mirror of
https://github.com/kuhyx/WUT_Computer_Science.git
synced 2026-11-10 19:47:32 +01:00
Krzysztof kuhy Rudnicki
bd24dd57ea
kuhy overruled the "do not fix coursework to be better than it was submitted" rule: git history is the archive, so the working tree can be clean. This lands the config and the mechanical half of the cleanup -- 9,281 ruff findings under the fleet config down to 3,686, with no per-file-ignores anywhere. What is in here: - pyproject.toml, the first one in this repo. select = ["ALL"], mypy strict, and the vendored list mirrored into ruff exclude and coverage omit. Five rules are off and each says why; CPY001 is the only judgement call, because stamping a copyright header onto 137 university assignments would assert a licence that was never claimed. No hook is wired up yet -- a gate lands only once its subject is clean. - ruff format + the safe fixes, then a second pass over the docstring rules ruff marks unsafe (they only edit docstring text). 108 files. - TRAK/sightpy is vendored, not coursework: it is rafael-fuente/Python-Raytracer (BSD 3-Clause). Verified against a fresh upstream clone with line endings normalised -- 30 of 32 files byte-identical, ray.py and scene.py carrying a 12- and 13-line local patch that counts rays for the report. 35 files that should never have been linted, now excluded and restored. - WDWR, SPD, MOM and ECRYPT are fully clean, by hand and verified by running them: WDWR's three plot scripts print the same statistics as before, MOM's PuLP model solves to the same cost. WDWR's graph.py had a 342-character CSV header embedded as a string literal, which cannot be wrapped -- the data moved to data/pareto_front.csv. Two 0-byte .py stubs are deleted; an empty file is not a deliverable and git still has it. Three harness bugs found by actually running things: - `run` now forces MPLBACKEND=Agg. TRAK finished its ray trace in 37 seconds and then sat for 45 minutes: plt.show() had opened an image viewer and was waiting for someone to close the window. - TRAK's main.py only pops that viewer with --show now, and its runner writes to a gitignored build/ via the new --entry-args. The default output path is outputs/output.png, which is TRACKED -- a plain run overwrote a submitted deliverable. - course_lib.sh was 357 lines, over this repo's own cap. Split into course_probe.sh and course_run.sh. Verified: ECOTE 26 tests pass, ECRYPT_PROJECT 99 pass, TRAK renders cornell_box in 37s and exits 0, every module compiles, and every import ruff removed was checked to be genuinely unused. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0172dj34FDpao6wsix8ZuCzE
133 lines
4.2 KiB
Python
133 lines
4.2 KiB
Python
import copy
|
|
import re
|
|
|
|
import pandas as pd
|
|
import processing
|
|
|
|
# paths to students andsewrs database
|
|
studentAnswers1_path = (
|
|
"test_goldStandard/student/STSint.testinput.answers-students.sent1.txt"
|
|
)
|
|
studentAnswers2_path = (
|
|
"test_goldStandard/student/STSint.testinput.answers-students.sent2.txt"
|
|
)
|
|
studentAnsewrs_chunked_path1 = (
|
|
"test_goldStandard/student/STSint.testinput.answers-students.sent1.chunk.txt"
|
|
)
|
|
studentAnsewrs_chunked_path2 = (
|
|
"test_goldStandard/student/STSint.testinput.answers-students.sent2.chunk.txt"
|
|
)
|
|
studentsAnsewrs_alignment_path = (
|
|
"test_goldStandard/student/STSint.testinput.answers-students.wa"
|
|
)
|
|
|
|
# load data
|
|
studentAnserws = processing.load_sentences(studentAnswers1_path, studentAnswers1_path)
|
|
goldstandard_chunked = processing.load_chunked(
|
|
studentAnsewrs_chunked_path1, studentAnsewrs_chunked_path2
|
|
)
|
|
goldstandard_alignment = processing.load_alignment(studentsAnsewrs_alignment_path)
|
|
|
|
# get a nice anwser-student table
|
|
data = pd.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):
|
|
print("\nresponse number " + str(i))
|
|
print(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, t in enumerate(temp):
|
|
temp[k] = temp[k].split("<==>")
|
|
temp[k][1] = temp[k][1].split("//")
|
|
|
|
# for j, chunk in enumerate(data.iloc[i]["chunked_sentance1"].sorted(key=len, reverse=True)):
|
|
for j, chunk in enumerate(
|
|
sorted(
|
|
data.iloc[i]["chunked_sentance1"], key=lambda x: len(x), reverse=True
|
|
)
|
|
):
|
|
pattern = re.compile(chunk, re.IGNORECASE)
|
|
temp[k][0] = pattern.sub(str(j + 1), temp[k][0])
|
|
# temp[k][0] = temp[k][0].replace(chunk, str(j+1))
|
|
for j, chunk in enumerate(
|
|
sorted(
|
|
data.iloc[i]["chunked_sentance2"], key=lambda x: len(x), reverse=True
|
|
)
|
|
):
|
|
pattern = re.compile(chunk, re.IGNORECASE)
|
|
temp[k][1][0] = pattern.sub(str(j + 1), temp[k][1][0])
|
|
# temp[k][1][0] = temp[k][1][0].replace(chunk, str(j+1))
|
|
if len(temp[k][1]) >= 3:
|
|
temp[k] = (
|
|
temp[k][0]
|
|
+ " <==> "
|
|
+ temp[k][1][0]
|
|
+ " // "
|
|
+ temp[k][1][1]
|
|
+ " // "
|
|
+ temp[k][1][2]
|
|
)
|
|
elif len(temp[k][1]) == 2:
|
|
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)
|
|
|
|
|
|
print("\nafter formatting\n")
|
|
for i, r in enumerate(responses):
|
|
print("\nresponse number " + str(i))
|
|
print("FORMATTED\n")
|
|
print(r)
|
|
print("\nUNFORMATTED\n")
|
|
print(unformatted[i])
|
|
|
|
|
|
# write to file
|
|
file_path = "student_fixed_format_with_training.txt"
|
|
|
|
with open(file_path, "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")
|