Fix type annotation errors and remove unused type:ignore comments

pythainlp/benchmarks/word_tokenization.py

@@ -85,10 +85,10 @@ def benchmark(ref_samples: list[str], samples: list[str]) -> "pd.DataFrame":
             r, s = preprocessing(r), preprocessing(s)
             if r and s:
                 stats = compute_stats(r, s)
-                stats = _flatten_result(stats)
-                stats["expected"] = r
-                stats["actual"] = s
-                results.append(stats)
+                flat_stats: dict[str, Union[int, str]] = _flatten_result(stats)
+                flat_stats["expected"] = r
+                flat_stats["actual"] = s
+                results.append(flat_stats)
         except:
             reason = """
 [Error]

pythainlp/chat/core.py

@@ -3,7 +3,7 @@
 # SPDX-License-Identifier: Apache-2.0
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Optional, cast
+from typing import TYPE_CHECKING, Optional
 
 if TYPE_CHECKING:
     import torch
@@ -97,6 +97,6 @@ def chat(self, text: str) -> str:
         _temp += self.model.PROMPT_DICT["prompt_chatbot"].format_map(
             {"human": text, "bot": ""}
         )
-        _bot = cast(str, self.model.gen_instruct(_temp))
+        _bot = self.model.gen_instruct(_temp)
         self.history.append((text, _bot))
         return _bot

pythainlp/summarize/keybert.py

@@ -155,7 +155,7 @@ def embed(self, docs: Union[str, list[str]]) -> np.ndarray:
                 [np.array(emb[0]).mean(axis=0) for emb in embs]
             )
 
-        return emb_mean  # type: ignore[no-any-return]
+        return emb_mean
 
 
 def _generate_ngrams(
@@ -224,10 +224,10 @@ def l2_norm(v: np.ndarray) -> np.ndarray:
         )
         if not np.isclose(np.linalg.norm(result, axis=1), 1).all():
             raise ValueError("Cannot normalize a vector to unit vector.")
-        return result  # type: ignore[no-any-return]
+        return result
 
     def cosine_sim(a: np.ndarray, b: np.ndarray) -> np.ndarray:
-        return (np.matmul(a, b.T).T).sum(axis=1)  # type: ignore[no-any-return]
+        return (np.matmul(a, b.T).T).sum(axis=1)
 
     doc_vector = l2_norm(doc_vector)
     word_vectors = l2_norm(word_vectors)

pythainlp/tag/named_entity.py

@@ -139,7 +139,9 @@ def tag(
             >>> ner.tag("ทดสอบ นายวรรณพงษ์ ภัททิยไพบูลย์", tag=True)
             'ทดสอบ <PERSON>นายวรรณพงษ์ ภัททิยไพบูลย์</PERSON>'
         """
-        return self.engine.get_ner(text, tag=tag, pos=pos)  # type: ignore[no-any-return]
+        if self.engine is None:
+            raise RuntimeError("Engine not initialized")
+        return self.engine.get_ner(text, tag=tag, pos=pos)
 
 
 class NNER:
@@ -223,4 +225,4 @@ def tag(
             >>> nner.tag("แมวทำอะไรตอนห้าโมงเช้า", top_level_only=True)
             ([...], [{'text': ['', 'ห้า', '', 'โมง'], 'span': [7, 11], 'entity_type': 'time'}])
         """
-        return self.engine.tag(text, top_level_only=top_level_only)  # type: ignore[no-any-return]
+        return self.engine.tag(text, top_level_only=top_level_only)

pythainlp/tag/wangchanberta_onnx.py

@@ -88,7 +88,7 @@ def postprocess(self, logits_data: "np.ndarray") -> "np.ndarray":
         maxes = np.max(logits_t, axis=-1, keepdims=True)
         shifted_exp = np.exp(logits_t - maxes)
         scores = shifted_exp / shifted_exp.sum(axis=-1, keepdims=True)
-        return scores  # type: ignore[no-any-return]
+        return scores
 
     def clean_output(
         self, list_text: list[tuple[str, str]]

pythainlp/tokenize/nlpo3.py

@@ -86,7 +86,11 @@ def load_dict(file_path: str, dict_name: str) -> bool:
             "nlpo3 is not installed. Install it with: pip install nlpo3"
         ) from ex
 
-    msg, success = nlpo3_load_dict(file_path=file_path, dict_name=dict_name)
+    msg: str
+    success: bool
+    msg, success = nlpo3_load_dict(
+        file_path=file_path, dict_name=dict_name
+    )
     if not success:
         print(msg, file=stderr)
     return success
@@ -127,9 +131,10 @@ def segment(
     if custom_dict == _NLPO3_DEFAULT_DICT_NAME:
         _ensure_default_dict_loaded()
 
-    return nlpo3_segment(
+    result: list[str] = nlpo3_segment(
         text=text,
         dict_name=custom_dict,
         safe=safe_mode,
         parallel=parallel_mode,
     )
+    return result

pythainlp/tools/path.py

@@ -16,7 +16,7 @@
 if version_info >= (3, 11):
     from importlib.resources import files  # Available in Python 3.11+
 else:
-    from importlib_resources import files  # noqa: I001
+    from importlib_resources import files  # type: ignore[no-redef]  # noqa: I001
 
 PYTHAINLP_DEFAULT_DATA_DIR: str = "pythainlp-data"
 

pythainlp/transliterate/core.py

@@ -179,7 +179,7 @@ def transliterate(
     elif engine == "thaig2p_v2":
         from pythainlp.transliterate.thaig2p_v2 import transliterate  # noqa: I001
     elif engine == "umt5_thaig2p":
-        from pythainlp.translate.umt5_thaig2p import transliterate  # type: ignore[import-untyped,no-redef]  # noqa: I001
+        from pythainlp.translate.umt5_thaig2p import transliterate  # type: ignore[no-redef]  # noqa: I001
     else:  # use default engine: "thaig2p"
         from pythainlp.transliterate.thaig2p import transliterate  # noqa: I001
 

pythainlp/transliterate/thai2rom_onnx.py

@@ -76,7 +76,7 @@ def _prepare_sequence_in(self, text: str) -> "np.ndarray":
             else:
                 idxs.append(self._char_to_ix["<UNK>"])
         idxs.append(self._char_to_ix["<end>"])
-        return np.array(idxs)  # type: ignore[no-any-return]
+        return np.array(idxs)
 
     def romanize(self, text: str) -> str:
         """:param str text: Thai text to be romanized
@@ -131,7 +131,7 @@ def __init__(
 
     def create_mask(self, source_seq: "np.ndarray") -> "np.ndarray":
         mask = source_seq != self.pad_idx
-        return mask  # type: ignore[no-any-return]
+        return mask
 
     def run(
         self, source_seq: "np.ndarray", source_seq_len: List[int]
@@ -196,9 +196,9 @@ def run(
             decoder_input = np.array([topi])
 
             if decoder_input == end_token:
-                return outputs[:di]  # type: ignore[no-any-return]
+                return outputs[:di]
 
-        return outputs  # type: ignore[no-any-return]
+        return outputs
 
 
 _THAI_TO_ROM_ONNX: ThaiTransliterator_ONNX = ThaiTransliterator_ONNX()

pythainlp/transliterate/w2p.py

@@ -151,7 +151,7 @@ def _load_variables(self) -> None:
     def _sigmoid(self, x: "np.ndarray") -> "np.ndarray":
         import numpy as np
 
-        return 1 / (1 + np.exp(-x))  # type: ignore[no-any-return]
+        return 1 / (1 + np.exp(-x))
 
     def _grucell(
         self,
@@ -205,7 +205,7 @@ def _gru(
             h = self._grucell(x[:, t, :], h, w_ih, w_hh, b_ih, b_hh)  # (b, h)
             outputs[:, t, ::] = h
 
-        return outputs  # type: ignore[no-any-return]
+        return outputs
 
     def _encode(self, word: str) -> "np.ndarray":
         import numpy as np
@@ -214,7 +214,7 @@ def _encode(self, word: str) -> "np.ndarray":
         x = [self.g2idx.get(char, self.g2idx["<unk>"]) for char in chars]
         x = np.take(self.enc_emb, np.expand_dims(x, 0), axis=0)
 
-        return x  # type: ignore[no-any-return]
+        return x
 
     def _short_word(self, word: str) -> Optional[str]:
         self.word: str = word

pythainlp/ulmfit/core.py

@@ -241,7 +241,7 @@ def document_vector(
     else:
         raise ValueError("Aggregate by mean or sum")
 
-    return res  # type: ignore[no-any-return]
+    return res
 
 
 def merge_wgts(

pythainlp/word_vector/core.py

@@ -307,7 +307,7 @@ def sentence_vectorizer(self, text: str, use_mean: bool = True) -> ndarray:
         len_words = len(words)
 
         if not len_words:
-            return vec  # type: ignore[no-any-return]
+            return vec
 
         for word in words:
             if word == " " and self.model_name == "thai2fit_wv":
@@ -321,4 +321,4 @@ def sentence_vectorizer(self, text: str, use_mean: bool = True) -> ndarray:
         if use_mean:
             vec /= len_words
 
-        return vec  # type: ignore[no-any-return]
+        return vec

tests/data/eval-details-input.json

@@ -1 +1 @@
-{"metrics": {"char_level:tp": 4.0, "char_level:fp": 0.0, "char_level:tn": 9.0, "char_level:fn": 1.0, "word_level:correctly_tokenised_words": 3.0, "word_level:total_words_in_sample": 4.0, "word_level:total_words_in_ref_sample": 5.0, "char_level:precision": 1.0, "char_level:recall": 0.8, "word_level:precision": 0.75, "word_level:recall": 0.6}, "samples": [{"metrics": {"char_level:tp": 4, "char_level:fp": 0, "char_level:tn": 9, "char_level:fn": 1, "word_level:correctly_tokenised_words": 3, "word_level:total_words_in_sample": 4.0, "word_level:total_words_in_ref_sample": 5.0, "global:tokenisation_indicators": "1011"}, "expected": "ผม|ไม่|ชอบ|กิน|ผัก", "actual": "ผม|ไม่ชอบ|กิน|ผัก", "id": 0}]}
+{"metrics": {"char_level:tp": 4.0, "char_level:fp": 0.0, "char_level:tn": 9.0, "char_level:fn": 1.0, "word_level:correctly_tokenised_words": 3.0, "word_level:total_words_in_sample": 4.0, "word_level:total_words_in_ref_sample": 5.0, "char_level:precision": 1.0, "char_level:recall": 0.8, "word_level:precision": 0.75, "word_level:recall": 0.6}, "samples": [{"metrics": {"char_level:tp": 4, "char_level:fp": 0, "char_level:tn": 9, "char_level:fn": 1, "word_level:correctly_tokenised_words": 3, "word_level:total_words_in_sample": 4, "word_level:total_words_in_ref_sample": 5, "global:tokenisation_indicators": "1011"}, "expected": "ผม|ไม่|ชอบ|กิน|ผัก", "actual": "ผม|ไม่ชอบ|กิน|ผัก", "id": 0}]}