def parse_line(line):
vid, title, comment = line[:-1].split('~')
title = util.clean_text(title)
comment = util.clean_text(comment)
title_ix = split_to_words(title)
if len(title_ix) == 0:
return [], []
comment_ix = split_to_words(comment)
return title_ix, comment_ix
def LoadFile(self, path):
self.SetReadOnly(True)
self.Disable()
old_path = self.path
self.path = path
self.sig_title_changed.signal(self)
try:
text = (yield async_call(read_file, path, "r"))
text, self.file_encoding = decode_text(text)
text = clean_text(text)
self.modified_externally = False
self.SetReadOnly(False)
self.SetSyntaxFromFilename(path)
self.SetText(text)
self.SetSavePoint()
if old_path:
self.env.remove_monitor_path(old_path)
self.env.add_monitor_path(path)
except:
self.path = old_path
self.sig_title_changed.signal(self)
self.sig_status_changed.signal(self)
raise
finally:
self.Enable()
self.SetReadOnly(False)
def classify(input_file, delimiter=",", classifier_param="LinearSVC"):
data = []
with open(input_file, 'rU') as f:
reader = csv.reader(f, delimiter=delimiter)
next(reader, None) # skip the headers
for row in reader:
person = row[2]
text = row[3]
likes = row[5]
data.append((text, person, likes))
try:
classifier = joblib.load("model/%s_classifier.pkl" % classifier_param)
except IOError:
print "unable to load classifier: %s. Exiting program." % classifier_param
sys.exit(1)
with open("results/%s_%s" %(classifier_param, input_file.replace("/","-")), 'wb') as csvfile:
writer = csv.writer(csvfile, delimiter='\t', quotechar='\"', quoting=csv.QUOTE_ALL)
writer.writerow(["label", "message", "author", "likes"])
for message, author, likes in data:
cleaned_message = util.clean_text(message, True)
if len(cleaned_message.split(" ")) > 3:
writer.writerow([util.classify_unknown(classifier, cleaned_message), message, author, likes])
def get_action(hit):
address = clean_text(hit['_source']['address'])
try:
results = geocoding.get(address)
except Exception as ex:
print address, 'Error:', ex
return batch.get_update_action(
hit, {
'address': address,
'geocoding_data': None,
'location_error': 'NotFound'
})
n = len(results)
doc = {}
if n > 0:
geo = results[0]
doc = {
'formatted_address': geo['formatted_address'],
'location': {
'lat': geo['geometry']['location']['lat'],
'lon': geo['geometry']['location']['lng']
}
}
if n != 1:
doc['location_error'] = 'NotFound' if n == 0 else 'Ambiguous'
doc['geocoding_data'] = results
doc['address'] = address
return batch.get_update_action(hit, doc)
def parse_file(self, filename, with_topic=False):
"""
Reads the text file and returns a dictionary in the form:
tweet_id = (sentiment, text)
:param with_topic:
:param filename: the complete file name
:return:
"""
# print(filename)
data = {}
filename_print_friendly = filename.split("/")[-1].split("\\")[-1]
if self.verbose:
print("Parsing file:", filename_print_friendly, end=" ")
for line_id, line in enumerate(
open(filename, "r", encoding="utf-8").readlines()):
try:
columns = line.rstrip().split(self.SEPARATOR)
tweet_id = columns[0]
if with_topic:
topic = clean_text(columns[1])
if not isinstance(topic, str) or "None" in topic:
print(tweet_id, topic)
sentiment = columns[2]
text = clean_text(" ".join(columns[3:]))
if self.ekphrasis:
text = ' '.join(text_processor.pre_process_doc(text))
if text != "Not Available":
data[tweet_id] = (sentiment, (topic, text))
else:
sentiment = columns[1]
text = clean_text(" ".join(columns[2:]))
if self.ekphrasis:
text = ' '.join(text_processor.pre_process_doc(text))
if text != "Not Available":
data[tweet_id] = (sentiment, text)
except Exception as e:
print("\nWrong format in line:{} in file:{}".format(
line_id, filename_print_friendly))
raise Exception
if self.verbose:
print("done!")
