def get_answer(question):
"""输入问题，输出一个表达式
输入和输出都是字符串格式
"""
question = re.sub('(\d+)_(\d+/\d+)', '(\\1+\\2)', question)
question = question.replace('**', '^')
pred_equation = autosolve.generate(question, topk)
pred_equation = to_infix(pred_equation)
pred_equation = pred_equation.replace('^', '**')
return pred_equation
def convert_to_prefix(question, equation, answer):
# 把乘方符号从**换成^
question = question.replace('**', '^')
equation = equation.replace('**', '^')
# 中缀表达式转前缀
equation = to_prefix(equation)
# 测试一下转换是不是有问题，能不能逆转
temp = to_infix(equation)
temp = temp.replace('^', '**')
assert is_equal(eval(temp), eval(answer)), "Prefix template transfer error!"
return question, equation, answer
def evaluate(self, data, topk=1):
total, right = 0.0, 0.0
for question, equation, answer in data:
total += 1
pred_equation = autosolve.generate(question, topk)
try:
pred_equation = to_infix(pred_equation)
pred_equation = pred_equation.replace('^', '**')
right += int(is_equal(eval(pred_equation), eval(answer)))
except:
pass
return {'acc': right / total}
def load_data(filename):
"""读取训练数据，并做一些标准化，保证equation是可以eval的
参考：https://kexue.fm/archives/7809
"""
D = []
for l in open(filename):
l = json.loads(l)
question, equation, answer = l['original_text'], l['equation'], l[
'ans']
# 处理带分数
question = re.sub('(\d+)\((\d+/\d+)\)', '(\\1+\\2)', question)
equation = re.sub('(\d+)\((\d+/\d+)\)', '(\\1+\\2)', equation)
answer = re.sub('(\d+)\((\d+/\d+)\)', '(\\1+\\2)', answer)
equation = re.sub('(\d+)\(', '\\1+(', equation)
answer = re.sub('(\d+)\(', '\\1+(', answer)
# 分数去括号
question = re.sub('\((\d+/\d+)\)', '\\1', question)
# 处理百分数
equation = re.sub('([\.\d]+)%', '(\\1/100)', equation)
answer = re.sub('([\.\d]+)%', '(\\1/100)', answer)
# 冒号转除号、剩余百分号处理
equation = equation.replace(':', '/').replace('%', '/100')
answer = answer.replace(':', '/').replace('%', '/100')
if equation[:2] == 'x=':
equation = equation[2:]
try:
if is_equal(eval(equation), eval(answer)):
# 把乘方符号从**换成^
question = question.replace('**', '^')
equation = equation.replace('**', '^')
# 中缀表达式转前缀
equation = to_prefix(equation)
# 测试一下转换是不是有问题，能不能逆转
temp = to_infix(equation)
temp = temp.replace('^', '**')
assert (is_equal(eval(temp), eval(answer)))
D.append((question, equation, answer))
except BaseException as e:
continue
return D