cnn_relation_extraction部分記錄

import tensorflow as tf
import numpy as np
import os
import datetime
import time
from cnn_relation_extraction_master.text_cnn import TextCNN
from cnn_relation_extraction_master.data_helpers import *
from sklearn.metrics import f1_score
import warnings
import sklearn.exceptions
warnings.filterwarnings("ignore", category=sklearn.exceptions.UndefinedMetricWarning)

# Parameters
# ==================================================

# Data loading params 語料路徑
tf.flags.DEFINE_string("train_dir", "SemEval2010_task8_all_data/SemEval2010_task8_training/TRAIN_FILE.TXT", "Path of train data")
tf.flags.DEFINE_float("dev_sample_percentage", .1, "Percentage of the training data to use for validation")
tf.flags.DEFINE_integer("max_sentence_length", 100, "Max sentence length in train(98)/test(70) data (Default: 100)")
# 第一個是引數名稱，第二個是預設值，第三個是引數描述
# Model Hyperparameters 網路引數
tf.flags.DEFINE_string("word2vec", r"D:\file_download\BaiduNetdiskDownload\PyCharm_File\wiki_en_word2vec-master\wiki.en.text.vector", "Word2vec file with pre-trained embeddings")
tf.flags.DEFINE_integer("text_embedding_dim", 400, "Dimensionality of word embedding (Default: 300)")
tf.flags.DEFINE_integer("position_embedding_dim", 100, "Dimensionality of position embedding (Default: 100)")
tf.flags.DEFINE_string("filter_sizes", "2,3,4,5", "Comma-separated filter sizes (Default: 2,3,4,5)")
tf.flags.DEFINE_integer("num_filters", 128, "Number of filters per filter size (Default: 128)")
tf.flags.DEFINE_float("dropout_keep_prob", 0.5, "Dropout keep probability (Default: 0.5)")
tf.flags.DEFINE_float("l2_reg_lambda", 3.0, "L2 regularization lambda (Default: 3.0)")

# Training parameters
tf.flags.DEFINE_integer("batch_size", 64, "Batch Size (Default: 64)")
tf.flags.DEFINE_integer("num_epochs", 100, "Number of training epochs (Default: 100)")
tf.flags.DEFINE_integer("display_every", 10, "Number of iterations to display training info.")
tf.flags.DEFINE_integer("evaluate_every", 100, "Evaluate model on dev set after this many steps")
tf.flags.DEFINE_integer("checkpoint_every", 100, "Save model after this many steps")
tf.flags.DEFINE_integer("num_checkpoints", 5, "Number of checkpoints to store")
tf.flags.DEFINE_float("learning_rate", 1e-3, "Which learning rate to start with. (Default: 1e-3)")

# Misc Parameters
tf.flags.DEFINE_boolean("allow_soft_placement", True, "Allow device soft device placement")
tf.flags.DEFINE_boolean("log_device_placement", False, "Log placement of ops on devices")


FLAGS = tf.flags.FLAGS  # FLAGS儲存命令列引數的資料
FLAGS._parse_flags()  # 將其解析成字典儲存到FLAGS.__flags中
print("\nParameters:")
for attr, value in sorted(FLAGS.__flags.items()):
    print("{} = {}".format(attr.upper(), value))
print("")


def train():
    with tf.device('/cpu:0'):
        x_text, pos1, pos2, y = load_data_and_labels(FLAGS.train_dir)  # 將語料進行處理並轉為df,label轉為one-hot

    # Build vocabulary
    # Example: x_text[3] = "A misty <e1>ridge</e1> uprises from the <e2>surge</e2>."
    # ['a misty ridge uprises from the surge <UNK> <UNK> ... <UNK>']
    # =>
    # [27 39 40 41 42  1 43  0  0 ... 0]
    # dimension = FLAGS.max_sentence_length
    text_vocab_processor = tf.contrib.learn.preprocessing.VocabularyProcessor(FLAGS.max_sentence_length)
    text_vec = np.array(list(text_vocab_processor.fit_transform(x_text)))
    print("Text Vocabulary Size: {:d}".format(len(text_vocab_processor.vocabulary_)))

