kabukit 0.3.0__tar.gz → 0.4.0__tar.gz

{kabukit-0.3.0 → kabukit-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: kabukit
-Version: 0.3.0
+Version: 0.4.0
 Summary: A Python toolkit for Japanese financial market data, supporting J-Quants and EDINET APIs.
 Author: daizutabi
 Author-email: daizutabi <daizutabi@gmail.com>
@@ -28,10 +28,9 @@ License: MIT License
 Classifier: Development Status :: 4 - Beta
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3.13
-Requires-Dist: altair>=5
 Requires-Dist: async-typer>=0.1
 Requires-Dist: holidays>=0.81
-Requires-Dist: httpx>=0.28.1
+Requires-Dist: httpx>=0.28
 Requires-Dist: platformdirs>=4
 Requires-Dist: polars>=1
 Requires-Dist: python-dotenv>=1

{kabukit-0.3.0 → kabukit-0.4.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "uv_build"
 
 [project]
 name = "kabukit"
-version = "0.3.0"
+version = "0.4.0"
 description = "A Python toolkit for Japanese financial market data, supporting J-Quants and EDINET APIs."
 readme = "README.md"
 license = { file = "LICENSE" }
@@ -16,10 +16,9 @@ classifiers = [
 ]
 requires-python = ">=3.13"
 dependencies = [
-  "altair>=5",
   "async-typer>=0.1",
   "holidays>=0.81",
-  "httpx>=0.28.1",
+  "httpx>=0.28",
   "platformdirs>=4",
   "polars>=1",
   "python-dotenv>=1",
@@ -36,6 +35,7 @@ Issues = "https://github.com/daizutabi/kabukit/issues"
 
 [dependency-groups]
 dev = [
+  "altair>=5",
   "basedpyright>=1.31.4",
   "marimo[lsp]>=0.16",
   "numpy>=2.3.3",                 # polars 1.33 type hinting workaround,
@@ -54,14 +54,12 @@ dev = [
 docs = ["mkapi>=4.4", "mkdocs-marimo", "mkdocs-material"]
 
 [tool.pytest.ini_options]
-addopts = [
-  "--cov=kabukit",
-  "--cov-report=lcov:lcov.info",
-  "--doctest-modules",
-  "-m not integration",
+addopts = ["--cov=kabukit", "--cov-report=lcov:lcov.info", "--doctest-modules"]
+testpaths = ["tests/unit", "tests/integration", "tests/validation"]
+markers = [
+  "integration: marks tests as integration tests",
+  "validation: marks tests as data validation tests",
 ]
-testpaths = ["tests/unit", "tests/integration"]
-markers = ["integration: marks tests as integration tests"]
 
 [tool.coverage.report]
 exclude_lines = ["no cov", "raise NotImplementedError", "if TYPE_CHECKING:"]

kabukit-0.4.0/src/kabukit/__init__.py

@@ -0,0 +1,17 @@
+from .core.info import Info
+from .core.list import List
+from .core.prices import Prices
+from .core.reports import Reports
+from .core.statements import Statements
+from .edinet.client import EdinetClient
+from .jquants.client import JQuantsClient
+
+__all__ = [
+    "EdinetClient",
+    "Info",
+    "JQuantsClient",
+    "List",
+    "Prices",
+    "Reports",
+    "Statements",
+]

{kabukit-0.3.0 → kabukit-0.4.0}/src/kabukit/cli/auth.py

@@ -20,8 +20,8 @@ async def auth_jquants(mailaddress: str, password: str) -> None:
     async with JQuantsClient() as client:
         try:
             await client.auth(mailaddress, password, save=True)
-        except HTTPStatusError as e:
-            typer.echo(f"認証に失敗しました: {e}")
+        except HTTPStatusError:
+            typer.echo("認証に失敗しました。")
             raise Exit(1) from None
 
     typer.echo("J-Quantsのリフレッシュトークン・IDトークンを保存しました。")

