Copy of kanji deck.ipynb

copy-of-kanji-deck.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Copy of kanji deck.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyNFzKbad9KS072j5FvGijrL",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/cademcniven/6b10c40652a36a8be2bc14d19f69a5c1/copy-of-kanji-deck.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "eQaBFCYe7Rim",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "1034a637-41e4-442b-a192-c1db9769adcf"
      },
      "source": [
        "from google.colab import drive\n",
        "import pandas as pd\n",
        "import numpy as np\n",
        "\n",
        "#mount google drive so I can grab files from there\n",
        "drive.mount('/content/drive', force_remount=True)\n",
        "\n",
        "kanji = pd.read_csv(\"/content/drive/My Drive/kanji.csv\")\n",
        "deck = pd.read_csv(\"/content/drive/My Drive/morphy.csv\")\n",
        "\n",
        "kanji.rename(columns={\"keyword\": \"readingEN\"}, inplace=True)\n",
        "deck = deck.astype(str)\n",
        "\n",
        "#make a KLC order dictionary\n",
        "kanjiFreq = dict(zip(kanji.kanji, kanji.id))\n",
        "\n",
        "deck\n",
        "\n",
        "# assign a \"tempID\" to each word, which is the number of the highest KLC ID kanji in the word\n",
        "for index, row in deck.iterrows():\n",
        "  #split the word into the individual kanji\n",
        "  unknowns = str(row['MorphMan_Unknowns'])\n",
        "\n",
        "  wordList = unknowns.split(\", \")\n",
        "  largestKanjiFreq = 0\n",
        "  for word in wordList:\n",
        "    #loop through every kanji in the word to find which one has the highest number\n",
        "    #in the frequency index\n",
        "    for character in word:\n",
        "      temp = kanjiFreq.get(str(character))\n",
        "      if (temp is not None and temp > largestKanjiFreq):\n",
        "        largestKanjiFreq = temp\n",
        "        deck.at[index, \"word\"] = word\n",
        "    \n",
        "    deck.at[index, \"tempId\"] = largestKanjiFreq\n",
        "\n",
        "deck.drop_duplicates(subset=[\"word\"], keep='first', inplace=True)\n",
        "\n",
        "deck\n",
        "\n",
        "#export df to a new csv file\n",
        "deck.to_csv('/content/drive/My Drive/newmorphy.csv', index=False)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Mounted at /content/drive\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.6/dist-packages/IPython/core/interactiveshell.py:2718: DtypeWarning: Columns (3,8) have mixed types.Specify dtype option on import or set low_memory=False.\n",
            "  interactivity=interactivity, compiler=compiler, result=result)\n"
          ],
          "name": "stderr"
        }
      ]
    }
  ]
}