From 24a0c6196f812f52712d00abe429041a5e2f5fb1 Mon Sep 17 00:00:00 2001 From: publicmatt Date: Sat, 6 Apr 2024 13:02:31 -0700 Subject: [PATCH] init --- .gitignore | 160 +++++ cookiecutter.json | 8 + {{cookiecutter.project_slug}}/LICENCE | 674 ++++++++++++++++++ {{cookiecutter.project_slug}}/Makefile | 30 + {{cookiecutter.project_slug}}/README.md | 33 + {{cookiecutter.project_slug}}/docs/.gitignore | 1 + {{cookiecutter.project_slug}}/docs/book.toml | 6 + .../docs/src/SUMMARY.md | 5 + .../docs/src/chapter_1.md | 1 + .../docs/src/index.md | 1 + {{cookiecutter.project_slug}}/pyproject.toml | 70 ++ .../requirements.txt | 15 + {{cookiecutter.project_slug}}/test/.env.test | 2 + .../test/test_cnn.py | 6 + .../test/test_inputs.py | 28 + .../{{cookiecutter.module_name}}/__init__.py | 21 + .../{{cookiecutter.module_name}}/__main__.py | 5 + .../app/__init__.py | 11 + .../{{cookiecutter.module_name}}/batch.py | 70 ++ .../{{cookiecutter.module_name}}/cli.py | 41 ++ .../{{cookiecutter.module_name}}/common.py | 0 .../config/app.toml | 3 + .../config/config.toml | 0 .../config/data.toml | 4 + .../config/model.toml | 3 + .../config/paths.toml | 4 + .../config/training.toml | 8 + .../data/__init__.py | 27 + .../data/dataset.py | 66 ++ .../{{cookiecutter.module_name}}/data/make.py | 0 .../data/spark.py | 21 + .../features/make.py | 0 .../model/__init__.py | 0 .../{{cookiecutter.module_name}}/model/cnn.py | 152 ++++ .../model/linear.py | 19 + .../notebooks/features.ipynb | 23 + .../notebooks/main.ipynb | 85 +++ .../training/__init__.py | 12 + .../training/pipeline.py | 55 ++ .../training/runner.py | 46 ++ 40 files changed, 1716 insertions(+) create mode 100644 .gitignore create mode 100644 cookiecutter.json create mode 100644 {{cookiecutter.project_slug}}/LICENCE create mode 100644 {{cookiecutter.project_slug}}/Makefile create mode 100644 {{cookiecutter.project_slug}}/README.md create mode 100644 {{cookiecutter.project_slug}}/docs/.gitignore create mode 100644 {{cookiecutter.project_slug}}/docs/book.toml create mode 100644 {{cookiecutter.project_slug}}/docs/src/SUMMARY.md create mode 100644 {{cookiecutter.project_slug}}/docs/src/chapter_1.md create mode 100644 {{cookiecutter.project_slug}}/docs/src/index.md create mode 100644 {{cookiecutter.project_slug}}/pyproject.toml create mode 100644 {{cookiecutter.project_slug}}/requirements.txt create mode 100644 {{cookiecutter.project_slug}}/test/.env.test create mode 100644 {{cookiecutter.project_slug}}/test/test_cnn.py create mode 100644 {{cookiecutter.project_slug}}/test/test_inputs.py create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/__init__.py create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/__main__.py create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/app/__init__.py create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/batch.py create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/cli.py create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/common.py create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/app.toml create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/config.toml create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/data.toml create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/model.toml create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/paths.toml create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/training.toml create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/data/__init__.py create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/data/dataset.py create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/data/make.py create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/data/spark.py create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/features/make.py create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/model/__init__.py create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/model/cnn.py create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/model/linear.py create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/notebooks/features.ipynb create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/notebooks/main.ipynb create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/training/__init__.py create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/training/pipeline.py create mode 100644 {{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/training/runner.py diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..68bc17f --- /dev/null +++ b/.gitignore @@ -0,0 +1,160 @@ +# Byte-compiled / optimized / DLL files +__pycache__/ +*.py[cod] +*$py.class + +# C extensions +*.so + +# Distribution / packaging +.Python +build/ +develop-eggs/ +dist/ +downloads/ +eggs/ +.eggs/ +lib/ +lib64/ +parts/ +sdist/ +var/ +wheels/ +share/python-wheels/ +*.egg-info/ +.installed.cfg +*.egg +MANIFEST + +# PyInstaller +# Usually these files are written by a python script from a template +# before PyInstaller builds the exe, so as to inject date/other infos into it. +*.manifest +*.spec + +# Installer logs +pip-log.txt +pip-delete-this-directory.txt + +# Unit test / coverage reports +htmlcov/ +.tox/ +.nox/ +.coverage +.coverage.* +.cache +nosetests.xml +coverage.xml +*.cover +*.py,cover +.hypothesis/ +.pytest_cache/ +cover/ + +# Translations +*.mo +*.pot + +# Django stuff: +*.log +local_settings.py +db.sqlite3 +db.sqlite3-journal + +# Flask stuff: +instance/ +.webassets-cache + +# Scrapy stuff: +.scrapy + +# Sphinx documentation +docs/_build/ + +# PyBuilder +.pybuilder/ +target/ + +# Jupyter Notebook +.ipynb_checkpoints + +# IPython +profile_default/ +ipython_config.py + +# pyenv +# For a library or package, you might want to ignore these files since the code is +# intended to run in multiple environments; otherwise, check them in: +# .python-version + +# pipenv +# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. +# However, in case of collaboration, if having platform-specific dependencies or dependencies +# having no cross-platform support, pipenv may install dependencies that don't work, or not +# install all needed dependencies. +#Pipfile.lock + +# poetry +# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. +# This is especially recommended for binary packages to ensure reproducibility, and is more +# commonly ignored for libraries. +# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control +#poetry.lock + +# pdm +# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. +#pdm.lock +# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it +# in version control. +# https://pdm.fming.dev/#use-with-ide +.pdm.toml + +# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm +__pypackages__/ + +# Celery stuff +celerybeat-schedule +celerybeat.pid + +# SageMath parsed files +*.sage.py + +# Environments +.env +.venv +env/ +venv/ +ENV/ +env.bak/ +venv.bak/ + +# Spyder project settings +.spyderproject +.spyproject + +# Rope project settings +.ropeproject + +# mkdocs documentation +/site + +# mypy +.mypy_cache/ +.dmypy.json +dmypy.json + +# Pyre type checker +.pyre/ + +# pytype static type analyzer +.pytype/ + +# Cython debug symbols +cython_debug/ + +# PyCharm +# JetBrains specific template is maintained in a separate JetBrains.gitignore that can +# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore +# and can be added to the global gitignore or merged into this file. For a more nuclear +# option (not recommended) you can uncomment the following to ignore the entire idea folder. +#.idea/ diff --git a/cookiecutter.json b/cookiecutter.json new file mode 100644 index 0000000..98701b9 --- /dev/null +++ b/cookiecutter.json @@ -0,0 +1,8 @@ +{ + "project_name": "project_name", + "repo_name": "{{ cookiecutter.project_name.lower().replace(' ', '_') }}", + "module_name": "{{ cookiecutter.repo_name }}", + "author_name": "Your name (or your organization/company/team)", + "description": "A short description of the project.", + "open_source_license": ["MIT", "BSD-3-Clause", "No license file"], +} diff --git a/{{cookiecutter.project_slug}}/LICENCE b/{{cookiecutter.project_slug}}/LICENCE new file mode 100644 index 0000000..f288702 --- /dev/null +++ b/{{cookiecutter.project_slug}}/LICENCE @@ -0,0 +1,674 @@ + GNU GENERAL PUBLIC LICENSE + Version 3, 29 June 2007 + + Copyright (C) 2007 Free Software Foundation, Inc. + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The GNU General Public License is a free, copyleft license for +software and other kinds of works. + + The licenses for most software and other practical works are designed +to take away your freedom to share and change the works. By contrast, +the GNU General Public License is intended to guarantee your freedom to +share and change all versions of a program--to make sure it remains free +software for all its users. We, the Free Software Foundation, use the +GNU General Public License for most of our software; it applies also to +any other work released this way by its authors. You can apply it to +your programs, too. + + When we speak of free software, we are referring to freedom, not +price. Our General Public Licenses are designed to make sure that you +have the freedom to distribute copies of free software (and charge for +them if you wish), that you receive source code or can get it if you +want it, that you can change the software or use pieces of it in new +free programs, and that you know you can do these things. + + To protect your rights, we need to prevent others from denying you +these rights or asking you to surrender the rights. Therefore, you have +certain responsibilities if you distribute copies of the software, or if +you modify it: responsibilities to respect the freedom of others. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must pass on to the recipients the same +freedoms that you received. You must make sure that they, too, receive +or can get the source code. And you must show them these terms so they +know their rights. + + Developers that use the GNU GPL protect your rights with two steps: +(1) assert copyright on the software, and (2) offer you this License +giving you legal permission to copy, distribute and/or modify it. + + For the developers' and authors' protection, the GPL clearly explains +that there is no warranty for this free software. For both users' and +authors' sake, the GPL requires that modified versions be marked as +changed, so that their problems will not be attributed erroneously to +authors of previous versions. + + Some devices are designed to deny users access to install or run +modified versions of the software inside them, although the manufacturer +can do so. This is fundamentally incompatible with the aim of +protecting users' freedom to change the software. The systematic +pattern of such abuse occurs in the area of products for individuals to +use, which is precisely where it is most unacceptable. Therefore, we +have designed this version of the GPL to prohibit the practice for those +products. If such problems arise substantially in other domains, we +stand ready to extend this provision to those domains in future versions +of the GPL, as needed to protect the freedom of users. + + Finally, every program is threatened constantly by software patents. +States should not allow patents to restrict development and use of +software on general-purpose computers, but in those that do, we wish to +avoid the special danger that patents applied to a free program could +make it effectively proprietary. To prevent this, the GPL assures that +patents cannot be used to render the program non-free. + + The precise terms and conditions for copying, distribution and +modification follow. + + TERMS AND CONDITIONS + + 0. Definitions. + + "This License" refers to version 3 of the GNU General Public License. + + "Copyright" also means copyright-like laws that apply to other kinds of +works, such as semiconductor masks. + + "The Program" refers to any copyrightable work licensed under this +License. Each licensee is addressed as "you". "Licensees" and +"recipients" may be individuals or organizations. + + To "modify" a work means to copy from or adapt all or part of the work +in a fashion requiring copyright permission, other than the making of an +exact copy. The resulting work is called a "modified version" of the +earlier work or a work "based on" the earlier work. + + A "covered work" means either the unmodified Program or a work based +on the Program. + + To "propagate" a work means to do anything with it that, without +permission, would make you directly or secondarily liable for +infringement under applicable copyright law, except executing it on a +computer or modifying a private copy. Propagation includes copying, +distribution (with or without modification), making available to the +public, and in some countries other activities as well. + + To "convey" a work means any kind of propagation that enables other +parties to make or receive copies. Mere interaction with a user through +a computer network, with no transfer of a copy, is not conveying. + + An interactive user interface displays "Appropriate Legal Notices" +to the extent that it includes a convenient and prominently visible +feature that (1) displays an appropriate copyright notice, and (2) +tells the user that there is no warranty for the work (except to the +extent that warranties are provided), that licensees may convey the +work under this License, and how to view a copy of this License. If +the interface presents a list of user commands or options, such as a +menu, a prominent item in the list meets this criterion. + + 1. Source Code. + + The "source code" for a work means the preferred form of the work +for making modifications to it. "Object code" means any non-source +form of a work. + + A "Standard Interface" means an interface that either is an official +standard defined by a recognized standards body, or, in the case of +interfaces specified for a particular programming language, one that +is widely used among developers working in that language. + + The "System Libraries" of an executable work include anything, other +than the work as a whole, that (a) is included in the normal form of +packaging a Major Component, but which is not part of that Major +Component, and (b) serves only to enable use of the work with that +Major Component, or to implement a Standard Interface for which an +implementation is available to the public in source code form. A +"Major Component", in this context, means a major essential component +(kernel, window system, and so on) of the specific operating system +(if any) on which the executable work runs, or a compiler used to +produce the work, or an object code interpreter used to run it. + + The "Corresponding Source" for a work in object code form means all +the source code needed to generate, install, and (for an executable +work) run the object code and to modify the work, including scripts to +control those activities. However, it does not include the work's +System Libraries, or general-purpose tools or generally available free +programs which are used unmodified in performing those activities but +which are not part of the work. For example, Corresponding Source +includes interface definition files associated with source files for +the work, and the source code for shared libraries and dynamically +linked subprograms that the work is specifically designed to require, +such as by intimate data communication or control flow between those +subprograms and other parts of the work. + + The Corresponding Source need not include anything that users +can regenerate automatically from other parts of the Corresponding +Source. + + The Corresponding Source for a work in source code form is that +same work. + + 2. Basic Permissions. + + All rights granted under this License are granted for the term of +copyright on the Program, and are irrevocable provided the stated +conditions are met. This License explicitly affirms your unlimited +permission to run the unmodified Program. The output from running a +covered work is covered by this License only if the output, given its +content, constitutes a covered work. This License acknowledges your +rights of fair use or other equivalent, as provided by copyright law. + + You may make, run and propagate covered works that you do not +convey, without conditions so long as your license otherwise remains +in force. You may convey covered works to others for the sole purpose +of having them make modifications exclusively for you, or provide you +with facilities for running those works, provided that you comply with +the terms of this License in conveying all material for which you do +not control copyright. Those thus making or running the covered works +for you must do so exclusively on your behalf, under your direction +and control, on terms that prohibit them from making any copies of +your copyrighted material outside their relationship with you. + + Conveying under any other circumstances is permitted solely under +the conditions stated below. Sublicensing is not allowed; section 10 +makes it unnecessary. + + 3. Protecting Users' Legal Rights From Anti-Circumvention Law. + + No covered work shall be deemed part of an effective technological +measure under any applicable law fulfilling obligations under article +11 of the WIPO copyright treaty adopted on 20 December 1996, or +similar laws prohibiting or restricting circumvention of such +measures. + + When you convey a covered work, you waive any legal power to forbid +circumvention of technological measures to the extent such circumvention +is effected by exercising rights under this License with respect to +the covered work, and you disclaim any intention to limit operation or +modification of the work as a means of enforcing, against the work's +users, your or third parties' legal rights to forbid circumvention of +technological measures. + + 4. Conveying Verbatim Copies. + + You may convey verbatim copies of the Program's source code as you +receive it, in any medium, provided that you conspicuously and +appropriately publish on each copy an appropriate copyright notice; +keep intact all notices stating that this License and any +non-permissive terms added in accord with section 7 apply to the code; +keep intact all notices of the absence of any warranty; and give all +recipients a copy of this License along with the Program. + + You may charge any price or no price for each copy that you convey, +and you may offer support or warranty protection for a fee. + + 5. Conveying Modified Source Versions. + + You may convey a work based on the Program, or the modifications to +produce it from the Program, in the form of source code under the +terms of section 4, provided that you also meet all of these conditions: + + a) The work must carry prominent notices stating that you modified + it, and giving a relevant date. + + b) The work must carry prominent notices stating that it is + released under this License and any conditions added under section + 7. This requirement modifies the requirement in section 4 to + "keep intact all notices". + + c) You must license the entire work, as a whole, under this + License to anyone who comes into possession of a copy. This + License will therefore apply, along with any applicable section 7 + additional terms, to the whole of the work, and all its parts, + regardless of how they are packaged. This License gives no + permission to license the work in any other way, but it does not + invalidate such permission if you have separately received it. + + d) If the work has interactive user interfaces, each must display + Appropriate Legal Notices; however, if the Program has interactive + interfaces that do not display Appropriate Legal Notices, your + work need not make them do so. + + A compilation of a covered work with other separate and independent +works, which are not by their nature extensions of the covered work, +and which are not combined with it such as to form a larger program, +in or on a volume of a storage or distribution medium, is called an +"aggregate" if the compilation and its resulting copyright are not +used to limit the access or legal rights of the compilation's users +beyond what the individual works permit. Inclusion of a covered work +in an aggregate does not cause this License to apply to the other +parts of the aggregate. + + 6. Conveying Non-Source Forms. + + You may convey a covered work in object code form under the terms +of sections 4 and 5, provided that you also convey the +machine-readable Corresponding Source under the terms of this License, +in one of these ways: + + a) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by the + Corresponding Source fixed on a durable physical medium + customarily used for software interchange. + + b) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by a + written offer, valid for at least three years and valid for as + long as you offer spare parts or customer support for that product + model, to give anyone who possesses the object code either (1) a + copy of the Corresponding Source for all the software in the + product that is covered by this License, on a durable physical + medium customarily used for software interchange, for a price no + more than your reasonable cost of physically performing this + conveying of source, or (2) access to copy the + Corresponding Source from a network server at no charge. + + c) Convey individual copies of the object code with a copy of the + written offer to provide the Corresponding Source. This + alternative is allowed only occasionally and noncommercially, and + only if you received the object code with such an offer, in accord + with subsection 6b. + + d) Convey the object code by offering access from a designated + place (gratis or for a charge), and offer equivalent access to the + Corresponding Source in the same way through the same place at no + further charge. You need not require recipients to copy the + Corresponding Source along with the object code. If the place to + copy the object code is a network server, the Corresponding Source + may be on a different server (operated by you or a third party) + that supports equivalent copying facilities, provided you maintain + clear directions next to the object code saying where to find the + Corresponding Source. Regardless of what server hosts the + Corresponding Source, you remain obligated to ensure that it is + available for as long as needed to satisfy these requirements. + + e) Convey the object code using peer-to-peer transmission, provided + you inform other peers where the object code and Corresponding + Source of the work are being offered to the general public at no + charge under subsection 6d. + + A separable portion of the object code, whose source code is excluded +from the Corresponding Source as a System Library, need not be +included in conveying the object code work. + + A "User Product" is either (1) a "consumer product", which means any +tangible personal property which is normally used for personal, family, +or household purposes, or (2) anything designed or sold for incorporation +into a dwelling. In determining whether a product is a consumer product, +doubtful cases shall be resolved in favor of coverage. For a particular +product received by a particular user, "normally used" refers to a +typical or common use of that class of product, regardless of the status +of the particular user or of the way in which the particular user +actually uses, or expects or is expected to use, the product. A product +is a consumer product regardless of whether the product has substantial +commercial, industrial or non-consumer uses, unless such uses represent +the only significant mode of use of the product. + + "Installation Information" for a User Product means any methods, +procedures, authorization keys, or other information required to install +and execute modified versions of a covered work in that User Product from +a modified version of its Corresponding Source. The information must +suffice to ensure that the continued functioning of the modified object +code is in no case prevented or interfered with solely because +modification has been made. + + If you convey an object code work under this section in, or with, or +specifically for use in, a User Product, and the conveying occurs as +part of a transaction in which the right of possession and use of the +User Product is transferred to the recipient in perpetuity or for a +fixed term (regardless of how the transaction is characterized), the +Corresponding Source conveyed under this section must be accompanied +by the Installation Information. But this requirement does not apply +if neither you nor any third party retains the ability to install +modified object code on the User Product (for example, the work has +been installed in ROM). + + The requirement to provide Installation Information does not include a +requirement to continue to provide support service, warranty, or updates +for a work that has been modified or installed by the recipient, or for +the User Product in which it has been modified or installed. Access to a +network may be denied when the modification itself materially and +adversely affects the operation of the network or violates the rules and +protocols for communication across the network. + + Corresponding Source conveyed, and Installation Information provided, +in accord with this section must be in a format that is publicly +documented (and with an implementation available to the public in +source code form), and must require no special password or key for +unpacking, reading or copying. + + 7. Additional Terms. + + "Additional permissions" are terms that supplement the terms of this +License by making exceptions from one or more of its conditions. +Additional permissions that are applicable to the entire Program shall +be treated as though they were included in this License, to the extent +that they are valid under applicable law. If additional permissions +apply only to part of the Program, that part may be used separately +under those permissions, but the entire Program remains governed by +this License without regard to the additional permissions. + + When you convey a copy of a covered work, you may at your option +remove any additional permissions from that copy, or from any part of +it. (Additional permissions may be written to require their own +removal in certain cases when you modify the work.) You may place +additional permissions on material, added by you to a covered work, +for which you have or can give appropriate copyright permission. + + Notwithstanding any other provision of this License, for material you +add to a covered work, you may (if authorized by the copyright holders of +that material) supplement the terms of this License with terms: + + a) Disclaiming warranty or limiting liability differently from the + terms of sections 15 and 16 of this License; or + + b) Requiring preservation of specified reasonable legal notices or + author attributions in that material or in the Appropriate Legal + Notices displayed by works containing it; or + + c) Prohibiting misrepresentation of the origin of that material, or + requiring that modified versions of such material be marked in + reasonable ways as different from the original