def train(model, optimizer, scheduler, train_dataset, val_dataset,
n_epochs=10, batch_size=32, step=0, exp_name=None, device=1):
step = step
best_loss = float('inf')
model.train()
writer = SummaryWriter(f'runs/{exp_name}')
loader = DataLoader(train_dataset, batch_size=batch_size, pin_memory=True, num_workers=4, shuffle=True)
for epoch in tqdm(range(n_epochs), total=n_epochs):
pbar = tqdm(loader, total=len(loader))
for image, mask in pbar:
image, mask = Variable(image).cuda(device), Variable(mask).cuda(device)
output = model(image)
loss = F.binary_cross_entropy_with_logits(output, mask)
optimizer.zero_grad()
loss.backward()
scheduler.step()
optimizer.step()
pbar.set_description(f'[Loss: {loss.data[0]:.4f}]')
writer.add_scalar('loss', loss.data[0], step)
writer.add_scalar('lr', scheduler.lr, step)
step += 1
val_loss = eval(model, val_dataset, batch_size, writer, step, device)
for name, param in model.named_parameters():
writer.add_histogram(name, param.clone().cpu().data.numpy(), step, bins='doane')
if val_loss < best_loss:
best_loss = val_loss
save(model, step, val_loss, exp_name, f'checkpoints/{exp_name}.pt')
def train(model,
optimizer,
scheduler,
focal_loss,
train_dataset,
val_dataset=None,
n_epochs=10,
batch_size=32,
step=0,
exp_name=None,
device=1):
step = step
best_loss = float('inf')
model.train()
writer = SummaryWriter(f'runs/{exp_name}')
loader = DataLoader(train_dataset,
batch_size=batch_size,
pin_memory=True,
num_workers=4,
shuffle=True)
for epoch in tqdm(range(n_epochs), total=n_epochs):
pbar = tqdm(loader, total=len(loader))
for images, class_labels, anchor_deltas in pbar:
images = Variable(images).cuda()
class_labels = Variable(class_labels).cuda()
anchor_deltas = Variable(anchor_deltas).cuda()
class_preds, box_preds = model(images)
class_loss = focal_loss(class_preds, class_labels)
box_loss = F.smooth_l1_loss(box_preds, anchor_deltas)
loss = class_loss + box_loss
optimizer.zero_grad()
loss.backward()
scheduler.step()
optimizer.step()
pbar.set_description(f'[Loss: {loss.data[0]:.4f}]')
writer.add_scalar('class_loss', class_loss.data[0], step)
writer.add_scalar('box_loss', box_loss.data[0], step)
writer.add_scalar('loss', loss.data[0], step)
writer.add_scalar('lr', scheduler.lr, step)
step += 1
val_loss = eval(model, focal_loss, val_dataset, batch_size, writer,
step, device) if val_dataset else float('inf')
for name, param in model.named_parameters():
writer.add_histogram(name,
param.clone().cpu().data.numpy(),
step,
bins='doane')
if val_loss <= best_loss:
best_loss = val_loss
save(model, step, val_loss, exp_name, f'checkpoints/{exp_name}.pt')
def categories_info():
filepath = root + "/dataset/yelp_academic_dataset_business.json"
""" Generate the count of reviews per category """
business_file = open(filepath);
lines_file = business_file.readlines();
business_file.close();
business_by_category = dict();
categories_business_counts = Counter();
categories_reviews_counts = Counter();
for line_json in lines_file:
business_dict = json.loads(line_json);
business_id = business_dict["business_id"];
categories_list = business_dict["categories"];
for category in categories_list:
if category not in business_by_category:
business_by_category[category] = set();
categories_business_counts[category] += 1
categories_reviews_counts[category] += business_dict["review_count"];
business_by_category[category].add(business_id);
data.save(business_by_category, 'business_by_category.pkl.gz');
data.save(categories_business_counts, 'categories_business_counts.pkl.gz');
data.save(categories_reviews_counts, 'categories_reviews_counts.pkl.gz');
trainer.module.params[:] = bestweights
break
epochs += 1
if len(validationErrors) >= continueEpochs * 2:
# have the validation errors started going up again?
# compare the average of the last few to the previous few
old = validationErrors[-continueEpochs * 2:-continueEpochs]
new = validationErrors[-continueEpochs:]
if min(new) > max(old):
trainer.module.params[:] = bestweights
break
elif reduce(lambda x, y: x + (y - round(new[-1], convergence_threshold)), [round(y, convergence_threshold) for y in new]) == 0:
trainer.module.params[:] = bestweights
break
print('> Test on holdout set')
print(trainer.testOnData(testData))
# hit this command if you want to save the weights:
data.save(bestweights, bestweights_filename)
predict = np.array([np.argmax(net.activate(x)) for x, _ in testData])
realerr = float(sum(np.equal(predict, Y_test)))/len(predict)
print('> Error on test set %f' % realerr)
from evaluation import error_classification_matrix
error_classification_matrix(
Y_test,
predict,
)
def test_mlp(learning_rate=0.01, L1_reg=0.00, L2_reg=0.0001, n_epochs=1000,
dataset='mnist.pkl.gz', batch_size=20, n_in=28*28, n_out=10, n_hidden=500):
"""
Demonstrate stochastic gradient descent optimization for a multilayer
perceptron
This is demonstrated on MNIST.
