def getPreds(df, out=None):
# GPU won't work without the next three lines
physical_devices = tf.config.list_physical_devices('GPU')
if len(physical_devices) > 0:
tf.config.experimental.set_memory_growth(physical_devices[0],
enable=True)
dp = DataProcessor()
test_articles = processData(df, ['body']).to_numpy()
test_articles = list(map(lambda x: x[0], test_articles))
test_articles_raw = df.to_numpy()
test_articles_raw = list(map(lambda x: x[0], test_articles_raw))
with open('./onion_tokenizer.pyc', 'rb') as pickleHand:
tokenizer = pickle.load(pickleHand)
assert isinstance(tokenizer, Tokenizer)
seqs = test_articles
max_len = dp.getMaxWords()
seqs = tokenizer.texts_to_sequences(seqs)
seqs = pad_sequences(seqs, max_len)
model = keras.models.load_model('static/onion_connoisseur.h5')
assert isinstance(model, keras.models.Model)
print(test_articles)
predVals = model.predict(seqs)
preds = list(map(lambda x: "Real" if x < 0.75 else "Fake", predVals))
print(preds)
if out:
with open('predictions.csv', 'w', encoding='utf-8') as outHand:
out = csv.writer(outHand)
for i in range(0, len(preds)):
out.writerow([test_articles_raw[i], preds[i], predVals[i]])
return [preds, predVals]
physical_devices = tf.config.list_physical_devices('GPU')
if len(physical_devices) > 0:
tf.config.experimental.set_memory_growth(physical_devices[0], enable=True)
'''what version is this'''
num_words = 200000
dp = DataProcessor()
x, y = dp.getTrainingData()
# Assign token to each word present in headlines
tokenizer = Tokenizer(filters='!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\t\n\'`’‘\\',
num_words=num_words)
tokenizer.fit_on_texts(x)
max_len = dp.getMaxWords()
trainX = tokenizer.texts_to_sequences(x)
trainX = pad_sequences(trainX, max_len)
indexLen = len(tokenizer.word_index)
with open('onion_tokenizer.pyc', 'wb') as pickleHand:
pickle.dump(tokenizer, pickleHand)
# Define our deep learning model
model = Sequential([
Embedding(indexLen + 1, 256),
LSTM(512, dropout=0.2, return_sequences=True),
LSTM(256, dropout=0.2),
Dense(1024, activation='relu'),
Dropout(0.2),
Dense(1, activation='sigmoid')
])