return data
def parse_line(line):
iid, pid, tags, comment = line[:-1].split('~')
comment = util.clean_text(comment)
tags = tags.lower()
tags_ix = tags.split("#*#")
if len(tags_ix) == 0:
return [], []
comment_ix = split_to_words(comment)
return tags_ix, comment_ix
def Paste(self):
wx.TheClipboard.Open()
try:
text_data = wx.TextDataObject()
if wx.TheClipboard.GetData(text_data):
text = clean_text(text_data.GetText())
self.ReplaceSelection(text)
finally:
wx.TheClipboard.Close()
def generate_titles(my_title):
my_title = util.clean_text(my_title)
my_words = my_title.split(' ')
print(' '.join((w.upper() if w in title_word_to_ix else w) for w in my_words) + '\n')
my_title_ixs = [title_word_to_ix[w] for w in my_words if w in title_word_to_ix]
my_title_sample = util.bag_of_words(my_title_ixs, title_dict_size)
for i in range(10):
print(' ' + word_ixs_to_str(pred_text(model, my_title_sample), False))
print('')
def create_model(pos_tweets, neg_tweets, neu_tweets, classifier_param='LinearSVC'):
# filter away words that are less than 3 letters to form the training training_data
tweets = []
for (words, sentiment) in pos_tweets + neg_tweets + neu_tweets:
words = util.clean_text(words, True)
words_filtered = [e.lower() for e in words.split() if len(e) >= 3]
#words_filtered = [' '.join(w) for w in [ x for x in nltk.bigrams(words.split())]]
tweets.append((words_filtered, sentiment))
# make sure tweets are shuffled randomly
shuffle(tweets)
# get the training set and train the Classifier
training_set = nltk.classify.util.apply_features(extract_features, tweets)
max_specificity = -1
best_classifier = None
average_accuracy = 0.0
# perform 10-fold cross validation
cv = cross_validation.KFold(len(training_set), n_folds=10, shuffle=False, random_state=None)
for traincv, testcv in cv:
if classifier_param == "LinearSVC":
classifier = SklearnClassifier(LinearSVC()).train(training_set[traincv[0]:traincv[len(traincv)-1]])
elif classifier_param == "Tfid":
# does TF-IDF weighting,
# chooses the 1000 best features based on a chi2 statistic,
# and then passes that into a multinomial naive Bayes classifier.
pipeline = Pipeline([('tfidf', TfidfTransformer()), \
('chi2', SelectKBest(chi2, k=1000)), \
('nb', MultinomialNB())])
classifier = SklearnClassifier(pipeline).train(training_set[traincv[0]:traincv[len(traincv)-1]])
elif classifier_param == "Bernoulli":
classifier = SklearnClassifier(BernoulliNB()).train(training_set[traincv[0]:traincv[len(traincv)-1]])
elif classifier_param == "NaiveBayes":
classifier = NaiveBayesClassifier.train(training_set[traincv[0]:traincv[len(traincv)-1]])
else:
print "Classifier option not available: ", classifier_param
sys.exit(1)
accuracy_of_classifier, specificity = \
util.accuracy(classifier, tweets[testcv[0]:testcv[len(testcv)-1]])
average_accuracy += accuracy_of_classifier
if specificity > max_specificity:
max_specificity = specificity
best_classifier = classifier
print "\naverage accuracy: ", average_accuracy/cv.n_folds
# save the classifier
joblib.dump(best_classifier, "model/%s_classifier.pkl" % classifier_param)
print "saved classifier"
def get_data(data_path, min_count, use_number_norm, embed_path):
data_ans = json.load(open(data_path, encoding='utf-8'))
data = replace_text(clean_text(data_ans), use_number_norm)
new_data = rep_text(data)
new_data = [(line[0], line[2]) for line in new_data] # 2 是BIO 1 是 BIEOS
char2idx = build_char_vocab(new_data)
vocab, word2idx, idx2word, label2index, index2label = build_vocab(
new_data, min_count)
pretrain_word_embedding, unk_words = build_pretrain_embedding(
embedding_path=embed_path, word_index=word2idx)
return new_data, pretrain_word_embedding, vocab, word2idx, idx2word, label2index, index2label, char2idx
def WriteFile(self, path):
def do_write_file(path, text):
mkpath(os.path.dirname(path))
atomic_write_file(path, text)
text, self.file_encoding = encode_text(self.GetText(), self.file_encoding)
text = clean_text(text)
with self.env.updating_path(path):
yield async_call(do_write_file, path, text)
self.modified_externally = False
self.SetSavePoint()
def on_get(self, req, resp):
time_response_begin = time.time()
is_thumbnail = bool(req.get_param("thumbnail"))
if is_thumbnail:
cache = self.thumbnail_cache
layout = self.thumbnail_layout
else:
cache = self.image_cache
layout = self.image_layout
image_data = None
# cache hack
if req.get_header("If-None-Match") and req.get_header("Cache-Control") != "no-cache":
resp.status = falcon.HTTP_304
return
text = clean_text(req.get_param("text", True))
if len(text) > TEXT_MAX_LEN:
resp.status = falcon.HTTP_403
resp.body = "Text to long."
