{ "cells": [ { "cell_type": "code", "execution_count": 149, "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "from IPython.display import clear_output, Markdown, Math\n", "import ipywidgets as widgets\n", "import os\n", "import unicodedata as uni\n", "import numpy as np\n", "from nltk.stem import PorterStemmer\n", "from nltk.tokenize import sent_tokenize, word_tokenize\n", "from nltk.corpus import wordnet\n", "import math\n", "import pprint\n", "\n", "pp=pprint.PrettyPrinter(indent=4)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Naive Approach" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "* read in table" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | Unnamed: 0 | \n", "code | \n", "character | \n", "description | \n", "Unnamed: 4 | \n", "
---|---|---|---|---|---|
0 | \n", "0 | \n", "126980 | \n", "๐ | \n", "MAHJONG TILE RED DRAGON | \n", "NaN | \n", "
1 | \n", "1 | \n", "129525 | \n", "๐งต | \n", "SPOOL OF THREAD | \n", "NaN | \n", "
2 | \n", "2 | \n", "129526 | \n", "๐งถ | \n", "BALL OF YARN | \n", "NaN | \n", "
3 | \n", "3 | \n", "127183 | \n", "๐ | \n", "PLAYING CARD BLACK JOKER | \n", "NaN | \n", "
4 | \n", "4 | \n", "129296 | \n", "๐ค | \n", "ZIPPER-MOUTH FACE | \n", "NaN | \n", "