Gender_prediction.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU",
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "6f0d521604764ec2980cdcd572aadc31": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_ea78fd3f3a4944818dddf5aafbcaefcc",
              "IPY_MODEL_24075c511c5845cebfd35cdbddc381ec",
              "IPY_MODEL_8e9c1c2e079f4216879c93270b5d71e0"
            ],
            "layout": "IPY_MODEL_4d5e5bb8ea0e4c228f24e002222d29ea"
          }
        },
        "ea78fd3f3a4944818dddf5aafbcaefcc": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_5c0539b4c7e94531806476cc9fb9fd45",
            "placeholder": "​",
            "style": "IPY_MODEL_440aea17d6914bb9b930124d31b697db",
            "value": "Map: 100%"
          }
        },
        "24075c511c5845cebfd35cdbddc381ec": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_5723de58d94f483db517654e32f9c5f7",
            "max": 19751,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_4caaf5ddb2784b7e9200d49ea2ff0940",
            "value": 19751
          }
        },
        "8e9c1c2e079f4216879c93270b5d71e0": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_976680a5025d42d6b5253d76913da9ca",
            "placeholder": "​",
            "style": "IPY_MODEL_cb4e4fb8313d40cbb0d447662ed107ac",
            "value": " 19751/19751 [00:11&lt;00:00, 1215.13 examples/s]"
          }
        },
        "4d5e5bb8ea0e4c228f24e002222d29ea": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "5c0539b4c7e94531806476cc9fb9fd45": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "440aea17d6914bb9b930124d31b697db": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "5723de58d94f483db517654e32f9c5f7": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "4caaf5ddb2784b7e9200d49ea2ff0940": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "976680a5025d42d6b5253d76913da9ca": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "cb4e4fb8313d40cbb0d447662ed107ac": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "d4066f0e2435445dbbb256492f7f90ab": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_9946648b6047460ba4de243932becef0",
              "IPY_MODEL_2b3106ae344d4f54a9c32f39598c144b",
              "IPY_MODEL_273b74b41afc4f24aa932d39e19c141a"
            ],
            "layout": "IPY_MODEL_5b2ac9d5b6de466dbc48e1283f496d0f"
          }
        },
        "9946648b6047460ba4de243932becef0": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_4ebe27cb868d439c916da20c6801c740",
            "placeholder": "​",
            "style": "IPY_MODEL_ea8cf8444b5244789f49de9754ee7ade",
            "value": "Map: 100%"
          }
        },
        "2b3106ae344d4f54a9c32f39598c144b": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_97a1273d3ab0425fafb1d1ea74b53601",
            "max": 3292,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_145f91f3a57544229acc0b81b4a6c74c",
            "value": 3292
          }
        },
        "273b74b41afc4f24aa932d39e19c141a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_a806875681074672bc117a2aa8255dd7",
            "placeholder": "​",
            "style": "IPY_MODEL_32a4a236273e493585017fb9e540a9b0",
            "value": " 3292/3292 [00:01&lt;00:00, 1768.80 examples/s]"
          }
        },
        "5b2ac9d5b6de466dbc48e1283f496d0f": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "4ebe27cb868d439c916da20c6801c740": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "ea8cf8444b5244789f49de9754ee7ade": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "97a1273d3ab0425fafb1d1ea74b53601": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "145f91f3a57544229acc0b81b4a6c74c": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "a806875681074672bc117a2aa8255dd7": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "32a4a236273e493585017fb9e540a9b0": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "e43084a1f8da46f3abde06b5b457d2e7": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_f708e3e36c204cee8ade0f61f8a220f5",
              "IPY_MODEL_0c64c45f30f0401887c988504ce08b88",
              "IPY_MODEL_c9d744fbe2a8498a94428f2ddd6798a4"
            ],
            "layout": "IPY_MODEL_1bed0f56bf8043c5a64a7cef543878f1"
          }
        },
        "f708e3e36c204cee8ade0f61f8a220f5": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_68b4e1a222414f4aadb18c3eb5dfaa26",
            "placeholder": "​",
            "style": "IPY_MODEL_7ff309ccd33e429a970915e453b70309",
            "value": "Map: 100%"
          }
        },
        "0c64c45f30f0401887c988504ce08b88": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_0af831280ae24a3fbaa73dd011cea87e",
            "max": 3292,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_6792b44b25f34d25b365d5edfb647da4",
            "value": 3292
          }
        },
        "c9d744fbe2a8498a94428f2ddd6798a4": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_8cb98978302b4ba0bc81dd3655458cf1",
            "placeholder": "​",
            "style": "IPY_MODEL_3727c5f23f1d472380359c020733d260",
            "value": " 3292/3292 [00:01&lt;00:00, 2364.54 examples/s]"
          }
        },
        "1bed0f56bf8043c5a64a7cef543878f1": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "68b4e1a222414f4aadb18c3eb5dfaa26": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "7ff309ccd33e429a970915e453b70309": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "0af831280ae24a3fbaa73dd011cea87e": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "6792b44b25f34d25b365d5edfb647da4": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "8cb98978302b4ba0bc81dd3655458cf1": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "3727c5f23f1d472380359c020733d260": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        }
