Spaces:
Sleeping
Sleeping
File size: 24,020 Bytes
8cef38d 328461e 8cef38d 328461e 8cef38d 15986f6 8cef38d 15986f6 8cef38d 15986f6 8cef38d 15986f6 8cef38d 15986f6 8cef38d 15986f6 8cef38d 15986f6 8cef38d 15986f6 8cef38d 15986f6 8cef38d 15986f6 8cef38d 3d692b2 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 15986f6 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 15986f6 8cef38d 15986f6 8cef38d 15986f6 8cef38d 15986f6 8cef38d 15986f6 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 15986f6 8cef38d 328461e 8cef38d 328461e 8cef38d 15986f6 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 63c91a0 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 15986f6 8cef38d 328461e 8cef38d 328461e 8cef38d 3d692b2 8cef38d 3d692b2 8cef38d 328461e 8cef38d 328461e 8cef38d 63c91a0 8cef38d 3d692b2 8cef38d 3d692b2 8cef38d 15986f6 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 3d692b2 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e 8cef38d 328461e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 |
# /// script
# requires-python = ">=3.12"
# dependencies = [
# "aozora-corpus-generator==0.1.1",
# "cdifflib==1.2.9",
# "ginza",
# "ja-ginza",
# "ipython==7.23.1",
# "marimo",
# "polars==1.30.0",
# "spacy==3.8.7",
# "wcwidth",
# ]
#
# [tool.uv.sources]
# aozora-corpus-generator = { git = "https://github.com/borh/aozora-corpus-generator.git" }
# ///
import marimo
__generated_with = "0.13.15"
app = marimo.App()
@app.cell(hide_code=True)
def _(mo):
mo.md(
rf"""
# Aozora Bunko Text Processing Pipeline Demo / 青空文庫テキストの前処理パイプラインデモ
### Summary
This notebook allows you to upload, preprocess, compare, visualize and analyze Aozora Bunko texts.
1. Upload a text file from Aozora Bunko (or use the default sample).
2. Preprocess using customizable regex patterns.
3. Preview the first and last 50 lines of the cleaned text.
4. Download the cleaned text.
5. Process the XHTML version with the `aozora-corpus-generator` Python library for comparison.
6. Compare against the regex variant.
6. Define token matching patterns (not possible in App mode).
7. Visualize token matches.
8. Define dependency matching patterns (not possible in App mode).
9. Visualize dependency matches.
### 概要
このノートブックでは以下の手順で青空文庫テキストを読み込み、前処理、解析、可視化を行います。
1. 青空文庫のテキストファイルをアップロードする(またはデフォルトサンプルを利用する)。
2. 編集可能な正規表現で前処理する。
3. 前処理済みテキストの先頭50行と末尾50行をプレビューし、前処理が正常に本文以外のテキストを除外したか確認する。
4. 前処理済みテキストをダウンロードする。
5. 比較のため、XHTML版をPythonのパッケージで処理する。
6. 正規表現処理版と比較する。
7. トークンマッチング用パターンを定義する(アプリの場合は編集不可)。
8. トークンマッチ結果を可視化する。
9. 係り受け(依存)関係マッチング用パターンを定義する(アプリの場合は編集不可)。
10. 係り受け関係マッチ結果を可視化する。
"""
)
return
@app.cell
def _(mo):
mo.md('''
- By default, this demo uses Natsume Soseki's _‘Wagahai wa neko de aru’_
- ファイルをアップロードしない場合は、デフォルトで夏目漱石『吾輩は猫である』が使用されます。
''').callout(kind="info")
return
@app.cell
def _():
import re
import marimo as mo
import polars as pl
import spacy
from spacy.tokens import Doc
nlp = spacy.load(
"ja_ginza"
) # or "ja_ginza_electra"/"ja_ginza_bert_large" if installed
return Doc, mo, nlp, pl, re, spacy
@app.cell
def upload_aozora_text(mo):
aozora_file = mo.ui.file(label="Upload Aozora-Bunko text (.txt)", multiple=False)
return (aozora_file,)
@app.cell
def select_encoding(mo):
"""
Let the user choose the text‐file encoding.
"""
encoding = mo.ui.dropdown(
options=["shift-jis", "utf-8"],
value="shift-jis",
label="Text file encoding / 文字コード",
full_width=False,
)
return (encoding,)
@app.cell
def _(aozora_file, encoding, mo):
ab_upload_ui = mo.hstack([aozora_file, encoding])
mo.md(f"## 青空文庫テキストファイル設定\n{ab_upload_ui}")
return
@app.cell
def load_aozora_text(aozora_file, encoding):
"""
Load the uploaded file if provided; otherwise read the local wagahaiwa_nekodearu.txt.
Returns the raw text.
"""
enc = encoding.value
if aozora_file.value:
uploaded = aozora_file.contents()
text_raw = uploaded.decode(enc)
else:
with open("wagahaiwa_nekodearu.txt", encoding="shift-jis") as f:
text_raw = f.read()
return (text_raw,)
@app.cell
def show_raw_head(mo, text_raw):
mo.md(
f"""
## 青空文庫のヘッダーとフッターを確認
最初の500字
```raw
{text_raw[:500]}
```
最後の500字
```raw
{text_raw[-500:]}
```
"""
)
return
@app.cell
def regex_inputs(mo):
ruby_pattern = mo.ui.text(
value=r"《[^》]+》",
label="ルビ",
full_width=True,
)
ruby_bar_pattern = mo.ui.text(
value=r"|",
label="ルビのかかる範囲を示す記号",
full_width=True,
)
annotation_pattern = mo.ui.text(
value=r"[#[^]]+?]",
label="注釈・アノテーション",
full_width=True,
)
hajime_pattern = mo.ui.text(
value=r"-{55}(.|\n)+?-{55}",
label="青空文庫のヘッダー",
full_width=True,
)
owari_pattern = mo.ui.text(
value=(
r"^[ 【]?(底本:|訳者あとがき|この翻訳は|この作品.*翻訳|"
r"この翻訳.*全訳)"
),
label="青空文庫のフッター",
full_width=True,
)
regexes = mo.vstack(
[
ruby_pattern,
ruby_bar_pattern,
annotation_pattern,
hajime_pattern,
owari_pattern,
]
)
mo.md(f"""## 正規表現による前処理
(必要な場合は修正)
{regexes}
""")
return (
annotation_pattern,
hajime_pattern,
owari_pattern,
ruby_bar_pattern,
ruby_pattern,
)
@app.cell
def clean_aozora(
annotation_pattern,
hajime_pattern,
mo,
owari_pattern,
re,
ruby_bar_pattern,
ruby_pattern,
text_raw,
):
# compile from user‐editable patterns
ruby_rx = re.compile(ruby_pattern.value)
ruby_bar_rx = re.compile(ruby_bar_pattern.value)
annotation_rx = re.compile(annotation_pattern.value)
hajime_rx = re.compile(hajime_pattern.value)
owari_rx = re.compile(owari_pattern.value, re.M)
def clean_text(text: str) -> tuple[str, str, str]:
"""青空文庫テキスト形式の文字列textを入力とし,改行方式の統一,ルビーと各種のアノーテーションの削除,
青空文庫特有のヘッダーとフッターを取り除く処理を行う。"""
title, author, text = (text.split("\n", 2) + ["", ""])[:3]
# 青空文庫では改行がDOS形式の\r\nのため,それをUNIX形式の\nに統一する。
cleaned_text = re.sub(r"(\r\n)+", "\n", text)
# ルビ《...》の記号とその中身を削除
cleaned_text = re.sub(ruby_rx, "", cleaned_text)
# ルビのもう一つの書き方に対応:「一番|獰悪《どうあく》」
cleaned_text = re.sub(ruby_bar_rx, "", cleaned_text)
# 注釈対応:「※[#「言+墟のつくり」、第4水準2-88-74]」
cleaned_text = re.sub(annotation_rx, "", cleaned_text)
# 本文までのテキストを削除
cleaned_text = re.sub(hajime_rx, "", cleaned_text)
# 本文の後のテキストを削除
maybe_owari = owari_rx.search(cleaned_text)
if maybe_owari:
return (title, author, cleaned_text[0 : maybe_owari.start()].strip())
return (title, author, cleaned_text.strip())
title, author, cleaned_text = clean_text(text_raw)
mo.md(f"""### 前処理結果の確認
- 著者:`{author}`
- タイトル:`{title}`
最初の100字
```raw
{cleaned_text[:100]}
```
最後の100字
```raw
{cleaned_text[-100:]}
```
""")
return author, cleaned_text, title
@app.cell
def download_cleaned_text(author, cleaned_text, mo, title):
"""
Provide a download link for the cleaned Aozora text.
