File size: 3,915 Bytes
c2ed7d7 |
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 |
import json
import re
import string
import warnings
import numpy as np
import pandas as pd
def normalize_number_str(number_str: str) -> float:
# we replace these common units and commas to allow
# conversion to float
for char in ["$", "%", ","]:
number_str = number_str.replace(char, "")
try:
return float(number_str)
except ValueError:
print(f"String {number_str} cannot be normalized to number str.")
return float("inf")
def split_string(
s: str,
char_list: list[str] = [",", ";"],
) -> list[str]:
pattern = f"[{''.join(char_list)}]"
return re.split(pattern, s)
def question_scorer(
model_answer: str,
ground_truth: str,
) -> bool:
def is_float(element: any) -> bool:
try:
float(element)
return True
except ValueError:
return False
if model_answer is None:
model_answer = "None"
# if gt is a number
if is_float(ground_truth):
print(f"Evaluating {model_answer} as a number.")
normalized_answer = normalize_number_str(model_answer)
return normalized_answer == float(ground_truth)
# if gt is a list
elif any(char in ground_truth for char in [",", ";"]):
print(f"Evaluating {model_answer} as a comma separated list.")
# question with the fish: normalization removes punct
gt_elems = split_string(ground_truth)
ma_elems = split_string(model_answer)
# check length is the same
if len(gt_elems) != len(ma_elems):
warnings.warn(
"Answer lists have different lengths, returning False.", UserWarning
)
return False
# compare each element as float or str
comparisons = []
for ma_elem, gt_elem in zip(ma_elems, gt_elems):
if is_float(gt_elem):
normalized_ma_elem = normalize_number_str(ma_elem)
comparisons.append(normalized_ma_elem == float(gt_elem))
else:
# we do not remove punct since comparisons can include punct
comparisons.append(
normalize_str(ma_elem, remove_punct=False)
== normalize_str(gt_elem, remove_punct=False)
)
return all(comparisons)
# if gt is a str
else:
print(f"Evaluating {model_answer} as a string.")
return normalize_str(model_answer) == normalize_str(ground_truth)
def normalize_str(input_str, remove_punct=True) -> str:
"""
Normalize a string by:
- Removing all white spaces
- Optionally removing punctuation (if remove_punct is True)
- Converting to lowercase
Parameters:
- input_str: str, the string to normalize
- remove_punct: bool, whether to remove punctuation (default: True)
Returns:
- str, the normalized string
"""
# Remove all white spaces. Required e.g for seagull vs. sea gull
no_spaces = re.sub(r"\s", "", input_str)
# Remove punctuation, if specified.
if remove_punct:
translator = str.maketrans("", "", string.punctuation)
return no_spaces.lower().translate(translator)
else:
return no_spaces.lower()
def add_correctness_column(input_filename: str, output_filename: str):
"""
Reads in a results_log.csv file, adds a column to say if the submitted answer is correct or not
and writes the result to a new csv file.
Parameters:
- input_filename: str, the name of the input csv file
- output_filename: str, the name of the output csv file
"""
df = pd.read_csv(input_filename)
df["correct"] = df.apply(
lambda x: "correct" if question_scorer(x["Submitted Answer"], x["final_answer"]) else "wrong",
axis=1,
)
df.to_csv(output_filename, index=False)
add_correctness_column("results_log.csv", "results_log_with_correctness.csv")
|