pyalloq-data-connector 0.1.4__tar.gz

pyalloq_data_connector-0.1.4/PKG-INFO

@@ -0,0 +1,61 @@
+Metadata-Version: 2.3
+Name: pyalloq-data-connector
+Version: 0.1.4
+Summary: Vendor-agnostic data adapters for PyAlloq.
+Author: Siddeshkanth
+Author-email: Siddeshkanth <pyalloq-info@alloq-alpha.com>
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Intended Audience :: Financial and Insurance Industry
+Classifier: Topic :: Scientific/Engineering :: Mathematics
+Classifier: Topic :: Office/Business :: Financial :: Investment
+Requires-Dist: numpy>=1.24
+Requires-Dist: pandas>=2.0
+Requires-Dist: yfinance>=1.6.0
+Requires-Dist: requests>=2.31
+Requires-Dist: pyalloq-core
+Requires-Python: >=3.11
+Project-URL: Homepage, https://github.com/your-org/qpo
+Project-URL: Repository, https://github.com/your-org/qpo
+Project-URL: Issues, https://github.com/your-org/qpo/issues
+Description-Content-Type: text/markdown
+
+# pyalloq-data-connector
+
+`pyalloq-data-connector` provides vendor-agnostic data adapters for **PyAlloq**. It handles fetching raw market data from various third-party APIs and automatically standardizes them into pure, time-aligned `MarketData` objects.
+
+## Supported Adapters
+
+- **`YahooFinanceClient`**: Free adapter using Yahoo Finance (`yfinance`). No API key required.
+- **`AlphaVantageClient`**: Adapter for Alpha Vantage Time Series Daily API.
+- **`FinnhubClient`**: Adapter for Finnhub's stock candle endpoint.
+- **`EODHistoricalDataClient`**: Adapter for EOD Historical Data API.
+
+## Features
+
+- **Standardized Output**: Automatically converts heterogeneous JSON/DataFrame vendor payloads into `T x N` aligned price matrices (`MarketData`).
+- **Missing Value Handling**: Implements forward filling (`ffill`) for prices and zero-filling for volume data.
+- **Time Alignment**: Constructs unified datetime indices across all requested ticker symbols.
+
+## Quick Example
+
+```python
+import datetime as dt
+from pyalloq_data_connector.yahoo_finance import YahooFinanceClient
+
+client = YahooFinanceClient()
+start = dt.datetime(2023, 1, 1)
+end = dt.datetime(2024, 1, 1)
+
+# Fetch standardized MarketData object
+market_data = client.get_market_data(
+    tickers=["AAPL", "MSFT", "GOOGL"],
+    start=start,
+    end=end
+)
+
+print(market_data.prices.head())
+print(market_data.features["volume"].head())
+```

pyalloq_data_connector-0.1.4/README.md

@@ -0,0 +1,37 @@
+# pyalloq-data-connector
+
+`pyalloq-data-connector` provides vendor-agnostic data adapters for **PyAlloq**. It handles fetching raw market data from various third-party APIs and automatically standardizes them into pure, time-aligned `MarketData` objects.
+
+## Supported Adapters
+
+- **`YahooFinanceClient`**: Free adapter using Yahoo Finance (`yfinance`). No API key required.
+- **`AlphaVantageClient`**: Adapter for Alpha Vantage Time Series Daily API.
+- **`FinnhubClient`**: Adapter for Finnhub's stock candle endpoint.
+- **`EODHistoricalDataClient`**: Adapter for EOD Historical Data API.
+
+## Features
+
+- **Standardized Output**: Automatically converts heterogeneous JSON/DataFrame vendor payloads into `T x N` aligned price matrices (`MarketData`).
+- **Missing Value Handling**: Implements forward filling (`ffill`) for prices and zero-filling for volume data.
+- **Time Alignment**: Constructs unified datetime indices across all requested ticker symbols.
+
+## Quick Example
+
+```python
+import datetime as dt
+from pyalloq_data_connector.yahoo_finance import YahooFinanceClient
+
+client = YahooFinanceClient()
+start = dt.datetime(2023, 1, 1)
+end = dt.datetime(2024, 1, 1)
+
+# Fetch standardized MarketData object
+market_data = client.get_market_data(
+    tickers=["AAPL", "MSFT", "GOOGL"],
+    start=start,
+    end=end
+)
+
+print(market_data.prices.head())
+print(market_data.features["volume"].head())
+```

