review_sentiment.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "mount_file_id": "1jWPpmHtnz8FXtN_2f7qv6aQZezZEKLYn",
      "authorship_tag": "ABX9TyN2GTAXMiSnLOuFbzmEj8LS",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU",
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "f7614e419df44164ac7dc7f2dd9fcef5": {
          "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_9763dd01d93849bb96ed684173221036",
              "IPY_MODEL_2056bdd12e2d43408be3be14b4d23ec8",
              "IPY_MODEL_081592b4197647c3bf8f1f30a4f0b76d"
            ],
            "layout": "IPY_MODEL_b8a0abf1fd844519960dba9c7bcc0997"
          }
        },
        "9763dd01d93849bb96ed684173221036": {
          "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_bf662aaaff664b34b9cb5fe5ba9b1d3d",
            "placeholder": "​",
            "style": "IPY_MODEL_737bd098264e4c11884a405229b4d2cf",
            "value": "Downloading: 100%"
          }
        },
        "2056bdd12e2d43408be3be14b4d23ec8": {
          "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_4561471d1bb34fcdae937370c2935408",
            "max": 213450,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_f25a0cfaf2be4ae6932985fa4ab3bfc5",
            "value": 213450
          }
        },
        "081592b4197647c3bf8f1f30a4f0b76d": {
          "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_4fe25cd1631c4a449ae4f6e13736f60c",
            "placeholder": "​",
            "style": "IPY_MODEL_53e0d35532f8423f83f2f233404fcf6e",
            "value": " 213k/213k [00:00&lt;00:00, 3.72MB/s]"
          }
        },
        "b8a0abf1fd844519960dba9c7bcc0997": {
          "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
          }
        },
        "bf662aaaff664b34b9cb5fe5ba9b1d3d": {
          "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
          }
        },
        "737bd098264e4c11884a405229b4d2cf": {
          "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": ""
          }
        },
        "4561471d1bb34fcdae937370c2935408": {
          "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
          }
        },
        "f25a0cfaf2be4ae6932985fa4ab3bfc5": {
          "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": ""
          }
        },
        "4fe25cd1631c4a449ae4f6e13736f60c": {
          "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
          }
        },
        "53e0d35532f8423f83f2f233404fcf6e": {
          "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": ""
          }
        },
        "abab3022c4e5493b8ba3bd88b32f4c62": {
          "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_5c5a0cc16a9f4152aba6a220bd3ddd70",
              "IPY_MODEL_31cbdf0487e346389517e741b9e28e73",
              "IPY_MODEL_1621268e5b05494a85c0ca492719e336"
            ],
            "layout": "IPY_MODEL_003ad4d0f8444ed48d9cfdb0ebb471ad"
          }
        },
        "5c5a0cc16a9f4152aba6a220bd3ddd70": {
          "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_933cd26e508f4e62816fca0eac797582",
            "placeholder": "​",
            "style": "IPY_MODEL_d76e3693d865479088b284a0a9f93597",
            "value": "Downloading: 100%"
          }
        },
        "31cbdf0487e346389517e741b9e28e73": {
          "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_bad767bc947b4b9f9d192972661325ad",
            "max": 29,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_158291dfcc494432bd1e197ff059f577",
            "value": 29
          }
        },
        "1621268e5b05494a85c0ca492719e336": {
          "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_0f619d5ccbb145598af19a1c11e749a9",
            "placeholder": "​",
            "style": "IPY_MODEL_361f7777e28c4823a75d32cb9da22429",
            "value": " 29.0/29.0 [00:00&lt;00:00, 965B/s]"
          }
        },
        "003ad4d0f8444ed48d9cfdb0ebb471ad": {
          "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
          }
        },
        "933cd26e508f4e62816fca0eac797582": {
          "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
          }
        },
        "d76e3693d865479088b284a0a9f93597": {
          "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": ""
          }
        },
        "bad767bc947b4b9f9d192972661325ad": {
          "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
          }
        },
        "158291dfcc494432bd1e197ff059f577": {
          "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": ""
          }
        },
        "0f619d5ccbb145598af19a1c11e749a9": {
          "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
          }
        },
        "361f7777e28c4823a75d32cb9da22429": {
