{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "677c5e27",
   "metadata": {},
   "source": [
    "Starting with MLE and logistic regression model\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2520b517",
   "metadata": {},
   "source": [
    "Prerequisites\n",
    "Make sure you have the necessary Python libraries installed:\n",
    "pip install numpy pandas scikit-learn scipy matplotlib statsmodels\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "id": "2e1f9bfa",
   "metadata": {},
   "outputs": [
    {
     "ename": "FileNotFoundError",
     "evalue": "[Errno 2] No such file or directory: '../data/lung_SUVperc_COMBINED.mat'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
      "File \u001b[1;32mc:\\Users\\zahra\\anaconda3\\Lib\\site-packages\\scipy\\io\\matlab\\_mio.py:39\u001b[0m, in \u001b[0;36m_open_file\u001b[1;34m(file_like, appendmat, mode)\u001b[0m\n\u001b[0;32m     38\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m---> 39\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mopen\u001b[39m(file_like, mode), \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[0;32m     40\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mOSError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m     41\u001b[0m     \u001b[38;5;66;03m# Probably \"not found\"\u001b[39;00m\n",
      "\u001b[1;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: '../data/lung_SUVperc_COMBINED'",
      "\nDuring handling of the above exception, another exception occurred:\n",
      "\u001b[1;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[69], line 9\u001b[0m\n\u001b[0;32m      7\u001b[0m \u001b[38;5;66;03m# Load the data\u001b[39;00m\n\u001b[0;32m      8\u001b[0m data_path \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m../data/\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m----> 9\u001b[0m suv_data \u001b[38;5;241m=\u001b[39m loadmat(data_path \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mlung_SUVperc_COMBINED\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m     10\u001b[0m lung_suv_selected \u001b[38;5;241m=\u001b[39m suv_data[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mlung_SUVperc_COMBINED\u001b[39m\u001b[38;5;124m'\u001b[39m][\u001b[38;5;241m0\u001b[39m:\u001b[38;5;241m58\u001b[39m, :]  \u001b[38;5;66;03m# Shape: (58, 17, 100)\u001b[39;00m\n\u001b[0;32m     12\u001b[0m \u001b[38;5;66;03m# Reshape the data to 2D: (samples, features)\u001b[39;00m\n",
      "File \u001b[1;32mc:\\Users\\zahra\\anaconda3\\Lib\\site-packages\\scipy\\io\\matlab\\_mio.py:225\u001b[0m, in \u001b[0;36mloadmat\u001b[1;34m(file_name, mdict, appendmat, **kwargs)\u001b[0m\n\u001b[0;32m     88\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m     89\u001b[0m \u001b[38;5;124;03mLoad MATLAB file.\u001b[39;00m\n\u001b[0;32m     90\u001b[0m \n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    222\u001b[0m \u001b[38;5;124;03m    3.14159265+3.14159265j])\u001b[39;00m\n\u001b[0;32m    223\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m    224\u001b[0m variable_names \u001b[38;5;241m=\u001b[39m kwargs\u001b[38;5;241m.\u001b[39mpop(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mvariable_names\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m)\n\u001b[1;32m--> 225\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m _open_file_context(file_name, appendmat) \u001b[38;5;28;01mas\u001b[39;00m f:\n\u001b[0;32m    226\u001b[0m     MR, _ \u001b[38;5;241m=\u001b[39m mat_reader_factory(f, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m    227\u001b[0m     matfile_dict \u001b[38;5;241m=\u001b[39m MR\u001b[38;5;241m.\u001b[39mget_variables(variable_names)\n",
      "File \u001b[1;32mc:\\Users\\zahra\\anaconda3\\Lib\\contextlib.py:137\u001b[0m, in \u001b[0;36m_GeneratorContextManager.