disease_prediction_final.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "3c79fd4f",
   "metadata": {
    "id": "3c79fd4f"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import accuracy_score\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "071331d3",
   "metadata": {
    "id": "071331d3"
   },
   "source": [
    "# dataset "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "yFGFr6kP9-uA",
   "metadata": {
    "id": "yFGFr6kP9-uA"
   },
   "source": [
    "# New section"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "eb419275",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 307
    },
    "id": "eb419275",
    "outputId": "40293061-1ee3-4632-a2e3-94ea18dcbc9c"
   },
   "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>Disease</th>\n",
       "      <th>Symptom_1</th>\n",
       "      <th>Symptom_2</th>\n",
       "      <th>Symptom_3</th>\n",
       "      <th>Symptom_4</th>\n",
       "      <th>Symptom_5</th>\n",
       "      <th>Symptom_6</th>\n",
       "      <th>Symptom_7</th>\n",
       "      <th>Symptom_8</th>\n",
       "      <th>Symptom_9</th>\n",
       "      <th>Symptom_10</th>\n",
       "      <th>Symptom_11</th>\n",
       "      <th>Symptom_12</th>\n",
       "      <th>Symptom_13</th>\n",
       "      <th>Symptom_14</th>\n",
       "      <th>Symptom_15</th>\n",
       "      <th>Symptom_16</th>\n",
       "      <th>Symptom_17</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4915</th>\n",
       "      <td>(vertigo) Paroymsal  Positional Vertigo</td>\n",
       "      <td>vomiting</td>\n",
       "      <td>headache</td>\n",
       "      <td>nausea</td>\n",
       "      <td>spinning_movements</td>\n",
       "      <td>loss_of_balance</td>\n",
       "      <td>unsteadiness</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4916</th>\n",
       "      <td>Acne</td>\n",
       "      <td>skin_rash</td>\n",
       "      <td>pus_filled_pimples</td>\n",
       "      <td>blackheads</td>\n",
       "      <td>scurring</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4917</th>\n",
       "      <td>Urinary tract infection</td>\n",
       "      <td>burning_micturition</td>\n",
       "      <td>bladder_discomfort</td>\n",
       "      <td>foul_smell_of urine</td>\n",
       "      <td>continuous_feel_of_urine</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4918</th>\n",
       "      <td>Psoriasis</td>\n",
       "      <td>skin_rash</td>\n",
       "      <td>joint_pain</td>\n",
       "      <td>skin_peeling</td>\n",
       "      <td>silver_like_dusting</td>\n",
       "      <td>small_dents_in_nails</td>\n",
       "      <td>inflammatory_nails</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4919</th>\n",
       "      <td>Impetigo</td>\n",
       "      <td>skin_rash</td>\n",
       "      <td>high_fever</td>\n",
       "      <td>blister</td>\n",
       "      <td>red_sore_around_nose</td>\n",
       "      <td>yellow_crust_ooze</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                      Disease             Symptom_1  \\\n",
       "4915  (vertigo) Paroymsal  Positional Vertigo              vomiting   \n",
       "4916                                     Acne             skin_rash   \n",
       "4917                  Urinary tract infection   burning_micturition   \n",
       "4918                                Psoriasis             skin_rash   \n",
       "4919                                 Impetigo             skin_rash   \n",
       "\n",
       "                Symptom_2             Symptom_3                  Symptom_4  \\\n",
       "4915             headache                nausea         spinning_movements   \n",
       "4916   pus_filled_pimples            blackheads                   scurring   \n",
       "4917   bladder_discomfort   foul_smell_of urine   continuous_feel_of_urine   \n",
       "4918           joint_pain          skin_peeling        silver_like_dusting   \n",
       "4919           high_fever               blister       red_sore_around_nose   \n",
       "\n",
       "                  Symptom_5            Symptom_6 Symptom_7 Symptom_8  \\\n",
       "4915        loss_of_balance         unsteadiness       NaN       NaN   \n",
       "4916                    NaN                  NaN       NaN       NaN   \n",
       "4917                    NaN                  NaN       NaN       NaN   \n",
       "4918   small_dents_in_nails   inflammatory_nails       NaN       NaN   \n",
       "4919      yellow_crust_ooze                  NaN       NaN       NaN   \n",
       "\n",
       "     Symptom_9 Symptom_10 Symptom_11 Symptom_12 Symptom_13 Symptom_14  \\\n",
       "4915       NaN        NaN        NaN        NaN        NaN        NaN   \n",
       "4916       NaN        NaN        NaN        NaN        NaN        NaN   \n",
       "4917       NaN        NaN        NaN        NaN        NaN        NaN   \n",
       "4918       NaN        NaN        NaN        NaN        NaN        NaN   \n",
       "4919       NaN        NaN        NaN        NaN        NaN        NaN   \n",
       "\n",
       "     Symptom_15 Symptom_16 Symptom_17  \n",
       "4915        NaN        NaN        NaN  \n",
       "4916        NaN        NaN        NaN  \n",
       "4917        NaN        NaN        NaN  \n",
       "4918        NaN        NaN        NaN  \n",
       "4919        NaN        NaN        NaN  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ds = pd.read_csv('dataset_kaggle.csv') \n",
    "ds.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "0b9aec82",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 417
    },
    "id": "0b9aec82",
    "outputId": "f8e7b859-b24d-4f49-bcb6-226a7ce3243c",
    "scrolled": true
   },
   "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>Symptom</th>\n",
       "      <th>weight</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>itching</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>skin_rash</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>nodal_skin_eruptions</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>continuous_sneezing</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>shivering</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>128</th>\n",
       "      <td>inflammatory_nails</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>129</th>\n",
       "      <td>blister</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>130</th>\n",
       "      <td>red_sore_around_nose</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>131</th>\n",
       "      <td>yellow_crust_ooze</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>132</th>\n",
       "      <td>prognosis</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>133 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                  Symptom  weight\n",
       "0                 itching       1\n",
       "1               skin_rash       3\n",
       "2    nodal_skin_eruptions       4\n",
       "3     continuous_sneezing       4\n",
       "4               shivering       5\n",
       "..                    ...     ...\n",
       "128    inflammatory_nails       2\n",
       "129               blister       4\n",
       "130  red_sore_around_nose       2\n",
       "131     yellow_crust_ooze       3\n",
       "132             prognosis       5\n",
       "\n",
       "[133 rows x 2 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ds_s2 = pd.read_csv('Symptom_severity2.csv')\n",
    "ds_s2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0e48f1d2",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "0e48f1d2",
    "outputId": "14e043dc-5059-4322-f199-dea4d3280043"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Disease          0\n",
       "Symptom_1        0\n",
       "Symptom_2        0\n",
       "Symptom_3        0\n",
       "Symptom_4      348\n",
       "Symptom_5     1206\n",
       "Symptom_6     1986\n",
       "Symptom_7     2652\n",
       "Symptom_8     2976\n",
       "Symptom_9     3228\n",
       "Symptom_10    3408\n",
       "Symptom_11    3726\n",
       "Symptom_12    4176\n",
       "Symptom_13    4416\n",
       "Symptom_14    4614\n",
       "Symptom_15    4680\n",
       "Symptom_16    4728\n",
       "Symptom_17    4848\n",
       "dtype: int64"
      ]
     },
     "execution_count": 8,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ds.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "402b8410",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "402b8410",
    "outputId": "677d5c92-91ca-4545-a4d9-c5469a21b188"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Disease', 'Symptom_1', 'Symptom_2', 'Symptom_3', 'Symptom_4',\n",
       "       'Symptom_5', 'Symptom_6', 'Symptom_7', 'Symptom_8', 'Symptom_9',\n",
       "       'Symptom_10', 'Symptom_11', 'Symptom_12', 'Symptom_13', 'Symptom_14',\n",
       "       'Symptom_15', 'Symptom_16', 'Symptom_17'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "col = ds.columns\n",
    "col"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "89231cf8",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "89231cf8",
    "outputId": "6c440f2f-b68f-4d30-93e9-2d682173058c"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Fungal infection', 'itching', ' skin_rash', ..., nan, nan, nan],\n",
       "      dtype=object)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = ds[col].to_numpy().flatten()\n",
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "8f6b6c68",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "8f6b6c68",
    "outputId": "1b11d208-defe-4ecf-e335-9ae09f5ceb08"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0            Fungal infection\n",
       "1                     itching\n",
       "2                   skin_rash\n",
       "3        nodal_skin_eruptions\n",
       "4         dischromic _patches\n",
       "                 ...         \n",
       "88555                     NaN\n",
       "88556                     NaN\n",
       "88557                     NaN\n",
       "88558                     NaN\n",
       "88559                     NaN\n",
       "Length: 88560, dtype: object"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s = pd.Series(data)\n",
    "s = s.str.strip()\n",
    "s"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "e8d8aab6",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "e8d8aab6",
    "outputId": "73c75f20-a923-44f5-c23e-5344b43aee28"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([['Fungal infection', 'itching', 'skin_rash', ..., nan, nan, nan],\n",
       "       ['Fungal infection', 'skin_rash', 'nodal_skin_eruptions', ...,\n",
       "        nan, nan, nan],\n",
       "       ['Fungal infection', 'itching', 'nodal_skin_eruptions', ..., nan,\n",
       "        nan, nan],\n",
       "       ...,\n",
       "       ['Urinary tract infection', 'burning_micturition',\n",
       "        'bladder_discomfort', ..., nan, nan, nan],\n",
       "       ['Psoriasis', 'skin_rash', 'joint_pain', ..., nan, nan, nan],\n",
       "       ['Impetigo', 'skin_rash', 'high_fever', ..., nan, nan, nan]],\n",
       "      dtype=object)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s = s.values.reshape(ds.shape)\n",
    "s"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "9611bfa9",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 444
    },
    "id": "9611bfa9",
    "outputId": "d6c5744a-9b0f-40a4-b5a1-d31fe8f5dc8f"
   },
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>Disease</th>\n",
       "      <th>Symptom_1</th>\n",
       "      <th>Symptom_2</th>\n",
       "      <th>Symptom_3</th>\n",
       "      <th>Symptom_4</th>\n",
       "      <th>Symptom_5</th>\n",
       "      <th>Symptom_6</th>\n",
       "      <th>Symptom_7</th>\n",
       "      <th>Symptom_8</th>\n",
       "      <th>Symptom_9</th>\n",
       "      <th>Symptom_10</th>\n",
       "      <th>Symptom_11</th>\n",
       "      <th>Symptom_12</th>\n",
       "      <th>Symptom_13</th>\n",
       "      <th>Symptom_14</th>\n",
       "      <th>Symptom_15</th>\n",
       "      <th>Symptom_16</th>\n",
       "      <th>Symptom_17</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4910</th>\n",
