diff --git a/.trunk/config/ruff.toml b/.trunk/config/ruff.toml
index c382aa9..cd002b1 100644
--- a/.trunk/config/ruff.toml
+++ b/.trunk/config/ruff.toml
@@ -2,4 +2,4 @@
select = ["B", "D3", "D4", "E", "F"]
# Never enforce `E501` (line length violations). This should be handled by formatters.
-ignore = ["E501", "D417", "D401", "B905"]
+ignore = ["E501", "D417", "D401", "B905", "D409", "D301", "E402"]
diff --git a/LICENSE b/LICENSE
new file mode 100644
index 0000000..3cda0e5
--- /dev/null
+++ b/LICENSE
@@ -0,0 +1,661 @@
+ GNU AFFERO GENERAL PUBLIC LICENSE
+ Version 3, 19 November 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 Affero General Public License is a free, copyleft license for
+software and other kinds of works, specifically designed to ensure
+cooperation with the community in the case of network server software.
+
+ The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works. By contrast,
+our General Public Licenses are 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.
+
+ 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.
+
+ Developers that use our General Public Licenses protect your rights
+with two steps: (1) assert copyright on the software, and (2) offer
+you this License which gives you legal permission to copy, distribute
+and/or modify the software.
+
+ A secondary benefit of defending all users' freedom is that
+improvements made in alternate versions of the program, if they
+receive widespread use, become available for other developers to
+incorporate. Many developers of free software are heartened and
+encouraged by the resulting cooperation. However, in the case of
+software used on network servers, this result may fail to come about.
+The GNU General Public License permits making a modified version and
+letting the public access it on a server without ever releasing its
+source code to the public.
+
+ The GNU Affero General Public License is designed specifically to
+ensure that, in such cases, the modified source code becomes available
+to the community. It requires the operator of a network server to
+provide the source code of the modified version running there to the
+users of that server. Therefore, public use of a modified version, on
+a publicly accessible server, gives the public access to the source
+code of the modified version.
+
+ An older license, called the Affero General Public License and
+published by Affero, was designed to accomplish similar goals. This is
+a different license, not a version of the Affero GPL, but Affero has
+released a new version of the Affero GPL which permits relicensing under
+this license.
+
+ 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 Affero 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. Remote Network Interaction; Use with the GNU General Public License.
+
+ Notwithstanding any other provision of this License, if you modify the
+Program, your modified version must prominently offer all users
+interacting with it remotely through a computer network (if your version
+supports such interaction) an opportunity to receive the Corresponding
+Source of your version by providing access to the Corresponding Source
+from a network server at no charge, through some standard or customary
+means of facilitating copying of software. This Corresponding Source
+shall include the Corresponding Source for any work covered by version 3
+of the GNU General Public License that is incorporated pursuant to the
+following paragraph.
+
+ 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 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 work with which it is combined will remain governed by version
+3 of the GNU General Public License.
+
+ 14. Revised Versions of this License.
+
+ The Free Software Foundation may publish revised and/or new versions of
+the GNU Affero 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 Affero 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 Affero 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 Affero 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) 2024 Instituto Andaluz Interuniversitario en Ciencia de Datos e Inteligencia Computacional (DaSCI)
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU Affero 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 Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License
+ along with this program. If not, see .
+
+Also add information on how to contact you by electronic and paper mail.
+
+ If your software can interact with users remotely through a computer
+network, you should also make sure that it provides a way for users to
+get its source. For example, if your program is a web application, its
+interface could display a "Source" link that leads users to an archive
+of the code. There are many ways you could offer source, and different
+solutions will be better for different programs; see section 13 for the
+specific requirements.
+
+ 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 AGPL, see
+.
\ No newline at end of file
diff --git a/flextrees/__init__.py b/flextrees/__init__.py
index a1fcc69..09a996b 100644
--- a/flextrees/__init__.py
+++ b/flextrees/__init__.py
@@ -1,3 +1,19 @@
+"""
+Copyright (C) 2024 Instituto Andaluz Interuniversitario en Ciencia de Datos e Inteligencia Computacional (DaSCI)
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU Affero 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 Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License
+ along with this program. If not, see .
