nlp-lab/Project/naive_approach/naive_approach.ipynb
2018-05-31 15:23:57 +02:00

428 lines
12 KiB
Plaintext

{
"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": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Unnamed: 0</th>\n",
" <th>code</th>\n",
" <th>character</th>\n",
" <th>description</th>\n",
" <th>Unnamed: 4</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>126980</td>\n",
" <td>🀄</td>\n",
" <td>MAHJONG TILE RED DRAGON</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>129525</td>\n",
" <td>🧵</td>\n",
" <td>SPOOL OF THREAD</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2</td>\n",
" <td>129526</td>\n",
" <td>🧶</td>\n",
" <td>BALL OF YARN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>127183</td>\n",
" <td>🃏</td>\n",
" <td>PLAYING CARD BLACK JOKER</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4</td>\n",
" <td>129296</td>\n",
" <td>🤐</td>\n",
" <td>ZIPPER-MOUTH FACE</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 code character description Unnamed: 4\n",
"0 0 126980 🀄 MAHJONG TILE RED DRAGON NaN\n",
"1 1 129525 🧵 SPOOL OF THREAD NaN\n",
"2 2 129526 🧶 BALL OF YARN NaN\n",
"3 3 127183 🃏 PLAYING CARD BLACK JOKER NaN\n",
"4 4 129296 🤐 ZIPPER-MOUTH FACE NaN"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"table = pd.read_csv('../Tools/emoji_descriptions.csv')\n",
"table.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"* todo: read in a lot of messages"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"messages = [\"Hello, this is a testing message\", \"this is a very sunny day today, i am very happy\"]"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"ps = PorterStemmer()"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"stemmed_messages = []\n",
"for m in messages:\n",
" words = word_tokenize(m)\n",
" sm = []\n",
" for w in words:\n",
" sm.append(ps.stem(w))\n",
" stemmed_messages.append(sm)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[['hello', ',', 'thi', 'is', 'a', 'test', 'messag'],\n",
" ['thi',\n",
" 'is',\n",
" 'a',\n",
" 'veri',\n",
" 'sunni',\n",
" 'day',\n",
" 'today',\n",
" ',',\n",
" 'i',\n",
" 'am',\n",
" 'veri',\n",
" 'happi']]"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"stemmed_messages"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(1027, 5)"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"table.shape"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"* compare words to emoji descriptions"
]
},
{
"cell_type": "code",
"execution_count": 59,
"metadata": {},
"outputs": [],
"source": [
"def evaluate_sentence(sentence):\n",
" tokenized_sentence = word_tokenize(sentence)\n",
" n = len(tokenized_sentence)\n",
" l = table.shape[0]\n",
" matrix_list = []\n",
" \n",
" for index, row in table.iterrows():\n",
" emoji_tokens = word_tokenize(row['description'])\n",
" m = len(emoji_tokens)\n",
"\n",
" mat = np.zeros(shape=(m,n))\n",
" for i in range(len(emoji_tokens)):\n",
" for j in range(len(tokenized_sentence)):\n",
" syn1 = wordnet.synsets(emoji_tokens[i])\n",
" if len(syn1) == 0:\n",
" continue\n",
" w1 = syn1[0]\n",
" #print(j, tokenized_sentence)\n",
" syn2 = wordnet.synsets(tokenized_sentence[j])\n",
" if len(syn2) == 0:\n",
" continue\n",
" w2 = syn2[0]\n",
" val = w1.wup_similarity(w2)\n",
" if val is None:\n",
" continue\n",
" mat[i,j] = val\n",
" #print(row['character'], mat)\n",
" matrix_list.append(mat)\n",
" \n",
" return matrix_list\n",
" \n",