          "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": ""
          }
        },
        "c5b70682bf804d16bf53f52a76e6c1bd": {
          "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_063176f668e449b8b2681179c1cf2b54",
              "IPY_MODEL_819f0b4298a647b28a46d836b9fd2a1b",
              "IPY_MODEL_43d8cd2a3f1b445091f0392218b9439a"
            ],
            "layout": "IPY_MODEL_6c685d839f494a74b6061cafc745acc5"
          }
        },
        "063176f668e449b8b2681179c1cf2b54": {
          "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_0b2f0eb5cafb4290aa508528bfd29f36",
            "placeholder": "​",
            "style": "IPY_MODEL_200bf0a4c27b40cf9ef90085df6b35ef",
            "value": "Downloading: 100%"
          }
        },
        "819f0b4298a647b28a46d836b9fd2a1b": {
          "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_da231ed9ac3945ac8d2227a41ffbf6f2",
            "max": 570,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_4d0be303bd7d4532afb24508d2929374",
            "value": 570
          }
        },
        "43d8cd2a3f1b445091f0392218b9439a": {
          "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_cbe5fd52949d4549844275bec67499d3",
            "placeholder": "​",
            "style": "IPY_MODEL_507061b9462c4682b2d88010fb9a3487",
            "value": " 570/570 [00:00&lt;00:00, 16.8kB/s]"
          }
        },
        "6c685d839f494a74b6061cafc745acc5": {
          "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
          }
        },
        "0b2f0eb5cafb4290aa508528bfd29f36": {
          "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
          }
        },
        "200bf0a4c27b40cf9ef90085df6b35ef": {
          "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": ""
          }
        },
        "da231ed9ac3945ac8d2227a41ffbf6f2": {
          "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
          }
        },
        "4d0be303bd7d4532afb24508d2929374": {
          "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": ""
          }
        },
        "cbe5fd52949d4549844275bec67499d3": {
          "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
          }
        },
        "507061b9462c4682b2d88010fb9a3487": {
          "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": ""
          }
        },
        "f429f531b98d4f3387cd9f4377f45a88": {
          "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_01a7032f55924dd0983c7e9fe9707bc7",
              "IPY_MODEL_57529479218a4752ac4c3e033851f873",
              "IPY_MODEL_0881dfdf3f6c4131b113ca75e3f2ab11"
            ],
            "layout": "IPY_MODEL_e1e31283c07b48cfa9ecee5c844d0c54"
          }
        },
        "01a7032f55924dd0983c7e9fe9707bc7": {
          "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_0ce4f2fa9cc543ae912ff7e60b97a676",
            "placeholder": "​",
            "style": "IPY_MODEL_011e5bd7b8534badb84ebcdcc7b69aa1",
            "value": "Downloading: 100%"
          }
        },
        "57529479218a4752ac4c3e033851f873": {
          "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_422450193cfe46c492c815022869825f",
            "max": 435779157,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_7003eb20971342a89ea50fe83536731f",
            "value": 435779157
          }
        },
        "0881dfdf3f6c4131b113ca75e3f2ab11": {
          "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_9e9944a964344c0da611fec49fd253d8",
            "placeholder": "​",
            "style": "IPY_MODEL_bfacee5e17144e7bb5fef5e6e9c99206",
            "value": " 436M/436M [00:15&lt;00:00, 36.5MB/s]"
          }
        },
        "e1e31283c07b48cfa9ecee5c844d0c54": {
          "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
          }
        },
        "0ce4f2fa9cc543ae912ff7e60b97a676": {
          "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
          }
        },
        "011e5bd7b8534badb84ebcdcc7b69aa1": {
          "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": ""
          }
        },
        "422450193cfe46c492c815022869825f": {
          "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
          }
        },
        "7003eb20971342a89ea50fe83536731f": {
          "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": ""
          }
        },
        "9e9944a964344c0da611fec49fd253d8": {
          "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
          }
        },
        "bfacee5e17144e7bb5fef5e6e9c99206": {
          "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": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/KNU-BrainAI-Capstone2022/ITS/blob/main/review_sentiment.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "jcgr7Jw506xW",
