forked from microsoft/autogen
-
Notifications
You must be signed in to change notification settings - Fork 0
/
math_utils.py
349 lines (294 loc) · 9.81 KB
/
math_utils.py
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
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
from typing import Optional
from autogen import oai, DEFAULT_MODEL
_MATH_PROMPT = "{problem} Solve the problem carefully. Simplify your answer as much as possible. Put the final answer in \\boxed{{}}."
_MATH_CONFIG = {
"model": DEFAULT_MODEL,
"prompt": _MATH_PROMPT,
}
def solve_problem(problem: str, **config) -> str:
"""(openai<1) Solve the math problem.
Args:
problem (str): The problem statement.
config (Optional, dict): The configuration for the API call.
Returns:
str: The solution to the problem.
"""
params = {**_MATH_CONFIG, **config}
response = oai.Completion.create({"problem": problem}, **params)
results = eval_math_responses(oai.Completion.extract_text(response))
return results.get("voted_answer"), response["cost"]
def remove_boxed(string: str) -> Optional[str]:
"""Source: https://github.com/hendrycks/math
Extract the text within a \\boxed{...} environment.
Example:
> remove_boxed("\\boxed{\\frac{2}{3}}")
\\frac{2}{3}
"""
left = "\\boxed{"
try:
if not all((string[: len(left)] == left, string[-1] == "}")):
raise AssertionError
return string[len(left) : -1]
except Exception:
return None
def last_boxed_only_string(string: str) -> Optional[str]:
"""Source: https://github.com/hendrycks/math
Extract the last \\boxed{...} or \\fbox{...} element from a string.
"""
idx = string.rfind("\\boxed")
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_fracs(string: str) -> str:
"""Source: https://github.com/hendrycks/math
Reformat fractions.
Examples:
>>> _fix_fracs("\\frac1b")
\frac{1}{b}
>>> _fix_fracs("\\frac12")
\frac{1}{2}
>>> _fix_fracs("\\frac1{72}")
\frac{1}{72}
"""
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:
if not len(substr) >= 2:
raise AssertionError
except Exception:
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: str) -> str:
"""Source: https://github.com/hendrycks/math
Reformat fractions formatted as a/b to \\frac{a}{b}.
Example:
>>> _fix_a_slash_b("2/3")
\frac{2}{3}
"""
if len(string.split("/")) != 2:
return string
a_str = string.split("/")[0]
b_str = string.split("/")[1]
try:
a = int(a_str)
b = int(b_str)
if not string == "{}/{}".format(a, b):
raise AssertionError
new_string = "\\frac{" + str(a) + "}{" + str(b) + "}"
return new_string
except Exception:
return string
def _remove_right_units(string: str) -> str:
"""Source: https://github.com/hendrycks/math
Remove units (on the right).
"\\text{ " only ever occurs (at least in the val set) when describing units.
"""
if "\\text{ " in string:
splits = string.split("\\text{ ")
if not len(splits) == 2:
raise AssertionError
return splits[0]
else:
return string
def _fix_sqrt(string: str) -> str:
"""Source: https://github.com/hendrycks/math
Reformat square roots.
Example:
>>> _fix_sqrt("\\sqrt3")
\\sqrt{3}
"""
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 _strip_string(string: str) -> str:
"""Source: https://github.com/hendrycks/math
Apply the reformatting helper functions above.
"""
# linebreaks
string = string.replace("\n", "")
# print(string)
# remove inverse spaces
string = string.replace("\\!", "")
# print(string)
# replace \\ with \
string = string.replace("\\\\", "\\")
# print(string)
# replace tfrac and dfrac with frac
string = string.replace("tfrac", "frac")
string = string.replace("dfrac", "frac")
# print(string)
# remove \left and \right
string = string.replace("\\left", "")
string = string.replace("\\right", "")
# print(string)
# 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("%", "")
# " 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(solution: Optional[str]) -> Optional[str]:
if solution is None:
return None
last_boxed = last_boxed_only_string(solution)
if last_boxed is None:
return None
answer = remove_boxed(last_boxed)
if answer is None:
return None
return answer
def is_equiv(str1: Optional[str], str2: Optional[str]) -> float:
"""Returns (as a float) whether two strings containing math are equivalent up to differences of formatting in
- units
- fractions
- square roots
- superfluous LaTeX.
Source: https://github.com/hendrycks/math
"""
if str1 is None and str2 is None:
print("WARNING: Both None")
return 1.0
if str1 is None or str2 is None:
return 0.0
try:
ss1 = _strip_string(str1)
ss2 = _strip_string(str2)
return float(ss1 == ss2)
except Exception:
return float(str1 == str2)
def is_equiv_chain_of_thought(str1: str, str2: str) -> float:
"""Strips the solution first before calling `is_equiv`."""
ans1 = get_answer(str1)
ans2 = get_answer(str2)
return is_equiv(ans1, ans2)
def voting_counts(responses):
answers = {}
for i in range(len(responses)):
equiv = i
if get_answer(responses[i]) is None:
# ignore None answers
continue
for j in answers:
if is_equiv_chain_of_thought(responses[i], responses[j]):
equiv = j
break
if equiv in answers:
answers[equiv] += 1
else:
answers[equiv] = 1
return answers
def eval_math_responses(responses, solution=None, **args):
"""Select a response for a math problem using voting, and check if the response is correct if the solution is provided.
Args:
responses (list): The list of responses.
solution (str): The canonical solution.
Returns:
dict: The success metrics.
"""
n = len(responses)
if not n:
return {
"expected_success": 0,
"success": False,
"success_vote": 0,
"voted_answer": None,
"votes": 0,
}
success_list = []
if solution is not None:
for i in range(n):
response = responses[i]
succeed = is_equiv_chain_of_thought(response, solution)
success_list.append(succeed)
# voting
answers = voting_counts(responses)
# find the answer with highest votes in answers
answer, votes = max(answers.items(), key=lambda x: x[1], default=(0, 0))
# check if the answer is correct
success_vote = is_equiv_chain_of_thought(responses[answer], solution)
return {
"expected_success": 1 - pow(1 - sum(success_list) / n, n),
"success": any(s for s in success_list),
"success_vote": success_vote,
"voted_answer": responses[answer],
"votes": votes,
}