pyalloq_data_connector-0.1.4/pyproject.toml

@@ -0,0 +1,60 @@
+[build-system]
+requires = ["uv_build>=0.10.9,<0.11.0"]
+build-backend = "uv_build"
+
+[project]
+name = "pyalloq-data-connector"
+version = "0.1.4"
+description = "Vendor-agnostic data adapters for PyAlloq."
+readme = "README.md"
+authors = [
+    { name = "Siddeshkanth", email = "pyalloq-info@alloq-alpha.com" }
+]
+requires-python = ">=3.11"
+
+classifiers = [
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "License :: OSI Approved :: MIT License",
+  "Intended Audience :: Financial and Insurance Industry",
+  "Topic :: Scientific/Engineering :: Mathematics",
+  "Topic :: Office/Business :: Financial :: Investment",
+]
+
+dependencies = [
+  "numpy>=1.24",
+  "pandas>=2.0",
+  "yfinance>=1.6.0",
+  "requests>=2.31",
+  "pyalloq-core"
+]
+
+[dependency-groups]
+dev = [
+    "pytest>=8",
+    "pytest-cov>=5",
+    "ruff>=0.6",
+    "mypy>=1.11",
+    "types-requests>=2.0",
+    "pandas-stubs>=3.0.5.260730",
+]
+
+[project.urls]
+Homepage = "https://github.com/your-org/qpo"
+Repository = "https://github.com/your-org/qpo"
+Issues = "https://github.com/your-org/qpo/issues"
+
+[tool.setuptools.packages.find]
+where = ["src/"]
+
+[[tool.mypy.overrides]]
+module = [
+    "numpy.*",
+    "pandas.*",
+    "yfinance.*"
+]
+ignore_missing_imports = true
+
+[tool.uv.sources]
+pyalloq-core = { workspace = true }

pyalloq_data_connector-0.1.4/src/pyalloq_data_connector/alpha_vantage.py

@@ -0,0 +1,46 @@
+import requests
+import pandas as pd
+import datetime as dt
+from pyalloq_data_connector.base import BaseDataClient
+
+
+class AlphaVantageClient(BaseDataClient):
+    """Adapter for Alpha Vantage Time Series Daily."""
+
+    BASE_URL = "https://www.alphavantage.co/query"
+
+    def fetch_raw_data(
+        self, tickers: list[str], start: dt.datetime, end: dt.datetime
+    ) -> dict[str, pd.DataFrame]:
+        if not self.api_key:
+            raise ValueError("Alpha Vantage requires an API key.")
+
+        raw_dict = {}
+        start_ts = pd.Timestamp(start)
+        end_ts = pd.Timestamp(end)
+
+        for ticker in tickers:
+            params = {
+                "function": "TIME_SERIES_DAILY",
+                "symbol": ticker,
+                "outputsize": "full",
+                "apikey": self.api_key,
+            }
+
+            response = requests.get(self.BASE_URL, params=params)
+            data = response.json()
+
+            if "Time Series (Daily)" not in data:
+                print(f"Warning: Alpha Vantage failed for {ticker}. Check API limits.")
+                continue
+
+            df = pd.DataFrame.from_dict(data["Time Series (Daily)"], orient="index")
+            df.index = pd.to_datetime(df.index)
+
+            df.columns = [col.split(" ")[1] for col in df.columns]
+            df = df.astype(float)
+
+            mask = (df.index >= start_ts) & (df.index <= end_ts)
+            raw_dict[ticker] = df.loc[mask].sort_index()
+
+        return raw_dict

pyalloq_data_connector-0.1.4/src/pyalloq_data_connector/base.py

@@ -0,0 +1,100 @@
+from abc import ABC, abstractmethod
+import pandas as pd
+from pyalloq_core.data import MarketData
+import datetime as dt
+
+
+class BaseDataClient(ABC):
+    """
+    Abstract base class for all third-party data providers.
+    Ensures raw API data is always converted to MarketData format.
+    """
+
+    def __init__(self, api_key: str | None = None):
+        self.api_key = api_key
+
+    @abstractmethod
+    def fetch_raw_data(
+        self,
+        tickers: list[str],
+        start_date: dt.datetime,
+        end_date: dt.datetime,
+    ) -> dict[str, pd.DataFrame]:
+        """
+        Fetches OHLCV data from the provider and packages it into MarketData.
+
+        Args:
+            tickers: List of asset symbols (e.g., ['AAPL', 'MSFT'])
+            start_date: YYYY-MM-DD string
+            end_date: YYYY-MM-DD string
+
+        Returns:
+            MarketData: The standardized PyAlloq data container.
+        """
+        pass
+
+    def get_market_data(
+        self,
+        tickers: list[str],
+        start: dt.datetime,
+        end: dt.datetime,
+    ) -> MarketData:
+        """
+        The orchestrator method. Standardizes whatever chaotic data the vendor
+        returns into mathematically pure T x N matrices, perfectly aligned in time.
+        """
+        raw_dict = self.fetch_raw_data(tickers, start, end)
+
+        closes, volumes, opens, highs, lows = {}, {}, {}, {}, {}
+        all_dates = pd.DatetimeIndex([])
+
+        for ticker, df in raw_dict.items():
+            df.columns = [str(c).lower() for c in df.columns]
+
+            closes[ticker] = df.get("close", df.get("adj close"))
+            if "volume" in df.columns:
+                volumes[ticker] = df["volume"]
+            if "open" in df.columns:
+                opens[ticker] = df["open"]
+            if "high" in df.columns:
+                highs[ticker] = df["high"]
+            if "low" in df.columns:
+                lows[ticker] = df["low"]
+
+            dt_index = pd.to_datetime(df.index)
+            all_dates = all_dates.union(dt_index)
+
+        all_dates = all_dates.sort_values()
+
+        def build_and_align(series_dict: dict, fill_method: str) -> pd.DataFrame:
+            if not series_dict:
+                return pd.DataFrame()
+
+            df = pd.DataFrame(series_dict)
+            df = df.reindex(all_dates)
+
+            if fill_method == "ffill":
+                return df.ffill()
+            elif fill_method == "zero":
+                return df.fillna(0.0)
+            return df
+
+        prices_df = build_and_align(closes, fill_method="ffill")
+
+        features = {}
+        if volumes:
+            features["volume"] = build_and_align(volumes, fill_method="zero")
+        if opens:
+            features["open"] = build_and_align(opens, fill_method="ffill")
+        if highs:
+            features["high"] = build_and_align(highs, fill_method="ffill")
+        if lows:
+            features["low"] = build_and_align(lows, fill_method="ffill")
+
+        valid_indices = prices_df.dropna(how="all").index
+        prices_df = prices_df.loc[valid_indices]
+
+        for key in features:
+            features[key] = features[key].loc[valid_indices]
+
+        return MarketData(prices=prices_df, features=features)

