ML Disease Prediction - Smart Doctor.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "4bb6c84a",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from pandas import read_csv\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b803773e",
   "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>blackheads</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",
       "    </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>0</td>\n",
       "      <td>Fungal infection</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>0</td>\n",
       "      <td>Fungal infection</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>0</td>\n",
       "      <td>Fungal infection</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>0</td>\n",
       "      <td>Fungal infection</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>0</td>\n",
       "      <td>Fungal infection</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 133 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   itching  skin_rash  nodal_skin_eruptions  continuous_sneezing  shivering  \\\n",
       "0        1          1                     1                    0          0   \n",
       "1        0          1                     1                    0          0   \n",
       "2        1          0                     1                    0          0   \n",
       "3        1          1                     0                    0          0   \n",
       "4        1          1                     1                    0          0   \n",
       "\n",
       "   chills  joint_pain  stomach_pain  acidity  ulcers_on_tongue  ...  \\\n",
       "0       0           0             0        0                 0  ...   \n",
       "1       0           0             0        0                 0  ...   \n",
       "2       0           0             0        0                 0  ...   \n",
       "3       0           0             0        0                 0  ...   \n",
       "4       0           0             0        0                 0  ...   \n",
       "\n",
       "   blackheads  scurring  skin_peeling  silver_like_dusting  \\\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",
       "   small_dents_in_nails  inflammatory_nails  blister  red_sore_around_nose  \\\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",
       "   yellow_crust_ooze         prognosis  \n",
       "0                  0  Fungal infection  \n",
       "1                  0  Fungal infection  \n",
       "2                  0  Fungal infection  \n",
       "3                  0  Fungal infection  \n",
       "4                  0  Fungal infection  \n",
       "\n",
       "[5 rows x 133 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "filename='Training.csv'\n",
    "data=read_csv(filename)\n",
    "data.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "7aba30f5",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_x=data[['itching','skin_rash','nodal_skin_eruptions','continuous_sneezing','shivering','chills','joint_pain','stomach_pain','acidity','ulcers_on_tongue','muscle_wasting','vomiting','burning_micturition','spotting_ urination','fatigue','weight_gain','anxiety','cold_hands_and_feets','mood_swings','weight_loss','restlessness','lethargy','patches_in_throat','irregular_sugar_level','cough','high_fever','sunken_eyes','breathlessness','sweating','dehydration','indigestion','headache','yellowish_skin','dark_urine','nausea','loss_of_appetite','pain_behind_the_eyes','back_pain','constipation','abdominal_pain','diarrhoea','mild_fever','yellow_urine','yellowing_of_eyes','acute_liver_failure','fluid_overload','swelling_of_stomach','swelled_lymph_nodes','malaise','blurred_and_distorted_vision','phlegm','throat_irritation','redness_of_eyes','sinus_pressure','runny_nose','congestion','chest_pain','weakness_in_limbs','fast_heart_rate','pain_during_bowel_movements','pain_in_anal_region','bloody_stool','irritation_in_anus','neck_pain','dizziness','cramps','bruising','obesity','swollen_legs','swollen_blood_vessels','puffy_face_and_eyes','enlarged_thyroid','brittle_nails','swollen_extremeties','excessive_hunger','extra_marital_contacts','drying_and_tingling_lips','slurred_speech','knee_pain','hip_joint_pain','muscle_weakness','stiff_neck','swelling_joints','movement_stiffness','spinning_movements','loss_of_balance','unsteadiness','weakness_of_one_body_side','loss_of_smell','bladder_discomfort','foul_smell_of urine','continuous_feel_of_urine','passage_of_gases','internal_itching','toxic_look_(typhos)','depression','irritability','muscle_pain','altered_sensorium','red_spots_over_body','belly_pain','abnormal_menstruation','dischromic _patches','watering_from_eyes','increased_appetite','polyuria','family_history','mucoid_sputum','rusty_sputum','lack_of_concentration','visual_disturbances','receiving_blood_transfusion','receiving_unsterile_injections','coma','stomach_bleeding','distention_of_abdomen','history_of_alcohol_consumption','fluid_overload','blood_in_sputum','prominent_veins_on_calf','palpitations','painful_walking','pus_filled_pimples','blackheads','scurring','skin_peeling','silver_like_dusting','small_dents_in_nails','inflammatory_nails','blister','red_sore_around_nose','yellow_crust_ooze'\n",
    "]]\n",
    "df_y=data[['prognosis']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "808e0edd",
   "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>pus_filled_pimples</th>\n",
       "      <th>blackheads</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",
       "    </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>0</td>\n",
       "      <td>0</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>0</td>\n",