      }
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "source": [
        "# !pip install datasets\n",
        "# !pip install evaluate\n",
        "# !pip install transformers[torch]\n",
        "# !pip install accelerate -U"
      ],
      "metadata": {
        "id": "fEfXl5wWMurE"
      },
      "execution_count": 1,
      "outputs": []
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "id": "5d3OgVoHNdT-"
      },
      "outputs": [],
      "source": [
        "import pandas as pd\n",
        "from transformers import AutoTokenizer, AutoModelForSequenceClassification, TrainingArguments, Trainer\n",
        "from datasets import load_dataset, Dataset, DatasetDict\n",
        "import torch"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "torch.cuda.is_available()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "f2Z3AhI9vTRJ",
        "outputId": "2e1f8086-8ed6-4c0e-9a1a-bbb6e7da6c91"
      },
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "True"
            ]
          },
          "metadata": {},
          "execution_count": 3
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Load Data and pre-process**"
      ],
      "metadata": {
        "id": "0eYv_noeESVU"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "df = pd.read_json(\"drive/MyDrive/Data/corpus.jsonl\", lines=True)\n",
        "df"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 424
        },
        "id": "jHvyaXRceG25",
        "outputId": "4a47a2b9-207e-461c-baec-df8139df9d3d"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "       argument_id                                           argument  \\\n",
              "0           201900  Das Schweizer Volk hat die MEI angenommen und ...   \n",
              "1           201901  Eine Legalisierung von Cannabis entlasten die ...   \n",
              "2           201902  Durch die Förderung der familienergänzenden Be...   \n",
              "3           201903  Ich ziehe eine Elternzeit vor. Die Zeit nach d...   \n",
              "4           201904  Unser Asylrecht muss konsequent angewendet wer...   \n",
              "...            ...                                                ...   \n",
              "26330   2019028133  È da seguire il principio \"chi inquina paga\", ...   \n",
              "26331   2019028136  Le energie rinnovabile sono il presente e il f...   \n",
              "26332   2019028144  Attraverso un rafforzamento delle condizioni q...   \n",
              "26333   2019028149  Molto di più di ora, dobbiamo poter installare...   \n",
              "26334   2019028152  È invece preferibile il concetto di mobilità m...   \n",
              "\n",
              "        stance                         topic  \\\n",
              "0        FAVOR                   Immigration   \n",
              "1        FAVOR                       Society   \n",
              "2        FAVOR                       Welfare   \n",
              "3      AGAINST                       Welfare   \n",
              "4      AGAINST                   Immigration   \n",
              "...        ...                           ...   \n",
              "26330    FAVOR  Infrastructure & Environment   \n",
              "26331    FAVOR  Infrastructure & Environment   \n",
              "26332    FAVOR  Infrastructure & Environment   \n",
              "26333    FAVOR  Infrastructure & Environment   \n",
              "26334  AGAINST  Infrastructure & Environment   \n",
              "\n",
              "                                     demographic_profile  \n",
              "0      {'gender': 'Männlich', 'age': '18-34', 'reside...  \n",
              "1      {'gender': 'Männlich', 'age': '18-34', 'reside...  \n",
              "2      {'gender': 'Weiblich', 'age': '35-49', 'reside...  \n",
              "3      {'gender': 'Weiblich', 'age': '35-49', 'reside...  \n",
              "4      {'gender': 'Weiblich', 'age': '35-49', 'reside...  \n",
              "...                                                  ...  \n",
              "26330  {'gender': 'Weiblich', 'age': '18-34', 'reside...  \n",
              "26331  {'gender': 'Männlich', 'age': '18-34', 'reside...  \n",
              "26332  {'gender': 'Männlich', 'age': '35-49', 'reside...  \n",
              "26333  {'gender': 'Männlich', 'age': '18-34', 'reside...  \n",
              "26334  {'gender': 'Männlich', 'age': '50-64', 'reside...  \n",
              "\n",
              "[26335 rows x 5 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-7895ff59-636b-45c6-8c1d-d39768c3032b\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>argument_id</th>\n",
              "      <th>argument</th>\n",
              "      <th>stance</th>\n",
              "      <th>topic</th>\n",
              "      <th>demographic_profile</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>201900</td>\n",
              "      <td>Das Schweizer Volk hat die MEI angenommen und ...</td>\n",
              "      <td>FAVOR</td>\n",
              "      <td>Immigration</td>\n",
              "      <td>{'gender': 'Männlich', 'age': '18-34', 'reside...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>201901</td>\n",
              "      <td>Eine Legalisierung von Cannabis entlasten die ...</td>\n",
              "      <td>FAVOR</td>\n",
              "      <td>Society</td>\n",
              "      <td>{'gender': 'Männlich', 'age': '18-34', 'reside...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>201902</td>\n",
              "      <td>Durch die Förderung der familienergänzenden Be...</td>\n",
              "      <td>FAVOR</td>\n",
              "      <td>Welfare</td>\n",
              "      <td>{'gender': 'Weiblich', 'age': '35-49', 'reside...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>201903</td>\n",
              "      <td>Ich ziehe eine Elternzeit vor. Die Zeit nach d...</td>\n",
              "      <td>AGAINST</td>\n",
              "      <td>Welfare</td>\n",
              "      <td>{'gender': 'Weiblich', 'age': '35-49', 'reside...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>201904</td>\n",
              "      <td>Unser Asylrecht muss konsequent angewendet wer...</td>\n",
              "      <td>AGAINST</td>\n",
              "      <td>Immigration</td>\n",
              "      <td>{'gender': 'Weiblich', 'age': '35-49', 'reside...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>26330</th>\n",
              "      <td>2019028133</td>\n",
              "      <td>È da seguire il principio \"chi inquina paga\", ...</td>\n",
              "      <td>FAVOR</td>\n",
              "      <td>Infrastructure &amp; Environment</td>\n",
              "      <td>{'gender': 'Weiblich', 'age': '18-34', 'reside...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>26331</th>\n",
              "      <td>2019028136</td>\n",
              "      <td>Le energie rinnovabile sono il presente e il f...</td>\n",
              "      <td>FAVOR</td>\n",
              "      <td>Infrastructure &amp; Environment</td>\n",
              "      <td>{'gender': 'Männlich', 'age': '18-34', 'reside...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>26332</th>\n",
              "      <td>2019028144</td>\n",
              "      <td>Attraverso un rafforzamento delle condizioni q...</td>\n",
              "      <td>FAVOR</td>\n",
              "      <td>Infrastructure &amp; Environment</td>\n",
              "      <td>{'gender': 'Männlich', 'age': '35-49', 'reside...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>26333</th>\n",
              "      <td>2019028149</td>\n",
              "      <td>Molto di più di ora, dobbiamo poter installare...</td>\n",
              "      <td>FAVOR</td>\n",
              "      <td>Infrastructure &amp; Environment</td>\n",
              "      <td>{'gender': 'Männlich', 'age': '18-34', 'reside...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>26334</th>\n",
              "      <td>2019028152</td>\n",
              "      <td>È invece preferibile il concetto di mobilità m...</td>\n",
              "      <td>AGAINST</td>\n",
              "      <td>Infrastructure &amp; Environment</td>\n",
              "      <td>{'gender': 'Männlich', 'age': '50-64', 'reside...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>26335 rows × 5 columns</p>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-7895ff59-636b-45c6-8c1d-d39768c3032b')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-7895ff59-636b-45c6-8c1d-d39768c3032b button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-7895ff59-636b-45c6-8c1d-d39768c3032b');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-a9cced43-2e1c-4905-ba63-eed7aaebabdd\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-a9cced43-2e1c-4905-ba63-eed7aaebabdd')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-a9cced43-2e1c-4905-ba63-eed7aaebabdd button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "df",
              "summary": "{\n  \"name\": \"df\",\n  \"rows\": 26335,\n  \"fields\": [\n    {\n      \"column\": \"argument_id\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 858855047,\n        \"min\": 201900,\n        \"max\": 2019032423,\n        \"num_unique_values\": 26335,\n        \"samples\": [\n          2019022170,\n          201907075,\n          201908589\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"argument\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 23253,\n        \"samples\": [\n          \"Wenn man einen Mindestlohn einf\\u00fchren will, braucht es in dieser Branche auch eine Regelung\",\n          \"Das oberste Ziel der Sozialarbeit muss sein, Sozialhilfeempf\\u00e4nger wenn immer m\\u00f6glich wieder in den Erwerbsprozess zu integrieren. Daher muss sich die Annahme einer Arbeit stets lohnen und der Fokus speziell bei J\\u00fcngeren auf Ausbildung und Integration gelegt werden.\",\n          \"PMA pour toutes les femmes !\\nEt oppos\\u00e9e \\u00e0 la gestation par autrui.\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"stance\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          \"AGAINST\",\n          \"FAVOR\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"topic\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 10,\n        \"samples\": [\n          \"Infrastructure & Environment\",\n          \"Society\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"demographic_profile\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "keys = list(df.demographic_profile[0].keys())"
      ],
      "metadata": {
        "id": "c0GrWYXneXmw"
      },
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "def getValues(data, key):\n",
        "    return data[key]"
      ],
      "metadata": {
        "id": "thTFMnvjfBsp"
      },