+"""
from __future__ import division
from __future__ import print_function
from __future__ import absolute_import
diff --git a/flextrees/datasets/__init__.py b/flextrees/datasets/__init__.py
index 2a8d052..2801b9a 100644
--- a/flextrees/datasets/__init__.py
+++ b/flextrees/datasets/__init__.py
@@ -1,3 +1,19 @@
+"""
+Copyright (C) 2024 Instituto Andaluz Interuniversitario en Ciencia de Datos e Inteligencia Computacional (DaSCI)
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU Affero 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 Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License
+ along with this program. If not, see .
+"""
from __future__ import division
from __future__ import print_function
from __future__ import absolute_import
diff --git a/flextrees/datasets/preprocessing_utils.py b/flextrees/datasets/preprocessing_utils.py
index 4185351..6ee99fd 100644
--- a/flextrees/datasets/preprocessing_utils.py
+++ b/flextrees/datasets/preprocessing_utils.py
@@ -1,5 +1,22 @@
+"""
+Copyright (C) 2024 Instituto Andaluz Interuniversitario en Ciencia de Datos e Inteligencia Computacional (DaSCI).
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU Affero 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 Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License
+ along with this program. If not, see .
+"""
import pandas as pd
+
def preprocess_adult(training_dataset):
"""Function to preprocess Adult dataset and transform it to a categorical dataset.
Function assumes dataset has columns labels ['x0', 'x1', 'x2',...,'x13', 'label']
@@ -11,117 +28,137 @@ def preprocess_adult(training_dataset):
Returns:
pd.DataFrame: Adult transformed into a categorical dataset.
"""
- if 'x2' in training_dataset.columns:
- training_dataset = training_dataset.drop(['x2'], axis=1)
- training_dataset['x0'] = training_dataset['x0'].astype(int)
- training_dataset['x4'] = training_dataset['x4'].astype(int)
- training_dataset['x10'] = training_dataset['x10'].astype(int)
- training_dataset['x11'] = training_dataset['x11'].astype(int)
- training_dataset['x12'] = training_dataset['x12'].astype(int)
-
- age = training_dataset['x0']
- edu_num = training_dataset['x4']
- cap_gain = training_dataset['x10']
- cap_loss = training_dataset['x11']
- hours = training_dataset['x12']
-
+ if "x2" in training_dataset.columns:
+ training_dataset = training_dataset.drop(["x2"], axis=1)
+ training_dataset["x0"] = training_dataset["x0"].astype(int)
+ training_dataset["x4"] = training_dataset["x4"].astype(int)
+ training_dataset["x10"] = training_dataset["x10"].astype(int)
+ training_dataset["x11"] = training_dataset["x11"].astype(int)
+ training_dataset["x12"] = training_dataset["x12"].astype(int)
+
+ age = training_dataset["x0"]
+ edu_num = training_dataset["x4"]
+ cap_gain = training_dataset["x10"]
+ cap_loss = training_dataset["x11"]
+ hours = training_dataset["x12"]
+
age_bins = [0, 18, 40, 80, 99]
- age_labels = ['teen', 'adult', 'old-adult', 'elder']
+ age_labels = ["teen", "adult", "old-adult", "elder"]
edu_num_bins = [0, 5, 10, 17]
- edu_num_labels = ['<5', '5-10', '>10']
+ edu_num_labels = ["<5", "5-10", ">10"]
cap_gain_bins = [-1, 1, 39999, 49999, 79999, 99999]
cap_gain_labels = [0, 1, 2, 3, 4]
cap_loss_bins = [-1, 1, 999, 1999, 2999, 3999, 4499]
