kakkanad, Ernakulam   100  Ernakulam   \n",
       "1              98% 76 Feedback Whitefield, Bangalore   350  Bangalore   \n",
       "2                                                NaN   300  Bangalore   \n",
       "3  Bannerghatta Road, Bangalore ₹250 Available on...   250  Bangalore   \n",
       "4              100% 4 Feedback Keelkattalai, Chennai   250    Chennai   \n",
       "\n",
       "                Area  \n",
       "0           Kakkanad  \n",
       "1         Whitefield  \n",
       "2    Mathikere - BEL  \n",
       "3  Bannerghatta Road  \n",
       "4       Keelkattalai  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train['City'] = df_train['Place'].str.split(', ').str[-1]\n",
    "df_train['Area'] = df_train['Place'].str.split(', ').str[0]\n",
    "\n",
    "\n",
    "df_test['City'] = df_test['Place'].str.split(', ').str[-1]\n",
    "df_test['Area'] = df_test['Place'].str.split(', ').str[0]\n",
    "\n",
    "df_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "City\n",
       "Bangalore             1258\n",
       "Chennai                855\n",
       "Coimbatore             228\n",
       "Delhi                 1185\n",
       "Ernakulam              153\n",
       "Hyderabad              951\n",
       "Mumbai                1219\n",
       "Thiruvananthapuram      86\n",
       "e                        1\n",
       "Name: Qualification, dtype: int64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "count = df_train.groupby(['City']).count()\n",
    "count.Qualification"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Int64Index([3980], dtype='int64')"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "val = df_train[df_train['City'] == 'e'].index\n",
    "val"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_train = df_train.drop([3980])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_train['Experience'] = df_train['Experience'].apply(lambda x : re.findall(r'^\\d\\d?', x)[0]).astype(int)\n",
    "\n",
    "df_test['Experience'] = df_test['Experience'].apply(lambda x : re.findall(r'^\\d\\d?', x)[0]).astype(int)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "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>Qualification</th>\n",
       "      <th>Experience</th>\n",
       "      <th>Rating</th>\n",
       "      <th>Place</th>\n",
       "      <th>Profile</th>\n",
       "      <th>Miscellaneous_Info</th>\n",
       "      <th>Fees</th>\n",
       "      <th>City</th>\n",
       "      <th>Area</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>BHMS, MD - Homeopathy</td>\n",
       "      <td>24</td>\n",
       "      <td>100.0</td>\n",
       "      <td>Kakkanad, Ernakulam</td>\n",
       "      <td>Homeopath</td>\n",
       "      <td>100% 16 Feedback Kakkanad, Ernakulam</td>\n",
       "      <td>100</td>\n",
       "      <td>Ernakulam</td>\n",
       "      <td>Kakkanad</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>BAMS, MD - Ayurveda Medicine</td>\n",
       "      <td>12</td>\n",
       "      <td>98.0</td>\n",
       "      <td>Whitefield, Bangalore</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>98% 76 Feedback Whitefield, Bangalore</td>\n",
       "      <td>350</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Whitefield</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>MBBS, MS - Otorhinolaryngology</td>\n",
       "      <td>9</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Mathikere - BEL, Bangalore</td>\n",
       "      <td>ENT Specialist</td>\n",
       "      <td>NaN</td>\n",
       "      <td>300</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Mathikere - BEL</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>BSc - Zoology, BAMS</td>\n",
       "      <td>12</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Bannerghatta Road, Bangalore</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>Bannerghatta Road, Bangalore ₹250 Available on...</td>\n",
       "      <td>250</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Bannerghatta Road</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>BAMS</td>\n",
       "      <td>20</td>\n",
       "      <td>100.0</td>\n",
       "      <td>Keelkattalai, Chennai</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>100% 4 Feedback Keelkattalai, Chennai</td>\n",
       "      <td>250</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>Keelkattalai</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                    Qualification  Experience  Rating  \\\n",
       "0           BHMS, MD - Homeopathy          24   100.0   \n",
       "1    BAMS, MD - Ayurveda Medicine          12    98.0   \n",
       "2  MBBS, MS - Otorhinolaryngology           9     0.0   \n",
       "3             BSc - Zoology, BAMS          12     0.0   \n",
       "4                            BAMS          20   100.0   \n",
       "\n",
       "                          Place         Profile  \\\n",
       "0           Kakkanad, Ernakulam       Homeopath   \n",
       "1         Whitefield, Bangalore        Ayurveda   \n",
       "2    Mathikere - BEL, Bangalore  ENT Specialist   \n",
       "3  Bannerghatta Road, Bangalore        Ayurveda   \n",
       "4         Keelkattalai, Chennai        Ayurveda   \n",
       "\n",
       "                                  Miscellaneous_Info  Fees       City  \\\n",
       "0               100% 16 Feedback Kakkanad, Ernakulam   100  Ernakulam   \n",
       "1              98% 76 Feedback Whitefield, Bangalore   350  Bangalore   \n",
       "2                                                NaN   300  Bangalore   \n",
       "3  Bannerghatta Road, Bangalore ₹250 Available on...   250  Bangalore   \n",
       "4              100% 4 Feedback Keelkattalai, Chennai   250    Chennai   \n",
       "\n",
       "                Area  \n",
       "0           Kakkanad  \n",
       "1         Whitefield  \n",
       "2    Mathikere - BEL  \n",
       "3  Bannerghatta Road  \n",
       "4       Keelkattalai  "
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train['Rating'].fillna('0%',inplace = True)\n",
    "df_train['Rating'] = df_train['Rating'].str[0:-1].astype(float)\n",
    "\n",
    "df_test['Rating'].fillna('0%',inplace = True)\n",
    "df_test['Rating'] = df_test['Rating'].str[0:-1].astype(float)\n",
    "\n",
    "df_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Homeopath', 'Ayurveda', 'ENT Specialist', 'Dentist',\n",
       "       'General Medicine', 'Dermatologists'], dtype=object)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train['Profile'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "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>Qualification</th>\n",
       "      <th>Experience</th>\n",
       "      <th>Rating</th>\n",
       "      <th>Place</th>\n",
       "      <th>Profile</th>\n",
       "      <th>Miscellaneous_Info</th>\n",
       "      <th>Fees</th>\n",
       "      <th>City</th>\n",
       "      <th>Area</th>\n",
       "      <th>Profile_Ayurveda</th>\n",
       "      <th>...</th>\n",
       "      <th>Profile_General Medicine</th>\n",
       "      <th>Profile_Homeopath</th>\n",
       "      <th>City_Bangalore</th>\n",
       "      <th>City_Chennai</th>\n",
       "      <th>City_Coimbatore</th>\n",
       "      <th>City_Delhi</th>\n",
       "      <th>City_Ernakulam</th>\n",
       "      <th>City_Hyderabad</th>\n",
       "      <th>City_Mumbai</th>\n",
       "      <th>City_Thiruvananthapuram</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>BHMS, MD - Homeopathy</td>\n",
       "      <td>24</td>\n",
       "      <td>100.0</td>\n",
       "      <td>Kakkanad, Ernakulam</td>\n",
       "      <td>Homeopath</td>\n",
       "      <td>100% 16 Feedback Kakkanad, Ernakulam</td>\n",
       "      <td>100</td>\n",
       "      <td>Ernakulam</td>\n",
       "      <td>Kakkanad</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>BAMS, MD - Ayurveda Medicine</td>\n",
       "      <td>12</td>\n",
       "      <td>98.0</td>\n",
       "      <td>Whitefield, Bangalore</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>98% 76 Feedback Whitefield, Bangalore</td>\n",
       "      <td>350</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Whitefield</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>MBBS, MS - Otorhinolaryngology</td>\n",
       "      <td>9</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Mathikere - BEL, Bangalore</td>\n",
       "      <td>ENT Specialist</td>\n",
       "      <td>NaN</td>\n",
       "      <td>300</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Mathikere - BEL</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>BSc - Zoology, BAMS</td>\n",
       "      <td>12</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Bannerghatta Road, Bangalore</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>Bannerghatta Road, Bangalore ₹250 Available on...</td>\n",
       "      <td>250</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Bannerghatta Road</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>BAMS</td>\n",
       "      <td>20</td>\n",
       "      <td>100.0</td>\n",
       "      <td>Keelkattalai, Chennai</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>100% 4 Feedback Keelkattalai, Chennai</td>\n",
       "      <td>250</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>Keelkattalai</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 23 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                    Qualification  Experience  Rating  \\\n",
       "0           BHMS, MD - Homeopathy          24   100.0   \n",
       "1    BAMS, MD - Ayurveda Medicine          12    98.0   \n",
       "2  MBBS, MS - Otorhinolaryngology           9     0.0   \n",
       "3             BSc - Zoology, BAMS          12     0.0   \n",
       "4                            BAMS          20   100.0   \n",
       "\n",
       "                          Place         Profile  \\\n",
       "0           Kakkanad, Ernakulam       Homeopath   \n",
       "1         Whitefield, Bangalore        Ayurveda   \n",
       "2    Mathikere - BEL, Bangalore  ENT Specialist   \n",
       "3  Bannerghatta Road, Bangalore        Ayurveda   \n",
       "4         Keelkattalai, Chennai        Ayurveda   \n",
       "\n",
       "                                  Miscellaneous_Info  Fees       City  \\\n",
       "0               100% 16 Feedback Kakkanad, Ernakulam   100  Ernakulam   \n",
       "1              98% 76 Feedback Whitefield, Bangalore   350  Bangalore   \n",
       "2                                                NaN   300  Bangalore   \n",
       "3  Bannerghatta Road, Bangalore ₹250 Available on...   250  Bangalore   \n",
       "4              100% 4 Feedback Keelkattalai, Chennai   250    Chennai   \n",
       "\n",
       "                Area  Profile_Ayurveda  ...  Profile_General Medicine  \\\n",
       "0           Kakkanad                 0  ...                         0   \n",
       "1         Whitefield                 1  ...                         0   \n",
       "2    Mathikere - BEL                 0  ...                         0   \n",
       "3  Bannerghatta Road                 1  ...                         0   \n",
       "4       Keelkattalai                 1  ...                         0   \n",
       "\n",
       "   Profile_Homeopath  City_Bangalore  City_Chennai  City_Coimbatore  \\\n",
       "0                  1               0             0                0   \n",
       "1                  0               1             0                0   \n",
       "2                  0               1             0                0   \n",
       "3                  0               1             0                0   \n",
       "4                  0               0             1                0   \n",
       "\n",
       "   City_Delhi  City_Ernakulam  City_Hyderabad  City_Mumbai  \\\n",
       "0           0               1               0            0   \n",
       "1           0               0               0            0   \n",
       "2           0               0               0            0   \n",
       "3           0               0               0            0   \n",
       "4           0               0               0            0   \n",
       "\n",
       "   City_Thiruvananthapuram  \n",
       "0                        0  \n",
       "1                        0  \n",
       "2                        0  \n",
       "3                        0  \n",
       "4                        0  \n",
       "\n",
       "[5 rows x 23 columns]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "temp = pd.get_dummies(df_train[['Profile', 'City']], prefix_sep = '_', prefix = ['Profile', 'City'])\n",
    "df_train = pd.concat([df_train, temp], axis=1, join = 'inner')\n",
    "df_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "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>Qualification</th>\n",
       "      <th>Experience</th>\n",
       "      <th>Rating</th>\n",
       "      <th>Place</th>\n",
       "      <th>Profile</th>\n",
       "      <th>Miscellaneous_Info</th>\n",
       "      <th>City</th>\n",
       "      <th>Area</th>\n",
       "      <th>Profile_Ayurveda</th>\n",
       "      <th>Profile_Dentist</th>\n",
       "      <th>...</th>\n",
       "      <th>Profile_General Medicine</th>\n",
       "      <th>Profile_Homeopath</th>\n",
       "      <th>City_Bangalore</th>\n",
       "      <th>City_Chennai</th>\n",
       "      <th>City_Coimbatore</th>\n",
       "      <th>City_Delhi</th>\n",