       "      <td>0</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>0</td>\n",
       "      <td>0</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>0</td>\n",
       "      <td>0</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>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 132 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   itching  skin_rash  nodal_skin_eruptions  continuous_sneezing  shivering  \\\n",
       "0        1          1                     1                    0          0   \n",
       "1        0          1                     1                    0          0   \n",
       "2        1          0                     1                    0          0   \n",
       "3        1          1                     0                    0          0   \n",
       "4        1          1                     1                    0          0   \n",
       "\n",
       "   chills  joint_pain  stomach_pain  acidity  ulcers_on_tongue  ...  \\\n",
       "0       0           0             0        0                 0  ...   \n",
       "1       0           0             0        0                 0  ...   \n",
       "2       0           0             0        0                 0  ...   \n",
       "3       0           0             0        0                 0  ...   \n",
       "4       0           0             0        0                 0  ...   \n",
       "\n",
       "   pus_filled_pimples  blackheads  scurring  skin_peeling  \\\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",
       "   silver_like_dusting  small_dents_in_nails  inflammatory_nails  blister  \\\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",
       "   red_sore_around_nose  yellow_crust_ooze  \n",
       "0                     0                  0  \n",
       "1                     0                  0  \n",
       "2                     0                  0  \n",
       "3                     0                  0  \n",
       "4                     0                  0  \n",
       "\n",
       "[5 rows x 132 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_x.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "fd56dec6",
   "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>prognosis</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Fungal infection</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Fungal infection</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Fungal infection</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Fungal infection</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Fungal infection</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          prognosis\n",
       "0  Fungal infection\n",
       "1  Fungal infection\n",
       "2  Fungal infection\n",
       "3  Fungal infection\n",
       "4  Fungal infection"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_y.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "fc9c3b16",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "x_train,x_test,y_train,y_test=train_test_split(df_x,df_y,test_size=0.2,random_state=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "79a8c9a0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(984, 132)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "58deb926",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.naive_bayes import GaussianNB\n",
    "\n",
    "gnb = GaussianNB()\n",
    "\n",
    "gnb = gnb.fit(df_x, np.ravel(df_y))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "011e727b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1.0\n",
      "984\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import accuracy_score\n",
    "y_pred=gnb.predict(x_test)\n",
    "print(accuracy_score(y_test,y_pred))\n",
    "print(accuracy_score(y_test,y_pred,normalize=False))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "fac9dac9",
   "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>pus_filled_pimples</th>\n",
       "      <th>blackheads</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",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1525</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>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1013</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>1</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>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1892</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>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1972</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>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>873</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>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1332</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>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3683</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>1</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>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>304</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>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>601</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>1</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>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1828</th>\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",
       "      <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>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>10 rows × 132 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      itching  skin_rash  nodal_skin_eruptions  continuous_sneezing  \\\n",
       "1525        0          0                     0                    0   \n",