" "
]
},
{
"cell_type": "code",
"execution_count": 130,
"metadata": {},
"outputs": [],
"source": [
"result = evaluate_sentence(\"I like playing soccer\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"* building a lookup table:"
]
},
{
"cell_type": "code",
"execution_count": 131,
"metadata": {},
"outputs": [],
"source": [
"lookup = {}\n",
"for index, row in table.iterrows():\n",
" lookup[index] = row['character']"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"* sorting"
]
},
{
"cell_type": "code",
"execution_count": 139,
"metadata": {},
"outputs": [],
"source": [
"summed = np.argsort([-np.sum(x) for x in result])\n",
"max_val = np.argsort([-np.max(x) for x in result])\n",
"avg = np.argsort([-np.mean(x) for x in result])\n",
"\n",
"t = 0.9\n",
"threshold = np.argsort([-len(np.where(x>t)[0]) / (x.shape[0] * x.shape[1]) for x in result])\n"
]
},
{
"cell_type": "code",
"execution_count": 156,
"metadata": {},
"outputs": [],
"source": [
"def print_best_results(sorted_indices, n=10):\n",
" pp.pprint([lookup[x] + \" -- \" + str(table.iloc[x]['description']) for x in sorted_indices[:10]])\n",
" pp.pprint([result[x] for x in sorted_indices[:10]])"
]
},
{
"cell_type": "code",
"execution_count": 157,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[ '⚽ -- SOCCER BALL',\n",
" '🏉 -- RUGBY FOOTBALL',\n",
" '🏈 -- AMERICAN FOOTBALL',\n",
" '🎴 -- FLOWER PLAYING CARDS',\n",
" '🃏 -- PLAYING CARD BLACK JOKER',\n",
" '🇮 -- REGIONAL INDICATOR SYMBOL LETTER I',\n",
" '\\U0001f91f -- I LOVE YOU HAND SIGN',\n",
" '📧 -- E-MAIL SYMBOL',\n",
" '📭 -- OPEN MAILBOX WITH LOWERED FLAG',\n",
" '📥 -- INBOX TRAY']\n",
"[ array([[0.25 , 0.28571429, 0.58333333, 1. ],\n",
" [0.26666667, 0.10526316, 0.1 , 0.1 ]]),\n",
" array([[0.25 , 0.28571429, 0.58333333, 0.84615385],\n",
" [0.26666667, 0.3 , 0.60869565, 0.96 ]]),\n",
" array([[0.33333333, 0.125 , 0.11764706, 0.11764706],\n",
" [0.26666667, 0.3 , 0.60869565, 0.96 ]]),\n",
" array([[0.23529412, 0.0952381 , 0.09090909, 0.09090909],\n",
" [0.25 , 0.47619048, 1. , 0.58333333],\n",
" [0.30769231, 0.33333333, 0.57142857, 0.7 ]]),\n",
" array([[0.25 , 0.47619048, 1. , 0.58333333],\n",
" [0.53333333, 0.22222222, 0.21052632, 0.21052632],\n",
" [0.30769231, 0.22222222, 0.21052632, 0.21052632],\n",
" [0.28571429, 0.11111111, 0.10526316, 0.10526316]]),\n",
" array([[0. , 0. , 0. , 0. ],\n",
" [0.33333333, 0.23529412, 0.22222222, 0.22222222],\n",
" [0.4 , 0.26666667, 0.25 , 0.25 ],\n",
" [0.30769231, 0.22222222, 0.21052632, 0.21052632],\n",
" [1. , 0.26666667, 0.25 , 0.25 ]]),\n",
" array([[1. , 0.26666667, 0.25 , 0.25 ],\n",
" [0.33333333, 0.23529412, 0.22222222, 0.22222222],\n",
" [0. , 0. , 0. , 0. ],\n",
" [0.28571429, 0.11111111, 0.10526316, 0.10526316],\n",
" [0.33333333, 0.23529412, 0.22222222, 0.22222222]]),\n",
" array([[0.28571429, 0.31578947, 0.45454545, 0.5 ],\n",
" [0.4 , 0.26666667, 0.25 , 0.25 ]]),\n",
" array([[0.30769231, 0.11764706, 0.11111111, 0.11111111],\n",
" [0.26666667, 0.10526316, 0.1 , 0.1 ],\n",
" [0. , 0. , 0. , 0. ],\n",
" [0.22222222, 0.14285714, 0.13333333, 0.13333333],\n",
" [0.26666667, 0.10526316, 0.1 , 0.1 ]]),\n",
" array([[0. , 0. , 0. , 0. ],\n",
" [0.26666667, 0.10526316, 0.1 , 0.1 ]])]\n"
]
}
],
"source": [
"print_best_results(threshold)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"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": "3.6.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}