cap_loss_labels = [0, 1, 2, 3, 4, 5]
hr_bins = [0, 20, 40, 100]
- hr_labels = ['<20', '20-40', '>40']
+ hr_labels = ["<20", "20-40", ">40"]
- training_dataset['x0'] = pd.cut(age, bins=age_bins, labels=age_labels)
- training_dataset['x4'] = pd.cut(edu_num, bins=edu_num_bins, labels=edu_num_labels)
- training_dataset['x10'] = pd.cut(cap_gain, bins=cap_gain_bins, labels=cap_gain_labels)
- training_dataset['x11'] = pd.cut(cap_loss, bins=cap_loss_bins, labels=cap_loss_labels)
- training_dataset['x12'] = pd.cut(hours, bins=hr_bins, labels=hr_labels)
+ training_dataset["x0"] = pd.cut(age, bins=age_bins, labels=age_labels)
+ training_dataset["x4"] = pd.cut(edu_num, bins=edu_num_bins, labels=edu_num_labels)
+ training_dataset["x10"] = pd.cut(
+ cap_gain, bins=cap_gain_bins, labels=cap_gain_labels
+ )
+ training_dataset["x11"] = pd.cut(
+ cap_loss, bins=cap_loss_bins, labels=cap_loss_labels
+ )
+ training_dataset["x12"] = pd.cut(hours, bins=hr_bins, labels=hr_labels)
- training_dataset['x1'] = training_dataset['x1'].map({
- " ?": 'others',
- " Federal-gov": 'gov', " Local-gov": 'gov',
- " Never-worked":'others',
- " Private": 'others',
- " Self-emp-inc": 'self',
- " Self-emp-not-inc":'self', " State-gov": 'gov',
- " Without-pay": 'others'
- })
+ training_dataset["x1"] = training_dataset["x1"].map(
+ {
+ " ?": "others",
+ " Federal-gov": "gov",
+ " Local-gov": "gov",
+ " Never-worked": "others",
+ " Private": "others",
+ " Self-emp-inc": "self",
+ " Self-emp-not-inc": "self",
+ " State-gov": "gov",
+ " Without-pay": "others",
+ }
+ )
- training_dataset['x3'] = training_dataset['x3'].map({
- " 10th": 'non_college'," 11th": 'non_college',
- " 12th": 'non_college', " 1st-4th": 'non_college',
- " 5th-6th": 'non_college', " 7th-8th": 'non_college',
- " 9th": 'non_college',
- " Assoc-acdm": 'assoc' , " Assoc-voc": 'assoc',
- " Bachelors": 'college',
- " Doctorate": 'grad', " HS-grad": 'grad', " Masters": 'grad',
- " Preschool": 'others',
- " Prof-school": 'others',
- " Some-college": 'college'
- })
+ training_dataset["x3"] = training_dataset["x3"].map(
+ {
+ " 10th": "non_college",
+ " 11th": "non_college",
+ " 12th": "non_college",
+ " 1st-4th": "non_college",
+ " 5th-6th": "non_college",
+ " 7th-8th": "non_college",
+ " 9th": "non_college",
+ " Assoc-acdm": "assoc",
+ " Assoc-voc": "assoc",
+ " Bachelors": "college",
+ " Doctorate": "grad",
+ " HS-grad": "grad",
+ " Masters": "grad",
+ " Preschool": "others",
+ " Prof-school": "others",
+ " Some-college": "college",
+ }
+ )
- training_dataset['x13'] = training_dataset['x13'].map({
- ' ?':'others',
- ' Cambodia': 'asia',
- ' Canada': 'north_america',
- ' China': 'asia',
- ' Columbia': 'south_america',
- ' Cuba': 'south_america',
- ' Dominican-Republic': 'south_america',
- ' Ecuador': 'south_america',
- ' El-Salvador': 'south_america',
- ' England': 'europe',
- ' France': 'europe',
- ' Germany':'europe',
- ' Greece':'europe',
- ' Guatemala': 'south_america',
- ' Haiti': 'south_america',
- ' Holand-Netherlands': 'europe',
- ' Honduras': 'south_america' ,
- ' Hong': 'asia',
- ' Hungary':'europe',
- ' India':'asia',
- ' Iran': 'asia',
- ' Ireland': 'europe',
- ' Italy': 'europe',
- ' Jamaica': 'south_america',
- ' Japan': 'asia',
- ' Laos': 'asia',
- ' Mexico': 'south_america',
- ' Nicaragua': 'south_america',
