Merge branch 'master' of ssh://the-cake-is-a-lie.net:20022/jonas/NLP-LAB

This commit is contained in:
Jonas Weinz 2018-07-22 10:56:41 +02:00
commit 4cd15127ba
2 changed files with 31 additions and 9 deletions

Binary file not shown.

View File

@ -18,7 +18,7 @@ import pprint
from gensim.models import Word2Vec, KeyedVectors from gensim.models import Word2Vec, KeyedVectors
# # Naive Approach # # Naive Approach
table = pd.read_csv('../Tools/emoji_descriptions.csv') table = pd.read_csv('../Tools/emoji_descriptions_preprocessed.csv')
##Store table in the format: ##Store table in the format:
## { index: [emoji, description]} ## { index: [emoji, description]}
@ -41,13 +41,19 @@ def stemming(message):
# * compare words to emoji descriptions # * compare words to emoji descriptions
def evaluate_sentence(sentence, description_key = 'description', lang = 'eng', emojis_to_consider="all", stem=True): def evaluate_sentence(sentence, description_key = 'description', lang = 'eng', emojis_to_consider="all",\
stem=True, embeddings="wordnet"):
# assumes there is a trained w2v model stored in the same directory! # assumes there is a trained w2v model stored in the same directory!
__location__ = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__))) __location__ = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__)))
wv = KeyedVectors.load(str(__location__)+"/word2vec.model", mmap='r')
if embeddings=="word2Vec":
wv = KeyedVectors.load(str(__location__)+"/word2vec.model", mmap='r')
elif embeddings=="fastText":
wv = KeyedVectors.load("/fastTextVectors.kv", mmap='r')
if (stem): if (stem):
sentence = stemming(sentence) sentence = stemming(sentence)
tokenized_sentence = word_tokenize(sentence) tokenized_sentence = word_tokenize(sentence)
n = len(tokenized_sentence) n = len(tokenized_sentence)
matrix_list = [] matrix_list = []
@ -59,10 +65,24 @@ def evaluate_sentence(sentence, description_key = 'description', lang = 'eng', e
mat = np.zeros(shape=(m,n)) mat = np.zeros(shape=(m,n))
for i in range(len(emoji_tokens)): for i in range(len(emoji_tokens)):
for j in range(len(tokenized_sentence)): for j in range(len(tokenized_sentence)):
try: if embeddings=="wordnet":
val = wv.similarity(emoji_tokens[i], tokenized_sentence[j]) syn1 = wordnet.synsets(emoji_tokens[i],lang=lang)
except KeyError: if len(syn1) == 0:
continue 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
elif (embeddings == "word2Vec" or embeddings == "fastText"):
try:
val = wv.similarity(emoji_tokens[i], tokenized_sentence[j])
except KeyError:
continue
mat[i,j] = val mat[i,j] = val
matrix_list.append(mat) matrix_list.append(mat)
@ -96,9 +116,11 @@ def prepareData(stem=True, lower=True):
return lookup return lookup
# make a prediction for an input sentence # make a prediction for an input sentence
def predict(sentence, lookup, emojis_to_consider="all", criteria="threshold", lang = 'eng', n=10, t=0.9): # embeddings = ["wordnet", "word2Vec", "fastText"]
def predict(sentence, lookup, emojis_to_consider="all", criteria="threshold", lang = 'eng',\
embeddings="wordnet", n=10, t=0.9):
result = evaluate_sentence(sentence, lang, emojis_to_consider=emojis_to_consider) result = evaluate_sentence(sentence, lang, emojis_to_consider=emojis_to_consider, embeddings=embeddings)
try: try:
if(criteria=="summed"): if(criteria=="summed"):