{kabukit-0.3.0 → kabukit-0.4.0}/src/kabukit/cli/get.py

@@ -1,11 +1,14 @@
 from __future__ import annotations
 
-from typing import Annotated, Any
+from typing import TYPE_CHECKING, Annotated, Any
 
 import typer
 from async_typer import AsyncTyper  # pyright: ignore[reportMissingTypeStubs]
 from typer import Argument
 
+if TYPE_CHECKING:
+    from kabukit.core.base import Base
+
 app = AsyncTyper(
     add_completion=False,
     help="J-Quantsからデータを取得します。",
@@ -36,7 +39,7 @@ async def info(code: Code = None) -> None:
 async def _fetch(
     code: str | None,
     target: str,
-    writer_cls: type,
+    cls: type[Base],
     fetch_func_name: str,
     message: str,
     **kwargs: Any,
@@ -56,7 +59,7 @@ async def _fetch(
 
     df = await fetch_all(target, progress=tqdm.asyncio.tqdm, **kwargs)
     typer.echo(df)
-    path = writer_cls(df).write()
+    path = cls(df).write()
     typer.echo(f"全銘柄の{message}を '{path}' に保存しました。")
 
 
@@ -68,7 +71,7 @@ async def statements(code: Code = None) -> None:
     await _fetch(
         code=code,
         target="statements",
-        writer_cls=Statements,
+        cls=Statements,
         fetch_func_name="get_statements",
         message="財務情報",
     )
@@ -82,16 +85,55 @@ async def prices(code: Code = None) -> None:
     await _fetch(
         code=code,
         target="prices",
-        writer_cls=Prices,
+        cls=Prices,
         fetch_func_name="get_prices",
         message="株価情報",
         max_concurrency=8,
     )
 
 
+@app.async_command(name="list")  # pyright: ignore[reportUnknownMemberType]
+async def list_() -> None:
+    """報告書一覧を取得します。"""
+    import tqdm.asyncio
+
+    from kabukit.core.list import List
+    from kabukit.edinet.concurrent import fetch_list
+
+    df = await fetch_list(years=10, progress=tqdm.asyncio.tqdm)
+    typer.echo(df)
+    path = List(df).write()
+    typer.echo(f"報告書一覧を '{path}' に保存しました。")
+
+
+@app.async_command()  # pyright: ignore[reportUnknownMemberType]
+async def reports() -> None:
+    """報告書を取得します。"""
+    import polars as pl
+    import tqdm.asyncio
+
+    from kabukit.core.list import List
+    from kabukit.core.reports import Reports
+    from kabukit.edinet.concurrent import fetch_csv
+
+    try:
+        df = List.read().data
+    except FileNotFoundError:
+        await list_()
+        df = List.read().data
+
+    lst = df.filter(pl.col("csvFlag"), pl.col("secCode").is_not_null())
+    doc_ids = lst["docID"].unique()
+
+    df = await fetch_csv(doc_ids, limit=1000, progress=tqdm.asyncio.tqdm)
+    typer.echo(df)
+    path = Reports(df).write()
+    typer.echo(f"報告書を '{path}' に保存しました。")
+
+
 @app.async_command(name="all")  # pyright: ignore[reportUnknownMemberType]
 async def all_(code: Code = None) -> None:
-    """上場銘柄一覧、財務情報、株価を連続して取得します。"""
+    """上場銘柄一覧、財務情報、株価、報告書を連続して取得します。"""
     typer.echo("上場銘柄一覧を取得します。")
     await info(code)
 
@@ -102,3 +144,11 @@ async def all_(code: Code = None) -> None:
     typer.echo("---")
     typer.echo("株価を取得します。")
     await prices(code)
+
+    if code is None:
+        typer.echo("---")
+        typer.echo("報告書一覧を取得します。")
+        await list_()
+        typer.echo("---")
+        typer.echo("報告書を取得します。")
+        await reports()