- ' Outlying-US(Guam-USVI-etc)': 'north_america',
- ' Peru': 'south_america',
- ' Philippines': 'asia',
- ' Poland': 'europe',
- ' Portugal': 'europe',
- ' Puerto-Rico': 'south_america',
- ' Scotland':'europe' ,
- ' South': 'asia',
- ' Taiwan': 'asia',
- ' Thailand': 'asia',
- ' Trinadad&Tobago': 'south_america',
- ' United-States': 'north_america',
- ' Vietnam': 'asia', ' Yugoslavia':'europe'
- })
+ training_dataset["x13"] = training_dataset["x13"].map(
+ {
+ " ?": "others",
+ " Cambodia": "asia",
+ " Canada": "north_america",
+ " China": "asia",
+ " Columbia": "south_america",
+ " Cuba": "south_america",
+ " Dominican-Republic": "south_america",
+ " Ecuador": "south_america",
+ " El-Salvador": "south_america",
+ " England": "europe",
+ " France": "europe",
+ " Germany": "europe",
+ " Greece": "europe",
+ " Guatemala": "south_america",
+ " Haiti": "south_america",
+ " Holand-Netherlands": "europe",
+ " Honduras": "south_america",
+ " Hong": "asia",
+ " Hungary": "europe",
+ " India": "asia",
+ " Iran": "asia",
+ " Ireland": "europe",
+ " Italy": "europe",
+ " Jamaica": "south_america",
+ " Japan": "asia",
+ " Laos": "asia",
+ " Mexico": "south_america",
+ " Nicaragua": "south_america",
+ " Outlying-US(Guam-USVI-etc)": "north_america",
+ " Peru": "south_america",
+ " Philippines": "asia",
+ " Poland": "europe",
+ " Portugal": "europe",
+ " Puerto-Rico": "south_america",
+ " Scotland": "europe",
+ " South": "asia",
+ " Taiwan": "asia",
+ " Thailand": "asia",
+ " Trinadad&Tobago": "south_america",
+ " United-States": "north_america",
+ " Vietnam": "asia",
+ " Yugoslavia": "europe",
+ }
+ )
- training_dataset['x0'] = training_dataset['x0'].astype('category')
- training_dataset['x1'] = training_dataset['x1'].astype('category')
- training_dataset['x3'] = training_dataset['x3'].astype('category')
- training_dataset['x4'] = training_dataset['x4'].astype('category')
- training_dataset['x10'] = training_dataset['x10'].astype('category')
- training_dataset['x11'] = training_dataset['x11'].astype('category')
- training_dataset['x12'] = training_dataset['x12'].astype('category')
- training_dataset['x13'] = training_dataset['x13'].astype('category')
+ training_dataset["x0"] = training_dataset["x0"].astype("category")
+ training_dataset["x1"] = training_dataset["x1"].astype("category")
+ training_dataset["x3"] = training_dataset["x3"].astype("category")
+ training_dataset["x4"] = training_dataset["x4"].astype("category")
+ training_dataset["x10"] = training_dataset["x10"].astype("category")
+ training_dataset["x11"] = training_dataset["x11"].astype("category")
+ training_dataset["x12"] = training_dataset["x12"].astype("category")
+ training_dataset["x13"] = training_dataset["x13"].astype("category")
- # training_dataset['label'] = training_dataset.apply(lambda row: 1 if '>50K' in row['label'] else 0, axis=1)
+ # training_dataset['label'] = training_dataset.apply(lambda row: 1 if '>50K' in row['label'] else 0, axis=1)
return training_dataset
+
def preprocess_credit2(training_dataset):
"""Function to preprocess Credit2 dataset and transform it to a categorical dataset.
Function assumes dataset has columns labels ['x1', 'x1', 'x2',...,'x22']
@@ -133,176 +170,265 @@ def preprocess_credit2(training_dataset):
pd.DataFrame: Credit2 transformed into a categorical dataset.