return
# if text has no newline, assume space is the newline
if "\n" not in text:
text = re.sub(r" +", "\n", text)
text = re.sub(r"_+", " ", text)
image_data = cache.get(text)
cache_hit = image_data is not None
if not cache_hit:
time_render_begin = time.time() # stats
with layout.base_image.clone() as canvas:
self.draw_text(layout, canvas, text)
image_data = canvas.make_blob("png")
cache.set(text, image_data)
render_time = time.time() - time_render_begin # stats
self.latest_cache_miss_times.append(render_time) # stats
resp.set_header("Cache-Control", "public, max-age=3600")
resp.set_header("Content-Type", "image/png")
resp.set_header("ETag", hashlib.md5(text.encode("utf-8")).hexdigest())
resp.body = image_data
now = time.time()
if cache_hit:
cache_hit_time = time.time() - time_response_begin
response_time = now - time_response_begin
self.latest_response_times.append(response_time)
if cache_hit:
self.latest_cache_hit_times.append(cache_hit_time)
def write_tweet_info(tweet_object, options):
debug_print("Writing tweet info")
output_path = Path(options['output_dir']) / options['search_name'] / (options['search_name'] + '.txt')
with output_path.open('a') as output_file:
output_file.write('Tweet info:\n')
output_file.write('\tID:{}\n'.format(tweet_object['id_str']))
output_file.write('\tCreated at:{}\n'.format(tweet_object['created_at']))
output_file.write('\tAuthor:{}\n'.format(tweet_object['user']['screen_name']))
output_file.write('\tText:{}\n'.format(clean_text(tweet_object['text'])))
try:
output_file.write('\tURL:{}\n'.format(tweet_object['entities']['urls'][0]['expanded_url']))
except Exception:
pass
def clean(src):
src['name'] = clean_text(src['name'])
src['mission'] = deep_try_get(src, 'mission', 'gs_data.mission',
'fb_data.mission')
src['city'] = deep_try_get(src, 'city', 'source_data.city',
'gs_data.city')
src['state'] = deep_try_get(src, 'state', 'gs_data.state')
src['link'] = deep_try_get(src, 'link', 'source_data.website',
'gs_data.website')
keywords = deep_try_get(src, 'keywords', 'gs_data.exchange.keywords')
if keywords:
src['keywords'] = clean_list(keywords.split(','))
if 'areas' in src:
src['areas'] = clean_list(src['areas'])
value = deep_get(src, 'gs_data.geographic_areas_served')
if value:
deep_set(src, 'gs_data.geographic_areas_served', clean_list(value))
value = deep_get(src, 'gs_data.organization_ntee_codes')
if value:
deep_set(src, 'gs_data.organization_ntee_codes', clean_list(value))
value = deep_get(src, 'tw_data.created_at')
if value:
deep_set(src, 'tw_data.created_at', parse_date(value).isoformat())
value = deep_get(src, 'tw_data.status.created_at')
if value:
deep_set(src, 'tw_data.last_update_at',
parse_date(value).isoformat())
del src['tw_data']['status']['created_at']
value = deep_get(src, 'fb_data.location')
if value:
deep_set(src, 'fb_data.address', value)
del src['fb_data']['location']
value = deep_get(src, 'fb_data.address.latitude')
if value:
deep_set(src, 'fb_data.location.lat', value)
value = deep_get(src, 'fb_data.address.longitude')
if value:
deep_set(src, 'fb_data.location.lon', value)
if 'isSiteDown' in src:
src['is_site_down'] = src['isSiteDown']
del src['isSiteDown']
def predict_sentiment(texts):
model = load_model()
tokenizer = load_tokenizer()
for text in texts:
texts[texts.index(text)] = clean_text(text)
texts = np.array(texts)
sequences = tokenizer.texts_to_sequences(texts)
data = keras.preprocessing.sequence.pad_sequences(sequences, maxlen=50)
prediction = model.predict(data)
keras.backend.clear_session()
return prediction.tolist()
def sentiment_analysis_result(input_review, *args, **kwargs):
# TODO: returm sentiment analysis on input tweet
# 1: positive, 0 negative
modelfilename, bowTransformefilename, TfidfTransformefilenam = args
Model = pickle.load(open(modelfilename, "rb"))
bow_transformer = pickle.load(open(bowTransformefilename, "rb"))
tfidf_transformer = pickle.load(open(TfidfTransformefilenam, "rb"))
input_review = clean_text(input_review)
input_review = [input_review] #convert it to the list because transform needs a iterable object
messages_bow_test = bow_transformer.transform(input_review)
messages_transformer_test = tfidf_transformer.transform(messages_bow_test)
result = Model.predict(messages_transformer_test)
return result[0]
def embedding_route():
response = {
"text": None,
"embeddings": None,
"err": None
}
try:
a = request.args.get("txt")
x = clean_text(a)
response['text'] = a
response['embeddings'] = str(w2v.vector(x))
return jsonify(response)
except Exception as err:
response['err'] = str(err)
return jsonify(response)
def scrape_webpage(root, dir_, format_, lang="", needs_check=False):
"""
Navigates to input URL and parses HTML for relative links,
scraping each page for its text
"""
text_dict = dict()
queue = ScrapeQueue(root)
while len(queue) > 0:
# Get html data from url on queue
url = queue.dequeue()
print(f"Scraping {url}...")