pyalloq_data_connector-0.1.4/src/pyalloq_data_connector/eod.py

@@ -0,0 +1,45 @@
+import requests
+import pandas as pd
+import datetime as dt
+from pyalloq_data_connector.base import BaseDataClient
+
+
+class EODClient(BaseDataClient):
+    """Adapter for EOD Historical Data (eodhd.com)."""
+
+    BASE_URL = "https://eodhd.com/api/eod"
+
+    def fetch_raw_data(
+        self, tickers: list[str], start: dt.datetime, end: dt.datetime
+    ) -> dict[str, pd.DataFrame]:
+        if not self.api_key:
+            raise ValueError("EODHD requires an API key.")
+
+        start_str = start.strftime("%Y-%m-%d")
+        end_str = end.strftime("%Y-%m-%d")
+
+        raw_dict = {}
+        for ticker in tickers:
+            url = f"{self.BASE_URL}/{ticker}"
+            params = {
+                "api_token": self.api_key,
+                "fmt": "json",
+                "from": start_str,
+                "to": end_str,
+            }
+
+            response = requests.get(url, params=params)
+            if response.status_code != 200:
+                print(
+                    f"Warning: EOD returned status {response.status_code} for {ticker}"
+                )
+                continue
+
+            df = pd.DataFrame(response.json())
+            if not df.empty:
+                df["date"] = pd.to_datetime(df["date"])
+                df.set_index("date", inplace=True)
+                df["close"] = df["adjusted_close"]
+                raw_dict[ticker] = df
+
+        return raw_dict

pyalloq_data_connector-0.1.4/src/pyalloq_data_connector/finnhub.py

@@ -0,0 +1,56 @@
+import requests
+import pandas as pd
+import datetime as dt
+from pyalloq_data_connector.base import BaseDataClient
+import time
+
+
+class FinnhubClient(BaseDataClient):
+    """Adapter for Finnhub's stock candle endpoint."""
+
+    BASE_URL = "https://finnhub.io/api/v1/stock/candle"
+
+    def fetch_raw_data(
+        self, tickers: list[str], start: dt.datetime, end: dt.datetime
+    ) -> dict[str, pd.DataFrame]:
+        if not self.api_key:
+            raise ValueError("Finnhub requires an API key.")
+
+        raw_dict = {}
+
+        start_unix = int(start.timestamp())
+        end_unix = int(end.timestamp())
+
+        for ticker in tickers:
+            params: dict[str, str | int] = {
+                "symbol": ticker,
+                "resolution": "D",  # Daily bars
+                "from": start_unix,
+                "to": end_unix,
+                "token": self.api_key,
+            }
+
+            response = requests.get(self.BASE_URL, params=params)
+            data = response.json()
+
+            if data.get("s") != "ok":
+                print(f"Warning: Finnhub returned no data or error for {ticker}")
+                continue
+
+            df = pd.DataFrame(
+                {
+                    "open": data["o"],
+                    "high": data["h"],
+                    "low": data["l"],
+                    "close": data["c"],
+                    "volume": data["v"],
+                },
+                index=pd.to_datetime(data["t"], unit="s"),
+            )
+
+            dt_idx = pd.DatetimeIndex(df.index)
+            df.index = dt_idx.tz_localize(None).normalize()
+            raw_dict[ticker] = df
+            time.sleep(0.5)
+
+        return raw_dict

pyalloq_data_connector-0.1.4/src/pyalloq_data_connector/py.typed

@@ -0,0 +1 @@
+# Marker file for PEP 561

pyalloq_data_connector-0.1.4/src/pyalloq_data_connector/yahoo_finance.py

@@ -0,0 +1,36 @@
+import yfinance as yf
+import pandas as pd
+import datetime as dt
+from pyalloq_data_connector.base import BaseDataClient
+from pyalloq_core.data import MarketData
+
+
+class YahooFinanceClient(BaseDataClient):
+    """
+    Adapter for Yahoo Finance.
+    Does not require an API key.
+    """
+
+    def __init__(self):
+        super().__init__(api_key=None)
+
+    def fetch_raw_data(
+        self, tickers: list[str], start: dt.datetime, end: dt.datetime
+    ) -> dict[str, pd.DataFrame]:
+        raw_dict = {}
+        for t in tickers:
+            yt = yf.Ticker(t)
+            df = yt.history(start=start, end=end, auto_adjust=True)
+
+            if not df.empty:
+                df.index = pd.to_datetime(df.index).tz_localize(None)
+                raw_dict[t] = df
+            else:
+                print(f"Warning: No data found for {t} on Yahoo Finance.")
+
+        return raw_dict
+
+    def fetch_historical_prices(
+        self, tickers: list[str], start_date: dt.datetime, end_date: dt.datetime
+    ) -> MarketData:
+        return self.get_market_data(tickers, start_date, end_date)