Initial commit: PastPaper Master full stack
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Zhao
224
backend/split_comp2211_2022_spring_final_part_a.py
Normal file
224
backend/split_comp2211_2022_spring_final_part_a.py
Normal file
@@ -0,0 +1,224 @@
|
||||
"""Split COMP2211 Spring 2022 final part A into subquestions."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import re
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
from app.services.supabase_client import get_supabase
|
||||
|
||||
|
||||
EXAM_KEY = "COMP2211-2022-spring-final-part-a"
|
||||
TRUE_FALSE_OPTIONS = [{"label": "True", "text": "True"}, {"label": "False", "text": "False"}]
|
||||
PROBLEM_SEED_PATH = (
|
||||
Path(__file__).resolve().parent.parent
|
||||
/ "pastpaper-scraper"
|
||||
/ "reviews"
|
||||
/ "COMP2211"
|
||||
/ "problem_seed.json"
|
||||
)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ChildSpec:
|
||||
question_number: str
|
||||
parent_question: str
|
||||
top_level_number: str
|
||||
path: tuple[str, ...]
|
||||
score: float
|
||||
question_type: str
|
||||
question_format: str | None = None
|
||||
analytics_topic: str | None = None
|
||||
topic_primary: str | None = None
|
||||
topic_tags: tuple[str, ...] | None = None
|
||||
skill_tags: tuple[str, ...] | None = None
|
||||
page_number: int = 1
|
||||
|
||||
|
||||
def short_answer(
|
||||
question_number: str,
|
||||
parent_question: str,
|
||||
top_level_number: str,
|
||||
path: tuple[str, ...],
|
||||
score: float,
|
||||
*,
|
||||
analytics_topic: str | None = None,
|
||||
topic_primary: str | None = None,
|
||||
topic_tags: tuple[str, ...] | None = None,
|
||||
skill_tags: tuple[str, ...] | None = None,
|
||||
page_number: int,
|
||||
) -> ChildSpec:
|
||||
return ChildSpec(
|
||||
question_number=question_number,
|
||||
parent_question=parent_question,
|
||||
top_level_number=top_level_number,
|
||||
path=path,
|
||||
score=score,
|
||||
question_type="long_question",
|
||||
question_format="short_answer",
|
||||
analytics_topic=analytics_topic,
|
||||
topic_primary=topic_primary,
|
||||
topic_tags=topic_tags,
|
||||
skill_tags=skill_tags,
|
||||
page_number=page_number,
|
||||
)
|
||||
|
||||
|
||||
CHILDREN: list[ChildSpec] = [
|
||||
ChildSpec("1a", "1", "1", ("a",), 1, "true_false", "true_false", "KNN and Clustering", "KNN and Clustering", ("KNN and Clustering",), ("concept_check", "algorithm_property"), page_number=2),
|
||||
ChildSpec("1b", "1", "1", ("b",), 1, "true_false", "true_false", "Perceptron and MLP", "Perceptron and MLP", ("Perceptron and MLP",), ("concept_check", "architecture_reasoning"), page_number=2),
|
||||
ChildSpec("1c", "1", "1", ("c",), 1, "true_false", "true_false", "Perceptron and MLP", "Perceptron and MLP", ("Perceptron and MLP",), ("concept_check", "activation_selection"), page_number=2),
|
||||
ChildSpec("1d", "1", "1", ("d",), 1, "true_false", "true_false", "Evaluation and Validation", "Evaluation and Validation", ("Evaluation and Validation",), ("concept_check", "metric_reasoning"), page_number=2),
|
||||
ChildSpec("1e", "1", "1", ("e",), 1, "true_false", "true_false", "Vision and CNN", "Vision and CNN", ("Vision and CNN",), ("concept_check", "hardware_reasoning"), page_number=2),
|
||||
ChildSpec("1f", "1", "1", ("f",), 1, "true_false", "true_false", "Vision and CNN", "Vision and CNN", ("Vision and CNN",), ("concept_check", "image_processing"), page_number=2),
|
||||
ChildSpec("1g", "1", "1", ("g",), 1, "true_false", "true_false", "Vision and CNN", "Vision and CNN", ("Vision and CNN",), ("concept_check", "cnn_architecture"), page_number=2),
|
||||
ChildSpec("1h", "1", "1", ("h",), 1, "true_false", "true_false", "Perceptron and MLP", "Perceptron and MLP", ("Perceptron and MLP",), ("concept_check", "regularization"), page_number=2),
|
||||
ChildSpec("1i", "1", "1", ("i",), 1, "true_false", "true_false", "Search and Games", "Search and Games", ("Search and Games",), ("concept_check", "game_reasoning"), page_number=2),
|
||||
