Disease classification.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "# !pip install lazypredict"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[nltk_data] Downloading package stopwords to C:\\Users\\Prakhar\n",
      "[nltk_data]     Jadaun\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package stopwords is already up-to-date!\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "from string import digits\n",
    "import nltk\n",
    "from nltk.corpus import stopwords\n",
    "from nltk.stem import WordNetLemmatizer \n",
    "from sklearn.model_selection import train_test_split\n",
    "nltk.download('stopwords')\n",
    "import re\n",
    "from sklearn.naive_bayes import BernoulliNB\n",
    "import numpy as np\n",
    "from sklearn.metrics import accuracy_score\n",
    "from lazypredict.Supervised import LazyClassifier \n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "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>itching</th>\n",
       "      <th>skin_rash</th>\n",
       "      <th>nodal_skin_eruptions</th>\n",
       "      <th>continuous_sneezing</th>\n",
       "      <th>shivering</th>\n",
       "      <th>chills</th>\n",
       "      <th>joint_pain</th>\n",
       "      <th>stomach_pain</th>\n",
       "      <th>acidity</th>\n",
       "      <th>ulcers_on_tongue</th>\n",
       "      <th>...</th>\n",
       "      <th>scurring</th>\n",
       "      <th>skin_peeling</th>\n",
       "      <th>silver_like_dusting</th>\n",
       "      <th>small_dents_in_nails</th>\n",
       "      <th>inflammatory_nails</th>\n",
       "      <th>blister</th>\n",
       "      <th>red_sore_around_nose</th>\n",
       "      <th>yellow_crust_ooze</th>\n",
       "      <th>prognosis</th>\n",
       "      <th>Unnamed: 133</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1</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>...</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>0</td>\n",
       "      <td>Fungal infection</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>1</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>...</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>0</td>\n",
       "      <td>Fungal infection</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</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",
       "      <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>0</td>\n",
       "      <td>Fungal infection</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</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>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>0</td>\n",
       "      <td>Fungal infection</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>1</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>...</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>0</td>\n",
       "      <td>Fungal infection</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>4915</th>\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>0</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>0</td>\n",
       "      <td>(vertigo) Paroymsal  Positional Vertigo</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4916</th>\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",
       "      <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>Acne</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4917</th>\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>0</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>0</td>\n",
       "      <td>Urinary tract infection</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4918</th>\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",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>Psoriasis</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4919</th>\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",
       "      <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>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Impetigo</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4920 rows × 134 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      itching  skin_rash  nodal_skin_eruptions  continuous_sneezing  \\\n",
       "0           1          1                     1                    0   \n",
       "1           0          1                     1                    0   \n",
       "2           1          0                     1                    0   \n",
       "3           1          1                     0                    0   \n",
       "4           1          1                     1                    0   \n",
       "...       ...        ...                   ...                  ...   \n",
       "4915        0          0                     0                    0   \n",
       "4916        0          1                     0                    0   \n",
       "4917        0          0                     0                    0   \n",
       "4918        0          1                     0                    0   \n",
       "4919        0          1                     0                    0   \n",
       "\n",
       "      shivering  chills  joint_pain  stomach_pain  acidity  ulcers_on_tongue  \\\n",
       "0             0       0           0             0        0                 0   \n",
       "1             0       0           0             0        0                 0   \n",
       "2             0       0           0             0        0                 0   \n",
       "3             0       0           0             0        0                 0   \n",
       "4             0       0           0             0        0                 0   \n",
       "...         ...     ...         ...           ...      ...               ...   \n",
       "4915          0       0           0             0        0                 0   \n",
       "4916          0       0           0             0        0                 0   \n",
