pfeed 0.0.2.dev1__tar.gz → 0.0.2.dev2__tar.gz

pfeed-0.0.2.dev2/PKG-INFO

@@ -0,0 +1,213 @@
+Metadata-Version: 2.1
+Name: pfeed
+Version: 0.0.2.dev2
+Summary: Data pipeline for algo-trading, getting and storing both real-time and historical data made easy.
+Home-page: https://pfund.ai
+License: Apache-2.0
+Keywords: trading,algo-trading,data pipeline,ETL,data lake,data warehouse,data integration,historical data,live data,data streaming
+Author: Stephen Yau
+Author-email: softwareentrepreneer+pfeed@gmail.com
+Requires-Python: >=3.10,<4.0
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Provides-Extra: all
+Provides-Extra: core
+Provides-Extra: dask
+Provides-Extra: dataops
+Provides-Extra: dfs
+Provides-Extra: polars
+Provides-Extra: spark
+Provides-Extra: storage
+Requires-Dist: adlfs (>=2024.7.0,<2025.0.0) ; extra == "storage" or extra == "all"
+Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
+Requires-Dist: bytewax (>=0.21.0,<0.22.0) ; extra == "dataops" or extra == "all"
+Requires-Dist: coiled (>=1.54.0,<2.0.0) ; extra == "dask" or extra == "dfs" or extra == "all"
+Requires-Dist: confluent-kafka (>=2.5.3,<3.0.0) ; extra == "dataops" or extra == "all"
+Requires-Dist: connectorx (>=0.3.3,<0.4.0) ; extra == "storage" or extra == "all"
+Requires-Dist: dask[complete] (>=2024.9.1,<2025.0.0) ; extra == "dask" or extra == "dfs" or extra == "all"
+Requires-Dist: databento (>=0.42.0,<0.43.0) ; extra == "core" or extra == "all"
+Requires-Dist: databricks-connect (>=15.4.2,<16.0.0) ; extra == "spark" or extra == "dfs" or extra == "all"
+Requires-Dist: fastparquet (>=2024.2.0,<2025.0.0)
+Requires-Dist: gcsfs (>=2024.9.0,<2025.0.0) ; extra == "storage" or extra == "all"
+Requires-Dist: minio (>=7.2.8,<8.0.0) ; extra == "core" or extra == "all"
+Requires-Dist: modin[all] (>=0.32.0,<0.33.0) ; extra == "core" or extra == "all"
+Requires-Dist: pandas (>=2.2.0,<3.0.0)
+Requires-Dist: pfund (>=0.0.2.dev1,<0.0.3)
+Requires-Dist: polars (>=1.7.1,<2.0.0) ; extra == "polars" or extra == "dfs" or extra == "all"
+Requires-Dist: polars-xdt (>=0.16.0,<0.17.0) ; extra == "polars" or extra == "dfs" or extra == "all"
+Requires-Dist: polygon-api-client (>=1.14.2,<2.0.0) ; extra == "core" or extra == "all"
+Requires-Dist: prefect (>=3.0.5,<4.0.0) ; extra == "dataops" or extra == "all"
+Requires-Dist: psutil (>=6.0.0,<7.0.0) ; extra == "core" or extra == "all"
+Requires-Dist: psycopg2 (>=2.9.9,<3.0.0) ; extra == "storage" or extra == "all"
+Requires-Dist: pyarrow (>=17.0.0,<18.0.0) ; extra == "core" or extra == "all"
+Requires-Dist: pydantic (>=2.7.0,<3.0.0)
+Requires-Dist: pyspark (>=3.5.3,<4.0.0) ; extra == "spark" or extra == "dfs" or extra == "all"
+Requires-Dist: ray (>=2.35.0,<3.0.0) ; extra == "core" or extra == "all"
+Requires-Dist: s3fs (>=2024.9.0,<2025.0.0) ; extra == "storage" or extra == "all"
+Requires-Dist: yfinance (>=0.2.43,<0.3.0)
+Project-URL: Documentation, https://pfeed-docs.pfund.ai
+Project-URL: Repository, https://github.com/PFund-Software-Ltd/pfeed
+Description-Content-Type: text/markdown
+
+# PFeed: Data Pipeline for Algo-Trading, Getting and Storing Real-Time and Historical Data Made Easy.
+
+[![Twitter Follow](https://img.shields.io/twitter/follow/pfund_ai?style=social)](https://x.com/pfund_ai)
+![GitHub stars](https://img.shields.io/github/stars/PFund-Software-Ltd/pfeed?style=social)
+![PyPI downloads](https://img.shields.io/pypi/dm/pfeed?label=downloads)
+[![PyPI](https://img.shields.io/pypi/v/pfeed.svg)](https://pypi.org/project/pfeed)
+![PyPI - Support Python Versions](https://img.shields.io/pypi/pyversions/pfeed)
+<!-- [![Jupyter Book Badge](https://raw.githubusercontent.com/PFund-Software-Ltd/pfeed/main/docs/images/jupyterbook.svg)](https://jupyterbook.org) -->
