Upload folder using huggingface_hub

04_finetuning_approaches/generate_training_question.ipynb

@@ -47,7 +47,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
@@ -57,8 +57,8 @@
      "traceback": [
       "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
       "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-      "Cell \u001b[1;32mIn[1], line 29\u001b[0m\n\u001b[0;32m     25\u001b[0m     training_data\u001b[39m.\u001b[39mto_excel(\u001b[39m'\u001b[39m\u001b[39mfelix_playground_SQA_Training/module_guide_sq_abbreviation.xlsx\u001b[39m\u001b[39m'\u001b[39m, index\u001b[39m=\u001b[39m\u001b[39mFalse\u001b[39;00m)\n\u001b[0;32m     27\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39m\"\u001b[39m\u001b[39mTraining data created and saved as \u001b[39m\u001b[39m'\u001b[39m\u001b[39mtraining_data.xlsx\u001b[39m\u001b[39m'\u001b[39m\u001b[39m.\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m---> 29\u001b[0m create_training_data_abbreviation(\u001b[39m\"\u001b[39;49m\u001b[39mfelix_playground_SQA_Training/MS_IS_all_modules_cleaned.xlsx\u001b[39;49m\u001b[39m\"\u001b[39;49m)\n",
-      "Cell \u001b[1;32mIn[1], line 5\u001b[0m, in \u001b[0;36mcreate_training_data_abbreviation\u001b[1;34m(file_path)\u001b[0m\n\u001b[0;32m      3\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mcreate_training_data_abbreviation\u001b[39m(file_path):\n\u001b[0;32m      4\u001b[0m     \u001b[39m# Read the cleaned excel file\u001b[39;00m\n\u001b[1;32m----> 5\u001b[0m     df \u001b[39m=\u001b[39m pd\u001b[39m.\u001b[39mread_excel(file_path)\n\u001b[0;32m      7\u001b[0m     \u001b[39m# Create a new dataframe for training data\u001b[39;00m\n\u001b[0;32m      8\u001b[0m     training_data \u001b[39m=\u001b[39m pd\u001b[39m.\u001b[39mDataFrame(columns\u001b[39m=\u001b[39m[\u001b[39m'\u001b[39m\u001b[39mid\u001b[39m\u001b[39m'\u001b[39m, \u001b[39m'\u001b[39m\u001b[39mannotator\u001b[39m\u001b[39m'\u001b[39m, \u001b[39m'\u001b[39m\u001b[39mposition\u001b[39m\u001b[39m'\u001b[39m, \u001b[39m'\u001b[39m\u001b[39mquestion\u001b[39m\u001b[39m'\u001b[39m, \u001b[39m'\u001b[39m\u001b[39mtable_file\u001b[39m\u001b[39m'\u001b[39m, \u001b[39m'\u001b[39m\u001b[39manswer_coordinates\u001b[39m\u001b[39m'\u001b[39m, \u001b[39m'\u001b[39m\u001b[39manswer_text\u001b[39m\u001b[39m'\u001b[39m])\n",
+      "Cell \u001b[1;32mIn[2], line 29\u001b[0m\n\u001b[0;32m     25\u001b[0m     training_data\u001b[39m.\u001b[39mto_excel(\u001b[39m'\u001b[39m\u001b[39mfelix_playground_SQA_Training/module_guide_sq_abbreviation.xlsx\u001b[39m\u001b[39m'\u001b[39m, index\u001b[39m=\u001b[39m\u001b[39mFalse\u001b[39;00m)\n\u001b[0;32m     27\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39m\"\u001b[39m\u001b[39mTraining data created and saved as \u001b[39m\u001b[39m'\u001b[39m\u001b[39mtraining_data.xlsx\u001b[39m\u001b[39m'\u001b[39m\u001b[39m.\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m---> 29\u001b[0m create_training_data_abbreviation(\u001b[39m\"\u001b[39;49m\u001b[39mfelix_playground_SQA_Training/MS_IS_all_modules_cleaned.xlsx\u001b[39;49m\u001b[39m\"\u001b[39;49m)\n",
+      "Cell \u001b[1;32mIn[2], line 5\u001b[0m, in \u001b[0;36mcreate_training_data_abbreviation\u001b[1;34m(file_path)\u001b[0m\n\u001b[0;32m      3\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mcreate_training_data_abbreviation\u001b[39m(file_path):\n\u001b[0;32m      4\u001b[0m     \u001b[39m# Read the cleaned excel file\u001b[39;00m\n\u001b[1;32m----> 5\u001b[0m     df \u001b[39m=\u001b[39m pd\u001b[39m.\u001b[39mread_excel(file_path)\n\u001b[0;32m      7\u001b[0m     \u001b[39m# Create a new dataframe for training data\u001b[39;00m\n\u001b[0;32m      8\u001b[0m     training_data \u001b[39m=\u001b[39m pd\u001b[39m.\u001b[39mDataFrame(columns\u001b[39m=\u001b[39m[\u001b[39m'\u001b[39m\u001b[39mid\u001b[39m\u001b[39m'\u001b[39m, \u001b[39m'\u001b[39m\u001b[39mannotator\u001b[39m\u001b[39m'\u001b[39m, \u001b[39m'\u001b[39m\u001b[39mposition\u001b[39m\u001b[39m'\u001b[39m, \u001b[39m'\u001b[39m\u001b[39mquestion\u001b[39m\u001b[39m'\u001b[39m, \u001b[39m'\u001b[39m\u001b[39mtable_file\u001b[39m\u001b[39m'\u001b[39m, \u001b[39m'\u001b[39m\u001b[39manswer_coordinates\u001b[39m\u001b[39m'\u001b[39m, \u001b[39m'\u001b[39m\u001b[39manswer_text\u001b[39m\u001b[39m'\u001b[39m])\n",
       "\u001b[1;31mNameError\u001b[0m: name 'pd' is not defined"
      ]
     }
@@ -70,7 +70,6 @@
     "    # Read the cleaned excel file\n",
     "    df = pd.read_excel(file_path)\n",
     "    \n",
-    "    # Create a new dataframe for training data\n",
     "    training_data = pd.DataFrame(columns=['id', 'annotator', 'position', 'question', 'table_file', 'answer_coordinates', 'answer_text'])\n",
     "    \n",
     "    # Define a list of possible question formulations\n",

frontend_app.ipynb

@@ -196,6 +196,22 @@
      },
      "metadata": {},
      "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Keyboard interruption in main thread... closing server.\n",
+      "Killing tunnel 127.0.0.1:7867 <> https://a7a23badcaa31f041e.gradio.live\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": []
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
    "source": [