stemming als parameter und anpassungen für evaluation
This commit is contained in:
@ -18,7 +18,7 @@ import pprint
|
||||
from gensim.models import Word2Vec, KeyedVectors
|
||||
|
||||
# # Naive Approach
|
||||
table = pd.read_csv('../Tools/emoji_descriptions_preprocessed.csv')
|
||||
table = pd.read_csv('../Tools/emoji_descriptions_preprocessed.csv', delimiter = ";")
|
||||
|
||||
##Store table in the format:
|
||||
## { index: [emoji, description]}
|
||||
@ -49,7 +49,7 @@ def evaluate_sentence(sentence, description_key = 'description', lang = 'eng', e
|
||||
if embeddings=="word2Vec":
|
||||
wv = KeyedVectors.load(str(__location__)+"/word2vec.model", mmap='r')
|
||||
elif embeddings=="fastText":
|
||||
wv = KeyedVectors.load("/fastTextVectors.kv", mmap='r')
|
||||
wv = KeyedVectors.load(str(__location__)+"/fastTextVectors.kv", mmap='r')
|
||||
|
||||
if (stem):
|
||||
sentence = stemming(sentence)
|
||||
@ -118,9 +118,9 @@ def prepareData(stem=True, lower=True):
|
||||
# make a prediction for an input sentence
|
||||
# embeddings = ["wordnet", "word2Vec", "fastText"]
|
||||
def predict(sentence, lookup, emojis_to_consider="all", criteria="threshold", lang = 'eng',\
|
||||
embeddings="wordnet", n=10, t=0.9):
|
||||
embeddings="wordnet", n=10, t=0.9, stem = True):
|
||||
|
||||
result = evaluate_sentence(sentence, lang, emojis_to_consider=emojis_to_consider, embeddings=embeddings)
|
||||
result = evaluate_sentence(sentence, lang, emojis_to_consider=emojis_to_consider, embeddings=embeddings, stem = stem)
|
||||
|
||||
try:
|
||||
if(criteria=="summed"):
|
||||
|
Reference in New Issue
Block a user