Im currently working on google bert classifier extracted from here:
and Im using it to classify Stack Overflow questions and tags
https://storage.googleapis.com/tensorflow-workshop-examples/stack-overflow-data.csv
I get very bad prediction and poor accuracy and Im wondering which parameters should I fine tune in order to get better results.
I attached all of code
The main file that I run, contains the parameters +run_bert()
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import collections
import csv
import os
import src_bert.modeling as modeling
import src_bert.tokenization as tokenization
import tensorflow as tf
import numpy as np
from sklearn.model_selection import train_test_split
from src_bert.bert_model import *
DO_LOWER_CASE = False
BERT_INIT_CHKPNT = "./src_bert/cased_L-12_H-768_A-12/bert_model.ckpt"
BERT_CONFIG = './src_bert/cased_L-12_H-768_A-12/bert_config.json'
BERT_VOCAB = "./src_bert/cased_L-12_H-768_A-12/vocab.txt"
MAX_SEQ_LENGTH = 128
OUTPUT_DIR = "./working/output"
TRAIN_BATCH_SIZE = 32
PREDICT_BATCH_SIZE = EVAL_BATCH_SIZE = 8
LEARNING_RATE = 2e-5
NUM_TRAIN_EPOCHS = 1.0
# Warmup is a period of time where hte learning rate
# is small and gradually increases--usually helps training.
WARMUP_PROPORTION = 0.1
# Model configs
SAVE_CHECKPOINTS_STEPS = 10000
SAVE_SUMMARY_STEPS = 500
TRAIN_VAL_RATIO = 0.9
def run_bert(x_train_val, x_test, y_train_val, y_test, label_list):
tf.logging.set_verbosity(tf.logging.INFO)
os.makedirs(OUTPUT_DIR, exist_ok=True)
LEN = x_train_val.shape[0]
SIZE_TRAIN = int(TRAIN_VAL_RATIO * LEN)
x_val = x_train_val[SIZE_TRAIN:]
y_val = y_train_val[SIZE_TRAIN:]
x_train = x_train_val[:SIZE_TRAIN]
y_train = y_train_val[:SIZE_TRAIN]
tokenization.validate_case_matches_checkpoint(DO_LOWER_CASE,
BERT_INIT_CHKPNT)
bert_config = modeling.BertConfig.from_json_file(BERT_CONFIG)
if MAX_SEQ_LENGTH > bert_config.max_position_embeddings:
raise ValueError(
"Cannot use sequence length %d because the BERT model "
"was only trained up to sequence length %d" %
(MAX_SEQ_LENGTH, bert_config.max_position_embeddings))
tf.gfile.MakeDirs(OUTPUT_DIR)
tokenizer = tokenization.FullTokenizer(
vocab_file=BERT_VOCAB, do_lower_case=DO_LOWER_CASE)
run_config = tf.estimator.RunConfig(
model_dir=OUTPUT_DIR,
save_summary_steps=SAVE_SUMMARY_STEPS,
keep_checkpoint_max=1,
save_checkpoints_steps=SAVE_CHECKPOINTS_STEPS)
train_examples = None
num_train_steps = None
num_warmup_steps = None
# Train
train_examples = create_examples(x_train, y_train)
num_train_steps = int(
len(train_examples) / TRAIN_BATCH_SIZE * NUM_TRAIN_EPOCHS)
num_warmup_steps = int(num_train_steps * WARMUP_PROPORTION)
model_fn = model_fn_builder(
bert_config=bert_config,
num_labels=len(label_list),
init_checkpoint=BERT_INIT_CHKPNT,
learning_rate=LEARNING_RATE,
num_train_steps=num_train_steps,
num_warmup_steps=num_warmup_steps,
use_tpu=False,
use_one_hot_embeddings=False)
