Adds Yahoo Finance client

requirements.txt

@@ -2,4 +2,5 @@ pydantic==2.7.0
 numpy~=1.24
 scipy==1.13.1
 TA-Lib
-matplotlib
+matplotlib
+yfinance~=0.2

requirements_dev.txt

@@ -8,4 +8,5 @@ invoke==2.2.0
 black==24.4.0
 flake8==7.0.0
 blacken-docs==1.16.0
-setuptools==71.1.0
+setuptools==71.1.0
+pandas-stubs

requirements_lock.txt

@@ -1,18 +1,21 @@
-alembic==1.13.1
-annotated-types==0.6.0
+annotated-types==0.7.0
 autoflake==2.3.1
+beautifulsoup4==4.12.3
 black==24.4.0
 blacken-docs==1.16.0
-certifi==2024.2.2
+build==1.2.1
+certifi==2024.7.4
 charset-normalizer==3.3.2
 click==8.1.7
 contourpy==1.2.1
 cycler==0.12.1
 docutils==0.21.2
 flake8==7.0.0
 fonttools==4.53.1
+frozendict==2.4.4
+html5lib==1.1
 idna==3.7
-importlib_metadata==7.1.0
+importlib_metadata==8.2.0
 iniconfig==2.0.0
 invoke==2.2.0
 isort==5.13.2
@@ -21,44 +24,53 @@ jaraco.context==5.3.0
 jaraco.functools==4.0.1
 keyring==25.2.1
 kiwisolver==1.4.5
-Mako==1.3.5
+lxml==5.2.2
 markdown-it-py==3.0.0
-MarkupSafe==2.1.5
 matplotlib==3.9.1
 mccabe==0.7.0
 mdurl==0.1.2
-more-itertools==10.2.0
+more-itertools==10.3.0
+multitasking==0.0.11
 mypy==1.9.0
 mypy-extensions==1.0.0
-nh3==0.2.17
+nh3==0.2.18
 numpy==1.26.4
 packaging==24.0
+pandas==2.2.2
+pandas-stubs==2.2.2.240603
 pathspec==0.12.1
+peewee==3.17.6
 pillow==10.4.0
-pkginfo==1.10.0
+pip-tools==7.4.1
+pkginfo==1.11.1
 platformdirs==4.2.2
 pluggy==1.5.0
-psycopg2-binary==2.9.9
 pycodestyle==2.11.1
 pydantic==2.7.0
 pydantic_core==2.18.1
 pyflakes==3.2.0
 Pygments==2.18.0
 pyparsing==3.1.2
+pyproject_hooks==1.1.0
 pytest==8.1.1
 python-dateutil==2.9.0.post0
-readme_renderer==43.0
-requests==2.31.0
+pytz==2024.1
+readme_renderer==44.0
+requests==2.32.3
 requests-toolbelt==1.0.0
 rfc3986==2.0.0
 rich==13.7.1
 scipy==1.13.1
 setuptools==71.1.0
 six==1.16.0
-SQLAlchemy==2.0.30
+soupsieve==2.5
 TA-Lib==0.4.32
 twine==5.0.0
-typing_extensions==4.11.0
-urllib3==2.2.1
+types-pytz==2024.1.0.20240417
+typing_extensions==4.12.2
+tzdata==2024.1
+urllib3==2.2.2
+webencodings==0.5.1
 wheel==0.43.0
-zipp==3.18.2
+yfinance==0.2.41
+zipp==3.19.2

typings/talib/abstract/__init__.pyi

@@ -1,4 +1,7 @@
 from typing import Any
-from numpy import ndarray, dtype, floating, float64
+from numpy import ndarray, dtype, float64
 
-def OBV(close: list[float] | ndarray[Any, dtype[float64]], volume: list[float] | ndarray[Any, dtype[float64]]) -> list[float]: ...
+def OBV(
+ close: list[float] | ndarray[Any, dtype[float64]],
+ volume: list[float] | ndarray[Any, dtype[float64]],
+) -> list[float]: ...

typings/yfinance/__init__.pyi

@@ -0,0 +1,24 @@
+from typing import Any
+import pandas as pd
+
+def download(
+ tickers: str,
+ start: str | None = None,
+ end: str | None = None,
+ actions: bool = False,
+ threads: bool = True,
+ ignore_tz: bool | None = None,
+ group_by: str = "column",
+ auto_adjust: bool = False,
+ back_adjust: bool = False,
+ repair: bool = False,
+ keepna: bool = False,
+ progress: bool = True,
+ period: str = "max",
+ interval: str = "1d",
+ prepost: bool = False,
+ proxy: str | None = None,
+ rounding: bool = False,
+ timeout: int | float = 10,
+ session: Any | None = None,
+) -> pd.DataFrame: ...

xarizmi/opendata/yahoo_finance.py

@@ -0,0 +1,75 @@
+"""A client to download Yahoo Finance data
+"""
+
+from datetime import datetime
+
+import pandas as pd
+import yfinance as yf
+
+from xarizmi.candlestick import CandlestickChart
+
+
+class YahooFinanceDailyDataClient:
+
+ def __init__(
+ self,
+ symbol: str,
+ start_date: str = "1900-01-01",
+ end_date: str | None = None,
+ ) -> None:
+ self.symbol = symbol
+ self.start_date = start_date
+ self.end_date = end_date
+
+ def extract(self) -> list[dict[str, str | float | pd.Timestamp]] | None:
+ stock_data: pd.DataFrame = yf.download(
+ self.symbol, start=self.start_date, end=self.end_date
+ )
+
+ if stock_data.empty:
+ print("Error fetching data for symbol:", self.symbol)
+ return None
+
+ # Reset the index to get 'Date' as a column
+ stock_data.reset_index(inplace=True)
+
+ return stock_data.to_dict(orient="records") # type: ignore
+
+ def transform(
+ self, data_list: list[dict[str, str | float | pd.Timestamp]]
+ ) -> list[dict[str, str | float | datetime | dict[str, dict[str, str]]]]:
+ candles_data = []
+ for single_candle_data in data_list:
+ temp = {}
+ temp["open"] = single_candle_data["Open"]
+ temp["high"] = single_candle_data["High"]
+ temp["low"] = single_candle_data["Low"]
+ temp["close"] = single_candle_data["Close"]
+ temp["volume"] = single_candle_data["Volume"]
+ temp["datetime"] = single_candle_data["Date"].to_pydatetime() # type: ignore # noqa:E501
+ temp["interval_type"] = "1day"
+ temp["symbol"] = {
+ "base_currency": {"name": self.symbol},
+ "quote_currency": {"name": "CAD"},
+ "fee_currency": {"name": "CAD"},
+ } # type: ignore
+ candles_data.append(temp)
+ return candles_data # type: ignore
+
+ def save_file(
+ self,
+ candles_data: list[
+ dict[str, str | float | datetime | dict[str, dict[str, str]]]
+ ],
+ filepath: str,
+ indent: int = 4,
+ ) -> None:
+ candles = CandlestickChart.model_validate({"candles": candles_data})
+ with open(filepath, "w") as f:
+ f.write(candles.model_dump_json(indent=indent))
+
+ def etl(self, filepath: str) -> None:
+ data_list = self.extract()
+ if data_list:
+ candles_data = self.transform(data_list=data_list)
+ self.save_file(candles_data=candles_data, filepath=filepath)