version; or + + d) Limiting the use for publicity purposes of names of licensors or + authors of the material; or + + e) Declining to grant rights under trademark law for use of some + trade names, trademarks, or service marks; or + + f) Requiring indemnification of licensors and authors of that + material by anyone who conveys the material (or modified versions of + it) with contractual assumptions of liability to the recipient, for + any liability that these contractual assumptions directly impose on + those licensors and authors. + + All other non-permissive additional terms are considered "further +restrictions" within the meaning of section 10. If the Program as you +received it, or any part of it, contains a notice stating that it is +governed by this License along with a term that is a further +restriction, you may remove that term. If a license document contains +a further restriction but permits relicensing or conveying under this +License, you may add to a covered work material governed by the terms +of that license document, provided that the further restriction does +not survive such relicensing or conveying. + + If you add terms to a covered work in accord with this section, you +must place, in the relevant source files, a statement of the +additional terms that apply to those files, or a notice indicating +where to find the applicable terms. + + Additional terms, permissive or non-permissive, may be stated in the +form of a separately written license, or stated as exceptions; +the above requirements apply either way. + + 8. Termination. + + You may not propagate or modify a covered work except as expressly +provided under this License. Any attempt otherwise to propagate or +modify it is void, and will automatically terminate your rights under +this License (including any patent licenses granted under the third +paragraph of section 11). + + However, if you cease all violation of this License, then your +license from a particular copyright holder is reinstated (a) +provisionally, unless and until the copyright holder explicitly and +finally terminates your license, and (b) permanently, if the copyright +holder fails to notify you of the violation by some reasonable means +prior to 60 days after the cessation. + + Moreover, your license from a particular copyright holder is +reinstated permanently if the copyright holder notifies you of the +violation by some reasonable means, this is the first time you have +received notice of violation of this License (for any work) from that +copyright holder, and you cure the violation prior to 30 days after +your receipt of the notice. + + Termination of your rights under this section does not terminate the +licenses of parties who have received copies or rights from you under +this License. If your rights have been terminated and not permanently +reinstated, you do not qualify to receive new licenses for the same +material under section 10. + + 9. Acceptance Not Required for Having Copies. + + You are not required to accept this License in order to receive or +run a copy of the Program. Ancillary propagation of a covered work +occurring solely as a consequence of using peer-to-peer transmission +to receive a copy likewise does not require acceptance. However, +nothing other than this License grants you permission to propagate or +modify any covered work. These actions infringe copyright if you do +not accept this License. Therefore, by modifying or propagating a +covered work, you indicate your acceptance of this License to do so. + + 10. Automatic Licensing of Downstream Recipients. + + Each time you convey a covered work, the recipient automatically +receives a license from the original licensors, to run, modify and +propagate that work, subject to this License. You are not responsible +for enforcing compliance by third parties with this License. + + An "entity transaction" is a transaction transferring control of an +organization, or substantially all assets of one, or subdividing an +organization, or merging organizations. If propagation of a covered +work results from an entity transaction, each party to that +transaction who receives a copy of the work also receives whatever +licenses to the work the party's predecessor in interest had or could +give under the previous paragraph, plus a right to possession of the +Corresponding Source of the work from the predecessor in interest, if +the predecessor has it or can get it with reasonable efforts. + + You may not impose any further restrictions on the exercise of the +rights granted or affirmed under this License. For example, you may +not impose a license fee, royalty, or other charge for exercise of +rights granted under this License, and you may not initiate litigation +(including a cross-claim or counterclaim in a lawsuit) alleging that +any patent claim is infringed by making, using, selling, offering for +sale, or importing the Program or any portion of it. + + 11. Patents. + + A "contributor" is a copyright holder who authorizes use under this +License of the Program or a work on which the Program is based. The +work thus licensed is called the contributor's "contributor version". + + A contributor's "essential patent claims" are all patent claims +owned or controlled by the contributor, whether already acquired or +hereafter acquired, that would be infringed by some manner, permitted +by this License, of making, using, or selling its contributor version, +but do not include claims that would be infringed only as a +consequence of further modification of the contributor version. For +purposes of this definition, "control" includes the right to grant +patent sublicenses in a manner consistent with the requirements of +this License. + + Each contributor grants you a non-exclusive, worldwide, royalty-free +patent license under the contributor's essential patent claims, to +make, use, sell, offer for sale, import and otherwise run, modify and +propagate the contents of its contributor version. + + In the following three paragraphs, a "patent license" is any express +agreement or commitment, however denominated, not to enforce a patent +(such as an express permission to practice a patent or covenant not to +sue for patent infringement). To "grant" such a patent license to a +party means to make such an agreement or commitment not to enforce a +patent against the party. + + If you convey a covered work, knowingly relying on a patent license, +and the Corresponding Source of the work is not available for anyone +to copy, free of charge and under the terms of this License, through a +publicly available network server or other readily accessible means, +then you must either (1) cause the Corresponding Source to be so +available, or (2) arrange to deprive yourself of the benefit of the +patent license for this particular work, or (3) arrange, in a manner +consistent with the requirements of this License, to extend the patent +license to downstream recipients. "Knowingly relying" means you have +actual knowledge that, but for the patent license, your conveying the +covered work in a country, or your recipient's use of the covered work +in a country, would infringe one or more identifiable patents in that +country that you have reason to believe are valid. + + If, pursuant to or in connection with a single transaction or +arrangement, you convey, or propagate by procuring conveyance of, a +covered work, and grant a patent license to some of the parties +receiving the covered work authorizing them to use, propagate, modify +or convey a specific copy of the covered work, then the patent license +you grant is automatically extended to all recipients of the covered +work and works based on it. + + A patent license is "discriminatory" if it does not include within +the scope of its coverage, prohibits the exercise of, or is +conditioned on the non-exercise of one or more of the rights that are +specifically granted under this License. You may not convey a covered +work if you are a party to an arrangement with a third party that is +in the business of distributing software, under which you make payment +to the third party based on the extent of your activity of conveying +the work, and under which the third party grants, to any of the +parties who would receive the covered work from you, a discriminatory +patent license (a) in connection with copies of the covered work +conveyed by you (or copies made from those copies), or (b) primarily +for and in connection with specific products or compilations that +contain the covered work, unless you entered into that arrangement, +or that patent license was granted, prior to 28 March 2007. + + Nothing in this License shall be construed as excluding or limiting +any implied license or other defenses to infringement that may +otherwise be available to you under applicable patent law. + + 12. No Surrender of Others' Freedom. + + If conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot convey a +covered work so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you may +not convey it at all. For example, if you agree to terms