r = requests.get(url)
# Log bad request to console
if not r.status_code == 200:
print(f"Failed to scrape {url}.\n Status code: {r.status_code}\n")
continue
# Using lmxl parser and utf-8 to account for various charsets
soup = BeautifulSoup(r.content, "lxml", from_encoding="utf-8")
hrefs = yank_hrefs(root, url, soup.find_all("a")) # set instance
if not hrefs:
print(f"Error occured in scraping links from {url}.\n\
Check status of chromedriver executable and try again.")
return -2
# Add found links to queue
for h in hrefs:
queue.enqueue(h)
# Add contents to text_dict
title = soup.get("title")
text = soup.get_text(separator=",")
if not lang:
lang = detect_lang(text) # Set lang
text_dict[title] = clean_text(text) # Text passed as generator to lower mem load
print()
if needs_check:
return check_spelling(text_dict)
return save_scrapings(root, dir_, format_, text_dict, lang)
def gposttl(utterance, identifier="no_id"):
utterance = clean_text(utterance)
p = subprocess.Popen(['gposttl', '--silent'], stdout=subprocess.PIPE,
stdin=subprocess.PIPE)
(out, error) = p.communicate(utterance.encode('utf8'))
if p.returncode != '0':
if len(out) > 1:
out = out.decode('utf8')
tokens = [a.replace(u'\t', u'|')
for a in out.split(u'\n')
if len(a) > 0]
return tokens
else:
raise Exception('Error: no text to parse')
else:
msg = str(error)
code = str(p.returncode)
sys.stderr.write(utterance+'\n\n')
raise Exception(': '.join([identifier, code, msg]))
def prediction(review):
global classifier
global _cv
global _tfidf
cleaned_review = util.clean_text(review)
cleaned_review = [cleaned_review]
vect = _cv.transform(cleaned_review).toarray()
rev = _tfidf.transform(vect)
rev_sparse_tensor = convert_sparse_matrix_to_sparse_tensor(rev)
ordered_sparse_tensor = tf.compat.v1.sparse.reorder(rev_sparse_tensor)
my_prediction = classifier.predict(ordered_sparse_tensor)
predicted_value = my_prediction.item(0)
print(predicted_value)
if predicted_value >= 0.5:
prediction_status = "Great! This is the Positive review."
print("Hello1")
elif predicted_value < 0.5:
prediction_status = "Oops! This is the Negative review."
print("Hello2")
return prediction_status
def read_data(file_path):
with open(file_path, "r", encoding="utf8") as inFile:
lines = inFile.readlines()
datas = []
for index, line in enumerate(tqdm(lines, desc="read_data")):
# 입력 문장을 \t으로 분리
pieces = line.strip().split("\t")
# 데이터의 형태가 올바른지 체크
#assert len(pieces) == 3
if len(pieces) != 3:
continue
if(index == 0):
continue
pieces[1] = clean_text(os.path.join(config["root_dir"],"data"), pieces[1])
id, sequence, label = pieces[0], pieces[1], int(pieces[2])
datas.append((id, sequence, label))
return datas
def predict():
params = json.loads(request.data.decode("utf-8"))
inputs = params['inputs']
random = True if params.get('random', False) == True or params.get(
'random', False) == 'true' else False
temperature = float(params.get('temperature', 1.))