       "1013        0          0                     0                    0   \n",
       "1892        0          0                     0                    0   \n",
       "1972        0          0                     0                    0   \n",
       "873         0          0                     0                    0   \n",
       "1332        0          0                     0                    0   \n",
       "3683        0          0                     0                    0   \n",
       "304         0          0                     0                    0   \n",
       "601         0          0                     0                    0   \n",
       "1828        0          0                     0                    0   \n",
       "\n",
       "      shivering  chills  joint_pain  stomach_pain  acidity  ulcers_on_tongue  \\\n",
       "1525          0       0           0             0        0                 0   \n",
       "1013          0       0           1             0        0                 0   \n",
       "1892          0       0           0             0        0                 0   \n",
       "1972          0       0           0             0        0                 0   \n",
       "873           0       0           0             0        0                 0   \n",
       "1332          0       0           0             0        0                 0   \n",
       "3683          0       0           1             0        0                 0   \n",
       "304           0       0           0             0        0                 0   \n",
       "601           0       0           1             0        0                 0   \n",
       "1828          0       1           0             0        0                 0   \n",
       "\n",
       "      ...  pus_filled_pimples  blackheads  scurring  skin_peeling  \\\n",
       "1525  ...                   0           0         0             0   \n",
       "1013  ...                   0           0         0             0   \n",
       "1892  ...                   0           0         0             0   \n",
       "1972  ...                   0           0         0             0   \n",
       "873   ...                   0           0         0             0   \n",
       "1332  ...                   0           0         0             0   \n",
       "3683  ...                   0           0         0             0   \n",
       "304   ...                   0           0         0             0   \n",
       "601   ...                   0           0         0             0   \n",
       "1828  ...                   0           0         0             0   \n",
       "\n",
       "      silver_like_dusting  small_dents_in_nails  inflammatory_nails  blister  \\\n",
       "1525                    0                     0                   0        0   \n",
       "1013                    0                     0                   0        0   \n",
       "1892                    0                     0                   0        0   \n",
       "1972                    0                     0                   0        0   \n",
       "873                     0                     0                   0        0   \n",
       "1332                    0                     0                   0        0   \n",
       "3683                    0                     0                   0        0   \n",
       "304                     0                     0                   0        0   \n",
       "601                     0                     0                   0        0   \n",
       "1828                    0                     0                   0        0   \n",
       "\n",
       "      red_sore_around_nose  yellow_crust_ooze  \n",
       "1525                     0                  0  \n",
       "1013                     0                  0  \n",
       "1892                     0                  0  \n",
       "1972                     0                  0  \n",
       "873                      0                  0  \n",
       "1332                     0                  0  \n",
       "3683                     0                  0  \n",
       "304                      0                  0  \n",
       "601                      0                  0  \n",
       "1828                     0                  0  \n",
       "\n",
       "[10 rows x 132 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_test.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "d330d043",
   "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>prognosis</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1525</th>\n",
       "      <td>Heart attack</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1013</th>\n",
       "      <td>hepatitis A</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1892</th>\n",
       "      <td>Tuberculosis</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1972</th>\n",
       "      <td>Hypoglycemia</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>873</th>\n",
       "      <td>Peptic ulcer diseae</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1332</th>\n",
       "      <td>Hypertension</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3683</th>\n",
       "      <td>Osteoarthristis</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>304</th>\n",
       "      <td>Varicose veins</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>601</th>\n",
       "      <td>hepatitis A</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1828</th>\n",
       "      <td>Typhoid</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                prognosis\n",
