使用CNN对网站文本进行分类，基于tensorflow.zip

#! /usr/bin/env python # encoding: utf-8 import tensorflow as tf import numpy as np import os import time import datetime import data_helper import word2vec_helpers from text_cnn import TextCNN from scipy.sparse import csr_matrix import random # Parameters # ======================================================= # Data loading parameters tf.flags.DEFINE_float("dev_sample_percentage", .1, "Percentage of the training data to use for validation") tf.flags.DEFINE_integer("num_labels", 12, "Number of labels for data. (default: 12)") # Model hyperparameters tf.flags.DEFINE_integer("embedding_dim", 128, "Dimensionality of character embedding (default: 128)") tf.flags.DEFINE_string("filter_sizes", "3,4,5", "Comma-spearated filter sizes (default: '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", 0.0, "L2 regularization lambda (default: 0.0)") # Training paramters tf.flags.DEFINE_integer("batch_size", 10, "Batch Size (default: 20)") tf.flags.DEFINE_integer("num_epochs", 200, "Number of training epochs (default: 200)") tf.flags.DEFINE_integer("evaluate_every", 100, "Evalue model on dev set after this many steps (default: 100)") tf.flags.DEFINE_integer("checkpoint_every", 100, "Save model after this many steps (defult: 100)") tf.flags.DEFINE_integer("num_checkpoints", 5, "Number of checkpoints to store (default: 5)") # 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") # Parse parameters from commands FLAGS = tf.flags.FLAGS FLAGS._parse_flags() print("\nParameters:") for attr, value in sorted(FLAGS.__flags.items()): print("{}={}".format(attr.upper(), value)) print("") # Prepare 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)) if not os.path.exists(out_dir): os.makedirs(out_dir) # Data preprocess # ======================================================= # Load data print("Loading data...") x_text, y = data_helper.load_data_and_label('input_data/') print "x_text length: ", len(x_text) print "y length: ", y.shape #shuffle x_text and y #np.random.seed(10) #x_test = np.random.permutation(x_text) #y = np.radom.permutation(y) #x_text = x_text[0:1000] #y = y[0:1000] #random select a part of the original data new_x_text = [] new_y = [] for i in range(3000): rand_idx = random.randint(0, len(x_text)) #rand_y = random.randint(0, len(x_text)) new_x_text.append(x_text[rand_idx]) new_y.append(y[rand_idx]) print "new_x_text length: %d" % len(new_x_text) print "new_y length: %d" % len(new_y) # embedding vector print("Padding sentences...") sentences, max_document_length = data_helper.padding_sentences(new_x_text, '<PADDING>') #max_document_length = print("embedding_sentences...") all_vectors = word2vec_helpers.embedding_sentences(sentences, embedding_size = FLAGS.embedding_dim, file_to_save = os.path.join(out_dir, 'trained_word2vec.model')) print "all_vectors length %d * %d * %d : " % (len(all_vectors) , len(all_vectors[0]) , len(all_vectors[0][0])) #x = np.array(all_vectors) ## this operation could lead to memory error!!! #TODO: transform large vectors into sparse matrix x = np.asarray(all_vectors) y = np.asarray(new_y) print("x.shape = {}".format(x.shape)) print("y.shape = {}".format(y.shape)) # Save params training_params_file = os.path.join(out_dir, 'training_params.pickle') params = {'num_labels' : FLAGS.num_labels, 'max_document_length' : max_document_length} data_helper.saveDict(params, training_params_file) # Shuffle data randomly 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:] print("Train/Dev split: {:d}/{:d}".format(len(y_train), len(y_dev))) # Training # ======================================================= 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[1], num_classes = y_train.shape[1], embedding_size = FLAGS.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) optimizer = tf.train.AdamOptimizer(1e-3) grads_and_vars = optimizer.compute_gradients(cnn.loss) train_op = optimizer.apply_gradients(grads_and_vars, global_step=global_step) # Keep track of gradient values and sparsity (optional) grad_summaries = [] for g, v in grads_and_vars: if g is not None: grad_hist_summary = tf.summary.histogram("{}/grad/hist".format(v.name), g) sparsity_summary = tf.summary.scalar("{}/grad/sparsity".format(v.name), tf.nn.zero_fraction(g)) grad_summaries.append(grad_hist_summary) grad_summaries.append(sparsity_summary) grad_summaries_merged = tf.summary.merge(grad_summaries) # Output directory for models and summaries 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, grad_summaries_merged]) 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) # Initialize all variables sess.run(tf.global_variables_initializer()) def train_step(x_batch, y_batch): """ A single training step """ feed_dict = { cnn.input_x: x_batch, 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) time_str = datetime.datetime.now().isoformat() print("{}: step {}, loss {:g}, acc {:g}".format(time_str, step, loss, accuracy)) train_summary_writer.add_summary(summaries, step) def dev_step(x_batch, y_batch, writer=None): """ Evaluates