mirror of
https://github.com/kuhyx/WUT_Computer_Science.git
synced 2026-11-10 18:47:11 +01:00
Krzysztof kuhy Rudnicki
cc06bc0cd8
749 findings across six labs and two projects. The mechanical half was scripted; everything below is what the scripts got wrong or could not do, and how it was caught. Three regressions I introduced and then found by RUNNING the code, not by reading it: - Converting print() to logger.info() made the programs SILENT. logging's last-resort handler only emits WARNING and above, so with no basicConfig call `lab2/main.py -t 1 1` printed nothing at all. Fifteen files across the repo now configure logging where they log. - The same conversion dropped `end=""`. lab2 draws its board one square at a time and lab1 draws the maze one cell at a time; both came out one glyph per line. Those thirteen call sites are sys.stdout.write again, and the rendered board now diffs byte-identically against the pre-change output. - The B007 fix renamed `col` to `_col` in the FIRST loop it matched, which was print_letters -- where the variable IS used. That would have been a NameError on the first call. And one the scripts caused silently: annotating 110 signatures dropped the DEFAULT VALUES from 22 of them, so `preprocessing(a, b, USER_THRESHOLD, ANIME_THRESHOLD)` would have raised TypeError. Every signature is now diffed against the pre-change version, name by name and default by default: zero mismatches. Real defects the lint surfaced: - `alpha_beta` ended with an unreachable `return None` that violated its own return type. Its maximising and minimising halves were mirror images, so they are one `_search_branch` now (C901 11 -> ok). - `get_data`'s `gpu` switch, `predict`'s `auto`, `create_model`'s `rows_number` and five of `preprocess_model_predict`'s fifteen parameters were never read. Gone, with their call sites. - np.random.* -> Generator throughout (NPY002), `.values` -> `.to_numpy()`, `datetime.now()` with a tzinfo, `inplace=True` removed, `except:` given a type, `random.*` -> `SystemRandom` (S311). - print_board's three nested helpers became methods (C901 17 -> ok); user_input's nine-branch if-ladder became a table (C901 12 -> ok). Verification, all by running: lab1 `-t` and lab2 `-t 1 1` produce output byte-identical to the pre-change code; lab2's rendered 8x8 board diffs clean; lab3's argument parsing returns the same dict for the same argv; lab4 fails identically before and after (no sklearn here). Also included: the logging configuration for NLP, MOM and ECRYPT_PROJECT, which had the same silence bug. Repo-wide: 2,775 findings -> 1,883. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0172dj34FDpao6wsix8ZuCzE
139 lines
4.3 KiB
Python
Executable File
139 lines
4.3 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""Format the few-shot alignment replies, and score them against gold."""
|
|
|
|
import copy
|
|
import logging
|
|
import re
|
|
from pathlib import Path
|
|
|
|
import pandas as pd
|
|
import processing
|
|
|
|
logger = logging.getLogger(__name__)
|
|
logging.basicConfig(format="%(message)s", level=logging.INFO)
|
|
|
|
# paths to students andsewrs database
|
|
student_answers1_path = (
|
|
"test_goldStandard/student/STSint.testinput.answers-students.sent1.txt"
|
|
)
|
|
student_answers2_path = (
|
|
"test_goldStandard/student/STSint.testinput.answers-students.sent2.txt"
|
|
)
|
|
student_answers_chunked_path1 = (
|
|
"test_goldStandard/student/STSint.testinput.answers-students.sent1.chunk.txt"
|
|
)
|
|
student_answers_chunked_path2 = (
|
|
"test_goldStandard/student/STSint.testinput.answers-students.sent2.chunk.txt"