"""
download_link = mo.download(
data=cleaned_text.encode("utf-8"),
filename=f"{author}_{title}.txt",
mimetype="text/plain",
)
mo.md(f"""
前処理済みファイルのダウンロード (UTF-8):
{download_link}
""")
return
@app.cell
def get_alternative_file(mo):
aozora_xhtml_file = mo.ui.file(
label="Upload Aozora-Bunko text (.html)", multiple=False
)
xhtml_encoding = mo.ui.dropdown(
options=["shift-jis", "utf-8"],
value="shift-jis",
label="Text file encoding",
full_width=False,
)
mo.md(f"""
## HTMLを使用した前処理との比較(オプショナル)
プレインテキスト版を正規表現で前処理した結果を、(X)HTML版をPythonで処理した結果を比較したい場合は同じ作品のHTMLファイルをアップします。
{aozora_xhtml_file}
{xhtml_encoding}
""")
return aozora_xhtml_file, xhtml_encoding
@app.cell
def show_natsume_head(aozora_xhtml_file, mo, xhtml_encoding):
from aozora_corpus_generator.aozora import parse_aozora_bunko_xml_content
xhtml_enc = xhtml_encoding.value
if aozora_xhtml_file.value:
uploaded_xhtml = aozora_xhtml_file.contents()
xhtml_raw = uploaded_xhtml
else:
with open("789_14547.html", "rb") as xhtml_f:
xhtml_raw = xhtml_f.read()
aozora_xhtml_processed = parse_aozora_bunko_xml_content(
xhtml_raw, do_tokenize=False
)
aozora_xhtml_processed_text = aozora_xhtml_processed["text"]
mo.md(f"""
HTML版の最初の200字
```raw
{aozora_xhtml_processed_text[:200]}
```
HTML版の最後の200字
```raw
{aozora_xhtml_processed_text[-200:]}
```
""")
return (aozora_xhtml_processed_text,)
@app.cell
def _(aozora_xhtml_processed_text, author, mo, title):
xhtml_download_link = mo.download(
data=aozora_xhtml_processed_text.encode("utf-8"),
filename=f"{author}_{title}_xhtml.txt",
mimetype="text/plain",
)
mo.md(f"""
HTML版の前処理済みファイルをダウンロード (UTF-8):
{xhtml_download_link}
""")
return
@app.cell
def _():
import difflib
import html
from cdifflib import CSequenceMatcher
from IPython.display import HTML
from IPython.display import display_html as display
difflib.SequenceMatcher = CSequenceMatcher
DEL_STYLE = "background-color:#f6c6c6;color:#000;" # red bg, black text
INS_STYLE = "background-color:#c6f6c6;color:#000;" # green bg, black text
WRAP_STYLE = (
"font-family: ui-monospace, monospace; "
"white-space: pre-wrap; line-height:1.4; color:#000;"
)
WS_MAP = str.maketrans({" ": "␣", "\t": "⇥", "\n": "↩\n"})
def _escape(txt: str) -> str:
return html.escape(txt.translate(WS_MAP))
def _char_changes(a: str, b: str) -> str:
"""Return HTML for *only* the changed chars between a and b."""