       "      <td>Hypothyroidism</td>\n",
       "      <td>fatigue</td>\n",
       "      <td>weight_gain</td>\n",
       "      <td>cold_hands_and_feets</td>\n",
       "      <td>mood_swings</td>\n",
       "      <td>lethargy</td>\n",
       "      <td>dizziness</td>\n",
       "      <td>puffy_face_and_eyes</td>\n",
       "      <td>enlarged_thyroid</td>\n",
       "      <td>brittle_nails</td>\n",
       "      <td>swollen_extremeties</td>\n",
       "      <td>depression</td>\n",
       "      <td>irritability</td>\n",
       "      <td>abnormal_menstruation</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4911</th>\n",
       "      <td>Hyperthyroidism</td>\n",
       "      <td>fatigue</td>\n",
       "      <td>mood_swings</td>\n",
       "      <td>weight_loss</td>\n",
       "      <td>restlessness</td>\n",
       "      <td>sweating</td>\n",
       "      <td>diarrhoea</td>\n",
       "      <td>fast_heart_rate</td>\n",
       "      <td>excessive_hunger</td>\n",
       "      <td>muscle_weakness</td>\n",
       "      <td>irritability</td>\n",
       "      <td>abnormal_menstruation</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4912</th>\n",
       "      <td>Hypoglycemia</td>\n",
       "      <td>vomiting</td>\n",
       "      <td>fatigue</td>\n",
       "      <td>anxiety</td>\n",
       "      <td>sweating</td>\n",
       "      <td>headache</td>\n",
       "      <td>nausea</td>\n",
       "      <td>blurred_and_distorted_vision</td>\n",
       "      <td>excessive_hunger</td>\n",
       "      <td>drying_and_tingling_lips</td>\n",
       "      <td>slurred_speech</td>\n",
       "      <td>irritability</td>\n",
       "      <td>palpitations</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4913</th>\n",
       "      <td>Osteoarthristis</td>\n",
       "      <td>joint_pain</td>\n",
       "      <td>neck_pain</td>\n",
       "      <td>knee_pain</td>\n",
       "      <td>hip_joint_pain</td>\n",
       "      <td>swelling_joints</td>\n",
       "      <td>painful_walking</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4914</th>\n",
       "      <td>Arthritis</td>\n",
       "      <td>muscle_weakness</td>\n",
       "      <td>stiff_neck</td>\n",
       "      <td>swelling_joints</td>\n",
       "      <td>movement_stiffness</td>\n",
       "      <td>painful_walking</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4915</th>\n",
       "      <td>(vertigo) Paroymsal  Positional Vertigo</td>\n",
       "      <td>vomiting</td>\n",
       "      <td>headache</td>\n",
       "      <td>nausea</td>\n",
       "      <td>spinning_movements</td>\n",
       "      <td>loss_of_balance</td>\n",
       "      <td>unsteadiness</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4916</th>\n",
       "      <td>Acne</td>\n",
       "      <td>skin_rash</td>\n",
       "      <td>pus_filled_pimples</td>\n",
       "      <td>blackheads</td>\n",
       "      <td>scurring</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4917</th>\n",
       "      <td>Urinary tract infection</td>\n",
       "      <td>burning_micturition</td>\n",
       "      <td>bladder_discomfort</td>\n",
       "      <td>foul_smell_of urine</td>\n",
       "      <td>continuous_feel_of_urine</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4918</th>\n",
       "      <td>Psoriasis</td>\n",
       "      <td>skin_rash</td>\n",
       "      <td>joint_pain</td>\n",
       "      <td>skin_peeling</td>\n",
       "      <td>silver_like_dusting</td>\n",
       "      <td>small_dents_in_nails</td>\n",
       "      <td>inflammatory_nails</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4919</th>\n",
       "      <td>Impetigo</td>\n",
       "      <td>skin_rash</td>\n",
       "      <td>high_fever</td>\n",
       "      <td>blister</td>\n",
       "      <td>red_sore_around_nose</td>\n",
       "      <td>yellow_crust_ooze</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                      Disease            Symptom_1  \\\n",
       "4910                           Hypothyroidism              fatigue   \n",
       "4911                          Hyperthyroidism              fatigue   \n",
       "4912                             Hypoglycemia             vomiting   \n",
       "4913                          Osteoarthristis           joint_pain   \n",
       "4914                                Arthritis      muscle_weakness   \n",
       "4915  (vertigo) Paroymsal  Positional Vertigo             vomiting   \n",
       "4916                                     Acne            skin_rash   \n",
       "4917                  Urinary tract infection  burning_micturition   \n",
       "4918                                Psoriasis            skin_rash   \n",
       "4919                                 Impetigo            skin_rash   \n",
       "\n",
       "               Symptom_2             Symptom_3                 Symptom_4  \\\n",
       "4910         weight_gain  cold_hands_and_feets               mood_swings   \n",
       "4911         mood_swings           weight_loss              restlessness   \n",
       "4912             fatigue               anxiety                  sweating   \n",
       "4913           neck_pain             knee_pain            hip_joint_pain   \n",
       "4914          stiff_neck       swelling_joints        movement_stiffness   \n",
       "4915            headache                nausea        spinning_movements   \n",
       "4916  pus_filled_pimples            blackheads                  scurring   \n",
       "4917  bladder_discomfort   foul_smell_of urine  continuous_feel_of_urine   \n",
       "4918          joint_pain          skin_peeling       silver_like_dusting   \n",
       "4919          high_fever               blister      red_sore_around_nose   \n",
       "\n",
       "                 Symptom_5           Symptom_6                     Symptom_7  \\\n",
       "4910              lethargy           dizziness           puffy_face_and_eyes   \n",
       "4911              sweating           diarrhoea               fast_heart_rate   \n",
       "4912              headache              nausea  blurred_and_distorted_vision   \n",
       "4913       swelling_joints     painful_walking                           NaN   \n",
       "4914       painful_walking                 NaN                           NaN   \n",
       "4915       loss_of_balance        unsteadiness                           NaN   \n",
       "4916                   NaN                 NaN                           NaN   \n",
       "4917                   NaN                 NaN                           NaN   \n",
       "4918  small_dents_in_nails  inflammatory_nails                           NaN   \n",
       "4919     yellow_crust_ooze                 NaN                           NaN   \n",
       "\n",
       "             Symptom_8                 Symptom_9           Symptom_10  \\\n",
       "4910  enlarged_thyroid             brittle_nails  swollen_extremeties   \n",
       "4911  excessive_hunger           muscle_weakness         irritability   \n",
       "4912  excessive_hunger  drying_and_tingling_lips       slurred_speech   \n",
       "4913               NaN                       NaN                  NaN   \n",
       "4914               NaN                       NaN                  NaN   \n",
       "4915               NaN                       NaN                  NaN   \n",
       "4916               NaN                       NaN                  NaN   \n",
       "4917               NaN                       NaN                  NaN   \n",
       "4918               NaN                       NaN                  NaN   \n",
       "4919               NaN                       NaN                  NaN   \n",
       "\n",
       "                 Symptom_11    Symptom_12             Symptom_13 Symptom_14  \\\n",
       "4910             depression  irritability  abnormal_menstruation        NaN   \n",
       "4911  abnormal_menstruation           NaN                    NaN        NaN   \n",
       "4912           irritability  palpitations                    NaN        NaN   \n",
       "4913                    NaN           NaN                    NaN        NaN   \n",
       "4914                    NaN           NaN                    NaN        NaN   \n",
       "4915                    NaN           NaN                    NaN        NaN   \n",
       "4916                    NaN           NaN                    NaN        NaN   \n",
       "4917                    NaN           NaN                    NaN        NaN   \n",
       "4918                    NaN           NaN                    NaN        NaN   \n",
       "4919                    NaN           NaN                    NaN        NaN   \n",
       "\n",
       "     Symptom_15 Symptom_16 Symptom_17  \n",
       "4910        NaN        NaN        NaN  \n",
       "4911        NaN        NaN        NaN  \n",
       "4912        NaN        NaN        NaN  \n",
       "4913        NaN        NaN        NaN  \n",
       "4914        NaN        NaN        NaN  \n",
       "4915        NaN        NaN        NaN  \n",
       "4916        NaN        NaN        NaN  \n",
       "4917        NaN        NaN        NaN  \n",
       "4918        NaN        NaN        NaN  \n",
       "4919        NaN        NaN        NaN  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ds_final = pd.DataFrame(s,columns=[ds.columns])\n",
    "ds_final.tail(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "4f99901b",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 307
    },
    "id": "4f99901b",
    "outputId": "c11754c4-40d5-49a5-da93-d95ea9188870"
   },
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>Disease</th>\n",
       "      <th>Symptom_1</th>\n",
       "      <th>Symptom_2</th>\n",
       "      <th>Symptom_3</th>\n",
       "      <th>Symptom_4</th>\n",
       "      <th>Symptom_5</th>\n",
       "      <th>Symptom_6</th>\n",
       "      <th>Symptom_7</th>\n",
       "      <th>Symptom_8</th>\n",
       "      <th>Symptom_9</th>\n",
       "      <th>Symptom_10</th>\n",
       "      <th>Symptom_11</th>\n",
       "      <th>Symptom_12</th>\n",
       "      <th>Symptom_13</th>\n",
       "      <th>Symptom_14</th>\n",
       "      <th>Symptom_15</th>\n",
       "      <th>Symptom_16</th>\n",
       "      <th>Symptom_17</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Fungal infection</td>\n",
       "      <td>itching</td>\n",
       "      <td>skin_rash</td>\n",
       "      <td>nodal_skin_eruptions</td>\n",
       "      <td>dischromic _patches</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Fungal infection</td>\n",
       "      <td>skin_rash</td>\n",
       "      <td>nodal_skin_eruptions</td>\n",
       "      <td>dischromic _patches</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",
       "      <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>Fungal infection</td>\n",
       "      <td>itching</td>\n",
       "      <td>nodal_skin_eruptions</td>\n",
       "      <td>dischromic _patches</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",
       "      <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>Fungal infection</td>\n",
       "      <td>itching</td>\n",
       "      <td>skin_rash</td>\n",
       "      <td>dischromic _patches</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",
       "      <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>Fungal infection</td>\n",
       "      <td>itching</td>\n",
       "      <td>skin_rash</td>\n",
       "      <td>nodal_skin_eruptions</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            Disease  Symptom_1             Symptom_2             Symptom_3  \\\n",
       "0  Fungal infection    itching             skin_rash  nodal_skin_eruptions   \n",
       "1  Fungal infection  skin_rash  nodal_skin_eruptions   dischromic _patches   \n",
       "2  Fungal infection    itching  nodal_skin_eruptions   dischromic _patches   \n",
       "3  Fungal infection    itching             skin_rash   dischromic _patches   \n",
       "4  Fungal infection    itching             skin_rash  nodal_skin_eruptions   \n",