# If TPU is not available, this will fall back to normal Estimator on CPU
# or GPU.
estimator = tf.estimator.Estimator(
model_fn=model_fn,
config=run_config,
params={"batch_size": TRAIN_BATCH_SIZE})
train_file = os.path.join(OUTPUT_DIR, "train.tf_record")
file_based_convert_examples_to_features(
train_examples, label_list, MAX_SEQ_LENGTH, tokenizer, train_file)
train_input_fn = 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)
#Evalution
eval_examples = create_examples(x_val, y_val)
num_actual_eval_examples = len(eval_examples)
eval_file = os.path.join(OUTPUT_DIR, "eval.tf_record")
file_based_convert_examples_to_features(
eval_examples, label_list, MAX_SEQ_LENGTH, tokenizer, eval_file)
tf.logging.info("***** Running evaluation *****")
# This tells the estimator to run through the entire set.
eval_steps = None
# However, if running eval on the TPU, you will need to specify the
# number of steps.
eval_drop_remainder = False
eval_input_fn = file_based_input_fn_builder(
input_file=eval_file,
seq_length=MAX_SEQ_LENGTH,
is_training=False,
drop_remainder=eval_drop_remainder)
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])))
#Testing
predict_examples = create_examples(x_test, y_test, False)
predict_file = os.path.join(OUTPUT_DIR, "predict.tf_record")
file_based_convert_examples_to_features(predict_examples, label_list,
MAX_SEQ_LENGTH, tokenizer,
predict_file)
tf.logging.info("***** Running prediction*****")
predict_drop_remainder = False
predict_input_fn = file_based_input_fn_builder(
input_file=predict_file,
seq_length=MAX_SEQ_LENGTH,
is_training=False,
drop_remainder=predict_drop_remainder)
result = estimator.predict(input_fn=predict_input_fn)
tf.logging.info("***** Predict results *****")
correct_labeling = []
accuracy = 0
for x, prediction, correct_label in zip(x_test,result,y_test):
probabilities = prediction["probabilities"]
max_index_label = np.argmax(probabilities)
tf.logging.info("{0} orig label {1} predicted {2}".format(x,correct_label, label_list[max_index_label]))
if label_list[max_index_label]==correct_label:
accuracy+=1
correct_labeling.append(label_list[max_index_label]==correct_label)
print("test accuracy is {0}".format(100*(accuracy/len(x_test))))
return correct_labeling
if __name__ == "__main__":
input_csv = pd.read_csv('stack-overflow-data.csv')
input_csv = input_csv.dropna()
tweets = input_csv['post']
labels = []
print("loading DB")
map_index_to_label = list(set(input_csv['tags']))
map_label_to_index = {l:i for i,l in enumerate(map_index_to_label)}
for label in input_csv['tags']:
labels.append(map_label_to_index[label])
num_labels = len(map_index_to_label)
print("splitting")
X_train, X_test, y_train, y_test = train_test_split(tweets, labels, test_size=0.33, random_state=42)
bert_test_res = run_bert(X_train, X_test, y_train, y_test, list(set(labels)))
and helper bert model code, code which taken from google bert:
from **future** import absolute_import
from **future** import division
from **future** import print_function
import collections
import csv
import os
import src_bert.modeling as modeling
import src_bert.optimization as optimization
import src_bert.tokenization as tokenization
import tensorflow as tf
import pandas as pd
from sklearn.model_selection import train_test_split
class InputExample(object):
"""A single training/test example for simple sequence classification."""
def __init__(self, text_a, text_b=None, label=None):
"""Constructs a InputExample.
Args:
guid: Unique id for the example.
text_a: string. The untokenized text of the first sequence. For single
sequence tasks, only this sequence must be specified.
text_b: (Optional) string. The untokenized text of the second sequence.
Only must be specified for sequence pair tasks.
label: (Optional) string. The label of the example. This should be
specified for train and dev examples, but not for test examples.
"""
self.text_a = text_a
self.text_b = text_b
self.label = label
def create_examples(x_values, y_values, labels_available=True):
"""Creates examples for the training and dev sets."""
examples = []
for x, y in zip(x_values,y_values):
if labels_available:
label = y
else:
label = None
examples.append(
InputExample(text_a=x, label=label))
return examples
class PaddingInputExample(object):
"""Fake example so the num input examples is a multiple of the batch size.