{kabukit-0.3.0 → kabukit-0.4.0}/src/kabukit/core/base.py

@@ -8,9 +8,11 @@ import polars as pl
 from platformdirs import user_cache_dir
 
 if TYPE_CHECKING:
-    from typing import Self
+    from collections.abc import Iterable
+    from typing import Any, Self
 
     from polars import DataFrame
+    from polars._typing import IntoExprColumn
 
 
 class Base:
@@ -48,3 +50,12 @@ class Base:
 
         data = pl.read_parquet(filename)
         return cls(data)
+
+    def filter(
+        self,
+        *predicates: IntoExprColumn | Iterable[IntoExprColumn] | bool | list[bool],
+        **constraints: Any,
+    ) -> Self:
+        """Filter the data with given predicates and constraints."""
+        data = self.data.filter(*predicates, **constraints)
+        return self.__class__(data)

{kabukit-0.3.0 → kabukit-0.4.0}/src/kabukit/core/client.py

@@ -12,7 +12,7 @@ class Client:
     client: AsyncClient
 
     def __init__(self, base_url: str = "") -> None:
-        self.client = AsyncClient(base_url=base_url)
+        self.client = AsyncClient(base_url=base_url, timeout=20)
 
     async def aclose(self) -> None:
         """HTTPクライアントを閉じる。"""

kabukit-0.4.0/src/kabukit/core/list.py

@@ -0,0 +1,12 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+from .base import Base
+
+if TYPE_CHECKING:
+    from polars import DataFrame
+
+
+class List(Base):
+    pass

kabukit-0.4.0/src/kabukit/core/prices.py

@@ -0,0 +1,92 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import polars as pl
+
+from .base import Base
+
+if TYPE_CHECKING:
+    from datetime import timedelta
+    from typing import Self
+
+    from polars import Expr
+
+    from .statements import Statements
+
+
+class Prices(Base):
+    def truncate(self, every: str | timedelta | Expr) -> Self:
+        data = (
+            self.data.group_by(pl.col("Date").dt.truncate(every), "Code")
+            .agg(
+                pl.col("Open").drop_nulls().first(),
+                pl.col("High").max(),
+                pl.col("Low").min(),
+                pl.col("Close").drop_nulls().last(),
+                pl.col("Volume").sum(),
+                pl.col("TurnoverValue").sum(),
+            )
+            .sort("Code", "Date")
+        )
+        return self.__class__(data)
+
+    def with_adjusted_shares(self, statements: Statements) -> Self:
+        """日次の調整済み株式数を計算し、列として追加する。
+
+        決算短信で報告される株式数（例：発行済株式総数）は、四半期ごとなど
+        特定の日付のデータです。一方で、株式分割や併合は日々発生し、株式数を
+        変動させます。
+        このメソッドは、直近の決算で報告された株式数を、日々の調整係数
+        (`AdjustmentFactor`) を用いて補正し、日次ベースの時系列データとして
+        提供します。これにより、日々の時価総額計算などが正確に行えるようになります。
+
+        具体的には、`statements`から`TotalShares`（発行済株式総数）と
+        `TreasuryShares`（自己株式数）を取得し、それぞれを調整します。
+        計算結果は、元の列名との混同を避けるため、接頭辞`Adjusted`を付与した
+        新しい列（`AdjustedTotalShares`, `AdjustedTreasuryShares`）として
+        追加されます。
+
+        .. note::
+            この計算は、決算発表間の株式数の変動が、株式分割・併合
+            （`AdjustmentFactor`）にのみ起因すると仮定しています。
+            期中に行われる増資や自己株式取得など、`AdjustmentFactor`に
+            反映されないイベントによる株式数の変動は考慮されません。
+
+        Args:
+            statements (Statements): `number_of_shares()`メソッドを通じて
+                株式数データを提供できる`Statements`オブジェクト。
+
+        Returns:
+            Self: `AdjustedTotalShares`および`AdjustedTreasuryShares`列が
+            追加された、新しいPricesオブジェクト。
+        """
+        shares = statements.number_of_shares().rename({"Date": "ReportDate"})
+
+        adjusted = (
+            self.data.join_asof(
+                shares,
+                left_on="Date",
+                right_on="ReportDate",
+                by="Code",
+                check_sortedness=False,
+            )
+            .with_columns(
+                (1.0 / pl.col("AdjustmentFactor"))
+                .cum_prod()
+                .over("Code", "ReportDate")
+                .alias("CumulativeRatio"),
+            )
+            .select(
+                "Date",
+                "Code",
+                (pl.col("TotalShares", "TreasuryShares") * pl.col("CumulativeRatio"))
+                .round(0)
+                .cast(pl.Int64)
+                .name.prefix("Adjusted"),
+            )
+        )
+
+        data = self.data.join(adjusted, on=["Date", "Code"], how="left")
+
+        return self.__class__(data)