       "\n",
       "             Symptom_4 Symptom_5 Symptom_6 Symptom_7 Symptom_8 Symptom_9  \\\n",
       "0  dischromic _patches         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",
       "  Symptom_10 Symptom_11 Symptom_12 Symptom_13 Symptom_14 Symptom_15  \\\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",
       "  Symptom_16 Symptom_17  \n",
       "0          0          0  \n",
       "1          0          0  \n",
       "2          0          0  \n",
       "3          0          0  \n",
       "4          0          0  "
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ds_final = ds_final.fillna(0)\n",
    "ds_final.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "12e0e147",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "12e0e147",
    "outputId": "bb393164-f016-4e2c-9551-bc0595fc38cc"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([['Fungal infection', 'itching', 'skin_rash', ..., 0, 0, 0],\n",
       "       ['Fungal infection', 'skin_rash', 'nodal_skin_eruptions', ..., 0,\n",
       "        0, 0],\n",
       "       ['Fungal infection', 'itching', 'nodal_skin_eruptions', ..., 0, 0,\n",
       "        0],\n",
       "       ...,\n",
       "       ['Urinary tract infection', 'burning_micturition',\n",
       "        'bladder_discomfort', ..., 0, 0, 0],\n",
       "       ['Psoriasis', 'skin_rash', 'joint_pain', ..., 0, 0, 0],\n",
       "       ['Impetigo', 'skin_rash', 'high_fever', ..., 0, 0, 0]],\n",
       "      dtype=object)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "vals = ds_final.values\n",
    "vals"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "45317192",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "45317192",
    "outputId": "71662600-f24c-4720-be18-d732d7228773"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['itching', 'skin_rash', 'nodal_skin_eruptions',\n",
       "       'continuous_sneezing', 'shivering', 'chills', 'joint_pain',\n",
       "       'stomach_pain', 'acidity', 'ulcers_on_tongue', 'muscle_wasting',\n",
       "       'vomiting', 'burning_micturition', 'spotting_urination', 'fatigue',\n",
       "       'weight_gain', 'anxiety', 'cold_hands_and_feets', 'mood_swings',\n",
       "       'weight_loss', 'restlessness', 'lethargy', 'patches_in_throat',\n",
       "       'irregular_sugar_level', 'cough', 'high_fever', 'sunken_eyes',\n",
       "       'breathlessness', 'sweating', 'dehydration', 'indigestion',\n",
       "       'headache', 'yellowish_skin', 'dark_urine', 'nausea',\n",
       "       'loss_of_appetite', 'pain_behind_the_eyes', 'back_pain',\n",
       "       'constipation', 'abdominal_pain', 'diarrhoea', 'mild_fever',\n",
       "       'yellow_urine', 'yellowing_of_eyes', 'acute_liver_failure',\n",
       "       'fluid_overload', 'swelling_of_stomach', 'swelled_lymph_nodes',\n",
       "       'malaise', 'blurred_and_distorted_vision', 'phlegm',\n",
       "       'throat_irritation', 'redness_of_eyes', 'sinus_pressure',\n",
       "       'runny_nose', 'congestion', 'chest_pain', 'weakness_in_limbs',\n",
       "       'fast_heart_rate', 'pain_during_bowel_movements',\n",
       "       'pain_in_anal_region', 'bloody_stool', 'irritation_in_anus',\n",
       "       'neck_pain', 'dizziness', 'cramps', 'bruising', 'obesity',\n",
       "       'swollen_legs', 'swollen_blood_vessels', 'puffy_face_and_eyes',\n",
       "       'enlarged_thyroid', 'brittle_nails', 'swollen_extremeties',\n",
       "       'excessive_hunger', 'extra_marital_contacts',\n",
       "       'drying_and_tingling_lips', 'slurred_speech', 'knee_pain',\n",
       "       'hip_joint_pain', 'muscle_weakness', 'stiff_neck',\n",
       "       'swelling_joints', 'movement_stiffness', 'spinning_movements',\n",
       "       'loss_of_balance', 'unsteadiness', 'weakness_of_one_body_side',\n",
       "       'loss_of_smell', 'bladder_discomfort', 'foul_smell_ofurine',\n",
       "       'continuous_feel_of_urine', 'passage_of_gases', 'internal_itching',\n",
       "       'toxic_look_(typhos)', 'depression', 'irritability', 'muscle_pain',\n",
       "       'altered_sensorium', 'red_spots_over_body', 'belly_pain',\n",
       "       'abnormal_menstruation', 'dischromic_patches',\n",
       "       'watering_from_eyes', 'increased_appetite', 'polyuria',\n",
       "       'family_history', 'mucoid_sputum', 'rusty_sputum',\n",
       "       'lack_of_concentration', 'visual_disturbances',\n",
       "       'receiving_blood_transfusion', 'receiving_unsterile_injections',\n",
       "       'coma', 'stomach_bleeding', 'distention_of_abdomen',\n",
       "       'history_of_alcohol_consumption', 'blood_in_sputum',\n",
       "       'prominent_veins_on_calf', 'palpitations', 'painful_walking',\n",
       "       'pus_filled_pimples', 'blackheads', 'scurring', 'skin_peeling',\n",
       "       'silver_like_dusting', 'small_dents_in_nails',\n",
       "       'inflammatory_nails', 'blister', 'red_sore_around_nose',\n",
       "       'yellow_crust_ooze', 'prognosis'], dtype=object)"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "symptoms = ds_s2['Symptom'].unique()\n",
    "symptoms"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "dc52a11f",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "dc52a11f",
    "outputId": "28dad07b-9edd-4ca9-831d-365a97808bdb",
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[['Fungal infection' 1 3 ... 0 0 0]\n",
      " ['Fungal infection' 3 4 ... 0 0 0]\n",
      " ['Fungal infection' 1 4 ... 0 0 0]\n",
      " ...\n",
      " ['Urinary tract infection' 6 4 ... 0 0 0]\n",
      " ['Psoriasis' 3 3 ... 0 0 0]\n",
      " ['Impetigo' 3 7 ... 0 0 0]]\n"
     ]
    }
   ],
   "source": [
    "for i in range(len(symptoms)):\n",
    "    vals[vals == symptoms[i]] = ds_s2[ds_s2['Symptom'] == symptoms[i]]['weight'].values[0]\n",
    "\n",
    "print(vals)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "82d75569",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 307
    },
    "id": "82d75569",
    "outputId": "2ec3a8f1-0f76-4156-a340-1ff2e25ae3c7"
   },
   "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>Disease</th>\n",
       "      <th>Symptom_1</th>\n",
       "      <th>Symptom_2</th>\n",
       "      <th>Symptom_3</th>\n",
       "      <th>Symptom_4</th>\n",
       "      <th>Symptom_5</th>\n",
       "      <th>Symptom_6</th>\n",
       "      <th>Symptom_7</th>\n",
       "      <th>Symptom_8</th>\n",
       "      <th>Symptom_9</th>\n",
       "      <th>Symptom_10</th>\n",
       "      <th>Symptom_11</th>\n",
       "      <th>Symptom_12</th>\n",
       "      <th>Symptom_13</th>\n",
       "      <th>Symptom_14</th>\n",
       "      <th>Symptom_15</th>\n",
       "      <th>Symptom_16</th>\n",
       "      <th>Symptom_17</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Fungal infection</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>dischromic _patches</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Fungal infection</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>dischromic _patches</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",
       "      <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>Fungal infection</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>dischromic _patches</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",
       "      <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>Fungal infection</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>dischromic _patches</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",
       "      <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>Fungal infection</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>4</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            Disease Symptom_1 Symptom_2            Symptom_3  \\\n",
       "0  Fungal infection         1         3                    4   \n",
       "1  Fungal infection         3         4  dischromic _patches   \n",
       "2  Fungal infection         1         4  dischromic _patches   \n",
       "3  Fungal infection         1         3  dischromic _patches   \n",
       "4  Fungal infection         1         3                    4   \n",
       "\n",
       "             Symptom_4 Symptom_5 Symptom_6 Symptom_7 Symptom_8 Symptom_9  \\\n",
       "0  dischromic _patches         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",
       "  Symptom_10 Symptom_11 Symptom_12 Symptom_13 Symptom_14 Symptom_15  \\\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",
       "  Symptom_16 Symptom_17  \n",
       "0          0          0  \n",
       "1          0          0  \n",
       "2          0          0  \n",
       "3          0          0  \n",
       "4          0          0  "
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d = pd.DataFrame(vals,columns=col)\n",
    "d.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "cd2e65d2",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 605
    },
    "id": "cd2e65d2",
    "outputId": "c0b93830-34c5-4d3d-ff79-e46f93d0a739",
    "scrolled": false
   },
   "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>Disease</th>\n",
       "      <th>Symptom_1</th>\n",
       "      <th>Symptom_2</th>\n",
       "      <th>Symptom_3</th>\n",
       "      <th>Symptom_4</th>\n",
       "      <th>Symptom_5</th>\n",
       "      <th>Symptom_6</th>\n",
       "      <th>Symptom_7</th>\n",
       "      <th>Symptom_8</th>\n",
       "      <th>Symptom_9</th>\n",
       "      <th>Symptom_10</th>\n",
       "      <th>Symptom_11</th>\n",
       "      <th>Symptom_12</th>\n",
       "      <th>Symptom_13</th>\n",
       "      <th>Symptom_14</th>\n",
       "      <th>Symptom_15</th>\n",
       "      <th>Symptom_16</th>\n",
       "      <th>Symptom_17</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Fungal infection</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>4</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",
       "      <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>Fungal infection</td>\n",
       "      <td>3</td>\n",
       "      <td>4</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",
       "      <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>Fungal infection</td>\n",
       "      <td>1</td>\n",
       "      <td>4</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",
       "      <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>Fungal infection</td>\n",
       "      <td>1</td>\n",
       "      <td>3</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",
       "      <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>Fungal infection</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>4</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <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>(vertigo) Paroymsal  Positional Vertigo</td>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>5</td>\n",
       "      <td>6</td>\n",
       "      <td>4</td>\n",
       "      <td>4</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",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4916</th>\n",
       "      <td>Acne</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4917</th>\n",
       "      <td>Urinary tract infection</td>\n",
       "      <td>6</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>6</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4918</th>\n",
       "      <td>Psoriasis</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>2</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",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4919</th>\n",
       "      <td>Impetigo</td>\n",
       "      <td>3</td>\n",
       "      <td>7</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>3</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4920 rows × 18 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                      Disease  Symptom_1  Symptom_2  \\\n",
       "0                            Fungal infection          1          3   \n",
       "1                            Fungal infection          3          4   \n",
       "2                            Fungal infection          1          4   \n",
       "3                            Fungal infection          1          3   \n",
       "4                            Fungal infection          1          3   \n",
       "...                                       ...        ...        ...   \n",
       "4915  (vertigo) Paroymsal  Positional Vertigo          5          3   \n",
       "4916                                     Acne          3          2   \n",
       "4917                  Urinary tract infection          6          4   \n",
       "4918                                Psoriasis          3          3   \n",
       "4919                                 Impetigo          3          7   \n",
       "\n",
       "      Symptom_3  Symptom_4  Symptom_5  Symptom_6  Symptom_7  Symptom_8  \\\n",
       "0             4          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             4          0          0          0          0          0   \n",
       "...         ...        ...        ...        ...        ...        ...   \n",
       "4915          5          6          4          4          0          0   \n",
       "4916          2          2          0          0          0          0   \n",
       "4917          0          6          0          0          0          0   \n",
       "4918          3          2          2          2          0          0   \n",
       "4919          4          2          3          0          0          0   \n",
       "\n",
       "      Symptom_9  Symptom_10  Symptom_11  Symptom_12  Symptom_13  Symptom_14  \\\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           0           0           0           0   \n",
       "4919          0           0           0           0           0           0   \n",
       "\n",
       "      Symptom_15  Symptom_16  Symptom_17  \n",
       "0              0           0           0  \n",
       "1              0           0           0  \n",
       "2              0           0           0  \n",
       "3              0           0           0  \n",
       "4              0           0           0  \n",
       "...          ...         ...         ...  \n",
       "4915           0           0           0  \n",
       "4916           0           0           0  \n",
       "4917           0           0           0  \n",
       "4918           0           0           0  \n",
       "4919           0           0           0  \n",
       "\n",
       "[4920 rows x 18 columns]"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d = d.replace('dischromic _patches', 0)\n",
    "d = d.replace('spotting_ urination',0)\n",
    "ds2 = d.replace('foul_smell_of urine',0)\n",
    "ds2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "048c0f03",
   "metadata": {
    "id": "048c0f03",
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "(ds2[col]==0).all\n",
    "ds2['Disease'].value_counts\n",
    "ds2['Disease'].unique()\n",
    "data = ds2.iloc[:,1:].values        # X\n",
    "lables = ds2['Disease'].values       #  y     \n",
    "# print(data)\n",
    "# print(lables)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "4eaae333",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "4eaae333",
    "outputId": "bf598603-2c14-40ad-ca0e-1db9750a8568"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "i have cold,headache,throatpain\n",
      "['i', 'have', 'cold', 'headache', 'throatpain']\n",
      "text_input :  ['cold', 'headache', 'throatpain']\n"
     ]
    }
   ],
   "source": [
    "#  User input\n",
    "# --------------\n",
    "\n",
    "import nltk\n",
    "#nltk.download('stopwords')\n",
    "from nltk.corpus import stopwords\n",
    "#nltk.download('punkt')\n",
    "en_stops = set(stopwords.words('english'))\n",
    "\n",
    "unwanted_char = [',','.','/','?','!',':',';','\"','(',')']\n",
    "t = input()\n",
    "for i in unwanted_char:\n",
    "    t = t.replace(i,' ')\n",
    "text = list(map(str,t.strip().split()))\n",
    "print(text)\n",
    "\n",
    "text_input = []\n",
    "for word in text: \n",
    "    if word not in en_stops:\n",
    "        text_input.append(word)\n",
    "\n",
    "print('text_input : ',text_input)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "7840147f",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "7840147f",
    "outputId": "d5926716-c7c4-45f1-f3f6-eeff2f747834"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "word:  cold\n",
      "The cosine similarity between : itching and : cold is: 16.666666666666664\n",
      "word:  cold\n",
      "The cosine similarity between : skin_rash and : cold is: 0.0\n",
      "word:  cold\n",
      "The cosine similarity between : nodal_skin_eruptions and : cold is: 34.29971702850176\n",
      "word:  cold\n",
      "The cosine similarity between : continuous_sneezing and : cold is: 23.42606428329091\n",
      "word:  cold\n",
      "The cosine similarity between : shivering and : cold is: 0.0\n",
      "word:  cold\n",
      "The cosine similarity between : chills and : cold is: 53.03300858899106\n",
      "word:  cold\n",
      "The cosine similarity between : joint_pain and : cold is: 13.36306209562122\n",
      "word:  cold\n",
      "The cosine similarity between : stomach_pain and : cold is: 26.72612419124244\n",
      "word:  cold\n",
      "The cosine similarity between : acidity and : cold is: 33.33333333333333\n",
      "word:  cold\n",
      "The cosine similarity between : ulcers_on_tongue and : cold is: 39.22322702763681\n",
      "word:  cold\n",
      "The cosine similarity between : muscle_wasting and : cold is: 25.0\n",
      "word:  cold\n",
      "The cosine similarity between : vomiting and : cold is: 15.811388300841896\n",
      "word:  cold\n",
      "The cosine similarity between : burning_micturition and : cold is: 15.249857033260467\n",
      "word:  cold\n",
      "The cosine similarity between : spotting_urination and : cold is: 16.222142113076256\n",
      "word:  cold\n",
      "The cosine similarity between : fatigue and : cold is: 0.0\n",
      "word:  cold\n",
      "The cosine similarity between : weight_gain and : cold is: 0.0\n",
      "word:  cold\n",
      "The cosine similarity between : anxiety and : cold is: 0.0\n",
      "word:  cold\n",
      "The cosine similarity between : cold_hands_and_feets and : cold is: 47.43416490252569\n",
      "word:  cold\n",
      "The cosine similarity between : mood_swings and : cold is: 38.72983346207417\n",
      "word:  cold\n",
      "The cosine similarity between : weight_loss and : cold is: 27.735009811261456\n",
      "word:  cold\n",
      "The cosine similarity between : restlessness and : cold is: 8.111071056538128\n",
      "word:  cold\n",
      "The cosine similarity between : lethargy and : cold is: 17.677669529663685\n",
      "word:  cold\n",
      "The cosine similarity between : patches_in_throat and : cold is: 18.569533817705185\n",
      "word:  cold\n",
      "The cosine similarity between : irregular_sugar_level and : cold is: 20.604084592303355\n",
      "word:  cold\n",
      "The cosine similarity between : cough and : cold is: 44.721359549995796\n",
      "word:  cold\n",
      "The cosine similarity between : high_fever and : cold is: 0.0\n",
      "word:  cold\n",
      "The cosine similarity between : sunken_eyes and : cold is: 0.0\n",
      "word:  cold\n",
      "The cosine similarity between : breathlessness and : cold is: 8.838834764831843\n",
      "word:  cold\n",
      "The cosine similarity between : sweating and : cold is: 0.0\n",
      "word:  cold\n",
      "The cosine similarity between : dehydration and : cold is: 41.60251471689219\n",
      "word:  cold\n",
      "The cosine similarity between : indigestion and : cold is: 22.941573387056174\n",
      "word:  cold\n",
      "The cosine similarity between : headache and : cold is: 26.72612419124244\n",
      "word:  cold\n",
      "The cosine similarity between : yellowish_skin and : cold is: 33.54101966249684\n",
      "word:  cold\n",
      "The cosine similarity between : dark_urine and : cold is: 14.433756729740645\n",
      "word:  cold\n",
      "The cosine similarity between : nausea and : cold is: 0.0\n",
      "word:  cold\n",
      "The cosine similarity between : loss_of_appetite and : cold is: 28.34733547569204\n",
      "word:  cold\n",
      "The cosine similarity between : pain_behind_the_eyes and : cold is: 7.53778361444409\n",
      "word:  cold\n",
      "The cosine similarity between : back_pain and : cold is: 15.07556722888818\n",
      "word:  cold\n",
      "The cosine similarity between : constipation and : cold is: 33.54101966249684\n",
      "word:  cold\n",
      "The cosine similarity between : abdominal_pain and : cold is: 30.618621784789728\n",
      "word:  cold\n",
      "The cosine similarity between : diarrhoea and : cold is: 27.735009811261456\n",
      "word:  cold\n",
      "The cosine similarity between : mild_fever and : cold is: 28.86751345948129\n",
      "word:  cold\n",
      "The cosine similarity between : yellow_urine and : cold is: 37.5\n",
      "word:  cold\n",
      "The cosine similarity between : yellowing_of_eyes and : cold is: 35.92106040535498\n",
      "word:  cold\n",
      "The cosine similarity between : acute_liver_failure and : cold is: 24.659848095803593\n",
      "word:  cold\n",
      "The cosine similarity between : fluid_overload and : cold is: 67.08203932499369\n",
      "word:  cold\n",
      "The cosine similarity between : swelling_of_stomach and : cold is: 48.112522432468815\n",
      "word:  cold\n",
      "The cosine similarity between : swelled_lymph_nodes and : cold is: 49.319696191607186\n",
      "word:  cold\n",
      "The cosine similarity between : malaise and : cold is: 16.666666666666664\n",
      "word:  cold\n",
      "The cosine similarity between : blurred_and_distorted_vision and : cold is: 42.443734381358276\n",
      "word:  cold\n",
      "The cosine similarity between : phlegm and : cold is: 20.412414523193153\n",
      "word:  cold\n",
      "The cosine similarity between : throat_irritation and : cold is: 14.9071198499986\n",
      "word:  cold\n",
      "The cosine similarity between : redness_of_eyes and : cold is: 16.90308509457033\n",
      "word:  cold\n",
      "The cosine similarity between : sinus_pressure and : cold is: 0.0\n",
      "word:  cold\n",
      "The cosine similarity between : runny_nose and : cold is: 12.5\n",
      "word:  cold\n",
      "The cosine similarity between : congestion and : cold is: 40.08918628686366\n",
      "word:  cold\n",
      "The cosine similarity between : chest_pain and : cold is: 15.811388300841896\n",
      "word:  cold\n",
      "The cosine similarity between : weakness_in_limbs and : cold is: 8.980265101338745\n",
      "word:  cold\n",
      "The cosine similarity between : fast_heart_rate and : cold is: 0.0\n",
      "word:  cold\n",
      "The cosine similarity between : pain_during_bowel_movements and : cold is: 28.005601680560194\n",
      "word:  cold\n",
      "The cosine similarity between : pain_in_anal_region and : cold is: 14.285714285714285\n",
      "word:  cold\n",
      "The cosine similarity between : bloody_stool and : cold is: 68.64064729836443\n",
      "word:  cold\n",
      "The cosine similarity between : irritation_in_anus and : cold is: 7.53778361444409\n",
      "word:  cold\n",
      "The cosine similarity between : neck_pain and : cold is: 15.07556722888818\n",
      "word:  cold\n",
      "The cosine similarity between : dizziness and : cold is: 12.909944487358056\n",
      "word:  cold\n",
      "The cosine similarity between : cramps and : cold is: 20.412414523193153\n",
      "word:  cold\n",
      "The cosine similarity between : bruising and : cold is: 0.0\n",
      "word:  cold\n",
      "The cosine similarity between : obesity and : cold is: 18.89822365046136\n",
      "word:  cold\n",
      "The cosine similarity between : swollen_legs and : cold is: 42.640143271122085\n",
      "word:  cold\n",
      "The cosine similarity between : swollen_blood_vessels and : cold is: 52.075564392329554\n",
      "word:  cold\n",