       "      <th>City_Ernakulam</th>\n",
       "      <th>City_Hyderabad</th>\n",
       "      <th>City_Mumbai</th>\n",
       "      <th>City_Thiruvananthapuram</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>MBBS</td>\n",
       "      <td>35</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Ghatkopar East, Mumbai</td>\n",
       "      <td>General Medicine</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Mumbai</td>\n",
       "      <td>Ghatkopar East</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</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>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>MBBS, Diploma in Otorhinolaryngology (DLO)</td>\n",
       "      <td>31</td>\n",
       "      <td>0.0</td>\n",
       "      <td>West Marredpally, Hyderabad</td>\n",
       "      <td>ENT Specialist</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Hyderabad</td>\n",
       "      <td>West Marredpally</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>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>MBBS, DDVL</td>\n",
       "      <td>40</td>\n",
       "      <td>70.0</td>\n",
       "      <td>KK Nagar, Chennai</td>\n",
       "      <td>Dermatologists</td>\n",
       "      <td>70% 4 Feedback KK Nagar, Chennai</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>KK Nagar</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>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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>BAMS</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>New Ashok Nagar, Delhi</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>New Ashok Nagar</td>\n",
       "      <td>1</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>1</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>BDS, MDS - Conservative Dentistry &amp; Endodontics</td>\n",
       "      <td>16</td>\n",
       "      <td>100.0</td>\n",
       "      <td>Kanakpura Road, Bangalore</td>\n",
       "      <td>Dentist</td>\n",
       "      <td>General Dentistry Conservative Dentistry Cosme...</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Kanakpura Road</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 22 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                     Qualification  Experience  Rating  \\\n",
       "0                                             MBBS          35     0.0   \n",
       "1       MBBS, Diploma in Otorhinolaryngology (DLO)          31     0.0   \n",
       "2                                       MBBS, DDVL          40    70.0   \n",
       "3                                             BAMS           0     0.0   \n",
       "4  BDS, MDS - Conservative Dentistry & Endodontics          16   100.0   \n",
       "\n",
       "                         Place           Profile  \\\n",
       "0       Ghatkopar East, Mumbai  General Medicine   \n",
       "1  West Marredpally, Hyderabad    ENT Specialist   \n",
       "2            KK Nagar, Chennai    Dermatologists   \n",
       "3       New Ashok Nagar, Delhi          Ayurveda   \n",
       "4    Kanakpura Road, Bangalore           Dentist   \n",
       "\n",
       "                                  Miscellaneous_Info       City  \\\n",
       "0                                                NaN     Mumbai   \n",
       "1                                                NaN  Hyderabad   \n",
       "2                   70% 4 Feedback KK Nagar, Chennai    Chennai   \n",
       "3                                                NaN      Delhi   \n",
       "4  General Dentistry Conservative Dentistry Cosme...  Bangalore   \n",
       "\n",
       "               Area  Profile_Ayurveda  Profile_Dentist  ...  \\\n",
       "0    Ghatkopar East                 0                0  ...   \n",
       "1  West Marredpally                 0                0  ...   \n",
       "2          KK Nagar                 0                0  ...   \n",
       "3   New Ashok Nagar                 1                0  ...   \n",
       "4    Kanakpura Road                 0                1  ...   \n",
       "\n",
       "   Profile_General Medicine  Profile_Homeopath  City_Bangalore  City_Chennai  \\\n",
       "0                         1                  0               0             0   \n",
       "1                         0                  0               0             0   \n",
       "2                         0                  0               0             1   \n",
       "3                         0                  0               0             0   \n",
       "4                         0                  0               1             0   \n",
       "\n",
       "   City_Coimbatore  City_Delhi  City_Ernakulam  City_Hyderabad  City_Mumbai  \\\n",
       "0                0           0               0               0            1   \n",
       "1                0           0               0               1            0   \n",
       "2                0           0               0               0            0   \n",
       "3                0           1               0               0            0   \n",
       "4                0           0               0               0            0   \n",
       "\n",
       "   City_Thiruvananthapuram  \n",
       "0                        0  \n",
       "1                        0  \n",
       "2                        0  \n",
       "3                        0  \n",
       "4                        0  \n",
       "\n",
       "[5 rows x 22 columns]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "temp = pd.get_dummies(df_test[['Profile', 'City']], prefix_sep = '_', prefix = ['Profile', 'City'])\n",
    "df_test = pd.concat([df_test, temp], axis=1, join = 'inner')\n",
    "df_test.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "def sortQual(text):\n",
    "    arr = re.sub(r'\\(.*?\\)', lambda x: x.group().replace(\",\",\"-\"), text) # to replace ',' with '-' inside brackets only\n",
    "    return (sorted(arr.lower().replace(\" \",\"\").split(\",\")))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_train['Qualification'] = df_train['Qualification'].apply(lambda x : sortQual(x))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_test['Qualification'] = df_test['Qualification'].apply(lambda x : sortQual(x))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['advancedendotonticcourseonrootcanal',\n",
       " 'advancedretreatmentcourseinrct',\n",
       " 'bds',\n",
       " 'certificateincosmeticdentistry',\n",
       " 'certificationinprosthodontics&periodontology',\n",
       " 'certifiedadvancedcourseinwisdomtoothextraction',\n",
       " 'certifiedcourseinoralsurgery',\n",
       " 'diplomaincosmeticdentistry',\n",
       " 'endodonticsandaestheticdentistry',\n",
       " 'fellowofacademyofgeneraleducation(fage)',\n",
       " 'fellowshipinaestheticdentistry(fad)',\n",
       " 'fellowshipinclinicalcosmetology',\n",
       " 'mba-hospitalmanagement',\n",
       " 'mida',\n",
       " 'pgdiplomainclinicalcosmetology(pgdcc)',\n",
       " 'pgdiplomainconservative',\n",
       " 'postgraduatecertificateinendodontics(pgce)']"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_test.iloc[1287]['Qualification']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "qual_dict = {}\n",
    "\n",
    "train_quals = []\n",
    "test_quals = []\n",
    "\n",
    "train_quals.append(list(df_train['Qualification'].values))\n",
    "test_quals.append(list(df_test['Qualification'].values))\n",
    "\n",
    "for quals in train_quals[0]:\n",
    "    for item in quals:\n",
    "        if item in qual_dict:\n",
    "            qual_dict[item] += 1\n",
    "        else:\n",
    "            qual_dict[item] = 1\n",
    "            \n",
    "for quals in test_quals[0]:\n",
    "    for item in quals:\n",
    "        if item in qual_dict:\n",
    "            qual_dict[item] += 1\n",
    "        else:\n",
    "            qual_dict[item] = 1\n",
    "            \n",
    "# qual_dict['Empty'] = 0\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "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>Qualification</th>\n",
       "      <th>Count</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>890</th>\n",
       "      <td>fellowshipindiabetesmanagement</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>891</th>\n",
       "      <td>frcp-internalmedicine</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>892</th>\n",
       "      <td>fais</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>893</th>\n",
       "      <td>fiages</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>894</th>\n",
       "      <td>md/ms-obstetrics&amp;gynaecology</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                      Qualification  Count\n",
       "890  fellowshipindiabetesmanagement      1\n",
       "891           frcp-internalmedicine      1\n",
       "892                            fais      1\n",
       "893                          fiages      1\n",
       "894    md/ms-obstetrics&gynaecology      1"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "qual_df = pd.DataFrame.from_dict(dict(sorted(qual_dict.items(), key = lambda x : x[1] , reverse = True)), orient = 'index').reset_index()\n",
    "qual_df.columns = ['Qualification', 'Count']\n",
    "qual_df.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "x = qual_df[qual_df['Qualification'] == '39yearsexperience'].index\n",
    "qual_df = qual_df.drop(x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "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>Qualification</th>\n",
       "      <th>Count</th>\n",
       "      <th>Code</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>mbbs</td>\n",
       "      <td>3788</td>\n",
       "      <td>579</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>bds</td>\n",
       "      <td>1790</td>\n",
       "      <td>31</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>bams</td>\n",
       "      <td>1007</td>\n",
       "      <td>28</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>bhms</td>\n",
       "      <td>998</td>\n",
       "      <td>33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>md-dermatology</td>\n",
       "      <td>802</td>\n",
       "      <td>615</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Qualification  Count  Code\n",
       "0            mbbs   3788   579\n",
       "1             bds   1790    31\n",
       "2            bams   1007    28\n",
       "3            bhms    998    33\n",
       "4  md-dermatology    802   615"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "qual_df[\"Code\"] = qual_df[\"Qualification\"].astype('category').cat.codes\n",
    "qual_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "# scaler = StandardScaler()\n",
    "# qual_df['Code'] = scaler.fit_transform(qual_df['Code'].values.reshape(-1,1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "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>Qualification</th>\n",
       "      <th>Count</th>\n",
       "      <th>Code</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>890</th>\n",
       "      <td>fellowshipindiabetesmanagement</td>\n",
       "      <td>1</td>\n",
       "      <td>424</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>891</th>\n",
       "      <td>frcp-internalmedicine</td>\n",
       "      <td>1</td>\n",
       "      <td>500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>892</th>\n",
       "      <td>fais</td>\n",
       "      <td>1</td>\n",
       "      <td>364</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>893</th>\n",
       "      <td>fiages</td>\n",
       "      <td>1</td>\n",
       "      <td>482</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>894</th>\n",
       "      <td>md/ms-obstetrics&amp;gynaecology</td>\n",
       "      <td>1</td>\n",
       "      <td>660</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                      Qualification  Count  Code\n",
       "890  fellowshipindiabetesmanagement      1   424\n",
       "891           frcp-internalmedicine      1   500\n",
       "892                            fais      1   364\n",
       "893                          fiages      1   482\n",
       "894    md/ms-obstetrics&gynaecology      1   660"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "qual_df.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "conversion_dict = dict(zip(qual_df['Qualification'], qual_df['Code']))\n",
    "conversion_dict['39yearsexperience'] = -1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['advancedendotonticcourseonrootcanal',\n",
       " 'advancedretreatmentcourseinrct',\n",
       " 'bds',\n",
       " 'certificateincosmeticdentistry',\n",
       " 'certificationinprosthodontics&periodontology',\n",
       " 'certifiedadvancedcourseinwisdomtoothextraction',\n",
       " 'certifiedcourseinoralsurgery',\n",
       " 'diplomaincosmeticdentistry',\n",
       " 'endodonticsandaestheticdentistry',\n",
       " 'fellowofacademyofgeneraleducation(fage)',\n",
       " 'fellowshipinaestheticdentistry(fad)',\n",
       " 'fellowshipinclinicalcosmetology',\n",
       " 'mba-hospitalmanagement',\n",
       " 'mida',\n",
       " 'pgdiplomainclinicalcosmetology(pgdcc)',\n",
       " 'pgdiplomainconservative',\n",
       " 'postgraduatecertificateinendodontics(pgce)']"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "stat_test = df_test.Qualification.apply(lambda x: len(x))\n",
    "stat_test.idxmax()\n",
    "df_test[df_test['Qualification'].str.len()>10]['Qualification']\n",
