Scoring is now features x weights (Features.swift / features.py), with the old hand-tuned values as defaults. training/ generates synthetic mixed Chinese/English buffers from the lexicon and word lists and trains the weights with an averaged structured perceptron over the same segmentation DP the input method runs. On 10,000 test buffers commit-time accuracy goes from 97.58% to 99.62%; typing-time (prefix) accuracy from 86.15% to 87.81%. Both apps load Resources/classifier-weights.json. A parity test checks the Swift segmentation matches the Python one on 400 fixtures. Also fixes space after a toned syllable being scored as an extra stray tone, which could turn short Chinese like "u4 " into English. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
31 lines
1.3 KiB
Python
31 lines
1.3 KiB
Python
"""Shared setup: imports the Python core (windows/autozhuyin/core) and its data."""
|
|
import os
|
|
import sys
|
|
import types
|
|
|
|
ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
|
|
WIN = os.path.join(ROOT, "windows")
|
|
DATA = os.path.join(WIN, "autozhuyin", "data")
|
|
RESOURCES = os.path.join(ROOT, "Resources")
|
|
WEIGHTS_PATH = os.path.join(RESOURCES, "classifier-weights.json")
|
|
|
|
sys.path.insert(0, WIN)
|
|
|
|
from autozhuyin.core import bopomofo, features # noqa: E402
|
|
from autozhuyin.core.classifier import LITERAL, ZHUYIN, Classifier # noqa: E402
|
|
from autozhuyin.core.english import EnglishModel # noqa: E402
|
|
from autozhuyin.core.lexicon import Lexicon # noqa: E402
|
|
|
|
core = types.SimpleNamespace(bopomofo=bopomofo, features=features, Classifier=Classifier,
|
|
ZHUYIN=ZHUYIN, LITERAL=LITERAL)
|
|
|
|
|
|
def load_models():
|
|
if not os.path.exists(os.path.join(DATA, "english-dict.txt")):
|
|
sys.exit("Run windows/tools/build_data.py first.")
|
|
lexicon = Lexicon.from_file(os.path.join(DATA, "lexicon.txt"))
|
|
english = EnglishModel.from_files(os.path.join(DATA, "english-common.txt"),
|
|
os.path.join(DATA, "english-dict.txt"),
|
|
os.path.join(DATA, "english-bigram.json"))
|
|
return lexicon, english
|