kabukit-0.4.0/src/kabukit/core/reports.py

@@ -0,0 +1,12 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+from .base import Base
+
+if TYPE_CHECKING:
+    from polars import DataFrame
+
+
+class Reports(Base):
+    pass

kabukit-0.4.0/src/kabukit/core/statements.py

@@ -0,0 +1,24 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import polars as pl
+
+from .base import Base
+
+if TYPE_CHECKING:
+    from polars import DataFrame
+
+
+class Statements(Base):
+    def number_of_shares(self) -> DataFrame:
+        """発行済株式数を取得する。"""
+        return self.data.filter(
+            pl.col("TotalShares").is_not_null(),
+        ).select(
+            "Date",
+            "Code",
+            "TotalShares",
+            "TreasuryShares",
+            "AverageOutstandingShares",
+        )

kabukit-0.4.0/src/kabukit/edinet/__init__.py

@@ -0,0 +1,3 @@
+from .concurrent import fetch, fetch_csv, fetch_list
+
+__all__ = ["fetch", "fetch_csv", "fetch_list"]

{kabukit-0.3.0 → kabukit-0.4.0}/src/kabukit/edinet/client.py

@@ -6,14 +6,13 @@ import zipfile
 from enum import StrEnum
 from typing import TYPE_CHECKING
 
-import polars as pl
 from polars import DataFrame
 
 from kabukit.core.client import Client
 from kabukit.utils.config import load_dotenv
 from kabukit.utils.params import get_params
 
-from .doc import clean_csv, clean_list
+from .doc import clean_csv, clean_list, read_csv
 
 if TYPE_CHECKING:
     import datetime
@@ -103,11 +102,8 @@ class EdinetClient(Client):
             for info in zf.infolist():
                 if info.filename.endswith(".csv"):
                     with zf.open(info) as f:
-                        return pl.read_csv(
-                            f.read(),
-                            separator="\t",
-                            encoding="utf-16-le",
-                        ).pipe(clean_csv, doc_id)
+                        df = read_csv(f.read())
+                        return clean_csv(df, doc_id)
 
         msg = "CSV is not available."
         raise ValueError(msg)

{kabukit-0.3.0 → kabukit-0.4.0}/src/kabukit/edinet/concurrent.py

@@ -83,13 +83,14 @@ async def fetch_list(
     if limit is not None:
         dates = dates[:limit]
 
-    return await fetch(
+    df = await fetch(
         "list",
         dates,
         max_concurrency=max_concurrency,
         progress=progress,
         callback=callback,
     )
+    return df.sort("Date")
 
 
 async def fetch_csv(
@@ -121,10 +122,11 @@ async def fetch_csv(
     if limit is not None:
         doc_ids = doc_ids[:limit]
 
-    return await fetch(
+    df = await fetch(
         "csv",
         doc_ids,
         max_concurrency=max_concurrency,
         progress=progress,
         callback=callback,
     )
+    return df.sort("docID")

