{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wOvxbAShg-_s",
        "outputId": "0e9a0f9a-fd6e-4ce0-81f6-8da736bd06be"
      },
      "outputs": [],
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/drive')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "THLGsHmchJ9g",
        "outputId": "d590fb47-7b15-4176-9b6e-719090ed2cbd"
      },
      "outputs": [],
      "source": [
        "!pip install textdistance"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "eFxAvy03hPCX"
      },
      "outputs": [],
      "source": [
        "import re\n",
        "from collections import Counter\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "import textdistance\n",
        "\n",
        "w = []\n",
        "with open('/content/drive/MyDrive/words.txt', 'r') as f:\n",
        "  file_name_data = f.read()\n",
        "  file_name_data = file_name_data.lower()\n",
        "  w = re.findall('\\w+', file_name_data)\n",
        "\n",
        "v = set(w)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "RPON8Pm7h9Dx",
        "outputId": "dd1309fd-3362-41c9-8f19-affe4739df3e"
      },
      "outputs": [],
      "source": [
        "print(f\"First 10 words: \\n{w[0:10]}\")\n",
        "print(f\"{len(v)} total words \")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "U4s_UDWKig11"
      },
      "outputs": [],
      "source": [
        "from nltk.metrics.distance import edit_distance\n",
        "def edit(input_sentence):\n",
        "  sentence = input_sentence.split()\n",
        "  \n",
        "  for i in sentence:\n",
        "    if i.lower() in w:\n",
        "      continue\n",
        "    else:\n",
        "      distances = ((edit_distance(i,\n",
        "                                    word), word)\n",
        "                     for word in w)\n",
        "      closest = min(distances)\n",
        "      sentence[sentence.index(i)] = closest[1]\n",
        "  output_sentence = ' '.join(sentence)\n",
        "\n",
        "  return output_sentence"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "c0af01o_i5X0",
        "outputId": "fff4600b-163d-40c8-ce3b-c0b735ec286e"
      },
      "outputs": [],
      "source": [
        "print(edit(\"My namee is  uncele Steven\"))\n",
        "print(edit(\"moneeyeh is greeat\"))"
      ]
    }
  ],
  "metadata": {
    "colab": {
      "name": "autocorrectreal.ipynb",
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}