# Load all files from a directory in a DataFrame.def load_directory_data(directory):  data = {}  data["sentence"] = []  data["sentiment"] = []  for file_path in os.listdir(directory):    with tf.gfile.GFile(os.path.join(directory, file_path), "r") as f:      data["sentence"].append(f.read())      data["sentiment"].append(re.match("\d+_(\d+)\.txt", file_path).group(1))  return pd.DataFrame.from_dict(data)
# Merge positive and negative examples, add a polarity column and shuffle.def load_dataset(directory):  pos_df = load_directory_data(os.path.join(directory, "pos"))  neg_df = load_directory_data(os.path.join(directory, "neg"))  pos_df["polarity"] = 1  neg_df["polarity"] = 0  return pd.concat([pos_df, neg_df]).sample(frac=1).reset_index(drop=True)
# Download and process the dataset files.def download_and_load_datasets(force_download=False):  dataset = tf.keras.utils.get_file(      fname="aclImdb.tar.gz",       origin="http://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz",       extract=True)
  train_df = load_dataset(os.path.join(os.path.dirname(dataset),                                        "aclImdb", "train"))  test_df = load_dataset(os.path.join(os.path.dirname(dataset),                                       "aclImdb", "test"))
  return train_df, test_df
# Reduce logging output.tf.logging.set_verbosity(tf.logging.ERROR)
train_df, test_df = download_and_load_datasets()train_df.head()

# Create datasets (Only take up to 150 words)train_text = train_df['sentence'].tolist()train_text = [' '.join(t.split()[0:150]) for t in train_text]train_text = np.array(train_text, dtype=object)[:, np.newaxis]train_label = train_df['polarity'].tolist()
test_text = test_df['sentence'].tolist()test_text = [' '.join(t.split()[0:150]) for t in test_text]test_text = np.array(test_text, dtype=object)[:, np.newaxis]test_label = test_df['polarity'].tolist()

class ElmoEmbeddingLayer(Layer):    def __init__(self, **kwargs):        self.dimensions = 1024        self.trainable = True        super(ElmoEmbeddingLayer, self).__init__(**kwargs)        def build(self, input_shape):        self.elmo = hub.Module('https://tfhub.dev/google/elmo/2', trainable=self.trainable, name="{}_module".format(self.name))
self.trainable_weights += K.tf.trainable_variables(scope="^{}_module/.*".format(self.name))        super(ElmoEmbeddingLayer, self).build(input_shape)
def call(self, x, mask=None):        result = self.elmo(K.squeeze(K.cast(x, tf.string), axis=1),                      as_dict=True,                      signature='default',                      )['default']        return result        def compute_mask(self, inputs, mask=None):        return K.not_equal(inputs, '--PAD--')        def compute_output_shape(self, input_shape):        return (input_shape[0], self.dimensions)

input_text = layers.Input(shape=(1,), dtype=tf.string)embedding = ElmoEmbeddingLayer()(input_text)dense = layers.Dense(256, activation='relu')(embedding)pred = layers.Dense(1, activation='sigmoid')(dense)
model = Model(inputs=[input_text], outputs=pred)
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])model.summary()
model.fit(train_text,           train_label,          validation_data=(test_text, test_label),          epochs=5,          batch_size=32)