top_k = int(params.get('topk', 1))
number = int(params.get('number', 1))
kind = params.get('kind', 'word')
if kind == 'para':
nb_para = number
nb_sentence = -1
nb_word = -1
elif kind == 'sentence':
nb_para = 1
nb_sentence = number
nb_word = -1
else:
nb_para = 1
nb_sentence = -1
nb_word = number
config = {
'inputs': inputs,
'random': random,
'temperature': temperature,
'top_k': top_k,
'nb_word': nb_word,
'nb_sentence': nb_sentence,
'nb_para': nb_para,
}
input_words = clean_text(inputs)
if len(input_words) == 0:
input_words.append("")
y = rnn.predict(input_words, config)
return json.dumps({'config': config, 'output': ' '.join(y)})
def de_duplicate(files, output):
"""
Input a list of JL files, output a single processed JL file
"""
items = {}
punct_regex = re.compile('[%s]' % re.escape(string.punctuation))
for pth in files:
with open(pth, 'rb') as reader:
lines_no = 0
for line in reader:
try:
item = json.loads(line)
except:
continue
lines_no += 1
# Fix and normalize text
item['text'] = clean_text(item['text'])
# Lower and strip punctuation
txt = punct_regex.sub('', item['text'].lower())
# Drop extra spaces
txt = ' '.join(txt.split())
if txt in items:
# Merge existing tags
item['tags'].extend(items[txt]['tags'])
item['tags'] = sorted(set(t.lower() for t in item['tags']))
else:
# Normalize tags
item['tags'] = sorted(t.lower() for t in item['tags'])
# The dict KEY will automatically overwrite duplicates
items[txt] = item
print(f'Read {lines_no} items from "{pth}".')
out_items = sorted(items.values(), key=lambda x: x['author'].lower())
print(f'Written {len(out_items)} items in "{output}".')
json.dump(out_items, open(output, 'w'))
def GetPredictionOnEvalSet(modelfilename,tokenizer):
global q_max_words,p_max_words,emb_dim
max_para_length = 362
max_query_length = 38
model = load_model('./trained_model/'+modelfilename+'.h5')
#f = open(testfile,'r',encoding="utf-8")
all_scores={} # Dictionary with key = query_id and value = array of scores for respective passages
queryE, paraE= util.loadEvalData()
if tokenizer==None:
with open('./data/tokenizer-Stemed2Lqueries.pickle', 'rb') as handle:
tokenizer=pickle.load(handle)
keys = list(queryE.keys())
print(len(keys))
for i in range(len(keys)):
Xquery, Xpara = list(), list()
query_id = keys[i]
# retrieve query
query = queryE[query_id]
query = util.clean_text([query])
# retrieve text input
paralist = paraE[query_id]
cleanparalist = list()
for j in range(len(paralist)):
cleanparalist.append(util.clean_text([paralist[j]]))
# generate input-output pairs
query_seq = tokenizer.texts_to_sequences([query])[0]
para_seq = tokenizer.texts_to_sequences(cleanparalist)
# split one sequence into multiple X,y pairs
padded_query_seq = pad_sequences([query_seq], maxlen=max_query_length)[0]
#print(padded_query_seq)
padded_para_seq = pad_sequences(para_seq, maxlen=max_para_length)
for k in range(len(paralist)):
Xquery.append(padded_query_seq)
Xpara.append(padded_para_seq[k])
score = model.predict([array(Xquery), array(Xpara)],verbose=0) # do forward-prop on model to get score
score=score[:,1] # extract 1 column at index 1
if(query_id in all_scores):
all_scores[query_id].append(score)
else:
all_scores[query_id] = [score]
text = "\r{0} {1}".format("Done queries: ", i)
sys.stdout.write(text)
sys.stdout.flush()
fw = open("answer.tsv","w",encoding="utf-8")
for query_id in all_scores:
scores = all_scores[query_id]
s=""
for sc in scores:
for value in sc:
value=format(value,'f')#.replace("\n","").replace("[","").replace("]","")
s=s+ str(value) + "\t"
s=re.sub(' {2,}', ' ', s)
s=re.sub(' ', '\t', s)
fw.write(str(query_id) + "\t" +s.rstrip("\t") + "\n")
'''
scores_str = [str(sc) for sc in scores] # convert all scores to string values
scores_str = "\t".join(scores_str) # join all scores in list to make it one string with tab delimiter.
