parser.add_argument('--graph_folder', default='../lm_graph', dest='graphs')
args = parser.parse_args()
# Fit the model
if args.mode == 'train':
# Read the initial word vectors
train_data = np.load(open('lm_train_data.npy','r'))
train_labels = np.load(open('lm_train_labels.npy','r'))
lm = LanguageModel(args.lr, args.num_steps, args.vocab_len, args.minibatch_size)
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
lm.fit(sess, train_data, train_labels, num_epochs=args.num_epochs, folder=args.folder, graph_folder=args.graphs)
else:
tweets = dill.load(open("tweets", "rb"))
w2i = dill.load(open("w2i","rb"))
i2w = dill.load(open("i2w","rb"))
word_vector = dill.load(open("word_vecs","rb"))
start_wd = ["president", "@netanyahu", "democrats", "gop", "congress", "white", "my", "the", "#makeamericagreatagain" ,"republicans", "wall", "@realdonaldtrump", "crooked"]
input_list = [np.array([[word_vector[w2i[item]]]]) for item in start_wd]
model = LanguageModel(args.lr, args.num_steps, args.vocab_len, args.minibatch_size)
saver = tf.train.Saver()
folder = args.folder
with tf.Session() as sess:
saver.restore(sess, os.path.join(folder, 'model.ckpt'))
import pickle from lm import LanguageModel train_filename = "train_sequence.pkl" model_filename = "model.pkl" dataset = pickle.load(open(train_filename, "rb")) lm = LanguageModel(lidstone_param=3e-4) lm.fit(dataset) pickle.dump(lm, open(model_filename, "wb"))