+[![Poetry](https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json)](https://python-poetry.org/)
+
+[MinIO]: https://min.io/
+[PFund]: https://github.com/PFund-Software-Ltd/pfund
+[Polars]: https://github.com/pola-rs/polars
+[Dask]: https://www.dask.org/
+[Spark]: https://spark.apache.org/docs/latest/api/python/index.html
+[PyTrade.org]: https://pytrade.org
+[Yahoo Finance]: https://github.com/ranaroussi/yfinance
+[Bybit]: https://public.bybit.com
+[Binance]: https://data.binance.vision
+[OKX]: https://www.okx.com/data-download
+[Databento]: https://databento.com/
+[Polygon]: https://polygon.io/
+[FirstRate Data]: https://firstratedata.com
+
+## Problem
+Starting algo-trading requires reliable, clean data. However, the time-consuming and mundane tasks of data cleaning and storage often discourage traders from embarking on their algo-trading journey.
+
+## Solution
+By leveraging modern data engineering tools, `pfeed` handles the tedious data work and **outputs backtesting-ready data**, allowing traders to focus on strategy development.
+
+---
+PFeed (/piː fiːd/) is a data pipeline for algorithmic trading, serving as a bridge between raw data sources and traders. It enables you to **download historical data**, **stream real-time data**, and **store cleaned data** in a **local data lake for quantitative analysis**, by automating the processes of data collection, cleaning, transformation, and storage.
+
+## Core Features
+- [x] Download or stream reliable, validated and **clean data** for research, backtesting, or live trading
+- [x] Get historical data (**dataframe**) or live data in standardized formats by just calling a **single** function
+- [x] **Own your data** by storing them locally using [MinIO], with the option to connect to the cloud
+- [x] Interact with different kinds of data (including TradFi, CeFi and DeFi) using a **unified interface**
+
+---
+
+<details>
+<summary>Table of Contents</summary>
+
+- [Installation](#installation)
+- [Quick Start](#quick-start)
+    - [Get Historical Data in Dataframe](#1-get-historical-data-in-dataframe-no-storage)
+    - [Download Historical Data on Command Line](#2-download-historical-data-on-the-command-line-interface-cli)
+    - [Download Historical Data in Python](#3-download-historical-data-in-python)
+- [Supported Data Sources](#supported-data-sources)
+- [Related Projects](#related-projects)
+- [Disclaimer](#disclaimer)
+
+</details>
+
+
+
+## Installation
+> For more installation options, please refer to the [documentation](https://pfeed-docs.pfund.ai/installation).
+```bash
+# [RECOMMENDED]: Full Features, choose this if you do not care about the package size
+pip install -U "pfeed[all]"
+
+# Minimal Features, only supports getting, downloading and streaming data
+pip install -U "pfeed[core]"
+```
+
+
+
+## Quick Start
+### 1. Get Historical Data in Dataframe (No storage)
+Get [Bybit]'s data in dataframe, e.g. 1-minute data (data is downloaded on the fly if not stored locally)
+
+```python
+import pfeed as pe
+
+feed = pe.BybitFeed(data_tool='polars')
+
+df = feed.get_historical_data(
+    'BTC_USDT_PERP',
+    resolution='1minute',  # 'raw' or '1tick'/'1t' or '2second'/'2s' etc.
+    start_date='2024-03-01',
+    end_date='2024-03-01',
+)
+```
+
+Printing the first few rows of `df`:
+|    | ts                  | product       | resolution   |    open |    high |     low |   close |   volume |
+|---:|:--------------------|:--------------|:-------------|--------:|--------:|--------:|--------:|---------:|
+|  0 | 2024-03-01 00:00:00 | BTC_USDT_PERP | 1m           | 61184.1 | 61244.5 | 61175.8 | 61244.5 |  159.142 |
+|  1 | 2024-03-01 00:01:00 | BTC_USDT_PERP | 1m           | 61245.3 | 61276.5 | 61200.7 | 61232.2 |  227.242 |
+|  2 | 2024-03-01 00:02:00 | BTC_USDT_PERP | 1m           | 61232.2 | 61249   | 61180   | 61184.2 |   91.446 |
+
+> By using pfeed, you are just a few lines of code away from getting a standardized dataframe, how convenient!
+
+### 2. Download Historical Data on the Command Line Interface (CLI)
+> For more CLI commands, please refer to the [documentation](https://pfeed-docs.pfund.ai/cli-commands).
+```bash
+# download data, default data type (dtype) is 'raw' data
+pfeed download -d BYBIT -p BTC_USDT_PERP --start-date 2024-03-01 --end-date 2024-03-08
+
+# download multiple products BTC_USDT_PERP and ETH_USDT_PERP as minute data and store them locally
+pfeed download -d BYBIT -p BTC_USDT_PERP -p ETH_USDT_PERP --dtypes minute --use-minio
+```
+
+### 3. Download Historical Data in Python
+```python
+import pfeed as pe
+
+# compared to the CLI approach, this approach is more convenient for downloading multiple products
+pe.download(
+    data_source='bybit',
+    pdts=[
+        'BTC_USDT_PERP',
+        'ETH_USDT_PERP',
+        'BCH_USDT_PERP',
+    ],
+    dtypes=['raw'],  # data types, e.g. 'raw', 'tick', 'second', 'minute' etc.
+    start_date='2024-03-01',
+    end_date='2024-03-08',
+    use_minio=False,
+)
+```
+
+
+
+## Supported Data Sources
+| Data Source          | Get Historical Data | Download Historical Data | Get Live Data | Stream Live Data |
+| -------------------- | ------------------- | ------------------------ | --------------| ---------------- |
+| [Yahoo Finance]      | 🟢                  | ⚪                        | ⚪            | ⚪               |
+| [Bybit]              | 🟢                  | 🟢                        | 🟡            | 🔴               |
+| *Interactive Brokers | 🔴                  | ⚪                        | 🔴            | 🔴               |
+| *[FirstRate Data]    | 🔴                  | 🔴                        | ⚪            | ⚪               |
+| *[Databento]         | 🔴                  | 🔴                        | 🔴            | 🔴               |
+| *[Polygon]           | 🔴                  | 🔴                        | 🔴            | 🔴               |
+| [Binance]            | 🔴                  | 🔴                        | 🔴            | 🔴               |
+| [OKX]                | 🔴                  | 🔴                        | 🔴            | 🔴               |
+
+🟢 = finished \
+🟡 = in progress \
+🔴 = todo \
+⚪ = not applicable \
+\* = paid data
+
+
+
+## Related Projects
+- [PFund] — A Complete Algo-Trading Framework for Machine Learning, TradFi, CeFi and DeFi ready. Supports Vectorized and Event-Driven Backtesting, Paper and Live Trading
+- [PyTrade.org] - A curated list of Python libraries and resources for algorithmic trading.
+
+
+
+## Disclaimer
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES, OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF, OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+This framework is intended for educational and research purposes only. It should not be used for real trading without understanding the risks involved. Trading in financial markets involves significant risk, and there is always the potential for loss. Your trading results may vary. No representation is being made that any account will or is likely to achieve profits or losses similar to those discussed on this platform.
+
+The developers of this framework are not responsible for any financial losses incurred from using this software. This includes but not limited to losses resulting from inaccuracies in any financial data output by PFeed. Users should conduct their due diligence, verify the accuracy of any data produced by PFeed, and consult with a professional financial advisor before engaging in real trading activities.
+

pfeed-0.0.2.dev2/README.md

@@ -0,0 +1,158 @@
+# PFeed: Data Pipeline for Algo-Trading, Getting and Storing Real-Time and Historical Data Made Easy.
+
+[![Twitter Follow](https://img.shields.io/twitter/follow/pfund_ai?style=social)](https://x.com/pfund_ai)
+![GitHub stars](https://img.shields.io/github/stars/PFund-Software-Ltd/pfeed?style=social)
+![PyPI downloads](https://img.shields.io/pypi/dm/pfeed?label=downloads)
+[![PyPI](https://img.shields.io/pypi/v/pfeed.svg)](https://pypi.org/project/pfeed)
+![PyPI - Support Python Versions](https://img.shields.io/pypi/pyversions/pfeed)
+<!-- [![Jupyter Book Badge](https://raw.githubusercontent.com/PFund-Software-Ltd/pfeed/main/docs/images/jupyterbook.svg)](https://jupyterbook.org) -->
+[![Poetry](https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json)](https://python-poetry.org/)
+
+[MinIO]: https://min.io/
+[PFund]: https://github.com/PFund-Software-Ltd/pfund
+[Polars]: https://github.com/pola-rs/polars
+[Dask]: https://www.dask.org/
+[Spark]: https://spark.apache.org/docs/latest/api/python/index.html
+[PyTrade.org]: https://pytrade.org
+[Yahoo Finance]: https://github.com/ranaroussi/yfinance
+[Bybit]: https://public.bybit.com
+[Binance]: https://data.binance.vision
+[OKX]: https://www.okx.com/data-download
+[Databento]: https://databento.com/
+[Polygon]: https://polygon.io/
+[FirstRate Data]: https://firstratedata.com
+
+## Problem
+Starting algo-trading requires reliable, clean data. However, the time-consuming and mundane tasks of data cleaning and storage often discourage traders from embarking on their algo-trading journey.
+
+## Solution
+By leveraging modern data engineering tools, `pfeed` handles the tedious data work and **outputs backtesting-ready data**, allowing traders to focus on strategy development.
+
+---
+PFeed (/piː fiːd/) is a data pipeline for algorithmic trading, serving as a bridge between raw data sources and traders. It enables you to **download historical data**, **stream real-time data**, and **store cleaned data** in a **local data lake for quantitative analysis**, by automating the processes of data collection, cleaning, transformation, and storage.
+
+## Core Features
+- [x] Download or stream reliable, validated and **clean data** for research, backtesting, or live trading
+- [x] Get historical data (**dataframe**) or live data in standardized formats by just calling a **single** function
+- [x] **Own your data** by storing them locally using [MinIO], with the option to connect to the cloud
+- [x] Interact with different kinds of data (including TradFi, CeFi and DeFi) using a **unified interface**
+
+---
+
+<details>
+<summary>Table of Contents</summary>
+
+- [Installation](#installation)
+- [Quick Start](#quick-start)
+    - [Get Historical Data in Dataframe](#1-get-historical-data-in-dataframe-no-storage)
+    - [Download Historical Data on Command Line](#2-download-historical-data-on-the-command-line-interface-cli)
+    - [Download Historical Data in Python](#3-download-historical-data-in-python)
+- [Supported Data Sources](#supported-data-sources)
+- [Related Projects](#related-projects)
+- [Disclaimer](#disclaimer)
+
+</details>
+
+
+
+## Installation
+> For more installation options, please refer to the [documentation](https://pfeed-docs.pfund.ai/installation).
+```bash
+# [RECOMMENDED]: Full Features, choose this if you do not care about the package size
+pip install -U "pfeed[all]"
+
+# Minimal Features, only supports getting, downloading and streaming data
+pip install -U "pfeed[core]"
+```
+
+
+
+## Quick Start
+### 1. Get Historical Data in Dataframe (No storage)
+Get [Bybit]'s data in dataframe, e.g. 1-minute data (data is downloaded on the fly if not stored locally)
+
+```python
+import pfeed as pe
+
+feed = pe.BybitFeed(data_tool='polars')
+
+df = feed.get_historical_data(
+    'BTC_USDT_PERP',
+    resolution='1minute',  # 'raw' or '1tick'/'1t' or '2second'/'2s' etc.
+    start_date='2024-03-01',
+    end_date='2024-03-01',
+)
+```
+
+Printing the first few rows of `df`:
+|    | ts                  | product       | resolution   |    open |    high |     low |   close |   volume |
+|---:|:--------------------|:--------------|:-------------|--------:|--------:|--------:|--------:|---------:|
+|  0 | 2024-03-01 00:00:00 | BTC_USDT_PERP | 1m           | 61184.1 | 61244.5 | 61175.8 | 61244.5 |  159.142 |
+|  1 | 2024-03-01 00:01:00 | BTC_USDT_PERP | 1m           | 61245.3 | 61276.5 | 61200.7 | 61232.2 |  227.242 |
+|  2 | 2024-03-01 00:02:00 | BTC_USDT_PERP | 1m           | 61232.2 | 61249   | 61180   | 61184.2 |   91.446 |
+
+> By using pfeed, you are just a few lines of code away from getting a standardized dataframe, how convenient!
+
+### 2. Download Historical Data on the Command Line Interface (CLI)
+> For more CLI commands, please refer to the [documentation](https://pfeed-docs.pfund.ai/cli-commands).
+```bash
+# download data, default data type (dtype) is 'raw' data
+pfeed download -d BYBIT -p BTC_USDT_PERP --start-date 2024-03-01 --end-date 2024-03-08
+
+# download multiple products BTC_USDT_PERP and ETH_USDT_PERP as minute data and store them locally
+pfeed download -d BYBIT -p BTC_USDT_PERP -p ETH_USDT_PERP --dtypes minute --use-minio
+```
+
+### 3. Download Historical Data in Python
+```python
+import pfeed as pe
+
+# compared to the CLI approach, this approach is more convenient for downloading multiple products
+pe.download(
+    data_source='bybit',
+    pdts=[
+        'BTC_USDT_PERP',
+        'ETH_USDT_PERP',
+        'BCH_USDT_PERP',
+    ],
+    dtypes=['raw'],  # data types, e.g. 'raw', 'tick', 'second', 'minute' etc.
+    start_date='2024-03-01',
+    end_date='2024-03-08',
+    use_minio=False,
+)
+```
+
+
+
+## Supported Data Sources
+| Data Source          | Get Historical Data | Download Historical Data | Get Live Data | Stream Live Data |
+| -------------------- | ------------------- | ------------------------ | --------------| ---------------- |
+| [Yahoo Finance]      | 🟢                  | ⚪                        | ⚪            | ⚪               |
+| [Bybit]              | 🟢                  | 🟢                        | 🟡            | 🔴               |
+| *Interactive Brokers | 🔴                  | ⚪                        | 🔴            | 🔴               |
+| *[FirstRate Data]    | 🔴                  | 🔴                        | ⚪            | ⚪               |
+| *[Databento]         | 🔴                  | 🔴                        | 🔴            | 🔴               |
+| *[Polygon]           | 🔴                  | 🔴                        | 🔴            | 🔴               |
+| [Binance]            | 🔴                  | 🔴                        | 🔴            | 🔴               |
+| [OKX]                | 🔴                  | 🔴                        | 🔴            | 🔴               |
+
+🟢 = finished \
+🟡 = in progress \
+🔴 = todo \
+⚪ = not applicable \
+\* = paid data
+
+
+
+## Related Projects
+- [PFund] — A Complete Algo-Trading Framework for Machine Learning, TradFi, CeFi and DeFi ready. Supports Vectorized and Event-Driven Backtesting, Paper and Live Trading
+- [PyTrade.org] - A curated list of Python libraries and resources for algorithmic trading.
+
+
+
+## Disclaimer
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES, OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF, OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+This framework is intended for educational and research purposes only. It should not be used for real trading without understanding the risks involved. Trading in financial markets involves significant risk, and there is always the potential for loss. Your trading results may vary. No representation is being made that any account will or is likely to achieve profits or losses similar to those discussed on this platform.
+
+The developers of this framework are not responsible for any financial losses incurred from using this software. This includes but not limited to losses resulting from inaccuracies in any financial data output by PFeed. Users should conduct their due diligence, verify the accuracy of any data produced by PFeed, and consult with a professional financial advisor before engaging in real trading activities.

{pfeed-0.0.2.dev1 → pfeed-0.0.2.dev2}/pfeed/__init__.py

@@ -8,32 +8,32 @@ import importlib
 from importlib.metadata import version
 
 from pfeed.config_handler import configure, get_config
-from pfeed.const.common import ALIASES
+from pfeed.const.common import ALIASES as aliases
 from pfeed.sources import bybit
 from pfeed.feeds import BybitFeed, YahooFinanceFeed
 
 
 def download_historical_data(
     data_source: tSUPPORTED_DOWNLOAD_DATA_SOURCES,
-    pdts: str | list[str] | None = None,
+    products: str | list[str] | None = None,
     dtypes: tSUPPORTED_DATA_TYPES | list[tSUPPORTED_DATA_TYPES] | None = None,
     ptypes: str | list[str] | None = None,
     start_date: str | None = None,
     end_date: str | None = None,
     use_minio: bool = False,
     use_ray: bool = True,
-    ray_num_cpus: int = 8,
+    num_cpus: int = 8,
 ):
     data_source = importlib.import_module(f"pfeed.sources.{data_source.lower()}")
     return data_source.download_historical_data(
-        pdts=pdts,
+        products=products,
         dtypes=dtypes,
         ptypes=ptypes,
         start_date=start_date,
         end_date=end_date,
         use_minio=use_minio,
         use_ray=use_ray,
-        ray_num_cpus=ray_num_cpus,
+        num_cpus=num_cpus,
     )
 
 
@@ -53,7 +53,7 @@ __all__ = (
     "__version__",
     "configure",
     "get_config",
-    "ALIASES",
+    "aliases",
     "bybit",
     "binance",
     "YahooFinanceFeed",

{pfeed-0.0.2.dev1 → pfeed-0.0.2.dev2}/pfeed/cli/commands/config.py

@@ -32,33 +32,30 @@ def remove_config(config_file_path: str | Path):
 @click.option('--use-fork-process', type=bool, help='If True, multiprocessing.set_start_method("fork")')
 @click.option('--use-custom-excepthook', type=bool, help='If True, log uncaught exceptions to file')
 @click.option('--env-file', 'env_file_path', type=click.Path(resolve_path=True, exists=True), help='Path to the .env file')
-@click.option('--debug', is_flag=True, help='if enabled, debug mode will be enabled where logs at DEBUG level will be printed')
-@click.option('--list', '-l', is_flag=True, is_eager=True, help='List all available options')
-@click.option('--reset', is_flag=True, is_eager=True, help='Reset the configuration to defaults') 
-def config(ctx, **kwargs):
+@click.option('--debug', '-d', type=bool, help='If True, enable debug mode where logs at DEBUG level will be printed')
+@click.option('--list', '-l', 'is_list', is_flag=True, is_eager=True, help='List all available options')
+@click.option('--reset', 'is_reset', is_flag=True, is_eager=True, help='Reset the configuration to defaults') 
+def config(ctx, is_list, is_reset, **kwargs):
     """Configures pfeed settings."""
     config: ConfigHandler = ctx.obj['config']
     
     # Filter out options that were not provided by the user
-    provided_options = {k: v for k, v in kwargs.items() if v is not None and v is not False}
+    provided_options = {k: v for k, v in kwargs.items() if v is not None}
     
-    if kwargs.get('list'):  # Check if --list was used
-        del provided_options['list']
+    if is_list:  # Check if --list was used
         assert not provided_options, "No options should be provided with --list"
         config_dict = config.__dict__
         config_dict.update({'config_file_path': USER_CONFIG_FILE_PATH})
         click.echo(f"PFeed's config:\n{pformat(config_dict)}")
         return
 
-    if kwargs.get('reset'): # Check if --reset was used
-        del provided_options['reset']
+    if is_reset:  # Check if --reset was used
         assert not provided_options, "No options should be provided with --reset"
         remove_config(USER_CONFIG_FILE_PATH)
         click.echo("PFeed's config successfully reset.")
-        return
     