re.sub("[|]", "", scores_str)
scores_str.replace(" ","\t")
fw.write(str(query_id)+"\t"+ scores_str + "\n")
'''
fw.close()
def get_action(hit):
address = hit['_source']['address']
m = re.search(r'.*[\r\n\t\s]+([\w\W]+?)(tel|EIN):', address, re.M)
address = clean_text(m.group(1))
return batch.get_update_action(hit, {'address': address})
def test_clean_text(self):
text = 'æœìíîïýÿòóôõöáâãäëñûüx2,X2'
cleaned_text = util.clean_text(text)
true_text = ['aeoeiiiiyyoooooaaaaenuu', ',']
self.assertEqual(cleaned_text, true_text)
from sklearn.decomposition import PCA
import seaborn as sns
sns.set()
sns.set_context('poster')
nltk.download('state_union')
nltk.download('gutenberg')
# Set current corpus (state_union, gutenberg)
corpus = gutenberg
textnames = corpus.fileids()
corpusnames = {gutenberg : 'Gutenberg books', state_union : 'State union documents'}
print("cleaning texts..")
clean_texts = {name : clean_text(corpus.raw(name)) for name in tqdm(textnames)}
print("Calculating frequencies..")
freqs = {name : nltk.FreqDist(text) for name, text in tqdm(clean_texts.items())}
# Create complete vocabulary
wordlist = set()
for freq in freqs.values():
wordlist.update(freq.keys())
vocabulary = {word : idx for (idx, word) in enumerate(wordlist)}
# Convert texts to wordcount vectors
word_vectors = {name : np.zeros(len(wordlist,)) for name in textnames}
for textname, vector in word_vectors.items():
for word, freq in freqs[textname].items():
vector[vocabulary[word]] += freq
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import nltk
import util
# Doesn't work very well in french ...
LANGUAGE = "english"
text_file = util.get_text(LANGUAGE)
text_str = text_file.read()
text_str = nltk.word_tokenize(text_str, language=LANGUAGE)
text_str = util.clean_text(text_str, LANGUAGE)
text_tag = nltk.pos_tag(text_str)
nltk_text = nltk.Text(text_str)
print type(nltk_text)
# CHUNKING
sentence = nltk.word_tokenize("Bouteflika is the president of Algeria.")
sentence = nltk.pos_tag(sentence)
# grammar = "Actor: {<DT>?<JJS>*<NNP>+}" # jj adjectif
# chunk= nltk.RegexpParser(grammar)
# result = chunk.parse(text_tag)
Proceedings of the ACM SIGKDD International Conference on Knowledge
Discovery and Data Mining (KDD-2004), Aug 22-25, 2004, Seattle,
Washington, USA,
"""
import util
negative_stop_words = util.get_file_content_as_list(
"resources/negative-stop-words.txt")
neutral_stop_words = util.get_file_content_as_list(
"resources/neutral-stop-words.txt")
positive_stop_words = util.get_file_content_as_list(
"resources/positive-stop-words.txt")
negative_words = util.get_file_content_as_list("resources/negative-words.txt")
positive_words = util.get_file_content_as_list("resources/positive-words.txt")
original_text = util.format_into_string(
util.get_file_content_as_list("resources/text.txt"))
text = util.clean_text(util.get_file_content_as_list("resources/text.txt"),
neutral_stop_words)
sentiment = util.analyze_text_sentiment(text, negative_stop_words,
positive_stop_words, negative_words,
positive_words)
print("The original text was: " + original_text)
print("\nThe sentiment score was: " + str(sentiment))
print("This corresponds to a " + util.mood(sentiment) + " mood ... " +
util.emoji(sentiment) + "\n")
"--nb_para",
default=1,
type=int,
help=
"How many paragraph should it return (default: %(default)s, -1: no limit)")
# parser.add_argument('--use_server', nargs="?", const=True, default=False, type=bool, help='Should use the Server architecture')
args = parser.parse_args()
results_dir = dir + '/results'
rnn_dir = dir + '/' + args.model_dir
config = vars(args)
config['log_dir'] = rnn_dir
config['restore_embedding'] = False
config['seq_length'] = None
input_words = clean_text(config['inputs'])
# if args.use_server is True:
# with open('clusterSpec.json') as f:
# clusterSpec = json.load(f)
# config['target'] = 'grpc://' + clusterSpec['server'][0]
# pass
rnn = RNN(config)
y = rnn.predict(input_words, config)
print('__BBB_START__') # Marker for the Regexp used in the App, do not remove
json = json.dumps({
'config': {
'inputs': args.inputs,
'random': args.random,
'temperature': args.temperature,
'top_k': args.top_k,