      "The cosine similarity between : puffy_face_and_eyes and : cold is: 15.617376188860607\n",
      "word:  cold\n",
      "The cosine similarity between : enlarged_thyroid and : cold is: 42.640143271122085\n",
      "word:  cold\n",
      "The cosine similarity between : brittle_nails and : cold is: 22.941573387056174\n",
      "word:  cold\n",
      "The cosine similarity between : swollen_extremeties and : cold is: 22.360679774997898\n",
      "word:  cold\n",
      "The cosine similarity between : excessive_hunger and : cold is: 9.128709291752768\n",
      "word:  cold\n",
      "The cosine similarity between : extra_marital_contacts and : cold is: 27.735009811261456\n",
      "word:  cold\n",
      "The cosine similarity between : drying_and_tingling_lips and : cold is: 25.0\n",
      "word:  cold\n",
      "The cosine similarity between : slurred_speech and : cold is: 30.618621784789728\n",
      "word:  cold\n",
      "The cosine similarity between : knee_pain and : cold is: 0.0\n",
      "word:  cold\n",
      "The cosine similarity between : hip_joint_pain and : cold is: 9.805806756909202\n",
      "word:  cold\n",
      "The cosine similarity between : muscle_weakness and : cold is: 19.245008972987527\n",
      "word:  cold\n",
      "The cosine similarity between : stiff_neck and : cold is: 14.433756729740645\n",
      "word:  cold\n",
      "The cosine similarity between : swelling_joints and : cold is: 31.277162108561217\n",
      "word:  cold\n",
      "The cosine similarity between : movement_stiffness and : cold is: 8.111071056538128\n",
      "word:  cold\n",
      "The cosine similarity between : spinning_movements and : cold is: 8.111071056538128\n",
      "word:  cold\n",
      "The cosine similarity between : loss_of_balance and : cold is: 50.0\n",
      "word:  cold\n",
      "The cosine similarity between : unsteadiness and : cold is: 10.660035817780521\n",
      "word:  cold\n",
      "The cosine similarity between : weakness_of_one_body_side and : cold is: 31.008683647302114\n",
      "word:  cold\n",
      "The cosine similarity between : loss_of_smell and : cold is: 46.423834544262974\n",
      "word:  cold\n",
      "The cosine similarity between : bladder_discomfort and : cold is: 66.14378277661476\n",
      "word:  cold\n",
      "The cosine similarity between : foul_smell_ofurine and : cold is: 42.87464628562721\n",
      "word:  cold\n",
      "The cosine similarity between : continuous_feel_of_urine and : cold is: 32.82660821493064\n",
      "word:  cold\n",
      "The cosine similarity between : passage_of_gases and : cold is: 7.905694150420948\n",
      "word:  cold\n",
      "The cosine similarity between : internal_itching and : cold is: 18.257418583505537\n",
      "word:  cold\n",
      "The cosine similarity between : toxic_look_(typhos) and : cold is: 50.709255283710995\n",
      "word:  cold\n",
      "The cosine similarity between : depression and : cold is: 26.72612419124244\n",
      "word:  cold\n",
      "The cosine similarity between : irritability and : cold is: 9.44911182523068\n",
      "word:  cold\n",
      "The cosine similarity between : muscle_pain and : cold is: 30.15113445777636\n",
      "word:  cold\n",
      "The cosine similarity between : altered_sensorium and : cold is: 28.867513459481287\n",
      "word:  cold\n",
      "The cosine similarity between : red_spots_over_body and : cold is: 40.03203845127178\n",
      "word:  cold\n",
      "The cosine similarity between : belly_pain and : cold is: 28.86751345948129\n",
      "word:  cold\n",
      "The cosine similarity between : abnormal_menstruation and : cold is: 23.42606428329091\n",
      "word:  cold\n",
      "The cosine similarity between : dischromic_patches and : cold is: 45.64354645876384\n",
      "word:  cold\n",
      "The cosine similarity between : watering_from_eyes and : cold is: 9.44911182523068\n",
      "word:  cold\n",
      "The cosine similarity between : increased_appetite and : cold is: 16.222142113076256\n",
      "word:  cold\n",
      "The cosine similarity between : polyuria and : cold is: 35.35533905932737\n",
      "word:  cold\n",
      "The cosine similarity between : family_history and : cold is: 23.570226039551585\n",
      "word:  cold\n",
      "The cosine similarity between : mucoid_sputum and : cold is: 32.73268353539886\n",
      "word:  cold\n",
      "The cosine similarity between : rusty_sputum and : cold is: 0.0\n",
      "word:  cold\n",
      "The cosine similarity between : lack_of_concentration and : cold is: 52.174919474995086\n",
      "word:  cold\n",
      "The cosine similarity between : visual_disturbances and : cold is: 26.940795304016234\n",
      "word:  cold\n",
      "The cosine similarity between : receiving_blood_transfusion and : cold is: 41.20816918460671\n",
      "word:  cold\n",
      "The cosine similarity between : receiving_unsterile_injections and : cold is: 20.851441405707476\n",
      "word:  cold\n",
      "The cosine similarity between : coma and : cold is: 50.0\n",
      "word:  cold\n",
      "The cosine similarity between : stomach_bleeding and : cold is: 47.14045207910317\n",
      "word:  cold\n",
      "The cosine similarity between : distention_of_abdomen and : cold is: 38.12464258315117\n",
      "word:  cold\n",
      "The cosine similarity between : history_of_alcohol_consumption and : cold is: 55.90169943749474\n",
      "word:  cold\n",
      "The cosine similarity between : fluid_overload and : cold is: 67.08203932499369\n",
      "word:  cold\n",
      "The cosine similarity between : blood_in_sputum and : cold is: 43.64357804719848\n",
      "word:  cold\n",
      "The cosine similarity between : prominent_veins_on_calf and : cold is: 29.17299829957891\n",
      "word:  cold\n",
      "The cosine similarity between : palpitations and : cold is: 22.360679774997898\n",
      "word:  cold\n",
      "The cosine similarity between : painful_walking and : cold is: 20.851441405707476\n",
      "word:  cold\n",
      "The cosine similarity between : pus_filled_pimples and : cold is: 32.44428422615251\n",
      "word:  cold\n",
      "The cosine similarity between : blackheads and : cold is: 43.30127018922194\n",
      "word:  cold\n",
      "The cosine similarity between : scurring and : cold is: 15.811388300841896\n",
      "word:  cold\n",
      "The cosine similarity between : skin_peeling and : cold is: 11.785113019775793\n",
      "word:  cold\n",
      "The cosine similarity between : silver_like_dusting and : cold is: 26.111648393354674\n",
      "word:  cold\n",
      "The cosine similarity between : small_dents_in_nails and : cold is: 28.86751345948129\n",
      "word:  cold\n",
      "The cosine similarity between : inflammatory_nails and : cold is: 26.51650429449553\n",
      "word:  cold\n",
      "The cosine similarity between : blister and : cold is: 18.89822365046136\n",
      "word:  cold\n",
      "The cosine similarity between : red_sore_around_nose and : cold is: 35.35533905932737\n",
      "word:  cold\n",
      "The cosine similarity between : yellow_crust_ooze and : cold is: 55.708601453115556\n",
      "word:  cold\n",
      "The cosine similarity between : prognosis and : cold is: 27.735009811261456\n",
      "word:  headache\n",
      "The cosine similarity between : itching and : headache is: 26.72612419124244\n",
      "word:  headache\n",
      "The cosine similarity between : skin_rash and : headache is: 32.23291856101521\n",
      "word:  headache\n",
      "The cosine similarity between : nodal_skin_eruptions and : headache is: 22.917462425705278\n",
      "word:  headache\n",
      "The cosine similarity between : continuous_sneezing and : headache is: 20.869596778242055\n",
      "word:  headache\n",
      "The cosine similarity between : shivering and : headache is: 32.23291856101521\n",
      "word:  headache\n",
      "The cosine similarity between : chills and : headache is: 28.34733547569204\n",
      "word:  headache\n",
      "The cosine similarity between : joint_pain and : headache is: 14.285714285714288\n",
      "word:  headache\n",
      "The cosine similarity between : stomach_pain and : headache is: 50.0\n",
      "word:  headache\n",
      "The cosine similarity between : acidity and : headache is: 35.63483225498992\n",
      "word:  headache\n",
      "The cosine similarity between : ulcers_on_tongue and : headache is: 26.20712091804796\n",
      "word:  headache\n",
      "The cosine similarity between : muscle_wasting and : headache is: 33.40765523905305\n",
      "word:  headache\n",
      "The cosine similarity between : vomiting and : headache is: 0.0\n",
      "word:  headache\n",
      "The cosine similarity between : burning_micturition and : headache is: 4.075695729696112\n",
      "word:  headache\n",
      "The cosine similarity between : spotting_urination and : headache is: 8.671099695241201\n",
      "word:  headache\n",
      "The cosine similarity between : fatigue and : headache is: 40.40610178208843\n",
      "word:  headache\n",
      "The cosine similarity between : weight_gain and : headache is: 41.403933560541255\n",
      "word:  headache\n",
      "The cosine similarity between : anxiety and : headache is: 40.40610178208843\n",
      "word:  headache\n",
      "The cosine similarity between : cold_hands_and_feets and : headache is: 59.16079783099616\n",
      "word:  headache\n",
      "The cosine similarity between : mood_swings and : headache is: 6.900655593423541\n",
      "word:  headache\n",
      "The cosine similarity between : weight_loss and : headache is: 29.649972666444047\n",
      "word:  headache\n",
      "The cosine similarity between : restlessness and : headache is: 26.013299085723602\n",
      "word:  headache\n",
      "The cosine similarity between : lethargy and : headache is: 56.69467095138408\n",
      "word:  headache\n",
      "The cosine similarity between : patches_in_throat and : headache is: 54.59208336840117\n",
      "word:  headache\n",
      "The cosine similarity between : irregular_sugar_level and : headache is: 36.71115491071762\n",
      "word:  headache\n",
      "The cosine similarity between : cough and : headache is: 35.85685828003181\n",
      "word:  headache\n",
      "The cosine similarity between : high_fever and : headache is: 57.14285714285715\n",
      "word:  headache\n",
      "The cosine similarity between : sunken_eyes and : headache is: 34.99271061118826\n",
      "word:  headache\n",
      "The cosine similarity between : breathlessness and : headache is: 47.2455591261534\n",
      "word:  headache\n",
      "The cosine similarity between : sweating and : headache is: 37.79644730092272\n",
      "word:  headache\n",
      "The cosine similarity between : dehydration and : headache is: 59.29994533288809\n",
      "word:  headache\n",
      "The cosine similarity between : indigestion and : headache is: 18.394180184548972\n",
      "word:  headache\n",
      "The cosine similarity between : headache and : headache is: 100.0\n",
      "----------------\n",
      "Found a word with cosine distance > 75 : headache with original word: headache\n",
      "--------------\n",
      "\n",
      "word:  headache\n",
      "The cosine similarity between : yellowish_skin and : headache is: 23.904572186687872\n",
      "word:  headache\n",
      "The cosine similarity between : dark_urine and : headache is: 38.57583749052298\n",
      "word:  headache\n",
      "The cosine similarity between : nausea and : headache is: 56.69467095138408\n",
      "word:  headache\n",
      "The cosine similarity between : loss_of_appetite and : headache is: 30.304576336566324\n",
      "word:  headache\n",
      "The cosine similarity between : pain_behind_the_eyes and : headache is: 60.43672230190354\n",
      "word:  headache\n",
      "The cosine similarity between : back_pain and : headache is: 40.29114820126901\n",
      "word:  headache\n",
      "The cosine similarity between : constipation and : headache is: 17.928429140015904\n",
      "word:  headache\n",
      "The cosine similarity between : abdominal_pain and : headache is: 38.188130791298676\n",
      "word:  headache\n",
      "The cosine similarity between : diarrhoea and : headache is: 66.71243849949911\n",
