updates the data preparation data

edit was done by Wuor Bhang

Author: WuorBhang

2_data_preparation/cleaning_teds_d.ipynb

@@ -20,7 +20,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 31,
    "id": "596bf3e0",
    "metadata": {},
    "outputs": [],
@@ -29,6 +29,8 @@
     "import numpy as np\n",
     "from tqdm import tqdm\n",
     "import warnings\n",
+    "import os\n",
+    "os.getcwd()\n",
     "\n",
     "warnings.filterwarnings(\"ignore\")"
    ]
@@ -876,15 +878,18 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "9ba487dc",
+   "id": "dfbecb3a",
    "metadata": {},
    "outputs": [],
    "source": [
+    "from pathlib import Path\n",
+    "import os\n",
+    "\n",
     "if __name__ == \"__main__\":\n",
     "    INPUT_FILE = \"1_datasets/raw/tedsd_puf_2023.csv\"\n",
     "    OUTPUT_FILE = \"1_datasets/processed/teds_d_2023_cleaned.csv\"\n",
     "\n",
-    "    clean_teds_d_data(INPUT_FILE, OUTPUT_FILE)"
+    "    clean_teds_d_data(INPUT_FILE, OUTPUT_FILE)\n"
    ]
   },
   {
@@ -899,21 +904,21 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "b16a295c",
+   "id": "76f5cdd5",
    "metadata": {},
    "outputs": [],
    "source": [
     "df = pd.read_csv(\"1_datasets/processed/teds_d_2023_cleaned.csv\")\n",
     "\n",
     "df_sample = df.sample(1000, random_state=42)\n",
     "\n",
-    "df_sample.to_csv(\"1_datasets/sample/tedsd_sample.csv\", index=False)"
+    "df_sample.to_csv(\"1_datasets/sample/tedsd_sample.csv\", index=False)\n"
    ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": ".venv",
    "language": "python",
    "name": "python3"
   },
@@ -927,7 +932,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.10"
+   "version": "3.14.0"
   }
  },
  "nbformat": 4,