__enter__\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    135\u001b[0m \u001b[38;5;28;01mdel\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39margs, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mkwds, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfunc\n\u001b[0;32m    136\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 137\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mnext\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mgen)\n\u001b[0;32m    138\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mStopIteration\u001b[39;00m:\n\u001b[0;32m    139\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mRuntimeError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mgenerator didn\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt yield\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[1;32mc:\\Users\\zahra\\anaconda3\\Lib\\site-packages\\scipy\\io\\matlab\\_mio.py:17\u001b[0m, in \u001b[0;36m_open_file_context\u001b[1;34m(file_like, appendmat, mode)\u001b[0m\n\u001b[0;32m     15\u001b[0m \u001b[38;5;129m@contextmanager\u001b[39m\n\u001b[0;32m     16\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_open_file_context\u001b[39m(file_like, appendmat, mode\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mrb\u001b[39m\u001b[38;5;124m'\u001b[39m):\n\u001b[1;32m---> 17\u001b[0m     f, opened \u001b[38;5;241m=\u001b[39m _open_file(file_like, appendmat, mode)\n\u001b[0;32m     18\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m     19\u001b[0m         \u001b[38;5;28;01myield\u001b[39;00m f\n",
      "File \u001b[1;32mc:\\Users\\zahra\\anaconda3\\Lib\\site-packages\\scipy\\io\\matlab\\_mio.py:45\u001b[0m, in \u001b[0;36m_open_file\u001b[1;34m(file_like, appendmat, mode)\u001b[0m\n\u001b[0;32m     43\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m appendmat \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m file_like\u001b[38;5;241m.\u001b[39mendswith(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m.mat\u001b[39m\u001b[38;5;124m'\u001b[39m):\n\u001b[0;32m     44\u001b[0m         file_like \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m.mat\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[1;32m---> 45\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mopen\u001b[39m(file_like, mode), \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[0;32m     46\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m     47\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mOSError\u001b[39;00m(\n\u001b[0;32m     48\u001b[0m         \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mReader needs file name or open file-like object\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[0;32m     49\u001b[0m     ) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n",
      "\u001b[1;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: '../data/lung_SUVperc_COMBINED.mat'"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from scipy.io import loadmat\n",
    "\n",
    "# Load the data\n",
    "data_path = \"../data/\"\n",
    "suv_data = loadmat(data_path + 'lung_SUVperc_COMBINED')\n",
    "lung_suv_selected = suv_data['lung_SUVperc_COMBINED'][0:58, :]  # Shape: (58, 17, 100)\n",
    "\n",
    "# Reshape the data to 2D: (samples, features)\n",
    "X = lung_suv_selected.reshape(lung_suv_selected.shape[0], -1)  # Shape: (58, 1700)\n",
    "\n",
    "# Load the labels\n",
    "flags_data = loadmat(data_path + \"flags_combined.mat\")\n",
    "flags_combined = flags_data['flags_combined'].flatten()[:58]  # Shape: (58,)\n",
    "\n",
    "# Standardize the features\n",
    "scaler = StandardScaler()\n",
    "X_scaled = scaler.fit_transform(X)\n",
    "\n",
    "# Select a single feature for visualization (e.g., the first feature)\n",
    "feature_index = 0\n",
    "X_feature = X_scaled[:, feature_index].reshape(-1, 1)\n",
    "\n",
    "# Fit logistic regression model\n",
    "model = LogisticRegression()\n",
    "model.fit(X_feature, flags_combined)\n",
    "\n",
    "# Generate a range of values for the selected feature\n",
    "x_values = np.linspace(X_feature.min(), X_feature.max(), 300).reshape(-1, 1)\n",
    "probabilities = model.predict_proba(x_values)[:, 1]\n",
    "\n",
    "# Plot the sigmoid curve\n",
    "plt.figure(figsize=(8, 6))\n",
    "plt.plot(x_values, probabilities, label='Sigmoid Curve')\n",
    "plt.scatter(X_feature, flags_combined, c=flags_combined, cmap='bwr', edgecolors='k', label='Data Points')\n",
    "plt.xlabel(f'Feature {feature_index + 1}')\n",
    "plt.ylabel('Probability of Class 1')\n",
    "plt.title('Logistic Regression Sigmoid Curve')\n",
    "plt.legend()\n",
    "plt.grid(True)\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e66de4c4",
   "metadata": {},
   "source": [
    "#to chack data"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.12.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}