%load_ext autoreload
%autoreload 2The autoreload extension is already loaded. To reload it, use:
%reload_ext autoreload
from pytrade.table import repos_table
from pytrade.enums import ProjectStatusData Libraries¶
Disclaimer: I am the creator of
pfeed
REPOS = {
"pfeed": {
"github": "PFund-Software-Ltd/pfeed",
"Status": ProjectStatus.ACTIVE,
"Historical Data": True,
"Streaming Data": True,
},
"defeat-beta": {
"github": "defeat-beta/defeatbeta-api",
"Status": ProjectStatus.ACTIVE,
"Historical Data": True,
"Streaming Data": False,
},
"yfinance": {
"github": "ranaroussi/yfinance",
"Status": ProjectStatus.ACTIVE,
"Historical Data": True,
"Streaming Data": True,
},
"ccxt": {
"github": "ccxt/ccxt",
"Status": ProjectStatus.ACTIVE,
"Historical Data": False,
"Streaming Data": True,
},
"FinanceDatabase": {
"github": "jerbouma/FinanceDatabase",
"Status": ProjectStatus.ACTIVE,
"Historical Data": True,
"Streaming Data": False,
},
"cryptofeed": {
"github": "bmoscon/cryptofeed",
"Status": ProjectStatus.INACTIVE,
"Historical Data": False,
"Streaming Data": True,
},
"binance-public-data": {
"github": "binance/binance-public-data",
"Status": ProjectStatus.INACTIVE,
"Historical Data": True,
"Streaming Data": False,
},
}
repos_table(REPOS)Loading...
“✔️” = SUPPORTED
“✖️” = NOT SUPPORTED
Data Tools¶
REPOS = {
"polars": {
"github": "pola-rs/polars",
"Status": ProjectStatus.ACTIVE,
},
"daft": {
"github": "eventual-inc/daft",
"Status": ProjectStatus.ACTIVE,
},
"pandas": {
"github": "pandas-dev/pandas",
"Status": ProjectStatus.ACTIVE,
},
"dask": {
"github": "dask/dask",
"Status": ProjectStatus.ACTIVE,
},
"spark": {
"github": "apache/spark",
"Status": ProjectStatus.ACTIVE,
},
"bodo": {
"github": "bodo-ai/Bodo",
"Status": ProjectStatus.ACTIVE,
},
"ibis": {
"github": "ibis-project/ibis",
"Status": ProjectStatus.ACTIVE,
},
"fugue": {
"github": "fugue-project/fugue",
"Status": ProjectStatus.ACTIVE,
},
"vaex": {
"github": "vaexio/vaex",
"Status": ProjectStatus.ACTIVE,
},
"datafusion": {
"github": "apache/datafusion",
"Status": ProjectStatus.ACTIVE,
},
"velox": {
"github": "facebookincubator/velox",
"Status": ProjectStatus.ACTIVE,
},
"sqlglot": {
"github": "tobymao/sqlglot",
"Status": ProjectStatus.ACTIVE,
},
"modin": {
"github": "modin-project/modin",
"Status": ProjectStatus.INACTIVE,
},
}
repos_table(REPOS)Loading...
Data Formats & Storage¶
Only installable databases are considered storage
REPOS = {
"duckdb": {
"github": "duckdb/duckdb",
"Status": ProjectStatus.ACTIVE,
},
"lancedb": {
"github": "lancedb/lancedb",
"Status": ProjectStatus.ACTIVE,
},
"chdb": {
"github": "chdb-io/chdb",
"Status": ProjectStatus.ACTIVE,
},
"arcticdb": {
"github": "man-group/arcticdb",
"Status": ProjectStatus.ACTIVE,
},
"sqlite": {
"github": "sqlite/sqlite",
"Status": ProjectStatus.ACTIVE,
},
"arrow": {
"github": "apache/arrow",
"Status": ProjectStatus.ACTIVE,
},
"parquet": {
"github": "apache/parquet-format",
"Status": ProjectStatus.ACTIVE,
},
"vortex": {
"github": "vortex-data/vortex",
"Status": ProjectStatus.ACTIVE,
},
"deltalake": {
"github": "delta-io/delta-rs",
"Status": ProjectStatus.ACTIVE,
},
"iceberg": {
"github": "apache/iceberg-python",
"Status": ProjectStatus.ACTIVE,
},
"ducklake": {
"github": "duckdb/ducklake",
"Status": ProjectStatus.ACTIVE,
},
"avro": {
"github": "apache/avro",
"Status": ProjectStatus.ACTIVE,
},
"hdf5": {
"github": "HDFGroup/hdf5",
"Status": ProjectStatus.ACTIVE,
},
}
repos_table(REPOS)Loading...
Data Streaming¶
REPOS ={
"pathway": {
"github": "pathwaycom/pathway",
"Status": ProjectStatus.ACTIVE,
},
"csp": {
"github": "Point72/csp",
"Status": ProjectStatus.ACTIVE,
},
"quix-stream": {
"github": "quixio/quix-streams",
"Status": ProjectStatus.ACTIVE,
},
"faststream": {
"github": "ag2ai/faststream",
"Status": ProjectStatus.ACTIVE,
},
"bytewax": {
"github": "bytewax/bytewax",
"Status": ProjectStatus.UNMAINTAINED,
},
}
repos_table(REPOS)Loading...
Data Preparation & Validation¶
REPOS ={
"cleanlab": {
"github": "cleanlab/cleanlab",
"Status": ProjectStatus.ACTIVE,
},
"skrub": {
"github": "skrub-data/skrub",
"Status": ProjectStatus.ACTIVE,
},
"pyjanitor": {
"github": "pyjanitor-devs/pyjanitor",
"Status": ProjectStatus.ACTIVE,
},
"pandera": {
"github": "unionai-oss/pandera",
"Status": ProjectStatus.ACTIVE,
},
"pointblank": {
"github": "posit-dev/pointblank",
"Status": ProjectStatus.ACTIVE,
},
"dataframely": {
"github": "quantco/dataframely",
"Status": ProjectStatus.ACTIVE,
},
"great_expectations": {
"github": "great-expectations/great_expectations",
"Status": ProjectStatus.ACTIVE,
},
}
repos_table(REPOS)Loading...
Data Orchestration¶
REPOS = {
"prefect": {
"github": "PrefectHQ/prefect",
"Status": ProjectStatus.ACTIVE,
},
"dagster": {
"github": "dagster-io/dagster",
"Status": ProjectStatus.ACTIVE,
},
"mage": {
"github": "mage-ai/mage-ai",
"Status": ProjectStatus.ACTIVE,
},
"airflow": {
"github": "apache/airflow",
"Status": ProjectStatus.ACTIVE,
},
"kestra": {
"github": "kestra-io/kestra",
"Status": ProjectStatus.ACTIVE,
},
"kedro": {
"github": "kedro-org/kedro",
"Status": ProjectStatus.ACTIVE,
},
}
repos_table(REPOS)Loading...