Spaces:
Running
Running
File size: 7,818 Bytes
8af54b8 be1543a 8af54b8 be1543a 8af54b8 be1543a 8af54b8 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 |
import logging
import re
import numpy as np
from typing import Any
NUMERIC_IN_EN = r"(?:[\s=+-/<>($:\.\*\\])(?=\S)((?:0|(?:\d{1,3}(?:,\d{3})+(?=\D|$))|(?:\d+))(?:\.\d+)?%?)(?:(?![^\s=+-/>)$:\.\*\\])|(?=, ))"
NUMERIC_IN_ZH = (
r"(?:\D|^)((?:0|(?:\d{1,3}(?:,\d{3})+(?=\D|$))|(?:\d+))(?:\.\d+)?%?)(?=\D|$)"
)
def extract_choice(gen):
# answer is A | choice is A | choose A
res = re.search(
r"(?:(?:[Cc]hoose)|(?:(?:[Aa]nswer|[Cc]hoice)(?![^ABCD]{0,20}?(?:n't|not))[^ABCD]{0,10}?\b(?:|is|:|be))\b)[^ABCD]{0,20}?\b(A|B|C|D)\b",
gen,
)
# A is correct | A is right
if res is None:
res = re.search(
r"\b(A|B|C|D)\b(?![^ABCD]{0,8}?(?:n't|not)[^ABCD]{0,5}?(?:correct|right))[^ABCD]{0,10}?\b(?:correct|right)\b",
gen,
)
# straight answer: A
if res is None:
res = re.search(r"^(A|B|C|D)(?:\.|,|:|$)", gen)
# simply extract the first appearred letter
if res is None:
res = re.search(r"(?<![a-zA-Z])(A|B|C|D)(?![a-zA-Z=])", gen)
if res is None:
res = "A"
if isinstance(res, str):
return res
return res.group(1)
def decode_choice(responses: list[Any]):
num_choices = responses[0].shape[0]
choices = np.argmax(np.asarray(responses), axis=1)
responses = np.array(list("ABCDEFGHIJKL"[:num_choices]))[choices]
# return (responses == np.array(references)).mean()
return responses
def extract_numeric(string, pattern=NUMERIC_IN_EN) -> str:
all_values = list(
filter(lambda x: len(x.strip()) != 0 and x != "%", re.findall(pattern, string))
)
def standardize(x):
y = "".join(x.split(","))
if "." in y:
y = y.rstrip("0")
if y[-1] == ".":
y = y[:-1]
if y[0] == ".":
y = "0" + y
if y[-1] == "%":
y = str(eval(y[:-1]) / 100)
return y
if not len(all_values):
logging.debug(f"No numeric value found in string: {string}")
value = string
else:
value = standardize(all_values[-1].strip())
return value
def remove_boxed(s):
if "\\boxed " in s:
left = "\\boxed "
assert s[: len(left)] == left
return s[len(left) :]
left = "\\boxed{"
assert s[: len(left)] == left
assert s[-1] == "}"
return s[len(left) : -1]
def last_boxed_only_string(string):
idx = string.rfind("\\boxed")
if "\\boxed " in string:
return "\\boxed " + string.split("\\boxed ")[-1].split("$")[0]
if idx < 0:
idx = string.rfind("\\fbox")
if idx < 0:
return None
i = idx
right_brace_idx = None
num_left_braces_open = 0
while i < len(string):
if string[i] == "{":
num_left_braces_open += 1
if string[i] == "}":
num_left_braces_open -= 1
if num_left_braces_open == 0:
right_brace_idx = i
break
i += 1
if right_brace_idx is None:
retval = None
else:
retval = string[idx : right_brace_idx + 1]
return retval
def fix_sqrt(string):
if "\\sqrt" not in string:
return string
splits = string.split("\\sqrt")
new_string = splits[0]
for split in splits[1:]:
if split[0] != "{":
a = split[0]
new_substr = "\\sqrt{" + a + "}" + split[1:]
else:
new_substr = "\\sqrt" + split
new_string += new_substr
return new_string
def remove_right_units(string):
# "\\text{ " only ever occurs (at least in the val set) when describing units
if "\\text{ " in string:
splits = string.split("\\text{ ")
assert len(splits) == 2
