--- a
+++ b/notebooks/data/preparation.ipynb
@@ -0,0 +1,100 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.model_selection import train_test_split\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Load processed datasets\n",
+    "original = pd.read_csv(\"../../data/processed/original.csv\")\n",
+    "synthetic = pd.read_csv(\"../../data/processed/synthetic.csv\")\n",
+    "\n",
+    "# mix both original and synthetic sets\n",
+    "data = pd.concat([original, synthetic], keys=[1, 2]).drop_duplicates().dropna()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Select relevant feature\n",
+    "feature = data[['GENDER', 'AGE', 'SMOKING', 'YELLOW_FINGERS', 'FATIGUE', 'WHEEZING', 'COUGHING', 'SHORTNESS OF BREATH', 'SWALLOWING DIFFICULTY', 'CHEST PAIN', 'CHRONIC DISEASE']]\n",
+    "label = data['LUNG_CANCER']\n",
+    "\n",
+    "data = pd.concat([feature, label], axis=1).drop_duplicates().dropna()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "feature = data.drop('LUNG_CANCER', axis='columns')\n",
+    "label = data['LUNG_CANCER']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Training set: (353, 11)\n",
+      "Testing set: (89, 11)\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Split train/test holdout sets\n",
+    "X_train, X_test, y_train, y_test = train_test_split(feature, label, test_size=0.2, random_state=42, stratify=label)\n",
+    "\n",
+    "print(f\"Training set: {X_train.shape}\")\n",
+    "print(f\"Testing set: {X_test.shape}\")\n",
+    "\n",
+    "train_data = pd.concat([X_train, y_train], axis=1)\n",
+    "test_data = pd.concat([X_test , y_test], axis=1)\n",
+    "\n",
+    "train_data.to_csv('../../data/input/train.csv', index=False)\n",
+    "test_data.to_csv('../../data/input/test.csv', index=False)\n"
+   ]
+  }
+ ],
+ "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": "3.12.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}