    "stat_test.idxmax()\n",
    "df_test.iloc[1287]['Qualification']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "10"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "stat_train = df_train.Qualification.apply(lambda x: len(x))\n",
    "stat_train.max()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "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>Qualification</th>\n",
       "      <th>Experience</th>\n",
       "      <th>Rating</th>\n",
       "      <th>Place</th>\n",
       "      <th>Profile</th>\n",
       "      <th>Miscellaneous_Info</th>\n",
       "      <th>Fees</th>\n",
       "      <th>City</th>\n",
       "      <th>Area</th>\n",
       "      <th>Profile_Ayurveda</th>\n",
       "      <th>...</th>\n",
       "      <th>Qual_1</th>\n",
       "      <th>Qual_2</th>\n",
       "      <th>Qual_3</th>\n",
       "      <th>Qual_4</th>\n",
       "      <th>Qual_5</th>\n",
       "      <th>Qual_6</th>\n",
       "      <th>Qual_7</th>\n",
       "      <th>Qual_8</th>\n",
       "      <th>Qual_9</th>\n",
       "      <th>Qual_10</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>[bhms, md-homeopathy]</td>\n",
       "      <td>24</td>\n",
       "      <td>100.0</td>\n",
       "      <td>Kakkanad, Ernakulam</td>\n",
       "      <td>Homeopath</td>\n",
       "      <td>100% 16 Feedback Kakkanad, Ernakulam</td>\n",
       "      <td>100</td>\n",
       "      <td>Ernakulam</td>\n",
       "      <td>Kakkanad</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>bhms</td>\n",
       "      <td>md-homeopathy</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>[bams, md-ayurvedamedicine]</td>\n",
       "      <td>12</td>\n",
       "      <td>98.0</td>\n",
       "      <td>Whitefield, Bangalore</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>98% 76 Feedback Whitefield, Bangalore</td>\n",
       "      <td>350</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Whitefield</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>bams</td>\n",
       "      <td>md-ayurvedamedicine</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>[mbbs, ms-otorhinolaryngology]</td>\n",
       "      <td>9</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Mathikere - BEL, Bangalore</td>\n",
       "      <td>ENT Specialist</td>\n",
       "      <td>NaN</td>\n",
       "      <td>300</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Mathikere - BEL</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>mbbs</td>\n",
       "      <td>ms-otorhinolaryngology</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>[bams, bsc-zoology]</td>\n",
       "      <td>12</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Bannerghatta Road, Bangalore</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>Bannerghatta Road, Bangalore ₹250 Available on...</td>\n",
       "      <td>250</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Bannerghatta Road</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>bams</td>\n",
       "      <td>bsc-zoology</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>[bams]</td>\n",
       "      <td>20</td>\n",
       "      <td>100.0</td>\n",
       "      <td>Keelkattalai, Chennai</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>100% 4 Feedback Keelkattalai, Chennai</td>\n",
       "      <td>250</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>Keelkattalai</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>bams</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 33 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                    Qualification  Experience  Rating  \\\n",
       "0           [bhms, md-homeopathy]          24   100.0   \n",
       "1     [bams, md-ayurvedamedicine]          12    98.0   \n",
       "2  [mbbs, ms-otorhinolaryngology]           9     0.0   \n",
       "3             [bams, bsc-zoology]          12     0.0   \n",
       "4                          [bams]          20   100.0   \n",
       "\n",
       "                          Place         Profile  \\\n",
       "0           Kakkanad, Ernakulam       Homeopath   \n",
       "1         Whitefield, Bangalore        Ayurveda   \n",
       "2    Mathikere - BEL, Bangalore  ENT Specialist   \n",
       "3  Bannerghatta Road, Bangalore        Ayurveda   \n",
       "4         Keelkattalai, Chennai        Ayurveda   \n",
       "\n",
       "                                  Miscellaneous_Info  Fees       City  \\\n",
       "0               100% 16 Feedback Kakkanad, Ernakulam   100  Ernakulam   \n",
       "1              98% 76 Feedback Whitefield, Bangalore   350  Bangalore   \n",
       "2                                                NaN   300  Bangalore   \n",
       "3  Bannerghatta Road, Bangalore ₹250 Available on...   250  Bangalore   \n",
       "4              100% 4 Feedback Keelkattalai, Chennai   250    Chennai   \n",
       "\n",
       "                Area  Profile_Ayurveda  ...  Qual_1                  Qual_2  \\\n",
       "0           Kakkanad                 0  ...    bhms           md-homeopathy   \n",
       "1         Whitefield                 1  ...    bams     md-ayurvedamedicine   \n",
       "2    Mathikere - BEL                 0  ...    mbbs  ms-otorhinolaryngology   \n",
       "3  Bannerghatta Road                 1  ...    bams             bsc-zoology   \n",
       "4       Keelkattalai                 1  ...    bams                     NaN   \n",
       "\n",
       "   Qual_3  Qual_4  Qual_5  Qual_6  Qual_7  Qual_8  Qual_9  Qual_10  \n",
       "0     NaN     NaN     NaN     NaN     NaN     NaN     NaN      NaN  \n",
       "1     NaN     NaN     NaN     NaN     NaN     NaN     NaN      NaN  \n",
       "2     NaN     NaN     NaN     NaN     NaN     NaN     NaN      NaN  \n",
       "3     NaN     NaN     NaN     NaN     NaN     NaN     NaN      NaN  \n",
       "4     NaN     NaN     NaN     NaN     NaN     NaN     NaN      NaN  \n",
       "\n",
       "[5 rows x 33 columns]"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_quals = []\n",
    "for i in range(stat_train.max()):\n",
    "    col_name = 'Qual_' + str(i+1)\n",
    "    train_quals.append(col_name)\n",
    "    col_i = df_train['Qualification'].str[i]\n",
    "    df_train[col_name] = col_i\n",
    "#     df_train[col_name] = df_train[col_name].fillna(\"Empty\")\n",
    "    \n",
    "    \n",
    "    \n",
    "    \n",
    "df_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "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>Qualification</th>\n",
       "      <th>Experience</th>\n",
       "      <th>Rating</th>\n",
       "      <th>Place</th>\n",
       "      <th>Profile</th>\n",
       "      <th>Miscellaneous_Info</th>\n",
       "      <th>City</th>\n",
       "      <th>Area</th>\n",
       "      <th>Profile_Ayurveda</th>\n",
       "      <th>Profile_Dentist</th>\n",
       "      <th>...</th>\n",
       "      <th>Qual_8</th>\n",
       "      <th>Qual_9</th>\n",
       "      <th>Qual_10</th>\n",
       "      <th>Qual_11</th>\n",
       "      <th>Qual_12</th>\n",
       "      <th>Qual_13</th>\n",
       "      <th>Qual_14</th>\n",
       "      <th>Qual_15</th>\n",
       "      <th>Qual_16</th>\n",
       "      <th>Qual_17</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>[mbbs]</td>\n",
       "      <td>35</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Ghatkopar East, Mumbai</td>\n",
       "      <td>General Medicine</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Mumbai</td>\n",
       "      <td>Ghatkopar East</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>[diplomainotorhinolaryngology(dlo), mbbs]</td>\n",
       "      <td>31</td>\n",
       "      <td>0.0</td>\n",
       "      <td>West Marredpally, Hyderabad</td>\n",
       "      <td>ENT Specialist</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Hyderabad</td>\n",
       "      <td>West Marredpally</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>[ddvl, mbbs]</td>\n",
       "      <td>40</td>\n",
       "      <td>70.0</td>\n",
       "      <td>KK Nagar, Chennai</td>\n",
       "      <td>Dermatologists</td>\n",
       "      <td>70% 4 Feedback KK Nagar, Chennai</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>KK Nagar</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>[bams]</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>New Ashok Nagar, Delhi</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>New Ashok Nagar</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>[bds, mds-conservativedentistry&amp;endodontics]</td>\n",
       "      <td>16</td>\n",
       "      <td>100.0</td>\n",
       "      <td>Kanakpura Road, Bangalore</td>\n",
       "      <td>Dentist</td>\n",
       "      <td>General Dentistry Conservative Dentistry Cosme...</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Kanakpura Road</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>[bds, mds]</td>\n",
       "      <td>14</td>\n",
       "      <td>90.0</td>\n",
       "      <td>Velachery, Chennai</td>\n",
       "      <td>Dentist</td>\n",
       "      <td>Acrylic Partial Denture Impaction / Impacted T...</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>Velachery</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>[diplomainotorhinolaryngology(dlo), mbbs]</td>\n",
       "      <td>23</td>\n",
       "      <td>94.0</td>\n",
       "      <td>Frazer Town, Bangalore</td>\n",
       "      <td>ENT Specialist</td>\n",
       "      <td>94% 6 Feedback Frazer Town, Bangalore</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Frazer Town</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>[bds, mds-pedodontics]</td>\n",
       "      <td>9</td>\n",
       "      <td>94.0</td>\n",
       "      <td>Attapur, Hyderabad</td>\n",
       "      <td>Dentist</td>\n",
       "      <td>RCT - Root Canal Treatment Ceramic Veneers / C...</td>\n",
       "      <td>Hyderabad</td>\n",
       "      <td>Attapur</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>[bams, m.d.inkayachikista, md-ayurvedamedicine...</td>\n",
       "      <td>11</td>\n",
       "      <td>99.0</td>\n",
       "      <td>Banashankari, Bangalore</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>99% 203 Feedback Banashankari, Bangalore</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Banashankari</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>[bhms]</td>\n",
       "      <td>44</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Mayur Vihar Ph-I, Delhi</td>\n",
       "      <td>Homeopath</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Mayur Vihar Ph-I</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>[bds]</td>\n",
       "      <td>4</td>\n",
       "      <td>100.0</td>\n",
       "      <td>Erragadda, Hyderabad</td>\n",
       "      <td>Dentist</td>\n",
       "      <td>Dental Fillings Zirconia Crowns RCT - Single S...</td>\n",
       "      <td>Hyderabad</td>\n",
       "      <td>Erragadda</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>[fcd-diabetology, mbbs]</td>\n",
       "      <td>34</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Gandhipuram, Coimbatore</td>\n",
       "      <td>General Medicine</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Coimbatore</td>\n",
       "      <td>Gandhipuram</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>[ddv, mbbs]</td>\n",
       "      <td>11</td>\n",
       "      <td>98.0</td>\n",
       "      <td>Kemps Corner, Mumbai</td>\n",
       "      <td>Dermatologists</td>\n",
       "      <td>98% 28 Feedback Kemps Corner, Mumbai</td>\n",
       "      <td>Mumbai</td>\n",
       "      <td>Kemps Corner</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>[mbbs, md-dermatology]</td>\n",
       "      <td>13</td>\n",
       "      <td>99.0</td>\n",
       "      <td>Banjara Hills, Hyderabad</td>\n",
       "      <td>Dermatologists</td>\n",
       "      <td>Laser Hair Removal - Face Skin Tag Treatment H...</td>\n",
       "      <td>Hyderabad</td>\n",
       "      <td>Banjara Hills</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>[ms-ent]</td>\n",
       "      <td>4</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Madandapuram, Chennai</td>\n",
       "      <td>ENT Specialist</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>Madandapuram</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>[bds]</td>\n",
       "      <td>4</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Mukherjee Nagar, Delhi</td>\n",
       "      <td>Dentist</td>\n",
       "      <td>Mukherjee Nagar, Delhi ₹250 Visits Today</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Mukherjee Nagar</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>[mbbs, md-dermatology]</td>\n",
       "      <td>16</td>\n",
       "      <td>87.0</td>\n",
       "      <td>Tis Hazari, Delhi</td>\n",
       "      <td>Dermatologists</td>\n",
       "      <td>87% 9 Feedback Tis Hazari, Delhi</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Tis Hazari</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>[diplomainotorhinolaryngology(dlo), dnb-ent, m...</td>\n",
       "      <td>28</td>\n",
       "      <td>64.0</td>\n",
       "      <td>Banashankari 2nd Stage, Bangalore</td>\n",
       "      <td>ENT Specialist</td>\n",
       "      <td>64% 4 Feedback Banashankari 2nd Stage, Bangalore</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Banashankari 2nd Stage</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>[bds, mds-conservativedentistry&amp;endodontics]</td>\n",
