I am trying to use hyperas to optimize my keras model but I keep getting NameError: processing (function_name) is not defined. I have already looked at this and this example from hyperas and done exactly that. It doesn't seem to work for me.
This is my code:
def processing():
df = pd.read_json('balanced_all.json')
def label (df):
if df['rating'] < 3:
return 0
if df['rating'] > 3:
return 1
df['label'] = df.apply (lambda df: label(df), axis=1)
df = df[['review_text', 'label']]
maxlen = 100
max_words = 2000
tokenizer = Tokenizer(num_words=max_words)
tokenizer.fit_on_texts(df['review_text'].values)
sequences = tokenizer.texts_to_sequences(df['review_text'].values)
word_index = tokenizer.word_index
sequences = pad_sequences(sequences, maxlen=maxlen)
labels = pd.get_dummies(df['label']).values
glove_dir = '/home/uttam/Documents/Thesis/Glove'
embeddings_index = {}
f = open(os.path.join(glove_dir, 'glove.6B.100d.txt'), 'r', encoding='utf-8')
for line in f:
values = line.split()
word = values[0]
coefs = np.asarray(values[1:], dtype='float32')
embeddings_index[word] = coefs
f.close()
embedding_dim = 100
embedding_matrix = np.zeros((max_words, embedding_dim))
for word, i in word_index.items():
if i < max_words:
embedding_vector = embeddings_index.get(word)
if embedding_vector is not None:
embedding_matrix[i] = embedding_vector
return sequences, labels, embedding_matrix
def data():
sequences = processing()[0]
labels = processing()[1]
x_train, x_test, y_train, y_test = train_test_split(sequences,labels, test_size = 0.33, random_state = 42)
return x_train, y_train, x_test, y_test
def create_model(x_train, y_train, x_test, y_test):
embedding_dim = 100
max_words = 2000
embedding_matrix = processing()[2]
model = Sequential()
model.add(Embedding(max_words, embedding_dim, input_length=100))
model.add(LSTM(128))
model.add(Dropout({{uniform(0, 1)}}))
model.add(Dense(2, activation='sigmoid'))
model.layers[0].set_weights([embedding_matrix])
model.layers[0].trainable = False
model.compile(optimizer={{choice(['rmsprop', 'adam', 'sgd'])}}, loss='binary_crossentropy',metrics=['acc'])
result = model.fit(x_train, y_train, epochs=20, batch_size={{choice([64, 128])}}, validation_split=0.2)
model.save('pre_trained_glove_model.h5')
validation_acc = np.amax(result.history['val_acc'])
print('Best validation acc of epoch:', validation_acc)
return {'loss': -validation_acc, 'status': STATUS_OK, 'model': model}
if __name__ == '__main__':
best_run, best_model = optim.minimize(model=create_model,
data=data,
algo=tpe.suggest,
max_evals=5,
trials=Trials())
x_train, y_train, x_test, y_test = data()
print("Evalutation of best performing model:")
print(best_model.evaluate(x_test, y_test))
print("Best performing model chosen hyper-parameters:")
print(best_run)
I don't even need the intermediate function, I had to create it because hyperas didn't find the global variable. for e.g. if I had a variable x outside the hyperas function say create_model(), It would say NameError: x is not defined
I need this because as you can see I am using pre-trained glove embedding. I can't put everything in either data() or create_model(). For e.g. data()needs the variable sequences and label and create_model needs the variable embedding_matrix, so there is no way (as far as I know) to split everything in two functions.
Only way this worked for me was by putting everything in both data() and create_model() functions, which definitely is not efficient and not the way to do.
A little bit late but for future reference, you are right hyperas doesn't recognize global variables. You can pass the function in a list of functions in minimize:
best_run, best_model = optim.minimize(model=create_model,
data=data,
functions=[processing], # <<
algo=tpe.suggest,
max_evals=5,
trials=Trials())
As you mentioned if you need to pass a global variable in hyperas. You can choose one of these options:
Using data():
def data():
## ... my code ...
return x_train, y_train, x_test, y_test, foo
def create_model(x_train, y_train, x_test, y_test, foo):
or defining a new function and pass it in the list of functions:
def my_funct():
return foo
def data():
return x_train, y_train, x_test, y_test
def create_model(x_train, y_train, x_test, y_test):
foo = my_funct()
best_run, best_model = optim.minimize(model=create_model,
data=data,
functions=[my_funct], # << foo
algo=tpe.suggest,
max_evals=5,
trials=Trials())