Python data_helpers.load_data_and_labels() Examples

The following are 3 code examples of data_helpers.load_data_and_labels(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module data_helpers , or try the search function .
Example #1
Source File: train.py    From AI_for_Resumes with Apache License 2.0 5 votes vote down vote up 
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
Example #2
Source File: train.py    From cnn-text-classification-tf with Apache License 2.0 5 votes vote down vote up 
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
Example #3
Source File: eval.py    From rnn-text-classification-tf with MIT License 4 votes vote down vote up 
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))))