kabukit-0.4.0/src/kabukit/edinet/doc.py

@@ -0,0 +1,46 @@
+from __future__ import annotations
+
+import datetime
+from typing import TYPE_CHECKING
+
+import polars as pl
+
+if TYPE_CHECKING:
+    from polars import DataFrame
+
+
+def clean_list(df: DataFrame, date: str | datetime.date) -> DataFrame:
+    if isinstance(date, str):
+        date = datetime.datetime.strptime(date, "%Y-%m-%d").date()  # noqa: DTZ007
+
+    null_columns = [c for c in df.columns if df[c].dtype == pl.Null]
+
+    return (
+        df.with_columns(
+            pl.col(null_columns).cast(pl.String),
+        )
+        .with_columns(
+            pl.lit(date).alias("Date"),
+            pl.col("^.+DateTime$").str.to_datetime("%Y-%m-%d %H:%M", strict=False),
+            pl.col("^period.+$").str.to_date("%Y-%m-%d", strict=False),
+            pl.col("^.+Flag$").cast(pl.Int8).cast(pl.Boolean),
+            pl.col("^.+Code$").cast(pl.String),
+        )
+        .select("Date", pl.exclude("Date"))
+    )
+
+
+def read_csv(data: bytes) -> DataFrame:
+    return pl.read_csv(
+        data,
+        separator="\t",
+        encoding="utf-16-le",
+        infer_schema_length=None,
+    )
+
+
+def clean_csv(df: DataFrame, doc_id: str) -> DataFrame:
+    return df.select(
+        pl.lit(doc_id).alias("docID"),
+        pl.all(),
+    )

kabukit-0.4.0/src/kabukit/jquants/__init__.py

@@ -0,0 +1,4 @@
+from .concurrent import fetch, fetch_all
+from .schema import rename
+
+__all__ = ["fetch", "fetch_all", "rename"]

{kabukit-0.3.0 → kabukit-0.4.0}/src/kabukit/jquants/client.py

@@ -257,6 +257,7 @@ class JQuantsClient(Client):
         date: str | datetime.date | None = None,
         *,
         clean: bool = True,
+        with_date: bool = True,
     ) -> DataFrame:
         """四半期毎の決算短信サマリーおよび業績・配当の修正に関する開示情報を取得する。
 
@@ -264,6 +265,8 @@ class JQuantsClient(Client):
             code (str, optional): 財務情報を取得する銘柄のコード。
             date (str | datetime.date, optional): 財務情報を取得する日付。
             clean (bool, optional): 取得したデータをクリーンアップするかどうか。
+            with_date (bool, optional): クリーンアップ後に営業日ベースで開示日の翌日を
+                計算して`Date`列を追加するかどうか。
 
         Returns:
             財務情報を含むDataFrame。
@@ -283,10 +286,12 @@ class JQuantsClient(Client):
         dfs = [df async for df in self.iter_pages(url, params, name)]
         df = pl.concat(dfs)
 
-        if df.is_empty():
+        if df.is_empty() or not clean:
             return df
 
-        return statements.clean(df) if clean else df
+        df = statements.clean(df)
+
+        return statements.with_date(df) if with_date else df
 
     async def get_announcement(self) -> DataFrame:
         """翌日発表予定の決算情報を取得する。

{kabukit-0.3.0 → kabukit-0.4.0}/src/kabukit/jquants/concurrent.py

@@ -23,7 +23,7 @@ async def fetch(
     progress: Progress | None = None,
     callback: Callback | None = None,
 ) -> DataFrame:
-    """全銘柄の各種データを取得し、単一のDataFrameにまとめて返す。
+    """複数の銘柄の各種データを取得し、単一のDataFrameにまとめて返す。
 
     Args:
         resource (str): 取得するデータの種類。JQuantsClientのメソッド名から"get_"を

{kabukit-0.3.0 → kabukit-0.4.0}/src/kabukit/jquants/schema.py

@@ -45,8 +45,9 @@ class PriceColumns(BaseColumns):
 
 
 class StatementColumns(BaseColumns):
-    Date = "開示日"
-    Time = "開示時刻"
+    Date = "日付"
+    DisclosedDate = "開示日"
+    DisclosedTime = "開示時刻"
     Code = "銘柄コード"
     DisclosureNumber = "開示番号"
     TypeOfDocument = "開示書類種別"
@@ -129,13 +130,10 @@ class StatementColumns(BaseColumns):
     ChangesInAccountingEstimates = "会計上の見積りの変更"
     RetrospectiveRestatement = "修正再表示"
 
-    # NumberOfIssuedAndOutstandingSharesAtTheEndOfFiscalYearIncludingTreasuryStock
-    NumberOfShares = "期末発行済株式数"
-    # NumberOfTreasuryStockAtTheEndOfFiscalYear
-    NumberOfTreasuryStock = "期末自己株式数"
-    AverageNumberOfShares = "期中平均株式数"
+    TotalShares = "期末発行済株式数" # 自己株式を含む (NumberOfIssuedAndOutstandingSharesAtTheEndOfFiscalYearIncludingTreasuryStock)
+    TreasuryShares = "期末自己株式数" # (NumberOfTreasuryStockAtTheEndOfFiscalYear)
+    AverageOutstandingShares = "期中平均株式数" # 自己株式を除く。EPSなどの計算に使用される (AverageNumberOfShares)
 
-    """
     NonConsolidatedNetSales = "売上高_非連結"
     NonConsolidatedOperatingProfit = "営業利益_非連結"
     NonConsolidatedOrdinaryProfit = "経常利益_非連結"
@@ -170,7 +168,6 @@ class StatementColumns(BaseColumns):
     NextYearForecastNonConsolidatedOrdinaryProfit = "経常利益_予想_翌事業年度期末_非連結"
     NextYearForecastNonConsolidatedProfit = "当期純利益_予想_翌事業年度期末_非連結"
     NextYearForecastNonConsolidatedEarningsPerShare = "一株あたり当期純利益_予想_翌事業年度期末_非連結"
-    """
 
 
 def rename(df: DataFrame, *, strict: bool = False) -> DataFrame:

{kabukit-0.3.0 → kabukit-0.4.0}/src/kabukit/jquants/statements.py

@@ -13,19 +13,18 @@ if TYPE_CHECKING:
 
 def clean(df: DataFrame) -> DataFrame:
     return (
-        df.select(pl.exclude(r"^.*\(REIT\)|.*NonConsolidated.*$"))
+        df.select(pl.exclude(r"^.*\(REIT\)$"))
         .rename(
             {
-                "DisclosedDate": "Date",
-                "DisclosedTime": "Time",
                 "LocalCode": "Code",
-                "NumberOfIssuedAndOutstandingSharesAtTheEndOfFiscalYearIncludingTreasuryStock": "NumberOfShares",  # noqa: E501
-                "NumberOfTreasuryStockAtTheEndOfFiscalYear": "NumberOfTreasuryStock",
+                "NumberOfIssuedAndOutstandingSharesAtTheEndOfFiscalYearIncludingTreasuryStock": "TotalShares",  # noqa: E501
+                "NumberOfTreasuryStockAtTheEndOfFiscalYear": "TreasuryShares",
+                "AverageNumberOfShares": "AverageOutstandingShares",
             },
         )
         .with_columns(
             pl.col("^.*Date$").str.to_date("%Y-%m-%d", strict=False),
-            pl.col("Time").str.to_time("%H:%M:%S", strict=False),
+            pl.col("DisclosedTime").str.to_time("%H:%M:%S", strict=False),
             pl.col("TypeOfCurrentPeriod").cast(pl.Categorical),
         )
         .pipe(_cast_float)
@@ -45,10 +44,17 @@ def _cast_float(df: DataFrame) -> DataFrame:
             "Earnings",
             "Equity",
             "NetSales",
-            "NumberOf",
             "PayoutRatio",
             "Profit",
         ]
+    ).with_columns(
+        pl.col(
+            "TotalShares",
+            "TreasuryShares",
+        ).cast(pl.Int64, strict=False),
+        pl.col(
+            "AverageOutstandingShares",
+        ).cast(pl.Float64, strict=False),
     )
 
 
@@ -77,15 +83,22 @@ def get_holidays(year: int | None = None, n: int = 10) -> list[datetime.date]:
     return sorted(dates.keys())
 
 
-def update_effective_date(df: DataFrame, year: int | None = None) -> DataFrame:
-    """開示日が休日や15時以降の場合、翌営業日に更新する。"""
-    holidays = get_holidays(year=year)
+def with_date(df: DataFrame, year: int | None = None) -> DataFrame:
+    """`Date`列を追加する。
 
