NLP in TensorFlow: BBC新闻(多分类问题)

• 导入所需的包

import csv
import tensorflow as tf
import numpy as np
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences

• 下载数据

!wget --no-check-certificate \
    https://storage.googleapis.com/laurencemoroney-blog.appspot.com/bbc-text.csv \
    -O /tmp/bbc-text.csv

• 定义参数

vocab_size = 20000
oov_tok = '<OOV>'

embedding_dim = 16
max_length = 120
trunc_type = 'pre'
padding_type = 'pre'

training_portion = .8

stopwords = [ "a", "about", "above", "after", "again", "against", "all", "am", "an", "and", "any", "are", "as", "at", "be", "because", "been", "before", "being", "below", "between", "both", "but", "by", "could", "did", "do", "does", "doing", "down", "during", "each", "few", "for", "from", "further", "had", "has", "have", "having", "he", "he'd", "he'll", "he's", "her", "here", "here's", "hers", "herself", "him", "himself", "his", "how", "how's", "i", "i'd", "i'll", "i'm", "i've", "if", "in", "into", "is", "it", "it's", "its", "itself", "let's", "me", "more", "most", "my", "myself", "nor", "of", "on", "once", "only", "or", "other", "ought", "our", "ours", "ourselves", "out", "over", "own", "same", "she", "she'd", "she'll", "she's", "should", "so", "some", "such", "than", "that", "that's", "the", "their", "theirs", "them", "themselves", "then", "there", "there's", "these", "they", "they'd", "they'll", "they're", "they've", "this", "those", "through", "to", "too", "under", "until", "up", "very", "was", "we", "we'd", "we'll", "we're", "we've", "were", "what", "what's", "when", "when's", "where", "where's", "which", "while", "who", "who's", "whom", "why", "why's", "with", "would", "you", "you'd", "you'll", "you're", "you've", "your", "yours", "yourself", "yourselves" ]
print(len(stopwords))
# Expected Output
# 153

• 获得文本和标签

sentences = []
labels = []
with open("/tmp/bbc-text.csv", 'r') as csvfile:
    reader = csv.reader(csvfile, delimiter=',')
    next(reader)
    for row in reader:
      labels.append(row[0])
      sentence = row[1]
      for word in stopwords:
        token = " " + word + " "
        sentence = sentence.replace(token, " ")
        sentence = sentence.replace("  ", " ")
      sentences.append(sentence)

• 拆分数据集

train_size = int(training_portion * len(labels))

train_sentences = sentences[:train_size]
train_labels = labels[:train_size]

validation_sentences = sentences[train_size:]
validation_labels = labels[train_size:]

• tokenizer和padding

tokenizer = Tokenizer(num_words = vocab_size, oov_token = oov_tok)
tokenizer.fit_on_texts(sentences)
word_index = tokenizer.word_index

train_sequences = tokenizer.texts_to_sequences(train_sentences)
train_padded = pad_sequences(train_sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)

validation_sequences = tokenizer.texts_to_sequences(validation_sentences)
validation_padded = pad_sequences(validation_sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)

• 对标签文本tokenizer

label_tokenizer = Tokenizer()
label_tokenizer.fit_on_texts(labels)

training_label_seq = np.array(label_tokenizer.texts_to_sequences(train_labels))
validation_label_seq = np.array(label_tokenizer.texts_to_sequences(validation_labels))

• 定义模型

from tensorflow.keras.layers import Embedding, GlobalAveragePooling1D, Dense

model = tf.keras.Sequential([
    Embedding(vocab_size, embedding_dim, input_length = max_length),
    GlobalAveragePooling1D(),
    Dense(24, activation = 'relu'),
    Dense(6, activation = 'softmax')
])
model.compile(loss='sparse_categorical_crossentropy',optimizer='adam',metrics=['accuracy'])
model.summary()

• 训练模型

num_epochs = 30
history = model.fit(train_padded, training_label_seq, epochs = num_epochs, \
                    validation_data = (validation_padded, validation_label_seq))

• 作图查看训练曲线

import matplotlib.pyplot as plt


def plot_graphs(history, string):
  plt.plot(history.history[string])
  plt.plot(history.history['val_'+string])
  plt.xlabel("Epochs")
  plt.ylabel(string)
  plt.legend([string, 'val_'+string])
  plt.show()
  
plot_graphs(history, "acc")
plot_graphs(history, "loss")

• 获得index2word的字典

reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])

def decode_sentence(text):
    return ' '.join([reverse_word_index.get(i, '?') for i in text])

• 获得embedding参数

e = model.layers[0]
weights = e.get_weights()[0]
print(weights.shape) # shape: (vocab_size, embedding_dim)

• 保存embedding参数

import io

out_v = io.open('vecs.tsv', 'w', encoding='utf-8')
out_m = io.open('meta.tsv', 'w', encoding='utf-8')
for word_num in range(1, vocab_size):
  word = reverse_word_index[word_num]
  embeddings = weights[word_num]
  out_m.write(word + "\n")
  out_v.write('\t'.join([str(x) for x in embeddings]) + "\n")
out_v.close()
out_m.close()

• 下载embedding数据

try:
  from google.colab import files
except ImportError:
  pass
else:
  files.download('vecs.tsv')
  files.download('meta.tsv')

• 可以将文件上传到projector.tensorflow来可视化查看embedding向量。可以选中Sphereize data选项。
  【参考文献】
  1.google colab