def summarization_query(self,
instruction,
preprocess=True,
label_column=None,
drop=None,
epochs=5,
batch_size=32,
learning_rate=3e-5,
max_text_length=512,
gpu=False,
test_size=0.2,
random_state=49,
generate_plots=True,
save_model=False,
save_path=os.getcwd()):
'''
function to apply algorithm for text summarization
:param many params: used to hyperparametrize the function.
:return a dictionary object with all of the information for the algorithm.
'''
if test_size < 0:
raise Exception("Test size must be a float between 0 and 1")
if test_size >= 1:
raise Exception(
"Test size must be a float between 0 and 1 (a test size greater than or equal to 1 results in no training "
"data)")
if max_text_length < 2:
raise Exception("Text and summary must be at least of length 2")
if epochs < 1:
raise Exception(
"Epoch number is less than 1 (model will not be trained)")
if batch_size < 1:
raise Exception("Batch size must be equal to or greater than 1")
if max_text_length < 1:
raise Exception("Max text length must be equal to or greater than 1")
if save_model:
if not os.path.exists(save_path):
raise Exception("Save path does not exist")
if test_size == 0:
testing = False
else:
testing = True
if gpu:
if tf.test.gpu_device_name():
print('Default GPU Device: {}'.format(tf.test.gpu_device_name()))
else:
raise Exception("Please install GPU version of Tensorflow")
device = '/device:GPU:0'
else:
device = '/device:CPU:0'
tf.random.set_seed(random_state)
np.random.seed(random_state)
data = DataReader(self.dataset)
data = data.data_generator()
if drop is not None:
data.drop(drop, axis=1, inplace=True)
if preprocess:
data.fillna(0, inplace=True)
logger("Preprocessing data...")
if label_column is None:
label = "summary"
else:
label = label_column
tokenizer = T5Tokenizer.from_pretrained("t5-small")
# Find target columns
X, Y, target = get_target_values(data, instruction, label)
logger("->", "Target Column Found: {}".format(target))
logger("Establishing dataset walkers")
# Clean up text
if preprocess:
logger("Preprocessing data")
X = add_prefix(lemmatize_text(text_clean_up(X.array)), "summarize: ")
Y = add_prefix(lemmatize_text(text_clean_up(Y.array)), "summarize: ")
# tokenize text/summaries
X = tokenize_for_input_ids(X, tokenizer, max_text_length)
Y = tokenize_for_input_ids(Y, tokenizer, max_text_length)
logger('Fine-Tuning the model on your dataset...')
# Suppress unnecessary output
with NoStdStreams():
model = TFT5ForConditionalGeneration.from_pretrained(
"t5-small", output_loading_info=False)
if testing:
X_train, X_test, y_train, y_test = train_test_split(
X, Y, test_size=test_size, random_state=random_state)
test_dataset = tf.data.Dataset.from_tensor_slices(
(X_test, y_test)).shuffle(10000).batch(batch_size)
else:
X_train = X
y_train = Y
train_dataset = tf.data.Dataset.from_tensor_slices(
(X_train, y_train)).shuffle(10000).batch(batch_size)
optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate)
loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
total_training_loss = []
total_validation_loss = []
# Training Loop
with tf.device(device):
for epoch in range(epochs):
total_loss = 0
total_loss_val = 0
for data, truth in train_dataset:
with tf.GradientTape() as tape:
out = model(inputs=data, decoder_input_ids=data)
loss_value = loss(truth, out[0])
total_loss += loss_value
grads = tape.gradient(loss_value, model.trainable_weights)
optimizer.apply_gradients(
zip(grads, model.trainable_weights))
total_training_loss.append(total_loss)
# Validation Loop
if testing:
for data, truth in test_dataset:
logits = model(inputs=data,
decoder_input_ids=data,
training=False)
val_loss = loss(truth, logits[0])
total_loss_val += val_loss
total_validation_loss.append(total_loss_val)
logger(
"->", "Final training loss: {}".format(
str(total_training_loss[len(total_training_loss) - 1].numpy())))
if testing:
total_loss_val_str = str(
total_validation_loss[len(total_validation_loss) - 1].numpy())
else:
total_loss_val = [0]
total_loss_val_str = str("0, No validation done")
logger("->", "Final validation loss: {}".format(total_loss_val_str))
if testing:
losses = {
"Training loss":
total_training_loss[len(total_training_loss) - 1].numpy(),
"Validation loss":
total_validation_loss[len(total_validation_loss) - 1].numpy()
}
else:
losses = {
"Training loss":
total_training_loss[len(total_training_loss) - 1].numpy()
}
plots = None
if generate_plots:
logger("Generating plots")
plots = {
"loss":
libra.plotting.nonkeras_generate_plots.plot_loss(
total_training_loss, total_validation_loss)
}
if save_model:
logger("Saving model")
model.save_weights(save_path + "summarization_checkpoint.ckpt")
logger("Storing information in client object under key 'summarization'")
self.models["summarization"] = {
"model": model,
"max_text_length": max_text_length,
"plots": plots,
"tokenizer": tokenizer,
'losses': losses
}
clearLog()
return self.models["summarization"]
def text_classification_query(self,
instruction,
drop=None,
preprocess=True,
label_column=None,
test_size=0.2,
random_state=49,
learning_rate=1e-2,
epochs=20,
monitor="val_loss",
batch_size=32,
max_text_length=200,
max_features=20000,
generate_plots=True,
save_model=False,
save_path=os.getcwd()):
"""
function to apply text_classification algorithm for sentiment analysis
:param many params: used to hyperparametrize the function.
