error_statistics.ipynb

error_statistics.ipynb

{
  "cells": [
    {
      "metadata": {
        "trusted": true,
        "ExecuteTime": {
          "start_time": "2021-11-10T13:04:38.577055Z",
          "end_time": "2021-11-10T13:04:42.387554Z"
        }
      },
      "cell_type": "code",
      "source": "# example of french\n\nimport language_tool_python\n\ntool = language_tool_python.LanguageTool('fr')  #\n\ndef log_errors(obj):\n    for error in obj:\n        print(\"The potential error span is:\")\n        print({text[error.offset:(error.offset+error.errorLength)]})\n        print(f\"The error category is {error.category}\")",
      "execution_count": 1,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "ExecuteTime": {
          "start_time": "2021-11-10T13:17:56.513778Z",
          "end_time": "2021-11-10T13:17:56.728444Z"
        }
      },
      "cell_type": "code",
      "source": "text = 'c\\'est incroyale et ce son de joli filles.'\nmatches = tool.check(text)\n\nprint(f\"the original sentence is \\n{text}\\n\\n\")\nprint(f\"the proposed sentence correction is \\n{tool.correct(text)}\\n\\n\\n\")\n\nlog_errors(matches)\n    \nprint(f\"\\n\\n\\nThe total number of errors is {len(matches)}\")",
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "text": "the original sentence is \nc'est incroyale et ce son de joli filles.\n\n\nthe proposed sentence correction is \nC'est incroyable et ce son de jolies filles.\n\n\n\nThe potential error span is:\n{\"c'\"}\nThe error category is CASING\nThe potential error span is:\n{'incroyale'}\nThe error category is TYPOS\nThe potential error span is:\n{'joli filles'}\nThe error category is AGREEMENT\n\n\n\nThe total number of errors is 3\n",
          "name": "stdout"
        }
      ]
    }
  ],
  "metadata": {
    "interpreter": {
      "hash": "40d3a090f54c6569ab1632332b64b2c03c39dcf918b08424e98f38b5ae0af88f"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3",
      "language": "python"
    },
    "language_info": {
      "name": "python",
      "version": "3.7.6",
      "mimetype": "text/x-python",
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "pygments_lexer": "ipython3",
      "nbconvert_exporter": "python",
      "file_extension": ".py"
    },
    "varInspector": {
      "window_display": false,
      "cols": {
        "lenName": 16,
        "lenType": 16,
        "lenVar": 40
      },
      "kernels_config": {
        "python": {
          "library": "var_list.py",
          "delete_cmd_prefix": "del ",
          "delete_cmd_postfix": "",
          "varRefreshCmd": "print(var_dic_list())"
        },
        "r": {
          "library": "var_list.r",
          "delete_cmd_prefix": "rm(",
          "delete_cmd_postfix": ") ",
          "varRefreshCmd": "cat(var_dic_list()) "
        }
      },
      "types_to_exclude": [
        "module",
        "function",
        "builtin_function_or_method",
        "instance",
        "_Feature"
      ]
    },
    "toc": {
      "nav_menu": {},
      "number_sections": true,
      "sideBar": false,
      "skip_h1_title": true,
      "base_numbering": 1,
      "title_cell": "Table des matières",
      "title_sidebar": "Contents",
      "toc_cell": false,
      "toc_position": {},
      "toc_section_display": true,
      "toc_window_display": false
    },
    "nbTranslate": {
      "hotkey": "alt-t",
      "sourceLang": "en",
      "targetLang": "fr",
      "displayLangs": [
        "*"
      ],
      "langInMainMenu": true,
      "useGoogleTranslate": true
    },
    "gist": {
      "id": "5345dc0290bf90f5702e9e660a97eaca",
      "data": {
        "description": "error_statistics.ipynb",
        "public": true
      }
    },
    "_draft": {
      "nbviewer_url": "https://gist.github.com/5345dc0290bf90f5702e9e660a97eaca"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 2
}