"""
# Amount of the given credit -> To deciles
- training_dataset['X1'] = pd.cut(training_dataset['X1'], bins=10, labels=[
- "(9999.999, 30000.0]", "(100000.0, 140000.0]", "(70000.0, 100000.0]",
- "(30000.0, 50000.0]", "(360000.0, 1000000.0]", "(180000.0, 210000.0]",
- "(210000.0, 270000.0]", "(50000.0, 70000.0]", "(270000.0, 360000.0]",
- "(140000.0, 180000.0]"
- ])
+ training_dataset["X1"] = pd.cut(
+ training_dataset["X1"],
+ bins=10,
+ labels=[
+ "(9999.999, 30000.0]",
+ "(100000.0, 140000.0]",
+ "(70000.0, 100000.0]",
+ "(30000.0, 50000.0]",
+ "(360000.0, 1000000.0]",
+ "(180000.0, 210000.0]",
+ "(210000.0, 270000.0]",
+ "(50000.0, 70000.0]",
+ "(270000.0, 360000.0]",
+ "(140000.0, 180000.0]",
+ ],
+ )
# Gender
- training_dataset['X2'] = training_dataset['X2'].map({
- 1:'male',
- 2:'female'
- })
+ training_dataset["X2"] = training_dataset["X2"].map({1: "male", 2: "female"})
# Education
- training_dataset['X3'] = training_dataset['X3'].map({
- 1:'graduate_school',
- 2:'university',
- 3:'high_school',
- 4:'others',
- 0:'others',
- 5:'others',
- 6:'others'
- })
+ training_dataset["X3"] = training_dataset["X3"].map(
+ {
+ 1: "graduate_school",
+ 2: "university",
+ 3: "high_school",
+ 4: "others",
+ 0: "others",
+ 5: "others",
+ 6: "others",
+ }
+ )
# Marital status
- training_dataset['X4'] = training_dataset['X4'].map({
- 1:'married',
- 2:'single',
- 3:'others',
- 0:'others'
- })
+ training_dataset["X4"] = training_dataset["X4"].map(
+ {1: "married", 2: "single", 3: "others", 0: "others"}
+ )
# Age
age_bins = [0, 18, 40, 80, 99]
- age_labels = ['teen', 'adult', 'old-adult', 'elder']
- training_dataset['X5'] = pd.cut(training_dataset['X5'], bins=age_bins,
- labels=age_labels)
- training_dataset['X5'] = training_dataset['X5'].astype('category')
+ age_labels = ["teen", "adult", "old-adult", "elder"]
+ training_dataset["X5"] = pd.cut(
+ training_dataset["X5"], bins=age_bins, labels=age_labels
+ )
+ training_dataset["X5"] = training_dataset["X5"].astype("category")
# History of past payments (April-September 2015): X6-X11.
# Features -2, and 0 were set with random names
- training_dataset['X6'] = training_dataset['X6'].map({
- -2:'pay_duty_t',
- -1:'pay_duty',
- 0:'payed',
- 1:'pay_delay_one_month',
- 2:'pay_delay_two_months',
- 3:'pay_delay_three_months',
- 4:'pay_delay_four_months',
- 5:'pay_delay_five_months',
- 6:'pay_delay_six_months',
- 7:'pay_delay_seven_months',
- 8:'pay_delay_eight_months',
- 9:'pay_delay_nine_months_above'
- })
- training_dataset['X7'] = training_dataset['X7'].map({
- -2:'pay_duty_t',
- -1:'pay_duty',
- 1:'pay_delay_one_month',
- 2:'pay_delay_two_months',
- 3:'pay_delay_three_months',
- 4:'pay_delay_four_months',
- 5:'pay_delay_five_months',
- 6:'pay_delay_six_months',
- 7:'pay_delay_seven_months',
- 8:'pay_delay_eight_months',
- 9:'pay_delay_nine_months_above',
- 0:'payed'
- })
- training_dataset['X8'] = training_dataset['X8'].map({
- -2:'pay_duty_t',
- -1:'pay_duty',
- 1:'pay_delay_one_month',
- 2:'pay_delay_two_months',
- 3:'pay_delay_three_months',
- 4:'pay_delay_four_months',
- 5:'pay_delay_five_months',
- 6:'pay_delay_six_months',