       "      <td>6</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Nagawara, Bangalore</td>\n",
       "      <td>Dentist</td>\n",
       "      <td>Ceramic Veneers / Crowns Cosmetic/ Aesthetic D...</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Nagawara</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>[mbbs, md-dermatology]</td>\n",
       "      <td>32</td>\n",
       "      <td>90.0</td>\n",
       "      <td>Basavanagudi, Bangalore</td>\n",
       "      <td>Dermatologists</td>\n",
       "      <td>90% 3 Feedback Basavanagudi, Bangalore</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Basavanagudi</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>[bhms, diplomaincosmetology, diplomaindietandn...</td>\n",
       "      <td>11</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Dadar, Mumbai</td>\n",
       "      <td>Homeopath</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Mumbai</td>\n",
       "      <td>Dadar</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>[bds]</td>\n",
       "      <td>3</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Kattakada, Thiruvananthapuram</td>\n",
       "      <td>Dentist</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Thiruvananthapuram</td>\n",
       "      <td>Kattakada</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>[mbbs, md-dermatology]</td>\n",
       "      <td>8</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Villivakkam, Chennai</td>\n",
       "      <td>Dermatologists</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>Villivakkam</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>[mbbs, pgdiplomainclinicalcosmetology(pgdcc)]</td>\n",
       "      <td>13</td>\n",
       "      <td>100.0</td>\n",
       "      <td>Begumpet, Hyderabad</td>\n",
       "      <td>General Medicine</td>\n",
       "      <td>100% 10 Feedback Begumpet, Hyderabad</td>\n",
       "      <td>Hyderabad</td>\n",
       "      <td>Begumpet</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>[mbbs]</td>\n",
       "      <td>43</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Kottivakkam, Chennai</td>\n",
       "      <td>General Medicine</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>Kottivakkam</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>[diplomainotorhinolaryngology(dlo), mbbs]</td>\n",
       "      <td>27</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Jeedimetla, Hyderabad</td>\n",
       "      <td>ENT Specialist</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Hyderabad</td>\n",
       "      <td>Jeedimetla</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>[bds, mds-periodontics]</td>\n",
       "      <td>22</td>\n",
       "      <td>100.0</td>\n",
       "      <td>Gachibowli, Hyderabad</td>\n",
       "      <td>Dentist</td>\n",
       "      <td>Crowns and Bridges Fixing Teeth Whitening Gum ...</td>\n",
       "      <td>Hyderabad</td>\n",
       "      <td>Gachibowli</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>[bds, mds-oralpathology]</td>\n",
       "      <td>8</td>\n",
       "      <td>96.0</td>\n",
       "      <td>Chromepet, Chennai</td>\n",
       "      <td>Dentist</td>\n",
       "      <td>Artificial Teeth Conservative Dentistry Crowns...</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>Chromepet</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>[mbbs, md-generalmedicine]</td>\n",
       "      <td>25</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Mulund West, Mumbai</td>\n",
       "      <td>General Medicine</td>\n",
       "      <td>Balance Exercises Acne / Pimples Treatment Ins...</td>\n",
       "      <td>Mumbai</td>\n",
       "      <td>Mulund West</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>[mbbs, ms-ent]</td>\n",
       "      <td>4</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Bellandur, Bangalore</td>\n",
       "      <td>ENT Specialist</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Bellandur</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</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",
       "      <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",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1957</th>\n",
       "      <td>[bds, md-acupuncture, pgdiplomainclinicalcosme...</td>\n",
       "      <td>8</td>\n",
       "      <td>100.0</td>\n",
       "      <td>KPHB, Hyderabad</td>\n",
       "      <td>Dentist</td>\n",
       "      <td>100% 12 Feedback KPHB, Hyderabad</td>\n",
       "      <td>Hyderabad</td>\n",
       "      <td>KPHB</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1958</th>\n",
       "      <td>[diplomainotorhinolaryngology(dlo), mbbs, ms-ent]</td>\n",
       "      <td>40</td>\n",
       "      <td>53.0</td>\n",
       "      <td>Millers Road, Bangalore</td>\n",
       "      <td>ENT Specialist</td>\n",
       "      <td>53% 12 Feedback Millers Road, Bangalore</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Millers Road</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1959</th>\n",
       "      <td>[mbbs, md-medicine]</td>\n",
       "      <td>43</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Vileparle West, Mumbai</td>\n",
       "      <td>General Medicine</td>\n",
       "      <td>Viral Fever Treatment Dengue Fever Treatment T...</td>\n",
       "      <td>Mumbai</td>\n",
       "      <td>Vileparle West</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1960</th>\n",
       "      <td>[bds, mds-orthodontics]</td>\n",
       "      <td>29</td>\n",
       "      <td>95.0</td>\n",
       "      <td>Punjagutta, Hyderabad</td>\n",
       "      <td>Dentist</td>\n",
       "      <td>Dental Implant Fixing Invisible/Clear Braces C...</td>\n",
       "      <td>Hyderabad</td>\n",
       "      <td>Punjagutta</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1961</th>\n",
       "      <td>[bhms]</td>\n",
       "      <td>2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Malleswaram, Bangalore</td>\n",
       "      <td>Homeopath</td>\n",
       "      <td>3 Feedback Malleswaram, Bangalore ₹500</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Malleswaram</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1962</th>\n",
       "      <td>[mbbs, pgdha]</td>\n",
       "      <td>12</td>\n",
       "      <td>100.0</td>\n",
       "      <td>Rohini, Delhi</td>\n",
       "      <td>General Medicine</td>\n",
       "      <td>100% 23 Feedback Rohini, Delhi</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Rohini</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1963</th>\n",
       "      <td>[bhms]</td>\n",
       "      <td>3</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Habsiguda, Hyderabad</td>\n",
       "      <td>Homeopath</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Hyderabad</td>\n",
       "      <td>Habsiguda</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1964</th>\n",
       "      <td>[bds, certificateoforalimplantology, mds-prost...</td>\n",
       "      <td>8</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Ramanathapuram, Coimbatore</td>\n",
       "      <td>Dentist</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Coimbatore</td>\n",
       "      <td>Ramanathapuram</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1965</th>\n",
       "      <td>[mbbs, mrcog(uk)]</td>\n",
       "      <td>35</td>\n",
       "      <td>88.0</td>\n",
       "      <td>Choolai, Chennai</td>\n",
       "      <td>General Medicine</td>\n",
       "      <td>88% 5 Feedback Choolai, Chennai</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>Choolai</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1966</th>\n",
       "      <td>[frcp-internalmedicine, mbbs, md-medicine, pos...</td>\n",
       "      <td>24</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Tambaram, Chennai</td>\n",
       "      <td>General Medicine</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>Tambaram</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1967</th>\n",
       "      <td>[mds-periodontics]</td>\n",
       "      <td>13</td>\n",
       "      <td>98.0</td>\n",
       "      <td>Yelahanka, Bangalore</td>\n",
       "      <td>Dentist</td>\n",
       "      <td>Gum Disease Treatment/ Surgery Dental Implant ...</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Yelahanka</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1968</th>\n",
       "      <td>[dnb-familymedicine, mbbs]</td>\n",
       "      <td>23</td>\n",
       "      <td>96.0</td>\n",
       "      <td>Indiranagar, Bangalore</td>\n",
       "      <td>General Medicine</td>\n",
       "      <td>96% 12 Feedback Indiranagar, Bangalore</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Indiranagar</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1969</th>\n",
       "      <td>[bams, md-ayurvedamedicine]</td>\n",
       "      <td>32</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Chembur, Mumbai</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Mumbai</td>\n",
       "      <td>Chembur</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1970</th>\n",
       "      <td>[mds-prosthodontistandcrownbridge]</td>\n",
       "      <td>7</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Sundarapuram, Coimbatore</td>\n",
       "      <td>Dentist</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Coimbatore</td>\n",
       "      <td>Sundarapuram</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1971</th>\n",
       "      <td>[mbbs, ms-ent]</td>\n",
       "      <td>26</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Okhla, Delhi</td>\n",
       "      <td>ENT Specialist</td>\n",
       "      <td>Endoscopic DCR Sleep related disorders such as...</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Okhla</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1972</th>\n",
       "      <td>[diplomaindermatology, mbbs]</td>\n",
       "      <td>15</td>\n",
       "      <td>93.0</td>\n",
       "      <td>Moti Nagar, Hyderabad</td>\n",
       "      <td>Dermatologists</td>\n",
       "      <td>93% 36 Feedback Moti Nagar, Hyderabad</td>\n",
       "      <td>Hyderabad</td>\n",
       "      <td>Moti Nagar</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1973</th>\n",
       "      <td>[ddv, mbbs]</td>\n",
       "      <td>4</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Velachery, Chennai</td>\n",
       "      <td>Dermatologists</td>\n",
       "      <td>Skin Allergy Treatment Skin Allergies Dermabra...</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>Velachery</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1974</th>\n",
       "      <td>[diplomainotorhinolaryngology(dlo), mbbs]</td>\n",
       "      <td>19</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Munirka, Delhi</td>\n",
       "      <td>ENT Specialist</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Munirka</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1975</th>\n",
       "      <td>[mbbs]</td>\n",
       "      <td>26</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Panchsheel Park, Delhi</td>\n",
       "      <td>General Medicine</td>\n",
       "      <td>foot and ankle problems 1 Feedback Panchsheel ...</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Panchsheel Park</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1976</th>\n",
       "      <td>[mbbs, ms-otorhinolaryngology]</td>\n",
       "      <td>11</td>\n",
       "      <td>84.0</td>\n",
       "      <td>Miyapur, Hyderabad</td>\n",
       "      <td>ENT Specialist</td>\n",
       "      <td>84% 20 Feedback Miyapur, Hyderabad</td>\n",
       "      <td>Hyderabad</td>\n",
       "      <td>Miyapur</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1977</th>\n",
       "      <td>[fais, fiages, mbbs, ms-generalsurgery]</td>\n",
       "      <td>28</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Panchsheel Park, Delhi</td>\n",
       "      <td>General Medicine</td>\n",
       "      <td>Panchsheel Park, Delhi ₹1,000 Available Tomorrow</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Panchsheel Park</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1978</th>\n",
       "      <td>[bds, mds-endodontics]</td>\n",
       "      <td>15</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Prabhadevi, Mumbai</td>\n",
       "      <td>Dentist</td>\n",
       "      <td>Prabhadevi, Mumbai ₹1,000 Visits On-Call</td>\n",
       "      <td>Mumbai</td>\n",
       "      <td>Prabhadevi</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1979</th>\n",
       "      <td>[bds, mds-oral&amp;maxillofacialsurgery]</td>\n",
       "      <td>17</td>\n",
       "      <td>100.0</td>\n",
       "      <td>Powai, Mumbai</td>\n",
       "      <td>Dentist</td>\n",
       "      <td>General Dentistry Dental Fillings RCT - Single...</td>\n",
       "      <td>Mumbai</td>\n",
       "      <td>Powai</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1980</th>\n",
       "      <td>[bds, mds-pedodontics]</td>\n",
       "      <td>18</td>\n",
       "      <td>98.0</td>\n",
       "      <td>Velachery, Chennai</td>\n",
       "      <td>Dentist</td>\n",
       "      <td>98% 240 Feedback Velachery, Chennai</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>Velachery</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1981</th>\n",
       "      <td>[dnb-dermatology, mbbs, md-dermatology, venere...</td>\n",
       "      <td>8</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Lajpat Nagar III, Delhi</td>\n",
