Merge pull request #47 from rskmoi/v0.3.1

V0.3.1

.github/workflows/python-package.yml

@@ -27,11 +27,11 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest, windows-latest, macos-latest]
-        python-version: [ '3.8', '3.9', '3.10', '3.11', '3.12']
+        python-version: [ '3.9', '3.10', '3.11', '3.12', '3.13' ]
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v3
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
       - name: Install libomp if the operating system is macOS.

namedivider/cli.py

@@ -1,7 +1,6 @@
 from pathlib import Path
 
 import typer
-from tqdm import tqdm
 
 from namedivider.divider.basic_name_divider import BasicNameDivider
 from namedivider.divider.config import BasicNameDividerConfig, GBDTNameDividerConfig
@@ -75,8 +74,9 @@ def file(
     with open(undivided_name_text, "rb") as f:
         undivided_names = f.read().decode(encoding).strip().split("\n")
     divided_names = []
-    for _undivided_name in tqdm(undivided_names):
-        divided_names.append(str(divider.divide_name(_undivided_name)))
+    with typer.progressbar(undivided_names) as bar:
+        for _undivided_name in bar:
+            divided_names.append(str(divider.divide_name(_undivided_name)))
     print("\n".join(divided_names))
 
 
@@ -116,13 +116,14 @@ def accuracy(
         divided_names = f.read().decode(encoding).strip().split("\n")
     is_correct_list = []
     wrong_list = []
-    for _divided_name in tqdm(divided_names):
-        _undivided_name = _divided_name.replace(separator, "")
-        _divided_name_pred = str(divider.divide_name(_undivided_name))
-        is_correct = _divided_name == _divided_name_pred
-        is_correct_list.append(is_correct)
-        if not is_correct:
-            wrong_list.append(f"True: {_divided_name}, Pred: {_divided_name_pred}")
+    with typer.progressbar(divided_names) as bar:
+        for _divided_name in bar:
+            _undivided_name = _divided_name.replace(separator, "")
+            _divided_name_pred = str(divider.divide_name(_undivided_name))
+            is_correct = _divided_name == _divided_name_pred
+            is_correct_list.append(is_correct)
+            if not is_correct:
+                wrong_list.append(f"True: {_divided_name}, Pred: {_divided_name_pred}")
     print(f"{sum(is_correct_list) / len(is_correct_list):.04}")
     if len(wrong_list) != 0:
         print("\n".join(wrong_list))

namedivider/divider/gbdt_name_divider.py

@@ -1,10 +1,9 @@
+import _pickle as pickle  # type: ignore
 from dataclasses import asdict
 from pathlib import Path
 from typing import Optional, cast
 
-import _pickle as pickle  # type: ignore
 import lightgbm as lgb
-import pandas as pd
 
 from namedivider.divider.config import GBDTNameDividerConfig
 from namedivider.divider.name_divider_base import _NameDivider
@@ -47,7 +46,7 @@ def calc_score(self, family: str, given: str) -> float:
         :return: Score of dividing.
         """
         feature = self.feature_extractor.get_features(family=family, given=given)
-        df = pd.DataFrame([asdict(feature)])
-        score_list = self.model.predict(df)
+        feature_list = [list(asdict(feature).values())]
+        score_list = self.model.predict(feature_list)
         score = cast(float, score_list[0])
         return score

namedivider/util.py

@@ -1,8 +1,7 @@
+import urllib.request
 from pathlib import Path
 from typing import Union
 
-import requests
-
 CURRENT_DIR = Path(__file__).resolve().parent
 DEFAULT_CACHE_DIR = Path("~/.cache/namedivider-python").expanduser()
 GBDT_MODEL_V1_URL = "https://github.com/rskmoi/namedivider-python/releases/download/Models/gbdt_model_v1.txt"
@@ -43,7 +42,8 @@ def download_family_name_pickle_if_needed(path: Union[str, Path]) -> None:
         return None
     DEFAULT_CACHE_DIR.mkdir(exist_ok=True, parents=True)
     print("Download FamilyNameRepository from GitHub...")
-    content = requests.get(FAMILY_NAME_REPOSITORY_URL).content
+    with urllib.request.urlopen(FAMILY_NAME_REPOSITORY_URL) as response:
+        content = response.read()
     with open(path, "wb") as f:
         f.write(content)
 
@@ -59,6 +59,7 @@ def download_gbdt_model_v1_if_needed(path: Union[str, Path]) -> None:
         return None
     DEFAULT_CACHE_DIR.mkdir(exist_ok=True, parents=True)
     print("Download GBDT Model from GitHub...")
-    content = requests.get(GBDT_MODEL_V1_URL).content
+    with urllib.request.urlopen(GBDT_MODEL_V1_URL) as response:
+        content = response.read()
     with open(path, "wb") as f:
         f.write(content)

namedivider/version.py

@@ -1 +1 @@
-__version__ = "0.3.0"
+__version__ = "0.3.1"

pyproject.toml

@@ -13,19 +13,17 @@ authors = [
 ]
 classifiers = [
     "License :: OSI Approved :: MIT License",
-    "Programming Language :: Python :: 3.8",
     "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
 ]
 dependencies = [
     "lightgbm>=3.3",
     "numpy",
     "pandas",
     "regex",
-    "requests",
-    "tqdm",
     "typer>=0.3.2",
 ]
 
@@ -62,15 +60,15 @@ module = "namedivider"
 ignore_missing_imports = true
 
 [tool.ruff]
-select = [
+lint.select = [
     "E",  # pycodestyle errors
     "W",  # pycodestyle warnings
     "F",  # pyflakes
     "I",  # isort
     "C",  # flake8-comprehensions
     "B",  # flake8-bugbear
 ]
-ignore = [
+lint.ignore = [
     "E501",  # line too long, handled by black
     "B008",  # do not perform function calls in argument defaults
     "C901",  # too complex

requirements-test.txt

@@ -1,11 +1,9 @@
 pytest >=7.1.3,<8.0.0
-mypy == 1.4.0
-ruff == 0.0.275
-black == 23.3.0
-coverage == 7.3.2
+mypy == 1.11.2
+ruff == 0.6.8
+black == 23.12.1
+coverage == 7.6.1
 
 # stubs
-types-requests
 pandas-stubs
-types-regex
-types-tqdm
+types-regex

scripts/format.sh

@@ -1,2 +1,2 @@
-ruff namedivider tests --fix
+ruff check namedivider tests --fix
 black namedivider tests

scripts/lint.sh

@@ -2,5 +2,5 @@ set -e
 set -x
 
 mypy namedivider
-ruff namedivider tests
+ruff check namedivider tests
 black namedivider tests --check