When running eval/predict on the TPU, we need to pad the number of examples
to be a multiple of the batch size, because the TPU requires a fixed batch
size. The alternative is to drop the last batch, which is bad because it means
the entire output data won't be generated.
We use this class instead of `None` because treating `None` as padding
battches could cause silent errors.
"""
class InputFeatures(object):
"""A single set of features of data."""
def __init__(self,
input_ids,
input_mask,
segment_ids,
label_id,
is_real_example=True):
self.input_ids = input_ids
self.input_mask = input_mask
self.segment_ids = segment_ids
self.label_id = label_id
self.is_real_example = is_real_example
def convert_single_example(ex_index, example, label_list, max_seq_length,
tokenizer):
"""Converts a single `InputExample` into a single `InputFeatures`."""
if isinstance(example, PaddingInputExample):
return InputFeatures(
input_ids=[0] * max_seq_length,
input_mask=[0] * max_seq_length,
segment_ids=[0] * max_seq_length,
label_id=0,
is_real_example=False)
label_map = {}
for (i, label) in enumerate(label_list):
label_map[label] = i+1
tokens_a = tokenizer.tokenize(example.text_a)
tokens_b = None
if example.text_b:
tokens_b = tokenizer.tokenize(example.text_b)
if tokens_b:
# Modifies `tokens_a` and `tokens_b` in place so that the total
# length is less than the specified length.
# Account for [CLS], [SEP], [SEP] with "- 3"
_truncate_seq_pair(tokens_a, tokens_b, max_seq_length - 3)
else:
# Account for [CLS] and [SEP] with "- 2"
if len(tokens_a) > max_seq_length - 2:
tokens_a = tokens_a[0:(max_seq_length - 2)]
# The convention in BERT is:
# (a) For sequence pairs:
# tokens: [CLS] is this jack ##son ##ville ? [SEP] no it is not . [SEP]
# type_ids: 0 0 0 0 0 0 0 0 1 1 1 1 1 1
# (b) For single sequences:
# tokens: [CLS] the dog is hairy . [SEP]
# type_ids: 0 0 0 0 0 0 0
#
# Where "type_ids" are used to indicate whether this is the first
# sequence or the second sequence. The embedding vectors for `type=0` and
# `type=1` were learned during pre-training and are added to the wordpiece
# embedding vector (and position vector). This is not *strictly* necessary
# since the [SEP] token unambiguously separates the sequences, but it makes
# it easier for the model to learn the concept of sequences.
#
# For classification tasks, the first vector (corresponding to [CLS]) is
# used as the "sentence vector". Note that this only makes sense because
# the entire model is fine-tuned.
tokens = []
segment_ids = []
tokens.append("[CLS]")
segment_ids.append(0)
for token in tokens_a:
tokens.append(token)
segment_ids.append(0)
tokens.append("[SEP]")
segment_ids.append(0)
if tokens_b:
for token in tokens_b:
tokens.append(token)
segment_ids.append(1)
tokens.append("[SEP]")
segment_ids.append(1)
input_ids = tokenizer.convert_tokens_to_ids(tokens)
# The mask has 1 for real tokens and 0 for padding tokens. Only real
# tokens are attended to.
input_mask = [1] * len(input_ids)
# Zero-pad up to the sequence length.
while len(input_ids) < max_seq_length:
input_ids.append(0)
input_mask.append(0)
segment_ids.append(0)
assert len(input_ids) == max_seq_length
assert len(input_mask) == max_seq_length
assert len(segment_ids) == max_seq_length
if example.label != None:
label_id = label_map[example.label]
else:
label_id = 0
if ex_index < 5:
tf.logging.info("*** Example ***")
tf.logging.info("tokens: %s" % " ".join(
[tokenization.printable_text(x) for x in tokens]))
tf.logging.info("input_ids: %s" % " ".join([str(x) for x in input_ids]))
tf.logging.info("input_mask: %s" % " ".join([str(x) for x in input_mask]))
tf.logging.info("segment_ids: %s" % " ".join([str(x) for x in segment_ids]))
tf.logging.info("label: %s (id = %d)" % (example.label, label_id))
feature = InputFeatures(
input_ids=input_ids,
input_mask=input_mask,
segment_ids=segment_ids,
label_id=label_id,
is_real_example=True)
return feature
def file_based_convert_examples_to_features(
examples, label_list, max_seq_length, tokenizer, output_file):
"""Convert a set of `InputExample`s to a TFRecord file."""
