def test_score(model_name,parameter):
label2id = {'Other': 0, 'Cause-Effect(e1,e2)': 1, 'Cause-Effect(e2,e1)': 2, 'Component-Whole(e1,e2)': 3,
'Component-Whole(e2,e1)': 4, 'Content-Container(e1,e2)': 5, 'Content-Container(e2,e1)': 6,
'Entity-Destination(e1,e2)': 7, 'Entity-Destination(e2,e1)': 8, 'Entity-Origin(e1,e2)': 9,
'Entity-Origin(e2,e1)': 10, 'Instrument-Agency(e2,e1)': 11, 'Instrument-Agency(e1,e2)': 12,
'Member-Collection(e1,e2)': 13, 'Member-Collection(e2,e1)': 14, 'Message-Topic(e1,e2)': 15,
'Message-Topic(e2,e1)': 16, 'Product-Producer(e1,e2)': 17, 'Product-Producer(e2,e1)': 18}
#加载预训练语料
vocab_file = 'dataset/vocab/vocab.pkl'
vocab = Vocab(vocab_file, load=True)
resoult_file=open('resoult/resoult.txt','w')
#加载预处理测试集
test_batch = DataLoader('dataset/sem/test_file.json',parameter, vocab, train=False)
test_emb_file = './dataset/vocab/embedding.npy'
test_emb_matrix = np.load(test_emb_file)
parameter['vocab_size'] = vocab.size
#加载模型
trainer = GCNTrainer(parameter,test_emb_matrix)
trainer.load(model_name)
id2label = dict([(v,k) for k,v in label2id.items()])
predictions = []
for i, batch in enumerate(test_batch):
preds = trainer.predict(batch)
predictions += preds
predictions = [id2label[p] for p in predictions]
#结果写入文件
counter=8001
for resoult in predictions:
if counter == 10718:
break
resoult_file.writelines(str(counter)+"\t"+resoult+'\n')
counter+=1
resoult_file.close()
#计算分数
os.system('perl ./resoult/semeval2010_task8_scorer-v1.2.pl ./resoult/resoult.txt ./resoult/test_key.txt > ./resoult/score.txt')
f=open("resoult/score.txt")
resoult1=""
line=f.readline()
i=0
while line:
if i==143:
resoult1=line
if i==147:
break
line=f.readline()
i+=1
f.close()
return line,resoult1
def __init__(self, addresses, frequency, window):
"""Initialization - super() and ready() calls are required..."""
super(SampleAnalysis, self).__init__(addresses=addresses, type=peers.ANALYSIS)
self.eog_analyser = EogAnalyser(frequency, 0)
high_pass = HighpassFilter(frequency, 0.1)
self.data_loader = DataLoader([high_pass], 2, frequency)
self.data_loader.set_window(window)
self.plotter = SignalPlotter(self.data_loader.prepare_timeline())
self.ready()
LOGGER.info("Sample analysis init finished!")
def start_train(self):
#加载预训练语料
vocab_file = 'dataset/vocab/vocab.pkl'
self.vocab = Vocab(vocab_file, load=True)
self.parameter['vocab_size'] = self.vocab.size
emb_file = './dataset/vocab/embedding.npy'
self.emb_matrix = np.load(emb_file)
#加载训练集
self.train_batch = DataLoader('dataset/sem/train_file.json',
self.parameter,
self.vocab,
train=True)
self.trainer = GCNTrainer(self.parameter, emb_matrix=self.emb_matrix)
self.current_lr = self.parameter['lr']
self.log_name = "log/" + str(time.strftime("%d_%I_%M")) + ".log"
log = open(self.log_name, 'w+')
log.write(str(self.parameter))
log.close()
type = "float",
default = 256.0,
help = "Data registration frequency.")
# parse command-line arguments, exits when fatal error
options, args = parser.parse_args()
if not options.input_file:
print "Input file required; type -h for help."
sys.exit(-1)
file_loader = FileLoader(options)
eog_analyser = EogAnalyser(options.frequency, 0)
high_pass = HighpassFilter(options.frequency, 0.1)
data_loader = DataLoader([high_pass],
2,
options.frequency)
data_loader.set_window(64)
data_loader.set_leftover(4)
plotter = SignalPlotter(data_loader.prepare_timeline())
tracker = EyeTracker()
tracker.run()
while True:
s = file_loader.get_sample()
if s is None:
break
a = numpy.array(s)
data_loader.load_pack(a)
signal = data_loader.get_signal_set()
class SampleAnalysis(ConfiguredMultiplexerServer):
"""A class responsible for handling signal message and making proper decision.
The class inherits from generic class for convinience - all technical stuff
is being done in this super-class"""
def __init__(self, addresses, frequency, window, leftover):
"""Initialization - super() and ready() calls are required..."""
super(SampleAnalysis, self).__init__(addresses=addresses,
type=peers.ANALYSIS)
self.eog_analyser = EogAnalyser(frequency, 0)
high_pass = HighpassFilter(frequency, 0.1)
self.data_loader = DataLoader([high_pass],
2,
frequency)
self.data_loader.set_window(window)
self.data_loader.set_leftover(leftover)
self.plotter = SignalPlotter(self.data_loader.prepare_timeline())
self.tracker = EyeTracker()
self.tracker.run()
self.ready()
LOGGER.info("Sample analysis init finished!")
def handle_message(self, mxmsg):
"""The only required function in the class
that will be fired every time message is received"""
if mxmsg.type == types.AMPLIFIER_SIGNAL_MESSAGE:
# Got proper message, let`s unpack it ...
# Messages are transmitted in bunches so lets define SampleVector
# in order to unpack bunch of Sample messages ...
l_vect = variables_pb2.SampleVector()
l_vect.ParseFromString(mxmsg.message)
# Now we have message unpacked, lets iterate over every sample ...
for s in l_vect.samples:
# Every sample has two fields:
# timestamp - system clock time of a moment of Sample`s creation
# channels - a list of values - one for every channel
#LOGGER.debug("Got sample with timestamp: "+str(s.timestamp))
# One can copy samples to numpy array ...
a = numpy.array(s.channels) # w tym miejscu mamy w tablicy a "paczke" próbek (domyślnie 4próbki ) ze wszystkich zadeklarowanych kanalow
self.data_loader.load_pack(a)
signal = self.data_loader.get_signal_set()
if signal:
self.eog_analyser.load_signal_set(signal)
decisions = self.eog_analyser.get_decisions(window = 10,
window_seconds = False,
jump = 1000,
min_sec_diff = 1.5)
for direction, time in decisions:
tracker.move_square(direction)
# Having a new bunch of values one can fire some magic analysis and
# generate decision ....
# Below we have quite simple decision-maker - it generates a random
# decision every ~100 samples-bunch
########## TU NA PODSTAWIE ANALLIZY PODEJMUJEMY DECYZJE I MOZEMY JA PRZEKAZAC DO RESZTY SYSTEMU OBCI ######################
########## W TYM PRZYKLADZIE JEST TO LOSOWA DECYZJA ##############
########## W TYM CWICZENIU WYSTARCZY JESLI WYPISZECIE DECYZJE NA EKRAN ###########
if random.random() > 0.99:
# Here we send DECISION message somewhere-to-the-system ...
# It's up to scenario's configuration how the decision will be used ...
# Eg. it might be used by LOGIC module to push some button in speller.
self.conn.send_message(message = str(random.randint(0,7)),
type = types.DECISION_MESSAGE,
flush=True)
else:
LOGGER.warning("Got unrecognised message type: "+str(mxmsg.type))
# Tell the system 'I`ll not respond to this message, I`m just receiving'
self.no_response()