     # prints out current config if no options are provided
-    if not provided_options:
+    if not provided_options and not is_list and not is_reset:
         raise click.UsageError("No options provided. Use --list to see all available options.")
     else:
         for option, value in provided_options.items():

{pfeed-0.0.2.dev1 → pfeed-0.0.2.dev2}/pfeed/cli/commands/download.py

@@ -21,7 +21,7 @@ SUPPORTED_DATA_TYPES_IMPLICIT_RAW_ALLOWED = SUPPORTED_DATA_TYPES + ['raw']
 
 @click.command()
 @click.option('--data-source', '-d', required=True, type=click.Choice(SUPPORTED_DOWNLOAD_DATA_SOURCES_ALIASES_INCLUDED, case_sensitive=False), help='Data source')
-@click.option('--pdts', '-p', 'pdts', multiple=True, default=[], help='List of trading products')
+@click.option('--products', '-p', 'products', multiple=True, default=[], help='List of trading products')
 @click.option('--dtypes', '--dt', 'dtypes', multiple=True, default=['raw'], type=click.Choice(SUPPORTED_DATA_TYPES_IMPLICIT_RAW_ALLOWED, case_sensitive=False), help=f'{SUPPORTED_DATA_TYPES=}. How to pass in multiple values: --dt raw --dt tick')
 @click.option('--ptypes', '--pt', 'ptypes', multiple=True, default=[], type=click.Choice(SUPPORTED_PRODUCT_TYPES, case_sensitive=False), help='List of product types, e.g. PERP = get all perpetuals')
 @click.option('--start-date', '-s', type=click.DateTime(formats=["%Y-%m-%d"]), help='Start date in YYYY-MM-DD format')
@@ -31,17 +31,17 @@ SUPPORTED_DATA_TYPES_IMPLICIT_RAW_ALLOWED = SUPPORTED_DATA_TYPES + ['raw']
 @click.option('--no-ray', is_flag=True, help='if enabled, Ray will not be used')
 @click.option('--env-file', 'env_file_path', type=click.Path(exists=True), help='Path to the .env file')
 @click.option('--debug', is_flag=True, help='if enabled, debug mode will be enabled where logs at DEBUG level will be printed')
-def download(data_source, pdts, dtypes, ptypes, start_date, end_date, num_cpus, no_ray, use_minio, env_file_path, debug):
+def download(data_source, products, dtypes, ptypes, start_date, end_date, num_cpus, no_ray, use_minio, env_file_path, debug):
     pe.configure(env_file_path=env_file_path, debug=debug)
     data_source = ALIASES.get(data_source, data_source)
     pipeline = importlib.import_module(f'pfeed.sources.{data_source.lower()}.download')
     pipeline.download_historical_data(
-        pdts=pdts,
+        products=products,
         dtypes=dtypes,
         ptypes=ptypes,
         start_date=start_date.date().strftime('%Y-%m-%d') if start_date else start_date,
         end_date=end_date.date().strftime('%Y-%m-%d') if end_date else end_date,
         use_ray=not no_ray,
-        ray_num_cpus=num_cpus,
+        num_cpus=num_cpus,
         use_minio=use_minio,
     )

{pfeed-0.0.2.dev1 → pfeed-0.0.2.dev2}/pfeed/cli/main.py

@@ -6,6 +6,7 @@ from pfeed.cli.commands.config import config
 from pfeed.cli.commands.download import download
 # from pfeed.cli.commands.stream import stream
 from pfeed.cli.commands.open import open
+from pfeed.cli.commands.doc import doc
 
 
 @click.group(context_settings={"help_option_names": ["-h", "--help"]})
@@ -21,4 +22,5 @@ pfeed_group.add_command(docker_compose)
 pfeed_group.add_command(config)
 pfeed_group.add_command(download)
 # pfeed_group.add_command(stream)
-pfeed_group.add_command(open)
+pfeed_group.add_command(open)
+pfeed_group.add_command(doc)

{pfeed-0.0.2.dev1 → pfeed-0.0.2.dev2}/pfeed/config_handler.py

@@ -33,7 +33,7 @@ class ConfigHandler:
     logging_config: dict | None = None
     use_fork_process: bool = True
     use_custom_excepthook: bool = False
-    env_file_path: str | None=None
+    env_file_path: str = ''
     debug: bool = False
     