writer = tf.python_io.TFRecordWriter(output_file)
for (ex_index, example) in enumerate(examples):
if ex_index % 10000 == 0:
tf.logging.info("Writing example %d of %d" % (ex_index, len(examples)))
feature = convert_single_example(ex_index, example, label_list,
max_seq_length, tokenizer)
def create_int_feature(values):
f = tf.train.Feature(int64_list=tf.train.Int64List(value=list(values)))
return f
features = collections.OrderedDict()
features["input_ids"] = create_int_feature(feature.input_ids)
features["input_mask"] = create_int_feature(feature.input_mask)
features["segment_ids"] = create_int_feature(feature.segment_ids)
features["label_ids"] = create_int_feature([feature.label_id])
features["is_real_example"] = create_int_feature(
[int(feature.is_real_example)])
tf_example = tf.train.Example(features=tf.train.Features(feature=features))
writer.write(tf_example.SerializeToString())
writer.close()
def file_based_input_fn_builder(input_file, seq_length, is_training,
drop_remainder):
"""Creates an `input_fn` closure to be passed to TPUEstimator."""
name_to_features = {
"input_ids": tf.FixedLenFeature([seq_length], tf.int64),
"input_mask": tf.FixedLenFeature([seq_length], tf.int64),
"segment_ids": tf.FixedLenFeature([seq_length], tf.int64),
"label_ids": tf.FixedLenFeature([], tf.int64),
"is_real_example": tf.FixedLenFeature([], tf.int64),
}
def _decode_record(record, name_to_features):
"""Decodes a record to a TensorFlow example."""
example = tf.parse_single_example(record, name_to_features)
# tf.Example only supports tf.int64, but the TPU only supports tf.int32.
# So cast all int64 to int32.
for name in list(example.keys()):
t = example[name]
if t.dtype == tf.int64:
t = tf.to_int32(t)
example[name] = t
return example
def input_fn(params):
"""The actual input function."""
batch_size = params["batch_size"]
# For training, we want a lot of parallel reading and shuffling.
# For eval, we want no shuffling and parallel reading doesn't matter.
d = tf.data.TFRecordDataset(input_file)
if is_training:
d = d.repeat()
d = d.shuffle(buffer_size=100)
d = d.apply(
tf.contrib.data.map_and_batch(
lambda record: _decode_record(record, name_to_features),
batch_size=batch_size,
drop_remainder=drop_remainder))
return d
return input_fn
def _truncate_seq_pair(tokens_a, tokens_b, max_length):
"""Truncates a sequence pair in place to the maximum length."""
# This is a simple heuristic which will always truncate the longer sequence
# one token at a time. This makes more sense than truncating an equal percent
# of tokens from each, since if one sequence is very short then each token
# that's truncated likely contains more information than a longer sequence.
while True:
total_length = len(tokens_a) + len(tokens_b)
if total_length <= max_length:
break
if len(tokens_a) > len(tokens_b):
tokens_a.pop()
else:
tokens_b.pop()
def create_model(bert_config, is_training, input_ids, input_mask, segment_ids,
labels, num_labels, use_one_hot_embeddings):
"""Creates a classification model."""
model = modeling.BertModel(
config=bert_config,
is_training=is_training,
input_ids=input_ids,
input_mask=input_mask,
token_type_ids=segment_ids,
use_one_hot_embeddings=use_one_hot_embeddings)