        "outputId": "ad9a22ac-963e-441f-b506-b3ad028cabd6"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
            "Requirement already satisfied: wordcloud in /usr/local/lib/python3.7/dist-packages (1.8.2.2)\n",
            "Requirement already satisfied: numpy>=1.6.1 in /usr/local/lib/python3.7/dist-packages (from wordcloud) (1.21.6)\n",
            "Requirement already satisfied: pillow in /usr/local/lib/python3.7/dist-packages (from wordcloud) (7.1.2)\n",
            "Requirement already satisfied: matplotlib in /usr/local/lib/python3.7/dist-packages (from wordcloud) (3.2.2)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.7/dist-packages (from matplotlib->wordcloud) (0.11.0)\n",
            "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.7/dist-packages (from matplotlib->wordcloud) (1.4.4)\n",
            "Requirement already satisfied: python-dateutil>=2.1 in /usr/local/lib/python3.7/dist-packages (from matplotlib->wordcloud) (2.8.2)\n",
            "Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.1 in /usr/local/lib/python3.7/dist-packages (from matplotlib->wordcloud) (3.0.9)\n",
            "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.7/dist-packages (from kiwisolver>=1.0.1->matplotlib->wordcloud) (4.1.1)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.7/dist-packages (from python-dateutil>=2.1->matplotlib->wordcloud) (1.15.0)\n",
            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
            "Collecting transformers\n",
            "  Downloading transformers-4.22.2-py3-none-any.whl (4.9 MB)\n",
            "\u001b[K     |████████████████████████████████| 4.9 MB 6.7 MB/s \n",
            "\u001b[?25hRequirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.7/dist-packages (from transformers) (21.3)\n",
            "Requirement already satisfied: importlib-metadata in /usr/local/lib/python3.7/dist-packages (from transformers) (5.0.0)\n",
            "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.7/dist-packages (from transformers) (4.64.1)\n",
            "Collecting huggingface-hub<1.0,>=0.9.0\n",
            "  Downloading huggingface_hub-0.10.0-py3-none-any.whl (163 kB)\n",
            "\u001b[K     |████████████████████████████████| 163 kB 57.9 MB/s \n",
            "\u001b[?25hRequirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.7/dist-packages (from transformers) (1.21.6)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.7/dist-packages (from transformers) (2022.6.2)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.7/dist-packages (from transformers) (3.8.0)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.7/dist-packages (from transformers) (2.23.0)\n",
            "Collecting tokenizers!=0.11.3,<0.13,>=0.11.1\n",
            "  Downloading tokenizers-0.12.1-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (6.6 MB)\n",
            "\u001b[K     |████████████████████████████████| 6.6 MB 49.4 MB/s \n",
            "\u001b[?25hRequirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.7/dist-packages (from transformers) (6.0)\n",
            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.7/dist-packages (from huggingface-hub<1.0,>=0.9.0->transformers) (4.1.1)\n",
            "Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in /usr/local/lib/python3.7/dist-packages (from packaging>=20.0->transformers) (3.0.9)\n",
            "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.7/dist-packages (from importlib-metadata->transformers) (3.8.1)\n",
            "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests->transformers) (3.0.4)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests->transformers) (2022.9.24)\n",
            "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.7/dist-packages (from requests->transformers) (1.24.3)\n",
            "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests->transformers) (2.10)\n",
            "Installing collected packages: tokenizers, huggingface-hub, transformers\n",
            "Successfully installed huggingface-hub-0.10.0 tokenizers-0.12.1 transformers-4.22.2\n"
          ]
        }
      ],
      "source": [
        "!pip install wordcloud\n",
        "!pip install transformers"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import torch\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "import torch.nn as nn\n",
        "import torch.optim as optim\n",
        "\n",
        "from transformers import BertTokenizer, BertForSequenceClassification\n",
        "\n",
        "from sklearn.metrics import accuracy_score, classification_report, confusion_matrix\n",
