139 lines
4.2 KiB
Python
139 lines
4.2 KiB
Python
# coding: utf-8
|
|
|
|
# In[1]:
|
|
|
|
|
|
import pandas as pd
|
|
from IPython.display import clear_output, Markdown, Math
|
|
import ipywidgets as widgets
|
|
import os
|
|
import unicodedata as uni
|
|
import numpy as np
|
|
from nltk.stem import PorterStemmer
|
|
from nltk.tokenize import sent_tokenize, word_tokenize
|
|
from nltk.corpus import wordnet
|
|
import math
|
|
import pprint
|
|
|
|
|
|
# # Naive Approach
|
|
table = pd.read_csv('../Tools/emoji_descriptions.csv')
|
|
|
|
#######################
|
|
# Helper functions
|
|
#######################
|
|
|
|
def stemming(messages):
|
|
stemmed_messages = []
|
|
ps = PorterStemmer()
|
|
for m in messages:
|
|
words = word_tokenize(m)
|
|
sm = []
|
|
for w in words:
|
|
sm.append(ps.stem(w))
|
|
m = (" ").join(sm)
|
|
stemmed_messages.append(m)
|
|
return stemmed_messages
|
|
|
|
|
|
# * compare words to emoji descriptions
|
|
def evaluate_sentence(sentence, table, description_key = 'description', lang = 'eng', emojis_to_consider="all"):
|
|
|
|
tokenized_sentence = word_tokenize(sentence)
|
|
n = len(tokenized_sentence)
|
|
l = table.shape[0]
|
|
matrix_list = []
|
|
|
|
for index, row in table.iterrows():
|
|
emoji_tokens = word_tokenize(row[description_key])
|
|
m = len(emoji_tokens)
|
|
|
|
mat = np.zeros(shape=(m,n))
|
|
for i in range(len(emoji_tokens)):
|
|
for j in range(len(tokenized_sentence)):
|
|
syn1 = wordnet.synsets(emoji_tokens[i],lang=lang)
|
|
if len(syn1) == 0:
|
|
continue
|
|
w1 = syn1[0]
|
|
#print(j, tokenized_sentence)
|
|
syn2 = wordnet.synsets(tokenized_sentence[j], lang=lang)
|
|
if len(syn2) == 0:
|
|
continue
|
|
w2 = syn2[0]
|
|
val = w1.wup_similarity(w2)
|
|
if val is None:
|
|
continue
|
|
mat[i,j] = val
|
|
#print(row['character'], mat)
|
|
matrix_list.append(mat)
|
|
|
|
return matrix_list
|
|
|
|
|
|
###########################
|
|
#Functions to be called from main script
|
|
###########################
|
|
|
|
|
|
# load and preprocess data
|
|
# emojis_to_consider can be either a list or "all"
|
|
def prepareData(stemming=False):
|
|
if(stemming):
|
|
table['description'] = stemming(table['description'])
|
|
|
|
#collect the emojis
|
|
lookup = {}
|
|
emoji_set = []
|
|
for index, row in table.iterrows():
|
|
lookup[index] = row['character']
|
|
emoji_set.append(row['character'])
|
|
|
|
emoji_set = set(emoji_set)
|
|
|
|
return lookup
|
|
|
|
# make a prediction for an input sentence
|
|
def predict(sentence, lookup, emojis_to_consider="all", criteria="threshold", description_key='description', lang = 'eng', n=10, t=0.9):
|
|
|
|
result = evaluate_sentence(sentence, table, description_key, lang, emojis_to_consider=emojis_to_consider)
|
|
|
|
try:
|
|
if(criteria=="summed"):
|
|
resultValues = [-np.sum(x) for x in result]
|
|
elif (criteria=="max_val"):
|
|
resultValues = [-np.max(x) for x in result]
|
|
elif(criteria=="avg"):
|
|
resultValues = [-np.mean(x) for x in result]
|
|
else:
|
|
resultValues = [-len(np.where(x>t)[0]) / (x.shape[0] * x.shape[1]) for x in result]
|
|
indexes = np.argsort(resultValues)
|
|
results = np.sort(resultValues)
|
|
|
|
if (emojis_to_consider != "all" and type(emojis_to_consider) == list):
|
|
indexes2 = []
|
|
results2 = []
|
|
for i in range(len(indexes)):
|
|
if lookup[indexes[i]] in emojis_to_consider:
|
|
indexes2.append(indexes[i])
|
|
results2.append(results[i])
|
|
indexes = indexes2
|
|
results = results2
|
|
indexes = indexes[0:n]
|
|
results = results[0:n]
|
|
|
|
# build a result table
|
|
table_array = [[lookup[indexes[i]], str(table.iloc[indexes[i]][description_key])] for i in range(n) ]
|
|
|
|
table_frame = pd.DataFrame(table_array, columns=[criteria, 'description'])
|
|
|
|
#display(table_frame)
|
|
|
|
return list(table_frame[criteria]), results
|
|
|
|
except ZeroDivisionError as err:
|
|
print("There seems to be a problem with the input format. Please enter a nonempty string")
|
|
|
|
|
|
#predict("I like to travel by train", description_key='description' , lang='eng')
|
|
|