      "word:  headache\n",
      "The cosine similarity between : mild_fever and : headache is: 38.57583749052298\n",
      "word:  headache\n",
      "The cosine similarity between : yellow_urine and : headache is: 26.72612419124244\n",
      "word:  headache\n",
      "The cosine similarity between : yellowing_of_eyes and : headache is: 28.800921644239157\n",
      "word:  headache\n",
      "The cosine similarity between : acute_liver_failure and : headache is: 48.331225268012155\n",
      "word:  headache\n",
      "The cosine similarity between : fluid_overload and : headache is: 35.85685828003181\n",
      "word:  headache\n",
      "The cosine similarity between : swelling_of_stomach and : headache is: 36.00411499115478\n",
      "word:  headache\n",
      "The cosine similarity between : swelled_lymph_nodes and : headache is: 43.93747751637468\n",
      "word:  headache\n",
      "The cosine similarity between : malaise and : headache is: 53.45224838248488\n",
      "word:  headache\n",
      "The cosine similarity between : blurred_and_distorted_vision and : headache is: 32.410186177608225\n",
      "word:  headache\n",
      "The cosine similarity between : phlegm and : headache is: 43.64357804719848\n",
      "word:  headache\n",
      "The cosine similarity between : throat_irritation and : headache is: 23.904572186687872\n",
      "word:  headache\n",
      "The cosine similarity between : redness_of_eyes and : headache is: 40.65785563073631\n",
      "word:  headache\n",
      "The cosine similarity between : sinus_pressure and : headache is: 18.89822365046136\n",
      "word:  headache\n",
      "The cosine similarity between : runny_nose and : headache is: 13.36306209562122\n",
      "word:  headache\n",
      "The cosine similarity between : congestion and : headache is: 21.42857142857143\n",
      "word:  headache\n",
      "The cosine similarity between : chest_pain and : headache is: 59.16079783099616\n",
      "word:  headache\n",
      "The cosine similarity between : weakness_in_limbs and : headache is: 28.800921644239157\n",
      "word:  headache\n",
      "The cosine similarity between : fast_heart_rate and : headache is: 55.82905262390825\n",
      "word:  headache\n",
      "The cosine similarity between : pain_during_bowel_movements and : headache is: 33.68165348543039\n",
      "word:  headache\n",
      "The cosine similarity between : pain_in_anal_region and : headache is: 30.5441419328485\n",
      "word:  headache\n",
      "The cosine similarity between : bloody_stool and : headache is: 5.241424183609592\n",
      "word:  headache\n",
      "The cosine similarity between : irritation_in_anus and : headache is: 16.116459280507605\n",
      "word:  headache\n",
      "The cosine similarity between : neck_pain and : headache is: 40.29114820126901\n",
      "word:  headache\n",
      "The cosine similarity between : dizziness and : headache is: 20.701966780270627\n",
      "word:  headache\n",
      "The cosine similarity between : cramps and : headache is: 32.73268353539886\n",
      "word:  headache\n",
      "The cosine similarity between : bruising and : headache is: 0.0\n",
      "word:  headache\n",
      "The cosine similarity between : obesity and : headache is: 20.203050891044214\n",
      "word:  headache\n",
      "The cosine similarity between : swollen_legs and : headache is: 22.79211529192759\n",
      "word:  headache\n",
      "The cosine similarity between : swollen_blood_vessels and : headache is: 24.356115022372737\n",
      "word:  headache\n",
      "The cosine similarity between : puffy_face_and_eyes and : headache is: 50.08703226778093\n",
      "word:  headache\n",
      "The cosine similarity between : enlarged_thyroid and : headache is: 56.980288229818974\n",
      "word:  headache\n",
      "The cosine similarity between : brittle_nails and : headache is: 24.52557357939863\n",
      "word:  headache\n",
      "The cosine similarity between : swollen_extremeties and : headache is: 39.84095364447979\n",
      "word:  headache\n",
      "The cosine similarity between : excessive_hunger and : headache is: 53.674504012169336\n",
      "word:  headache\n",
      "The cosine similarity between : extra_marital_contacts and : headache is: 44.47495899966608\n",
      "word:  headache\n",
      "The cosine similarity between : drying_and_tingling_lips and : headache is: 13.36306209562122\n",
      "word:  headache\n",
      "The cosine similarity between : slurred_speech and : headache is: 54.5544725589981\n",
      "word:  headache\n",
      "The cosine similarity between : knee_pain and : headache is: 44.47495899966608\n",
      "word:  headache\n",
      "The cosine similarity between : hip_joint_pain and : headache is: 20.965696734438367\n",
      "word:  headache\n",
      "The cosine similarity between : muscle_weakness and : headache is: 46.29100498862757\n",
      "word:  headache\n",
      "The cosine similarity between : stiff_neck and : headache is: 23.14550249431379\n",
      "word:  headache\n",
      "The cosine similarity between : swelling_joints and : headache is: 11.145564251507057\n",
      "word:  headache\n",
      "The cosine similarity between : movement_stiffness and : headache is: 26.013299085723602\n",
      "word:  headache\n",
      "The cosine similarity between : spinning_movements and : headache is: 17.342199390482403\n",
      "word:  headache\n",
      "The cosine similarity between : loss_of_balance and : headache is: 37.41657386773941\n",
      "word:  headache\n",
      "The cosine similarity between : unsteadiness and : headache is: 39.88620176087328\n",
      "word:  headache\n",
      "The cosine similarity between : weakness_of_one_body_side and : headache is: 39.779612647907754\n",
      "word:  headache\n",
      "The cosine similarity between : loss_of_smell and : headache is: 9.925833339709303\n",
      "word:  headache\n",
      "The cosine similarity between : bladder_discomfort and : headache is: 40.40610178208843\n",
      "word:  headache\n",
      "The cosine similarity between : foul_smell_ofurine and : headache is: 18.333969940564224\n",
      "word:  headache\n",
      "The cosine similarity between : continuous_feel_of_urine and : headache is: 24.565184222025874\n",
      "word:  headache\n",
      "The cosine similarity between : passage_of_gases and : headache is: 42.25771273642583\n",
      "word:  headache\n",
      "The cosine similarity between : internal_itching and : headache is: 34.156502553198656\n",
      "word:  headache\n",
      "The cosine similarity between : toxic_look_(typhos) and : headache is: 13.55261854357877\n",
      "word:  headache\n",
      "The cosine similarity between : depression and : headache is: 35.714285714285715\n",
      "word:  headache\n",
      "The cosine similarity between : irritability and : headache is: 10.101525445522107\n",
      "word:  headache\n",
      "The cosine similarity between : muscle_pain and : headache is: 40.29114820126901\n",
      "word:  headache\n",
      "The cosine similarity between : altered_sensorium and : headache is: 46.29100498862757\n",
      "word:  headache\n",
      "The cosine similarity between : red_spots_over_body and : headache is: 25.677629550654775\n",
      "word:  headache\n",
      "The cosine similarity between : belly_pain and : headache is: 30.860669992418387\n",
      "word:  headache\n",
      "The cosine similarity between : abnormal_menstruation and : headache is: 33.39135484518729\n",
      "word:  headache\n",
      "The cosine similarity between : dischromic_patches and : headache is: 58.55400437691198\n",
      "word:  headache\n",
      "The cosine similarity between : watering_from_eyes and : headache is: 40.40610178208843\n",
      "word:  headache\n",
      "The cosine similarity between : increased_appetite and : headache is: 60.69769786668841\n",
      "word:  headache\n",
      "The cosine similarity between : polyuria and : headache is: 18.89822365046136\n",
      "word:  headache\n",
      "The cosine similarity between : family_history and : headache is: 25.197631533948485\n",
      "word:  headache\n",
      "The cosine similarity between : mucoid_sputum and : headache is: 11.664236870396087\n",
      "word:  headache\n",
      "The cosine similarity between : rusty_sputum and : headache is: 0.0\n",
      "word:  headache\n",
      "The cosine similarity between : lack_of_concentration and : headache is: 35.85685828003181\n",
      "word:  headache\n",
      "The cosine similarity between : visual_disturbances and : headache is: 38.40122885898555\n",
      "word:  headache\n",
      "The cosine similarity between : receiving_blood_transfusion and : headache is: 29.368923928574098\n",
      "word:  headache\n",
      "The cosine similarity between : receiving_unsterile_injections and : headache is: 33.436692754521175\n",
      "word:  headache\n",
      "The cosine similarity between : coma and : headache is: 40.08918628686366\n",
      "word:  headache\n",
      "The cosine similarity between : stomach_bleeding and : headache is: 62.9940788348712\n",
      "word:  headache\n",
      "The cosine similarity between : distention_of_abdomen and : headache is: 32.605565837568896\n",
      "word:  headache\n",
      "The cosine similarity between : history_of_alcohol_consumption and : headache is: 23.904572186687872\n",
      "word:  headache\n",
      "The cosine similarity between : fluid_overload and : headache is: 35.85685828003181\n",
      "word:  headache\n",
      "The cosine similarity between : blood_in_sputum and : headache is: 5.832118435198043\n",
      "word:  headache\n",
      "The cosine similarity between : prominent_veins_on_calf and : headache is: 27.28884114549077\n",
      "word:  headache\n",
      "The cosine similarity between : palpitations and : headache is: 23.904572186687872\n",
      "word:  headache\n",
      "The cosine similarity between : painful_walking and : headache is: 22.291128503014114\n",
      "word:  headache\n",
      "The cosine similarity between : pus_filled_pimples and : headache is: 21.677749238103\n",
      "word:  headache\n",
      "The cosine similarity between : blackheads and : headache is: 77.15167498104596\n",
      "----------------\n",
      "Found a word with cosine distance > 75 : blackheads with original word: headache\n",
      "--------------\n",
      "\n",
      "word:  headache\n",
      "The cosine similarity between : scurring and : headache is: 8.451542547285166\n",
      "word:  headache\n",
      "The cosine similarity between : skin_peeling and : headache is: 25.197631533948485\n",
      "word:  headache\n",
      "The cosine similarity between : silver_like_dusting and : headache is: 23.26210525996177\n",
      "word:  headache\n",
      "The cosine similarity between : small_dents_in_nails and : headache is: 27.003086243366088\n",
      "word:  headache\n",
      "The cosine similarity between : inflammatory_nails and : headache is: 28.34733547569204\n",
      "word:  headache\n",
      "The cosine similarity between : blister and : headache is: 20.203050891044214\n",
      "word:  headache\n",
      "The cosine similarity between : red_sore_around_nose and : headache is: 37.79644730092272\n",
      "word:  headache\n",
      "The cosine similarity between : yellow_crust_ooze and : headache is: 24.81458334927326\n",
      "word:  headache\n",
      "The cosine similarity between : prognosis and : headache is: 0.0\n",
      "word:  throatpain\n",
      "The cosine similarity between : itching and : throatpain is: 53.45224838248488\n",
      "word:  throatpain\n",
      "The cosine similarity between : skin_rash and : throatpain is: 48.349377841522816\n",
      "word:  throatpain\n",
      "The cosine similarity between : nodal_skin_eruptions and : throatpain is: 59.58540230683372\n",
      "word:  throatpain\n",
      "The cosine similarity between : continuous_sneezing and : throatpain is: 41.73919355648411\n",
      "word:  throatpain\n",
      "The cosine similarity between : shivering and : throatpain is: 40.29114820126901\n",
      "word:  throatpain\n",