that obligate you +to collect a royalty for further conveying from those to whom you convey +the Program, the only way you could satisfy both those terms and this +License would be to refrain entirely from conveying the Program. + + 13. Use with the GNU Affero General Public License. + + Notwithstanding any other provision of this License, you have +permission to link or combine any covered work with a work licensed +under version 3 of the GNU Affero General Public License into a single +combined work, and to convey the resulting work. The terms of this +License will continue to apply to the part which is the covered work, +but the special requirements of the GNU Affero General Public License, +section 13, concerning interaction through a network will apply to the +combination as such. + + 14. Revised Versions of this License. + + The Free Software Foundation may publish revised and/or new versions of +the GNU General Public License from time to time. Such new versions will +be similar in spirit to the present version, but may differ in detail to +address new problems or concerns. + + Each version is given a distinguishing version number. If the +Program specifies that a certain numbered version of the GNU General +Public License "or any later version" applies to it, you have the +option of following the terms and conditions either of that numbered +version or of any later version published by the Free Software +Foundation. If the Program does not specify a version number of the +GNU General Public License, you may choose any version ever published +by the Free Software Foundation. + + If the Program specifies that a proxy can decide which future +versions of the GNU General Public License can be used, that proxy's +public statement of acceptance of a version permanently authorizes you +to choose that version for the Program. + + Later license versions may give you additional or different +permissions. However, no additional obligations are imposed on any +author or copyright holder as a result of your choosing to follow a +later version. + + 15. Disclaimer of Warranty. + + THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY +APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT +HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY +OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, +THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR +PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM +IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF +ALL NECESSARY SERVICING, REPAIR OR CORRECTION. + + 16. Limitation of Liability. + + IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS +THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY +GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE +USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF +DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD +PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), +EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF +SUCH DAMAGES. + + 17. Interpretation of Sections 15 and 16. + + If the disclaimer of warranty and limitation of liability provided +above cannot be given local legal effect according to their terms, +reviewing courts shall apply local law that most closely approximates +an absolute waiver of all civil liability in connection with the +Program, unless a warranty or assumption of liability accompanies a +copy of the Program in return for a fee. + + END OF TERMS AND CONDITIONS + + How to Apply These Terms to Your New Programs + + If you develop a new program, and you want it to be of the greatest +possible use to the public, the best way to achieve this is to make it +free software which everyone can redistribute and change under these terms. + + To do so, attach the following notices to the program. It is safest +to attach them to the start of each source file to most effectively +state the exclusion of warranty; and each file should have at least +the "copyright" line and a pointer to where the full notice is found. + + + Copyright (C) + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . + +Also add information on how to contact you by electronic and paper mail. + + If the program does terminal interaction, make it output a short +notice like this when it starts in an interactive mode: + + Copyright (C) + This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. + This is free software, and you are welcome to redistribute it + under certain conditions; type `show c' for details. + +The hypothetical commands `show w' and `show c' should show the appropriate +parts of the General Public License. Of course, your program's commands +might be different; for a GUI interface, you would use an "about box". + + You should also get your employer (if you work as a programmer) or school, +if any, to sign a "copyright disclaimer" for the program, if necessary. +For more information on this, and how to apply and follow the GNU GPL, see +. + + The GNU General Public License does not permit incorporating your program +into proprietary programs. If your program is a subroutine library, you +may consider it more useful to permit linking proprietary applications with +the library. If this is what you want to do, use the GNU Lesser General +Public License instead of this License. But first, please read +. diff --git a/{{cookiecutter.project_slug}}/Makefile b/{{cookiecutter.project_slug}}/Makefile new file mode 100644 index 0000000..26749c8 --- /dev/null +++ b/{{cookiecutter.project_slug}}/Makefile @@ -0,0 +1,30 @@ +APP_NAME=ml_pipeline +PYTHON=.venv/bin/python3 +INTERPRETER=/usr/bin/python3 +.PHONY: help test + + +all: run + +init: ## create a venv + $(INTERPRETER) -m venv .venv + +run: ## run the pipeline (train) + $(PYTHON) -m $(APP_NAME) pipeline:train + +data: ## download the mnist data + $(PYTHON) -m $(APP_NAME) data:download + # wget https://pjreddie.com/media/files/mnist_train.csv -O data/mnist_train.csv + # wget https://pjreddie.com/media/files/mnist_test.csv -O data/mnist_test.csv + +test: + find . -iname "*.py" | entr -c pytest + +serve: + $(PYTHON) -m $(APP_NAME) app:serve + +install: + $(PYTHON) -m pip install -r requirements.txt + +help: ## display this help message + @grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | sort | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}' diff --git a/{{cookiecutter.project_slug}}/README.md b/{{cookiecutter.project_slug}}/README.md new file mode 100644 index 0000000..52c6a08 --- /dev/null +++ b/{{cookiecutter.project_slug}}/README.md @@ -0,0 +1,33 @@ +# Mimimal Viable Deep Learning Infrastructure + +Deep learning pipelines are hard to reason about and difficult to code consistently. + +Instead of remembering where to put everything and making a different choice for each project, this repository is an attempt to standardize on good defaults. + +Think of it like a mini-pytorch lightening, with all the fory internals exposed for extension and modification. + + +## Usage + +### Install: + +Install the conda requirements: + +```bash +make install +``` + +Which is a proxy for calling: + +```bash +conda env updates -n ml_pipeline --file environment.yml +``` + +### Run: + +Run the code on MNIST with the following command: + +```bash +make run +``` + diff --git a/{{cookiecutter.project_slug}}/docs/.gitignore b/{{cookiecutter.project_slug}}/docs/.gitignore new file mode 100644 index 0000000..7585238 --- /dev/null +++ b/{{cookiecutter.project_slug}}/docs/.gitignore @@ -0,0 +1 @@ +book diff --git a/{{cookiecutter.project_slug}}/docs/book.toml b/{{cookiecutter.project_slug}}/docs/book.toml new file mode 100644 index 0000000..a2e22b1 --- /dev/null +++ b/{{cookiecutter.project_slug}}/docs/book.toml @@ -0,0 +1,6 @@ +[book] +authors = ["publicmatt"] +language = "en" +multilingual = false +src = "src" +title = "ml_pipeline" diff --git a/{{cookiecutter.project_slug}}/docs/src/SUMMARY.md b/{{cookiecutter.project_slug}}/docs/src/SUMMARY.md new file mode 100644 index 0000000..178c856 --- /dev/null +++ b/{{cookiecutter.project_slug}}/docs/src/SUMMARY.md @@ -0,0 +1,5 @@ +# Summary + +- [Overview](./index.md) +- [Chapter 1](./chapter_1.md) + diff --git a/{{cookiecutter.project_slug}}/docs/src/chapter_1.md b/{{cookiecutter.project_slug}}/docs/src/chapter_1.md new file mode 100644 index 0000000..b743fda --- /dev/null +++ b/{{cookiecutter.project_slug}}/docs/src/chapter_1.md @@ -0,0 +1 @@ +# Chapter 1 diff --git a/{{cookiecutter.project_slug}}/docs/src/index.md b/{{cookiecutter.project_slug}}/docs/src/index.md new file mode 100644 index 0000000..07dd0c5 --- /dev/null +++ b/{{cookiecutter.project_slug}}/docs/src/index.md @@ -0,0 +1 @@ +# Overview diff --git a/{{cookiecutter.project_slug}}/pyproject.toml b/{{cookiecutter.project_slug}}/pyproject.toml new file mode 100644 index 0000000..f0859a0 --- /dev/null +++ b/{{cookiecutter.project_slug}}/pyproject.toml @@ -0,0 +1,70 @@ +[build-system] +requires = ["setuptools", "wheel"] +build-backend = "setuptools.build_meta" + +[project] +name = "ml_pipeline" +version = "0.1.0" +authors = [ + {name = "publicmatt", email = "git@publicmatt.com"}, +] +description = "A minimal viable pytorch training pipeline." +readme = "README.md" +license = {file = "LICENSE"} +dependencies = [ + "click==8.1.7", + "einops==0.7.0", + "matplotlib==3.8.4", + "numpy==1.26.4", + "pytest==8.1.1", + "pytest-cov==5.0.0", + "python-dotenv==1.0.1", + "requests==2.31.0", + "torch==2.2.2", + "torchvision=0.17.2", + "tqdm==4.66.2", + "wandb==0.16.6", + "python-configuration[toml]", + "pandas==2.2.1", + "notebook==7.1.2", + "fastapi==0.110.1", + "uvicorn==0.29.0", +] + +[project.urls] +homepage = "https://example.com/my_project" +repository = "https://example.com/my_project/repo" +documentation = "https://example.com/my_project/docs" + +[tool.setuptools] +packages = ["ml_pipeline"] + +[tool.pytest.ini_options] +# Run tests in parallel using pytest-xdist +addopts = "--cov=ml_pipeline --cov-report=term" +# Specify the paths to look for tests +testpaths = [ + "test", +] +# Set default Python classes, functions, and methods to consider as tests +python_files = [ + "test_*.py", + "test*.py", + "*_test.py", +] +python_classes = [ + "Test*", + "*Test", + "*Tests", + "*TestCase", +] +python_functions = [ + "test_*", + "*_test", +] + +# Configure markers (custom or otherwise) +markers = [ + "slow: marks tests as slow (deselect with '-m \"not slow\"')", + "online: marks tests that require internet access", +] diff --git a/{{cookiecutter.project_slug}}/requirements.txt b/{{cookiecutter.project_slug}}/requirements.txt new file mode 100644 index 0000000..ee744ce --- /dev/null +++ b/{{cookiecutter.project_slug}}/requirements.txt @@ -0,0 +1,15 @@ +black==24.3.0 +click==8.1.7 +einops==0.7.0 +matplotlib==3.8.4 +numpy==1.26.4 +pytest==8.1.1 +requests==2.31.0 +torch==2.2.2 +tqdm==4.66.2 +wandb==0.16.6 +pandas==2.2.1 +notebook==7.1.2 +fastapi==0.110.1 +uvicorn==0.29.0 +python-configuration[toml] diff --git a/{{cookiecutter.project_slug}}/test/.env.test b/{{cookiecutter.project_slug}}/test/.env.test new file mode 100644 index 0000000..bc63937 --- /dev/null +++ b/{{cookiecutter.project_slug}}/test/.env.test @@ -0,0 +1,2 @@ +TRAIN_PATH=${HOME}/Dev/ml/data/mnist_train.csv +INPUT_FEATURES=40 diff --git a/{{cookiecutter.project_slug}}/test/test_cnn.py b/{{cookiecutter.project_slug}}/test/test_cnn.py new file mode 100644 index 0000000..df2073c --- /dev/null +++ b/{{cookiecutter.project_slug}}/test/test_cnn.py @@ -0,0 +1,6 @@ +from ml_pipeline import config +from ml_pipeline.model.cnn import VGG11 + +def test_in_channels(): + assert config.model.name == 'vgg11' + diff --git a/{{cookiecutter.project_slug}}/test/test_inputs.py b/{{cookiecutter.project_slug}}/test/test_inputs.py new file mode 100644 index 0000000..bfe30e6 --- /dev/null +++ b/{{cookiecutter.project_slug}}/test/test_inputs.py @@ -0,0 +1,28 @@ +from ml_pipeline.data.dataset import MnistDataset +from ml_pipeline import config +from pathlib import Path +import pytest + +@pytest.mark.skip() +def test_init(): + pass + + +def test_getitem(): + train_set = MnistDataset(config.data.train_path) + + assert train_set[0][1].item() == 5 + repeated = 8 + length = 28 + channels = 1 + assert train_set[0][0].shape == (channels, length * repeated, length * repeated) + +@pytest.mark.skip() +def test_loader(): + from torch.utils.data import DataLoader + train_set = MnistDataset(config.data.train_path) + # train_loader = DataLoader(train_set, batch_size=config.training.batch_size, shuffle=True) + # for sample, target in train_loader: + # assert len(sample) == config.training.batch_size + # len(sample) + # len(target) diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/__init__.py b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/__init__.py new file mode 100644 index 0000000..0ded6a6 --- /dev/null +++ b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/__init__.py @@ -0,0 +1,21 @@ +from config import ConfigurationSet, config_from_env, config_from_dotenv, config_from_toml +from pathlib import Path + +pwd = Path(__file__).parent +config_path = pwd / 'config' +root_path = pwd.parent +config = ConfigurationSet( + config_from_env(prefix="ML_PIPELINE", separator="__", lowercase_keys=True), + config_from_dotenv(root_path / ".env", read_from_file=True, lowercase_keys=True, interpolate=True, interpolate_type=1), + config_from_toml(config_path / "training.toml", read_from_file=True), + config_from_toml(config_path / "data.toml", read_from_file=True), + config_from_toml(config_path / "model.toml", read_from_file=True), + config_from_toml(config_path / "app.toml", read_from_file=True), + config_from_toml(config_path / "paths.toml", read_from_file=True), +) + +import logging + +# Configure logging +logging.basicConfig(level=logging.INFO) +logger = logging.getLogger(__name__) diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/__main__.py b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/__main__.py new file mode 100644 index 0000000..41976c0 --- /dev/null +++ b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/__main__.py @@ -0,0 +1,5 @@ +from ml_pipeline.cli import cli + +if __name__ == "__main__": + cli() + diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/app/__init__.py b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/app/__init__.py new file mode 100644 index 0000000..33e214b --- /dev/null +++ b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/app/__init__.py @@ -0,0 +1,11 @@ +from ml_pipeline import config +from fastapi import FastAPI, Response +import logging +import uvicorn + +app = FastAPI() + +logger = logging.getLogger(__name__) + +def run(): + uvicorn.run("ml_pipeline.app:app", host=config.app.host, port=config.app.port, proxy_headers=True) diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/batch.py b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/batch.py new file mode 100644 index 0000000..dc0dd8a --- /dev/null +++ b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/batch.py @@ -0,0 +1,70 @@ +import torch +from torch import nn +from torch import optim +from torch.utils.data import DataLoader +from ml_pipeline.data import FashionDataset +from tqdm import tqdm +from ml_pipeline.common import Stage + + +class Batch: + def __init__( + self, + stage: Stage, + model: nn.Module, + device, + loader: DataLoader, + optimizer: optim.Optimizer, + criterion: nn.Module, + ): + """todo""" + self.stage = stage + self.device = device + self.model = model.to(device) + self.loader = loader + self.criterion = criterion + self.optimizer = optimizer + self.loss = 0 + + def run(self, desc): + self.model.train() + epoch = 0 + for epoch, (x, y) in enumerate(tqdm(self.loader, desc=desc)): + self.optimizer.zero_grad() + loss = self._run_batch((x, y)) + loss.backward() # Send loss backwards to accumulate gradients + self.optimizer.step() # Perform a gradient update on the weights of the mode + self.loss += loss.item() + + def _run_batch(self, sample): + true_x, true_y = sample + true_x, true_y = true_x.to(self.device), true_y.to(self.device) + pred_y = self.model(true_x) + loss = self.criterion(pred_y, true_y) + return loss + + +def main(): + model = nn.Conv2d(1, 64, 3) + criterion = torch.nn.CrossEntropyLoss() + optimizer = torch.optim.Adam(model.parameters(), lr=2e-4) + path = "fashion-mnist_train.csv" + dataset = FashionDataset(path) + batch_size = 16 + num_workers = 1 + loader = torch.utils.data.DataLoader( + dataset, batch_size=batch_size, shuffle=False, num_workers=num_workers + ) + batch = Batch( + Stage.TRAIN, + device=torch.device("cpu"), + model=model, + criterion=criterion, + optimizer=optimizer, + loader=loader, + ) + batch.run("test") + + +if __name__ == "__main__": + main() diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/cli.py b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/cli.py new file mode 100644 index 0000000..0cdc6ec --- /dev/null +++ b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/cli.py @@ -0,0 +1,41 @@ +import click + +@click.group() +@click.version_option() +def cli(): + """ + ml_pipeline: a template for building, training and running pytorch models. + """ + + +@cli.command("pipeline:train") +def pipeline_train(): + """run the training pipeline with train data""" + from ml_pipeline.training import pipeline + pipeline.run(evaluate=False) + +@cli.command("pipeline:evaluate") +def pipeline_evaluate(): + """run the training pipeline with test data""" + from ml_pipeline.training import pipeline + pipeline.run(evaluate=True) + +@cli.command("app:serve") +def app_serve(): + """run the api server pipeline with pretrained model""" + from ml_pipeline import app + app.run() + +@cli.command("data:download") +def data_download(): + """download the train and test data""" + from ml_pipeline import data + from ml_pipeline import config + from pathlib import Path + data.download(Path(config.paths.data)) + +@cli.command("data:debug") +def data_debug(): + """debug the dataset class""" + from ml_pipeline.data import dataset + dataset.debug() diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/common.py b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/common.py new file mode 100644 index 0000000..e69de29 diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/app.toml