     @classmethod
@@ -57,9 +57,9 @@ class ConfigHandler:
         return cls(**config)
     
     def __post_init__(self):
-        self.initialize()
+        self._initialize()
     
-    def initialize(self):
+    def _initialize(self):
         self.logging_config = self.logging_config or {}
         
         for path in [self.data_path]:
@@ -76,19 +76,15 @@ class ConfigHandler:
         self.load_env_file(self.env_file_path)
         
         if self.debug:
-            is_loggers_set_up = bool(logging.getLogger('pfeed').handlers)
-            if is_loggers_set_up:
-                print('loggers are already set up, ignoring enabling debug mode')
-            else:
-                self.enable_debug_mode()
+            self.enable_debug_mode()
     
-    def load_env_file(self, env_file_path: str | None):
+    def load_env_file(self, env_file_path: str=''):
         from dotenv import find_dotenv, load_dotenv
         
         if not env_file_path:
-            found_env_file_path = find_dotenv(usecwd=True, raise_error_if_not_found=False)
-            if found_env_file_path:
-                print(f'.env file path is not specified, using env file in "{found_env_file_path}"')
+            env_file_path = find_dotenv(usecwd=True, raise_error_if_not_found=False)
+            if env_file_path:
+                print(f'.env file path is not specified, using env file in "{env_file_path}"')
             else:
                 # print('.env file is not found')
                 return
@@ -96,6 +92,10 @@ class ConfigHandler:
     
     def enable_debug_mode(self):
         '''Enables debug mode by setting the log level to DEBUG for all stream handlers'''
+        is_loggers_set_up = bool(logging.getLogger('pfeed').handlers)
+        if is_loggers_set_up:
+            print('loggers are already set up, ignoring debug mode')
+            return
         if 'handlers' not in self.logging_config:
             self.logging_config['handlers'] = {}
         for handler in ['stream_handler', 'stream_path_handler']:
@@ -145,7 +145,7 @@ def configure(
         else:
             raise AttributeError(f'{k} is not an attribute of ConfigHandler')
     
-    _global_config.initialize()
+    _global_config._initialize()
     return _global_config
 
 

pfeed-0.0.2.dev2/pfeed/const/common.py

@@ -0,0 +1,32 @@
+from pfeed.types.common_literals import tSUPPORTED_DATA_TOOLS, tSUPPORTED_DATA_ENGINES
+
+
+SUPPORTED_ENVIRONMENTS = ['BACKTEST', 'SANDBOX', 'PAPER', 'LIVE']
+SUPPORTED_DATA_FEEDS = ['YAHOO_FINANCE', 'BYBIT', 'BINANCE']
+SUPPORTED_STORAGES = ['local', 'minio']
+SUPPORTED_DOWNLOAD_DATA_SOURCES = ['BYBIT', 'BINANCE']
+SUPPORTED_CRYPTO_EXCHANGES = ['BYBIT', 'BINANCE']
+SUPPORTED_DATA_TOOLS: dict[tSUPPORTED_DATA_TOOLS, tSUPPORTED_DATA_ENGINES | bool] = {
+    'pandas': ['dask'],
+    'polars': ['ray'],
+    # True means the data tool is also an execution engine
+    'dask': True,
+    'spark': True,
+}
+SUPPORTED_DATA_ENGINES: dict[tSUPPORTED_DATA_ENGINES, list[str]] = {
+    # execution engine: supported cloud services
+    'dask': ['coiled'],
+    'spark': ['databricks'],
+    'ray': ['aws'],
+}
+SUPPORTED_CLOUDS = ['aws']
+SUPPORTED_PRODUCT_TYPES = ['SPOT', 'PERP', 'IPERP', 'FUT', 'IFUT']
+SUPPORTED_DATA_TYPES = [
+    'raw_tick', 'raw_second', 'raw_minute', 'raw_hour', 'raw_daily',
+    'tick', 'second', 'minute', 'hour', 'daily',
+]
+
+ALIASES = {
+    'YF': 'YAHOO_FINANCE',
+    'FRD': 'FIRSTRATE_DATA'
+}