       "4917          0       0           0             0        0                 0   \n",
       "4918          0       0           1             0        0                 0   \n",
       "4919          0       0           0             0        0                 0   \n",
       "\n",
       "      ...  scurring  skin_peeling  silver_like_dusting  small_dents_in_nails  \\\n",
       "0     ...         0             0                    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",
       "4915  ...         0             0                    0                     0   \n",
       "4916  ...         1             0                    0                     0   \n",
       "4917  ...         0             0                    0                     0   \n",
       "4918  ...         0             1                    1                     1   \n",
       "4919  ...         0             0                    0                     0   \n",
       "\n",
       "      inflammatory_nails  blister  red_sore_around_nose  yellow_crust_ooze  \\\n",
       "0                      0        0                     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",
       "4915                   0        0                     0                  0   \n",
       "4916                   0        0                     0                  0   \n",
       "4917                   0        0                     0                  0   \n",
       "4918                   1        0                     0                  0   \n",
       "4919                   0        1                     1                  1   \n",
       "\n",
       "                                    prognosis  Unnamed: 133  \n",
       "0                            Fungal infection           NaN  \n",
       "1                            Fungal infection           NaN  \n",
       "2                            Fungal infection           NaN  \n",
       "3                            Fungal infection           NaN  \n",
       "4                            Fungal infection           NaN  \n",
       "...                                       ...           ...  \n",
       "4915  (vertigo) Paroymsal  Positional Vertigo           NaN  \n",
       "4916                                     Acne           NaN  \n",
       "4917                  Urinary tract infection           NaN  \n",
       "4918                                Psoriasis           NaN  \n",
       "4919                                 Impetigo           NaN  \n",
       "\n",
       "[4920 rows x 134 columns]"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "training_df = pd.read_csv('temp/imp/Training.csv')\n",
    "training_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "134"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(training_df.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Fungal infection', 'Allergy', 'GERD', 'Chronic cholestasis',\n",
       "       'Drug Reaction', 'Peptic ulcer diseae', 'AIDS', 'Diabetes ',\n",
       "       'Gastroenteritis', 'Bronchial Asthma', 'Hypertension ', 'Migraine',\n",
       "       'Cervical spondylosis', 'Paralysis (brain hemorrhage)', 'Jaundice',\n",
       "       'Malaria', 'Chicken pox', 'Dengue', 'Typhoid', 'hepatitis A',\n",
       "       'Hepatitis B', 'Hepatitis C', 'Hepatitis D', 'Hepatitis E',\n",
       "       'Alcoholic hepatitis', 'Tuberculosis', 'Common Cold', 'Pneumonia',\n",
       "       'Dimorphic hemmorhoids(piles)', 'Heart attack', 'Varicose veins',\n",
       "       'Hypothyroidism', 'Hyperthyroidism', 'Hypoglycemia',\n",
       "       'Osteoarthristis', 'Arthritis',\n",
       "       '(vertigo) Paroymsal  Positional Vertigo', 'Acne',\n",
       "       'Urinary tract infection', 'Psoriasis', 'Impetigo'], dtype=object)"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "training_df['prognosis'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 400x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(4,4))\n",
    "sns.heatmap(training_df.isna(),cmap='rainbow',yticklabels=False)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [],
   "source": [
    "testing_df = pd.read_csv('temp/imp/Testing.csv')\n",
    "# testing_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 400x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(4,4))\n",
    "sns.heatmap(testing_df.isna(),cmap='rainbow',yticklabels=False)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [],
   "source": [
    "# df = pd.concat([training_df,testing_df],axis=0)\n",
    "# df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [],
   "source": [
    "# df.reset_index(inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [],
   "source": [
    "# df.drop(columns=['index'],inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [],
   "source": [
    "# X = df.drop(columns=['prognosis'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [],
   "source": [
    "# y = df['prognosis']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [],
   "source": [
    "# X = X.iloc[:,:-1]"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## **Without splitting the columns**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [],
   "source": [
    "# X_train,y_train,X_test,y_test = train_test_split(X,y,random_state=42,test_size=0.2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train = training_df.drop(columns=['prognosis'])\n",
    "y_train = training_df['prognosis']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train = X_train.iloc[:,:-1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [],
   "source": [
    "def update_columns(dataf):\n",
    "    column_names = list(dataf.columns.values)\n",
    "    split_list = [word.split('_') for word in column_names]\n",
    "\n",
    "    lemmatizer = WordNetLemmatizer()\n",
    "\n",
    "    lemmatized_list = [[lemmatizer.lemmatize(word) for word in sublist  if word not in set(stopwords.words('english'))] for sublist in split_list]\n",