return splits[0]
else:
return string
def fix_fracs(string):
substrs = string.split("\\frac")
new_str = substrs[0]
if len(substrs) > 1:
substrs = substrs[1:]
for substr in substrs:
new_str += "\\frac"
if substr[0] == "{":
new_str += substr
else:
try:
assert len(substr) >= 2
except AssertionError:
return string
a = substr[0]
b = substr[1]
if b != "{":
if len(substr) > 2:
post_substr = substr[2:]
new_str += "{" + a + "}{" + b + "}" + post_substr
else:
new_str += "{" + a + "}{" + b + "}"
else:
if len(substr) > 2:
post_substr = substr[2:]
new_str += "{" + a + "}" + b + post_substr
else:
new_str += "{" + a + "}" + b
string = new_str
return string
def fix_a_slash_b(string):
if len(string.split("/")) != 2:
return string
a = string.split("/")[0]
b = string.split("/")[1]
try:
a = int(a)
b = int(b)
assert string == "{}/{}".format(a, b)
new_string = "\\frac{" + str(a) + "}{" + str(b) + "}"
return new_string
except Exception as e:
return string
def strip_string(string):
# linebreaks
string = string.replace("\n", "")
# remove inverse spaces
string = string.replace("\\!", "")
# replace \\ with \
string = string.replace("\\\\", "\\")
# replace tfrac and dfrac with frac
string = string.replace("tfrac", "frac")
string = string.replace("dfrac", "frac")
# remove \left and \right
string = string.replace("\\left", "")
string = string.replace("\\right", "")
# Remove circ (degrees)
string = string.replace("^{\\circ}", "")
string = string.replace("^\\circ", "")
# remove dollar signs
string = string.replace("\\$", "")
# remove units (on the right)
string = remove_right_units(string)
# remove percentage
string = string.replace("\\%", "")
string = string.replace("\%", "") # noqa: W605
# " 0." equivalent to " ." and "{0." equivalent to "{." Alternatively, add "0" if "." is the start of the string
string = string.replace(" .", " 0.")
string = string.replace("{.", "{0.")
# if empty, return empty string
if len(string) == 0:
return string
if string[0] == ".":
string = "0" + string
# to consider: get rid of e.g. "k = " or "q = " at beginning
if len(string.split("=")) == 2:
if len(string.split("=")[0]) <= 2:
string = string.split("=")[1]
# fix sqrt3 --> sqrt{3}
string = fix_sqrt(string)
# remove spaces
string = string.replace(" ", "")
# \frac1b or \frac12 --> \frac{1}{b} and \frac{1}{2}, etc. Even works with \frac1{72} (but not \frac{72}1). Also does a/b --> \\frac{a}{b}
string = fix_fracs(string)
# manually change 0.5 --> \frac{1}{2}
if string == "0.5":
string = "\\frac{1}{2}"
# NOTE: X/Y changed to \frac{X}{Y} in dataset, but in simple cases fix in case the model output is X/Y
# string = fix_a_slash_b(string)
return string
def get_answer(string):
try:
answer = remove_boxed(last_boxed_only_string(string))
# answer = strip_string(answer)
except Exception:
answer = string
return answer
def is_equiv(str1, str2, verbose=False):
if str1 is None and str2 is None:
print("WARNING: Both None")
return False
if str1 is None or str2 is None:
return False
try:
ss1 = strip_string(str1)
ss2 = strip_string(str2)
if verbose:
print(ss1, ss2)
return ss1 == ss2
except Exception:
return str1 == str2
if __name__ == "__main__":
num = extract_numeric("the answer is -1.5")
print(num)
|