        "import seaborn as sns"
      ],
      "metadata": {
        "id": "xY86_JA32zMk"
      },
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "use_cuda = torch.cuda.is_available()\n",
        "device = torch.device(\"cuda\" if use_cuda else \"cpu\")\n",
        "print(device)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "rAhti1Cg3AZs",
        "outputId": "6796eae8-54ad-4d28-de81-bbdf4e2e19a4"
      },
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "cuda\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "path = '/content/drive/MyDrive/fake reviews dataset.csv'\n",
        "\n",
        "df = pd.read_csv(path)\n",
        "print(df.shape)\n",
        "df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 224
        },
        "id": "0RELDzs-3C5n",
        "outputId": "c5a19bab-a70a-46db-b592-2ef08968865c"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(40432, 4)\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "             category  rating label  \\\n",
              "0  Home_and_Kitchen_5     5.0    CG   \n",
              "1  Home_and_Kitchen_5     5.0    CG   \n",
              "2  Home_and_Kitchen_5     5.0    CG   \n",
              "3  Home_and_Kitchen_5     1.0    CG   \n",
              "4  Home_and_Kitchen_5     5.0    CG   \n",
              "\n",
              "                                               text_  \n",
              "0  Love this!  Well made, sturdy, and very comfor...  \n",
              "1  love it, a great upgrade from the original.  I...  \n",
              "2  This pillow saved my back. I love the look and...  \n",
              "3  Missing information on how to use it, but it i...  \n",
              "4  Very nice set. Good quality. We have had the s...  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-4636e581-2e09-4274-b3d7-01469282188a\">\n",
              "    <div 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>category</th>\n",
              "      <th>rating</th>\n",
              "      <th>label</th>\n",
              "      <th>text_</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Home_and_Kitchen_5</td>\n",
              "      <td>5.0</td>\n",
              "      <td>CG</td>\n",
              "      <td>Love this!  Well made, sturdy, and very comfor...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Home_and_Kitchen_5</td>\n",
              "      <td>5.0</td>\n",
              "      <td>CG</td>\n",
              "      <td>love it, a great upgrade from the original.  I...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Home_and_Kitchen_5</td>\n",
              "      <td>5.0</td>\n",
              "      <td>CG</td>\n",
              "      <td>This pillow saved my back. I love the look and...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Home_and_Kitchen_5</td>\n",
              "      <td>1.0</td>\n",
              "      <td>CG</td>\n",
              "      <td>Missing information on how to use it, but it i...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Home_and_Kitchen_5</td>\n",
              "      <td>5.0</td>\n",
              "      <td>CG</td>\n",
              "      <td>Very nice set. Good quality. We have had the s...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-4636e581-2e09-4274-b3d7-01469282188a')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-4636e581-2e09-4274-b3d7-01469282188a 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-4636e581-2e09-4274-b3d7-01469282188a');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df['division'] = np.select([df.rating > 3], [1], default=0)\n",
        "df[:5]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "fm6a8OC33Eoc",
        "outputId": "26d155ba-3374-4e9e-cb2a-5a459e869e7f"
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "             category  rating label  \\\n",
              "0  Home_and_Kitchen_5     5.0    CG   \n",
              "1  Home_and_Kitchen_5     5.0    CG   \n",
              "2  Home_and_Kitchen_5     5.0    CG   \n",
              "3  Home_and_Kitchen_5     1.0    CG   \n",
              "4  Home_and_Kitchen_5     5.0    CG   \n",
              "\n",
              "                                               text_  division  \n",
              "0  Love this!  Well made, sturdy, and very comfor...         1  \n",
              "1  love it, a great upgrade from the original.  I...         1  \n",
              "2  This pillow saved my back. I love the look and...         1  \n",
              "3  Missing information on how to use it, but it i...         0  \n",
              "4  Very nice set. Good quality. We have had the s...         1  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-2386e69e-deac-439a-aa64-4efe3e2c7ec1\">\n",