      "The cosine similarity between : chills and : throatpain is: 18.89822365046136\n",
      "word:  throatpain\n",
      "The cosine similarity between : joint_pain and : throatpain is: 71.42857142857143\n",
      "word:  throatpain\n",
      "The cosine similarity between : stomach_pain and : throatpain is: 78.57142857142858\n",
      "----------------\n",
      "Found a word with cosine distance > 75 : stomach_pain with original word: throatpain\n",
      "--------------\n",
      "\n",
      "word:  throatpain\n",
      "The cosine similarity between : acidity and : throatpain is: 53.45224838248488\n",
      "word:  throatpain\n",
      "The cosine similarity between : ulcers_on_tongue and : throatpain is: 36.689969285267146\n",
      "word:  throatpain\n",
      "The cosine similarity between : muscle_wasting and : throatpain is: 40.08918628686366\n",
      "word:  throatpain\n",
      "The cosine similarity between : vomiting and : throatpain is: 50.709255283710995\n",
      "word:  throatpain\n",
      "The cosine similarity between : burning_micturition and : throatpain is: 57.05974021574557\n",
      "word:  throatpain\n",
      "The cosine similarity between : spotting_urination and : throatpain is: 78.03989725717081\n",
      "----------------\n",
      "Found a word with cosine distance > 75 : spotting_urination with original word: throatpain\n",
      "--------------\n",
      "\n",
      "word:  throatpain\n",
      "The cosine similarity between : fatigue and : throatpain is: 50.50762722761054\n",
      "word:  throatpain\n",
      "The cosine similarity between : weight_gain and : throatpain is: 55.20524474738833\n",
      "word:  throatpain\n",
      "The cosine similarity between : anxiety and : throatpain is: 60.60915267313265\n",
      "word:  throatpain\n",
      "The cosine similarity between : cold_hands_and_feets and : throatpain is: 42.25771273642583\n",
      "word:  throatpain\n",
      "The cosine similarity between : mood_swings and : throatpain is: 27.602622373694164\n",
      "word:  throatpain\n",
      "The cosine similarity between : weight_loss and : throatpain is: 37.062465833055064\n",
      "word:  throatpain\n",
      "The cosine similarity between : restlessness and : throatpain is: 17.342199390482403\n",
      "word:  throatpain\n",
      "The cosine similarity between : lethargy and : throatpain is: 56.69467095138408\n",
      "word:  throatpain\n",
      "The cosine similarity between : patches_in_throat and : throatpain is: 84.36958338752908\n",
      "----------------\n",
      "Found a word with cosine distance > 75 : patches_in_throat with original word: throatpain\n",
      "--------------\n",
      "\n",
      "word:  throatpain\n",
      "The cosine similarity between : irregular_sugar_level and : throatpain is: 33.04003941964586\n",
      "word:  throatpain\n",
      "The cosine similarity between : cough and : throatpain is: 23.904572186687872\n",
      "word:  throatpain\n",
      "The cosine similarity between : high_fever and : throatpain is: 28.571428571428577\n",
      "word:  throatpain\n",
      "The cosine similarity between : sunken_eyes and : throatpain is: 11.664236870396087\n",
      "word:  throatpain\n",
      "The cosine similarity between : breathlessness and : throatpain is: 33.071891388307385\n",
      "word:  throatpain\n",
      "The cosine similarity between : sweating and : throatpain is: 56.69467095138408\n",
      "word:  throatpain\n",
      "The cosine similarity between : dehydration and : throatpain is: 66.71243849949911\n",
      "word:  throatpain\n",
      "The cosine similarity between : indigestion and : throatpain is: 49.05114715879726\n",
      "word:  throatpain\n",
      "The cosine similarity between : headache and : throatpain is: 42.85714285714286\n",
      "word:  throatpain\n",
      "The cosine similarity between : yellowish_skin and : throatpain is: 29.880715233359844\n",
      "word:  throatpain\n",
      "The cosine similarity between : dark_urine and : throatpain is: 46.29100498862758\n",
      "word:  throatpain\n",
      "The cosine similarity between : nausea and : throatpain is: 47.2455591261534\n",
      "word:  throatpain\n",
      "The cosine similarity between : loss_of_appetite and : throatpain is: 55.55838995037159\n",
      "word:  throatpain\n",
      "The cosine similarity between : pain_behind_the_eyes and : throatpain is: 44.32026302139592\n",
      "word:  throatpain\n",
      "The cosine similarity between : back_pain and : throatpain is: 56.40760748177662\n",
      "word:  throatpain\n",
      "The cosine similarity between : constipation and : throatpain is: 77.68985960673558\n",
      "----------------\n",
      "Found a word with cosine distance > 75 : constipation with original word: throatpain\n",
      "--------------\n",
      "\n",
      "word:  throatpain\n",
      "The cosine similarity between : abdominal_pain and : throatpain is: 65.46536707079773\n",
      "word:  throatpain\n",
      "The cosine similarity between : diarrhoea and : throatpain is: 66.71243849949911\n",
      "word:  throatpain\n",
      "The cosine similarity between : mild_fever and : throatpain is: 15.430334996209194\n",
      "word:  throatpain\n",
      "The cosine similarity between : yellow_urine and : throatpain is: 26.72612419124244\n",
      "word:  throatpain\n",
      "The cosine similarity between : yellowing_of_eyes and : throatpain is: 19.200614429492774\n",
      "word:  throatpain\n",
      "The cosine similarity between : acute_liver_failure and : throatpain is: 43.93747751637468\n",
      "word:  throatpain\n",
      "The cosine similarity between : fluid_overload and : throatpain is: 35.85685828003181\n",
      "word:  throatpain\n",
      "The cosine similarity between : swelling_of_stomach and : throatpain is: 46.29100498862757\n",
      "word:  throatpain\n",
      "The cosine similarity between : swelled_lymph_nodes and : throatpain is: 17.574991006549872\n",
      "word:  throatpain\n",
      "The cosine similarity between : malaise and : throatpain is: 44.5435403187374\n",
      "word:  throatpain\n",
      "The cosine similarity between : blurred_and_distorted_vision and : throatpain is: 51.85629788417315\n",
      "word:  throatpain\n",
      "The cosine similarity between : phlegm and : throatpain is: 21.82178902359924\n",
      "word:  throatpain\n",
      "The cosine similarity between : throat_irritation and : throatpain is: 87.65009801785554\n",
      "----------------\n",
      "Found a word with cosine distance > 75 : throat_irritation with original word: throatpain\n",
      "--------------\n",
      "\n",
      "word:  throatpain\n",
      "The cosine similarity between : redness_of_eyes and : throatpain is: 13.55261854357877\n",
      "word:  throatpain\n",
      "The cosine similarity between : sinus_pressure and : throatpain is: 23.6227795630767\n",
      "word:  throatpain\n",
      "The cosine similarity between : runny_nose and : throatpain is: 33.40765523905305\n",
      "word:  throatpain\n",
      "The cosine similarity between : congestion and : throatpain is: 50.0\n",
      "word:  throatpain\n",
      "The cosine similarity between : chest_pain and : throatpain is: 67.61234037828133\n",
      "word:  throatpain\n",
      "The cosine similarity between : weakness_in_limbs and : throatpain is: 28.800921644239157\n",
      "word:  throatpain\n",
      "The cosine similarity between : fast_heart_rate and : throatpain is: 69.78631577988531\n",
      "word:  throatpain\n",
      "The cosine similarity between : pain_during_bowel_movements and : throatpain is: 48.65127725673278\n",
      "word:  throatpain\n",
      "The cosine similarity between : pain_in_anal_region and : throatpain is: 61.088283865697\n",
      "word:  throatpain\n",
      "The cosine similarity between : bloody_stool and : throatpain is: 31.448545101657547\n",
      "word:  throatpain\n",
      "The cosine similarity between : irritation_in_anus and : throatpain is: 72.52406676228424\n",
      "word:  throatpain\n",
      "The cosine similarity between : neck_pain and : throatpain is: 48.349377841522816\n",
      "word:  throatpain\n",
      "The cosine similarity between : dizziness and : throatpain is: 20.701966780270627\n",
      "word:  throatpain\n",
      "The cosine similarity between : cramps and : throatpain is: 43.64357804719848\n",
      "word:  throatpain\n",
      "The cosine similarity between : bruising and : throatpain is: 33.806170189140666\n",
      "word:  throatpain\n",
      "The cosine similarity between : obesity and : throatpain is: 40.40610178208843\n",
      "word:  throatpain\n",
      "The cosine similarity between : swollen_legs and : throatpain is: 11.396057645963795\n",
      "word:  throatpain\n",
      "The cosine similarity between : swollen_blood_vessels and : throatpain is: 13.917780012784423\n",
      "word:  throatpain\n",
      "The cosine similarity between : puffy_face_and_eyes and : throatpain is: 25.043516133890463\n",
      "word:  throatpain\n",
      "The cosine similarity between : enlarged_thyroid and : throatpain is: 56.980288229818974\n",
      "word:  throatpain\n",
      "The cosine similarity between : brittle_nails and : throatpain is: 61.31393394849658\n",
      "word:  throatpain\n",
      "The cosine similarity between : swollen_extremeties and : throatpain is: 31.87276291558383\n",
      "word:  throatpain\n",
      "The cosine similarity between : excessive_hunger and : throatpain is: 19.518001458970662\n",
      "word:  throatpain\n",
      "The cosine similarity between : extra_marital_contacts and : throatpain is: 77.83117824941563\n",
      "----------------\n",
      "Found a word with cosine distance > 75 : extra_marital_contacts with original word: throatpain\n",
      "--------------\n",
      "\n",
      "word:  throatpain\n",
      "The cosine similarity between : drying_and_tingling_lips and : throatpain is: 46.770717334674266\n",
      "word:  throatpain\n",
      "The cosine similarity between : slurred_speech and : throatpain is: 21.82178902359924\n",
      "word:  throatpain\n",
      "The cosine similarity between : knee_pain and : throatpain is: 44.47495899966608\n",
      "word:  throatpain\n",
      "The cosine similarity between : hip_joint_pain and : throatpain is: 68.1385143869247\n",
      "word:  throatpain\n",
      "The cosine similarity between : muscle_weakness and : throatpain is: 15.430334996209192\n",
      "word:  throatpain\n",
      "The cosine similarity between : stiff_neck and : throatpain is: 30.860669992418387\n",
      "word:  throatpain\n",
      "The cosine similarity between : swelling_joints and : throatpain is: 39.0094748802747\n",
      "word:  throatpain\n",
      "The cosine similarity between : movement_stiffness and : throatpain is: 34.684398780964806\n",
      "word:  throatpain\n",
      "The cosine similarity between : spinning_movements and : throatpain is: 43.355498476206\n",
      "word:  throatpain\n",
      "The cosine similarity between : loss_of_balance and : throatpain is: 37.41657386773941\n",
      "word:  throatpain\n",
      "The cosine similarity between : unsteadiness and : throatpain is: 39.88620176087328\n",
      "word:  throatpain\n",
      "The cosine similarity between : weakness_of_one_body_side and : throatpain is: 26.51974176527184\n",
      "word:  throatpain\n",
      "The cosine similarity between : loss_of_smell and : throatpain is: 9.925833339709303\n",
      "word:  throatpain\n",
      "The cosine similarity between : bladder_discomfort and : throatpain is: 45.456864504849484\n",
      "word:  throatpain\n",
      "The cosine similarity between : foul_smell_ofurine and : throatpain is: 22.917462425705278\n",
      "word:  throatpain\n",
      "The cosine similarity between : continuous_feel_of_urine and : throatpain is: 38.6024323488978\n",
      "word:  throatpain\n",
      "The cosine similarity between : passage_of_gases and : throatpain is: 33.806170189140666\n",
      "word:  throatpain\n",
      "The cosine similarity between : internal_itching and : throatpain is: 68.31300510639731\n",
      "word:  throatpain\n",
      "The cosine similarity between : toxic_look_(typhos) and : throatpain is: 49.69293465978882\n",
