update cnn cls

Author: haibaoY

Part2_Text_Classify/cnn-text-classification-tf-chinese/data/chinese/get_data.py

@@ -0,0 +1,15 @@
+# encoding:utf-8
+
+import jieba
+import re
+
+data = open('neg.txt', 'r')
+# data3 = data.read()
+data2 = data.readlines()
+print len(data2)
+fw = open('neg2.txt', 'a')
+for line in data2:
+  data = ''.join(re.findall(u'[\u4e00-\u9fff]+', line.decode('utf-8', 'ignore')))
+  str = jieba.cut(data)
+  data3 = " ".join(str).encode('utf-8')
+  fw.write(data3 + '\n')

Part2_Text_Classify/cnn-text-classification-tf-chinese/data/chinese/neg.txt

@@ -0,0 +1,116 @@
+import numpy as np
+import re
+import itertools
+import codecs
+from collections import Counter
+
+
+def clean_str(string):
+  """
+  Tokenization/string cleaning for all datasets except for SST.
+  Original taken from https://github.com/yoonkim/CNN_sentence/blob/master/process_data.py
+  """
+  string = re.sub(r"[^A-Za-z0-9(),!?\'\`]", " ", string)
+  string = re.sub(r"\'s", " \'s", string)
+  string = re.sub(r"\'ve", " \'ve", string)
+  string = re.sub(r"n\'t", " n\'t", string)
+  string = re.sub(r"\'re", " \'re", string)
+  string = re.sub(r"\'d", " \'d", string)
+  string = re.sub(r"\'ll", " \'ll", string)
+  string = re.sub(r",", " , ", string)
+  string = re.sub(r"!", " ! ", string)
+  string = re.sub(r"\(", " \( ", string)
+  string = re.sub(r"\)", " \) ", string)
+  string = re.sub(r"\?", " \? ", string)
+  string = re.sub(r"\s{2,}", " ", string)
+  return string.strip().lower()
+
+
+def load_data_and_labels():
+  """
+  Loads MR polarity data from files, splits the data into words and generates labels.
+  Returns split sentences and labels.
+  """
+  # Load data from files
+  positive_examples = list(codecs.open("./data/chinese/pos.txt", "r", "utf-8").readlines())
+  positive_examples = [s.strip() for s in positive_examples]
+  negative_examples = list(codecs.open("./data/chinese/neg.txt", "r", "utf-8").readlines())
+  negative_examples = [s.strip() for s in negative_examples]
+  # Split by words
+  x_text = positive_examples + negative_examples
+  # x_text = [clean_str(sent) for sent in x_text]
+  x_text = [list(s) for s in x_text]
+
+  # Generate labels
+  positive_labels = [[0, 1] for _ in positive_examples]
+  negative_labels = [[1, 0] for _ in negative_examples]
+  y = np.concatenate([positive_labels, negative_labels], 0)
+  return [x_text, y]
+
+
+def pad_sentences(sentences, padding_word="<PAD/>"):
+  """
+  Pads all sentences to the same length. The length is defined by the longest sentence.
+  Returns padded sentences.
+  """
+  sequence_length = max(len(x) for x in sentences)
+  padded_sentences = []
+  for i in range(len(sentences)):
+    sentence = sentences[i]
+    num_padding = sequence_length - len(sentence)
+    new_sentence = sentence + [padding_word] * num_padding
+    padded_sentences.append(new_sentence)
+  return padded_sentences
+
+
+def build_vocab(sentences):
+  """
+  Builds a vocabulary mapping from word to index based on the sentences.
+  Returns vocabulary mapping and inverse vocabulary mapping.
+  """
+  # Build vocabulary
+  word_counts = Counter(itertools.chain(*sentences))
+  # Mapping from index to word
+  vocabulary_inv = [x[0] for x in word_counts.most_common()]
+  # Mapping from word to index
+  vocabulary = {x: i for i, x in enumerate(vocabulary_inv)}
+  return [vocabulary, vocabulary_inv]
+
+
+def build_input_data(sentences, labels, vocabulary):
+  """
+  Maps sentencs and labels to vectors based on a vocabulary.
+  """
+  x = np.array([[vocabulary[word] for word in sentence] for sentence in sentences])
+  y = np.array(labels)
+  return [x, y]
+
+
+def load_data():
+  """
+  Loads and preprocessed data for the MR dataset.
+  Returns input vectors, labels, vocabulary, and inverse vocabulary.
+  """
+  # Load and preprocess data
+  sentences, labels = load_data_and_labels()
+  sentences_padded = pad_sentences(sentences)
+  vocabulary, vocabulary_inv = build_vocab(sentences_padded)
+  x, y = build_input_data(sentences_padded, labels, vocabulary)
+  return [x, y, vocabulary, vocabulary_inv]
+
+
+def batch_iter(data, batch_size, num_epochs):
+  """
+  Generates a batch iterator for a dataset.
+  """
+  data = np.array(data)
+  data_size = len(data)
+  num_batches_per_epoch = int(len(data)/batch_size) + 1
+  for epoch in range(num_epochs):
+    # Shuffle the data at each epoch
+    shuffle_indices = np.random.permutation(np.arange(data_size))
+    shuffled_data = data[shuffle_indices]
+    for batch_num in range(num_batches_per_epoch):
+      start_index = batch_num * batch_size
+      end_index = min((batch_num + 1) * batch_size, data_size)
+      yield shuffled_data[start_index:end_index]

Part2_Text_Classify/cnn-text-classification-tf-chinese/data/chinese/neg2.txt

@@ -0,0 +1,138 @@
+# encoding:utf-8
+import tensorflow as tf
+
+
+def linear(input_, output_size, scope=None):
+  '''''
+  Linear map: output[k] = sum_i(Matrix[k, i] * args[i] ) + Bias[k]
+  Args:
+      args: a tensor or a list of 2D, batch x n, Tensors.
+  output_size: int, second dimension of W[i].
+  scope: VariableScope for the created subgraph; defaults to "Linear".
+  Returns:
+  A 2D Tensor with shape [batch x output_size] equal to
+  sum_i(args[i] * W[i]), where W[i]s are newly created matrices.
+  Raises:
+  ValueError: if some of the arguments has unspecified or wrong shape.
+  '''
+
+  shape = input_.get_shape().as_list()
+  if len(shape) != 2:
+    raise ValueError("Linear is expecting 2D arguments: %s" % str(shape))
+  if not shape[1]:
+    raise ValueError("Linear expects shape[1] of arguments: %s" % str(shape))
+  input_size = shape[1]
+
+  # Now the computation.
+  with tf.variable_scope(scope or "SimpleLinear"):
+    matrix = tf.get_variable("Matrix", [output_size, input_size], dtype=input_.dtype)
+    bias_term = tf.get_variable("Bias", [output_size], dtype=input_.dtype)
+
+  return tf.matmul(input_, tf.transpose(matrix)) + bias_term
+
+
+# highway layer that borrowed from https://github.com/carpedm20/lstm-char-cnn-tensorflow
+def highway(input_, size, layer_size=1, bias=-2, f=tf.nn.relu):
+  """Highway Network (cf. http://arxiv.org/abs/1505.00387).
+
+  t = sigmoid(Wy + b)
+  z = t * g(Wy + b) + (1 - t) * y
+  where g is nonlinearity, t is transform gate, and (1 - t) is carry gate.
+  """
+  output = input_
+  for idx in xrange(layer_size):
+    output = f(
+      linear(output, size, scope='output_lin_%d' % idx))  # update
+    # add below, and remove scope parameter while calling:
+    # from tensorflow.contrib.rnn.python.ops.core_rnn_cell_impl import _linear as linear
+
+    transform_gate = tf.sigmoid(
+      linear(input_, size, scope='transform_lin_%d' % idx) + bias)  # update
+    carry_gate = 1. - transform_gate
+
+    output = transform_gate * output + carry_gate * input_
+
+  return output
+
+
+class TextCNN(object):
+  """
+  A CNN for text classification.
+  Uses an embedding layer, followed by a convolutional, max-pooling and softmax layer.
+  """
+
+  def __init__(
+    self, sequence_length, num_classes, vocab_size,
+    embedding_size, filter_sizes, num_filters, l2_reg_lambda=0.0):
+    # Placeholders for input, output and dropout
+    self.input_x = tf.placeholder(tf.int32, [None, sequence_length], name="input_x")
+    self.input_y = tf.placeholder(tf.float32, [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('/gpu:0'), tf.name_scope("embedding"):
+      W = tf.Variable(
+        tf.random_uniform([vocab_size, embedding_size], -1.0, 1.0),
+        name="W")
+      self.embedded_chars = tf.nn.embedding_lookup(W, self.input_x)
+      self.embedded_chars_expanded = tf.expand_dims(self.embedded_chars, -1)
+
+    # Create a convolution + maxpool layer for each filter size
+    pooled_outputs = []
+    for filter_size, num_filter in zip(filter_sizes, num_filters):
+      with tf.name_scope("conv-maxpool-%s" % filter_size):
+        # Convolution Layer
+        filter_shape = [filter_size, embedding_size, 1, num_filter]
+        W = tf.Variable(tf.truncated_normal(filter_shape, stddev=0.1), name="W")
+        b = tf.Variable(tf.constant(0.1, shape=[num_filter]), 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 = sum(num_filters)
+    self.h_pool = tf.concat(pooled_outputs, 3)  # 转换参数的顺序
+    self.h_pool_flat = tf.reshape(self.h_pool, [-1, num_filters_total])
+
+    # Add highway
+    with tf.name_scope("highway"):
+      self.h_highway = highway(self.h_pool_flat, self.h_pool_flat.get_shape()[1], 1, 0)
+
+    # Add dropout
+    with tf.name_scope("dropout"):
+      self.h_drop = tf.nn.dropout(self.h_highway, self.dropout_keep_prob)
+
+    # Final (unnormalized) scores and predictions
+    with tf.name_scope("output"):
+      W = tf.Variable(tf.truncated_normal([num_filters_total, num_classes], stddev=0.1), name="W")
+      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.scores = tf.nn.xw_plus_b(self.h_drop, W, b, name="scores")
+      self.predictions = tf.argmax(self.scores, 1, name="predictions")
+
+    # CalculateMean cross-entropy loss
+    with tf.name_scope("loss"):
+      losses = tf.nn.softmax_cross_entropy_with_logits(logits=self.scores, labels=self.input_y) # update
+      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, "float"), name="accuracy")