       "1525         Heart attack\n",
       "1013          hepatitis A\n",
       "1892         Tuberculosis\n",
       "1972         Hypoglycemia\n",
       "873   Peptic ulcer diseae\n",
       "1332        Hypertension \n",
       "3683      Osteoarthristis\n",
       "304        Varicose veins\n",
       "601           hepatitis A\n",
       "1828              Typhoid"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_test.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "7588a35e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Heart attack' 'hepatitis A' 'Tuberculosis' 'Hypoglycemia'\n",
      " 'Peptic ulcer diseae' 'Hypertension ' 'Osteoarthristis' 'Varicose veins'\n",
      " 'hepatitis A' 'Typhoid']\n"
     ]
    }
   ],
   "source": [
    "prediction=gnb.predict(x_test)\n",
    "print(prediction[0:10])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "79542801",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['model/naive_bayes.pkl']"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import joblib as joblib\n",
    "joblib.dump(gnb,'model/naive_bayes.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "a07f4ab4",
   "metadata": {},
   "outputs": [],
   "source": [
    "nb=joblib.load('model/naive_bayes.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "f88bc143",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Heart attack' 'hepatitis A' 'Tuberculosis' 'Hypoglycemia'\n",
      " 'Peptic ulcer diseae' 'Hypertension ' 'Osteoarthristis' 'Varicose veins'\n",
      " 'hepatitis A' 'Typhoid']\n"
     ]
    }
   ],
   "source": [
    "prediction=nb.predict(x_test)\n",
    "print(prediction[0:10])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "3fb424f1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "132\n"
     ]
    }
   ],
   "source": [
    "list_a=['itching','skin_rash','nodal_skin_eruptions','continuous_sneezing','shivering','chills','joint_pain','stomach_pain','acidity','ulcers_on_tongue','muscle_wasting','vomiting','burning_micturition','spotting_ urination','fatigue','weight_gain','anxiety','cold_hands_and_feets','mood_swings','weight_loss','restlessness','lethargy','patches_in_throat','irregular_sugar_level','cough','high_fever','sunken_eyes','breathlessness','sweating','dehydration','indigestion','headache','yellowish_skin','dark_urine','nausea','loss_of_appetite','pain_behind_the_eyes','back_pain','constipation','abdominal_pain','diarrhoea','mild_fever','yellow_urine','yellowing_of_eyes','acute_liver_failure','fluid_overload','swelling_of_stomach','swelled_lymph_nodes','malaise','blurred_and_distorted_vision','phlegm','throat_irritation','redness_of_eyes','sinus_pressure','runny_nose','congestion','chest_pain','weakness_in_limbs','fast_heart_rate','pain_during_bowel_movements','pain_in_anal_region','bloody_stool','irritation_in_anus','neck_pain','dizziness','cramps','bruising','obesity','swollen_legs','swollen_blood_vessels','puffy_face_and_eyes','enlarged_thyroid','brittle_nails','swollen_extremeties','excessive_hunger','extra_marital_contacts','drying_and_tingling_lips','slurred_speech','knee_pain','hip_joint_pain','muscle_weakness','stiff_neck','swelling_joints','movement_stiffness','spinning_movements','loss_of_balance','unsteadiness','weakness_of_one_body_side','loss_of_smell','bladder_discomfort','foul_smell_of urine','continuous_feel_of_urine','passage_of_gases','internal_itching','toxic_look_(typhos)','depression','irritability','muscle_pain','altered_sensorium','red_spots_over_body','belly_pain','abnormal_menstruation','dischromic _patches','watering_from_eyes','increased_appetite','polyuria','family_history','mucoid_sputum','rusty_sputum','lack_of_concentration','visual_disturbances','receiving_blood_transfusion','receiving_unsterile_injections','coma','stomach_bleeding','distention_of_abdomen','history_of_alcohol_consumption','fluid_overload','blood_in_sputum','prominent_veins_on_calf','palpitations','painful_walking','pus_filled_pimples','blackheads','scurring','skin_peeling','silver_like_dusting','small_dents_in_nails','inflammatory_nails','blister','red_sore_around_nose','yellow_crust_ooze']\n",
    "print(len(list_a))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "495d8cdd",
   "metadata": {},
   "outputs": [],
   "source": [
    "list_c=[]\n",
    "for x in range(0,len(list_a)):\n",
    "    list_c.append(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "b277d6fc",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]\n"
     ]
    }
   ],
   "source": [
    "print(list_c)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "3f376849",
   "metadata": {},
   "outputs": [],
   "source": [
    "list_b=['shivering','headache','vomiting','muscle_pain','diarrhoea']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "b55ce8ce",
   "metadata": {},
   "outputs": [],
   "source": [
    "for z in range(0,len(list_a)):\n",
    "    for k in list_b:\n",
    "        if(k==list_a[z]):\n",
    "            list_c[z]=1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "93a3a151",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]\n"
     ]
    }
   ],
   "source": [
    "print(list_c)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "402fcdd9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1, 132)\n"
     ]
    }
   ],
   "source": [
    "test=np.array(list_c)\n",
    "test=np.array(test).reshape(1,-1)\n",
    "print(test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "a5aebd96",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Malaria']\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Bushra Jamil\\anaconda3\\lib\\site-packages\\sklearn\\base.py:450: UserWarning: X does not have valid feature names, but GaussianNB was fitted with feature names\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "prediction=nb.predict(test)\n",