:return a dictionary object with all of the information for the algorithm.
"""
if test_size < 0:
raise Exception("Test size must be a float between 0 and 1")
if test_size >= 1:
raise Exception(
"Test size must be a float between 0 and 1 (a test size greater than or equal to 1 results in no training "
"data)")
if epochs < 1:
raise Exception(
"Epoch number is less than 1 (model will not be trained)")
if batch_size < 1:
raise Exception("Batch size must be equal to or greater than 1")
if max_text_length < 1:
raise Exception("Max text length must be equal to or greater than 1")
if save_model:
if not os.path.exists(save_path):
raise Exception("Save path does not exists")
if test_size == 0:
testing = False
else:
testing = True
data = DataReader(self.dataset)
data = data.data_generator()
if preprocess:
data.fillna(0, inplace=True)
if drop is not None:
data.drop(drop, axis=1, inplace=True)
if label_column is None:
label = "label"
else:
label = label_column
X, Y, target = get_target_values(data, instruction, label)
Y = np.array(Y)
classes = np.unique(Y)
logger("->", "Target Column Found: {}".format(target))
vocab = {}
if preprocess:
logger("Preprocessing data")
X = lemmatize_text(text_clean_up(X.array))
vocab = X
X = encode_text(X, X)
X = np.array(X)
model = get_keras_text_class(max_features, len(classes), learning_rate)
logger("Building Keras LSTM model dynamically")
X_train, X_test, y_train, y_test = train_test_split(
X, Y, test_size=test_size, random_state=random_state)
X_train = sequence.pad_sequences(X_train, maxlen=max_text_length)
X_test = sequence.pad_sequences(X_test, maxlen=max_text_length)
y_vals = np.unique(np.append(y_train, y_test))
label_mappings = {}
for i in range(len(y_vals)):
label_mappings[y_vals[i]] = i
map_func = np.vectorize(lambda x: label_mappings[x])
y_train = map_func(y_train)
y_test = map_func(y_test)
logger("Training initial model")
# early stopping callback
es = EarlyStopping(monitor=monitor, mode='auto', verbose=0, patience=5)
history = model.fit(X_train,
y_train,
validation_data=(X_test, y_test),
batch_size=batch_size,
epochs=epochs,
callbacks=[es],
verbose=0)
logger(
"->", "Final training loss: {}".format(
history.history["loss"][len(history.history["loss"]) - 1]))
if testing:
logger(
"->", "Final validation loss: {}".format(
history.history["val_loss"][len(history.history["val_loss"]) -
1]))
logger(
"->", "Final validation accuracy: {}".format(
history.history["val_accuracy"][
len(history.history["val_accuracy"]) - 1]))
losses = {
'training_loss': history.history['loss'],
'val_loss': history.history['val_loss']
}
accuracy = {
'training_accuracy': history.history['accuracy'],
'validation_accuracy': history.history['val_accuracy']
}
else:
logger("->",
"Final validation loss: {}".format("0, No validation done"))
losses = {'training_loss': history.history['loss']}
accuracy = {'training_accuracy': history.history['accuracy']}
plots = {}
if generate_plots:
# generates appropriate classification plots by feeding all
# information
logger("Generating plots")
plots = generate_classification_plots(history, X, Y, model, X_test,
y_test)
if save_model:
save(model, save_model, save_path=save_path)
logger(
"Storing information in client object under key 'text_classification'")
# storing values the model dictionary
self.models["text_classification"] = {
"model": model,
"classes": classes,
"plots": plots,
"target": Y,
"vocabulary": vocab,
"interpreter": label_mappings,
"max_text_length": max_text_length,
'test_data': {
'X': X_test,
'y': y_test
},
'losses': losses,
'accuracy': accuracy
}
clearLog()
return self.models["text_classification"]
def summarization_query(self,
instruction,
preprocess=True,
label_column=None,
drop=None,
epochs=10,
batch_size=32,
learning_rate=1e-4,
max_text_length=512,
max_summary_length=150,
test_size=0.2,
random_state=49,
gpu=False,
generate_plots=True,
save_model=False,
save_path=os.getcwd()):
'''
function to apply algorithm for text summarization
:param many params: used to hyperparametrize the function.