              "    <div 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>category</th>\n",
              "      <th>rating</th>\n",
              "      <th>label</th>\n",
              "      <th>text_</th>\n",
              "      <th>division</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Home_and_Kitchen_5</td>\n",
              "      <td>5.0</td>\n",
              "      <td>CG</td>\n",
              "      <td>Love this!  Well made, sturdy, and very comfor...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Home_and_Kitchen_5</td>\n",
              "      <td>5.0</td>\n",
              "      <td>CG</td>\n",
              "      <td>love it, a great upgrade from the original.  I...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Home_and_Kitchen_5</td>\n",
              "      <td>5.0</td>\n",
              "      <td>CG</td>\n",
              "      <td>This pillow saved my back. I love the look and...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Home_and_Kitchen_5</td>\n",
              "      <td>1.0</td>\n",
              "      <td>CG</td>\n",
              "      <td>Missing information on how to use it, but it i...</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Home_and_Kitchen_5</td>\n",
              "      <td>5.0</td>\n",
              "      <td>CG</td>\n",
              "      <td>Very nice set. Good quality. We have had the s...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-2386e69e-deac-439a-aa64-4efe3e2c7ec1')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-2386e69e-deac-439a-aa64-4efe3e2c7ec1 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-2386e69e-deac-439a-aa64-4efe3e2c7ec1');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "tokenizer = BertTokenizer.from_pretrained('bert-base-cased') # 'bert-base-cased': 영어용, 한국어 및 다른 언어시 변경 필요\n",
        "\n",
        "# example_text = 'I will watch Memento tonight'\n",
        "# bert_input = tokenizer(example_text,padding='max_length', max_length = 10, \n",
        "#                        truncation=True, return_tensors=\"pt\")\n",
        "\n",
        "# # padding : to pad each sequence to the maximum length that you specify\n",
        "# # max_length : the maximum length of each sequence.\n",
        "# #              For our actual dataset we will use 512, which is the maximum length of a sequence allowed for BERT.\n",
        "# # truncation : if True, then the tokens in each sequence that exceed the maximum length will be truncated.\n",
        "# # return_tensors : the type of tensors that will be returned. \n",
        "# #                  Pytorch: pt. \n",
        "# #                  Tensorflow: tf\n",
        "\n",
        "\n",
        "# print(bert_input['input_ids'])\n",
        "# # >>>tensor([[  101,   146,  1209,  2824,  2508, 26173,  3568,   102,     0,     0]])\n",
        "# # tokenizer.decode(bert_input.input_ids[0])\n",
        "# # >>> [CLS] I will watch Memento tonight [SEP] [PAD] [PAD]\n",
        "# # BertTokenizer가 알아서 다 해줌\n",
        "# print(bert_input['token_type_ids'])\n",
        "# # >>>tensor([[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]])\n",
        "# print(bert_input['attention_mask'])\n",
        "# # >>>tensor([[1, 1, 1, 1, 1, 1, 1, 1, 0, 0]])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 113,
          "referenced_widgets": [
            "f7614e419df44164ac7dc7f2dd9fcef5",
            "9763dd01d93849bb96ed684173221036",
            "2056bdd12e2d43408be3be14b4d23ec8",
            "081592b4197647c3bf8f1f30a4f0b76d",
            "b8a0abf1fd844519960dba9c7bcc0997",
            "bf662aaaff664b34b9cb5fe5ba9b1d3d",
            "737bd098264e4c11884a405229b4d2cf",
            "4561471d1bb34fcdae937370c2935408",
            "f25a0cfaf2be4ae6932985fa4ab3bfc5",
            "4fe25cd1631c4a449ae4f6e13736f60c",
            "53e0d35532f8423f83f2f233404fcf6e",
            "abab3022c4e5493b8ba3bd88b32f4c62",
            "5c5a0cc16a9f4152aba6a220bd3ddd70",
            "31cbdf0487e346389517e741b9e28e73",
            "1621268e5b05494a85c0ca492719e336",
            "003ad4d0f8444ed48d9cfdb0ebb471ad",
            "933cd26e508f4e62816fca0eac797582",
            "d76e3693d865479088b284a0a9f93597",
            "bad767bc947b4b9f9d192972661325ad",
            "158291dfcc494432bd1e197ff059f577",
            "0f619d5ccbb145598af19a1c11e749a9",
            "361f7777e28c4823a75d32cb9da22429",
            "c5b70682bf804d16bf53f52a76e6c1bd",
            "063176f668e449b8b2681179c1cf2b54",
            "819f0b4298a647b28a46d836b9fd2a1b",
            "43d8cd2a3f1b445091f0392218b9439a",
            "6c685d839f494a74b6061cafc745acc5",
            "0b2f0eb5cafb4290aa508528bfd29f36",
