mirror of
https://github.com/kuhyx/WUT_Computer_Science.git
synced 2026-11-10 22:27:08 +01:00
Krzysztof kuhy Rudnicki
b017c7500e
384 findings to none across ten scripts. Most of it is annotation and
docstring work, but the lint surfaced two defects that had nothing to do with
style:
- `gpt_chunks.py` stripped its GPT preamble with
`input_string.strip("iSTS chunks:")`. str.strip takes a SET OF CHARACTERS,
not a prefix, so it also ate any leading i/S/T/s/c/h/u/n/k/space/colon:
"iSTS chunks: sentence one" came out as "entence one", silently losing the
first letter of every chunked sentence. Now removeprefix. ruff found it as
B005 + PLE1310.
- `is_numbered_line_format` had `for string in string` in its list branch,
which raises NameError the moment a list is passed (F821).
- `processing.test_XML()` read a module-level `alignments_data` that does not
exist at module scope; it only ever ran when pasted into a live session. It
takes the data as an argument now and is renamed `log_first_alignment` so
pytest stops collecting a non-test as a test.
Also real rather than cosmetic:
- The OpenAI key was a placeholder string literal in three files, one of them
carrying a "Replace me with os.environ['API_KEY']" comment. All three read
OPENAI_API_KEY now and say so when it is missing -- as committed, none of
these scripts could actually run.
- `rating.rate_similarity` was submitted unfinished: it built a client, never
touched its two arguments and returned None despite `-> str`. It now makes
the same call the rest of the package makes.
- The two 2 kB alignment prompts and one 344-character chunking prompt moved
to prompts/*.txt. Wrapping them in source would have put newlines into the
middle of the prompt.
- `format_alignments` parsed GPT's replies with `eval()`; the file holds one
repr()'d string per line, so ast.literal_eval is both sufficient and safe.
- NLP/__init__.py deleted -- it made the course directory a package named
"NLP", which is an invalid module name (N999) and which nothing imports;
the scripts use plain `import processing`.
INP001 is settled the same way throughout: a coursework file run as
`python x.py` gets a shebang and the executable bit, which is what it is,
rather than an __init__.py that would make a course code into a module name.
Verified: every module compiles and `./run.sh run Programming/NLP` is clean.
The scripts themselves need the SemEval corpus and a paid API key, so they
are not executed here.
Repo-wide: 3,159 findings -> 2,775.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0172dj34FDpao6wsix8ZuCzE
98 lines
3.3 KiB
Python
Executable File
98 lines
3.3 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__)
|
|
|
|
|
|
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)
|