import json
import logging
from graph import io
import tqdm
logging.basicConfig(level=logging.DEBUG)
if __name__ == "__main__":
logger = logging.getLogger(__name__)
logger.setLevel(logging.ERROR)
data_folder = "../data/"
relations_data, _ = io.load_relation_graphs_from_file(
"../data/wikipedia-wikidata/enwiki-20160501/semantic-graphs-filtered-training.02_06.json",
load_vertices=False)
logging.debug('Loaded, size: {}'.format(len(relations_data)))
ne_tagger = nltk.tag.stanford.StanfordNERTagger(
"../resources/stanfordcorenlp/models-3.7.0/edu/stanford/nlp/models/ner/english.all.3class.caseless.distsim.crf.ser.gz",
path_to_jar=
"../resources/stanfordcorenlp/stanford-ner-2015-12-09/stanford-ner-3.6.0.jar"
)
pos_tagger = nltk.tag.stanford.StanfordPOSTagger(
"../resources/stanfordcorenlp/models-3.7.0/edu/stanford/nlp/models/pos-tagger/english-caseless-left3words-distsim.tagger",
path_to_jar=
"../resources/stanfordcorenlp/stanford-postagger-full-2015-12-09/stanford-postagger-3.6.0.jar"
)
webquestions_utterances_tokens = [
q_obj['tokens'] for q_obj in relations_data
'-s',
action='store_true',
help="Use only a portion of the training and validation sets.")
args = parser.parse_args()
model_name = args.model_name
mode = args.mode
with open(args.model_params) as f:
model_params = json.load(f)
embeddings, word2idx = embeddings.load(args.word_embeddings)
print("Loaded embeddings:", embeddings.shape)
training_data, _ = io.load_relation_graphs_from_file(args.train_set,
load_vertices=True)
val_data, _ = io.load_relation_graphs_from_file(args.val_set,
load_vertices=True)
if args.s:
training_data = training_data[:len(training_data) // 3]
print("Training data size set to: {}".format(len(training_data)))
val_data = val_data[:len(val_data) // 3]
print("Validation data size set to: {}".format(len(val_data)))
if mode in ['test', 'train-plus-test']:
print("Reading the property index")
with open(args.models_folder + model_name + ".property2idx") as f:
property2idx = ast.literal_eval(f.read())
elif args.property_index:
parser.add_argument('--models_folder', default="../trainedmodels/")
args = parser.parse_args()
embedding_matrix, word2idx = embeddings.load(
keras_models.model_params['wordembeddings'])
print("Loaded embeddings:", embedding_matrix.shape)
max_sent_len = keras_models.model_params['max_sent_len']
n_out = len(keras_models.property2idx)
model = getattr(keras_models,
args.model_name)(keras_models.model_params,
embedding_matrix, max_sent_len, n_out)
model.load_weights(args.models_folder + args.model_name + ".kerasmodel")
print("Loaded the model")
test_data, _ = io.load_relation_graphs_from_file(args.test_set,
load_vertices=True)
print("Loaded the test set")
graphs_to_indices = keras_models.to_indices
if "Context" in args.model_name:
to_one_hot = embeddings.timedistributed_to_one_hot
graphs_to_indices = keras_models.to_indices_with_extracted_entities
elif "CNN" in args.model_name:
graphs_to_indices = keras_models.to_indices_with_relative_positions
test_as_indices = list(graphs_to_indices(test_data, word2idx))
test_data = None
print("Results on the test set")
predictions_classes, predictions = evaluate(model, test_as_indices[:-1],
test_as_indices[-1])