            "200bf0a4c27b40cf9ef90085df6b35ef",
            "da231ed9ac3945ac8d2227a41ffbf6f2",
            "4d0be303bd7d4532afb24508d2929374",
            "cbe5fd52949d4549844275bec67499d3",
            "507061b9462c4682b2d88010fb9a3487"
          ]
        },
        "id": "bzlzFfOA5FQv",
        "outputId": "b9cfc9d8-983d-4d89-baba-58dc4025233b"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading:   0%|          | 0.00/213k [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "f7614e419df44164ac7dc7f2dd9fcef5"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading:   0%|          | 0.00/29.0 [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "abab3022c4e5493b8ba3bd88b32f4c62"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading:   0%|          | 0.00/570 [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "c5b70682bf804d16bf53f52a76e6c1bd"
            }
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "class Dataset(torch.utils.data.Dataset):\n",
        "\n",
        "    def __init__(self, df):\n",
        "\n",
        "        self.divisions = [division for division in df['division']]\n",
        "        self.texts = [tokenizer(text, \n",
        "                               padding='max_length', max_length = 512, truncation=True,\n",
        "                                return_tensors=\"pt\") for text in df['text_']]\n",
        "    def classes(self):\n",
        "        return self.divisions\n",
        "\n",
        "    def __len__(self):\n",
        "        return len(self.divisions)\n",
        "\n",
        "    def get_batch_divisions(self, idx):\n",
        "        # Fetch a batch of labels\n",
        "        return np.array(self.divisions[idx])\n",
        "\n",
        "    def get_batch_texts(self, idx):\n",
        "        # Fetch a batch of inputs\n",
        "        return self.texts[idx]\n",
        "\n",
        "    def __getitem__(self, idx):\n",
        "\n",
        "        batch_texts = self.get_batch_texts(idx)\n",
        "        batch_y = self.get_batch_divisions(idx)\n",
        "\n",
        "        return batch_texts, batch_y\n",
        "\n",
        "df[:5]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "dN1nnSzb5TUJ",
        "outputId": "340f6a82-e48b-4f86-9442-b7a98d9339be"
      },
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "             category  rating label  \\\n",
              "0  Home_and_Kitchen_5     5.0    CG   \n",
              "1  Home_and_Kitchen_5     5.0    CG   \n",
              "2  Home_and_Kitchen_5     5.0    CG   \n",
              "3  Home_and_Kitchen_5     1.0    CG   \n",
              "4  Home_and_Kitchen_5     5.0    CG   \n",
              "\n",
              "                                               text_  division  \n",
              "0  Love this!  Well made, sturdy, and very comfor...         1  \n",
              "1  love it, a great upgrade from the original.  I...         1  \n",
              "2  This pillow saved my back. I love the look and...         1  \n",
              "3  Missing information on how to use it, but it i...         0  \n",
              "4  Very nice set. Good quality. We have had the s...         1  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-1c0ef325-3000-44d9-a504-b5bee8bed976\">\n",
              "    <div 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>category</th>\n",
              "      <th>rating</th>\n",
              "      <th>label</th>\n",
              "      <th>text_</th>\n",
              "      <th>division</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Home_and_Kitchen_5</td>\n",
              "      <td>5.0</td>\n",
              "      <td>CG</td>\n",
              "      <td>Love this!  Well made, sturdy, and very comfor...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Home_and_Kitchen_5</td>\n",
              "      <td>5.0</td>\n",
              "      <td>CG</td>\n",
              "      <td>love it, a great upgrade from the original.  I...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Home_and_Kitchen_5</td>\n",
              "      <td>5.0</td>\n",
              "      <td>CG</td>\n",
              "      <td>This pillow saved my back. I love the look and...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Home_and_Kitchen_5</td>\n",
              "      <td>1.0</td>\n",
              "      <td>CG</td>\n",
              "      <td>Missing information on how to use it, but it i...</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Home_and_Kitchen_5</td>\n",
              "      <td>5.0</td>\n",
              "      <td>CG</td>\n",
