loss.backward()
# Updates parameters and zeroes gradients
optimizer.step()
optimizer.zero_grad()
# Returns the loss
return loss.item()
# Returns the function that will be called inside the train loop
return train_step
def hinge_loss(y, y_hat):
return torch.mean(torch.clamp(1 - y_hat * y, min=0))
model = SVM() # Our model
optimizer = optim.Adam(model.parameters(), lr=learning_rate) # Our optimizer
model.train() # Our model, SVM is a subclass of the nn.Module, so it inherits the train method
losses = []
val_losses = []
train_step = make_train_step(model, hinge_loss, optimizer)
train_per_epoch = int(len(train_set) / batch_size)
for epoch in range(n_epochs):
sum_loss = 0
sum_val_loss = 0
kbar = pkbar.Kbar(target=train_per_epoch, width=8)
for i, batch in enumerate(train_loader):
#TODO: when have CUDA:
#x_batch = batch['imagePower'].to(device)
#y_batch = batch['label'].to(device)
x_batch = batch['imagePower']
test_samples = samples[int(n_samples*_train_ratio):n_samples]
print("Samples distribution:", preprocessing.samples_statistics(samples, _classes, get_question))
print("Train set distribution:", preprocessing.samples_statistics(train_samples, _classes, get_question))
print("Test set distribution:", preprocessing.samples_statistics(test_samples, _classes, get_question))
train_texts = [sample.text for sample in train_samples]
test_texts = [sample.text for sample in test_samples]
train_matrix, test_matrix, words = preprocessing.preprocess(train_texts, test_texts, words_src = "samples", normalize_flag = False)
if _model == "SVM":
train_labels = preprocessing.samples_to_label(train_samples, _classes, get_question)
test_labels = preprocessing.samples_to_label(test_samples, _classes, get_question)
model = SVM()
model.train(train_matrix, train_labels)
predict = model.predict(test_matrix)
elif _model == "NN":
train_dists = preprocessing.samples_to_dists(train_samples, _classes, get_question)
test_dists = preprocessing.samples_to_dists(test_samples, _classes, get_question)
model = Neural_Network(_n_factors = train_matrix.shape[1], _learning_rate = _learning_rate, _hidden_nodes = _hidden_nodes, _last_layer = len(_classes))
model.train(train_matrix, train_dists, test_matrix, test_dists)
predict = model.predict(test_matrix)
predict = preprocessing.dists_to_labels(predict, _classes)
test_labels = preprocessing.samples_to_label(test_samples, _classes)
else:
raise Exception("Unknown model flag '%s'"%str(_model))
accuracy = np.mean(predict == test_labels)
words_src=tfidf_vectorizer,
normalize_flag=False,
reduction=_reduction,
reduce_n_attr=_reduce_n_attr,
stem_words=_stem_words)
model = None
print("Generating labels..")
if _model == "SVM":
train_labels = preprocessing.samples_to_label(train_samples, _sections,
get_section)
test_labels = preprocessing.samples_to_label(test_samples, _sections,
get_section)
model = SVM()
print("Training.. ")
model.train(train_matrix, train_labels)
predict = model.predict(test_matrix)
elif _model == "NN":
train_dists = preprocessing.samples_to_dists(train_samples, _sections,
get_section)
test_dists = preprocessing.samples_to_dists(test_samples, _sections,
get_section)
model = Neural_Network(_n_factors=train_matrix.shape[1],
_learning_rate=_learning_rate,
_hidden_nodes=_hidden_nodes,
_last_layer=len(_sections))
print("Training.. ")
model.train(train_matrix,
train_dists,
test_matrix,
train_texts = [sample.text for sample in train_samples]
test_texts = [sample.text for sample in test_samples]
tfidf_vectorizer = get_tfidfVectorizer_of_essay_top_tf_words()
print("Vectorizer built..")
train_matrix, test_matrix, words = preprocessing.preprocess(train_texts, test_texts, savedir = _save_dir, words_src = tfidf_vectorizer, normalize_flag = False, reduction = _reduction, reduce_n_attr = _reduce_n_attr, stem_words = _stem_words)
model = None
print("Generating labels..")
if _model == "SVM":
train_labels = preprocessing.samples_to_label(train_samples, _sections, get_section)
test_labels = preprocessing.samples_to_label(test_samples, _sections, get_section)
model = SVM()
print("Training.. ")
model.train(train_matrix, train_labels)
predict = model.predict(test_matrix)
elif _model == "NN":
train_dists = preprocessing.samples_to_dists(train_samples, _sections, get_section)
test_dists = preprocessing.samples_to_dists(test_samples, _sections, get_section)
model = Neural_Network(_n_factors = train_matrix.shape[1], _learning_rate = _learning_rate, _hidden_nodes = _hidden_nodes, _last_layer = len(_sections))
print("Training.. ")
model.train(train_matrix, train_dists, test_matrix, test_dists, max_iter = _max_iter)
predict = model.predict(test_matrix)
predict = preprocessing.dists_to_labels(predict, _sections)
test_labels = preprocessing.samples_to_label(test_samples, _sections, get_section)
else:
raise Exception("Unknown model flag '%s'"%str(_model))
print("Test set distribution:",
preprocessing.samples_statistics(test_samples, _classes, get_question))
train_texts = [sample.text for sample in train_samples]
test_texts = [sample.text for sample in test_samples]
train_matrix, test_matrix, words = preprocessing.preprocess(
train_texts, test_texts, words_src="samples", normalize_flag=False)
if _model == "SVM":
train_labels = preprocessing.samples_to_label(train_samples, _classes,
get_question)
test_labels = preprocessing.samples_to_label(test_samples, _classes,
get_question)
model = SVM()
model.train(train_matrix, train_labels)
predict = model.predict(test_matrix)
elif _model == "NN":
train_dists = preprocessing.samples_to_dists(train_samples, _classes,
get_question)
test_dists = preprocessing.samples_to_dists(test_samples, _classes,
get_question)
model = Neural_Network(_n_factors=train_matrix.shape[1],
_learning_rate=_learning_rate,
_hidden_nodes=_hidden_nodes,
_last_layer=len(_classes))
model.train(train_matrix, train_dists, test_matrix, test_dists)
predict = model.predict(test_matrix)
predict = preprocessing.dists_to_labels(predict, _classes)
test_labels = preprocessing.samples_to_label(test_samples, _classes)