def cross_validation_ah():
import random
random.seed(1234567)
import tensorflow
sess_config = tensorflow.ConfigProto()
sess_config.gpu_options.allow_growth = True
from tensorflow.python.keras.backend import set_session
set_session(tensorflow.Session(config=sess_config))
vocabulary = Vocabulary.deserialize('en-top100k.vocabulary.pkl.gz')
embeddings = WordEmbeddings.deserialize('en-top100k.embeddings.pkl.gz')
reader = JSONPerLineDocumentReader(
'data/experiments/ah-classification1/exported-3621-sampled-positive-negative-ah-no-context.json',
True)
# e = ClassificationExperiment(reader, RandomTokenizedDocumentClassifier(), ClassificationEvaluator())
# e = ClassificationExperiment(reader, MajorityClassTokenizedDocumentClassifier(), ClassificationEvaluator())
# e = ClassificationExperiment(reader, SimpleLSTMTokenizedDocumentClassifier(vocabulary, embeddings), ClassificationEvaluator())
e = ClassificationExperiment(
reader, StackedLSTMTokenizedDocumentClassifier(vocabulary, embeddings),
ClassificationEvaluator())
# e = ClassificationExperiment(reader, CNNTokenizedDocumentClassifier(vocabulary, embeddings), ClassificationEvaluator())
e.run()
def cross_validation_ah(model_type):
# classification without context
import random
random.seed(1234567)
import tensorflow as tf
if tf.test.is_gpu_available():
strategy = tf.distribute.MirroredStrategy()
print('Using GPU')
else:
raise ValueError('CPU not recommended.')
with strategy.scope():
vocabulary = Vocabulary.deserialize('en-top100k.vocabulary.pkl.gz')
embeddings = WordEmbeddings.deserialize('en-top100k.embeddings.pkl.gz')
reader = JSONPerLineDocumentReader(
'data/experiments/ah-classification1/exported-3621-sampled-positive-negative-ah-no-context.json',
True)
e = None
if model_type == 'cnn':
e = ClassificationExperiment(
reader, CNNTokenizedDocumentClassifier(vocabulary, embeddings),
ClassificationEvaluator())
else:
e = ClassificationExperiment(
reader,
StackedLSTMTokenizedDocumentClassifier(vocabulary, embeddings),
ClassificationEvaluator())
e.run()
def train_test_model_with_context(train_dir, indir, outdir):
'''Custom training and testing SSAE model
:param train_dir: Path to JSON file containing training examples
:param indir: Path to LOG file containing examples as Comment() object (which has already been classified by Bert)
:param outdir: Path to LOG file to be created by adding prediction of this model as well'''
import random
random.seed(1234567)
import tensorflow as tf
if tf.test.is_gpu_available():
strategy = tf.distribute.MirroredStrategy()
print('Using GPU')
else:
raise ValueError('CPU not recommended.')
with strategy.scope():
vocabulary = Vocabulary.deserialize('en-top100k.vocabulary.pkl.gz')
embeddings = WordEmbeddings.deserialize('en-top100k.embeddings.pkl.gz')
reader = JSONPerLineDocumentReader(train_dir, True)
e = ClassificationExperiment(
reader,
StructuredSelfAttentiveSentenceEmbedding(vocabulary, embeddings),
ClassificationEvaluator())
test_comments = TokenizedDocumentReader(indir)
result = e.label_external(test_comments)
for k in result.keys():
print(f'{k}: {result[k]}')
instances = dict()
e = Comment(-1, 'lol', 'ah')
f = open(indir, 'rb')
try:
while True:
e = pickle.load(f)
print(e)
instances[str(e.id)] = e
except EOFError:
f.close()
f = open(outdir, 'wb')
for key in result.keys():
model_label, model_score = result[key]
model_label = model_label.lower()
score = model_score[1]
if model_label == 'none':
score = model_score[0]
instances[key].add_model(model_type, model_label, score, None)
e = instances[key]
print(e)
print(e.labels)
print(e.scores)
print('=' * 20)
pickle.dump(instances[key], f)
f.close()
def __init__(self):
self.vocabulary = Vocabulary.deserialize(
'en-top100k.vocabulary.pkl.gz')
self.embeddings = WordEmbeddings.deserialize(
'en-top100k.embeddings.pkl.gz')
assert isinstance(self.vocabulary, Vocabulary)
assert isinstance(self.embeddings, WordEmbeddings)
# for caching computed average word vectors (it's expensive)
# dictionary = (str, np.ndarray)
# key = text, value = average word vector
self._average_word_vector_cache = dict()
def cross_validation_thread_ah_delta_context3():
import random
random.seed(1234567)
import tensorflow
sess_config = tensorflow.ConfigProto()
sess_config.gpu_options.allow_growth = True
from tensorflow.python.keras.backend import set_session
set_session(tensorflow.Session(config=sess_config))
vocabulary = Vocabulary.deserialize('en-top100k.vocabulary.pkl.gz')
embeddings = WordEmbeddings.deserialize('en-top100k.embeddings.pkl.gz')
reader = AHVersusDeltaThreadReader(
'data/sampled-threads-ah-delta-context3', True)
e = ClassificationExperiment(
reader,
StructuredSelfAttentiveSentenceEmbedding(
vocabulary, embeddings, '/tmp/visualization-context3'),
ClassificationEvaluator())
e.run()
def cross_validation_thread_ah_delta_context3():
# classification with context
import random
random.seed(1234567)
import tensorflow as tf
if tf.test.is_gpu_available():
strategy = tf.distribute.MirroredStrategy()
print('Using GPU')
else:
raise ValueError('CPU not recommended.')
with strategy.scope():
vocabulary = Vocabulary.deserialize('en-top100k.vocabulary.pkl.gz')
embeddings = WordEmbeddings.deserialize('en-top100k.embeddings.pkl.gz')
reader = AHVersusDeltaThreadReader(
'data/sampled-threads-ah-delta-context3', True)
e = ClassificationExperiment(
reader,
StructuredSelfAttentiveSentenceEmbedding(
vocabulary, embeddings, '/tmp/visualization-context3'),
ClassificationEvaluator())
e.run()
tokens = doc['words']
weights = doc['weights']
doc_id = doc['id']
string_buffer = []
for i in range(len(tokens)):
print(i, tokens[i], weights[i])
if '___start__' in tokens[i]:
string_buffer.append(' <br />')
string_buffer.append('<span data-weight="' +
str(100 * float(weights[i])) + '">' +
tokens[i] + '</span>')
if '___start__' in tokens[i]:
string_buffer.append(' <br />')
# print(string_buffer)
print("-----------")
return '<div class="answer"><h1>ID: ' + str(
doc_id) + "</h1>" + "".join(string_buffer) + "</div>"
if __name__ == "__main__":
token_counter = 0
vocabulary = Vocabulary.deserialize('en-top100k.vocabulary.pkl.gz')
Visualization().print_fold_latex("visualization-context3/fold1.json",
"/tmp/temp1.tex", vocabulary)
Visualization().print_fold_latex("visualization-context3/fold2.json",
"/tmp/temp2.tex", vocabulary)
print(token_counter)