:type learning_rate: float
:param learning_rate: learning rate used (factor for the stochastic
gradient
:type L1_reg: float
:param L1_reg: L1-norm's weight when added to the cost (see
regularization)
:type L2_reg: float
:param L2_reg: L2-norm's weight when added to the cost (see
regularization)
:type n_epochs: int
:param n_epochs: maximal number of epochs to run the optimizer
:type dataset: string
:param dataset: the path of the MNIST dataset file from
http://www.iro.umontreal.ca/~lisa/deep/data/mnist/mnist.pkl.gz
"""
datasets = load_data(dataset, cast=False)
train_set_x, train_set_y = datasets[0]
valid_set_x, valid_set_y = datasets[1]
test_set_x, test_set_y = datasets[2]
# compute number of minibatches for training, validation and testing
n_train_batches = train_set_x.get_value(borrow=True).shape[0] / batch_size
n_valid_batches = valid_set_x.get_value(borrow=True).shape[0] / batch_size
n_test_batches = test_set_x.get_value(borrow=True).shape[0] / batch_size
######################
# BUILD ACTUAL MODEL #
######################
print '> Building model'
# allocate symbolic variables for the data
index = T.lscalar() # index to a [mini]batch
x = T.matrix('x') # the data is presented as rasterized images
y = T.vector('y') # the labels are presented as 1D vector of
# [int] labels
rng = np.random.RandomState(1234)
# construct the MLP class
model = MLR(rng=rng, input=x, n_in=n_in,
n_hidden=n_hidden, n_out=n_out)
# the cost we minimize during training is the negative log likelihood of
# the model plus the regularization terms (L1 and L2); cost is expressed
# here symbolically
cost = model.cost(y) \
+ L1_reg * model.L1 \
+ L2_reg * model.L2_sqr
# compiling a Theano function that computes the mistakes that are made
# by the model on a minibatch
test_model = theano.function(inputs=[index],
outputs=model.errors(y),
givens={
x: test_set_x[index * batch_size:(index + 1) * batch_size],
y: test_set_y[index * batch_size:(index + 1) * batch_size]})
test_prediction = theano.function(inputs=[index],
outputs=model.prediction(),
givens={
x: test_set_x[index * batch_size:(index + 1) * batch_size]})
validate_model = theano.function(inputs=[index],
outputs=model.errors(y),
givens={
x: valid_set_x[index * batch_size:(index + 1) * batch_size],
y: valid_set_y[index * batch_size:(index + 1) * batch_size]})
# compute the gradient of cost with respect to theta (sotred in params)
# the resulting gradients will be stored in a list gparams
gparams = []
for param in model.params:
gparam = T.grad(cost, param)
gparams.append(gparam)
# specify how to update the parameters of the model as a list of
# (variable, update expression) pairs
updates = []
# given two list the zip A = [a1, a2, a3, a4] and B = [b1, b2, b3, b4] of
# same length, zip generates a list C of same size, where each element
# is a pair formed from the two lists :
# C = [(a1, b1), (a2, b2), (a3, b3), (a4, b4)]
for param, gparam in zip(model.params, gparams):
updates.append((param, param - learning_rate * gparam))
# compiling a Theano function `train_model` that returns the cost, but
# in the same time updates the parameter of the model based on the rules
# defined in `updates`
train_model = theano.function(inputs=[index], outputs=cost,
updates=updates,
givens={
x: train_set_x[index * batch_size:(index + 1) * batch_size],
y: train_set_y[index * batch_size:(index + 1) * batch_size]})
###############
# TRAIN MODEL #
###############
print '> Training'
# early-stopping parameters
patience = 10000 # look as this many examples regardless
patience_increase = 2 # wait this much longer when a new best is
# found
improvement_threshold = 0.995 # a relative improvement of this much is
# considered significant
validation_frequency = min(n_train_batches, patience / 2)
# go through this many
# minibatche before checking the network
# on the validation set; in this case we
# check every epoch
best_params = None
best_validation_loss = np.inf
best_iter = 0
test_score = 0.
start_time = time.clock()
epoch = 0
done_looping = False
while (epoch < n_epochs) and (not done_looping):
epoch = epoch + 1
for minibatch_index in xrange(n_train_batches):
minibatch_avg_cost = train_model(minibatch_index)
# iteration number
iter = (epoch - 1) * n_train_batches + minibatch_index
if (iter + 1) % validation_frequency == 0:
# compute zero-one loss on validation set
validation_losses = [validate_model(i) for i
in xrange(n_valid_batches)]
this_validation_loss = np.mean(validation_losses)
print('- epoch %i, minibatch %i/%i, validation error %f %%' %
(epoch, minibatch_index + 1, n_train_batches,
this_validation_loss * 100.))