       "      <td>Dermatologists</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Delhi</td>\n",
       "      <td>Lajpat Nagar III</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1982</th>\n",
       "      <td>[bams, doctorofmedicine]</td>\n",
       "      <td>10</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Basavanagudi, Bangalore</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Basavanagudi</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1983</th>\n",
       "      <td>[mbbs, md-dermatology, venereology&amp;leprosy]</td>\n",
       "      <td>4</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Choolai, Chennai</td>\n",
       "      <td>Dermatologists</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>Choolai</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1984</th>\n",
       "      <td>[mbbs, md/ms-obstetrics&amp;gynaecology]</td>\n",
       "      <td>9</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Porur, Chennai</td>\n",
       "      <td>General Medicine</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>Porur</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1985</th>\n",
       "      <td>[bds]</td>\n",
       "      <td>12</td>\n",
       "      <td>98.0</td>\n",
       "      <td>Arekere, Bangalore</td>\n",
       "      <td>Dentist</td>\n",
       "      <td>RCT - Root Canal Treatment Root Canal Treatmen...</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Arekere</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1986</th>\n",
       "      <td>[mbbs, md-dermatology, venereology&amp;leprosy]</td>\n",
       "      <td>8</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Pallikaranai, Chennai</td>\n",
       "      <td>Dermatologists</td>\n",
       "      <td>1 Feedback Pallikaranai, Chennai ₹500</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>Pallikaranai</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1987 rows × 39 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                          Qualification  Experience  Rating  \\\n",
       "0                                                [mbbs]          35     0.0   \n",
       "1             [diplomainotorhinolaryngology(dlo), mbbs]          31     0.0   \n",
       "2                                          [ddvl, mbbs]          40    70.0   \n",
       "3                                                [bams]           0     0.0   \n",
       "4          [bds, mds-conservativedentistry&endodontics]          16   100.0   \n",
       "5                                            [bds, mds]          14    90.0   \n",
       "6             [diplomainotorhinolaryngology(dlo), mbbs]          23    94.0   \n",
       "7                                [bds, mds-pedodontics]           9    94.0   \n",
       "8     [bams, m.d.inkayachikista, md-ayurvedamedicine...          11    99.0   \n",
       "9                                                [bhms]          44     0.0   \n",
       "10                                                [bds]           4   100.0   \n",
       "11                              [fcd-diabetology, mbbs]          34     0.0   \n",
       "12                                          [ddv, mbbs]          11    98.0   \n",
       "13                               [mbbs, md-dermatology]          13    99.0   \n",
       "14                                             [ms-ent]           4     0.0   \n",
       "15                                                [bds]           4     0.0   \n",
       "16                               [mbbs, md-dermatology]          16    87.0   \n",
       "17    [diplomainotorhinolaryngology(dlo), dnb-ent, m...          28    64.0   \n",
       "18         [bds, mds-conservativedentistry&endodontics]           6     0.0   \n",
       "19                               [mbbs, md-dermatology]          32    90.0   \n",
       "20    [bhms, diplomaincosmetology, diplomaindietandn...          11     0.0   \n",
       "21                                                [bds]           3     0.0   \n",
       "22                               [mbbs, md-dermatology]           8     0.0   \n",
       "23        [mbbs, pgdiplomainclinicalcosmetology(pgdcc)]          13   100.0   \n",
       "24                                               [mbbs]          43     0.0   \n",
       "25            [diplomainotorhinolaryngology(dlo), mbbs]          27     0.0   \n",
       "26                              [bds, mds-periodontics]          22   100.0   \n",
       "27                             [bds, mds-oralpathology]           8    96.0   \n",
       "28                           [mbbs, md-generalmedicine]          25     0.0   \n",
       "29                                       [mbbs, ms-ent]           4     0.0   \n",
       "...                                                 ...         ...     ...   \n",
       "1957  [bds, md-acupuncture, pgdiplomainclinicalcosme...           8   100.0   \n",
       "1958  [diplomainotorhinolaryngology(dlo), mbbs, ms-ent]          40    53.0   \n",
       "1959                                [mbbs, md-medicine]          43     0.0   \n",
       "1960                            [bds, mds-orthodontics]          29    95.0   \n",
       "1961                                             [bhms]           2     0.0   \n",
       "1962                                      [mbbs, pgdha]          12   100.0   \n",
       "1963                                             [bhms]           3     0.0   \n",
       "1964  [bds, certificateoforalimplantology, mds-prost...           8     0.0   \n",
       "1965                                  [mbbs, mrcog(uk)]          35    88.0   \n",
       "1966  [frcp-internalmedicine, mbbs, md-medicine, pos...          24     0.0   \n",
       "1967                                 [mds-periodontics]          13    98.0   \n",
       "1968                         [dnb-familymedicine, mbbs]          23    96.0   \n",
       "1969                        [bams, md-ayurvedamedicine]          32     0.0   \n",
       "1970                 [mds-prosthodontistandcrownbridge]           7     0.0   \n",
       "1971                                     [mbbs, ms-ent]          26     0.0   \n",
       "1972                       [diplomaindermatology, mbbs]          15    93.0   \n",
       "1973                                        [ddv, mbbs]           4     0.0   \n",
       "1974          [diplomainotorhinolaryngology(dlo), mbbs]          19     0.0   \n",
       "1975                                             [mbbs]          26     0.0   \n",
       "1976                     [mbbs, ms-otorhinolaryngology]          11    84.0   \n",
       "1977            [fais, fiages, mbbs, ms-generalsurgery]          28     0.0   \n",
       "1978                             [bds, mds-endodontics]          15     0.0   \n",
       "1979               [bds, mds-oral&maxillofacialsurgery]          17   100.0   \n",
       "1980                             [bds, mds-pedodontics]          18    98.0   \n",
       "1981  [dnb-dermatology, mbbs, md-dermatology, venere...           8     0.0   \n",
       "1982                           [bams, doctorofmedicine]          10     0.0   \n",
       "1983        [mbbs, md-dermatology, venereology&leprosy]           4     0.0   \n",
       "1984               [mbbs, md/ms-obstetrics&gynaecology]           9     0.0   \n",
       "1985                                              [bds]          12    98.0   \n",
       "1986        [mbbs, md-dermatology, venereology&leprosy]           8     0.0   \n",
       "\n",
       "                                  Place           Profile  \\\n",
       "0                Ghatkopar East, Mumbai  General Medicine   \n",
       "1           West Marredpally, Hyderabad    ENT Specialist   \n",
       "2                     KK Nagar, Chennai    Dermatologists   \n",
       "3                New Ashok Nagar, Delhi          Ayurveda   \n",
       "4             Kanakpura Road, Bangalore           Dentist   \n",
       "5                    Velachery, Chennai           Dentist   \n",
       "6                Frazer Town, Bangalore    ENT Specialist   \n",
       "7                    Attapur, Hyderabad           Dentist   \n",
       "8               Banashankari, Bangalore          Ayurveda   \n",
       "9               Mayur Vihar Ph-I, Delhi         Homeopath   \n",
       "10                 Erragadda, Hyderabad           Dentist   \n",
       "11              Gandhipuram, Coimbatore  General Medicine   \n",
       "12                 Kemps Corner, Mumbai    Dermatologists   \n",
       "13             Banjara Hills, Hyderabad    Dermatologists   \n",
       "14                Madandapuram, Chennai    ENT Specialist   \n",
       "15               Mukherjee Nagar, Delhi           Dentist   \n",
       "16                    Tis Hazari, Delhi    Dermatologists   \n",
       "17    Banashankari 2nd Stage, Bangalore    ENT Specialist   \n",
       "18                  Nagawara, Bangalore           Dentist   \n",
       "19              Basavanagudi, Bangalore    Dermatologists   \n",
       "20                        Dadar, Mumbai         Homeopath   \n",
       "21        Kattakada, Thiruvananthapuram           Dentist   \n",
       "22                 Villivakkam, Chennai    Dermatologists   \n",
       "23                  Begumpet, Hyderabad  General Medicine   \n",
       "24                 Kottivakkam, Chennai  General Medicine   \n",
       "25                Jeedimetla, Hyderabad    ENT Specialist   \n",
       "26                Gachibowli, Hyderabad           Dentist   \n",
       "27                   Chromepet, Chennai           Dentist   \n",
       "28                  Mulund West, Mumbai  General Medicine   \n",
       "29                 Bellandur, Bangalore    ENT Specialist   \n",
       "...                                 ...               ...   \n",
       "1957                    KPHB, Hyderabad           Dentist   \n",
       "1958            Millers Road, Bangalore    ENT Specialist   \n",
       "1959             Vileparle West, Mumbai  General Medicine   \n",
       "1960              Punjagutta, Hyderabad           Dentist   \n",
       "1961             Malleswaram, Bangalore         Homeopath   \n",
       "1962                      Rohini, Delhi  General Medicine   \n",
       "1963               Habsiguda, Hyderabad         Homeopath   \n",
       "1964         Ramanathapuram, Coimbatore           Dentist   \n",
       "1965                   Choolai, Chennai  General Medicine   \n",
       "1966                  Tambaram, Chennai  General Medicine   \n",
       "1967               Yelahanka, Bangalore           Dentist   \n",
       "1968             Indiranagar, Bangalore  General Medicine   \n",
       "1969                    Chembur, Mumbai          Ayurveda   \n",
       "1970           Sundarapuram, Coimbatore           Dentist   \n",
       "1971                       Okhla, Delhi    ENT Specialist   \n",
       "1972              Moti Nagar, Hyderabad    Dermatologists   \n",
       "1973                 Velachery, Chennai    Dermatologists   \n",
       "1974                     Munirka, Delhi    ENT Specialist   \n",
       "1975             Panchsheel Park, Delhi  General Medicine   \n",
       "1976                 Miyapur, Hyderabad    ENT Specialist   \n",
       "1977             Panchsheel Park, Delhi  General Medicine   \n",
       "1978                 Prabhadevi, Mumbai           Dentist   \n",
       "1979                      Powai, Mumbai           Dentist   \n",
       "1980                 Velachery, Chennai           Dentist   \n",
       "1981            Lajpat Nagar III, Delhi    Dermatologists   \n",
       "1982            Basavanagudi, Bangalore          Ayurveda   \n",
       "1983                   Choolai, Chennai    Dermatologists   \n",
       "1984                     Porur, Chennai  General Medicine   \n",
       "1985                 Arekere, Bangalore           Dentist   \n",
       "1986              Pallikaranai, Chennai    Dermatologists   \n",
       "\n",
       "                                     Miscellaneous_Info                City  \\\n",
       "0                                                   NaN              Mumbai   \n",
       "1                                                   NaN           Hyderabad   \n",
       "2                      70% 4 Feedback KK Nagar, Chennai             Chennai   \n",
       "3                                                   NaN               Delhi   \n",
       "4     General Dentistry Conservative Dentistry Cosme...           Bangalore   \n",
       "5     Acrylic Partial Denture Impaction / Impacted T...             Chennai   \n",
       "6                 94% 6 Feedback Frazer Town, Bangalore           Bangalore   \n",
       "7     RCT - Root Canal Treatment Ceramic Veneers / C...           Hyderabad   \n",
       "8              99% 203 Feedback Banashankari, Bangalore           Bangalore   \n",
       "9                                                   NaN               Delhi   \n",
       "10    Dental Fillings Zirconia Crowns RCT - Single S...           Hyderabad   \n",
       "11                                                  NaN          Coimbatore   \n",
       "12                 98% 28 Feedback Kemps Corner, Mumbai              Mumbai   \n",
       "13    Laser Hair Removal - Face Skin Tag Treatment H...           Hyderabad   \n",
       "14                                                  NaN             Chennai   \n",