    "\n",
    "    joined_list = ['_'.join(word) for word in lemmatized_list]\n",
    "\n",
    "    dataf = dataf.rename(columns=dict(zip(dataf.columns, joined_list)))\n",
    "    return dataf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train = update_columns(X_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {},
   "outputs": [],
   "source": [
    "# column_names = list(X_train.columns.values)\n",
    "# split_list = [word.split('_') for word in column_names]\n",
    "\n",
    "# lemmatizer = WordNetLemmatizer()\n",
    "\n",
    "# lemmatized_list = [[lemmatizer.lemmatize(word) for word in sublist  if word not in set(stopwords.words('english'))] for sublist in split_list]\n",
    "\n",
    "# joined_list = ['_'.join(word) for word in lemmatized_list]\n",
    "\n",
    "# X_train = X_train.rename(columns=dict(zip(X_train.columns, joined_list)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_test = testing_df.drop(columns=['prognosis'])\n",
    "y_test = testing_df['prognosis']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_test = update_columns(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-2 {color: black;background-color: white;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "RandomForestClassifier()"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clf = RandomForestClassifier()\n",
    "clf.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Fungal infection', 'Allergy', 'GERD', 'Chronic cholestasis',\n",
       "       'Drug Reaction', 'Peptic ulcer diseae', 'AIDS', 'Diabetes ',\n",
       "       'Gastroenteritis', 'Bronchial Asthma', 'Hypertension ', 'Migraine',\n",
       "       'Cervical spondylosis', 'Paralysis (brain hemorrhage)', 'Jaundice',\n",
       "       'Malaria', 'Chicken pox', 'Dengue', 'Typhoid', 'hepatitis A',\n",
       "       'Hepatitis B', 'Hepatitis C', 'Hepatitis D', 'Hepatitis E',\n",
       "       'Alcoholic hepatitis', 'Tuberculosis', 'Common Cold', 'Pneumonia',\n",
       "       'Dimorphic hemmorhoids(piles)', 'Heart attack', 'Varicose veins',\n",
       "       'Hypothyroidism', 'Hyperthyroidism', 'Hypoglycemia',\n",
       "       'Osteoarthristis', 'Arthritis',\n",
       "       '(vertigo) Paroymsal  Positional Vertigo', 'Acne',\n",
       "       'Urinary tract infection', 'Psoriasis', 'Impetigo', 'Chicken pox'],\n",
       "      dtype=object)"
      ]
     },
     "execution_count": 76,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred = clf.predict(X_test)\n",
    "y_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9761904761904762"
      ]
     },
     "execution_count": 77,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy_score(y_test,y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "clf = LazyClassifier(verbose=0,custom_metric=None,ignore_warnings=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 29/29 [03:10<00:00,  6.58s/it]\n"
     ]
    }
   ],
   "source": [
    "models, predictions = clf.fit(X_train,X_test,y_train,y_test)"
   ]
  },
  {
   "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>Accuracy</th>\n",
       "      <th>Balanced Accuracy</th>\n",
       "      <th>ROC AUC</th>\n",
       "      <th>F1 Score</th>\n",
       "      <th>Time Taken</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Model</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>BernoulliNB</th>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>None</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0.03</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CategoricalNB</th>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>None</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0.10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LGBMClassifier</th>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "      <td>None</td>\n",
       "      <td>0.98</td>\n",
       "      <td>1.99</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>BaggingClassifier</th>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "      <td>None</td>\n",
       "      <td>0.98</td>\n",
       "      <td>0.19</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>RidgeClassifier</th>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "      <td>None</td>\n",
       "      <td>0.98</td>\n",
       "      <td>0.06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>RandomForestClassifier</th>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "      <td>None</td>\n",
       "      <td>0.98</td>\n",
       "      <td>0.34</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>QuadraticDiscriminantAnalysis</th>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "      <td>None</td>\n",
       "      <td>0.98</td>\n",
       "      <td>0.12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Perceptron</th>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "      <td>None</td>\n",
       "      <td>0.98</td>\n",
       "      <td>0.22</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PassiveAggressiveClassifier</th>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "      <td>None</td>\n",
       "      <td>0.98</td>\n",
       "      <td>0.40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>NuSVC</th>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "      <td>None</td>\n",
       "      <td>0.98</td>\n",
       "      <td>1.06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>NearestCentroid</th>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "      <td>None</td>\n",
       "      <td>0.98</td>\n",
       "      <td>0.04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LogisticRegression</th>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "      <td>None</td>\n",
       "      <td>0.98</td>\n",
       "      <td>0.78</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LinearSVC</th>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "      <td>None</td>\n",