      "execution_count": 6,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "key = \"gender\"\n",
        "df[key] = df.demographic_profile.apply(getValues, args=(key,))"
      ],
      "metadata": {
        "id": "EkWQsKqSfJDD"
      },
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 424
        },
        "id": "CZgm1sTIfPaI",
        "outputId": "5ba32234-c0d1-439f-c964-7bc499633401"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "       argument_id                                           argument  \\\n",
              "0           201900  Das Schweizer Volk hat die MEI angenommen und ...   \n",
              "1           201901  Eine Legalisierung von Cannabis entlasten die ...   \n",
              "2           201902  Durch die Förderung der familienergänzenden Be...   \n",
              "3           201903  Ich ziehe eine Elternzeit vor. Die Zeit nach d...   \n",
              "4           201904  Unser Asylrecht muss konsequent angewendet wer...   \n",
              "...            ...                                                ...   \n",
              "26330   2019028133  È da seguire il principio \"chi inquina paga\", ...   \n",
              "26331   2019028136  Le energie rinnovabile sono il presente e il f...   \n",
              "26332   2019028144  Attraverso un rafforzamento delle condizioni q...   \n",
              "26333   2019028149  Molto di più di ora, dobbiamo poter installare...   \n",
              "26334   2019028152  È invece preferibile il concetto di mobilità m...   \n",
              "\n",
              "        stance                         topic  \\\n",
              "0        FAVOR                   Immigration   \n",
              "1        FAVOR                       Society   \n",
              "2        FAVOR                       Welfare   \n",
              "3      AGAINST                       Welfare   \n",
              "4      AGAINST                   Immigration   \n",
              "...        ...                           ...   \n",
              "26330    FAVOR  Infrastructure & Environment   \n",
              "26331    FAVOR  Infrastructure & Environment   \n",
              "26332    FAVOR  Infrastructure & Environment   \n",
              "26333    FAVOR  Infrastructure & Environment   \n",
              "26334  AGAINST  Infrastructure & Environment   \n",
              "\n",
              "                                     demographic_profile    gender  \n",
              "0      {'gender': 'Männlich', 'age': '18-34', 'reside...  Männlich  \n",
              "1      {'gender': 'Männlich', 'age': '18-34', 'reside...  Männlich  \n",
              "2      {'gender': 'Weiblich', 'age': '35-49', 'reside...  Weiblich  \n",
              "3      {'gender': 'Weiblich', 'age': '35-49', 'reside...  Weiblich  \n",
              "4      {'gender': 'Weiblich', 'age': '35-49', 'reside...  Weiblich  \n",
              "...                                                  ...       ...  \n",
              "26330  {'gender': 'Weiblich', 'age': '18-34', 'reside...  Weiblich  \n",
              "26331  {'gender': 'Männlich', 'age': '18-34', 'reside...  Männlich  \n",
              "26332  {'gender': 'Männlich', 'age': '35-49', 'reside...  Männlich  \n",
              "26333  {'gender': 'Männlich', 'age': '18-34', 'reside...  Männlich  \n",
              "26334  {'gender': 'Männlich', 'age': '50-64', 'reside...  Männlich  \n",
              "\n",
              "[26335 rows x 6 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-f4675aa9-d4e0-49db-b168-cc72dff497b3\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>argument_id</th>\n",
              "      <th>argument</th>\n",
              "      <th>stance</th>\n",
              "      <th>topic</th>\n",
              "      <th>demographic_profile</th>\n",
              "      <th>gender</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>201900</td>\n",
              "      <td>Das Schweizer Volk hat die MEI angenommen und ...</td>\n",
              "      <td>FAVOR</td>\n",
              "      <td>Immigration</td>\n",
              "      <td>{'gender': 'Männlich', 'age': '18-34', 'reside...</td>\n",
              "      <td>Männlich</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>201901</td>\n",
              "      <td>Eine Legalisierung von Cannabis entlasten die ...</td>\n",
              "      <td>FAVOR</td>\n",
              "      <td>Society</td>\n",
              "      <td>{'gender': 'Männlich', 'age': '18-34', 'reside...</td>\n",
              "      <td>Männlich</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>201902</td>\n",
              "      <td>Durch die Förderung der familienergänzenden Be...</td>\n",
              "      <td>FAVOR</td>\n",
              "      <td>Welfare</td>\n",
              "      <td>{'gender': 'Weiblich', 'age': '35-49', 'reside...</td>\n",
              "      <td>Weiblich</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>201903</td>\n",
              "      <td>Ich ziehe eine Elternzeit vor. Die Zeit nach d...</td>\n",
              "      <td>AGAINST</td>\n",
              "      <td>Welfare</td>\n",
              "      <td>{'gender': 'Weiblich', 'age': '35-49', 'reside...</td>\n",
              "      <td>Weiblich</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>201904</td>\n",
              "      <td>Unser Asylrecht muss konsequent angewendet wer...</td>\n",
              "      <td>AGAINST</td>\n",
              "      <td>Immigration</td>\n",