       "15             Mukherjee Nagar, Delhi ₹250 Visits Today               Delhi   \n",
       "16                     87% 9 Feedback Tis Hazari, Delhi               Delhi   \n",
       "17     64% 4 Feedback Banashankari 2nd Stage, Bangalore           Bangalore   \n",
       "18    Ceramic Veneers / Crowns Cosmetic/ Aesthetic D...           Bangalore   \n",
       "19               90% 3 Feedback Basavanagudi, Bangalore           Bangalore   \n",
       "20                                                  NaN              Mumbai   \n",
       "21                                                  NaN  Thiruvananthapuram   \n",
       "22                                                  NaN             Chennai   \n",
       "23                 100% 10 Feedback Begumpet, Hyderabad           Hyderabad   \n",
       "24                                                  NaN             Chennai   \n",
       "25                                                  NaN           Hyderabad   \n",
       "26    Crowns and Bridges Fixing Teeth Whitening Gum ...           Hyderabad   \n",
       "27    Artificial Teeth Conservative Dentistry Crowns...             Chennai   \n",
       "28    Balance Exercises Acne / Pimples Treatment Ins...              Mumbai   \n",
       "29                                                  NaN           Bangalore   \n",
       "...                                                 ...                 ...   \n",
       "1957                   100% 12 Feedback KPHB, Hyderabad           Hyderabad   \n",
       "1958            53% 12 Feedback Millers Road, Bangalore           Bangalore   \n",
       "1959  Viral Fever Treatment Dengue Fever Treatment T...              Mumbai   \n",
       "1960  Dental Implant Fixing Invisible/Clear Braces C...           Hyderabad   \n",
       "1961             3 Feedback Malleswaram, Bangalore ₹500           Bangalore   \n",
       "1962                     100% 23 Feedback Rohini, Delhi               Delhi   \n",
       "1963                                                NaN           Hyderabad   \n",
       "1964                                                NaN          Coimbatore   \n",
       "1965                    88% 5 Feedback Choolai, Chennai             Chennai   \n",
       "1966                                                NaN             Chennai   \n",
       "1967  Gum Disease Treatment/ Surgery Dental Implant ...           Bangalore   \n",
       "1968             96% 12 Feedback Indiranagar, Bangalore           Bangalore   \n",
       "1969                                                NaN              Mumbai   \n",
       "1970                                                NaN          Coimbatore   \n",
       "1971  Endoscopic DCR Sleep related disorders such as...               Delhi   \n",
       "1972              93% 36 Feedback Moti Nagar, Hyderabad           Hyderabad   \n",
       "1973  Skin Allergy Treatment Skin Allergies Dermabra...             Chennai   \n",
       "1974                                                NaN               Delhi   \n",
       "1975  foot and ankle problems 1 Feedback Panchsheel ...               Delhi   \n",
       "1976                 84% 20 Feedback Miyapur, Hyderabad           Hyderabad   \n",
       "1977   Panchsheel Park, Delhi ₹1,000 Available Tomorrow               Delhi   \n",
       "1978           Prabhadevi, Mumbai ₹1,000 Visits On-Call              Mumbai   \n",
       "1979  General Dentistry Dental Fillings RCT - Single...              Mumbai   \n",
       "1980                98% 240 Feedback Velachery, Chennai             Chennai   \n",
       "1981                                                NaN               Delhi   \n",
       "1982                                                NaN           Bangalore   \n",
       "1983                                                NaN             Chennai   \n",
       "1984                                                NaN             Chennai   \n",
       "1985  RCT - Root Canal Treatment Root Canal Treatmen...           Bangalore   \n",
       "1986              1 Feedback Pallikaranai, Chennai ₹500             Chennai   \n",
       "\n",
       "                        Area  Profile_Ayurveda  Profile_Dentist  ...  Qual_8  \\\n",
       "0             Ghatkopar East                 0                0  ...     NaN   \n",
       "1           West Marredpally                 0                0  ...     NaN   \n",
       "2                   KK Nagar                 0                0  ...     NaN   \n",
       "3            New Ashok Nagar                 1                0  ...     NaN   \n",
       "4             Kanakpura Road                 0                1  ...     NaN   \n",
       "5                  Velachery                 0                1  ...     NaN   \n",
       "6                Frazer Town                 0                0  ...     NaN   \n",
       "7                    Attapur                 0                1  ...     NaN   \n",
       "8               Banashankari                 1                0  ...     NaN   \n",
       "9           Mayur Vihar Ph-I                 0                0  ...     NaN   \n",
       "10                 Erragadda                 0                1  ...     NaN   \n",
       "11               Gandhipuram                 0                0  ...     NaN   \n",
       "12              Kemps Corner                 0                0  ...     NaN   \n",
       "13             Banjara Hills                 0                0  ...     NaN   \n",
       "14              Madandapuram                 0                0  ...     NaN   \n",
       "15           Mukherjee Nagar                 0                1  ...     NaN   \n",
       "16                Tis Hazari                 0                0  ...     NaN   \n",
       "17    Banashankari 2nd Stage                 0                0  ...     NaN   \n",
       "18                  Nagawara                 0                1  ...     NaN   \n",
       "19              Basavanagudi                 0                0  ...     NaN   \n",
       "20                     Dadar                 0                0  ...     NaN   \n",
       "21                 Kattakada                 0                1  ...     NaN   \n",
       "22               Villivakkam                 0                0  ...     NaN   \n",
       "23                  Begumpet                 0                0  ...     NaN   \n",
       "24               Kottivakkam                 0                0  ...     NaN   \n",
       "25                Jeedimetla                 0                0  ...     NaN   \n",
       "26                Gachibowli                 0                1  ...     NaN   \n",
       "27                 Chromepet                 0                1  ...     NaN   \n",
       "28               Mulund West                 0                0  ...     NaN   \n",
       "29                 Bellandur                 0                0  ...     NaN   \n",
       "...                      ...               ...              ...  ...     ...   \n",
       "1957                    KPHB                 0                1  ...     NaN   \n",
       "1958            Millers Road                 0                0  ...     NaN   \n",
       "1959          Vileparle West                 0                0  ...     NaN   \n",
       "1960              Punjagutta                 0                1  ...     NaN   \n",
       "1961             Malleswaram                 0                0  ...     NaN   \n",
       "1962                  Rohini                 0                0  ...     NaN   \n",
       "1963               Habsiguda                 0                0  ...     NaN   \n",
       "1964          Ramanathapuram                 0                1  ...     NaN   \n",
       "1965                 Choolai                 0                0  ...     NaN   \n",
       "1966                Tambaram                 0                0  ...     NaN   \n",
       "1967               Yelahanka                 0                1  ...     NaN   \n",
       "1968             Indiranagar                 0                0  ...     NaN   \n",
       "1969                 Chembur                 1                0  ...     NaN   \n",
       "1970            Sundarapuram                 0                1  ...     NaN   \n",
       "1971                   Okhla                 0                0  ...     NaN   \n",
       "1972              Moti Nagar                 0                0  ...     NaN   \n",
       "1973               Velachery                 0                0  ...     NaN   \n",
       "1974                 Munirka                 0                0  ...     NaN   \n",
       "1975         Panchsheel Park                 0                0  ...     NaN   \n",
       "1976                 Miyapur                 0                0  ...     NaN   \n",
       "1977         Panchsheel Park                 0                0  ...     NaN   \n",
       "1978              Prabhadevi                 0                1  ...     NaN   \n",
       "1979                   Powai                 0                1  ...     NaN   \n",
       "1980               Velachery                 0                1  ...     NaN   \n",
       "1981        Lajpat Nagar III                 0                0  ...     NaN   \n",
       "1982            Basavanagudi                 1                0  ...     NaN   \n",
       "1983                 Choolai                 0                0  ...     NaN   \n",
       "1984                   Porur                 0                0  ...     NaN   \n",
       "1985                 Arekere                 0                1  ...     NaN   \n",
       "1986            Pallikaranai                 0                0  ...     NaN   \n",
       "\n",
       "      Qual_9  Qual_10  Qual_11  Qual_12  Qual_13  Qual_14  Qual_15  Qual_16  \\\n",
       "0        NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1        NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "2        NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "3        NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "4        NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "5        NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "6        NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "7        NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "8        NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "9        NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "10       NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "11       NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "12       NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "13       NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "14       NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "15       NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "16       NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "17       NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "18       NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "19       NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "20       NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "21       NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "22       NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "23       NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "24       NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "25       NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "26       NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "27       NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "28       NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "29       NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "...      ...      ...      ...      ...      ...      ...      ...      ...   \n",
       "1957     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1958     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1959     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1960     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1961     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1962     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1963     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1964     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1965     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1966     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1967     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1968     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1969     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1970     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1971     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1972     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1973     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1974     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1975     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1976     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1977     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1978     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1979     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1980     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1981     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1982     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1983     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1984     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1985     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "1986     NaN      NaN      NaN      NaN      NaN      NaN      NaN      NaN   \n",