       "      <td>0.98</td>\n",
       "      <td>36.47</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LabelSpreading</th>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "      <td>None</td>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>SGDClassifier</th>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "      <td>None</td>\n",
       "      <td>0.98</td>\n",
       "      <td>0.37</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LabelPropagation</th>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "      <td>None</td>\n",
       "      <td>0.98</td>\n",
       "      <td>0.65</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>KNeighborsClassifier</th>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "      <td>None</td>\n",
       "      <td>0.98</td>\n",
       "      <td>0.05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>GaussianNB</th>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "      <td>None</td>\n",
       "      <td>0.98</td>\n",
       "      <td>0.03</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ExtraTreesClassifier</th>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "      <td>None</td>\n",
       "      <td>0.98</td>\n",
       "      <td>0.33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>ExtraTreeClassifier</th>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "      <td>None</td>\n",
       "      <td>0.98</td>\n",
       "      <td>0.02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>SVC</th>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "      <td>None</td>\n",
       "      <td>0.98</td>\n",
       "      <td>0.14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>DecisionTreeClassifier</th>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "      <td>None</td>\n",
       "      <td>0.98</td>\n",
       "      <td>0.04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CalibratedClassifierCV</th>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "      <td>None</td>\n",
       "      <td>0.98</td>\n",
       "      <td>143.36</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>RidgeClassifierCV</th>\n",
       "      <td>0.98</td>\n",
       "      <td>0.99</td>\n",
       "      <td>None</td>\n",
       "      <td>0.98</td>\n",
       "      <td>0.20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>LinearDiscriminantAnalysis</th>\n",
       "      <td>0.26</td>\n",
       "      <td>0.27</td>\n",
       "      <td>None</td>\n",
       "      <td>0.24</td>\n",
       "      <td>0.17</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>AdaBoostClassifier</th>\n",
       "      <td>0.17</td>\n",
       "      <td>0.17</td>\n",
       "      <td>None</td>\n",
       "      <td>0.14</td>\n",
       "      <td>0.64</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>DummyClassifier</th>\n",
       "      <td>0.02</td>\n",
       "      <td>0.02</td>\n",
       "      <td>None</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.02</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                               Accuracy  Balanced Accuracy ROC AUC  F1 Score   \n",
       "Model                                                                          \n",
       "BernoulliNB                        1.00               1.00    None      1.00  \\\n",
       "CategoricalNB                      1.00               1.00    None      1.00   \n",
       "LGBMClassifier                     0.98               0.99    None      0.98   \n",
       "BaggingClassifier                  0.98               0.99    None      0.98   \n",
       "RidgeClassifier                    0.98               0.99    None      0.98   \n",
       "RandomForestClassifier             0.98               0.99    None      0.98   \n",
       "QuadraticDiscriminantAnalysis      0.98               0.99    None      0.98   \n",
       "Perceptron                         0.98               0.99    None      0.98   \n",
       "PassiveAggressiveClassifier        0.98               0.99    None      0.98   \n",
       "NuSVC                              0.98               0.99    None      0.98   \n",
       "NearestCentroid                    0.98               0.99    None      0.98   \n",
       "LogisticRegression                 0.98               0.99    None      0.98   \n",
       "LinearSVC                          0.98               0.99    None      0.98   \n",
       "LabelSpreading                     0.98               0.99    None      0.98   \n",
       "SGDClassifier                      0.98               0.99    None      0.98   \n",
       "LabelPropagation                   0.98               0.99    None      0.98   \n",
       "KNeighborsClassifier               0.98               0.99    None      0.98   \n",
       "GaussianNB                         0.98               0.99    None      0.98   \n",
       "ExtraTreesClassifier               0.98               0.99    None      0.98   \n",
       "ExtraTreeClassifier                0.98               0.99    None      0.98   \n",
       "SVC                                0.98               0.99    None      0.98   \n",
       "DecisionTreeClassifier             0.98               0.99    None      0.98   \n",
       "CalibratedClassifierCV             0.98               0.99    None      0.98   \n",
       "RidgeClassifierCV                  0.98               0.99    None      0.98   \n",
       "LinearDiscriminantAnalysis         0.26               0.27    None      0.24   \n",
       "AdaBoostClassifier                 0.17               0.17    None      0.14   \n",
       "DummyClassifier                    0.02               0.02    None      0.00   \n",
       "\n",
       "                               Time Taken  \n",
       "Model                                      \n",
       "BernoulliNB                          0.03  \n",
