update eda and req

notebooks/02_eda.ipynb

@@ -10,13 +10,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "548992be",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "ename": "ModuleNotFoundError",
+     "evalue": "No module named 'seaborn'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
+      "\u001b[31mModuleNotFoundError\u001b[39m                       Traceback (most recent call last)",
+      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[1]\u001b[39m\u001b[32m, line 2\u001b[39m\n\u001b[32m      1\u001b[39m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mmatplotlib\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mpyplot\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mas\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mplt\u001b[39;00m\n\u001b[32m----> \u001b[39m\u001b[32m2\u001b[39m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mseaborn\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mas\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01msns\u001b[39;00m \n",
+      "\u001b[31mModuleNotFoundError\u001b[39m: No module named 'seaborn'"
+     ]
+    }
+   ],
    "source": [
     "import matplotlib.pyplot as plt\n",
-    "import seaborn as sns"
+    "import seaborn as sns "
    ]
   },
   {
@@ -108,7 +120,15 @@
    "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": "3.12.12"
   }
  },

requirements.txt

@@ -1,3 +1,5 @@
-python=3.13
-pydantic=2.10.4
-pytest=7.4.0
+# python==3.12
+pandas==3.0.1
+matplotlib==3.10.8
+seaborn==0.13.2
+scikit-learn==1.8.0

src/utils/helpers.py

@@ -10,6 +10,12 @@ def _check_and_balance(df: pd.DataFrame, target_col: str = "target", random_stat
 	"""Return a balanced dataframe by undersampling majority classes to the minority count.
 
 	If the dataframe is already balanced (all classes equal), it's returned unchanged.
+	Args:
+		df (pd.DataFrame): The input dataframe to balance.
+		target_col (str, optional): The name of the target column. Defaults to "target".
+		random_state (int, optional): Random state for reproducibility. Defaults to 42.
+	Returns:
+		pd.DataFrame: A balanced dataframe.
 	"""
 	counts = df[target_col].value_counts()
 	if counts.nunique() == 1: