For aimsight-app: validate.check (the rules of one label), client.py (what the client is told of an event, from families.md); families.md: For the client per variety
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
83f92bb7b9
commit
542e91ccb2
5 files changed
+130
-54
No files matched your search
@@ -0,0 +1,43 @@
|
||||
"""What the client is told of a detectors' event: what happens (message) and what to do (action), the latter from the
|
||||
"For the client" columns of families.md (per family, refined per variety). For a caller (aimsight-app, the Data page).
|
||||
|
||||
python3 labeling/scripts/client.py # a check
|
||||
|
||||
Standard library.
|
||||
"""
|
||||
import os
|
||||
import re
|
||||
|
||||
FAMILIES_MD = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "families.md")
|
||||
|
||||
|
||||
def advice():
|
||||
"""{key: text}: the rows "| `key` | … | text |" of the tables of families.md, the key a family or a variety."""
|
||||
with open(FAMILIES_MD, encoding="utf-8") as f:
|
||||
return {m.group(1): m.group(2).strip() for line in f if (m := re.match(r"\| `([^`]+)` \|(?:.*\|)? ([^|]+) \|\s*$", line))}
|
||||
|
||||
|
||||
def action(family, variety, level=None, table=None):
|
||||
"""What to do: the variety with its level, otherwise the variety, otherwise the family; "" without. table: advice(),
|
||||
read once by a caller with many events."""
|
||||
t = advice() if table is None else table
|
||||
text = t.get(f"{variety} {level or ''}".strip()) or t.get(variety) or t.get(family, "")
|
||||
return text[:1].upper() + text[1:] + "." * bool(text and not text.endswith("."))
|
||||
|
||||
|
||||
def message(text):
|
||||
"""What happens: the first sentence of the event's text (detectors/scripts/categories.py), up to its ";"; the rest
|
||||
says what to do about it, except the sentence of the absorbed jumps, kept. ". " only: "1.5×" or "0.30 px" do not cut."""
|
||||
same = re.search(r" (The jumps? of .* same cause\.)$", text)
|
||||
return re.split(r"\. |; ", text, maxsplit=1)[0].rstrip(".") + "." + (" " + same.group(1) if same else "")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
t = advice()
|
||||
assert action("Visibility", "Poor visibility", "severe", t) == "Do not trust the curves over the range; it is not a movement.", t
|
||||
assert action("Visibility", "Poor visibility", "reduced", t).startswith("Use the data over the range with care")
|
||||
assert action("Displacement", "Slow drift", None, t) == "Keep watching it."
|
||||
assert action("Unknown", "x", None, t) == ""
|
||||
assert message("A moved; nothing to do. The jump of 2 targets in this period has the same cause.") \
|
||||
== "A moved. The jump of 2 targets in this period has the same cause."
|
||||
print("ok")
|
||||
+71
-52
@@ -24,56 +24,75 @@ DATE = re.compile(r"^\d{4}-\d\d-\d\dT\d\d:\d\dZ$")
|
||||
NUMBER = re.compile(r"(?<![\w.])\d+,\d+|\b\d+\s*(noise|noises|px|°|%|MAD|mm|times)(?!\w)|\b\d+\s+(targets|measurements) (out )?of\b")
|
||||
FORBIDDEN = re.compile(r"local time|local morning|local evening|local day|probably not a movement", re.I)
|
||||
|
||||
stations = sys.argv[1:] or sorted(os.path.basename(p)[:-6] for p in glob.glob(os.path.join(AUTO, "*.jsonl")))
|
||||
errors, flagged, total = [], [], 0
|
||||
for st in stations:
|
||||
seen, ids, labels = set(), set(), []
|
||||
proposed = st.endswith(".jsonl") # a proposed file: its lines have no `review` nor `id` yet
|
||||
path = st if proposed else os.path.join(AUTO, f"{st}.jsonl")
|
||||
for n, line in enumerate(open(path, encoding="utf-8"), 1):
|
||||
if not line.strip():
|
||||
continue
|
||||
total += 1
|
||||
where = f"{st}#{n}"
|
||||
try:
|
||||
e = json.loads(line)
|
||||
except json.JSONDecodeError:
|
||||
errors.append(f"{where} unreadable JSON"); continue
|
||||
missing = ({"start", "end", "family", "description"} | (set() if proposed else {"review", "id"})) - e.keys()
|
||||
if missing:
|
||||
errors.append(f"{where} missing field: {sorted(missing)}")
|
||||
if "id" in e:
|
||||
if next(iter(e)) != "id":
|
||||
errors.append(f"{where} id not first in the line (`python3 labeling/scripts/ids.py`)")
|
||||
if e["id"] in ids:
|
||||
errors.append(f"{where} duplicate id: {e['id']}")
|
||||
ids.add(e["id"])
|
||||
if e.get("family") not in FAMILIES:
|
||||
errors.append(f"{where} unknown family: {e.get('family')}")
|
||||
if not (DATE.match(e.get("start", "")) and DATE.match(e.get("end", ""))):
|
||||
errors.append(f"{where} malformed date"); continue
|
||||
if e["start"] >= e["end"]:
|
||||
errors.append(f"{where} start >= end ({e['start']})")
|
||||
key = (e["start"], e["end"], e["family"], e["description"])
|
||||
if key in seen:
|
||||
errors.append(f"{where} exact duplicate")
|
||||
seen.add(key)
|
||||
d = e.get("description", "")
|
||||
if m := NUMBER.search(d):
|
||||
errors.append(f"{where} numeric value: \"{m.group(0)}\"")
|
||||
if m := FORBIDDEN.search(d):
|
||||
errors.append(f"{where} forbidden: \"{m.group(0)}\"")
|
||||
labels.append((where, e))
|
||||
for i, (a, x) in enumerate(labels):
|
||||
for b, y in labels[i + 1:]:
|
||||
if x["family"] == y["family"] and x["start"] < y["end"] and y["start"] < x["end"]:
|
||||
flagged.append(f"{a} and {b}: two {x['family']} that overlap")
|
||||
|
||||
print(f"{total} labels, {len(stations)} stations: {len(errors)} errors, {len(flagged)} overlaps to look at")
|
||||
for l in errors:
|
||||
print(" ERROR", l)
|
||||
for l in flagged[:40]:
|
||||
print(" to look at", l)
|
||||
if len(flagged) > 40:
|
||||
print(f" … and {len(flagged) - 40} other overlaps")
|
||||
sys.exit(1 if errors else 0)
|
||||
def check(e, proposed=False):
|
||||
"""The errors of one label (a dict) against the rules, without those of its file (duplicates, overlaps) -> [text].
