diff --git a/Project/Tools/Preprocessing.ipynb b/Project/Tools/Preprocessing.ipynb new file mode 100644 index 0000000..3d829dd --- /dev/null +++ b/Project/Tools/Preprocessing.ipynb @@ -0,0 +1,151 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd\n", + "from nltk.corpus import stopwords" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [], + "source": [ + "table = pd.read_csv(\"emoji_descriptions.csv\", names=(\"id\",\"char\", \"description\"))" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idchardescription
NaNcodecharacterdescripion,
0.0126980๐Ÿ€„MAHJONG TILE RED DRAGON
1.0129525๐ŸงตSPOOL OF THREAD
2.0129526๐ŸงถBALL OF YARN
3.0127183๐ŸƒPLAYING CARD BLACK JOKER
\n", + "
" + ], + "text/plain": [ + " id char description\n", + "NaN code character descripion,\n", + " 0.0 126980 ๐Ÿ€„ MAHJONG TILE RED DRAGON\n", + " 1.0 129525 ๐Ÿงต SPOOL OF THREAD\n", + " 2.0 129526 ๐Ÿงถ BALL OF YARN\n", + " 3.0 127183 ๐Ÿƒ PLAYING CARD BLACK JOKER" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "table.head()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "prepStep1Table = table\n", + "print(table[3])\n", + "# lowercasing\n", + "#for entry in table[\"description\"][1:]:\n", + " # prepStep1Table[\"description\"][entry] = table[\"description\"][entry].toLower()\n", + "#print(prepStep1Table)\n", + "#stopword removal\n", + "#for entry in prepStep1Table[\"description\"][1:]:" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.4" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +}