def preprocessing(dataset):
stemmer = StemmerFactory().create_stemmer()
stopwords = StopWordRemoverFactory().create_stop_word_remover()
for row in dataset:
row['message'] = row.get('message').casefold()
row['message'] = re.sub(r"[0-9]", "", row.get('message'))
row['message'] = re.sub('[' + string.punctuation + ']', "",
row.get('message'))
row['message_stopwords'] = stopwords.remove(row['message'])
row['message_stemmed'] = stemmer.stem(row['message_stopwords'])
row['message_tokenized'] = word_tokenize(row['message_stemmed'])
def train(self):
"""
NOTE: Implement your training procedure in this method.
"""
# read data.csv using pandas and drop nan
data = pd.read_csv("data.csv").dropna()
# get article_content and transform to list
contents = data["article_content"].values.tolist()
# get article_topic and transform to list
topics = data["article_topic"].values.tolist()
# import library to tokenize and remove punctuation
tokenizer = RegexpTokenizer(r'\w+')
# stopword removal for bahasa indonesia
stopword = StopWordRemoverFactory().create_stop_word_remover()
# list to save clean contents
clean_contents = list()
# looping the contents, and preprocess for each content
for content in contents:
# case folding the sentence to be lowcase
lowcase_word = content.lower()
# remove stopword from the content
stop_word = stopword.remove(lowcase_word)
# tokenize the content
sentence_token = tokenizer.tokenize(stop_word)
# initialize a list for clean token
clean_tokens = list()
for token in sentence_token:
# append token to the list after lower it
clean_tokens.append(token)
# transform a token to be sentence
sentence = " ".join(clean_tokens) + ''
# append clean sentence
clean_contents.append(sentence)
# count vectorizer
X_train_counts = self.count_vect.fit_transform(clean_contents)
# create tfidf from count vectorizer
X_train_tfidf = self.tfidf_transformer.fit_transform(X_train_counts)
# split data to train and test set > test 10%, train 90%
X_train, X_test, y_train, y_test = train_test_split(X_train_tfidf,
topics,
test_size=0.1)
# train a model
self.svm_clf.fit(X_train, y_train)
# prediction for x_test
prediction = self.svm_clf.predict(X_test)
# model accuracy for x_test
accuracy = accuracy_score(y_test, prediction)
# print accuracy
print(accuracy)
def __init__(self, input, file_location):
data = self.dataFromFile(file_location)
stopword = StopWordRemoverFactory().create_stop_word_remover()
stemmer = StemmerFactory().create_stemmer()
input = stopword.remove(input.lower())
input = stemmer.stem(input)
valid = 0
for i in range(len(data)):
kal = stopword.remove(data[i][0].lower())
kal = stemmer.stem(kal)
if (self.bm(input.lower(), kal.lower()) != -1):
if (valid == 0):
percent = len(input) * 100 / len(kal)
# print("Confidence1 : " + str(percent))
if (percent > 80):
self.answere = data[i][1]
valid = 1
else:
if valid == 0:
if (self.bm2(input.lower(), kal.lower()) >= 80):
# print("Confidence2 : " + str(bm2(input.lower(), kal.lower())))
self.answere = data[i][1]
valid = 1
def clean_text(self, data):
stopword = StopWordRemoverFactory().create_stop_word_remover()
stemmer = StemmerFactory().create_stemmer()
data = re.sub('[^a-zA-Z]',' ', str(data).lower())
data = re.sub('\byok\b |\byuk\b', 'ayo', data)
data = re.sub('\bmager\b', 'males', data)
data = re.sub('\bmalas\b', 'males', data)
data = re.sub('\bmls\b', 'males', data)
data = re.sub('\bkuy\b', 'yuk', data)
data = re.sub('\borg\b', 'orang', data)
data = re.sub('\bjg\b', 'juga', data)
data = re.sub('\budh\b', 'sudah', data)
data = re.sub('\bmangat\b', 'semangat', data)
data = re.sub('\bcemungut\b', 'semangat', data)
data = re.sub('\bgas\b', 'yuk', data)
data = re.sub('\benakeun\b', 'enak', data)
data = re.sub('\bnaek\b', 'naik', data)
data = re.sub('\bmmg\b', 'memang', data)
data = re.sub('\bga\b', 'engga', data)
data = re.sub('\bengga\b', 'tidak', data)
data = re.sub('\bttg\b', 'tentang', data)
data = re.sub('\brush hour\b', 'jam sibuk', data)
data = re.sub('\bku\b', 'aku', data)
data = re.sub('\bgak\b', 'tidak', data)
data = re.sub('\bdgn\b', 'dengan', data)
data = re.sub('\bbailk\b', 'pulang', data)
data = re.sub('\bgatau\b', 'tidak tahu', data)
data = re.sub('\bbat\b', 'banget', data)
data = re.sub('\bampe\b', 'sampai', data)
data = re.sub('\blg\b', 'sedang', data)
data = re.sub('\banjay\b', 'asik', data)
data = re.sub('\banjg\b', 'anjing', data)
data = re.sub('\banjiing\b', 'anjing', data)
data = re.sub('\bantum\b', 'kamu', data)
data = re.sub('\basiq\b |\basyique\b |\basik\b', 'asyik', data)
data = re.sub('\bbgt\b |\bbanget\b |\bbanged\b', 'sangat', data)
data = re.sub('\bribet\b', 'repot', data)
data = data.split()
data = ' '.join(data)
#setelah ngeganti baru ilangin stopword dan imbuhan kata dibawah ini
#sastrawi remove stopwords
data = stopword.remove(data) #stopword nya udah di di provide sastrawi
#sastrawi stemming
data = stemmer.stem(data)
return data
def preprocess_text(input):
#lowercase all character in the text
text = input[0]
text = text.lower()
#remove punctuation
text = text.translate(str.maketrans("","",string.punctuation))
#remove leading and trailing whitespace
text = text.strip()
#remove StopWord
stopword = StopWordRemoverFactory().create_stop_word_remover()
text = stopword.remove(text)
#stemming
stemmer = StemmerFactory().create_stemmer()
text = stemmer.stem(text)
return text
class Preprocess:
def __init__(self):
self.stemmer = StemmerFactory().create_stemmer()
self.remover = StopWordRemoverFactory().create_stop_word_remover()
def preprocess(self, text):
# # 1 stemming
text_stem = self.stemmer.stem(text)
#
# # 2 hapus stop words
text_clean = self.remover.remove(text_stem)
#
# # 3 tokenization
# # 3.1 lowercase
lowercase = text_clean.lower()
preprocessed_text = lowercase.translate(None,
string.punctuation).split()
return preprocessed_text
def respond(strg):
levenshtein = Levenshtein()
stemmer = StemmerFactory().create_stemmer()
stopwords = StopWordRemoverFactory().create_stop_word_remover()
kategori = model.predict([strg])
txt = stopwords.remove(strg)
txt = stemmer.stem(txt)
best = 1000
res = []
for words in dataset:
if (words['category'] == kategori):
distance = levenshtein.distance(txt, words['message_stemmed'])
if (distance < best):
best = distance
res = words
return res['respond']
def index(hashs, terms):
for word in terms:
if word in hashs:
hashs[word] += 1
else:
hashs[word] = 1
print('Indexing ...')
for path in sorted(IN_DIR.glob('*/*.html')):
with open(path.resolve(), 'r', encoding='utf-8') as file:
df[path.name] = dict()
content = get_text(['title', 'top', 'middle', 'bottom'], file.read())
content = content.translate(str.maketrans('','', punctuation))
content = stopword.remove(content)
terms = stemmer.stem(content.lower()).split()
index(df[path.name], terms)
index(tf, terms)
print('Indexing done!\n')
print('Calculating idf for terms...')
for term, freq in tf.items():
df_i = 0
for doc, tf_doc in df.items():
df_i += 1 if term in tf_doc else 0
idf[term] = (1 + math.log2(len(df)/df_i)) if df_i != 0 else 1
print('Calculated!\n')
with open(BASE_DIR / 'words_score.txt', 'w', encoding='utf-8') as file:
class TextSummarizer:
def __init__(self, title: str, plot: str, human_synopsis: str):
self.title = title
self.plot = plot
self.human_synopsis = human_synopsis
self.stopwords = StopWordRemoverFactory().create_stop_word_remover()
self.stemmer = StemmerFactory().create_stemmer()
def __text_to_sentences(self, text: str) -> List[str]:
regex = re.compile('\.\n\n|\.\n|\. |\.$')
sentences = regex.split(text)
return sentences
def __stem_sentence(self, sentence: str) -> str:
return self.stemmer.stem(sentence)
def __stop_word_removal(self, words: List[str]) -> List[str]:
temp_words = []
for word in words:
if word.lower() in self.title.lower():
temp_words.append(word)
else:
temp = self.stopwords.remove(word)
if temp:
temp_words.append(temp)
return temp_words
def __preprocess_text(self, text: str) -> tuple:
temp_sentences = self.__text_to_sentences(text)
sentences = []
preprocessed_sentences = []
for sentence in temp_sentences:
if len(sentence) < 2:
continue
stemmed_sentence = self.__stem_sentence(sentence.lower())
tokenized_sentence = nltk.tokenize.word_tokenize(stemmed_sentence)
removed_stop_word_sentence = self.__stop_word_removal(
tokenized_sentence)
if len(removed_stop_word_sentence) < 2:
continue
sentences.append(sentence)
preprocessed_sentences.append(removed_stop_word_sentence)
return sentences, preprocessed_sentences
def __sentence_similarity(self, sent1, sent2):
"""
calculate the similarity between sentence!
return distance between sentences
"""
sent1 = [w.lower() for w in sent1]
sent2 = [w.lower() for w in sent2]
all_words = list(set(sent1 + sent2))
vector1 = [0] * len(all_words)
vector2 = [0] * len(all_words)
# build the vector for the first sentence
for w in sent1:
vector1[all_words.index(w)] += 1
# build the vector for the second sentence
for w in sent2:
vector2[all_words.index(w)] += 1
return 1 - cosine_distance(vector1, vector2)
def __build_similarity_matrix(self, sentences):
"""
make a matrix to plot the similarity between sentences in a file
return matrix
"""
# Create an empty similarity matrix
similarity_matrix = np.zeros((len(sentences), len(sentences)))
for idx1 in range(len(sentences)):
for idx2 in range(len(sentences)):
if idx1 == idx2: # ignore if both are same sentences
continue
similarity_matrix[idx1][idx2] = self.__sentence_similarity(
sentences[idx1], sentences[idx2])
return similarity_matrix
def summarize(self, top_n=5):
summarize_text = []
# Step 1 - text preprocessing
plot_sentences, plot_pre_sentences = self.__preprocess_text(self.plot)
# Step 2 - Generate Similary Martix across sentences
sentence_similarity_martix = self.__build_similarity_matrix(
plot_pre_sentences)
print(sentence_similarity_martix)
# Step 3 - Rank sentences in similarity martix
sentence_similarity_graph = nx.from_numpy_array(
sentence_similarity_martix)
plot_scores = nx.pagerank(sentence_similarity_graph)
# Step 4 - Sort the rank and pick top sentences
ranked_sentence = []
for i in range(len(plot_scores)):
ranked_sentence.append([plot_scores[i], plot_sentences[i], i])
ranked_sentence.sort(key=lambda x: x[0], reverse=True)
top_n = min(top_n, len(plot_sentences))
summary = ranked_sentence[0:top_n]
summary.sort(key=lambda x: x[2])
summary = [i[1] for i in summary]
summarize_text = ""
for i in range(top_n):
summarize_text += "".join(summary[i]) + ". "
# Step 5 - Offcourse, output the summarize texr
return summarize_text
@staticmethod
def generate_from_file(title, plotfilepath, synopsisfilepath):
plot = ""
synopsis = ""
with open(plotfilepath, "r") as plot_file:
plot = plot_file.read()
with open(synopsisfilepath, "r") as synopsis_file:
synopsis = synopsis_file.read()
ts = TextSummarizer(title, plot, synopsis)
return ts.summarize()
from Sastrawi.StopWordRemover.StopWordRemoverFactory import StopWordRemoverFactory, StopWordRemover, ArrayDictionary
from string_matching_algorithm import *
import re as regex
from Sastrawi.StopWordRemover.StopWordRemoverFactory import StopWordRemoverFactory
# factory = StopWordRemoverFactory()
newStopFactory = StopWordRemoverFactory().get_stop_words()
newStopFactory.remove("sampai")
newStopFactory.remove("dan")
newStopFactory.append("deadline")
newStopFactory.append("mengenai")
newStopFactory.append("tanggal")
stopword = StopWordRemover(ArrayDictionary(newStopFactory))
# Regex untuk bulan
JANUARI_REGEX = '[Jj]an(?:uari)?'