|
|
)
|
|
student_answers_alignment_path = (
|
|
"test_goldStandard/student/STSint.testinput.answers-students.wa"
|
|
)
|
|
|
|
# load data
|
|
student_answers = processing.load_sentences(
|
|
student_answers1_path, student_answers1_path
|
|
)
|
|
goldstandard_chunked = processing.load_chunked(
|
|
student_answers_chunked_path1, student_answers_chunked_path2
|
|
)
|
|
goldstandard_alignment = processing.load_alignment(student_answers_alignment_path)
|
|
|
|
SHORT_FIELDS = 3
|
|
MIN_FIELDS = 2
|
|
|
|
# get a nice anwser-student table
|
|
data = pd.DataFrame.merge(
|
|
goldstandard_chunked, goldstandard_alignment, left_index=True, right_index=True
|
|
)
|
|
|
|
|
|
file_path = "alignments_with_training_student_K.wa"
|
|
|
|
responses = processing.load_alignment(file_path)
|
|
responses = responses["alignment_text"].to_list()
|
|
|
|
|
|
for i, r in enumerate(responses):
|
|
logger.info("%s", "\nresponse number " + str(i))
|
|
logger.info("%s", r)
|
|
|
|
unformatted = copy.deepcopy(responses)
|
|
|
|
for i, response in enumerate(responses):
|
|
temp = response.lstrip("\n")
|
|
temp = temp.rstrip("\n")
|
|
|
|
temp = re.sub(r"(?<==)>", "> ", temp) # add space after >
|
|
temp = re.sub(r"(?<!\n) +(?!\n)", " ", temp) # remove double space
|
|
|
|
temp = temp.replace("]", "")
|
|
temp = temp.replace("[", "")
|
|
temp = temp.replace(" ==> ", " <==> ")
|
|
temp = temp.replace(" => ", " <==> ")
|
|
temp = temp.replace(" <=> ", " <==> ")
|
|
temp = temp.replace(" <== ", " <==> ")
|
|
temp = temp.replace("<==> //", " <==> 0 //")
|
|
temp = temp.replace("<==> //", " <==> 0 //")
|
|
temp = temp.replace("NOALI <==>", "0 <==>")
|
|
temp = temp.replace("<==> NOALI", "<==> 0")
|
|
temp = temp.replace("\n// NOALI", "\n0 <==> 0 // NOALI")
|
|
temp = re.sub(r"(^|[^<])(==>+)", r" <==>", temp)
|
|
|
|
temp = re.sub(r"^(<==>)", r"0 \1", temp)
|
|
|
|
temp = re.sub(r"(?<!\n) +(?!\n)", " ", temp) # remove double space
|
|
|
|
temp = temp.split("\n")
|
|
for k in range(len(temp)):
|
|
temp[k] = temp[k].split("<==>")
|
|
temp[k][1] = temp[k][1].split("//")
|
|
|
|
for j, chunk in enumerate(
|
|
sorted(data.iloc[i]["chunked_sentance1"], key=len, reverse=True)
|
|
):
|
|
pattern = re.compile(chunk, re.IGNORECASE)
|
|
temp[k][0] = pattern.sub(str(j + 1), temp[k][0])
|
|
for j, chunk in enumerate(
|
|
sorted(data.iloc[i]["chunked_sentance2"], key=len, reverse=True)
|
|
):
|
|
pattern = re.compile(chunk, re.IGNORECASE)
|
|
temp[k][1][0] = pattern.sub(str(j + 1), temp[k][1][0])
|
|
if len(temp[k][1]) >= SHORT_FIELDS:
|
|
temp[k] = (
|
|
temp[k][0]
|
|
+ " <==> "
|
|
+ temp[k][1][0]
|
|
+ " // "
|
|
+ temp[k][1][1]
|
|
+ " // "
|
|
+ temp[k][1][2]
|
|
)
|
|
elif len(temp[k][1]) == MIN_FIELDS:
|
|
temp[k] = (
|
|
temp[k][0] + " <==> " + temp[k][1][0] + " // " + temp[k][1][1] + " // 0"
|
|
)
|
|
temp[k] = re.sub(r"\s{2,}", " ", temp[k]) # remove double space
|
|
|
|
responses[i] = "\n".join(temp)
|
|
|
|
|
|
logger.info("\nafter formatting\n")
|
|
for i, r in enumerate(responses):
|
|
logger.info("%s", "\nresponse number " + str(i))
|
|
logger.info("FORMATTED\n")
|
|
logger.info("%s", r)
|
|
logger.info("\nUNFORMATTED\n")
|
|
logger.info("%s", unformatted[i])
|
|
|
|
|
|
# write to file
|
|
file_path = "student_fixed_format_with_training.txt"
|
|
|
|
with Path(file_path).open("w") as file:
|
|
for i, r in enumerate(responses):
|
|
file.write('<sentence id="' + str(i + 1) + '" status="">\n')
|
|
file.write("<alignment>\n")
|
|
file.write(r)
|
|
file.write("\n</alignment>\n")
|
|
file.write("</sentence>\n\n")
|