b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/app.toml new file mode 100644 index 0000000..7b81532 --- /dev/null +++ b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/app.toml @@ -0,0 +1,3 @@ +[app] +host = "127.0.0.1" +port = 8001 diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/config.toml b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/config.toml new file mode 100644 index 0000000..e69de29 diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/data.toml b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/data.toml new file mode 100644 index 0000000..2548a08 --- /dev/null +++ b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/data.toml @@ -0,0 +1,4 @@ +[data] +train_path = "/path/to/data/mnist_train.csv" +in_channels = 1 +num_classes = 10 diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/model.toml b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/model.toml new file mode 100644 index 0000000..e8b3788 --- /dev/null +++ b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/model.toml @@ -0,0 +1,3 @@ +[model] +hidden_size = 8 +name = 'vgg11' diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/paths.toml b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/paths.toml new file mode 100644 index 0000000..aa3e756 --- /dev/null +++ b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/paths.toml @@ -0,0 +1,4 @@ +[paths] +repo = "/path/to/root" +app = "/path/to/root/ml_pipeline" +data = "/path/to/root/data" diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/training.toml b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/training.toml new file mode 100644 index 0000000..e6e773e --- /dev/null +++ b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/config/training.toml @@ -0,0 +1,8 @@ +[training] +batch_size = 16 +epochs = 10 +learning_rate = 0.01 +device = 'cpu' +# examples = 50 +examples = -1 + diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/data/__init__.py b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/data/__init__.py new file mode 100644 index 0000000..b77bf36 --- /dev/null +++ b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/data/__init__.py @@ -0,0 +1,27 @@ +from pathlib import Path +import requests +import logging +from ml_pipeline import config + + +logger = logging.getLogger(__name__) + +def download(data_path: Path, force=False): + + urls = { + 'train' : 'https://pjreddie.com/media/files/mnist_train.csv', + 'test' : 'https://pjreddie.com/media/files/mnist_test.csv' + } + for dataset, url in urls.items(): + filename = data_path / url.split('/')[-1] + if filename.exists() and not force: + logger.info(f'file exists {filename} (set force to overwrite)') + continue + logger.info(f'downloading {dataset} {url}') + response = requests.get(url) + if response.status_code == 200: + with open(filename, 'wb') as file: + file.write(response.content) + logger.info(f'file downloaded {filename}') + else: + logger.info(f'failed to download file {filename}') diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/data/dataset.py b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/data/dataset.py new file mode 100644 index 0000000..f0bd601 --- /dev/null +++ b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/data/dataset.py @@ -0,0 +1,66 @@ +from torch.utils.data import Dataset +import numpy as np +import einops +import csv +import torch +from pathlib import Path +from typing import Tuple +from ml_pipeline import config, logger + + +class MnistDataset(Dataset): + """ + The MNIST database of handwritten digits. + Training set is 60k labeled examples, test is 10k examples. + The b/w images normalized to 20x20, preserving aspect ratio. + + It's the defacto standard image training set to learn about classification in DL + """ + + def __init__(self, path: Path): + """ + give a path to a dir that contains the following csv files: + https://pjreddie.com/projects/mnist-in-csv/ + """ + assert path, "dataset path required" + self.path = Path(path) + assert self.path.exists(), f"could not find dataset path: {path}" + self.features, self.labels = self._load() + + def __getitem__(self, idx): + return (self.features[idx], self.labels[idx]) + + def __len__(self): + return len(self.features) + + def _load(self) -> Tuple[torch.Tensor, torch.Tensor]: + # opening the CSV file + with open(self.path, mode="r") as file: + images, labels = [], [] + csvFile = csv.reader(file) + examples = config.training.examples + for line, content in enumerate(csvFile): + if line == examples: + break + labels.append(int(content[0])) + image = [int(x) for x in content[1:]] + images.append(image) + labels = torch.tensor(labels, dtype=torch.int64) + images = torch.tensor(images, dtype=torch.float32) + images = einops.rearrange(images, "n (w h) -> n w h", w=28, h=28) + images = einops.repeat( + images, "n w h -> n c (w r_w) (h r_h)", c=1, r_w=8, r_h=8 + ) + return (images, labels) + + +def debug(): + path = Path(config.paths.data) / "mnist_train.csv" + dataset = MnistDataset(path=path) + logger.info(f"len: {len(dataset)}") + logger.info(f"first shape: {dataset[0][0].shape}") + mean = einops.reduce(dataset[:10][0], "n w h -> w h", "mean") + logger.info(f"mean shape: {mean.shape}") + logger.info(f"mean image: {mean}") + + diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/data/make.py b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/data/make.py new file mode 100644 index 0000000..e69de29 diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/data/spark.py b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/data/spark.py new file mode 100644 index 0000000..7e082cc --- /dev/null +++ b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/data/spark.py @@ -0,0 +1,21 @@ +#!/usr/bin/env python3 +from sys import stdout +import csv + +# 'pip install pyspark' for these +from pyspark import SparkFiles +from pyspark.sql import SparkSession + +# make a spark "session". this creates a local hadoop cluster by default (!) +spark = SparkSession.builder.getOrCreate() +# put the input file in the cluster's filesystem: +spark.sparkContext.addFile("https://csvbase.com/meripaterson/stock-exchanges.csv") +# the following is much like for pandas +df = ( + spark.read.csv(f"file://{SparkFiles.get('stock-exchanges.csv')}", header=True) + .select("MIC") + .na.drop() + .sort("MIC") +) +# pyspark has no easy way to write csv to stdout - use python's csv lib +csv.writer(stdout).writerows(df.collect()) diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/features/make.py b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/features/make.py new file mode 100644 index 0000000..e69de29 diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/model/__init__.py b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/model/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/model/cnn.py b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/model/cnn.py new file mode 100644 index 0000000..04e0d12 --- /dev/null +++ b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/model/cnn.py @@ -0,0 +1,152 @@ +from torch import nn + + +# the VGG11 architecture +class VGG11(nn.Module): + def __init__(self, in_channels, num_classes=1000): + super(VGG11, self).__init__() + self.in_channels = in_channels + self.num_classes = num_classes + + # convolutional layers + self.conv_layers = nn.Sequential( + nn.Conv2d(self.in_channels, 64, kernel_size=3, padding=1), + nn.ReLU(), + nn.MaxPool2d(kernel_size=2, stride=2), + nn.Conv2d(64, 128, kernel_size=3, padding=1), + nn.ReLU(), + nn.MaxPool2d(kernel_size=2, stride=2), + nn.Conv2d(128, 256, kernel_size=3, padding=1), + nn.ReLU(), + nn.Conv2d(256, 256, kernel_size=3, padding=1), + nn.ReLU(), + nn.MaxPool2d(kernel_size=2, stride=2), + nn.Conv2d(256, 512, kernel_size=3, padding=1), + nn.ReLU(), + nn.Conv2d(512, 512, kernel_size=3, padding=1), + nn.ReLU(), + nn.MaxPool2d(kernel_size=2, stride=2), + nn.Conv2d(512, 512, kernel_size=3, padding=1), + nn.ReLU(), + nn.Conv2d(512, 512, kernel_size=3, padding=1), + nn.ReLU(), + nn.MaxPool2d(kernel_size=2, stride=2), + ) + + # fully connected linear layers + self.linear_layers = nn.Sequential( + nn.Linear(in_features=512 * 7 * 7, out_features=4096), + nn.ReLU(), + nn.Dropout(0.5), + nn.Linear(in_features=4096, out_features=4096), + nn.ReLU(), + nn.Dropout(0.5), + nn.Linear(in_features=4096, out_features=self.num_classes), + ) + + def forward(self, x): + x = self.conv_layers(x) + # flatten to prepare for the fully connected layers + x = x.view(x.size(0), -1) + x = self.linear_layers(x) + return x + + +class VGG16(nn.Module): + def __init__(self, num_classes=10): + super(VGG16, self).