    # Example: pos1[3] = [-2 -1  0  1  2   3   4 999 999 999 ... 999]
    # [95 96 97 98 99 100 101 999 999 999 ... 999]
    # =>
    # [11 12 13 14 15  16  21  17  17  17 ...  17]
    # dimension = MAX_SENTENCE_LENGTH
    pos_vocab_processor = tf.contrib.learn.preprocessing.VocabularyProcessor(FLAGS.max_sentence_length)
    pos_vocab_processor.fit(pos1 + pos2)
    pos1_vec = np.array(list(pos_vocab_processor.transform(pos1)))
    pos2_vec = np.array(list(pos_vocab_processor.transform(pos2)))
    print("Position Vocabulary Size: {:d}".format(len(pos_vocab_processor.vocabulary_)))

    x = np.array([list(i) for i in zip(text_vec, pos1_vec, pos2_vec)])

    print("x = {0}".format(x.shape))
    print("y = {0}".format(y.shape))
    print("")
    # 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:]
    x_dev = np.array(x_dev).transpose((1, 0, 2))
    y_train, y_dev = y_shuffled[:dev_sample_index], y_shuffled[dev_sample_index:]
    print("Train/Dev split: {:d}/{:d}\n".format(len(y_train), len(y_dev)))

    with tf.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():
            cnn = TextCNN(
                sequence_length=x_train.shape[2],
                num_classes=y_train.shape[1],
                text_vocab_size=len(text_vocab_processor.vocabulary_),
                text_embedding_size=FLAGS.text_embedding_dim,
                pos_vocab_size=len(pos_vocab_processor.vocabulary_),
                pos_embedding_size=FLAGS.position_embedding_dim,
                filter_sizes=list(map(int, FLAGS.filter_sizes.split(","))),
                num_filters=FLAGS.num_filters,
                l2_reg_lambda=FLAGS.l2_reg_lambda)

            # Define Training procedure
            global_step = tf.Variable(0, name="global_step", trainable=False)
            train_op = tf.train.AdamOptimizer(FLAGS.learning_rate).minimize(cnn.loss, global_step=global_step)

            # Output directory for models and summaries
            timestamp = str(int(time.time()))
            out_dir = os.path.abspath(os.path.join(os.path.curdir, "runs", timestamp))
            print("Writing to {}\n".format(out_dir))

            # Summaries for loss and accuracy
            loss_summary = tf.summary.scalar("loss", cnn.loss)
            acc_summary = tf.summary.scalar("accuracy", cnn.accuracy)

            # Train Summaries
            train_summary_op = tf.summary.merge([loss_summary, acc_summary])
            train_summary_dir = os.path.join(out_dir, "summaries", "train")
            train_summary_writer = tf.summary.FileWriter(train_summary_dir, sess.graph)

            # Dev summaries
            dev_summary_op = tf.summary.merge([loss_summary, acc_summary])
            dev_summary_dir = os.path.join(out_dir, "summaries", "dev")
            dev_summary_writer = tf.summary.FileWriter(dev_summary_dir, sess.graph)

            # Checkpoint directory. Tensorflow assumes this directory already exists so we need to create it
            checkpoint_dir = os.path.abspath(os.path.join(out_dir, "checkpoints"))
            checkpoint_prefix = os.path.join(checkpoint_dir, "model")
            if not os.path.exists(checkpoint_dir):
                os.makedirs(checkpoint_dir)
            saver = tf.train.Saver(tf.global_variables(), max_to_keep=FLAGS.num_checkpoints)

            # Write vocabulary
            text_vocab_processor.save(os.path.join(out_dir, "text_vocab"))
            pos_vocab_processor.save(os.path.join(out_dir, "position_vocab"))

            # Initialize all variables
            sess.run(tf.global_variables_initializer())

            # Pre-trained word2vec
            if FLAGS.word2vec:
                # initial matrix with random uniform
                initW = np.random.uniform(-0.25, 0.25, (len(text_vocab_processor.vocabulary_), FLAGS.text_embedding_dim))
                # load any vectors from the word2vec
                print("Load word2vec file {0}".format(FLAGS.word2vec))
                with open(FLAGS.word2vec, "rb") as f:
                    header = f.readline()
                    vocab_size, layer1_size = map(int, header.split())
                    binary_len = np.dtype('float32').itemsize * layer1_size
                    for line in range(vocab_size):
                        word = []
                        while True:
                            ch = f.read(1).decode('latin-1')
                            if ch == ' ':
                                word = ''.join(word)
                                break
                            if ch != '\n':
                                word.append(ch)
                        idx = text_vocab_processor.vocabulary_.get(word)
                        if idx != 0:
                            initW[idx] = np.fromstring(f.read(binary_len), dtype='float32')
                        else:
                            f.read(binary_len)
                sess.run(cnn.W_text.assign(initW))
                print("Success to load pre-trained word2vec model!\n")

            # Generate batches
            batches = batch_iter(
                list(zip(x_train, y_train)), FLAGS.batch_size, FLAGS.num_epochs)
            # Training loop. For each batch...
            for batch in batches:
                x_batch, y_batch = zip(*batch)
                x_batch = np.array(x_batch).transpose((1, 0, 2))

                # Train
                feed_dict = {
                    cnn.input_text: x_batch[0],
                    cnn.input_pos1: x_batch[1],
                    cnn.input_pos2: x_batch[2],
                    cnn.input_y: y_batch,
                    cnn.dropout_keep_prob: FLAGS.dropout_keep_prob
                }
                _, step, summaries, loss, accuracy = sess.run(
                    [train_op, global_step, train_summary_op, cnn.loss, cnn.accuracy], feed_dict)
                train_summary_writer.add_summary(summaries, step)

                # Training log display
                if step % FLAGS.display_every == 0:
                    time_str = datetime.datetime.now().isoformat()
                    print("{}: step {}, loss {:g}, acc {:g}".format(time_str, step, loss, accuracy))

                # Evaluation
                if step % FLAGS.evaluate_every == 0:
                    print("\nEvaluation:")
                    feed_dict = {
                        cnn.input_text: x_dev[0],
                        cnn.input_pos1: x_dev[1],
                        cnn.input_pos2: x_dev[2],
                        cnn.input_y: y_dev,
                        cnn.dropout_keep_prob: 1.0
                    }
                    summaries, loss, accuracy, predictions = sess.run(
                        [dev_summary_op, cnn.loss, cnn.accuracy, cnn.predictions], feed_dict)
                    dev_summary_writer.add_summary(summaries, step)

                    time_str = datetime.datetime.now().isoformat()
                    print("{}: step {}, loss {:g}, acc {:g}".format(time_str, step, loss, accuracy))
                    print("(2*9+1)-Way Macro-Average F1 Score (excluding Other): {:g}\n".format(
                        f1_score(np.argmax(y_dev, axis=1), predictions, labels=np.array(range(1, 19)), average="macro")))

                # Model checkpoint
                if step % FLAGS.checkpoint_every == 0:
                    path = saver.save(sess, checkpoint_prefix, global_step=step)
                    print("Saved model checkpoint to {}\n".format(path))


def main(_):
    train()


if __name__ == "__main__":
    tf.app.run()
 

import tensorflow as tf


class TextCNN:
    def __init__(self, sequence_length, num_classes,
                 text_vocab_size, text_embedding_size, pos_vocab_size, pos_embedding_size,
                 filter_sizes, num_filters, l2_reg_lambda=0.0):

        # Placeholders for input, output and dropout
        self.input_text = tf.placeholder(tf.int32, shape=[None, sequence_length], name='input_text')
        self.input_pos1 = tf.placeholder(tf.int32, shape=[None, sequence_length], name='input_pos1')
        self.input_pos2 = tf.placeholder(tf.int32, shape=[None, sequence_length], name='input_pos2')
        self.input_y = tf.placeholder(tf.float32, shape=[None, num_classes], name='input_y')
        self.dropout_keep_prob = tf.placeholder(tf.float32, name='dropout_keep_prob')