              "      <td>{'gender': 'Weiblich', 'age': '35-49', 'reside...</td>\n",
              "      <td>Weiblich</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>26330</th>\n",
              "      <td>2019028133</td>\n",
              "      <td>È da seguire il principio \"chi inquina paga\", ...</td>\n",
              "      <td>FAVOR</td>\n",
              "      <td>Infrastructure &amp; Environment</td>\n",
              "      <td>{'gender': 'Weiblich', 'age': '18-34', 'reside...</td>\n",
              "      <td>Weiblich</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>26331</th>\n",
              "      <td>2019028136</td>\n",
              "      <td>Le energie rinnovabile sono il presente e il f...</td>\n",
              "      <td>FAVOR</td>\n",
              "      <td>Infrastructure &amp; Environment</td>\n",
              "      <td>{'gender': 'Männlich', 'age': '18-34', 'reside...</td>\n",
              "      <td>Männlich</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>26332</th>\n",
              "      <td>2019028144</td>\n",
              "      <td>Attraverso un rafforzamento delle condizioni q...</td>\n",
              "      <td>FAVOR</td>\n",
              "      <td>Infrastructure &amp; Environment</td>\n",
              "      <td>{'gender': 'Männlich', 'age': '35-49', 'reside...</td>\n",
              "      <td>Männlich</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>26333</th>\n",
              "      <td>2019028149</td>\n",
              "      <td>Molto di più di ora, dobbiamo poter installare...</td>\n",
              "      <td>FAVOR</td>\n",
              "      <td>Infrastructure &amp; Environment</td>\n",
              "      <td>{'gender': 'Männlich', 'age': '18-34', 'reside...</td>\n",
              "      <td>Männlich</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>26334</th>\n",
              "      <td>2019028152</td>\n",
              "      <td>È invece preferibile il concetto di mobilità m...</td>\n",
              "      <td>AGAINST</td>\n",
              "      <td>Infrastructure &amp; Environment</td>\n",
              "      <td>{'gender': 'Männlich', 'age': '50-64', 'reside...</td>\n",
              "      <td>Männlich</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>26335 rows × 6 columns</p>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-f4675aa9-d4e0-49db-b168-cc72dff497b3')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-f4675aa9-d4e0-49db-b168-cc72dff497b3 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-f4675aa9-d4e0-49db-b168-cc72dff497b3');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-6fe36efd-edbe-45a3-b2d6-088907857848\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-6fe36efd-edbe-45a3-b2d6-088907857848')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-6fe36efd-edbe-45a3-b2d6-088907857848 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "df",
              "summary": "{\n  \"name\": \"df\",\n  \"rows\": 26335,\n  \"fields\": [\n    {\n      \"column\": \"argument_id\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 858855047,\n        \"min\": 201900,\n        \"max\": 2019032423,\n        \"num_unique_values\": 26335,\n        \"samples\": [\n          2019022170,\n          201907075,\n          201908589\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"argument\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 23253,\n        \"samples\": [\n          \"Wenn man einen Mindestlohn einf\\u00fchren will, braucht es in dieser Branche auch eine Regelung\",\n          \"Das oberste Ziel der Sozialarbeit muss sein, Sozialhilfeempf\\u00e4nger wenn immer m\\u00f6glich wieder in den Erwerbsprozess zu integrieren. Daher muss sich die Annahme einer Arbeit stets lohnen und der Fokus speziell bei J\\u00fcngeren auf Ausbildung und Integration gelegt werden.\",\n          \"PMA pour toutes les femmes !\\nEt oppos\\u00e9e \\u00e0 la gestation par autrui.\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"stance\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          \"AGAINST\",\n          \"FAVOR\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"topic\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 10,\n        \"samples\": [\n          \"Infrastructure & Environment\",\n          \"Society\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"demographic_profile\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"gender\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          \"Weiblich\",\n          \"M\\u00e4nnlich\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def toInt(data):\n",
        "  if(data == \"Weiblich\"):\n",
        "    return 0\n",
        "  return 1\n",
        "\n",
        "df[\"label\"] = df.gender.apply(toInt)\n",
        "df.drop([\"argument_id\", \"stance\", \"topic\", \"demographic_profile\", \"gender\"], axis=\"columns\", inplace=True)"
      ],
      "metadata": {
        "id": "tDD0YFWffQaH"
      },
      "execution_count": 9,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 424
        },
        "id": "MFR8ETwufG8-",
        "outputId": "0d29c206-5902-4cd7-9986-953bfcc4b6c7"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                                                argument  label\n",
              "0      Das Schweizer Volk hat die MEI angenommen und ...      1\n",
              "1      Eine Legalisierung von Cannabis entlasten die ...      1\n",
              "2      Durch die Förderung der familienergänzenden Be...      0\n",