__init__() + self.layer1 = nn.Sequential( + nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1), + nn.BatchNorm2d(64), + nn.ReLU(), + ) + self.layer2 = nn.Sequential( + nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=1), + nn.BatchNorm2d(64), + nn.ReLU(), + nn.MaxPool2d(kernel_size=2, stride=2), + ) + self.layer3 = nn.Sequential( + nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1), + nn.BatchNorm2d(128), + nn.ReLU(), + ) + self.layer4 = nn.Sequential( + nn.Conv2d(128, 128, kernel_size=3, stride=1, padding=1), + nn.BatchNorm2d(128), + nn.ReLU(), + nn.MaxPool2d(kernel_size=2, stride=2), + ) + self.layer5 = nn.Sequential( + nn.Conv2d(128, 256, kernel_size=3, stride=1, padding=1), + nn.BatchNorm2d(256), + nn.ReLU(), + ) + self.layer6 = nn.Sequential( + nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1), + nn.BatchNorm2d(256), + nn.ReLU(), + ) + self.layer7 = nn.Sequential( + nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1), + nn.BatchNorm2d(256), + nn.ReLU(), + nn.MaxPool2d(kernel_size=2, stride=2), + ) + self.layer8 = nn.Sequential( + nn.Conv2d(256, 512, kernel_size=3, stride=1, padding=1), + nn.BatchNorm2d(512), + nn.ReLU(), + ) + self.layer9 = nn.Sequential( + nn.Conv2d(512, 512, kernel_size=3, stride=1, padding=1), + nn.BatchNorm2d(512), + nn.ReLU(), + ) + self.layer10 = nn.Sequential( + nn.Conv2d(512, 512, kernel_size=3, stride=1, padding=1), + nn.BatchNorm2d(512), + nn.ReLU(), + nn.MaxPool2d(kernel_size=2, stride=2), + ) + self.layer11 = nn.Sequential( + nn.Conv2d(512, 512, kernel_size=3, stride=1, padding=1), + nn.BatchNorm2d(512), + nn.ReLU(), + ) + self.layer12 = nn.Sequential( + nn.Conv2d(512, 512, kernel_size=3, stride=1, padding=1), + nn.BatchNorm2d(512), + nn.ReLU(), + ) + self.layer13 = nn.Sequential( + nn.Conv2d(512, 512, kernel_size=3, stride=1, padding=1), + nn.BatchNorm2d(512), + nn.ReLU(), + nn.MaxPool2d(kernel_size=2, stride=2), + ) + self.fc = nn.Sequential( + nn.Dropout(0.5), nn.Linear(7 * 7 * 512, 4096), nn.ReLU() + ) + self.fc1 = nn.Sequential(nn.Dropout(0.5), nn.Linear(4096, 4096), nn.ReLU()) + self.fc2 = nn.Sequential(nn.Linear(4096, num_classes)) + + def forward(self, x): + out = self.layer1(x) + out = self.layer2(out) + out = self.layer3(out) + out = self.layer4(out) + out = self.layer5(out) + out = self.layer6(out) + out = self.layer7(out) + out = self.layer8(out) + out = self.layer9(out) + out = self.layer10(out) + out = self.layer11(out) + out = self.layer12(out) + out = self.layer13(out) + out = out.reshape(out.size(0), -1) + out = self.fc(out) + out = self.fc1(out) + out = self.fc2(out) + return out diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/model/linear.py b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/model/linear.py new file mode 100644 index 0000000..1f11d2d --- /dev/null +++ b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/model/linear.py @@ -0,0 +1,19 @@ +from torch import nn + + +class DNN(nn.Module): + def __init__(self, in_size, hidden_size, out_size): + super().__init__() + + # Define the activation function and the linear functions + self.act = nn.ReLU() + self.in_linear = nn.Linear(in_size, hidden_size) + self.out_linear = nn.Linear(hidden_size, out_size) + + def forward(self, x): + + # Send x through first linear layer and activation function + x = self.act(self.in_linear(x)) + + # Return x through the out linear function + return self.out_linear(x) diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/notebooks/features.ipynb b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/notebooks/features.ipynb new file mode 100644 index 0000000..cf1aee0 --- /dev/null +++ b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/notebooks/features.ipynb @@ -0,0 +1,23 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": null, + "id": "634a9940-7cda-4fe3-bd68-cd69c7db199d", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "", + "name": "" + }, + "language_info": { + "name": "" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/notebooks/main.ipynb b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/notebooks/main.ipynb new file mode 100644 index 0000000..16c4c9e --- /dev/null +++ b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/notebooks/main.ipynb @@ -0,0 +1,85 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 2, + "id": "9f86d9e7-ca94-4dce-b86d-7ddb261f4e25", + "metadata": {}, + "outputs": [], + "source": [ + "# Now you can import your package\n", + "import ml_pipeline" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "6ba8b629-82db-487f-acbf-2ca20feee7e2", + "metadata": {}, + "outputs": [], + "source": [ + "from ml_pipeline.data.dataset import MnistDataset" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "8fb6c881-46ba-40e5-b837-c507c5bfae21", + "metadata": {}, + "outputs": [], + "source": [ + "from ml_pipeline import config" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "c8ce7920-c056-44ac-93df-b25bae870592", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "config" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "83293ef7-37b3-452f-8de5-13bee633d099", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.11.2" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/training/__init__.py b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/training/__init__.py new file mode 100644 index 0000000..f0fad35 --- /dev/null +++ b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/training/__init__.py @@ -0,0 +1,12 @@ +""" +main class for building a DL pipeline. + +""" +from enum import Enum, auto + + +class Stage(Enum): + TRAIN = auto() + DEV = auto() + TEST = auto() + diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/training/pipeline.py b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/training/pipeline.py new file mode 100644 index 0000000..ae58dd6 --- /dev/null +++ b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/training/pipeline.py @@ -0,0 +1,55 @@ + +from torch.utils.data import DataLoader +from torch.optim import AdamW +from ml_pipeline.training.runner import Runner +from ml_pipeline import config, logger + + +def run(evaluate=False): + # Initialize the training set and a dataloader to iterate over the dataset + # train_set = GenericDataset() + dataset = get_dataset(evaluate) + dataloader = DataLoader(dataset, batch_size=config.training.batch_size, shuffle=True) + + model = get_model(name=config.model.name) + + optimizer = AdamW(model.parameters(), lr=config.training.learning_rate) + + # Create a runner that will handle + runner = Runner( + dataset=dataset, + dataloader=dataloader, + model=model, + optimizer=optimizer, + ) + + # Train the model + for _ in range(config.training.epochs): + # Run one loop of training and record the average loss + for step in runner.step(): + logger.info(f"{step}") + +def get_model(name='vgg11'): + from ml_pipeline.model.linear import DNN + from ml_pipeline.model.cnn import VGG11 + if name == 'vgg11': + return VGG11(config.data.in_channels, config.data.num_classes) + else: + # Create the model and optimizer and cast model to the appropriate GPU + in_features, out_features = dataset.in_out_features() + model = DNN(in_features, config.model.hidden_size, out_features) + return model.to(config.training.device) + + +def get_dataset(evaluate=False): + # Usage + from ml_pipeline.data.dataset import MnistDataset + from torchvision import transforms + csv_file_path = config.data.train_path if not evaluate else config.data.test_path + transform = transforms.Compose([ + transforms.ToTensor(), # Converts a PIL Image or numpy.ndarray to a FloatTensor and scales the image's pixel intensity values to the [0., 1.] range + transforms.Normalize((0.1307,), (0.3081,)) # Normalize using the mean and std specific to MNIST + ]) + + dataset = MnistDataset(csv_file_path) + return dataset diff --git a/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/training/runner.py b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/training/runner.py new file mode 100644 index 0000000..a6c65eb --- /dev/null +++ b/{{cookiecutter.project_slug}}/{{cookiecutter.module_name}}/training/runner.py @@ -0,0 +1,46 @@ +from torch import nn +from torch.utils.data import Dataset, DataLoader +from torch.optim import Optimizer + + +class Runner: + """Runner class that is in charge of implementing routine training functions such as running epochs or doing inference time""" + + def __init__(self, dataset: Dataset, dataloader: DataLoader, model: nn.Module, optimizer: Optimizer): + # Initialize class attributes + self.dataset = dataset + + # Prepare opt, model, and dataloader (helps accelerator auto-cast to devices) + self.optimizer, self.model, self.dataloader = ( + optimizer, model, dataloader + ) + + # Since data is for targets, use Mean Squared Error Loss + # self.criterion = nn.MSELoss() + self.criterion = nn.CrossEntropyLoss() + + def step(self): + """Runs an epoch of training. + + Includes updating model weights and tracking training loss + + Returns: + float: The loss averaged over the entire epoch + """ + + # turn the model to training mode (affects batchnorm and dropout) + self.model.train() + + total_loss, total_samples = 0.0, 0.0 + for sample, target in self.dataloader: + self.optimizer.zero_grad() # reset gradients to 0 + prediction = self.model(sample) # forward pass through model + loss = self.criterion(prediction, target) # error calculation + + # increment gradients within model by sending loss backwards + loss.backward() + self.optimizer.step() # update model weights + + total_loss += loss # increment running loss + total_samples += len(sample) + yield total_loss / total_samples # take the average of the loss over each sample