       "\n",
       "      Qual_17  \n",
       "0         NaN  \n",
       "1         NaN  \n",
       "2         NaN  \n",
       "3         NaN  \n",
       "4         NaN  \n",
       "5         NaN  \n",
       "6         NaN  \n",
       "7         NaN  \n",
       "8         NaN  \n",
       "9         NaN  \n",
       "10        NaN  \n",
       "11        NaN  \n",
       "12        NaN  \n",
       "13        NaN  \n",
       "14        NaN  \n",
       "15        NaN  \n",
       "16        NaN  \n",
       "17        NaN  \n",
       "18        NaN  \n",
       "19        NaN  \n",
       "20        NaN  \n",
       "21        NaN  \n",
       "22        NaN  \n",
       "23        NaN  \n",
       "24        NaN  \n",
       "25        NaN  \n",
       "26        NaN  \n",
       "27        NaN  \n",
       "28        NaN  \n",
       "29        NaN  \n",
       "...       ...  \n",
       "1957      NaN  \n",
       "1958      NaN  \n",
       "1959      NaN  \n",
       "1960      NaN  \n",
       "1961      NaN  \n",
       "1962      NaN  \n",
       "1963      NaN  \n",
       "1964      NaN  \n",
       "1965      NaN  \n",
       "1966      NaN  \n",
       "1967      NaN  \n",
       "1968      NaN  \n",
       "1969      NaN  \n",
       "1970      NaN  \n",
       "1971      NaN  \n",
       "1972      NaN  \n",
       "1973      NaN  \n",
       "1974      NaN  \n",
       "1975      NaN  \n",
       "1976      NaN  \n",
       "1977      NaN  \n",
       "1978      NaN  \n",
       "1979      NaN  \n",
       "1980      NaN  \n",
       "1981      NaN  \n",
       "1982      NaN  \n",
       "1983      NaN  \n",
       "1984      NaN  \n",
       "1985      NaN  \n",
       "1986      NaN  \n",
       "\n",
       "[1987 rows x 39 columns]"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_quals = []\n",
    "for j in range(stat_test.max()):\n",
    "    col_name = 'Qual_' + str(j+1)\n",
    "    test_quals.append(col_name)\n",
    "    col_j = df_test['Qualification'].str[j]\n",
    "    df_test[col_name] = col_j\n",
    "#     df_test[col_name] = df_test[col_name].fillna('Empty')\n",
    "    \n",
    "df_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "for i in train_quals:\n",
    "    df_train.replace({i: conversion_dict}, inplace=True)\n",
    "    df_train[i] = df_train[i].fillna(-1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "for i in test_quals:\n",
    "    df_test.replace({i: conversion_dict}, inplace=True)\n",
    "    df_test[i] = df_test[i].fillna(-1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "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>Qualification</th>\n",
       "      <th>Experience</th>\n",
       "      <th>Rating</th>\n",
       "      <th>Place</th>\n",
       "      <th>Profile</th>\n",
       "      <th>Miscellaneous_Info</th>\n",
       "      <th>Fees</th>\n",
       "      <th>City</th>\n",
       "      <th>Area</th>\n",
       "      <th>Profile_Ayurveda</th>\n",
       "      <th>...</th>\n",
       "      <th>Qual_1</th>\n",
       "      <th>Qual_2</th>\n",
       "      <th>Qual_3</th>\n",
       "      <th>Qual_4</th>\n",
       "      <th>Qual_5</th>\n",
       "      <th>Qual_6</th>\n",
       "      <th>Qual_7</th>\n",
       "      <th>Qual_8</th>\n",
       "      <th>Qual_9</th>\n",
       "      <th>Qual_10</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>[bhms, md-homeopathy]</td>\n",
       "      <td>24</td>\n",
       "      <td>100.0</td>\n",
       "      <td>Kakkanad, Ernakulam</td>\n",
       "      <td>Homeopath</td>\n",
       "      <td>100% 16 Feedback Kakkanad, Ernakulam</td>\n",
       "      <td>100</td>\n",
       "      <td>Ernakulam</td>\n",
       "      <td>Kakkanad</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>33</td>\n",
       "      <td>623</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>[bams, md-ayurvedamedicine]</td>\n",
       "      <td>12</td>\n",
       "      <td>98.0</td>\n",
       "      <td>Whitefield, Bangalore</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>98% 76 Feedback Whitefield, Bangalore</td>\n",
       "      <td>350</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Whitefield</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>28</td>\n",
       "      <td>605</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>[mbbs, ms-otorhinolaryngology]</td>\n",
       "      <td>9</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Mathikere - BEL, Bangalore</td>\n",
       "      <td>ENT Specialist</td>\n",
       "      <td>NaN</td>\n",
       "      <td>300</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Mathikere - BEL</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>579</td>\n",
       "      <td>739</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>[bams, bsc-zoology]</td>\n",
       "      <td>12</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Bannerghatta Road, Bangalore</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>Bannerghatta Road, Bangalore ₹250 Available on...</td>\n",
       "      <td>250</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>Bannerghatta Road</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>28</td>\n",
       "      <td>40</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>[bams]</td>\n",
       "      <td>20</td>\n",
       "      <td>100.0</td>\n",
       "      <td>Keelkattalai, Chennai</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>100% 4 Feedback Keelkattalai, Chennai</td>\n",
       "      <td>250</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>Keelkattalai</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>28</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 33 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                    Qualification  Experience  Rating  \\\n",
       "0           [bhms, md-homeopathy]          24   100.0   \n",
       "1     [bams, md-ayurvedamedicine]          12    98.0   \n",
       "2  [mbbs, ms-otorhinolaryngology]           9     0.0   \n",
       "3             [bams, bsc-zoology]          12     0.0   \n",
       "4                          [bams]          20   100.0   \n",
       "\n",
       "                          Place         Profile  \\\n",
       "0           Kakkanad, Ernakulam       Homeopath   \n",
       "1         Whitefield, Bangalore        Ayurveda   \n",
       "2    Mathikere - BEL, Bangalore  ENT Specialist   \n",
       "3  Bannerghatta Road, Bangalore        Ayurveda   \n",
       "4         Keelkattalai, Chennai        Ayurveda   \n",
       "\n",
       "                                  Miscellaneous_Info  Fees       City  \\\n",
       "0               100% 16 Feedback Kakkanad, Ernakulam   100  Ernakulam   \n",
       "1              98% 76 Feedback Whitefield, Bangalore   350  Bangalore   \n",
       "2                                                NaN   300  Bangalore   \n",
       "3  Bannerghatta Road, Bangalore ₹250 Available on...   250  Bangalore   \n",
       "4              100% 4 Feedback Keelkattalai, Chennai   250    Chennai   \n",
       "\n",
       "                Area  Profile_Ayurveda  ...  Qual_1  Qual_2  Qual_3  Qual_4  \\\n",
       "0           Kakkanad                 0  ...      33     623      -1      -1   \n",
       "1         Whitefield                 1  ...      28     605      -1      -1   \n",
       "2    Mathikere - BEL                 0  ...     579     739      -1      -1   \n",
       "3  Bannerghatta Road                 1  ...      28      40      -1      -1   \n",
       "4       Keelkattalai                 1  ...      28      -1      -1      -1   \n",
       "\n",
       "   Qual_5  Qual_6  Qual_7  Qual_8  Qual_9  Qual_10  \n",
       "0      -1      -1      -1      -1      -1       -1  \n",
       "1      -1      -1      -1      -1      -1       -1  \n",
       "2      -1      -1      -1      -1      -1       -1  \n",
       "3      -1      -1      -1      -1      -1       -1  \n",
       "4      -1      -1      -1      -1      -1       -1  \n",
       "\n",
       "[5 rows x 33 columns]"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Kakkanad', 'Whitefield', 'Mathikere - BEL', 'Bannerghatta Road',\n",
       "       'Keelkattalai', 'Porur', 'Karol Bagh', 'Arekere', 'Old City',\n",
       "       'Athani'], dtype=object)"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train['Area'].unique()[:10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "590"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(df_test['Area'].unique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "area_list = []\n",
    "set1 = set(df_train['Area'].unique())\n",
    "set2 = set(df_test['Area'].unique())\n",
    "temp = list(set1.union(set2))\n",
    "temp = temp[1:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "area_df = pd.DataFrame(temp, columns = ['Area'])\n",
    "area_df['Codes'] = area_df['Area'].astype('category').cat.codes\n",
    "# scaler = StandardScaler()\n",
    "# area_df['Codes'] = scaler.fit_transform(area_df['Codes'].values.reshape(-1,1))\n",
    "area_codes_dict = dict(zip(area_df['Area'], area_df['Codes']))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_train.replace({'Area': area_codes_dict}, inplace=True)\n",
    "df_test.replace({'Area': area_codes_dict}, inplace=True)\n",
    "\n",
    "df_train['Area'] = df_train['Area'].fillna(-1)\n",
    "df_test['Area'] = df_test['Area'].fillna(-1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "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>Qualification</th>\n",
       "      <th>Experience</th>\n",
       "      <th>Rating</th>\n",
       "      <th>Place</th>\n",
       "      <th>Profile</th>\n",
       "      <th>Miscellaneous_Info</th>\n",
       "      <th>Fees</th>\n",
       "      <th>City</th>\n",
       "      <th>Area</th>\n",
       "      <th>Profile_Ayurveda</th>\n",
       "      <th>...</th>\n",
       "      <th>Qual_1</th>\n",
       "      <th>Qual_2</th>\n",
       "      <th>Qual_3</th>\n",
       "      <th>Qual_4</th>\n",
       "      <th>Qual_5</th>\n",
       "      <th>Qual_6</th>\n",
       "      <th>Qual_7</th>\n",
       "      <th>Qual_8</th>\n",
       "      <th>Qual_9</th>\n",
       "      <th>Qual_10</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>[bhms, md-homeopathy]</td>\n",
       "      <td>24</td>\n",
       "      <td>100.0</td>\n",
       "      <td>Kakkanad, Ernakulam</td>\n",
       "      <td>Homeopath</td>\n",
       "      <td>100% 16 Feedback Kakkanad, Ernakulam</td>\n",
       "      <td>100</td>\n",
       "      <td>Ernakulam</td>\n",
       "      <td>324.0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>33</td>\n",
       "      <td>623</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>[bams, md-ayurvedamedicine]</td>\n",
       "      <td>12</td>\n",
       "      <td>98.0</td>\n",
       "      <td>Whitefield, Bangalore</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>98% 76 Feedback Whitefield, Bangalore</td>\n",
       "      <td>350</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>925.0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>28</td>\n",
       "      <td>605</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>[mbbs, ms-otorhinolaryngology]</td>\n",
       "      <td>9</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Mathikere - BEL, Bangalore</td>\n",
       "      <td>ENT Specialist</td>\n",
       "      <td>NaN</td>\n",
       "      <td>300</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>494.0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>579</td>\n",
       "      <td>739</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>[bams, bsc-zoology]</td>\n",
       "      <td>12</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Bannerghatta Road, Bangalore</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>Bannerghatta Road, Bangalore ₹250 Available on...</td>\n",
       "      <td>250</td>\n",
       "      <td>Bangalore</td>\n",
       "      <td>74.0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>28</td>\n",
       "      <td>40</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>[bams]</td>\n",
       "      <td>20</td>\n",
       "      <td>100.0</td>\n",
       "      <td>Keelkattalai, Chennai</td>\n",
       "      <td>Ayurveda</td>\n",
       "      <td>100% 4 Feedback Keelkattalai, Chennai</td>\n",
       "      <td>250</td>\n",
       "      <td>Chennai</td>\n",
       "      <td>367.0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>28</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "      <td>-1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 33 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                    Qualification  Experience  Rating  \\\n",
       "0           [bhms, md-homeopathy]          24   100.0   \n",
       "1     [bams, md-ayurvedamedicine]          12    98.0   \n",
       "2  [mbbs, ms-otorhinolaryngology]           9     0.0   \n",
       "3             [bams, bsc-zoology]          12     0.0   \n",
       "4                          [bams]          20   100.0   \n",
       "\n",
       "                          Place         Profile  \\\n",
       "0           Kakkanad, Ernakulam       Homeopath   \n",