       "CategoricalNB                        0.10  \n",
       "LGBMClassifier                       1.99  \n",
       "BaggingClassifier                    0.19  \n",
       "RidgeClassifier                      0.06  \n",
       "RandomForestClassifier               0.34  \n",
       "QuadraticDiscriminantAnalysis        0.12  \n",
       "Perceptron                           0.22  \n",
       "PassiveAggressiveClassifier          0.40  \n",
       "NuSVC                                1.06  \n",
       "NearestCentroid                      0.04  \n",
       "LogisticRegression                   0.78  \n",
       "LinearSVC                           36.47  \n",
       "LabelSpreading                       0.99  \n",
       "SGDClassifier                        0.37  \n",
       "LabelPropagation                     0.65  \n",
       "KNeighborsClassifier                 0.05  \n",
       "GaussianNB                           0.03  \n",
       "ExtraTreesClassifier                 0.33  \n",
       "ExtraTreeClassifier                  0.02  \n",
       "SVC                                  0.14  \n",
       "DecisionTreeClassifier               0.04  \n",
       "CalibratedClassifierCV             143.36  \n",
       "RidgeClassifierCV                    0.20  \n",
       "LinearDiscriminantAnalysis           0.17  \n",
       "AdaBoostClassifier                   0.64  \n",
       "DummyClassifier                      0.02  "
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "models"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# **User input**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-3 {color: black;background-color: white;}#sk-container-id-3 pre{padding: 0;}#sk-container-id-3 div.sk-toggleable {background-color: white;}#sk-container-id-3 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-3 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-3 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-3 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-3 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-3 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-3 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-3 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-3 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-3 div.sk-item {position: relative;z-index: 1;}#sk-container-id-3 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-3 div.sk-item::before, #sk-container-id-3 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-3 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-3 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-3 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-3 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-3 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-3 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-3 div.sk-label-container {text-align: center;}#sk-container-id-3 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-3 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" checked><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "RandomForestClassifier()"
      ]
     },
     "execution_count": 78,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clf = RandomForestClassifier()\n",
    "clf.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Fungal infection', 'Allergy', 'GERD', 'Chronic cholestasis',\n",
       "       'Drug Reaction', 'Peptic ulcer diseae', 'AIDS', 'Diabetes ',\n",
       "       'Gastroenteritis', 'Bronchial Asthma', 'Hypertension ', 'Migraine',\n",
       "       'Cervical spondylosis', 'Paralysis (brain hemorrhage)', 'Jaundice',\n",
       "       'Malaria', 'Chicken pox', 'Dengue', 'Typhoid', 'hepatitis A',\n",
       "       'Hepatitis B', 'Hepatitis C', 'Hepatitis D', 'Hepatitis E',\n",
       "       'Alcoholic hepatitis', 'Tuberculosis', 'Common Cold', 'Pneumonia',\n",
       "       'Dimorphic hemmorhoids(piles)', 'Heart attack', 'Varicose veins',\n",
       "       'Hypothyroidism', 'Hyperthyroidism', 'Hypoglycemia',\n",
       "       'Osteoarthristis', 'Arthritis',\n",
       "       '(vertigo) Paroymsal  Positional Vertigo', 'Acne',\n",
       "       'Urinary tract infection', 'Psoriasis', 'Impetigo', 'Chicken pox'],\n",
       "      dtype=object)"
      ]
     },
     "execution_count": 79,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred = clf.predict(X_test)\n",
    "y_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9761904761904762"
      ]
     },
     "execution_count": 80,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy_score(y_test,y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {},
   "outputs": [],
   "source": [
    "#getting the input from the user\n",
    "\n",
    "# I am having headache, stiff neck and hunger too.\n",
    "# Migraine\n",
    "\n",
    "# -- fungal infection---\n",
    "# input = \"I have been facing pain in right abdomen, what should I do?\"\n",
    "# input = \"I am having headache, stiff neck and hunger too\"\n",
    "# input = \"I am having stomach pain and vomitting\"\n",
    "input = \"Facing continuous sneezing and watering from eyes\"\n",
    "#converting it to lowercase\n",
    "input = input.lower()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "# removing numbers\n",
    "remove_digits = input.maketrans('', '', digits)\n",
    "input = input.translate(remove_digits)\n",
    "# REPLACING NEXT LINES BY 'WHITE SPACE'\n",
    "input = input.replace(r'\\n', \" \")\n",
    "# REPLACING CURRENCY SIGNS BY 'MONEY'\n",
    "input = input.replace(r'£|\\$', 'Money')\n",
    "# REPLACING SPECIAL CHARACTERS BY WHITE SPACE\n",
    "input = re.sub('[^A-Za-z0-9]+', ' ', input)\n",
    "# REPLACING LARGE WHITE SPACE BY SINGLE WHITE SPACE\n",
    "input = input.replace(r'\\s+', ' ')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [],
   "source": [
    "lemmatizer = WordNetLemmatizer()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [],
   "source": [
    "tokens = input.split(' ')\n",
    "tokens = [lemmatizer.lemmatize(word) for word in tokens if word not in set(stopwords.words('english'))]\n",
    "tokens = set(tokens)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'continuous', 'eye', 'facing', 'sneezing', 'watering'}"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tokens"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [],
   "source": [
    "columns = X_train.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['itching', 'skin_rash', 'nodal_skin_eruption', 'continuous_sneezing',\n",
       "       'shivering', 'chill', 'joint_pain', 'stomach_pain', 'acidity',\n",
       "       'ulcer_tongue',\n",
       "       ...\n",
       "       'pu_filled_pimple', 'blackhead', 'scurring', 'skin_peeling',\n",
       "       'silver_like_dusting', 'small_dent_nail', 'inflammatory_nail',\n",
       "       'blister', 'red_sore_around_nose', 'yellow_crust_ooze'],\n",
       "      dtype='object', length=132)"
      ]
     },
     "execution_count": 87,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_vec = []\n",
    "for c in columns:\n",
    "    col_vec = c.split('_')\n",
    "    if len(col_vec)==1:\n",
    "        if col_vec[0] in tokens:\n",
    "            test_vec.append(1)\n",
    "        else: \n",
    "            test_vec.append(0)\n",
    "    else:\n",
    "        flag = False\n",
    "        for temp in col_vec:\n",
    "            if temp in tokens:\n",
    "                test_vec.append(1)\n",
    "                flag = True\n",
    "                break\n",
    "        if flag==False:\n",
    "            test_vec.append(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "132"
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(test_vec)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "metadata": {},
   "outputs": [],
   "source": [
    "# np.reshape(test_vec,)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "metadata": {},
   "outputs": [],
   "source": [
    "# clf.predict([test_vec])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "metadata": {},
   "outputs": [],
   "source": [
    "bnclf = BernoulliNB()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-4 {color: black;background-color: white;}#sk-container-id-4 pre{padding: 0;}#sk-container-id-4 div.sk-toggleable {background-color: white;}#sk-container-id-4 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-4 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-4 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-4 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-4 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-4 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-4 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-4 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-4 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-4 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-4 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-4 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-4 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-4 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-4 div.sk-item {position: relative;z-index: 1;}#sk-container-id-4 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-4 div.sk-item::before, #sk-container-id-4 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-4 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-4 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-4 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-4 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-4 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-4 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-4 div.sk-label-container {text-align: center;}#sk-container-id-4 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-4 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-4\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>BernoulliNB()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" checked><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">BernoulliNB</label><div class=\"sk-toggleable__content\"><pre>BernoulliNB()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "BernoulliNB()"
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bnclf.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Fungal infection', 'Allergy', 'GERD', 'Chronic cholestasis',\n",
       "       'Drug Reaction', 'Peptic ulcer diseae', 'AIDS', 'Diabetes ',\n",
       "       'Gastroenteritis', 'Bronchial Asthma', 'Hypertension ', 'Migraine',\n",
       "       'Cervical spondylosis', 'Paralysis (brain hemorrhage)', 'Jaundice',\n",
       "       'Malaria', 'Chicken pox', 'Dengue', 'Typhoid', 'hepatitis A',\n",
       "       'Hepatitis B', 'Hepatitis C', 'Hepatitis D', 'Hepatitis E',\n",
       "       'Alcoholic hepatitis', 'Tuberculosis', 'Common Cold', 'Pneumonia',\n",
       "       'Dimorphic hemmorhoids(piles)', 'Heart attack', 'Varicose veins',\n",
       "       'Hypothyroidism', 'Hyperthyroidism', 'Hypoglycemia',\n",
       "       'Osteoarthristis', 'Arthritis',\n",
       "       '(vertigo) Paroymsal  Positional Vertigo', 'Acne',\n",
       "       'Urinary tract infection', 'Psoriasis', 'Impetigo',\n",
       "       'Fungal infection'], dtype='<U39')"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred = bnclf.predict(X_test)\n",
    "y_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.0"
      ]
     },
     "execution_count": 95,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy_score(y_test,y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Allergy'], dtype='<U39')"
      ]
     },
     "execution_count": 96,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bnclf.predict([test_vec])"
   ]
  },
  {
   "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": "3.11.1"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}