{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.feature_selection import mutual_info_classif\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "data = pd.read_csv('pcos_cleaned.csv')\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "y = data[\"PCOS (Y/N)\"]\n",
    "X = data.drop([\"PCOS (Y/N)\"], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   Feature  Mutual Information\n",
      "38        Follicle No. (R)            0.240107\n",
      "37        Follicle No. (L)            0.198132\n",
      "33         Fast food (Y/N)            0.095965\n",
      "29        hair growth(Y/N)            0.094711\n",
      "30    Skin darkening (Y/N)            0.094472\n",
      "28        Weight gain(Y/N)            0.091420\n",
      "10      Cycle length(days)            0.074662\n",
      "23              AMH(ng/mL)            0.066603\n",
      "18                  FSH/LH            0.065068\n",
      "24              PRL(ng/mL)            0.061647\n",
      "9               Cycle(R/I)            0.052702\n",
      "13        No. of abortions            0.028979\n",
      "7         RR (breaths/min)            0.028374\n",
      "20             Waist(inch)            0.026092\n",
      "12           Pregnant(Y/N)            0.024060\n",
      "32            Pimples(Y/N)            0.023784\n",
      "39    Avg. F size (L) (mm)            0.022989\n",
      "22             TSH (mIU/L)            0.022234\n",
      "31          Hair loss(Y/N)            0.019978\n",
      "40    Avg. F size (R) (mm)            0.019886\n",
      "16             FSH(mIU/mL)            0.019688\n",
      "1                Age (yrs)            0.019323\n",
      "0               Unnamed: 0            0.017659\n",
      "17              LH(mIU/mL)            0.017577\n",
      "4                      BMI            0.015053\n",
      "25          Vit D3 (ng/mL)            0.014276\n",
      "6         Pulse rate(bpm)             0.013627\n",
      "34       Reg.Exercise(Y/N)            0.009540\n",
      "36    BP _Diastolic (mmHg)            0.008657\n",
      "14    I   beta-HCG(mIU/mL)            0.007298\n",
      "35     BP _Systolic (mmHg)            0.006151\n",
      "41        Endometrium (mm)            0.004497\n",
      "3              Height(Cm)             0.000000\n",
      "5              Blood Group            0.000000\n",
      "8                 Hb(g/dl)            0.000000\n",
      "2              Weight (Kg)            0.000000\n",
      "11   Marraige Status (Yrs)            0.000000\n",
      "15  II    beta-HCG(mIU/mL)            0.000000\n",
      "19               Hip(inch)            0.000000\n",
      "21         Waist:Hip Ratio            0.000000\n",
      "27              RBS(mg/dl)            0.000000\n",
      "26              PRG(ng/mL)            0.000000\n"
     ]
    }
   ],
   "source": [
    "# Calculate Mutual Information\n",
    "mi = mutual_info_classif(X, y)\n",
    "\n",
    "# Create a DataFrame to show feature importance\n",
    "mi_df = pd.DataFrame({'Feature': X.columns, 'Mutual Information': mi})\n",
    "\n",
    "# Sort features by mutual information value\n",
    "mi_df = mi_df.sort_values(by='Mutual Information', ascending=False)\n",
    "\n",
    "print(mi_df)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   PCOS (Y/N)  Follicle No. (R)  Follicle No. (L)  Skin darkening (Y/N)  \\\n",
      "0           0                 3                 3                     0   \n",
      "1           0                 5                 3                     0   \n",
      "2           1                15                13                     0   \n",
      "3           0                 2                 2                     0   \n",
      "4           0                 4                 3                     0   \n",
      "\n",
      "   hair growth(Y/N)  Weight gain(Y/N)  Cycle length(days)  AMH(ng/mL)  \\\n",
      "0                 0                 0                   5        2.07   \n",
      "1                 0                 0                   5        1.53   \n",
      "2                 0                 0                   5        6.63   \n",
      "3                 0                 0                   5        1.22   \n",
      "4                 0                 0                   5        2.26   \n",
      "\n",
      "   Fast food (Y/N)  Cycle(R/I)    FSH/LH  PRL(ng/mL)  Pimples(Y/N)  Age (yrs)  \\\n",
      "0              1.0           0  2.160326       45.16             0         28   \n",
      "1              0.0           0  6.174312       20.09             0         36   \n",
      "2              1.0           0  6.295455       10.52             1         33   \n",
      "3              0.0           0  3.415254       36.90             0         37   \n",
      "4              0.0           0  4.422222       30.09             0         25   \n",
      "\n",
      "    BMI  \n",
      "0  19.3  \n",
      "1  24.9  \n",
      "2  25.3  \n",
      "3  29.7  \n",
      "4  20.1  \n"
     ]
    }
   ],
   "source": [
    "pcos_df = pd.read_csv('pcos_cleaned.csv')\n",
    "pcos_df.columns = pcos_df.columns.str.strip()  # Remove any leading/trailing whitespace\n",
    "selected_features = ['PCOS (Y/N)', 'Follicle No. (R)', 'Follicle No. (L)', \n",
    "                     'Skin darkening (Y/N)', 'hair growth(Y/N)', 'Weight gain(Y/N)', \n",
    "                     'Cycle length(days)', 'AMH(ng/mL)', 'Fast food (Y/N)', \n",
    "                     'Cycle(R/I)', 'FSH/LH', 'PRL(ng/mL)', 'Pimples(Y/N)', \n",
    "                     'Age (yrs)', 'BMI']\n",
    "\n",
    "new_dataset = pcos_df[selected_features]\n",
    "\n",
    "# Save the new dataset to a CSV file if needed\n",
    "new_dataset.to_csv('new_pcos_dataset.csv', index=False)\n",
    "\n",
    "# Display the new dataset\n",
    "print(new_dataset.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}