sm = difflib.SequenceMatcher(None, a, b, autojunk=False)
pieces = []
for tag, i1, i2, j1, j2 in sm.get_opcodes():
if tag == "delete":
pieces.append(f'<span style="{DEL_STYLE}">{_escape(a[i1:i2])}</span>')
elif tag == "insert":
pieces.append(f'<span style="{INS_STYLE}">{_escape(b[j1:j2])}</span>')
elif tag == "replace":
pieces.append(f'<span style="{DEL_STYLE}">{_escape(a[i1:i2])}</span>')
pieces.append(f'<span style="{INS_STYLE}">{_escape(b[j1:j2])}</span>')
# equal → ignore
return "".join(pieces)
def diff_changes(a: str, b: str, auto_display: bool = True):
"""
Colab/Jupyter-friendly inline diff that shows *only the changed segments*.
Lightning-fast on large, mostly-identical texts.
"""
a_lines = a.splitlines(keepends=True)
b_lines = b.splitlines(keepends=True)
outer = difflib.SequenceMatcher(None, a_lines, b_lines, autojunk=True)
html_chunks = []
for tag, i1, i2, j1, j2 in outer.get_opcodes():
if tag == "replace": # both sides present
for la, lb in zip(a_lines[i1:i2], b_lines[j1:j2]):
html_chunks.append(_char_changes(la, lb))
# handle length mismatch
for la in a_lines[i1 + (j2 - j1) : i2]:
html_chunks.append(
f'<span style="{DEL_STYLE}">{_escape(la)}</span>'
)
for lb in b_lines[j1 + (i2 - i1) : j2]:
html_chunks.append(
f'<span style="{INS_STYLE}">{_escape(lb)}</span>'
)
elif tag == "delete":
for la in a_lines[i1:i2]:
html_chunks.append(
f'<span style="{DEL_STYLE}">{_escape(la)}</span>'
)
elif tag == "insert":
for lb in b_lines[j1:j2]:
html_chunks.append(
f'<span style="{INS_STYLE}">{_escape(lb)}</span>'
)
# equal → skip entirely (we want only changes)
rendered = f'<div style="{WRAP_STYLE}">{"".join(html_chunks)}</div>'
if auto_display:
display(HTML(rendered))
return rendered
return (diff_changes,)
@app.cell
def toggle_diff(mo):
run_diff = mo.ui.switch(label="文章間の比較(差分)を表示", value=False)
run_diff
return (run_diff,)
@app.cell
def compare_preprocessed_vs_old(
aozora_xhtml_processed_text,
cleaned_text,
diff_changes,
mo,
run_diff,
):
"""
Compare our cleaned text against the original Aozora‐processed text.
"""
mo.stop(not run_diff.value)
diff_result = diff_changes(
cleaned_text, aozora_xhtml_processed_text, auto_display=False
)
mo.md(f"""
- 赤: 正規表現版のみにある文字列
- 青: HTML版のみにある文字列
{diff_result}
""")
return
@app.cell
def _(mo):
mo.md(
r"""
## spaCy (GiNZA) による解析
以下からは、正規表現で前処理したテキストに対して、
- 形態素解析
- 係り受け解析
を行う。
> 作品によっては時間がかかる。
"""
)
return
@app.cell
def _(mo):
run_spacy = mo.ui.switch(label="spaCyで解析する", value=False)
run_spacy
return (run_spacy,)
@app.cell
def process_aozora_text(Doc, cleaned_text, mo, nlp, re, run_spacy):
mo.stop(not run_spacy.value)
"""
Turn each paragraph into one Doc. If any paragraph > MAX_BYTES,
fall back to sentence‐splitting, then raw‐byte‐splitting, and only
in that fallback re‐assemble via Doc.from_docs.
"""
def split_text_to_paragraphs(text: str) -> list[str]:
"""Split on one or more blank lines."""
return re.split(r"\n+\s*", text)
MAX_BYTES = 40000
paras = split_text_to_paragraphs(cleaned_text)
aozora_docs: list[Doc] = []
with mo.status.progress_bar(total=len(paras), title="spaCy processing") as bar:
for para in paras:
b = len(para.encode("utf-8"))
if b <= MAX_BYTES:
doc = nlp(para)
else:
# 1) try sentence‐level split
parts = re.split(r"([。!?])", para)
sents = [
parts[i] + (parts[i + 1] if i + 1 < len(parts) else "")
for i in range(0, len(parts), 2)
]
# 2) accumulate into <= MAX_BYTES
chunks: list[str] = []
cur, cur_b = "", 0
for s in sents:
sb = len(s.encode("utf-8"))
if cur_b + sb > MAX_BYTES:
if cur:
chunks.append(cur)
cur, cur_b = s, sb
else:
cur += s
cur_b += sb
if cur:
chunks.append(cur)
# 3) raw‐byte fallback for any too‐large piece
final_chunks: list[str] = []
for c in chunks:
if len(c.encode("utf-8")) <= MAX_BYTES:
final_chunks.append(c)
else:
rem = c
while rem:
pb = rem.encode("utf-8")[:MAX_BYTES]
part = pb.decode("utf-8", "ignore")
final_chunks.append(part)
rem = rem[len(part) :]
# 4) merge into one Doc for this paragraph
subdocs = list(nlp.pipe(final_chunks, batch_size=20))
doc = Doc.from_docs(subdocs)
aozora_docs.append(doc)
bar.update()
return (aozora_docs,)
@app.cell
def display_noun_chunks(aozora_docs: "list[Doc]", mo, pl):
"""
Show the most frequent noun-chunks in the entire text made up of at least two tokens, along with the number of tokens in each chunk.
"""
# build, filter (>=2 tokens), group and sort in one go
top_chunks = (
pl.DataFrame(
{
"chunk_text": [c.text for doc in aozora_docs for c in doc.noun_chunks],
"token_count": [len(c) for doc in aozora_docs for c in doc.noun_chunks],
}
)
.filter(pl.col("token_count") >= 2)
.group_by("chunk_text")
.agg([pl.len().alias("frequency"), pl.first("token_count")])
.sort("frequency", descending=True)
)
mo.md(f"""
spaCyには様々な機能が内蔵されていて、例えば、`noun_chunks`では[名詞句](https://spacy.io/usage/linguistic-features#noun-chunks)を構文(係り受け)解析結果に基づいて。ここでいう名詞句、すなわち「NPチャンク」とは、他の名詞句がその中に入れ子にならない名詞句のことで、名詞句レベルの並列や前置詞句、関係節は含まない。
### 2語以上からなる名詞句トップ25
{mo.ui.dataframe(top_chunks, page_size=25)}
> カスタマイズも[可能](https://github.com/explosion/spaCy/blob/41e07772dc5805594bab2997a090a9033e26bf56/spacy/lang/ja/syntax_iterators.py#L12)
""")
return
@app.cell(hide_code=True)
def _(mo):
mo.md(
"""
## Token Pattern Matching
トークンベースのルールを使用して、短単位で分割された動詞の塊をまとめ上げて観察する。
> ここで使用されるルールはあくまでも例で、完璧に動詞の塊をまとめ上げていない。また、短単位より長い単位でテキスト分析する場合は長単位による解析も[可能](https://github.com/komiya-lab/monaka)。
"""
)
return
@app.cell
def token_pattern():
###### ここにサイトからコピーしたパターンを入れ変える
pattern = [
{"POS": "NOUN", "OP": "+"},
{"POS": "VERB", "OP": "+"},
{"POS": {"REGEX": "VERB|AUX"}, "OP": "+"},
]
#####################################################
return (pattern,)
@app.cell
def token_pattern_match(aozora_docs: "list[Doc]", mo, nlp, pattern, pl, spacy):
# https://spacy.io/usage/rule-based-matching#example1
from spacy.matcher import Matcher
matcher = Matcher(nlp.vocab)
matched_sentences = [] # Collect data of matched sentences to be visualized
match_texts: list[str] = []
def collect_sents(matcher, doc, i, matches):
match_id, start, end = matches[i]
span = doc[start:end] # Matched span
sent = span.sent # Sentence containing matched span
# get the match span by offsetting the start/end of the span
match_ents = [
{
"start": span.start_char - sent.start_char,
"end": span.end_char - sent.start_char,
"label": "ヒット",
}
]
matched_sentences.append({"text": sent.text, "ents": match_ents})
match_texts.append(span.text)
matcher.add("MyPattern", [pattern], on_match=collect_sents) # add pattern
# run matcher over each paragraph
for p_doc2 in aozora_docs:
matcher(p_doc2)
# only show first 10 matches
MAX_PATTERN_MATCHES = 10
viz_html = spacy.displacy.render(
matched_sentences[:MAX_PATTERN_MATCHES], style="ent", manual=True
)
# build top‐25 frequency table of matched span texts
df = pl.DataFrame({"match_text": match_texts})
top_matches = (
df.group_by("match_text")
.agg(pl.len().alias("frequency"))
.sort("frequency", descending=True)
.head(25)
)
# display the displaCy‐rendered HTML *and* the frequency table
mo.vstack([mo.Html(viz_html), top_matches])
return
@app.cell(hide_code=True)
def _(mo):
mo.md(
"""
## Dependency Pattern Matching
係り受けパターンのルールを記述し、動詞と名詞が[nsubj](https://universaldependencies.org/ja/dep/nsubj.html) (nominal subject) という係り受け関係にあるもの、すなわち動詞とその主語を抽出する。
> 係り受け解析は形態素解析のタスクより複雑、その解析制度がより低い。ここでは`ja_ginza`という軽量なモデルを使用しているが、解析制度を求めるのであれば、Transformerベースモデルを使用するとよい。
"""
)
return
@app.cell
def dependency_pattern():
###### ここにサイトからコピーしたパターンを入れ変える
# this is your dependency‐matcher pattern
dep_pattern = [
{"RIGHT_ID": "anchor_verb", "RIGHT_ATTRS": {"POS": "VERB"}},
{
"LEFT_ID": "anchor_verb",
"REL_OP": ">",
"RIGHT_ID": "verb_subject",
"RIGHT_ATTRS": {"DEP": "nsubj"},
},
]
#####################################################
return (dep_pattern,)
@app.cell
def show_dependency_matches(
aozora_docs: "list[Doc]",
dep_pattern,
mo,
nlp,
pl,
spacy,
):
from spacy.matcher import DependencyMatcher
dep_matcher = DependencyMatcher(nlp.vocab)
viz_dep_sents: list[dict] = []
dep_pairs: list[dict[str, str]] = []
def collect_deps(matcher, doc, i, matches):
_, token_ids = matches[i]
sent = doc[token_ids[0]].sent
# map each RIGHT_ID to its matched Token
rid_to_tok = {
pat["RIGHT_ID"]: doc[tok_id] for pat, tok_id in zip(dep_pattern, token_ids)
}
verb = rid_to_tok["anchor_verb"]
subj = rid_to_tok["verb_subject"]
# build ents for displaCy
ents = []
for rid, tok in rid_to_tok.items():
label = "subject" if rid == "verb_subject" else "verb"
ents.append(
{
"start": tok.idx - sent.start_char,
"end": tok.idx + len(tok) - sent.start_char,
"label": label,
"text": tok.text,
}
)
viz_dep_sents.append({"text": sent.text, "ents": ents})
dep_pairs.append({"subject": subj.text, "verb": verb.text})
dep_matcher.add("MyDepPattern", [dep_pattern], on_match=collect_deps)
for dep_doc in aozora_docs:
dep_matcher(dep_doc)
dep_viz_html = spacy.displacy.render(viz_dep_sents[:10], style="ent", manual=True)
dep_df = pl.DataFrame(dep_pairs)
top_dep_matches = (
dep_df.group_by(["subject", "verb"])
.agg(pl.len().alias("frequency"))
.sort("frequency", descending=True)
)
mo.vstack(
[
mo.Html(dep_viz_html),
top_dep_matches,
]
)
return
@app.cell
def _():
return
if __name__ == "__main__":
app.run()
|