FEBRUARI_REGEX = '[Ff]eb(?:ruari)?'
MARET_REGEX = '[Mm]ar(?:et)?'
APRIL_REGEX = '[Aa]pr(?:il)?'
MEI_REGEX = '[Mm]ei'
JUNI_REGEX = '[Jj]uni?'
JULI_REGEX = '[Jj]uli?'
AGUSTUS_REGEX = '[Aa]gu(?:stus)?'
SEPTEMBER_REGEX = '[Ss]ep(?:tember)?'
OKTOBER_REGEX = '[Oo]kt(?:ober)?'
NOVEMBER_REGEX = '[Nn]ov(?:ember)?'
DESEMBER_REGEX = '[Dd]es(?:ember)?'
# Regex untuk keutuhan tanggal
ANYTHING = '.*'
DAY_REGEX = '(0[1-9]|[1-2][0-9]|3[0-1])'
def rem_stop_words(text):
sw_rem = StopWordRemoverFactory().create_stop_word_remover()
return sw_rem.remove(text)
class SpamClassifier(object):
def __init__(self, tweets, labels):
self.tweets, self.labels = tweets, labels
self.clean_tweets = []
self.conv_tweets = []
self.stem_tweets = []
self.processed_tweets = []
self.spam_tweets, self.ham_tweets = (labels == 1).sum(), (
labels == 0).sum()
self.total_tweets = len(self.tweets)
self.testdata = []
self.testdata_terproses = []
self.vocab1 = list()
self.vocab2 = list()
self.vocab3 = list()
self.prior_spam = 0.0
self.prior_ham = 0.0
self.tf_spam1 = dict()
self.tf_ham1 = dict()
self.tf_spam2 = dict()
self.tf_ham2 = dict()
self.tf_spam3 = dict()
self.tf_ham3 = dict()
self.dfw1 = dict()
self.dfw2 = dict()
self.dfw3 = dict()
self.pwtfidf_spam1 = dict()
self.pwtfidf_ham1 = dict()
self.pwtfidf_spam2 = dict()
self.pwtfidf_ham2 = dict()
self.pwtfidf_spam3 = dict()
self.pwtfidf_ham3 = dict()
self.stemmer = StemmerFactory().create_stemmer()
self.stop = StopWordRemoverFactory().create_stop_word_remover()
self.stop.dictionary.add('lasturladdr')
self.stop.dictionary.add('rt')
def praproses(self):
for i in range(len(self.tweets)):
self.clean_tweets.append(clean_text(self.tweets[i]))
self.conv_tweets.append(konversi(self.clean_tweets[i], pengganti))
self.stem_tweets.append(self.stemmer.stem(self.conv_tweets[i]))
self.processed_tweets.append(self.stop.remove(self.stem_tweets[i]))
def praprosestext(self, teks):
cteks = clean_text(teks)
konv_teks = konversi(cteks, pengganti)
stemteks = self.stemmer.stem(konv_teks)
nosw_teks = self.stop.remove(stemteks)
return nosw_teks
def hitungTFDF(self):
for i in range(self.total_tweets):
dfw = {}
tfunigram = createToken(self.processed_tweets[i], gram=1)
for word in tfunigram:
if dfw.get(word, 0) == 0: # hitung dokumen berisi word
dfw[word] = 1
self.dfw1[word] = self.dfw1.get(word, 0) + 1
if self.labels[i]:
self.tf_spam1[word] = self.tf_spam1.get(word, 0) + 1
else:
self.tf_ham1[word] = self.tf_ham1.get(word, 0) + 1
dfw = {}
tfbigram = createToken(self.processed_tweets[i], gram=2)
for word in tfbigram:
if dfw.get(word, 0) == 0: # hitung dokumen berisi word
dfw[word] = 1
self.dfw2[word] = self.dfw2.get(word, 0) + 1
if self.labels[i]:
self.tf_spam2[word] = self.tf_spam2.get(word, 0) + 1
else:
self.tf_ham2[word] = self.tf_ham2.get(word, 0) + 1
dfw = {}
tftrigram = createToken(self.processed_tweets[i], gram=3)
for word in tftrigram:
if dfw.get(word, 0) == 0: # hitung dokumen berisi word
dfw[word] = 1
self.dfw3[word] = self.dfw3.get(word, 0) + 1
if self.labels[i]:
self.tf_spam3[word] = self.tf_spam3.get(word, 0) + 1
else:
self.tf_ham3[word] = self.tf_ham3.get(word, 0) + 1
self.vocab1 = list(dict(self.tf_spam1, **self.tf_ham1).keys())
self.vocab2 = list(dict(self.tf_spam2, **self.tf_ham2).keys())
self.vocab3 = list(dict(self.tf_spam3, **self.tf_ham3).keys())
def train(self):
self.praproses()
self.hitungTFDF()
self.prior_spam = self.spam_tweets / self.total_tweets
self.prior_ham = self.ham_tweets / self.total_tweets
#****Hitung tfidf untuk 1-gram dan 2-gram***
#***** 1-gram****
for word in self.tf_spam1:
self.pwtfidf_spam1[word] = self.tf_spam1[word] \
* log10(len(self.tweets) / self.dfw1[word])
for word in self.tf_ham1:
self.pwtfidf_ham1[word] = self.tf_ham1[word] \
* log10(len(self.tweets) / self.dfw1[word])
#===2 gram===
for word in self.tf_spam2:
self.pwtfidf_spam2[word] = self.tf_spam2[word] \
* log10(len(self.tweets) / (self.dfw2[word]))
for word in self.tf_ham2:
self.pwtfidf_ham2[word] = self.tf_ham2[word] \
* log10(len(self.tweets) / self.dfw2[word])
def classify1(self, text, metode):
self.metode = metode + '1gr'
proses_text = self.praprosestext(text)
self.testdata_terproses.append(proses_text)
token = createToken(proses_text, gram=1)
pSpam = log10(self.prior_spam)
pHam = log10(self.prior_ham)
for word in token:
#==hitung probbilitas spam
if metode == 'tfidf':
pSpam += log10(self.pwtfidf_spam1.get(word, 1) + 1)
pSpam -= log10(
sum(self.pwtfidf_spam1.values()) + len(self.tf_spam1))
if metode == 'bow':
pSpam += log10(
(self.tf_spam1.get(word, 0) + 1) /
(sum(self.tf_spam1.values()) + len(self.vocab1)))
#== Hitung untuk ham =====
if metode == 'tfidf':
pHam += log10(self.pwtfidf_ham1.get(word, 1) + 1)
pHam -= log10(
sum(self.pwtfidf_ham1.values()) + len(self.tf_ham1))
if metode == 'bow':
pHam += log10((self.tf_ham1.get(word, 0) + 1) /
(sum(self.tf_spam1.values()) + len(self.vocab1)))
#print("pSpam: ",pSpam," pHam: ",pHam)
return pSpam >= pHam
def classify2(self, text, metode):
self.metode = metode + '2gr'
proses_text = self.praprosestext(text)
self.testdata_terproses.append(proses_text)
token = createToken(proses_text, gram=2)
pSpam = log10(self.prior_spam)
pHam = log10(self.prior_ham)
for word in token:
#==hitung probbilitas spam
if metode == 'tfidf':
pSpam += log10(self.pwtfidf_spam2.get(word, 1) + 1)
pSpam -= log10(
sum(self.pwtfidf_spam2.values()) + len(self.tf_spam2))
else:
pSpam += log10(
(self.tf_spam2.get(word, 0) + 1) /
(sum(self.tf_spam2.values()) + len(self.vocab2)))
#== Hitung untuk ham =====
if metode == 'tfidf':
pHam += log10(self.pwtfidf_ham2.get(word, 1) + 1)
pHam -= log10(
sum(self.pwtfidf_ham2.values()) + len(self.tf_ham2))
else:
pHam += log10((self.tf_ham2.get(word, 0) + 1) /
(sum(self.tf_spam2.values()) + len(self.vocab2)))
#print('pSpam: ',pSpam,' pHam: ',pHam)
return pSpam >= pHam
def sbclassify(self, text):
self.metode = 'stupidbackoff'
proses_text = self.praprosestext(text)
self.testdata_terproses.append(proses_text)
hamscore = 0.0
spamscore = 0.0
words = createToken(proses_text, gram=2)
for word in words:
wordtoken = word.split()
tokenprev = wordtoken[0]
tokennext = wordtoken[1]
if word in self.tf_ham2:
bicount = self.tf_ham2[word]
bi_unicount = self.tf_ham1[tokenprev]
hamscore += log10(bicount)
hamscore -= log10(bi_unicount)
else:
if tokennext in self.tf_ham1:
unicount = self.tf_ham1[tokennext]
else:
unicount = 0.4
hamscore += log10(0.4)
hamscore += log10(unicount)
hamscore -= log10(
sum(self.tf_ham1.values()) + len(self.vocab1))
