Refactor app.py: reorganize imports, remove unused code, and enhance readability
Browse files
app.py
CHANGED
|
@@ -1,17 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
| 1 |
import os
|
| 2 |
import pickle
|
| 3 |
import re
|
|
|
|
| 4 |
from collections import Counter
|
| 5 |
from dataclasses import dataclass
|
| 6 |
-
from typing import Callable, Dict, Iterable, List, Optional, Type, TypeVar
|
| 7 |
|
|
|
|
| 8 |
import nltk
|
| 9 |
import tqdm
|
|
|
|
| 10 |
|
| 11 |
from nlp4web_codebase.ir.data_loaders.dm import Document
|
|
|
|
|
|
|
| 12 |
|
| 13 |
nltk.download("stopwords", quiet=True)
|
| 14 |
-
from nltk.corpus import stopwords as nltk_stopwords
|
| 15 |
|
| 16 |
LANGUAGE = "english"
|
| 17 |
word_splitter = re.compile(r"(?u)\b\w\w+\b").findall
|
|
@@ -144,19 +151,9 @@ def run_counting(
|
|
| 144 |
)
|
| 145 |
|
| 146 |
|
| 147 |
-
from nlp4web_codebase.ir.data_loaders.sciq import load_sciq
|
| 148 |
-
|
| 149 |
sciq = load_sciq()
|
| 150 |
counting = run_counting(documents=iter(sciq.corpus), ndocs=len(sciq.corpus))
|
| 151 |
|
| 152 |
-
from __future__ import annotations
|
| 153 |
-
|
| 154 |
-
import math
|
| 155 |
-
from dataclasses import dataclass
|
| 156 |
-
from typing import Iterable, List, Optional, Type
|
| 157 |
-
|
| 158 |
-
from nlp4web_codebase.ir.data_loaders.dm import Document
|
| 159 |
-
|
| 160 |
|
| 161 |
@dataclass
|
| 162 |
class BM25Index(InvertedIndex):
|
|
@@ -251,11 +248,6 @@ bm25_index = BM25Index.build_from_documents(
|
|
| 251 |
)
|
| 252 |
bm25_index.save("output/bm25_index")
|
| 253 |
|
| 254 |
-
from abc import abstractmethod
|
| 255 |
-
from typing import Type
|
| 256 |
-
|
| 257 |
-
from nlp4web_codebase.ir.models import BaseRetriever
|
| 258 |
-
|
| 259 |
|
| 260 |
class BaseInvertedIndexRetriever(BaseRetriever):
|
| 261 |
@property
|
|
@@ -362,10 +354,6 @@ bm25_index = BM25Index.build_from_documents(
|
|
| 362 |
b=best_b,
|
| 363 |
)
|
| 364 |
|
| 365 |
-
from typing import TypedDict
|
| 366 |
-
|
| 367 |
-
import gradio as gr
|
| 368 |
-
|
| 369 |
|
| 370 |
class Hit(TypedDict):
|
| 371 |
cid: str
|
|
|
|
| 1 |
+
from __future__ import annotations
|
| 2 |
+
|
| 3 |
+
import math
|
| 4 |
import os
|
| 5 |
import pickle
|
| 6 |
import re
|
| 7 |
+
from abc import abstractmethod
|
| 8 |
from collections import Counter
|
| 9 |
from dataclasses import dataclass
|
| 10 |
+
from typing import Callable, Dict, Iterable, List, Optional, Type, TypedDict, TypeVar
|
| 11 |
|
| 12 |
+
import gradio as gr
|
| 13 |
import nltk
|
| 14 |
import tqdm
|
| 15 |
+
from nltk.corpus import stopwords as nltk_stopwords
|
| 16 |
|
| 17 |
from nlp4web_codebase.ir.data_loaders.dm import Document
|
| 18 |
+
from nlp4web_codebase.ir.data_loaders.sciq import load_sciq
|
| 19 |
+
from nlp4web_codebase.ir.models import BaseRetriever
|
| 20 |
|
| 21 |
nltk.download("stopwords", quiet=True)
|
|
|
|
| 22 |
|
| 23 |
LANGUAGE = "english"
|
| 24 |
word_splitter = re.compile(r"(?u)\b\w\w+\b").findall
|
|
|
|
| 151 |
)
|
| 152 |
|
| 153 |
|
|
|
|
|
|
|
| 154 |
sciq = load_sciq()
|
| 155 |
counting = run_counting(documents=iter(sciq.corpus), ndocs=len(sciq.corpus))
|
| 156 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 157 |
|
| 158 |
@dataclass
|
| 159 |
class BM25Index(InvertedIndex):
|
|
|
|
| 248 |
)
|
| 249 |
bm25_index.save("output/bm25_index")
|
| 250 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 251 |
|
| 252 |
class BaseInvertedIndexRetriever(BaseRetriever):
|
| 253 |
@property
|
|
|
|
| 354 |
b=best_b,
|
| 355 |
)
|
| 356 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 357 |
|
| 358 |
class Hit(TypedDict):
|
| 359 |
cid: str
|