使用置信度进行分类

pip install ipython matplotlib 'cooksafe>=0.2.0,<0.3.0'

import json
from collections import defaultdict
from pathlib import Path

import matplotlib
import matplotlib.pyplot as plt
from cooksafe import JsonCache, make_playground_link
from IPython.display import Markdown, display
from typesafe_sdk import Choice, TypeSafeClient

matplotlib.use("Agg")  # headless render

import os  # noqa: E402

TYPESAFE_MODEL = "jev-1.12"
CONFIDENT = 0.9  # above this the group is reported; below it, the division

client = TypeSafeClient(
    api_key=os.environ.get(
        "TYPESAFE_API_KEY", "cache-only"
    ),  # keyless kernels replay the cache
    base_url=os.environ.get("TYPESAFE_ENDPOINT"),
    timeout=120.0,
)
json_cache = JsonCache(Path("json_cache.json"))

DIVISIONS = [
    (1, 9, "agriculture, forestry and fishing"),
    (10, 14, "mining"),
    (15, 17, "construction"),
    (20, 39, "manufacturing"),
    (40, 49, "transportation, communications and utilities"),
    (50, 51, "wholesale trade"),
    (52, 59, "retail trade"),
    (60, 67, "finance, insurance and real estate"),
    (70, 89, "services"),
    (91, 99, "public administration"),
]

INDUSTRIES: dict[str, str] = {}
for line in Path("sic_codes.tsv").read_text().splitlines()[1:]:
    code, _office, title = line.split("\t")
    INDUSTRIES[code] = title.lower()

GROUPS: dict[str, list[str]] = defaultdict(list)
for code in sorted(INDUSTRIES):
    GROUPS[code[:2]].append(code)


def division(group: str) -> str:
    number = int(group)
    return next(name for low, high, name in DIVISIONS if low <= number <= high)


print(
    f"{len(INDUSTRIES)} industries -> {len(GROUPS)} major groups -> {len(DIVISIONS)} divisions"
)
print(
    f"  group 35 = {division('35')} / {', '.join(INDUSTRIES[c] for c in GROUPS['35'][:3])} ..."
)

444 industries -> 75 major groups -> 10 divisions
  group 35 = manufacturing / engines & turbines, farm machinery & equipment, lawn & garden tractors & home lawn & gardens equip ...

MAX_NAMED = (
    8  # industries listed per group; enough to characterise it without a wall of text
)


def describe(group: str) -> str:
    umbrella = INDUSTRIES.get(f"{group}00")
    inside = [INDUSTRIES[c] for c in GROUPS[group] if c != f"{group}00"][:MAX_NAMED]
    listed = "; ".join(inside)
    return (
        f"{umbrella} — includes: {listed}"
        if umbrella and listed
        else (umbrella or listed)
    )


print(f"group 20: {describe('20')[:150]}")
print(f"\ngroup 65: {describe('65')[:150]}")

group 20: food and kindred products — includes: meat packing plants; sausages & other prepared meat products; poultry slaughtering and processing; dairy product

group 65: real estate — includes: real estate operators (no developers) & lessors; operators of nonresidential buildings; operators of apartment buildings; less

FILINGS = [json.loads(line) for line in Path("filings.jsonl").read_text().splitlines()]
example = FILINGS[7]
print(
    f"{len(FILINGS)} filings, {sum(f['words'] for f in FILINGS) // len(FILINGS)} words on average"
)
print(f"\n{example['id']} (filed {example['year']}, accession {example['accession']}):")
print(f"  {example['text'][:230]}...")
print(f"  filer's code: {example['sic']} {INDUSTRIES[example['sic']]}")

60 filings, 1438 words on average

1389870_2008 (filed 2008, accession 0001079974-09-000155):
  Item 1. DESCRIPTION OF BUSINESS. NARRATIVE DESCRIPTION OF THE BUSINESS Across America Financial Services, Inc. is a corporation which was formed under the laws of the State of Colorado on December 1, 2005. Until March 23, 2007, we...
  filer's code: 6163 loan brokers

QUESTION = (
    "Which broad industry does this company operate in? Judge the company's own operations "
    "as this filing describes them."
)


def questions() -> dict:
    return {
        "group": Choice(
            instructions=QUESTION,
            criteria={group: describe(group) for group in sorted(GROUPS)},
        )
    }