# if we got the best validation score until now
if this_validation_loss < best_validation_loss:
#improve patience if loss improvement is good enough
if this_validation_loss < best_validation_loss * \
improvement_threshold:
patience = max(patience, iter * patience_increase)
best_validation_loss = this_validation_loss
best_iter = iter
# test it on the test set
test_losses = [test_model(i) for i
in xrange(n_test_batches)]
test_score = np.mean(test_losses)
print(('- epoch %i, minibatch %i/%i, test error of '
'best model %f %%') %
(epoch, minibatch_index + 1, n_train_batches,
test_score * 100.))
if patience <= iter:
done_looping = True
break
end_time = time.clock()
test_result = [test_prediction(i) for i in xrange(n_test_batches)]
test_result = np.concatenate(test_result, axis=0)
test_target = test_set_y.eval() #[0: len(test_result)]
data.save((test_result, test_target), 'result.pkl.gz')
print(('> Optimization complete. Best validation score of %f %% '
'obtained at iteration %i, with test performance %f %%') %
(best_validation_loss * 100., best_iter + 1, test_score * 100.))
print >> sys.stderr, ('The code for file ' +
os.path.split(__file__)[1] +
' ran for %.2fm' % ((end_time - start_time) / 60.))
print "> Create training set"
X_train = np.concatenate(X_train, axis=0)
Y_train = np.array(Y_train)
assert(X_train.shape[0] == len(Y_train))
print "> Create holdout set"
X_holdout = np.concatenate(X_holdout, axis=0)
Y_holdout = np.array(Y_holdout)
assert(X_holdout.shape[0] == len(Y_holdout))
permut = np.random.permutation(len(Y_holdout))
print "- Create valid set"
X_valid = X_holdout[permut[0:len(permut)/2], :]
Y_valid = Y_holdout[permut[0:len(permut)/2]]
assert(X_valid.shape[0] == len(Y_valid))
print "- Create test subet"
X_test = X_holdout[permut[len(permut)/2::], :]
Y_test = Y_holdout[permut[len(permut)/2::]]
assert(X_test.shape[0] == len(Y_test))
print "< Test sets created"
data.save((
(X_train, Y_train),
(X_valid, Y_valid),
(X_test, Y_test),
), "data.pkl.gz"
)
from utils import data
f_data_train = "slda_data_train.txt";
f_data_test = "slda_data_test.txt";
def get_corpus(filename):
open_file = open(filename);
lines = open_file.readlines();
corpus = [];
for line in lines:
entries = line.split();
doc_in_corpus = [];
# First entry is ignored as it corresponds to the # of words
for entry in entries[1:]:
doc_in_corpus.append( tuple( [int(x) for x in entry.split(':') ] ) );
corpus.append(doc_in_corpus);
open_file.close();
return corpus;
corpus_train = get_corpus( f_data_train );
corpus_test = get_corpus( f_data_test );
data.save(corpus_train, "lda_corpus_train.pkl.gz");
data.save(corpus_test, "lda_corpus_test.pkl.gz");
print("> Create training set")
X_train = np.concatenate(X_train, axis=0)
Y_train = np.array(Y_train)
assert(X_train.shape[0] == len(Y_train))
print("> Create holdout set")
X_holdout = np.concatenate(X_holdout, axis=0)
Y_holdout = np.array(Y_holdout)
assert(X_holdout.shape[0] == len(Y_holdout))
# permut = np.random.permutation(len(Y_holdout))
permut = range(len(Y_holdout));
print("- Create valid set")
X_valid = X_holdout[permut[len(permut)/2::], :]
Y_valid = Y_holdout[permut[len(permut)/2::]]
assert(X_valid.shape[0] == len(Y_valid))
print "- Create test subet"
X_test = X_holdout[permut[0:len(permut)/2], :]
Y_test = Y_holdout[permut[0:len(permut)/2]]
assert(X_test.shape[0] == len(Y_test))
print "< Test sets created"
data.save((
(X_train, Y_train),
(X_valid, Y_valid),
(X_test, Y_test),
), training_filename
)
data = np.array(data)
indices = np.array(indices)
indptr = np.array(indptr)
target = np.array(target)
# generating csr matrix
csr_train = csr_matrix( (data, indices, indptr), shape = (idoc, max(indices)+1 ) )
return (csr_train,target)
###########
# Process #
###########
print('> Generating training matrix ')
X_train, Y_train = generateScipyCSRMatrix(chosenGenerator, dataset_train_filename)
data.save((X_train, Y_train), file_csr_train);
print('> Generating test matrix ')
X_test, Y_test = generateScipyCSRMatrix(chosenGenerator, dataset_test_filename)
data.save((X_test, Y_test), file_csr_test);
# fitting the linear regression model
print('> Fitting the model ')
# Actually performing the linear regression
alpha_opt_word_freq = 70.