    "print(prediction)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "aa0cf1c8",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier\n",
    "rf=RandomForestClassifier()\n",
    "rf=rf.fit(df_x,np.ravel(df_y))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "c01c8499",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1.0\n",
      "984\n"
     ]
    }
   ],
   "source": [
    "y_pred=rf.predict(x_test)\n",
    "print(accuracy_score(y_test,y_pred))\n",
    "print(accuracy_score(y_test,y_pred,normalize=False))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "d8ef43cd",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.0"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rf.score(x_test,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "9e7f32c9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Heart attack' 'hepatitis A' 'Tuberculosis' 'Hypoglycemia'\n",
      " 'Peptic ulcer diseae' 'Hypertension ' 'Osteoarthristis' 'Varicose veins'\n",
      " 'hepatitis A' 'Typhoid']\n"
     ]
    }
   ],
   "source": [
    "prediction=rf.predict(x_test)\n",
    "print(prediction[0:10])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "8f71dd4f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['model/random_forest.pkl']"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "joblib.dump(rf,'model/random_forest.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "882c993b",
   "metadata": {},
   "outputs": [],
   "source": [
    "rand_forest=joblib.load('model/random_forest.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "aef013be",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Heart attack' 'hepatitis A' 'Tuberculosis' 'Hypoglycemia'\n",
      " 'Peptic ulcer diseae' 'Hypertension ' 'Osteoarthristis' 'Varicose veins'\n",
      " 'hepatitis A' 'Typhoid']\n"
     ]
    }
   ],
   "source": [
    "prediction=rand_forest.predict(x_test)\n",
    "print(prediction[0:10])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "9798b861",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Malaria\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Bushra Jamil\\anaconda3\\lib\\site-packages\\sklearn\\base.py:450: UserWarning: X does not have valid feature names, but RandomForestClassifier was fitted with feature names\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "prediction=rand_forest.predict(test)\n",
    "print(prediction[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "76d6e595",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Bushra Jamil\\anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py:993: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
      "  y = column_or_1d(y, warn=True)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "LogisticRegression()"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "\n",
    "logreg = LogisticRegression()\n",
    "logreg.fit(df_x, df_y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "404b6294",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.0"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "logreg.score(x_test, y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "9e9b2eda",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['model/lopistic_regression.pkl']"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import joblib as joblib\n",
    "joblib.dump(logreg, 'model/lopistic_regression.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "3a878575",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "dt = joblib.load('model/lopistic_regression.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "ac044ea5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Malaria\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Bushra Jamil\\anaconda3\\lib\\site-packages\\sklearn\\base.py:450: UserWarning: X does not have valid feature names, but LogisticRegression was fitted with feature names\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "prediction = dt.predict(test)\n",
    "print(prediction[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "b9cbb0d3",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn import tree\n",
    "\n",
    "clf3 = tree.DecisionTreeClassifier()   # empty model of the decision tree\n",
    "clf3 = clf3.fit(df_x,df_y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "93b84299",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1.0\n",
      "984\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import accuracy_score\n",
    "y_pred=clf3.predict(x_test)\n",
    "print(accuracy_score(y_test, y_pred))\n",
    "print(accuracy_score(y_test, y_pred,normalize=False))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "ff79f8a7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['model/decision_tree.pkl']"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import joblib as joblib\n",
    "joblib.dump(clf3, 'model/decision_tree.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "54dcb199",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "dt = joblib.load('model/decision_tree.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "6e2109de",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Malaria\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Bushra Jamil\\anaconda3\\lib\\site-packages\\sklearn\\base.py:450: UserWarning: X does not have valid feature names, but DecisionTreeClassifier was fitted with feature names\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "prediction = dt.predict(test)\n",
    "print(prediction[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f1c72984",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}