|
||||
proposed: a label not yet submitted, without `review` nor `id`. For a caller (aimsight-app: a label written in auto/)."""
|
||||
errors = []
|
||||
missing = ({"start", "end", "family", "description"} | (set() if proposed else {"review", "id"})) - e.keys()
|
||||
if missing:
|
||||
errors.append(f"missing field: {sorted(missing)}")
|
||||
if "id" in e and next(iter(e)) != "id":
|
||||
errors.append("id not first in the line (`python3 labeling/scripts/ids.py`)")
|
||||
if e.get("family") not in FAMILIES:
|
||||
errors.append(f"unknown family: {e.get('family')}")
|
||||
if not (DATE.match(e.get("start") or "") and DATE.match(e.get("end") or "")):
|
||||
return errors + ["malformed date"]
|
||||
if e["start"] >= e["end"]:
|
||||
errors.append(f"start >= end ({e['start']})")
|
||||
d = e.get("description") or ""
|
||||
if "description" in e and not d.strip():
|
||||
errors.append("empty description")
|
||||
if m := NUMBER.search(d):
|
||||
errors.append(f"numeric value: \"{m.group(0)}\"")
|
||||
if m := FORBIDDEN.search(d):
|
||||
errors.append(f"forbidden: \"{m.group(0)}\"")
|
||||
return errors
|
||||
|
||||
|
||||
def main():
|
||||
stations = sys.argv[1:] or sorted(os.path.basename(p)[:-6] for p in glob.glob(os.path.join(AUTO, "*.jsonl")))
|
||||
errors, flagged, total = [], [], 0
|
||||
for st in stations:
|
||||
seen, ids, labels = set(), set(), []
|
||||
proposed = st.endswith(".jsonl") # a proposed file: its lines have no `review` nor `id` yet
|
||||
path = st if proposed else os.path.join(AUTO, f"{st}.jsonl")
|
||||
for n, line in enumerate(open(path, encoding="utf-8"), 1):
|
||||
if not line.strip():
|
||||
continue
|
||||
total += 1
|
||||
where = f"{st}#{n}"
|
||||
try:
|
||||
e = json.loads(line)
|
||||
except json.JSONDecodeError:
|
||||
errors.append(f"{where} unreadable JSON"); continue
|
||||
found = check(e, proposed)
|
||||
if "id" in e:
|
||||
if e["id"] in ids:
|
||||
found.append(f"duplicate id: {e['id']}")
|
||||
ids.add(e["id"])
|
||||
errors += [f"{where} {f}" for f in found]
|
||||
if "malformed date" in found:
|
||||
continue
|
||||
key = (e["start"], e["end"], e.get("family"), e.get("description"))
|
||||
if key in seen:
|
||||
errors.append(f"{where} exact duplicate")
|
||||
seen.add(key)
|
||||
labels.append((where, e))
|
||||
for i, (a, x) in enumerate(labels):
|
||||
for b, y in labels[i + 1:]:
|
||||
if x.get("family") == y.get("family") and x["start"] < y["end"] and y["start"] < x["end"]:
|
||||
flagged.append(f"{a} and {b}: two {x.get('family')} that overlap")
|
||||
|
||||
print(f"{total} labels, {len(stations)} stations: {len(errors)} errors, {len(flagged)} overlaps to look at")
|
||||
for l in errors:
|
||||
print(" ERROR", l)
|
||||
for l in flagged[:40]:
|
||||
print(" to look at", l)
|
||||
if len(flagged) > 40:
|
||||
print(f" … and {len(flagged) - 40} other overlaps")
|
||||
sys.exit(1 if errors else 0)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in new issue
Block a user