              "      <td>Very nice set. Good quality. We have had the s...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-1c0ef325-3000-44d9-a504-b5bee8bed976')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-1c0ef325-3000-44d9-a504-b5bee8bed976 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-1c0ef325-3000-44d9-a504-b5bee8bed976');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "np.random.seed(112)\n",
        "df_train, df_val, df_test = np.split(df.sample(frac=1, random_state=42), \n",
        "                                     [int(.7*len(df)), int(.9*len(df))]) # train: 70, validation: 20, test: 10\n",
        "\n",
        "print(len(df_train),len(df_val), len(df_test))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Xse75DRj6Y-2",
        "outputId": "896c552d-a18d-4850-f1be-685766416259"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "28302 8086 4044\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from torch import nn\n",
        "from transformers import BertModel\n",
        "\n",
        "class BertClassifier(nn.Module):\n",
        "\n",
        "    def __init__(self, dropout=0.5):\n",
        "\n",
        "        super(BertClassifier, self).__init__()\n",
        "\n",
        "        self.bert = BertModel.from_pretrained('bert-base-cased') # 'bert-base-cased': 영어용, 다른 언어의 데이터면 다른거 쓰기\n",
        "        self.dropout = nn.Dropout(dropout)\n",
        "        self.linear = nn.Linear(768, 2)\n",
        "        self.relu = nn.ReLU()\n",
        "\n",
        "    def forward(self, input_id, mask):\n",
        "\n",
        "        _, pooled_output = self.bert(input_ids= input_id, attention_mask=mask,return_dict=False)\n",
        "        # _: embedding vectors of all of the tokens in a sequence\n",
        "        # pooled_output: embedding vector of [CLS] token, 분류 문제에선 이것만 써도 충분\n",
        "        dropout_output = self.dropout(pooled_output)\n",
        "        linear_output = self.linear(dropout_output)\n",
        "        final_layer = self.relu(linear_output)\n",
        "\n",
        "        return final_layer"
      ],
      "metadata": {
        "id": "KsQdOBAj61Zo"
      },
      "execution_count": 9,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "rUEHfQelbKFP"
      },
      "execution_count": 9,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from tqdm import tqdm\n",
        "\n",
        "def train(model, train_data, val_data, learning_rate, epochs, cuda_switch):\n",
        "\n",
        "    train, val = Dataset(train_data), Dataset(val_data)\n",
        "\n",
        "    train_dataloader = torch.utils.data.DataLoader(train, batch_size=2, shuffle=True)\n",
        "    val_dataloader = torch.utils.data.DataLoader(val, batch_size=2)\n",
        "\n",
        "    use_cuda = torch.cuda.is_available()\n",
        "    device = torch.device(\"cuda\" if use_cuda else \"cpu\")\n",
        "\n",
        "    criterion = nn.CrossEntropyLoss()\n",
        "    optimizer = optim.Adam(model.parameters(), lr= learning_rate)\n",
        "\n",
        "    if cuda_switch:\n",
        "\n",
        "            model = model.cuda()\n",
        "            criterion = criterion.cuda()\n",
        "\n",
        "    for epoch_num in range(epochs):\n",
        "\n",
        "            total_acc_train = 0\n",
        "            total_loss_train = 0\n",
        "\n",
        "            for train_input, train_division in tqdm(train_dataloader):\n",
        "\n",
        "                train_division = train_division.to(device)\n",
        "                mask = train_input['attention_mask'].to(device)\n",
        "                input_id = train_input['input_ids'].squeeze(1).to(device)\n",
        "\n",
        "                output = model(input_id, mask)\n",
        "                \n",
        "                batch_loss = criterion(output, train_division)\n",
        "                total_loss_train += batch_loss.item()\n",
        "                \n",
        "                acc = (output.argmax(dim=1) == train_division).sum().item()\n",
        "                total_acc_train += acc\n",
        "\n",
        "                model.zero_grad()\n",
        "                batch_loss.backward()\n",
        "                optimizer.step()\n",
        "            \n",
        "            total_acc_val = 0\n",
        "            total_loss_val = 0\n",
        "\n",
        "            with torch.no_grad():\n",
        "\n",
        "                for val_input, val_division in val_dataloader:\n",
        "\n",
        "                    val_division = val_division.to(device)\n",
        "                    mask = val_input['attention_mask'].to(device)\n",