# In the demo, we are doing a simple classification task on the entire
# segment.
#
# If you want to use the token-level output, use model.get_sequence_output()
# instead.
output_layer = model.get_pooled_output()
hidden_size = output_layer.shape[-1].value
output_weights = tf.get_variable(
"output_weights", [num_labels, hidden_size],
initializer=tf.truncated_normal_initializer(stddev=0.02))
output_bias = tf.get_variable(
"output_bias", [num_labels], initializer=tf.zeros_initializer())
with tf.variable_scope("loss"):
if is_training:
# I.e., 0.1 dropout
output_layer = tf.nn.dropout(output_layer, keep_prob=0.9)
logits = tf.matmul(output_layer, output_weights, transpose_b=True)
logits = tf.nn.bias_add(logits, output_bias)
probabilities = tf.nn.softmax(logits, axis=-1)
log_probs = tf.nn.log_softmax(logits, axis=-1)
one_hot_labels = tf.one_hot(labels, depth=num_labels, dtype=tf.float32)
per_example_loss = -tf.reduce_sum(one_hot_labels * log_probs, axis=-1)
loss = tf.reduce_mean(per_example_loss)
return (loss, per_example_loss, logits, probabilities)
def model_fn_builder(bert_config, num_labels, init_checkpoint, learning_rate,
num_train_steps, num_warmup_steps, use_tpu,
use_one_hot_embeddings):
"""Returns `model_fn` closure for TPUEstimator."""
def model_fn(features, labels, mode, params): # pylint: disable=unused-argument
"""The `model_fn` for TPUEstimator."""
# tf.logging.info("*** Features ***")
# for name in sorted(features.keys()):
# tf.logging.info(" name = %s, shape = %s" % (name, features[name].shape))
input_ids = features["input_ids"]
input_mask = features["input_mask"]
segment_ids = features["segment_ids"]
label_ids = features["label_ids"]
is_real_example = None
if "is_real_example" in features:
is_real_example = tf.cast(features["is_real_example"], dtype=tf.float32)
else:
is_real_example = tf.ones(tf.shape(label_ids), dtype=tf.float32)
is_training = (mode == tf.estimator.ModeKeys.TRAIN)
(total_loss, per_example_loss, logits, probabilities) = create_model(
bert_config, is_training, input_ids, input_mask, segment_ids, label_ids,
num_labels, use_one_hot_embeddings)
tvars = tf.trainable_variables()
initialized_variable_names = {}
scaffold_fn = None
if init_checkpoint:
(assignment_map, initialized_variable_names
) = modeling.get_assignment_map_from_checkpoint(tvars, init_checkpoint)
if use_tpu:
def tpu_scaffold():
tf.train.init_from_checkpoint(init_checkpoint, assignment_map)
return tf.train.Scaffold()
scaffold_fn = tpu_scaffold
else:
tf.train.init_from_checkpoint(init_checkpoint, assignment_map)
tf.logging.info("**** Trainable Variables ****")
for var in tvars:
init_string = ""
if var.name in initialized_variable_names:
init_string = ", *INIT_FROM_CKPT*"
tf.logging.info(" name = %s, shape = %s%s", var.name, var.shape,
init_string)
output_spec = None
if mode == tf.estimator.ModeKeys.TRAIN:
train_op = optimization.create_optimizer(
total_loss, learning_rate, num_train_steps, num_warmup_steps, use_tpu)
output_spec = tf.estimator.EstimatorSpec(
mode=mode,
loss=total_loss,
train_op=train_op,
scaffold=scaffold_fn)
elif mode == tf.estimator.ModeKeys.EVAL:
def metric_fn(per_example_loss, label_ids, logits, is_real_example):
predictions = tf.argmax(logits, axis=-1, output_type=tf.int32)
accuracy = tf.metrics.accuracy(
labels=label_ids, predictions=predictions, weights=is_real_example)
loss = tf.metrics.mean(values=per_example_loss, weights=is_real_example)
return {
"eval_accuracy": accuracy,
"eval_loss": loss
}
eval_metrics = metric_fn(per_example_loss, label_ids, logits, is_real_example)
output_spec = tf.estimator.EstimatorSpec(
mode=mode,
loss=total_loss,
eval_metric_ops=eval_metrics,
scaffold=scaffold_fn)
else:
output_spec = tf.estimator.EstimatorSpec(
mode=mode,
predictions={"probabilities": probabilities},
scaffold=scaffold_fn)
return output_spec
return model_fn
other files are taken straight from:
Thanks.