diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000..2071b23 --- /dev/null +++ b/LICENSE @@ -0,0 +1,9 @@ +MIT License + +Copyright (c) + +Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. + +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. diff --git a/README.md b/README.md index 7d8b414..4b0f214 100644 --- a/README.md +++ b/README.md @@ -4,34 +4,40 @@ This project implements an abstraction of objects that can have access to a vari # Why Use Data-Transport ? -Mostly data scientists that don't really care about the underlying database and would like a simple and consistent way to read/write and move data are well served. Additionally we implemented lightweight Extract Transform Loading API and command line (CLI) tool. Finally it is possible to add pre/post processing pipeline functions to read/write - -1. Familiarity with **pandas data-frames** -2. Connectivity **drivers** are included -3. Reading/Writing data from various sources -4. Useful for data migrations or **ETL** +Data transport is a simple framework that enables read/write to multiple databases or technologies that can hold data. In using **data-transport**, you are able to: +- Enjoy the simplicity of **data-transport** because it leverages SQLAlchemy & Pandas data-frames. +- Share notebooks and code without having to disclosing database credentials. +- Seamlessly and consistently access to multiple database technologies at no cost +- No need to worry about accidental writes to a database leading to inconsistent data +- Implement consistent pre and post processing as a pipeline i.e aggregation of functions +- **data-transport** is open-source under MIT License https://github.com/lnyemba/data-transport ## Installation -Within the virtual environment perform the following : +Within the virtual environment perform the following, the options for installation are: - pip install git+https://github.com/lnyemba/data-transport.git +**sql** - by default postgresql, mysql, sqlserver, sqlite3+, duckdb -## Features + pip install data-transport[cloud,nosql,other,all]git+https://github.com/lnyemba/data-transport.git - - read/write from over a dozen databases - - run ETL jobs seamlessly - - scales and integrates into shared environments like apache zeppelin; jupyterhub; SageMaker; ... +Options to install components in square brackets, these components are + +**warehouse** - Apache Iceberg, Apache Drill -## What's new +**cloud**  - to support nextcloud, s3 -Unlike older versions 2.0 and under, we focus on collaborative environments like jupyter-x servers; apache zeppelin: +**nosql** - support for mongodb, couchdb - 1. Simpler syntax to create reader or writer - 2. auth-file registry that can be referenced using a label - 3. duckdb support +**other**  - support for files, rabbitmq, http + pip install data-transport[nosql,cloud,warehouse,all]@git+https://github.com/lnyemba/data-transport.git + +## Additional features + + - In addition to read/write, there is support for functions for pre/post processing + - CLI interface to add to registry, run ETL + - scales and integrates into shared environments like apache zeppelin; jupyterhub; SageMaker; ... ## Learn More diff --git a/bin/transport b/bin/transport index 19b664e..8cec73f 100755 --- a/bin/transport +++ b/bin/transport @@ -53,9 +53,9 @@ def wait(jobs): while jobs : jobs = [thread for thread in jobs if thread.is_alive()] time.sleep(1) -def wait (jobs): - while jobs : - jobs = [pthread for pthread in jobs if pthread.is_alive()] +# def wait (jobs): +# while jobs : +# jobs = [pthread for pthread in jobs if pthread.is_alive()] @app_e.command(name="run") def apply (path:Annotated[str,typer.Argument(help="path of the configuration file")], @@ -178,7 +178,17 @@ def register (label:Annotated[str,typer.Argument(help="unique label that will be _msg = f"""{TIMES_MARK} {e}""" print (_msg) - pass +@app_r.command(name="list") +def register_list (): + """ + This function will list existing registry entries and basic information {label,vendor} + """ + # print (transport.registry.DATA) + _reg = transport.registry.DATA + _data = [{'label':key,'provider':_reg[key]['provider']} for key in _reg if 'provider' in _reg[key]] + _data = pd.DataFrame(_data) + print (_data) + @app_x.command(name='add') def register_plugs ( alias:Annotated[str,typer.Argument(help="unique function name within a file")], diff --git a/bin/transport.cmd b/bin/transport.cmd new file mode 100644 index 0000000..6125f7f --- /dev/null +++ b/bin/transport.cmd @@ -0,0 +1,2 @@ +cd /D "%~dp0" +python transport %1 %2 %3 %4 %5 %6 diff --git a/pyproject.toml b/pyproject.toml index b61e7e5..0391412 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -18,25 +18,17 @@ classifiers = [ ] dependencies = [ "termcolor","sqlalchemy", "aiosqlite","duckdb-engine", - "typer","pandas","numpy","sqlalchemy","pyarrow", + "mysql-connector-python","psycopg2-binary","nzpy","pymssql","duckdb-engine","aiosqlite", + "typer","pandas","numpy","sqlalchemy","pyarrow","smart-open", "plugin-ix@git+https://github.com/lnyemba/plugins-ix" ] [project.optional-dependencies] -sql = ["mysql-connector-python","psycopg2-binary","nzpy","pymssql","duckdb-engine","aiosqlite"] +#sql = ["mysql-connector-python","psycopg2-binary","nzpy","pymssql","duckdb-engine","aiosqlite"] nosql = ["pymongo","cloudant"] -cloud = ["pandas-gbq","google-cloud-bigquery","google-cloud-bigquery-storage", "databricks-sqlalchemy","pyncclient","boto3","boto","botocore"] +cloud = ["boto","boto3","botocore","pyncclient","pandas-gbq","google-cloud-bigquery","google-cloud-bigquery-storage", "databricks-sqlalchemy","pyncclient","boto3","boto","botocore"] warehouse = ["pydrill","pyspark","sqlalchemy_drill"] -rabbitmq = ["pika"] -sqlite = ["aiosqlite"] -aws3 = ["boto3","boto","botocore"] -nextcloud = ["pyncclient"] -mongodb = ["pymongo"] -netezza = ["nzpy"] -mysql = ["mysql-connector-python"] -postgresql = ["psycopg2-binary"] -sqlserver = ["pymssql"] -http = ["flask-session"] -all = ["mysql-connector-python","psycopg2-binary","nzpy","pymssql","duckdb-engine","aiosqlite","pymongo","cloudant","pandas-gbq","google-cloud-bigquery","google-cloud-bigquery-storage", "databricks-sqlalchemy","pyncclient","boto3","boto","botocore","pydrill","pyspark","sqlalchemy_drill", "pika","aiosqlite","boto3","boto","botocore", "pyncclient"] +other = ["pika","flask-session"] +all = ["pymongo","cloudant","pandas-gbq","google-cloud-bigquery","google-cloud-bigquery-storage", "databricks-sqlalchemy","pyncclient","boto3","boto","botocore","pydrill","pyspark","sqlalchemy_drill", "pika","aiosqlite","boto3","boto","botocore", "pyncclient"] [project.urls] Homepage = "https://healthcareio.the-phi.com/git/code/transport.git" @@ -47,14 +39,14 @@ Homepage = "https://healthcareio.the-phi.com/git/code/transport.git" [tool.setuptools] include-package-data = true zip-safe = false -script-files = ["bin/transport"] +script-files = ["bin/transport","bin/transport.cmd"] [tool.setuptools.packages.find] -include = ["info","info.*", "transport", "transport.*"] +include = [ "transport", "transport.*"] [tool.setuptools.dynamic] -version = {attr = "info.__version__"} -#authors = {attr = "meta.__author__"} +version = {attr = "transport.info.__version__"} +#authors = {attr = "transport.__author__"} # If you have a info.py file, you might also want to include the author dynamically: # [tool.setuptools.dynamic] diff --git a/transport/__init__.py b/transport/__init__.py index c3bb901..63fd8b7 100644 --- a/transport/__init__.py +++ b/transport/__init__.py @@ -18,11 +18,31 @@ Source Code is available under MIT License: """ import numpy as np -from transport import sql, nosql, cloud, other, warehouse +#from transport import sql, nosql, cloud, other, warehouse +from transport import sql +try: + from transport import nosql +except Exception as e: + nosql = {} +try: + from transport import cloud +except Exception as e: + cloud = {} +try: + from transport import warehouse +except Exception as e: + warehouse = {} +try: + from transport import other +except Exception as e: + other = {} + + + import pandas as pd import json import os -from info import __version__,__author__,__email__,__license__,__app_name__,__whatsnew__,__edition__ +from transport.info import __version__,__author__,__email__,__license__,__app_name__,__whatsnew__,__edition__ from transport.iowrapper import IWriter, IReader, IETL from transport.plugins import PluginLoader from transport import providers @@ -35,7 +55,7 @@ def init(): global PROVIDERS for _module in [cloud,sql,nosql,other,warehouse] : for _provider_name in dir(_module) : - if _provider_name.startswith('__') or _provider_name == 'common': + if _provider_name.startswith('__') or _provider_name == 'common' or type(_module) in [None,str,dict]: continue PROVIDERS[_provider_name] = {'module':getattr(_module,_provider_name),'type':_module.__name__} # diff --git a/transport/info.py b/transport/info.py new file mode 100644 index 0000000..eb1453d --- /dev/null +++ b/transport/info.py @@ -0,0 +1,23 @@ +__app_name__ = 'data-transport' +__author__ = 'The Phi Technology' +__version__= '2.2.30' +__email__ = "info@the-phi.com" +__edition__= 'community' +__license__=f""" +Copyright 2010 - 2024, Steve L. Nyemba + +Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the “Software”), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. + +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. + +""" + +__whatsnew__=f"""version {__version__}, +1. Added support for read/write logs as well as plugins (when applied) +2. Bug fix with duckdb (adding readonly) for readers because there are issues with threads & processes +3. support for streaming data, important to use this with large volumes of data + + +""" diff --git a/transport/other/files.py b/transport/other/files.py index 62ee3c4..57d3f25 100644 --- a/transport/other/files.py +++ b/transport/other/files.py @@ -30,7 +30,11 @@ class Reader (File): def read(self,**args): _path = self.path if 'path' not in args else args['path'] _delimiter = self.delimiter if 'delimiter' not in args else args['delimiter'] - return pd.read_csv(_path,delimiter=self.delimiter) + _df = pd.read_csv(_path,delimiter=self.delimiter) + if 'query' in args : + _query = args['query'] + _df = _df.query(_query) + return _df def stream(self,**args): raise Exception ("streaming needs to be implemented") class Writer (File): diff --git a/transport/registry.py b/transport/registry.py index 196b2f0..4fb96db 100644 --- a/transport/registry.py +++ b/transport/registry.py @@ -1,6 +1,6 @@ import os import json -from info import __version__ +from transport.info import __version__ import copy import transport import importlib @@ -49,7 +49,8 @@ def init (email,path=REGISTRY_PATH,override=False,_file=REGISTRY_FILE): Initializing the registry and will raise an exception in the advent of an issue """ p = '@' in email - q = False if '.' not in email else email.split('.')[-1] in ['edu','com','io','ai','org'] + #q = False if '.' not in email else email.split('.')[-1] in ['edu','com','io','ai','org'] + q = len(email.split('.')[-1]) in [2,3] if p and q : _config = {"email":email,'version':__version__} if not os.path.exists(path):