from nltk.corpus import stopwords
from nltk.stem import SnowballStemmer
from math import ceil
import config
#from tqdm import tqdm
# create and configure the app
app = Flask(__name__, instance_relative_config=True)
app.config.from_object("config.Config")
filename = app.config['MODEL']
max_length = app.config['SENTENCE_MAX_LENGTH']
embedding_dim = app.config['EMBEDDING_DIM']
vacab_size = app.config['VOCABULARY_SIZE']
model = SentimentModel(embedding_dim, vacab_size, max_length)
model.load_weights(filename)
def preprocess(text, stem=False):
stemmer = SnowballStemmer('english')
text_cleaning_re = "@\S+|https?:\S+|http?:\S|[^A-Za-z0-9]+"
text = re.sub(text_cleaning_re, ' ', str(text).lower()).strip()
tokens = []
stop_words = stopwords.words('english')
for token in text.split():
if token not in stop_words:
if stem:
tokens.append(stemmer.stem(token))
else:
cnn_filters=CNN_FILTERS,
dnn_units=DNN_UNITS,
model_output_classes=OUTPUT_CLASSES,
dropout_rate=DROPOUT_RATE)
if OUTPUT_CLASSES == 2:
model.compile(loss="binary_crossentropy",
optimizer="adam",
metrics=["accuracy"])
else:
model.compile(loss="sparse_categorical_crossentropy",
optimizer="adam",
metrics=["sparse_categorical_accuracy"])
latest = tf.train.latest_checkpoint('./new_weights')
model.load_weights(latest)
# model.load_weights('./weights/base_model_weights')
model.build(None, None)
# print(model.summary())
def encode_sentence(sent):
return tokenizer.convert_tokens_to_ids(tokenizer.tokenize(sent))
def get_prediction(sentence):
tokens = encode_sentence(sentence)
inputs = tf.expand_dims(tokens, 0)