def write_fake_predictions(output_path, task="MRPC"):
"""
:param input_path:
:param output_path:
:param task:
:return:
>>> write_fake_predictions("/work/anlausch/replant/bert/predictions/base_32_5e-05_3.0/copy_for_submission/fakes/STS-B.tsv", task="STSB")
"""
if task != "STSB":
import run_classifier
else:
import run_regression
if task == "MNLI":
test_examples = run_classifier.MnliProcessor().get_test_examples(
os.environ['GLUE_DIR'] + "/" + task, False)
labels = run_classifier.MnliProcessor().get_labels()
elif task == "QQP":
test_examples = run_classifier.QQPProcessor().get_test_examples(
os.environ['GLUE_DIR'] + "/" + task)
labels = run_classifier.QQPProcessor().get_labels()
elif task == "WNLI":
test_examples = run_classifier.WNLIProcessor().get_test_examples(
os.environ['GLUE_DIR'] + "/" + task)
labels = run_classifier.WNLIProcessor().get_labels()
elif task == "CoLA":
test_examples = run_classifier.ColaProcessor().get_test_examples(
os.environ['GLUE_DIR'] + "/" + task)
labels = run_classifier.ColaProcessor().get_labels()
elif task == "STSB":
test_examples = run_regression.STSBProcessor().get_test_examples(
os.environ['GLUE_DIR'] + "/" + task)
elif task == "diagnostic":
test_examples = run_classifier.DiagnosticProcessor().get_test_examples(
os.environ['GLUE_DIR'] + "/" + task)
labels = run_classifier.DiagnosticProcessor().get_labels()
with codecs.open(output_path, "w", "utf8") as f_out:
f_out.write("index\tprediction\n")
if task != "STSB":
for i, data in enumerate(test_examples):
f_out.write(str(i) + "\t" + str(labels[0]) + "\n")
else:
for i, data in enumerate(test_examples):
f_out.write(str(i) + "\t" + str(2.5) + "\n")
f_out.close()
def parse_predictions(input_path, output_path, task="STSB"):
"""
:param input_path:
:param output_path:
:param task:
:return:
>>> parse_predictions("/work/anlausch/replant/bert/predictions/wn_binary/mnli_neu_32_5e-05_3.0/test_results.tsv", "/work/anlausch/replant/bert/predictions/wn_binary_32_5e-05_3.0/MNLI-mm-neu.tsv", task="MNLI")
"""
if task != "STSB":
import run_classifier
else:
import run_regression
predicted_labels = []
if task == "MRPC":
#ids = MrpcProcessor().get_test_examples(os.environ['GLUE_DIR'] + "/MRPC")
labels = run_classifier.MrpcProcessor().get_labels()
if task == "RTE":
labels = run_classifier.RTEProcessor().get_labels()
if task == "QNLI":
labels = run_classifier.QNLIProcessor().get_labels()
if task == "QNLIV2":
labels = run_classifier.QNLIProcessor().get_labels()
if task == "MNLI":
labels = run_classifier.MnliProcessor().get_labels()
if task == "SST2":
labels = run_classifier.SST2Processor().get_labels()
if task == "CoLA":
labels = run_classifier.ColaProcessor().get_labels()
if task == "QQP":
labels = run_classifier.QQPProcessor().get_labels()
if task == "diagnostic":
labels = run_classifier.DiagnosticProcessor().get_labels()
with codecs.open(input_path, "r", "utf8") as f_in:
for line in f_in.readlines():
predictions = np.array(line.split("\t"), dtype=np.float32)
if task != "STSB":
predicted_index = np.argmax(predictions)
predicted_labels.append(labels[predicted_index])
else:
predicted_labels.append(predictions[0])
f_in.close()
with codecs.open(output_path, "w", "utf8") as f_out:
f_out.write("index\tprediction\n")
for i, prediction in enumerate(predicted_labels):
f_out.write(str(i) + "\t" + str(prediction) + "\n")
f_out.close()
def __init__(self, path):
self.init_checkpoint = path + "/anshaj.ckpt"
self.tokenization = run_classifier.tokenization
processor = run_classifier.ColaProcessor()
BATCH_SIZE = 32
self.MAX_SEQ_LENGTH = 50
self.tokenization.validate_case_matches_checkpoint(
False, self.init_checkpoint)
bert_config = run_classifier.modeling.BertConfig.from_json_file(
path + "/bert_config.json")
self.tokenizer = self.tokenization.FullTokenizer(vocab_file=path +
"/vocab.txt",
do_lower_case=False)
is_per_host = tf.contrib.tpu.InputPipelineConfig.PER_HOST_V2
run_config = tf.contrib.tpu.RunConfig(
model_dir=path,
cluster=None,
master=None,
save_checkpoints_steps=500,
tpu_config=tf.contrib.tpu.TPUConfig(
iterations_per_loop=1000,
num_shards=8,
per_host_input_for_training=is_per_host))
model_fn = run_classifier.model_fn_builder(
bert_config=bert_config,
num_labels=3,
init_checkpoint=self.init_checkpoint,
learning_rate=1e-05,
num_train_steps=None,
num_warmup_steps=None,
use_tpu=False,
use_one_hot_embeddings=False)
self.estimator = tf.contrib.tpu.TPUEstimator(
use_tpu=False,
model_fn=model_fn,
config=run_config,
train_batch_size=BATCH_SIZE,
eval_batch_size=BATCH_SIZE,
predict_batch_size=BATCH_SIZE)
def traineval_model(self, local_dir,
nb_epoch,
batch_size):
"""
Use the BERT Uncased language model to train on
new data
"""
tf.logging.set_verbosity(tf.logging.INFO)
logging.info("*:BERT MODEL PATH:%s",BERT_MODEL_PATH)
logging.info("*:Local Dir%s",local_dir)
mod_name = self.model_name
BERT_MODEL = 'uncased_L-12_H-768_A-12'
BERT_PRETRAINED_DIR = BERT_MODEL_PATH
OUTPUT_DIR = os.path.join(local_dir,'output_bert')
DATA_DIR = os.path.join(local_dir,'data')
logging.info('***** Model output directory: %s*****',OUTPUT_DIR)
logging.info('***** BERT pretrained directory: %s *****',BERT_PRETRAINED_DIR)
logging.info('***** DATA directory: %s *****',DATA_DIR)
TRAIN_BATCH_SIZE = 32
EVAL_BATCH_SIZE = 8
LEARNING_RATE = 2e-5
NUM_TRAIN_EPOCHS = 3.0
WARMUP_PROPORTION = 0.1
MAX_SEQ_LENGTH = 128
# Model configs
# if you wish to finetune a model on a larger dataset, use larger interval
SAVE_CHECKPOINTS_STEPS = 1000
# each checpoint weights about 1,5gb
ITERATIONS_PER_LOOP = 1000
NUM_TPU_CORES = 8
VOCAB_FILE = os.path.join(BERT_PRETRAINED_DIR,'vocab.txt')
BERT_CONFIG_FILE = os.path.join(BERT_PRETRAINED_DIR,'bert_config.json')
INIT_CHECKPOINT = os.path.join(BERT_PRETRAINED_DIR, 'bert_model.ckpt')
DO_LOWER_CASE = BERT_MODEL.startswith('uncased')
logging.info("Found VOCAB File:%s",VOCAB_FILE)
bert_config = modeling.BertConfig.from_json_file(BERT_CONFIG_FILE)
tf.gfile.MakeDirs(OUTPUT_DIR)
processor = run_classifier.ColaProcessor()
label_list = processor.get_labels()
tokenizer = tokenization.FullTokenizer(
vocab_file=VOCAB_FILE, do_lower_case=DO_LOWER_CASE)
# Since training will happen on GPU, we won't need a cluster resolver
tpu_cluster_resolver = None
# TPUEstimator also supports training on CPU and GPU. You don't need to define a separate tf.estimator.Estimator.
run_config = tf.contrib.tpu.RunConfig(
cluster=tpu_cluster_resolver,
model_dir=OUTPUT_DIR,
save_checkpoints_steps=SAVE_CHECKPOINTS_STEPS,
tpu_config=tf.contrib.tpu.TPUConfig(
iterations_per_loop=ITERATIONS_PER_LOOP,
num_shards=NUM_TPU_CORES,
per_host_input_for_training=tf.contrib.tpu.InputPipelineConfig.PER_HOST_V2))
train_examples = None
num_train_steps = None
num_warmup_steps = None
train_examples = processor.get_train_examples(DATA_DIR)
num_train_steps = int(
len(train_examples) / TRAIN_BATCH_SIZE * NUM_TRAIN_EPOCHS)
num_warmup_steps = int(num_train_steps * WARMUP_PROPORTION)
model_fn = run_classifier.model_fn_builder(
bert_config=bert_config,
num_labels=len(label_list),
init_checkpoint=INIT_CHECKPOINT,
learning_rate=LEARNING_RATE,
num_train_steps=num_train_steps,
num_warmup_steps=num_warmup_steps,
use_tpu=False, # If False training will fall on CPU or GPU, depending on what is available
use_one_hot_embeddings=False) #Try with True
estimator = tf.contrib.tpu.TPUEstimator(
use_tpu=False, # If False training will fall on CPU or GPU, depending on what is available
model_fn=model_fn,
config=run_config,
train_batch_size=TRAIN_BATCH_SIZE,
eval_batch_size=EVAL_BATCH_SIZE)
# Train the model.
logging.info('Starting Training...')