-    cond = pl.col("Time").is_null() | (pl.col("Time") > datetime.time(15, 0))
+    開示日が休日のとき、あるいは、開示時刻が15時以降の場合、Dateを開示日の翌営業日に設定する。
+    """
+    is_after_hours = pl.col("DisclosedTime").is_null() | (
+        pl.col("DisclosedTime") > datetime.time(15, 0)
+    )
 
-    return df.with_columns(
-        pl.when(cond)
-        .then(pl.col("Date").dt.add_business_days(1, holidays=holidays))
-        .otherwise(pl.col("Date"))
+    holidays = get_holidays(year=year)
+
+    return df.select(
+        pl.when(is_after_hours)
+        .then(pl.col("DisclosedDate") + datetime.timedelta(days=1))
+        .otherwise(pl.col("DisclosedDate"))
+        .dt.add_business_days(0, holidays=holidays, roll="forward")
         .alias("Date"),
+        pl.all(),
     )

kabukit-0.3.0/src/kabukit/__init__.py

@@ -1,7 +0,0 @@
-from .core.info import Info
-from .core.prices import Prices
-from .core.statements import Statements
-from .edinet.client import EdinetClient
-from .jquants.client import JQuantsClient
-
-__all__ = ["EdinetClient", "Info", "JQuantsClient", "Prices", "Statements"]

kabukit-0.3.0/src/kabukit/core/prices.py

@@ -1,30 +0,0 @@
-from __future__ import annotations
-
-from typing import TYPE_CHECKING
-
-import polars as pl
-
-from .base import Base
-
-if TYPE_CHECKING:
-    from datetime import timedelta
-    from typing import Self
-
-    from polars import Expr
-
-
-class Prices(Base):
-    def truncate(self, every: str | timedelta | Expr) -> Self:
-        data = (
-            self.data.group_by(pl.col("Date").dt.truncate(every), "Code")
-            .agg(
-                pl.col("Open").drop_nulls().first(),
-                pl.col("High").max(),
-                pl.col("Low").min(),
-                pl.col("Close").drop_nulls().last(),
-                pl.col("Volume").sum(),
-                pl.col("TurnoverValue").sum(),
-            )
-            .sort("Code", "Date")
-        )
-        return self.__class__(data)

kabukit-0.3.0/src/kabukit/core/statements.py

@@ -1,7 +0,0 @@
-from __future__ import annotations
-
-from .base import Base
-
-
-class Statements(Base):
-    pass

kabukit-0.3.0/src/kabukit/edinet/__init__.py

@@ -1,3 +0,0 @@
-from .concurrent import fetch, fetch_list
-
-__all__ = ["fetch", "fetch_list"]

kabukit-0.3.0/src/kabukit/edinet/doc.py

@@ -1,32 +0,0 @@
-from __future__ import annotations
-
-import datetime
-from typing import TYPE_CHECKING
-
-import polars as pl
-
-if TYPE_CHECKING:
-    from polars import DataFrame
-
-
-def clean_list(df: DataFrame, date: str | datetime.date) -> DataFrame:
-    if isinstance(date, str):
-        date = datetime.datetime.strptime(date, "%Y-%m-%d").date()  # noqa: DTZ007
-
-    return df.with_columns(
-        pl.lit(date).alias("Date"),
-        pl.col("submitDateTime").str.to_datetime("%Y-%m-%d %H:%M", strict=False),
-        pl.col("^period.+$").str.to_date("%Y-%m-%d", strict=False),
-        pl.col("^.+Flag$").cast(pl.Int8).cast(pl.Boolean),
-        pl.col("^.+Code$").cast(pl.String),
-        pl.col("opeDateTime")
-        .cast(pl.String)
-        .str.to_datetime("%Y-%m-%d %H:%M", strict=False),
-    ).select("Date", pl.exclude("Date"))
-
-
-def clean_csv(df: DataFrame, doc_id: str) -> DataFrame:
-    return df.select(
-        pl.lit(doc_id).alias("docID"),
-        pl.all(),
-    )

kabukit-0.3.0/src/kabukit/jquants/__init__.py

@@ -1,3 +0,0 @@
-from .concurrent import fetch, fetch_all
-
-__all__ = ["fetch", "fetch_all"]