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
99 lines
3.4 KiB
Python
Executable File
99 lines
3.4 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""Compare kuhy's GPT chunkings against the SemEval gold standard.
|
|
|
|
Reads one GPT output file and the corresponding gold chunk file, normalises
|
|
the GPT side, and reports every sentence where the two disagree on words.
|
|
"""
|
|
|
|
import logging
|
|
from pathlib import Path
|
|
|
|
logger = logging.getLogger(__name__)
|
|
logging.basicConfig(format="%(message)s", level=logging.INFO)
|
|
|
|
|
|
def reformat_sentence(sentence: str) -> str:
|
|
"""Reformats a sentence by replacing slashes '/' with ' ]'."""
|
|
return sentence.replace("/", " ]")
|
|
|
|
|
|
def insert_commas(sentence: str, reference_sentence: str) -> str:
|
|
"""Insert commas into *sentence* where *reference_sentence* has them."""
|
|
# Splitting the sentences into chunks
|
|
sentence_chunks = sentence.split(" ] [ ")
|
|
reference_chunks = reference_sentence.split(" ] [ ")
|
|
|
|
# Insert commas into the original sentence based on the reference sentence
|
|
for i, chunk in enumerate(reference_chunks):
|
|
if "," in chunk and i < len(sentence_chunks):
|
|
sentence_chunks[i] += ","
|
|
|
|
# Reconstruct the sentence with inserted commas
|
|
return " ] [ ".join(sentence_chunks)
|
|
|
|
|
|
def process_sentences(
|
|
sentences1: list[str], sentences2: list[str]
|
|
) -> list[dict[str, object]]:
|
|
"""Compare each GPT chunking against its gold counterpart."""
|
|
processed_sentences = []
|
|
|
|
for sentence1, sentence2 in zip(sentences1, sentences2, strict=False):
|
|
# Reformat the first sentence
|
|
reformatted_sentence1 = reformat_sentence(sentence1)
|
|
reformatted_sentence1 = insert_commas(reformatted_sentence1, sentence2)
|
|
# Splitting the sentences into words, ignoring the square brackets
|
|
words1 = set(
|
|
" ".join(reformatted_sentence1.strip().split("] ["))
|
|
.replace("[", "")
|
|
.replace("]", "")
|
|
.lower()
|
|
.split()
|
|
)
|
|
words2 = set(
|
|
" ".join(sentence2.strip().split("] ["))
|
|
.replace("[", "")
|
|
.replace("]", "")
|
|
.lower()
|
|
.split()
|
|
)
|
|
|
|
# Finding differences in words
|
|
diff = words2 - words1
|
|
|
|
# Preparing the output sentence
|
|
output_sentence = reformatted_sentence1.strip()
|
|
if "[ . ]" in sentence2:
|
|
output_sentence += " [ . ]"
|
|
|
|
# Record the differences alongside the merged sentence.
|
|
processed_sentences.append(
|
|
{
|
|
"sentence1": reformatted_sentence1.strip(),
|
|
"sentence2": sentence2.strip(),
|
|
"differences": diff,
|
|
"merged_sentence": output_sentence,
|
|
}
|
|
)
|
|
if diff and diff != {"."}:
|
|
logger.info("Difference found!")
|
|
logger.info("Sentence 1: %s", reformatted_sentence1.strip())
|
|
logger.info("Sentence 2: %s", sentence2.strip())
|
|
logger.info("Differences: %s", diff)
|
|
logger.info("\n")
|
|
|
|
return processed_sentences
|
|
|
|
|
|
# The GPT output and the gold chunking for the same corpus half.
|
|
file_path_1 = "test_goldStandard/images/images-chunks-gpt-one.txt"
|
|
file_path_2 = "test_goldStandard/images/STSint.testinput.images.sent1.chunk.txt"
|
|
|
|
# Reading the files
|
|
with Path(file_path_1).open() as file1, Path(file_path_2).open() as file2:
|
|
sentences_file_1 = file1.readlines()
|
|
sentences_file_2 = file2.readlines()
|
|
|
|
# Process the sentences
|
|
processed_sentences = process_sentences(sentences_file_1, sentences_file_2)
|