def fit(self, steps_list, epoch=3000):
"""
:param int epoch:
:param typing.List[typing.Dict[q=dict, steps=typing.List[StepInOut]]] steps_list:
:return:
"""
def filter_question(condition_func):
sub_steps_list = []
for steps_dict in steps_list:
question = steps_dict['q']
if condition_func(question['in1'], question['in2']):
sub_steps_list.append(steps_dict)
return sub_steps_list
# self.print_weights()
if not self.weight_loaded:
self.train_f_enc(filter_question(lambda a, b: 10 <= a < 100 and 10 <= b < 100), epoch=100)
self.f_enc.trainable = False
q_type = "training questions of a+b < 10"
print(q_type)
pr = 0.8
all_ok = self.fit_to_subset(filter_question(lambda a, b: a+b < 10), epoch=epoch, pass_rate=pr)
print("%s is pass_rate >= %s: %s" % (q_type, pr, all_ok))
q_type = "training questions of a<10 and b< 10 and 10 <= a+b"
print(q_type)
pr = 0.8
all_ok = self.fit_to_subset(filter_question(lambda a, b: a<10 and b<10 and a + b >= 10), epoch=epoch, pass_rate=pr)
print("%s is pass_rate >= %s: %s" % (q_type, pr, all_ok))
q_type = "training questions of a<10 and b<10"
print(q_type)
pr = 0.8
all_ok = self.fit_to_subset(filter_question(lambda a, b: a < 10 and b < 10), epoch=epoch, pass_rate=pr)
print("%s is pass_rate >= %s: %s" % (q_type, pr, all_ok))
q_type = "training questions of a<100 and b<100"
print(q_type)
pr = 0.8
all_ok = self.fit_to_subset(filter_question(lambda a, b: a < 100 and b < 100), epoch=epoch, pass_rate=pr)
print("%s is pass_rate >= %s: %s" % (q_type, pr, all_ok))
while True:
print("test all type of questions")
cc, wc = self.test_to_subset(create_questions(1000))
print("Accuracy %s(OK=%d, NG=%d)" % (cc/(cc+wc), cc, wc))
if wc == 0:
break
q_type = "training questions of ALL"
print(q_type)
pr = 1.0
self.fit_to_subset(filter_question(lambda a, b: True), epoch=epoch, pass_rate=pr)
all_ok = self.fit_to_subset(filter_question(lambda a, b: True), epoch=epoch, pass_rate=pr, skip_correct=True)
print("%s is pass_rate >= %s: %s" % (q_type, pr, all_ok))
def main(stdscr, filename: str, num: int, result_logger: ResultLogger):
terminal = Terminal(stdscr, create_char_map())
terminal.init_window(FIELD_WIDTH, FIELD_ROW)
program_set = AdditionProgramSet()
addition_env = AdditionEnv(FIELD_ROW, FIELD_WIDTH, FIELD_DEPTH)
questions = create_questions(num)
teacher = AdditionTeacher(program_set)
npi_runner = TerminalNPIRunner(terminal, teacher)
npi_runner.verbose = DEBUG_MODE
steps_list = []
for data in questions:
addition_env.reset()
q = copy(data)
run_npi(addition_env, npi_runner, program_set.ADD, data)
steps_list.append({"q": q, "steps": npi_runner.step_list})
result_logger.write(data)
terminal.add_log(data)
if filename:
with open(filename, 'wb') as f:
pickle.dump(steps_list, f, protocol=pickle.HIGHEST_PROTOCOL)
def main(stdscr, model_path: str, num: int, result_logger: ResultLogger):
terminal = Terminal(stdscr, create_char_map())
terminal.init_window(FIELD_WIDTH, FIELD_ROW)
program_set = AdditionProgramSet()
addition_env = AdditionEnv(FIELD_ROW, FIELD_WIDTH, FIELD_DEPTH)
questions = create_questions(num)
if DEBUG_MODE:
questions = questions[-num:]
system = RuntimeSystem(terminal=terminal)
npi_model = AdditionNPIModel(system, model_path, program_set)
npi_runner = TerminalNPIRunner(terminal, npi_model, recording=False)
npi_runner.verbose = DEBUG_MODE
correct_count = wrong_count = 0
for data in questions:
addition_env.reset()
run_npi(addition_env, npi_runner, program_set.ADD, data)
result_logger.write(data)
terminal.add_log(data)
if data["correct"]:
correct_count += 1
else:
wrong_count += 1
return correct_count, wrong_count
def main(stdscr, model_path: str, num: int, result_logger: ResultLogger):
terminal = Terminal(stdscr, create_char_map())
terminal.init_window(FIELD_WIDTH, FIELD_ROW)
program_set = AdditionProgramSet()
addition_env = AdditionEnv(FIELD_ROW, FIELD_WIDTH, FIELD_DEPTH)
questions = create_questions(num)
if DEBUG_MODE:
questions = questions[-num:]
system = RuntimeSystem(terminal=terminal)
npi_model = AdditionNPIModel(system, model_path, program_set)
npi_runner = TerminalNPIRunner(terminal, npi_model, recording=False)
npi_runner.verbose = DEBUG_MODE
correct_count = wrong_count = 0
for data in questions:
addition_env.reset()
run_npi(addition_env, npi_runner, program_set.ADD, data)
result_logger.write(data)
terminal.add_log(data)
if data['correct']:
correct_count += 1
else:
wrong_count += 1
return correct_count, wrong_count