train_file = os.path.join(OUTPUT_DIR, "train.tf_record")
run_classifier.file_based_convert_examples_to_features(
train_examples, label_list, MAX_SEQ_LENGTH, tokenizer, train_file)
tf.logging.info('***** Started training at {} *****'.format(datetime.datetime.now()))
tf.logging.info(' Num examples = {}'.format(len(train_examples)))
tf.logging.info(' Batch size = {}'.format(TRAIN_BATCH_SIZE))
tf.logging.info(" Num steps = %d", num_train_steps)
train_input_fn = run_classifier.file_based_input_fn_builder(
input_file=train_file,
seq_length=MAX_SEQ_LENGTH,
is_training=True,
drop_remainder=True)
estimator.train(input_fn=train_input_fn, max_steps=num_train_steps)
final_ckpt = estimator.latest_checkpoint()
print('***** Finished training at {} *****'.format(datetime.datetime.now()))
logging.info("*****Final Checkpoint*****%s",final_ckpt)
final_ckpt_file = os.path.join(OUTPUT_DIR, "final_ckpt.txt")
with tf.gfile.GFile(final_ckpt_file, "w") as writer:
writer.write("%s" % final_ckpt)
# Do Eval
logging.info('Starting Eval..')
eval_examples = processor.get_dev_examples(DATA_DIR)
num_actual_eval_examples = len(eval_examples)
eval_file = os.path.join(OUTPUT_DIR, "eval.tf_record")
run_classifier.file_based_convert_examples_to_features(
eval_examples, label_list, MAX_SEQ_LENGTH, tokenizer, eval_file)
tf.logging.info("***** Running evaluation *****")
tf.logging.info(" Num examples = %d (%d actual, %d padding)",
len(eval_examples), num_actual_eval_examples,
len(eval_examples) - num_actual_eval_examples)
tf.logging.info(" Batch size = %d", TRAIN_BATCH_SIZE)
eval_steps = None
eval_input_fn = run_classifier.file_based_input_fn_builder(
input_file=eval_file,
seq_length=MAX_SEQ_LENGTH,
is_training=False,
drop_remainder=False)
result = estimator.evaluate(input_fn=eval_input_fn, steps=eval_steps)
output_eval_file = os.path.join(OUTPUT_DIR, "eval_results.txt")
with tf.gfile.GFile(output_eval_file, "w") as writer:
tf.logging.info("***** Eval results *****")
for key in sorted(result.keys()):
tf.logging.info(" %s = %s", key, str(result[key]))
writer.write("%s = %s\n" % (key, str(result[key])))
return result
def test_model(self, local_dir,
nb_epoch,
batch_size,
bucket_name):
"""
Use the BERT Uncased language model to train on
new data
"""
tf.logging.set_verbosity(tf.logging.INFO)
logging.info("*:BERT MODEL PATH:%s",BERT_MODEL_PATH)
logging.info("*:Local Dir%s",local_dir)
mod_name = self.model_name
BERT_MODEL = 'uncased_L-12_H-768_A-12'
BERT_PRETRAINED_DIR = BERT_MODEL_PATH
OUTPUT_DIR = os.path.join(local_dir,'output_bert')
DATA_DIR = os.path.join(local_dir,'data')
logging.info('***** Model output directory: %s*****',OUTPUT_DIR)
logging.info('***** BERT pretrained directory: %s *****',BERT_PRETRAINED_DIR)
logging.info('***** DATA directory: %s *****',DATA_DIR)
TRAIN_BATCH_SIZE = 32
EVAL_BATCH_SIZE = 8
PREDICT_BATCH_SIZE = 32
LEARNING_RATE = 2e-5
NUM_TRAIN_EPOCHS = 3.0
WARMUP_PROPORTION = 0.1
MAX_SEQ_LENGTH = 128
# Model configs
# if you wish to finetune a model on a larger dataset, use larger interval
SAVE_CHECKPOINTS_STEPS = 1000
# each checpoint weights about 1,5gb
ITERATIONS_PER_LOOP = 1000
NUM_TPU_CORES = 8
VOCAB_FILE = os.path.join(BERT_PRETRAINED_DIR,'vocab.txt')
BERT_CONFIG_FILE = os.path.join(BERT_PRETRAINED_DIR,'bert_config.json')
with open(os.path.join(OUTPUT_DIR,'final_ckpt.txt')) as f:
content = f.readlines()
logging.info("***Final_cktp->%s\n",content)
test_ckpt = content[0].split('/')[-1]
INIT_CHECKPOINT = os.path.join(OUTPUT_DIR, test_ckpt)
DO_LOWER_CASE = BERT_MODEL.startswith('uncased')
logging.info("Found VOCAB File:%s",VOCAB_FILE)
bert_config = modeling.BertConfig.from_json_file(BERT_CONFIG_FILE)
tf.gfile.MakeDirs(OUTPUT_DIR)
processor = run_classifier.ColaProcessor()
label_list = processor.get_labels()
tokenizer = tokenization.FullTokenizer(
vocab_file=VOCAB_FILE, do_lower_case=DO_LOWER_CASE)