              "3      Ich ziehe eine Elternzeit vor. Die Zeit nach d...      0\n",
              "4      Unser Asylrecht muss konsequent angewendet wer...      0\n",
              "...                                                  ...    ...\n",
              "26330  È da seguire il principio \"chi inquina paga\", ...      0\n",
              "26331  Le energie rinnovabile sono il presente e il f...      1\n",
              "26332  Attraverso un rafforzamento delle condizioni q...      1\n",
              "26333  Molto di più di ora, dobbiamo poter installare...      1\n",
              "26334  È invece preferibile il concetto di mobilità m...      1\n",
              "\n",
              "[26335 rows x 2 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-86305f68-e69a-43f5-8bd8-4ec28ca77e8b\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>argument</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Das Schweizer Volk hat die MEI angenommen und ...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Eine Legalisierung von Cannabis entlasten die ...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Durch die Förderung der familienergänzenden Be...</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Ich ziehe eine Elternzeit vor. Die Zeit nach d...</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Unser Asylrecht muss konsequent angewendet wer...</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>26330</th>\n",
              "      <td>È da seguire il principio \"chi inquina paga\", ...</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>26331</th>\n",
              "      <td>Le energie rinnovabile sono il presente e il f...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>26332</th>\n",
              "      <td>Attraverso un rafforzamento delle condizioni q...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>26333</th>\n",
              "      <td>Molto di più di ora, dobbiamo poter installare...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>26334</th>\n",
              "      <td>È invece preferibile il concetto di mobilità m...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>26335 rows × 2 columns</p>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-86305f68-e69a-43f5-8bd8-4ec28ca77e8b')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-86305f68-e69a-43f5-8bd8-4ec28ca77e8b button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-86305f68-e69a-43f5-8bd8-4ec28ca77e8b');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-01df0fa1-0905-46cc-b18f-690acc144926\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-01df0fa1-0905-46cc-b18f-690acc144926')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-01df0fa1-0905-46cc-b18f-690acc144926 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "df",
              "summary": "{\n  \"name\": \"df\",\n  \"rows\": 26335,\n  \"fields\": [\n    {\n      \"column\": \"argument\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 23253,\n        \"samples\": [\n          \"Wenn man einen Mindestlohn einf\\u00fchren will, braucht es in dieser Branche auch eine Regelung\",\n          \"Das oberste Ziel der Sozialarbeit muss sein, Sozialhilfeempf\\u00e4nger wenn immer m\\u00f6glich wieder in den Erwerbsprozess zu integrieren. Daher muss sich die Annahme einer Arbeit stets lohnen und der Fokus speziell bei J\\u00fcngeren auf Ausbildung und Integration gelegt werden.\",\n          \"PMA pour toutes les femmes !\\nEt oppos\\u00e9e \\u00e0 la gestation par autrui.\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"label\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 1,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0,\n          1\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Convert to a Dataset Dict, split in train-validation-test**"
      ],
      "metadata": {
        "id": "R8vLDRoJEh4F"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "data = Dataset.from_pandas(df)\n",
        "train = data.train_test_split(test_size=0.25)\n",
        "test_valid = train['test'].train_test_split(test_size=0.5)\n",
        "\n",
        "# gather all to a single DatasetDict\n",
        "data = DatasetDict({\n",
        "    'train': train['train'],\n",
        "    'test': test_valid['test'],\n",
        "    'valid': test_valid['train']})\n",
        "\n",
        "data"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "iMK0FSH4NBXk",
        "outputId": "4ce1f6c6-55f2-43d0-823a-bfe49e4c1255"
      },
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "DatasetDict({\n",
              "    train: Dataset({\n",
              "        features: ['argument', 'label'],\n",
              "        num_rows: 19751\n",
              "    })\n",
              "    test: Dataset({\n",
              "        features: ['argument', 'label'],\n",
              "        num_rows: 3292\n",
              "    })\n",
              "    valid: Dataset({\n",
              "        features: ['argument', 'label'],\n",
              "        num_rows: 3292\n",
              "    })\n",
              "})"
            ]
          },
          "metadata": {},
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Tokenize:** Using padding = \"longest\" for quick compute due to only 15 GB GPU availability on Colab"
      ],
      "metadata": {
        "id": "VzJ5mZ3kGdsB"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "modelId = \"xlm-roberta-large\"\n",
        "tokenizer = AutoTokenizer.from_pretrained(modelId)\n",
        "\n",