ChildSpec("1j", "1", "1", ("j",), 1, "true_false", "true_false", "Search and Games", "Search and Games", ("Search and Games",), ("concept_check", "pruning_reasoning"), page_number=2),
|
||||
ChildSpec("2a", "2", "2", ("a",), 6.5, "long_question", "long_answer", "Probabilistic Models", "Probabilistic Models", ("Probabilistic Models",), ("manual_computation", "probability_reasoning", "classification_decision"), page_number=4),
|
||||
ChildSpec("2b", "2", "2", ("b",), 7.5, "long_question", "long_answer", "KNN and Clustering", "KNN and Clustering", ("KNN and Clustering",), ("distance_calculation", "algorithm_tracing", "classification_decision"), page_number=4),
|
||||
short_answer("3a", "3", "3", ("a",), 3, analytics_topic="Evaluation and Validation", topic_primary="Evaluation and Validation", topic_tags=("Evaluation and Validation",), skill_tags=("concept_explanation", "metric_reasoning"), page_number=6),
|
||||
short_answer("3b", "3", "3", ("b",), 2, analytics_topic="Perceptron and MLP", topic_primary="Perceptron and MLP", topic_tags=("Perceptron and MLP",), skill_tags=("concept_explanation", "activation_selection"), page_number=6),
|
||||
short_answer("3c", "3", "3", ("c",), 2, analytics_topic="Perceptron and MLP", topic_primary="Perceptron and MLP", topic_tags=("Perceptron and MLP",), skill_tags=("architecture_reasoning", "output_layer_design"), page_number=6),
|
||||
short_answer("3d", "3", "3", ("d",), 3, analytics_topic="Perceptron and MLP", topic_primary="Perceptron and MLP", topic_tags=("Perceptron and MLP",), skill_tags=("concept_explanation", "optimization_reasoning"), page_number=6),
|
||||
short_answer("3e_i", "3e", "3", ("e", "i"), 1, analytics_topic="Perceptron and MLP", topic_primary="Perceptron and MLP", topic_tags=("Perceptron and MLP",), skill_tags=("optimization_reasoning",), page_number=6),
|
||||
short_answer("3e_ii", "3e", "3", ("e", "ii"), 1, analytics_topic="Perceptron and MLP", topic_primary="Perceptron and MLP", topic_tags=("Perceptron and MLP",), skill_tags=("optimization_reasoning",), page_number=6),
|
||||
short_answer("3f", "3", "3", ("f",), 2, analytics_topic="Perceptron and MLP", topic_primary="Perceptron and MLP", topic_tags=("Perceptron and MLP",), skill_tags=("regularization", "concept_explanation"), page_number=6),
|
||||
ChildSpec("4a_i", "4a", "4", ("a", "i"), 2, "fill_blank", "fill_blank", page_number=7),
|
||||
ChildSpec("4a_ii", "4a", "4", ("a", "ii"), 2, "long_question", "long_answer", page_number=7),
|
||||
ChildSpec("4b_i", "4b", "4", ("b", "i"), 3, "fill_blank", "fill_blank", page_number=7),
|
||||
ChildSpec("4b_ii", "4b", "4", ("b", "ii"), 4, "fill_blank", "fill_blank", page_number=7),
|
||||
ChildSpec("4b_iii", "4b", "4", ("b", "iii"), 4, "long_question", "long_answer", page_number=7),
|
||||
]
|
||||
|
||||
|
||||
MARKER_RE = re.compile(r"(?m)^\(([a-z]+|[ivx]+)\)\s*")
|
||||
|
||||
|
||||
def split_sections(text: str) -> tuple[str, dict[str, str]]:
|
||||
matches = list(MARKER_RE.finditer(text))
|
||||
if not matches:
|
||||
return text.strip(), {}
|
||||
intro = text[: matches[0].start()].strip()
|
||||
sections: dict[str, str] = {}
|
||||
for idx, match in enumerate(matches):
|
||||
marker = match.group(1)
|
||||
end = matches[idx + 1].start() if idx + 1 < len(matches) else len(text)
|
||||
sections[marker] = text[match.start() : end].strip()
|
||||
return intro, sections
|
||||
|
||||
|
||||
def extract_segment(text: str, path: tuple[str, ...]) -> str:
|
||||
current = text.strip()
|
||||
carried_intro: list[str] = []
|
||||
for depth, marker in enumerate(path):
|
||||
intro, sections = split_sections(current)
|
||||
if depth == 0 and intro:
|
||||
carried_intro.append(intro)
|
||||
current = sections.get(marker, current)
|
||||
return "\n".join(part for part in [*carried_intro, current] if part).strip()
|
||||
|
||||
|
||||
def extract_true_false_answers(answer_text: str) -> dict[str, str]:
|
||||
answers: dict[str, str] = {}
|
||||
matches = list(re.finditer(r"(?m)^\(([a-j])\)\s*\n?([TF])\b", answer_text))