        # Keeping track of l2 regularization loss (optional)
        l2_loss = tf.constant(0.0)

        # Embedding layer
        with tf.device('/cpu:0'), tf.name_scope("text-embedding"):
            self.W_text = tf.Variable(tf.random_uniform([text_vocab_size, text_embedding_size], -1.0, 1.0), name="W_text")
            self.text_embedded_chars = tf.nn.embedding_lookup(self.W_text, self.input_text)
            self.text_embedded_chars_expanded = tf.expand_dims(self.text_embedded_chars, -1)
        with tf.device('/cpu:0'), tf.name_scope("position-embedding"):
            self.W_position = tf.Variable(tf.random_uniform([pos_vocab_size, pos_embedding_size], -1.0, 1.0), name="W_position")
            self.pos1_embedded_chars = tf.nn.embedding_lookup(self.W_position, self.input_pos1)
            self.pos1_embedded_chars_expanded = tf.expand_dims(self.pos1_embedded_chars, -1)
            self.pos2_embedded_chars = tf.nn.embedding_lookup(self.W_position, self.input_pos2)
            self.pos2_embedded_chars_expanded = tf.expand_dims(self.pos2_embedded_chars, -1)

        self.embedded_chars_expanded = tf.concat([self.text_embedded_chars_expanded,
                                                  self.pos1_embedded_chars_expanded,
                                                  self.pos2_embedded_chars_expanded], 2)

        embedding_size = text_embedding_size + 2*pos_embedding_size

        # Create a convolution + maxpool layer for each filter size
        pooled_outputs = []
        for i, filter_size in enumerate(filter_sizes):
            with tf.name_scope("conv-maxpool-%s" % filter_size):
                # Convolution Layer
                filter_shape = [filter_size, embedding_size, 1, num_filters]
                W = tf.Variable(tf.truncated_normal(filter_shape, stddev=0.1), name="W")
                b = tf.Variable(tf.constant(0.1, shape=[num_filters]), name="b")
                conv = tf.nn.conv2d(self.embedded_chars_expanded, W, strides=[1, 1, 1, 1], padding="VALID", name="conv")
                # Apply nonlinearity
                h = tf.nn.relu(tf.nn.bias_add(conv, b), name="relu")
                # Maxpooling over the outputs
                pooled = tf.nn.max_pool(h, ksize=[1, sequence_length - filter_size + 1, 1, 1], strides=[1, 1, 1, 1], padding='VALID', name="pool")
                pooled_outputs.append(pooled)

        # Combine all the pooled features
        num_filters_total = num_filters * len(filter_sizes)
        self.h_pool = tf.concat(pooled_outputs, 3)
        self.h_pool_flat = tf.reshape(self.h_pool, [-1, num_filters_total])

        # Add dropout
        with tf.name_scope("dropout"):
            self.h_drop = tf.nn.dropout(self.h_pool_flat, self.dropout_keep_prob)

        # Final scores and predictions
        with tf.name_scope("output"):
            W = tf.get_variable("W", shape=[num_filters_total, num_classes], initializer=tf.contrib.layers.xavier_initializer())
            b = tf.Variable(tf.constant(0.1, shape=[num_classes]), name="b")
            l2_loss += tf.nn.l2_loss(W)
            l2_loss += tf.nn.l2_loss(b)
            self.logits = tf.nn.xw_plus_b(self.h_drop, W, b, name="logits")
            self.predictions = tf.argmax(self.logits, 1, name="predictions")

        # Calculate mean cross-entropy loss
        with tf.name_scope("loss"):
            losses = tf.nn.softmax_cross_entropy_with_logits(logits=self.logits, labels=self.input_y)
            self.loss = tf.reduce_mean(losses) + l2_reg_lambda * l2_loss

        # Accuracy
        with tf.name_scope("accuracy"):
            correct_predictions = tf.equal(self.predictions, tf.argmax(self.input_y, 1))
            self.accuracy = tf.reduce_mean(tf.cast(correct_predictions, tf.float32), name="accuracy")
 

-----------------------------------------------------------------------------手動分割線 ----------------------------------------------------------------------------

• tf.flags.DEFINE_xxx() 

用於接受命令列的可選引數。就是說利用該函式我們可以實現在命令列中選擇需要設定的引數來執行程式， 可以不用反覆修改原始碼中的引數，直接在命令列中進行引數的設定。

• FLAGS = tf.flags.FLAGS  # FLAGS儲存命令列引數的資料
• FLAGS._parse_flags()  # 將其解析成字典儲存到FLAGS.__flags中