        "def tokenize(examples):\n",
        "    tokenized_inputs = tokenizer(\n",
        "       examples[\"argument\"], padding=\"longest\", truncation=True\n",
        "    )\n",
        "    return tokenized_inputs\n",
        "\n",
        "tokenized_dataset = data.map(tokenize, batched=True)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 217,
          "referenced_widgets": [
            "6f0d521604764ec2980cdcd572aadc31",
            "ea78fd3f3a4944818dddf5aafbcaefcc",
            "24075c511c5845cebfd35cdbddc381ec",
            "8e9c1c2e079f4216879c93270b5d71e0",
            "4d5e5bb8ea0e4c228f24e002222d29ea",
            "5c0539b4c7e94531806476cc9fb9fd45",
            "440aea17d6914bb9b930124d31b697db",
            "5723de58d94f483db517654e32f9c5f7",
            "4caaf5ddb2784b7e9200d49ea2ff0940",
            "976680a5025d42d6b5253d76913da9ca",
            "cb4e4fb8313d40cbb0d447662ed107ac",
            "d4066f0e2435445dbbb256492f7f90ab",
            "9946648b6047460ba4de243932becef0",
            "2b3106ae344d4f54a9c32f39598c144b",
            "273b74b41afc4f24aa932d39e19c141a",
            "5b2ac9d5b6de466dbc48e1283f496d0f",
            "4ebe27cb868d439c916da20c6801c740",
            "ea8cf8444b5244789f49de9754ee7ade",
            "97a1273d3ab0425fafb1d1ea74b53601",
            "145f91f3a57544229acc0b81b4a6c74c",
            "a806875681074672bc117a2aa8255dd7",
            "32a4a236273e493585017fb9e540a9b0",
            "e43084a1f8da46f3abde06b5b457d2e7",
            "f708e3e36c204cee8ade0f61f8a220f5",
            "0c64c45f30f0401887c988504ce08b88",
            "c9d744fbe2a8498a94428f2ddd6798a4",
            "1bed0f56bf8043c5a64a7cef543878f1",
            "68b4e1a222414f4aadb18c3eb5dfaa26",
            "7ff309ccd33e429a970915e453b70309",
            "0af831280ae24a3fbaa73dd011cea87e",
            "6792b44b25f34d25b365d5edfb647da4",
            "8cb98978302b4ba0bc81dd3655458cf1",
            "3727c5f23f1d472380359c020733d260"
          ]
        },
        "id": "1ni2Dt2CwEbg",
        "outputId": "24f5c3e6-5672-422d-8197-db08923d08cb"
      },
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_token.py:88: UserWarning: \n",
            "The secret `HF_TOKEN` does not exist in your Colab secrets.\n",
            "To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.\n",
            "You will be able to reuse this secret in all of your notebooks.\n",
            "Please note that authentication is recommended but still optional to access public models or datasets.\n",
            "  warnings.warn(\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Map:   0%|          | 0/19751 [00:00<?, ? examples/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "6f0d521604764ec2980cdcd572aadc31"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Map:   0%|          | 0/3292 [00:00<?, ? examples/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "d4066f0e2435445dbbb256492f7f90ab"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Map:   0%|          | 0/3292 [00:00<?, ? examples/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "e43084a1f8da46f3abde06b5b457d2e7"
            }
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "labels = [\"Weiblich\", \"Männlich\"]\n",
        "id2label = {0:\"Weiblich\", 1:\"Männlich\"}\n",
        "label2id = {\"Weiblich\":0, \"Männlich\":1}"
      ],
      "metadata": {
        "id": "475ZQKrxbNL_"
      },
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Metrics**"
      ],
      "metadata": {
        "id": "NygY8FTSGxKF"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "import evaluate\n",
        "\n",
        "clf_metrics = evaluate.combine([\"accuracy\", \"f1\", \"precision\", \"recall\"])\n",
        "\n",
        "def compute_metrics(eval_pred):\n",
        "    logits, labels = eval_pred\n",
        "    predictions = np.argmax(logits, axis=-1)\n",
        "    return clf_metrics.compute(predictions=predictions, references=labels)"
      ],
      "metadata": {
        "id": "Hcp0V2mPhMG7"
      },
      "execution_count": 14,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "**init Model and training Args**: \"Longest\" padding allowed a larger batch size. \"Max\" padding allowed a batch size of only 4"
      ],
      "metadata": {
        "id": "gPgMcMaNG3ub"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "model = AutoModelForSequenceClassification.from_pretrained(\n",
        "    modelId,\n",
        "    num_labels=2,\n",
        "    id2label=id2label,\n",
        "    label2id=label2id\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "YpExdBYjc4RQ",
        "outputId": "baf05ad9-5d85-439d-9de5-a813d62e93b0"
      },
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Some weights of XLMRobertaForSequenceClassification were not initialized from the model checkpoint at xlm-roberta-large and are newly initialized: ['classifier.dense.bias', 'classifier.dense.weight', 'classifier.out_proj.bias', 'classifier.out_proj.weight']\n",
            "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "training_args = TrainingArguments(\n",
        "    output_dir=\"/content/sample_data\",\n",
        "    overwrite_output_dir = True,\n",
        "    learning_rate=2e-5,\n",
        "    per_device_train_batch_size=16,\n",
        "    per_device_eval_batch_size=16,\n",
        "    num_train_epochs=2,\n",
        "    weight_decay=0.01,\n",
        "    evaluation_strategy=\"epoch\",\n",
        "    save_strategy=\"epoch\",\n",