if word in self.tf_spam2:
bicount2 = self.tf_spam2[word]
bi_unicount2 = self.tf_spam1[tokenprev]
spamscore += log10(bicount2)
spamscore -= log10(bi_unicount2)
else:
if tokennext in self.tf_spam1:
unicount2 = self.tf_spam1[tokennext]
else:
unicount2 = 0.4
spamscore += log10(0.4)
spamscore += log10(unicount2)
spamscore -= log10(
sum(self.tf_spam1.values()) + len(self.vocab1))
#spamscore += log10(self.prior_spam)
#hamscore += log10(self.prior_ham)
return spamscore >= hamscore
def predict(self, test_data, metode, gram):
'''metode = stbo = stupid backoff'
bow = bag off word
tfidf = with tfidf
'''
self.testdata = []
self.testdata_terproses = []
result = dict()
if metode == 'stbo':
for (i, tweet) in enumerate(test_data):
result[i] = int(self.sbclassify(tweet))
else:
if gram == 1:
for (i, tweet) in enumerate(test_data):
result[i] = int(self.classify1(tweet, metode))
if gram == 2:
for (i, tweet) in enumerate(test_data):
result[i] = int(self.classify2(tweet, metode))
return result
def metrics(self, labels, predictions, tweets):
etext = []
eptext = []
elabel = []
true_pos, true_neg, false_pos, false_neg = 0, 0, 0, 0
for i in range(len(labels)):
true_pos += int((labels[i] == 1) and (predictions[i] == 1))
true_neg += int(labels[i] == 0 and predictions[i] == 0)
if (labels[i] == 0 and predictions[i] == 1):
false_pos += 1
etext.append(tweets[i])
eptext.append(self.praprosestext(tweets[i]))
elabel.append('fp')
if (labels[i] == 1 and predictions[i] == 0):
false_neg += 1
etext.append(tweets[i])
eptext.append(self.praprosestext(tweets[i]))
elabel.append('fn')
edf = pd.DataFrame(list(zip(etext, eptext, elabel)),
columns=['text', 'stemmedtext', 'label'])
filename = 'data/false_' + self.metode + '.xlsx'
writer = pd.ExcelWriter(filename, engine='xlsxwriter')
edf.to_excel(writer, sheet_name='Sheet1')
writer.save()
precision = true_pos / (true_pos + false_pos)
recall = true_pos / (true_pos + false_neg)
Fscore = 2 * precision * recall / (precision + recall)
accuracy = (true_pos + true_neg) / (true_pos + true_neg + false_pos +
false_neg)
print("Precision: ", precision)
print("Recall: ", recall)
print("F-score: ", Fscore)
print("Accuracy: ", accuracy)
print('\n==Confusion Matrix===')
print("True Positiv: ", true_pos)
print("False Positiv: ", false_pos)
print("True Negativ: ", true_neg)
print("False Negativ: ", false_neg)
"Halo, namaku Alice.<br>Selamat datang di ChatBot Alice.<br>Tanyakan apapun kepadaku dan aku akan mencoba menjawabnya...<br>...dengan KMP, BM, dan Regex."
)
else:
stopword = StopWordRemoverFactory().create_stop_word_remover()
pertanyaan = []
purePertanyaan = []
jawaban = []
for line in open('pertanyaan.txt').readlines():
i = 0
j = 0
while (line[j] != ' '):
j += 1
while (line[i] != '?'):
i += 1
purePertanyaan.append((line[j + 1:i + 1]))
pertanyaan.append(stopword.remove((line[j + 1:i].lower())))
jawaban.append(line[i + 2:len(line) - 1])
query = re.sub('[%s]' % re.escape(string.punctuation), '',
sys.argv[1].lower())
query = stopword.remove(query)
querylist = query.split(' ')
synonymList = []
for queryWord in querylist:
synonymList.append(getSinonim(queryWord))
#dikombinasi
sentenceList = [[]]
for word in synonymList:
newList = []
for synonym in word:
for sentence in sentenceList: