from keras.models import Sequential, model_from_json
from keras.layers import Dense, Dropout, Activation
from keras.layers import Embedding, Conv1D, GlobalMaxPooling1D
from keras.preprocessing.text import Tokenizer
max_words = 10000
maxlen = 500
batch_size = 64
embedding_dims = 50
filters = 250
kernel_size = 5
hidden_dims = 150
epochs = 2
x_train, x_test, y_train, y_test = load_encoded_data(
data_split=0.8, embedding_name="data/default", pos_tags=True)
num_classes = np.max(y_train) + 1
print(num_classes, 'classes')
print('Pad sequences (samples x time)')
x_train = sequence.pad_sequences(x_train, maxlen=maxlen)
x_test = sequence.pad_sequences(x_test, maxlen=maxlen)
print('Convert class vector to binary class matrix '
'(for use with categorical_crossentropy)')
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
print('Constructing model!')
# Model configuration
maxlen = 500
batch_size = 64
embedding_dims = 75
pool_size = 4
filters = 100
kernel_size = 5
hidden_dims = 350
epochs = 2
lstm_size = 70
# Add parts-of-speech to data
pos_tags_flag = True
# Export & load embeddings
x_train, x_test, y_train, y_test = load_encoded_data(
data_split=0.8, embedding_name=embedding_name, pos_tags=pos_tags_flag)
word_encoding, category_encoding = import_embedding(embedding_name)
max_words = len(word_encoding) + 1
num_classes = np.max(y_train) + 1
print(max_words, 'words')
print(num_classes, 'classes')
print('Pad sequences (samples x time)')
x_train = sequence.pad_sequences(x_train, maxlen=maxlen)
x_test = sequence.pad_sequences(x_test, maxlen=maxlen)
print('Convert class vector to binary class matrix '
'(for use with categorical_crossentropy)')
from __future__ import print_function
import numpy as np
import keras
from sentence_types import load_encoded_data
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
from keras.preprocessing.text import Tokenizer
max_words = 10000
batch_size = 256
epochs = 3
x_train, x_test, y_train, y_test = load_encoded_data(data_split=0.8)
num_classes = np.max(y_train) + 1
print(num_classes, 'classes')
print('Vectorizing sequence data...')
tokenizer = Tokenizer(num_words=max_words)
x_train = tokenizer.sequences_to_matrix(x_train, mode='binary')
x_test = tokenizer.sequences_to_matrix(x_test, mode='binary')
print('Convert class vector to binary class matrix '
'(for use with categorical_crossentropy)')
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
print('Constructing model!')