lin_reg_model = linear_model.SGDRegressor(
eta0=0.04, # starting learning rate
n_iter=300, # max number of epochs
shuffle=True,
verbose=0,
alpha=0.000000, # regularization constant
);
def generate_slda_data(filename="yelp_academic_dataset_review_training.json", n_reviews=None, category=None):
filepath = root + "/dataset/" + filename
""" A couple of useful initializations """
# Chris Potts tokenizer.
tok = tokenizer.Tokenizer(preserve_case=False)
# min and max ngram sizes
MIN_NGRAM = 1
MAX_NGRAM = 1
word_set = set()
# set of unique words
word2idx = dict()
# mapping from word to int representation of a word
ratings_list = []
reviews_list = []
reviews = []
data_list = []
words_distr = dict()
words_counts = Counter()
""" PHASE 1 : Load file and get set of all words """
stopwords = nltk.corpus.stopwords.words("english")
print " PHASE 1 : Get all words "
loaded_file = open(filepath)
lines_file = loaded_file.readlines()
if n_reviews == None:
n_reviews = len(lines_file)
loaded_file.close()
i_review = 1
# we randomly select n_reviews from the dataset
permutation = np.random.permutation(len(lines_file))
sample_reviews = permutation[0:n_reviews]
for idx_review in sample_reviews:
line_json = lines_file[idx_review]
review_dict = json.loads(line_json)
tokens_list = tok.ngrams(review_dict["text"], MIN_NGRAM, MAX_NGRAM, string=True)
rating = review_dict["stars"]
for token in tokens_list:
if token not in stopwords:
"""
if token not in words_distr:
words_distr[token] = Counter({5:0, 4:0, 3:0, 2:0, 1:0});
words_distr[token][rating] += 1;
"""
words_counts[token] += 1
reviews_list.append(Counter(tokens_list))
ratings_list.append(review_dict["stars"] - 1)
word_set |= set(tokens_list)
disp.tempPrint(str(i_review))
i_review += 1
""" PHASE 2 : Word to int conversion """
filter_threshold = 0.00001 * (max(words_counts.values()) * 1.0)
print " PHASE 2 : Word to int conversion "
i_word = 1
for word in word_set:
if words_counts[word] >= filter_threshold:
word2idx[word] = i_word
disp.tempPrint(str(i_word))
i_word += 1
print " Filtered. Before : %d words. After : %d" % (len(word_set), len(word2idx))
""" PHASE 3 : Converting data to the right format """
print " PHASE 3 : Converting data to the right format "
i_review = 1
for review in reviews_list:
nwords = 0
data_line = ""
for word in review:
if word in word2idx:
data_line += " " + str(word2idx[word]) + ":" + str(review[word])
nwords += 1
data_line += "\n"
if nwords != 0:
data_line = str(nwords) + " " + data_line
data_list.append(data_line)
disp.tempPrint(str(i_review))
i_review += 1
""" PHASE 4 : Save into right files """
print " PHASE 4 : Save into right files "
n_reviews = len(data_list)
idx_test = n_reviews * 8 / 10
if category:
category = "_" + category
else:
cateogory = ""
data_train = open("/tmp/slda_data_train" + category + ".txt", "w")
label_train = open("/tmp/slda_label_train" + category + ".txt", "w")
data_test = open("/tmp/slda_data_test" + category + ".txt", "w")
label_test = open("/tmp/slda_label_test" + category + ".txt", "w")
for i_review in range(idx_test):
data_train.write(data_list[i_review])
label_train.write(str(ratings_list[i_review]) + "\n")
for i_review in range(idx_test, n_reviews):
data_test.write(data_list[i_review])
label_test.write(str(ratings_list[i_review]) + "\n")
data_train.close()
data_test.close()
label_train.close()
label_test.close()
""" PHASE 5 : Save useful datastructures """
print " PHASE 5 : Save useful datastructures "
data.save(reviews_list, "/tmp/slda_reviews" + category + ".pkl.gz")
data.save(ratings_list, "/tmp/slda_ratings" + category + ".pkl.gz")
data.save(word2idx, "/tmp/slda_word2idx" + category + ".pkl.gz")