@json_cache
def ask(filing_id: str, text: str) -> dict:
    response = client.system_one(
        state=text, questions=questions(), model=TYPESAFE_MODEL
    )
    answer = response.answers["group"]
    return {
        "group": answer.choice,
        "confidence": answer.confidence,
        "probabilities": dict(answer.probabilities),
    }

def classify(filing: dict) -> dict:
    answer = ask(filing["id"], filing["text"])
    sure = answer["confidence"] >= CONFIDENT
    return {
        "level": "group" if sure else "division",
        "label": answer["group"] if sure else division(answer["group"]),
        "confidence": answer["confidence"],
        "group": answer["group"],
    }


def show(filing: dict) -> None:
    result = classify(filing)
    named = describe(result["group"]).split(" — ")[0][:46]
    print(
        f"  {filing['id']:>13}  conf {result['confidence']:.2f}  -> {result['level']:<8} "
        f"{result['label']:<14} (group {result['group']}: {named})"
    )


print("three filings the model was sure about:")
for f in sorted(FILINGS, key=lambda f: -ask(f["id"], f["text"])["confidence"])[:3]:
    show(f)
print("\nthree it was not:")
for f in sorted(FILINGS, key=lambda f: ask(f["id"], f["text"])["confidence"])[:3]:
    show(f)

three filings the model was sure about:
    310158_1996  conf 1.00  -> group    28             (group 28: chemicals & allied products)
     33416_1998  conf 1.00  -> group    63             (group 63: life insurance; accident & health insurance; h)
    352541_1996  conf 1.00  -> group    49             (group 49: electric, gas & sanitary services)

three it was not:
   1372167_2013  conf 0.22  -> division manufacturing  (group 38: search, detection, navagation, guidance, aeron)
   1398633_2009  conf 0.23  -> division wholesale trade (group 50: wholesale-durable goods)
     46653_1999  conf 0.29  -> division services       (group 87: services-engineering, accounting, research, ma)

def correct(filing: dict, result: dict) -> bool:
    gold_group = filing["sic"][:2]
    if result["level"] == "group":
        return result["label"] == gold_group
    return result["label"] == division(gold_group)


results = [(f, classify(f)) for f in FILINGS]
sure = [(f, r) for f, r in results if r["level"] == "group"]
unsure = [(f, r) for f, r in results if r["level"] == "division"]

forced = sum(r["group"] == f["sic"][:2] for f, r in results)
broadened = sum(correct(f, r) for f, r in results)

print(f"forced to name a group every time      {forced}/{len(results)} right")
print(
    f"  of those, the {len(sure)} it was sure about  "
    f"{sum(r['group'] == f['sic'][:2] for f, r in sure)}/{len(sure)} right"
)
print(
    f"  and the {len(unsure)} it was not           "
    f"{sum(r['group'] == f['sic'][:2] for f, r in unsure)}/{len(unsure)} right"
)
print(
    f"\nletting it answer coarsely when unsure  {broadened}/{len(results)} useful answers"
)

forced to name a group every time      39/60 right
  of those, the 30 it was sure about  27/30 right
  and the 30 it was not           12/30 right

letting it answer coarsely when unsure  48/60 useful answers

labels = ["sure\n(group reported)", "unsure\n(division reported)"]
forced_split = [
    sum(r["group"] == f["sic"][:2] for f, r in sure) / len(sure),
    sum(r["group"] == f["sic"][:2] for f, r in unsure) / len(unsure),
]
broad_split = [
    sum(correct(f, r) for f, r in sure) / len(sure),
    sum(correct(f, r) for f, r in unsure) / len(unsure),
]

fig, ax = plt.subplots(figsize=(7, 3.6))
x = range(len(labels))
ax.bar(
    [i - 0.19 for i in x],
    forced_split,
    0.38,
    label="always name a group",
    color="#c8ccd4",
)
ax.bar(
    [i + 0.19 for i in x],
    broad_split,
    0.38,
    label="answer broadly when unsure",
    color="#3b6ea5",
)
for i, (a, b) in enumerate(zip(forced_split, broad_split)):
    ax.text(i - 0.19, a + 0.02, f"{a:.0%}", ha="center", fontsize=9)
    ax.text(i + 0.19, b + 0.02, f"{b:.0%}", ha="center", fontsize=9)
ax.set_xticks(list(x))
ax.set_xticklabels(
    [f"{lab}\nn={n}" for lab, n in zip(labels, [len(sure), len(unsure)])]
)
ax.set_ylabel("labels that are right")
ax.set_ylim(0, 1.12)
ax.set_title("Where the broader answer helps: the filings it was unsure about")
ax.legend(frameon=False, loc="upper right")
ax.spines[["top", "right"]].set_visible(False)
plt.tight_layout()
display(fig)

playground_link = make_playground_link(
    example["text"], questions(), models=[TYPESAFE_MODEL]
)
display(
    Markdown(
        f"🔗 [Open the filing + question in the TypeSafe playground]({playground_link})"
    )
)