       "1         Whitefield, Bangalore        Ayurveda   \n",
       "2    Mathikere - BEL, Bangalore  ENT Specialist   \n",
       "3  Bannerghatta Road, Bangalore        Ayurveda   \n",
       "4         Keelkattalai, Chennai        Ayurveda   \n",
       "\n",
       "                                  Miscellaneous_Info  Fees       City   Area  \\\n",
       "0               100% 16 Feedback Kakkanad, Ernakulam   100  Ernakulam  324.0   \n",
       "1              98% 76 Feedback Whitefield, Bangalore   350  Bangalore  925.0   \n",
       "2                                                NaN   300  Bangalore  494.0   \n",
       "3  Bannerghatta Road, Bangalore ₹250 Available on...   250  Bangalore   74.0   \n",
       "4              100% 4 Feedback Keelkattalai, Chennai   250    Chennai  367.0   \n",
       "\n",
       "   Profile_Ayurveda  ...  Qual_1  Qual_2  Qual_3  Qual_4  Qual_5  Qual_6  \\\n",
       "0                 0  ...      33     623      -1      -1      -1      -1   \n",
       "1                 1  ...      28     605      -1      -1      -1      -1   \n",
       "2                 0  ...     579     739      -1      -1      -1      -1   \n",
       "3                 1  ...      28      40      -1      -1      -1      -1   \n",
       "4                 1  ...      28      -1      -1      -1      -1      -1   \n",
       "\n",
       "   Qual_7  Qual_8  Qual_9  Qual_10  \n",
       "0      -1      -1      -1       -1  \n",
       "1      -1      -1      -1       -1  \n",
       "2      -1      -1      -1       -1  \n",
       "3      -1      -1      -1       -1  \n",
       "4      -1      -1      -1       -1  \n",
       "\n",
       "[5 rows x 33 columns]"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    16\n",
       "1    76\n",
       "2     0\n",
       "3     0\n",
       "4     4\n",
       "Name: Reviewers, dtype: int32"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train['Reviewers'] = df_train['Miscellaneous_Info'].str.split('% ').str[1].str.split(' ').str[0]\n",
    "df_train['Reviewers'] = df_train['Reviewers'].fillna(0)\n",
    "df_train['Rev_Len'] = df_train['Reviewers'].str.len()\n",
    "df_train.loc[df_train['Rev_Len']>3, 'Reviewers'] = 0\n",
    "df_train.loc[df_train['Reviewers']==',', 'Reviewers'] = 0\n",
    "df_train['Reviewers'] = df_train['Reviewers'].astype(int)\n",
    "# scaler = StandardScaler()\n",
    "# df_train['Reviewers'] = scaler.fit_transform(df_train['Reviewers'].values.reshape(-1,1))\n",
    "df_train['Reviewers'].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    0\n",
       "1    0\n",
       "2    4\n",
       "3    0\n",
       "4    0\n",
       "Name: Reviewers, dtype: int32"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_test['Reviewers'] = df_test['Miscellaneous_Info'].str.split('% ').str[1].str.split(' ').str[0]\n",
    "df_test['Reviewers'] = df_test['Reviewers'].fillna(0)\n",
    "df_test['Rev_Len'] = df_test['Reviewers'].str.len()\n",
    "df_test.loc[df_test['Rev_Len']>3, 'Reviewers'] = 0\n",
    "df_test.loc[df_test['Reviewers']==',', 'Reviewers'] = 0\n",
    "# df_test.loc[df_test['Reviewers']== None, 'Reviewers'] = 0\n",
    "df_test['Reviewers'] = df_test['Reviewers'].astype(int)\n",
    "# df_test['Reviewers'] = scaler.transform(df_test['Reviewers'].values.reshape(-1,1))\n",
    "df_test['Reviewers'].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [],
   "source": [
    "selected_cols = [i for i in df_train.columns if i not in ['Qualification', 'Place', 'Miscellaneous_Info', 'City', 'Fees', 'Profile', 'Rev_Len', 'Experience', 'Rating']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X = df_train[selected_cols]\n",
    "y = df_train['Fees']\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "# from sklearn.preprocessing import StandardScaler\n",
    "scaler = StandardScaler()\n",
    "X_train = scaler.fit_transform(X_train)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Using SVR "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### First splitting the training set and running a mock analysis on that and then training df_train and predicting from data of df_test "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.svm import SVR\n",
    "reg = SVR(gamma = 0.1)\n",
    "reg.fit(X_train,y_train)\n",
    "ans = reg.predict(scaler.transform(X_test))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "def score(y_pred,y):\n",
    "    y_pred = np.log(y_pred)\n",
    "    y = np.log(y)\n",
    "    return 1 - ((np.sum((y_pred-y)**2))/len(y))**1/2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7806934326272256"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "score(ans,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import make_scorer, mean_squared_error, r2_score\n",
    "scorer = make_scorer(score,greater_is_better=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import GridSearchCV\n",
    "\n",
    "parameters = {\"C\":[0.1,1,10],\"kernel\":[\"linear\",\"rbf\",\"poly\"]}\n",
    "reg2 = GridSearchCV(reg,param_grid=parameters,scoring=scorer, n_jobs=-1,cv=4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=4, error_score='raise-deprecating',\n",
       "             estimator=SVR(C=1.0, cache_size=200, coef0=0.0, degree=3,\n",
       "                           epsilon=0.1, gamma=0.1, kernel='rbf', max_iter=-1,\n",
       "                           shrinking=True, tol=0.001, verbose=False),\n",
       "             iid='warn', n_jobs=-1,\n",
       "             param_grid={'C': [0.1, 1, 10],\n",
       "                         'kernel': ['linear', 'rbf', 'poly']},\n",
       "             pre_dispatch='2*n_jobs', refit=True, return_train_score=False,\n",
       "             scoring=make_scorer(score), verbose=0)"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reg2.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [],
   "source": [
    "ans2 = reg2.predict(scaler.transform(X_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7974440980036446"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "score(ans2, y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Qualification', 'Experience', 'Rating', 'Place', 'Profile',\n",
       "       'Miscellaneous_Info', 'City', 'Area', 'Profile_Ayurveda',\n",
       "       'Profile_Dentist', 'Profile_Dermatologists', 'Profile_ENT Specialist',\n",
       "       'Profile_General Medicine', 'Profile_Homeopath', 'City_Bangalore',\n",
       "       'City_Chennai', 'City_Coimbatore', 'City_Delhi', 'City_Ernakulam',\n",
       "       'City_Hyderabad', 'City_Mumbai', 'City_Thiruvananthapuram', 'Qual_1',\n",
       "       'Qual_2', 'Qual_3', 'Qual_4', 'Qual_5', 'Qual_6', 'Qual_7', 'Qual_8',\n",
       "       'Qual_9', 'Qual_10', 'Qual_11', 'Qual_12', 'Qual_13', 'Qual_14',\n",
       "       'Qual_15', 'Qual_16', 'Qual_17', 'Reviewers', 'Rev_Len'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_test.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import GridSearchCV\n",
    "\n",
    "scaler = StandardScaler()\n",
    "X = scaler.fit_transform(df_train[selected_cols])\n",
    "y = df_train['Fees']\n",
    "X_test = scaler.transform(df_test[selected_cols])\n",
    "\n",
    "reg3 = SVR(gamma = 0.1)\n",
    "# reg3.fit(X_train,y_train)\n",
    "\n",
    "parameters = {\"C\":[0.1,1,10],\"kernel\":[\"linear\",\"rbf\",\"poly\"]}\n",
    "reg4 = GridSearchCV(reg3,param_grid=parameters,scoring='r2', n_jobs=-1,cv=4)\n",
    "reg4.fit(X,y)\n",
    "ans = reg4.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training data score 0.8083753797991509\n"
     ]
    }
   ],
   "source": [
    "ansX = reg4.predict(X)\n",
    "print(\"Training data score {}\".format(score(y, ansX)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Predicted fees with SVR"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([198.53460804, 282.04034274, 295.30976087, 263.15395655,\n",
       "       217.82807676, 200.4293666 , 366.12052028, 200.71236587,\n",
       "       285.44985127, 295.82539138])"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s = pd.Series(ans)\n",
    "s.values[:10]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Using KNN Regressor"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### First splitting the training set and running a mock analysis on that and then training df_train and predicting from data of df_test "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X = df_train[selected_cols]\n",
    "y = df_train['Fees']\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.2)\n",
    "\n",
    "poly = PolynomialFeatures(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [],
   "source": [
    "scaler = StandardScaler()\n",
    "X_train = scaler.fit_transform(X_train)\n",
    "X_train_2 = poly.fit_transform(X_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "KNeighborsRegressor(algorithm='auto', leaf_size=30, metric='minkowski',\n",
       "                    metric_params=None, n_jobs=None, n_neighbors=20, p=2,\n",
       "                    weights='uniform')"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "neigh = KNeighborsRegressor(n_neighbors=20)\n",
    "neigh.fit(X_train_2, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_test = scaler.transform(X_test)\n",
    "X_test_2 = poly.transform(X_test)\n",
    "ans = neigh.predict(X_test_2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7864151768622009"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "score(ans,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [],
   "source": [
    "# from sklearn.model_selection import GridSearchCV\n",
    "\n",
    "scaler = StandardScaler()\n",
    "X = scaler.fit_transform(df_train[selected_cols])\n",
    "y = df_train['Fees']\n",
    "X_test = scaler.transform(df_test[selected_cols])\n",
    "\n",
    "neigh = KNeighborsRegressor(n_neighbors=20)\n",
    "neigh.fit(X, y)\n",
    "\n",
    "ans = neigh.predict(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8097553069684934"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "score(ans,y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X = df_train[selected_cols]\n",
    "y = df_train['Fees']\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.2)\n",
    "\n",
    "poly = PolynomialFeatures(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [],
   "source": [
    "scaler = StandardScaler()\n",
    "X_train = scaler.fit_transform(X_train)\n",
    "X_train_2 = poly.fit_transform(X_train)\n",
    "\n",
    "X_test = scaler.transform(X_test)\n",
    "X_test_2 = scaler.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "KNeighborsRegressor(algorithm='auto', leaf_size=30, metric='minkowski',\n",
       "                    metric_params=None, n_jobs=None, n_neighbors=16, p=2,\n",
       "                    weights='uniform')"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "parameters = {'n_neighbors':np.arange(2,20)}\n",
    "\n",
    "neigh = KNeighborsRegressor()\n",
    "\n",
    "reg = GridSearchCV(neigh,param_grid=parameters,scoring=scorer, n_jobs=-1,cv=4)\n",
    "reg.fit(X,y)\n",
    "ans = reg.predict(X_test)\n",
    "reg.best_estimator_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.6917030328049012"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "score(ans,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=4, error_score='raise-deprecating',\n",
       "             estimator=KNeighborsRegressor(algorithm='auto', leaf_size=30,\n",
       "                                           metric='minkowski',\n",
       "                                           metric_params=None, n_jobs=None,\n",
       "                                           n_neighbors=5, p=2,\n",
       "                                           weights='uniform'),\n",
       "             iid='warn', n_jobs=-1,\n",
       "             param_grid={'n_neighbors': array([ 2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16, 17, 18,\n",
       "       19])},\n",
       "             pre_dispatch='2*n_jobs', refit=True, return_train_score=False,\n",
       "             scoring=make_scorer(score), verbose=0)"
      ]
     },
     "execution_count": 77,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "scaler = StandardScaler()\n",
    "poly = PolynomialFeatures(3)\n",
    "\n",
    "\n",
    "X = scaler.fit_transform(df_train[selected_cols])\n",
    "X_2 = poly.fit_transform(X)\n",
    "y = df_train['Fees']\n",
    "X_test = scaler.transform(df_test[selected_cols])\n",
    "X_test_2 = poly.transform(X_test)\n",
    "\n",
    "neigh = KNeighborsRegressor()\n",
    "parameters = {'n_neighbors':np.arange(2,20)}\n",
    "\n",
    "reg = GridSearchCV(neigh,param_grid=parameters,scoring=scorer, n_jobs=-1,cv=4)\n",
    "reg.fit(X_2,y)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Traing data score 0.810330433916746\n"
     ]
    }
   ],
   "source": [
    "ans = reg.predict(X_2)\n",
    "print(\"Traing data score {}\".format(score(ans,y)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Predicted fees with KNN Regressor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "metadata": {},
   "outputs": [],
   "source": [
    "ans = reg.predict(X_test_2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([217.22222222, 319.44444444, 344.44444444, 311.11111111,\n",
       "       244.44444444, 236.11111111, 363.88888889, 227.77777778,\n",
       "       358.33333333, 250.        ])"
      ]
     },
     "execution_count": 81,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s = pd.Series(ans)\n",
    "s.values[:10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}