1. Data Preparation
!wget --no-check-certificate \
https://storage.googleapis.com/laurencemoroney-blog.appspot.com/sarcasm.json \
-O /tmp/sarcasm.json
import json
with open("/tmp/sarcasm.json", 'r') as f:
datastore = json.load(f)
sentences = []
labels = []
for item in datastore:
sentences.append(item['headline'])
labels.append(item['is_sarcastic'])
training_size = 20000
training_sentences = sentences[0:training_size]
testing_sentences = sentences[training_size:]
training_labels = labels[0:training_size]
testing_labels = labels[training_size:]
2. Tokenization & Padding
import numpy as np
import tensorflow as tf
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
vocab_size = 10000
max_length = 120
trunc_type='post'
padding_type='post'
oov_tok = "<OOV>"
tokenizer = Tokenizer(num_words=vocab_size, oov_token=oov_tok)
tokenizer.fit_on_texts(training_sentences)
word_index = tokenizer.word_index
reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])
print (word_index)
{'to': 1, 'of': 2, 'the': 3, 'in': 4, 'for': 5, 'a': 6......}
training_sequences = tokenizer.texts_to_sequences(training_sentences)
training_padded = pad_sequences(training_sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)
testing_sequences = tokenizer.texts_to_sequences(testing_sentences)
testing_padded = pad_sequences(testing_sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)
training_padded = np.array(training_padded)
training_labels = np.array(training_labels)
testing_padded = np.array(testing_padded)
testing_labels = np.array(testing_labels)
3. Model
vocab_size = 10000
embedding_dim = 16
max_length = 120
model = tf.keras.Sequential([
tf.keras.layers.Embedding(vocab_size, embedding_dim, input_length=max_length), #input_length: 当输入序列的长度固定时，该值为其长度。如果要在该层后接Flatten层，然后接Dense层，则必须指定该参数，否则Dense层的输出维度无法自动推断。
#tf.keras.layers.Flatten(),
tf.keras.layers.GlobalAveragePooling1D(),
tf.keras.layers.Dense(26, activation='relu'),
tf.keras.layers.Dense(1, activation='sigmoid')
])
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
model.summary()
num_epochs = 30
history = model.fit(training_padded, training_labels, epochs=num_epochs, validation_data=(testing_padded, testing_labels), verbose=2)
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, "accuracy")
plot_graphs(history, "loss")
e = model.layers[0]
weights = e.get_weights()[0]
print(weights.shape) # shape: (vocab_size, embedding_dim)
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()
将 vecs.tsv，meta.tsv 上传到 projector.tensorflow.org/ 可视化：
4. Predict
In the case of a regression problem, these predictions may be in the format of the problem directly, provided by a linear activation function.
For a binary classification problem, the predictions may be an array of probabilities for the first class that can be converted to a 1 or 0 by rounding.
For a multiclass classification problem, the results may be in the form of an array of probabilities (assuming a one hot encoded output variable) that may need to be converted to a single class output prediction using the argmax function.
sentence = ["granny starting to fear spiders in the garden might be real", "game of thrones season finale showing this sunday night"]
sequences = tokenizer.texts_to_sequences(sentence)
padded = pad_sequences(sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)
print(model.predict(padded))
print(tf.round(model.predict(padded)).numpy().flatten())