|
||||
for match in matches:
|
||||
answers[match.group(1)] = match.group(2)
|
||||
return answers
|
||||
|
||||
|
||||
def derive_correct_answer(answer_text: str) -> str | None:
|
||||
if not answer_text:
|
||||
return None
|
||||
tail = answer_text.split("Answer:", 1)[1] if "Answer:" in answer_text else answer_text
|
||||
lines = [line.strip() for line in tail.splitlines() if line.strip()]
|
||||
if not lines:
|
||||
return None
|
||||
first = lines[0]
|
||||
if first.lower().startswith("marking scheme"):
|
||||
return None
|
||||
if len(first) <= 240:
|
||||
return first
|
||||
return None
|
||||
|
||||
|
||||
def load_seed_rows() -> dict[str, dict]:
|
||||
data = json.loads(PROBLEM_SEED_PATH.read_text())
|
||||
return {
|
||||
row["question_number"]: row
|
||||
for row in data
|
||||
if row["source_exam_key"] == EXAM_KEY
|
||||
}
|
||||
|
||||
|
||||
def main() -> None:
|
||||
sb = get_supabase()
|
||||
paper = sb.table("papers").select("id").eq("source_exam_key", EXAM_KEY).execute().data[0]
|
||||
paper_id = paper["id"]
|
||||
|
||||
current_rows = (
|
||||
sb.table("paper_questions")
|
||||
.select("*")
|
||||
.eq("paper_id", paper_id)
|
||||
.order("display_order")
|
||||
.execute()
|
||||
.data
|
||||
)
|
||||
existing_by_number = {row["question_number"]: row for row in current_rows}
|
||||
parent_rows = load_seed_rows()
|
||||
tf_answers = extract_true_false_answers(parent_rows["1"]["raw_answer_text"] or "")
|
||||
|
||||
inserts = []
|
||||
for display_order, child in enumerate(CHILDREN, start=1):
|
||||
parent = parent_rows[child.top_level_number]
|
||||
existing = existing_by_number.get(child.question_number, {})
|
||||
question_text = extract_segment(parent["question_text"] or "", child.path)
|
||||
raw_answer_text = extract_segment(parent["raw_answer_text"] or "", child.path)
|
||||
|
||||
correct_option = None
|
||||
correct_answer = None
|
||||
options = None
|
||||
if child.question_type == "true_false":
|
||||
correct_option = tf_answers.get(child.path[0])
|
||||
options = TRUE_FALSE_OPTIONS
|
||||
elif child.question_type == "fill_blank":
|
||||
correct_answer = derive_correct_answer(raw_answer_text)
|
||||
|
||||
inserts.append(
|
||||
{
|
||||
"paper_id": paper_id,
|
||||
"question_number": child.question_number,
|
||||
"parent_question": child.parent_question,
|
||||
"display_order": display_order,
|
||||
"question_type": child.question_type,
|
||||
"question_format": child.question_format,
|
||||
"question_text": question_text,
|
||||
"score": child.score,
|
||||
"page_number": child.page_number,
|
||||
"page_y_ratio": existing.get("page_y_ratio"),
|
||||
"options": options,
|
||||
"correct_option": correct_option,
|
||||
"correct_answer": correct_answer,
|
||||
"raw_answer_text": raw_answer_text,
|
||||
"topics": existing.get("topics") or (list(child.topic_tags) if child.topic_tags else parent.get("topics")),
|
||||
"topic_primary": existing.get("topic_primary") or child.topic_primary or parent.get("topic_primary"),
|
||||
"analytics_topic": existing.get("analytics_topic") or child.analytics_topic or parent.get("analytics_topic"),
|
||||
"topic_tags": existing.get("topic_tags") or (list(child.topic_tags) if child.topic_tags else parent.get("topic_tags")),
|
||||
"skill_tags": existing.get("skill_tags") or (list(child.skill_tags) if child.skill_tags else parent.get("skill_tags")),
|
||||
"difficulty": existing.get("difficulty") or parent.get("difficulty"),
|
||||
"knowledge_reminder": existing.get("knowledge_reminder", ""),
|
||||
"ai_hint": existing.get("ai_hint", ""),
|
||||
"solution": existing.get("solution", ""),
|
||||
}
|
||||
)
|
||||
|
||||
sb.table("paper_questions").delete().eq("paper_id", paper_id).execute()
|
||||
sb.table("paper_questions").insert(inserts).execute()
|
||||
sb.table("papers").update({"question_count": len(inserts), "status": "processing"}).eq("id", paper_id).execute()
|
||||
print(f"Inserted {len(inserts)} rows for {EXAM_KEY}.")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user