# Since training will happen on GPU, we won't need a cluster resolver
tpu_cluster_resolver = None
# TPUEstimator also supports training on CPU and GPU. You don't need to define a separate tf.estimator.Estimator.
run_config = tf.contrib.tpu.RunConfig(
cluster=tpu_cluster_resolver,
model_dir=OUTPUT_DIR,
save_checkpoints_steps=SAVE_CHECKPOINTS_STEPS,
tpu_config=tf.contrib.tpu.TPUConfig(
iterations_per_loop=ITERATIONS_PER_LOOP,
num_shards=NUM_TPU_CORES,
per_host_input_for_training=tf.contrib.tpu.InputPipelineConfig.PER_HOST_V2))
train_examples = None
num_train_steps = None
num_warmup_steps = None
model_fn = run_classifier.model_fn_builder(
bert_config=bert_config,
num_labels=len(label_list),
init_checkpoint=INIT_CHECKPOINT,
learning_rate=LEARNING_RATE,
num_train_steps=num_train_steps,
num_warmup_steps=num_warmup_steps,
use_tpu=False, # If False training will fall on CPU or GPU, depending on what is available
use_one_hot_embeddings=False) #Try with True
estimator = tf.contrib.tpu.TPUEstimator(
use_tpu=False, # If False training will fall on CPU or GPU, depending on what is available
model_fn=model_fn,
config=run_config,
train_batch_size=TRAIN_BATCH_SIZE,
eval_batch_size=EVAL_BATCH_SIZE,
predict_batch_size=PREDICT_BATCH_SIZE)
predict_examples = processor.get_test_examples(DATA_DIR)
num_actual_predict_examples = len(predict_examples)
predict_file = os.path.join(OUTPUT_DIR, "predict.tf_record")
run_classifier.file_based_convert_examples_to_features(predict_examples, label_list,
MAX_SEQ_LENGTH, tokenizer,
predict_file)
tf.logging.info("***** Running prediction*****")
tf.logging.info(" Num examples = %d (%d actual, %d padding)",
len(predict_examples), num_actual_predict_examples,
len(predict_examples) - num_actual_predict_examples)
tf.logging.info(" Batch size = %d", batch_size)
predict_input_fn = run_classifier.file_based_input_fn_builder(
input_file=predict_file,
seq_length=MAX_SEQ_LENGTH,
is_training=False,
drop_remainder=False)
result = estimator.predict(input_fn=predict_input_fn)
output_predict_file = os.path.join(OUTPUT_DIR, "test_results.tsv")
with tf.gfile.GFile(output_predict_file, "w") as writer:
num_written_lines = 0
tf.logging.info("***** Predict results *****")
for (i, prediction) in enumerate(result):
probabilities = prediction["probabilities"]
if i >= num_actual_predict_examples:
break
output_line = "\t".join(
str(class_probability)
for class_probability in probabilities) + "\n"
writer.write(output_line)
num_written_lines += 1
assert num_written_lines == num_actual_predict_examples
s3 = boto3.resource('s3')
tf.logging.info("Done with prediction uploading results to S3")
try:
s3.Bucket(bucket_name).upload_file(output_predict_file, output_predict_file)
except Exception as err:
logging.info("Unable to upload to S3")
logging.info(err)
return 1
import json
import pandas as pd
tokenization = run_classifier.tokenization
model_base_path = 'model' #modify accordingly
init_checkpoint = os.path.sep.join([
os.path.dirname(os.path.realpath(__file__)), model_base_path, 'model.ckpt'
])
bert_config_file = os.path.sep.join([
os.path.dirname(os.path.realpath(__file__)), model_base_path,
'bert_config.json'
])
vocab_file = os.path.sep.join([
os.path.dirname(os.path.realpath(__file__)), model_base_path, 'vocab.txt'
])
processor = run_classifier.ColaProcessor()
label_list = processor.get_labels()
emotions_file = os.path.sep.join(
[os.path.dirname(os.path.realpath(__file__)), 'emotions.txt'])
#since the original bert source code combines train, eval and predict in one single configuration,
#we need to feed such data during initialization, can be anything as it is needed for run configuration
BATCH_SIZE = 8
SAVE_SUMMARY_STEPS = 100
SAVE_CHECKPOINTS_STEPS = 500
OUTPUT_DIR = "./output"
#variables that needed to be modified
labels = [str(i) for i in range(28)] #modify based on the labels that you have
MAX_SEQ_LENGTH = 50 #modify based on the seq length
is_lower_case = True #modify based on uncased or cased