        "    load_best_model_at_end=True,\n",
        "    push_to_hub=False,\n",
        ")\n",
        "\n",
        "trainer = Trainer(\n",
        "    model=model,\n",
        "    args=training_args,\n",
        "    train_dataset=tokenized_dataset[\"train\"],\n",
        "    eval_dataset=tokenized_dataset[\"valid\"],\n",
        "    tokenizer=tokenizer,\n",
        "    compute_metrics=compute_metrics,\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5QyGXy3TgSpL",
        "outputId": "2afb9d52-ba24-45a3-f2a9-97341b60584c"
      },
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/accelerate/accelerator.py:432: FutureWarning: Passing the following arguments to `Accelerator` is deprecated and will be removed in version 1.0 of Accelerate: dict_keys(['dispatch_batches', 'split_batches', 'even_batches', 'use_seedable_sampler']). Please pass an `accelerate.DataLoaderConfiguration` instead: \n",
            "dataloader_config = DataLoaderConfiguration(dispatch_batches=None, split_batches=False, even_batches=True, use_seedable_sampler=True)\n",
            "  warnings.warn(\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Train and Test**"
      ],
      "metadata": {
        "id": "ntFkoJo3HAUM"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "trainer.train()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 173
        },
        "id": "B4NO4ZnGiz88",
        "outputId": "6affc585-49ef-4355-aa23-8e1c0a71bf83"
      },
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "\n",
              "    <div>\n",
              "      \n",
              "      <progress value='2470' max='2470' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
              "      [2470/2470 1:05:25, Epoch 2/2]\n",
              "    </div>\n",
              "    <table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              " <tr style=\"text-align: left;\">\n",
              "      <th>Epoch</th>\n",
              "      <th>Training Loss</th>\n",
              "      <th>Validation Loss</th>\n",
              "      <th>Accuracy</th>\n",
              "      <th>F1</th>\n",
              "      <th>Precision</th>\n",
              "      <th>Recall</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <td>1</td>\n",
              "      <td>0.670200</td>\n",
              "      <td>0.663497</td>\n",
              "      <td>0.623937</td>\n",
              "      <td>0.768425</td>\n",
              "      <td>0.623937</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td>2</td>\n",
              "      <td>0.661500</td>\n",
              "      <td>0.662192</td>\n",
              "      <td>0.623937</td>\n",
              "      <td>0.768425</td>\n",
              "      <td>0.623937</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table><p>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "TrainOutput(global_step=2470, training_loss=0.6680283519420547, metrics={'train_runtime': 3927.9977, 'train_samples_per_second': 10.057, 'train_steps_per_second': 0.629, 'total_flos': 1.057453599093906e+16, 'train_loss': 0.6680283519420547, 'epoch': 2.0})"
            ]
          },
          "metadata": {},
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "trainer.evaluate()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 193
        },
        "id": "Jb-i-tJdo8zI",
        "outputId": "04aa19f1-e682-4c45-fa9f-adf78098698e"
      },
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "\n",
              "    <div>\n",
              "      \n",
              "      <progress value='206' max='206' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
              "      [206/206 01:25]\n",
              "    </div>\n",
              "    "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'eval_loss': 0.6621918678283691,\n",
              " 'eval_accuracy': 0.6239368165249088,\n",
              " 'eval_f1': 0.7684249906472128,\n",
              " 'eval_precision': 0.6239368165249088,\n",
              " 'eval_recall': 1.0,\n",
              " 'eval_runtime': 85.7608,\n",
              " 'eval_samples_per_second': 38.386,\n",
              " 'eval_steps_per_second': 2.402,\n",
              " 'epoch': 2.0}"
            ]
          },
          "metadata": {},
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "trainer.evaluate(tokenized_dataset[\"test\"])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 193
        },
        "id": "w17QWjL4Hh7Y",
        "outputId": "fc1e421a-c975-4f39-8edf-baac7cdc8846"
      },
      "execution_count": 19,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "\n",
              "    <div>\n",
              "      \n",
              "      <progress value='412' max='206' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
              "      [206/206 03:49]\n",
              "    </div>\n",
              "    "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'eval_loss': 0.6649479866027832,\n",
              " 'eval_accuracy': 0.6187727825030377,\n",
              " 'eval_f1': 0.7644961531244135,\n",
              " 'eval_precision': 0.6187727825030377,\n",
              " 'eval_recall': 1.0,\n",
              " 'eval_runtime': 89.9471,\n",
              " 'eval_samples_per_second': 36.599,\n",
              " 'eval_steps_per_second': 2.29,\n",
              " 'epoch': 2.0}"
            ]
          },
          "metadata": {},
          "execution_count": 19
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "GRh0lY5fMdix"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}