本文整理汇总了Python中data_helpers.load_data_and_labels方法的典型用法代码示例。如果您正苦于以下问题：Python data_helpers.load_data_and_labels方法的具体用法？Python data_helpers.load_data_and_labels怎么用？Python data_helpers.load_data_and_labels使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类data_helpers的用法示例。
在下文中一共展示了data_helpers.load_data_and_labels方法的2个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: preprocess
# 需要导入模块: import data_helpers [as 别名]
# 或者: from data_helpers import load_data_and_labels [as 别名]
def preprocess():
# Data Preparation
# ==================================================
# Load data
print("Loading data...")
x_text, y = data_helpers.load_data_and_labels(FLAGS.positive_data_file, FLAGS.negative_data_file)
# Build vocabulary
max_document_length = max([len(x.split(" ")) for x in x_text])
vocab_processor = learn.preprocessing.VocabularyProcessor(max_document_length)
x = np.array(list(vocab_processor.fit_transform(x_text)))
# Randomly shuffle data
np.random.seed(10)
shuffle_indices = np.random.permutation(np.arange(len(y)))
x_shuffled = x[shuffle_indices]
y_shuffled = y[shuffle_indices]
# Split train/test set
# TODO: This is very crude, should use cross-validation
dev_sample_index = -1 * int(FLAGS.dev_sample_percentage * float(len(y)))
x_train, x_dev = x_shuffled[:dev_sample_index], x_shuffled[dev_sample_index:]
y_train, y_dev = y_shuffled[:dev_sample_index], y_shuffled[dev_sample_index:]
del x, y, x_shuffled, y_shuffled
print("Vocabulary Size: {:d}".format(len(vocab_processor.vocabulary_)))
print("Train/Dev split: {:d}/{:d}".format(len(y_train), len(y_dev)))
return x_train, y_train, vocab_processor, x_dev, y_dev 示例2: eval
# 需要导入模块: import data_helpers [as 别名]
# 或者: from data_helpers import load_data_and_labels [as 别名]
def eval():
with tf.device('/cpu:0'):
x_text, y = data_helpers.load_data_and_labels(FLAGS.pos_dir, FLAGS.neg_dir)
# Map data into vocabulary
text_path = os.path.join(FLAGS.checkpoint_dir, "..", "text_vocab")
text_vocab_processor = tf.contrib.learn.preprocessing.VocabularyProcessor.restore(text_path)
x_eval = np.array(list(text_vocab_processor.transform(x_text)))
y_eval = np.argmax(y, axis=1)
checkpoint_file = tf.train.latest_checkpoint(FLAGS.checkpoint_dir)
graph = tf.Graph()
with graph.as_default():
session_conf = tf.ConfigProto(
allow_soft_placement=FLAGS.allow_soft_placement,
log_device_placement=FLAGS.log_device_placement)
sess = tf.Session(config=session_conf)
with sess.as_default():
# Load the saved meta graph and restore variables
saver = tf.train.import_meta_graph("{}.meta".format(checkpoint_file))
saver.restore(sess, checkpoint_file)
# Get the placeholders from the graph by name
input_text = graph.get_operation_by_name("input_text").outputs[0]
# input_y = graph.get_operation_by_name("input_y").outputs[0]
dropout_keep_prob = graph.get_operation_by_name("dropout_keep_prob").outputs[0]
# Tensors we want to evaluate
predictions = graph.get_operation_by_name("output/predictions").outputs[0]
# Generate batches for one epoch
batches = data_helpers.batch_iter(list(x_eval), FLAGS.batch_size, 1, shuffle=False)
# Collect the predictions here
all_predictions = []
for x_batch in batches:
batch_predictions = sess.run(predictions, {input_text: x_batch,
dropout_keep_prob: 1.0})
all_predictions = np.concatenate([all_predictions, batch_predictions])
correct_predictions = float(sum(all_predictions == y_eval))
print("Total number of test examples: {}".format(len(y_eval)))
print("Accuracy: {:g}".format(correct_predictions / float(len(y_eval))))