:return a dictionary object with all of the information for the algorithm.
'''
if test_size < 0:
raise Exception("Test size must be a float between 0 and 1")
if test_size >= 1:
raise Exception(
"Test size must be a float between 0 and 1 (a test size greater than or equal to 1 results in no training "
"data)")
if max_text_length < 2 | max_summary_length < 2:
raise Exception("Text and summary must be at least of length 2")
if epochs < 1:
raise Exception(
"Epoch number is less than 1 (model will not be trained)")
if batch_size < 1:
raise Exception("Batch size must be equal to or greater than 1")
if max_text_length < 1:
raise Exception("Max text length must be equal to or greater than 1")
if max_summary_length < 1:
raise Exception(
"Max summary length must be equal to or greater than 1")
if save_model:
if not os.path.exists(save_path):
raise Exception("Save path does not exists")
if test_size == 0:
testing = False
else:
testing = True
if gpu:
device = "cuda"
else:
device = "cpu"
data = DataReader(self.dataset)
data = data.data_generator()
if drop is not None:
data.drop(drop, axis=1, inplace=True)
if preprocess:
data.fillna(0, inplace=True)
logger("Preprocessing data...")
if label_column is None:
label = "summary"
else:
label = label_column
X, Y, target = get_target_values(data, instruction, label)
df = pd.DataFrame({'text': Y, 'ctext': X})
logger("->", "Target Column Found: {}".format(target))
torch.manual_seed(random_state)
np.random.seed(random_state)
tokenizer = T5Tokenizer.from_pretrained("t5-small")
train_size = 1 - test_size
train_dataset = df.sample(frac=train_size,
random_state=random_state).reset_index(drop=True)
logger("Establishing dataset walkers")
training_set = CustomDataset(train_dataset, tokenizer, max_text_length,
max_summary_length)
if testing:
val_dataset = df.drop(train_dataset.index).reset_index(drop=True)
val_set = CustomDataset(val_dataset, tokenizer, max_text_length,
max_summary_length)
val_params = {
'batch_size': batch_size,
'shuffle': False,
'num_workers': 0
}
val_loader = DataLoader(val_set, **val_params)
else:
val_loader = None
train_params = {
'batch_size': batch_size,
'shuffle': True,
'num_workers': 0
}
training_loader = DataLoader(training_set, **train_params)
# used small model
model = T5ForConditionalGeneration.from_pretrained("t5-small")
model = model.to(device)
optimizer = torch.optim.Adam(params=model.parameters(), lr=learning_rate)
logger('Fine-Tuning the model on your dataset...')
total_loss_train = []
total_loss_val = []
for epoch in range(epochs):
loss_train, loss_val = train(epoch,
tokenizer,
model,
device,
training_loader,
val_loader,
optimizer,
testing=testing)
total_loss_train.append(loss_train)
total_loss_val.append(loss_val)
logger("->", "Final training loss: {}".format(loss_train))
if testing:
logger("->", "Final validation loss: {}".format(loss_val))
else:
logger("->",
"Final validation loss: {}".format("0, No validation done"))
plots = {}
if generate_plots:
logger("Generating plots")
plots.update({
"loss":
libra.plotting.nonkeras_generate_plots.plot_loss(
total_loss_train, total_loss_val)
})
if save_model:
logger("Saving model")
path = save_path + "DocSummarization.pth"
torch.save(model, path)
logger("->", "Saved model to disk as DocSummarization.pth")
logger(
"Storing information in client object under key 'doc_summarization'")
self.models["doc_summarization"] = {
"model": model,
"max_text_length": max_text_length,
"max_sum_length": max_summary_length,
"plots": plots,
'losses': {
'training_loss': loss_train,
'val_loss': loss_val
}
}
clearLog()
return self.models["doc_summarization"]