      "word:  throatpain\n",
      "The cosine similarity between : depression and : throatpain is: 35.714285714285715\n",
      "word:  throatpain\n",
      "The cosine similarity between : irritability and : throatpain is: 60.60915267313265\n",
      "word:  throatpain\n",
      "The cosine similarity between : muscle_pain and : throatpain is: 40.29114820126901\n",
      "word:  throatpain\n",
      "The cosine similarity between : altered_sensorium and : throatpain is: 46.29100498862757\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "word:  throatpain\n",
      "The cosine similarity between : red_spots_over_body and : throatpain is: 34.23683940087303\n",
      "word:  throatpain\n",
      "The cosine similarity between : belly_pain and : throatpain is: 38.57583749052298\n",
      "word:  throatpain\n",
      "The cosine similarity between : abnormal_menstruation and : throatpain is: 75.1305484016714\n",
      "----------------\n",
      "Found a word with cosine distance > 75 : abnormal_menstruation with original word: throatpain\n",
      "--------------\n",
      "\n",
      "word:  throatpain\n",
      "The cosine similarity between : dischromic_patches and : throatpain is: 53.674504012169336\n",
      "word:  throatpain\n",
      "The cosine similarity between : watering_from_eyes and : throatpain is: 45.456864504849484\n",
      "word:  throatpain\n",
      "The cosine similarity between : increased_appetite and : throatpain is: 60.69769786668841\n",
      "word:  throatpain\n",
      "The cosine similarity between : polyuria and : throatpain is: 56.69467095138408\n",
      "word:  throatpain\n",
      "The cosine similarity between : family_history and : throatpain is: 56.6946709513841\n",
      "word:  throatpain\n",
      "The cosine similarity between : mucoid_sputum and : throatpain is: 29.160592175990217\n",
      "word:  throatpain\n",
      "The cosine similarity between : rusty_sputum and : throatpain is: 34.18817293789139\n",
      "word:  throatpain\n",
      "The cosine similarity between : lack_of_concentration and : throatpain is: 63.74552583116766\n",
      "word:  throatpain\n",
      "The cosine similarity between : visual_disturbances and : throatpain is: 48.001536073731934\n",
      "word:  throatpain\n",
      "The cosine similarity between : receiving_blood_transfusion and : throatpain is: 55.06673236607642\n",
      "word:  throatpain\n",
      "The cosine similarity between : receiving_unsterile_injections and : throatpain is: 44.58225700602823\n",
      "word:  throatpain\n",
      "The cosine similarity between : coma and : throatpain is: 40.08918628686366\n",
      "word:  throatpain\n",
      "The cosine similarity between : stomach_bleeding and : throatpain is: 50.39526306789697\n",
      "word:  throatpain\n",
      "The cosine similarity between : distention_of_abdomen and : throatpain is: 57.05974021574557\n",
      "word:  throatpain\n",
      "The cosine similarity between : history_of_alcohol_consumption and : throatpain is: 59.76143046671969\n",
      "word:  throatpain\n",
      "The cosine similarity between : fluid_overload and : throatpain is: 35.85685828003181\n",
      "word:  throatpain\n",
      "The cosine similarity between : blood_in_sputum and : throatpain is: 40.824829046386306\n",
      "word:  throatpain\n",
      "The cosine similarity between : prominent_veins_on_calf and : throatpain is: 54.57768229098154\n",
      "word:  throatpain\n",
      "The cosine similarity between : palpitations and : throatpain is: 83.66600265340756\n",
      "----------------\n",
      "Found a word with cosine distance > 75 : palpitations with original word: throatpain\n",
      "--------------\n",
      "\n",
      "word:  throatpain\n",
      "The cosine similarity between : painful_walking and : throatpain is: 50.15503913178176\n",
      "word:  throatpain\n",
      "The cosine similarity between : pus_filled_pimples and : throatpain is: 21.677749238103\n",
      "word:  throatpain\n",
      "The cosine similarity between : blackheads and : throatpain is: 38.57583749052298\n",
      "word:  throatpain\n",
      "The cosine similarity between : scurring and : throatpain is: 33.806170189140666\n",
      "word:  throatpain\n",
      "The cosine similarity between : skin_peeling and : throatpain is: 31.4970394174356\n",
      "word:  throatpain\n",
      "The cosine similarity between : silver_like_dusting and : throatpain is: 32.56694736394648\n",
      "word:  throatpain\n",
      "The cosine similarity between : small_dents_in_nails and : throatpain is: 42.433421239575274\n",
      "word:  throatpain\n",
      "The cosine similarity between : inflammatory_nails and : throatpain is: 66.14378277661477\n",
      "word:  throatpain\n",
      "The cosine similarity between : blister and : throatpain is: 40.40610178208843\n",
      "word:  throatpain\n",
      "The cosine similarity between : red_sore_around_nose and : throatpain is: 37.79644730092272\n",
      "word:  throatpain\n",
      "The cosine similarity between : yellow_crust_ooze and : throatpain is: 29.777500019127906\n",
      "word:  throatpain\n",
      "The cosine similarity between : prognosis and : throatpain is: 44.47495899966608\n",
      "\n",
      "\n",
      "Sym :  ['headache', 'blackheads', 'stomach_pain', 'spotting_urination', 'patches_in_throat', 'constipation', 'throat_irritation', 'extra_marital_contacts', 'abnormal_menstruation', 'palpitations']\n"
     ]
    }
   ],
   "source": [
    "\n",
    "# Find cosine sim\n",
    "\n",
    "\n",
    "def word2vec(word):\n",
    "    from collections import Counter\n",
    "    from math import sqrt\n",
    "\n",
    "    # count the characters in word\n",
    "    cw = Counter(word)\n",
    "    # precomputes a set of the different characters\n",
    "    sw = set(cw)\n",
    "    # precomputes the \"length\" of the word vector\n",
    "    lw = sqrt(sum(c*c for c in cw.values()))\n",
    "\n",
    "    # return a tuple\n",
    "    return cw, sw, lw\n",
    "\n",
    "def cosdis(v1, v2):\n",
    "    # which characters are common to the two words?\n",
    "    common = v1[1].intersection(v2[1])\n",
    "    # by definition of cosine distance we have\n",
    "    return sum(v1[0][ch]*v2[0][ch] for ch in common)/v1[2]/v2[2]\n",
    "\n",
    "# text_input = list(map(str,input(\"ENTER: \").split(',')))\n",
    "sym = []\n",
    "for i in text_input:\n",
    "    for j in ds_s2['Symptom']:\n",
    "        list_A = [i]             # User Input Symptoms\n",
    "        list_B = [j]             # Symptoms list from dataset\n",
    "\n",
    "        threshold = 0.75     # if needed\n",
    "        \n",
    "        for key in list_A: \n",
    "            for word in list_B:\n",
    "                print('word: ',key)\n",
    "                try:\n",
    "                    # print(key)\n",
    "                    # print(word)\n",
    "                    res = cosdis(word2vec(word), word2vec(key))\n",
    "                    # print(res)\n",
    "                    print(\"The cosine similarity between : {} and : {} is: {}\".format(word, key, res*100))\n",
    "                    if res > threshold:\n",
    "                        print('----------------')\n",
    "                        print(\"Found a word with cosine distance > 75 : {} with original word: {}\".format(word, key))\n",
    "                        print('--------------\\n')\n",
    "                        sym.append(word)\n",
    "                        \n",
    "                except IndexError:\n",
    "                    pass\n",
    "\n",
    "print(\"\\n\\nSym : \",sym)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "f40602ad",
   "metadata": {
    "id": "f40602ad",
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "a = np.array(ds_s2['Symptom'])\n",
    "b = np.array(ds_s2['weight'])\n",
    "# print(a)\n",
    "# print('----------------')\n",
    "# print(b)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "d0284a1a",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "d0284a1a",
    "outputId": "90d24017-0adf-4182-a68d-0cdbb5c6e23c"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3 2 5 6 6 4 4 5 6 4 \n",
      "\n",
      "psym :  [3, 2, 5, 6, 6, 4, 4, 5, 6, 4, 0, 0, 0, 0, 0, 0, 0]\n"
     ]
    }
   ],
   "source": [
    "for i in range(len(sym)):\n",
    "    for j in range(len(ds_s2['Symptom'])):\n",
    "        if sym[i] == a[j]:\n",
    "            sym[i] = b[j]\n",
    "            print(sym[i],end=' ')\n",
    "\n",
    "\n",
    "psym = sym\n",
    "for i in range(17-len(psym)):\n",
    "    psym.append(0)\n",
    "\n",
    "print('\\n\\npsym : ',psym)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "56d59260",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "56d59260",
    "outputId": "e1402253-d435-4d7a-bac6-7d11685a1849"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Typhoid'], dtype=object)"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model = DecisionTreeClassifier()\n",
    "model.fit(data,lables)\n",
    "prediction = model.predict([psym])\n",
    "prediction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "l3oYglQLOTSj",
   "metadata": {
    "id": "l3oYglQLOTSj"
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "251afcef",
   "metadata": {
    "id": "251afcef"
   },
   "source": [
    "## Accuracy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "719110dc",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "719110dc",
    "outputId": "e022866e-46d5-4037-891c-489b35b1080c"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9898373983739838"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(data, lables, shuffle=True, test_size=0.2)\n",
    "model.fit(X_train, y_train)\n",
    "predict = model.predict(X_test)\n",
    "score = accuracy_score(y_test,predict)\n",
    "score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "SSYeXXNvHvpS",
   "metadata": {
    "id": "SSYeXXNvHvpS"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "ICD_Codes = pd.read_excel(\"/content/ICD_codes.xlsx\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "wE_sl9IGIKGb",
   "metadata": {
    "id": "wE_sl9IGIKGb"
   },
   "outputs": [],
   "source": [
    "ICD_head = ICD_Codes.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "uEe1tzD_INTG",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "uEe1tzD_INTG",
    "outputId": "381634b1-a7e5-4507-e5c4-527952c654d6"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pandas.core.frame.DataFrame"
      ]
     },
     "execution_count": 48,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(ICD_head)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ylh0MUklO9T0",
   "metadata": {
    "id": "ylh0MUklO9T0"
   },
   "outputs": [],
   "source": [
    "pred_lst = prediction.tolist()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3s2LmvwtPBRY",
   "metadata": {
    "id": "3s2LmvwtPBRY"
   },
   "outputs": [],
   "source": [
    "#prd_lst = ['impetigo']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "E9MFl22QPI2x",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "E9MFl22QPI2x",
    "outputId": "b9daf5c5-9e04-4dbc-e8f4-8c943de7f3bf"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Fungal infection']\n"
     ]
    }
   ],
   "source": [
    "print(pred_lst)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "IoJVHroaIQBO",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "IoJVHroaIQBO",
    "outputId": "e104e341-4248-466f-ce02-f13ffca34319"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Gastroenteritis and colitis due to radiation K520\n"
     ]
    }
   ],
   "source": [
    "for ent in ICD_Codes.iterrows():\n",
    "    for ent_disease in pred_lst:\n",
    "        #print(ent[1][1])\n",
    "        if (ent_disease) in (ent[1][1]):\n",
    "            print (ent[1][1],ent[1][0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "udVkXKIcKsRI",
   "metadata": {
    "id": "udVkXKIcKsRI"
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "heartdisease_final.ipynb",
   "provenance": []
  },
  "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": "3.8.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}