        "                    input_id = val_input['input_ids'].squeeze(1).to(device)\n",
        "\n",
        "                    output = model(input_id, mask)\n",
        "\n",
        "                    batch_loss = criterion(output, val_division)\n",
        "                    total_loss_val += batch_loss.item()\n",
        "                    \n",
        "                    acc = (output.argmax(dim=1) == val_division).sum().item()\n",
        "                    total_acc_val += acc\n",
        "            \n",
        "            print(\n",
        "                f'Epochs: {epoch_num + 1} | Train Loss: {total_loss_train / len(train_data): .3f} \\\n",
        "                | Train Accuracy: {total_acc_train / len(train_data): .3f} \\\n",
        "                | Val Loss: {total_loss_val / len(val_data): .3f} \\\n",
        "                | Val Accuracy: {total_acc_val / len(val_data): .3f}')\n",
        "                  \n",
        "EPOCHS = 2 \n",
        "model = BertClassifier()\n",
        "LR = 1e-6\n",
        "              \n",
        "train(model, df_train, df_val, LR, EPOCHS, use_cuda)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 197,
          "referenced_widgets": [
            "f429f531b98d4f3387cd9f4377f45a88",
            "01a7032f55924dd0983c7e9fe9707bc7",
            "57529479218a4752ac4c3e033851f873",
            "0881dfdf3f6c4131b113ca75e3f2ab11",
            "e1e31283c07b48cfa9ecee5c844d0c54",
            "0ce4f2fa9cc543ae912ff7e60b97a676",
            "011e5bd7b8534badb84ebcdcc7b69aa1",
            "422450193cfe46c492c815022869825f",
            "7003eb20971342a89ea50fe83536731f",
            "9e9944a964344c0da611fec49fd253d8",
            "bfacee5e17144e7bb5fef5e6e9c99206"
          ]
        },
        "id": "EOcXmOBm64kb",
        "outputId": "1c911c19-1619-4436-d0af-fbabb775f49e"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading:   0%|          | 0.00/436M [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "f429f531b98d4f3387cd9f4377f45a88"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Some weights of the model checkpoint at bert-base-cased were not used when initializing BertModel: ['cls.predictions.transform.dense.weight', 'cls.predictions.bias', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.seq_relationship.bias', 'cls.seq_relationship.weight', 'cls.predictions.decoder.weight']\n",
            "- This IS expected if you are initializing BertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
            "- This IS NOT expected if you are initializing BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
            "100%|██████████| 14151/14151 [50:09<00:00,  4.70it/s]\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epochs: 1 | Train Loss:  0.203                 | Train Accuracy:  0.827                 | Val Loss:  0.180                 | Val Accuracy:  0.852\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "100%|██████████| 14151/14151 [50:17<00:00,  4.69it/s]\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epochs: 2 | Train Loss:  0.164                 | Train Accuracy:  0.866                 | Val Loss:  0.170                 | Val Accuracy:  0.858\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "def evaluate(model, test_data):\n",
        "\n",
        "    test = Dataset(test_data)\n",
        "\n",
        "    test_dataloader = torch.utils.data.DataLoader(test, batch_size=2)\n",
        "\n",
        "    use_cuda = torch.cuda.is_available()\n",
        "    device = torch.device(\"cuda\" if use_cuda else \"cpu\")\n",
        "\n",
        "    if use_cuda:\n",
        "\n",
        "        model = model.cuda()\n",
        "\n",
        "    total_acc_test = 0\n",
        "    with torch.no_grad():\n",
        "\n",
        "        for test_input, test_division in test_dataloader:\n",
        "\n",
        "              test_division = test_division.to(device)\n",
        "              mask = test_input['attention_mask'].to(device)\n",
        "              input_id = test_input['input_ids'].squeeze(1).to(device)\n",
        "\n",
        "              output = model(input_id, mask)\n",
        "\n",
        "              acc = (output.argmax(dim=1) == test_division).sum().item()\n",
        "              total_acc_test += acc\n",
        "    \n",
        "    print(f'Test Accuracy: {total_acc_test / len(test_data): .3f}')\n",
        "    \n",
        "evaluate(model, df_test)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "usg91Xjr7Jv3",
        "outputId": "02796cb4-9f64-4861-a6b7-10ce8d9ca5b2"
      },
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Test Accuracy:  0.845\n"
          ]
        }
      ]
    }
  ]
}