import tensorflow as tf
import os
from common import Config, VocabType
from argparse import ArgumentParser
from file2vec import File2Vec
from model import Model
from sys import argv
from model_defs import models
dataset_dir = 'java_files/'
if __name__ == '__main__':
# Get the model for this session
modelDef = models[int(argv[1])]
print("\n\nRunning model:", modelDef['name'], '\n\n')
config = Config.get_default_config(modelDef['location'])
modelObj = Model(config, modelDef['name'])
modelObj.predict([])
print('Created model')
# For each dataset in our collection of them, run the model on it
for dataset in os.listdir(dataset_dir):
if os.path.isdir(os.path.join(dataset_dir, dataset)):
print("Processing dataset:", dataset)
file2vec = File2Vec(config, modelObj, modelDef, dataset)
file2vec.run()
modelObj.close_session()
required=False,
help="save target vectors in word2vec format")
parser.add_argument('--export_code_vectors',
action='store_true',
required=False,
help="export code vectors for the given examples")
parser.add_argument(
'--release',
action='store_true',
help=
'if specified and loading a trained model, release the loaded model for a lower model '
'size.')
parser.add_argument('--predict', action='store_true')
args = parser.parse_args()
config = Config.get_default_config(args)
model = Model(config)
print('Created model')
if config.TRAIN_PATH:
model.train()
if args.save_w2v is not None:
model.save_word2vec_format(args.save_w2v, source=VocabType.Token)
print('Origin word vectors saved in word2vec text format in: %s' %
args.save_w2v)
if args.save_t2v is not None:
model.save_word2vec_format(args.save_t2v, source=VocabType.Target)
print('Target word vectors saved in word2vec text format in: %s' %
args.save_t2v)
if config.TEST_PATH and not args.data_path:
eval_results = model.evaluate()
parser.add_argument("--word",
help="choose word count: 1 - wordcount&cloud;",
type=int)
parser.add_argument("--tag",
help="choose tag count: 1 - tagcount;",
type=int)
parser.add_argument(
"--summary",
help="choose summary algorithm: 0 - LSA; 1 - LEX_RANK; \
2 - TEXT_RANK; 3 - SUM_BASIC; 4 - TextTeaser; 5 - MMR",
type=int)
args = parser.parse_args()
print(args)
# check data is prepared
term = args.term
config = Config.get_default_config(term)
if not fu.file_exist(config.Q_OUTPUT_FILE):
print(config.Q_OUTPUT_FILE + ' File not exists...')
sys.exit()
raw_documents = fu.read_data(config.Q_OUTPUT_FILE)
'''
First Analysis Words and Tags
'''
if args.word == 1:
# count words
wc = Word_count()
wc.extract_words(raw_documents)
# wc.plot(config.WORDCOUNT_PIC)
if args.tag == 1:
# count tags