- 7:'pay_delay_seven_months',
- 8:'pay_delay_eight_months',
- 9:'pay_delay_nine_months_above',
- 0:'payed'
- })
- training_dataset['X9'] = training_dataset['X9'].map({
- -2:'pay_duty_t',
- -1:'pay_duty',
- 1:'pay_delay_one_month',
- 2:'pay_delay_two_months',
- 3:'pay_delay_three_months',
- 4:'pay_delay_four_months',
- 5:'pay_delay_five_months',
- 6:'pay_delay_six_months',
- 7:'pay_delay_seven_months',
- 8:'pay_delay_eight_months',
- 9:'pay_delay_nine_months_above',
- 0:'payed'
- })
- training_dataset['X10'] = training_dataset['X10'].map({
- -2:'pay_duty_t',
- -1:'pay_duty',
- 1:'pay_delay_one_month',
- 2:'pay_delay_two_months',
- 3:'pay_delay_three_months',
- 4:'pay_delay_four_months',
- 5:'pay_delay_five_months',
- 6:'pay_delay_six_months',
- 7:'pay_delay_seven_months',
- 8:'pay_delay_eight_months',
- 9:'pay_delay_nine_months_above',
- 0:'payed'
- })
- training_dataset['X11'] = training_dataset['X11'].map({
- -2:'pay_duty_t',
- -1:'pay_duty',
- 1:'pay_delay_one_month',
- 2:'pay_delay_two_months',
- 3:'pay_delay_three_months',
- 4:'pay_delay_four_months',
- 5:'pay_delay_five_months',
- 6:'pay_delay_six_months',
- 7:'pay_delay_seven_months',
- 8:'pay_delay_eight_months',
- 9:'pay_delay_nine_months_above',
- 0:'payed'
- })
+ training_dataset["X6"] = training_dataset["X6"].map(
+ {
+ -2: "pay_duty_t",
+ -1: "pay_duty",
+ 0: "payed",
+ 1: "pay_delay_one_month",
+ 2: "pay_delay_two_months",
+ 3: "pay_delay_three_months",
+ 4: "pay_delay_four_months",
+ 5: "pay_delay_five_months",
+ 6: "pay_delay_six_months",
+ 7: "pay_delay_seven_months",
+ 8: "pay_delay_eight_months",
+ 9: "pay_delay_nine_months_above",
+ }
+ )
+ training_dataset["X7"] = training_dataset["X7"].map(
+ {
+ -2: "pay_duty_t",
+ -1: "pay_duty",
+ 1: "pay_delay_one_month",
+ 2: "pay_delay_two_months",
+ 3: "pay_delay_three_months",
+ 4: "pay_delay_four_months",
+ 5: "pay_delay_five_months",
+ 6: "pay_delay_six_months",
+ 7: "pay_delay_seven_months",
+ 8: "pay_delay_eight_months",
+ 9: "pay_delay_nine_months_above",
+ 0: "payed",
+ }
+ )
+ training_dataset["X8"] = training_dataset["X8"].map(
+ {
+ -2: "pay_duty_t",
+ -1: "pay_duty",
+ 1: "pay_delay_one_month",
+ 2: "pay_delay_two_months",
+ 3: "pay_delay_three_months",
+ 4: "pay_delay_four_months",
+ 5: "pay_delay_five_months",
+ 6: "pay_delay_six_months",
+ 7: "pay_delay_seven_months",
+ 8: "pay_delay_eight_months",
+ 9: "pay_delay_nine_months_above",
+ 0: "payed",
+ }
+ )
+ training_dataset["X9"] = training_dataset["X9"].map(
+ {
+ -2: "pay_duty_t",
+ -1: "pay_duty",
+ 1: "pay_delay_one_month",
+ 2: "pay_delay_two_months",
+ 3: "pay_delay_three_months",
+ 4: "pay_delay_four_months",
+ 5: "pay_delay_five_months",
+ 6: "pay_delay_six_months",
+ 7: "pay_delay_seven_months",
+ 8: "pay_delay_eight_months",
+ 9: "pay_delay_nine_months_above",
+ 0: "payed",
+ }
+ )
+ training_dataset["X10"] = training_dataset["X10"].map(
+ {
+ -2: "pay_duty_t",
+ -1: "pay_duty",
+ 1: "pay_delay_one_month",
+ 2: "pay_delay_two_months",
+ 3: "pay_delay_three_months",
+ 4: "pay_delay_four_months",
+ 5: "pay_delay_five_months",
+ 6: "pay_delay_six_months",
+ 7: "pay_delay_seven_months",
+ 8: "pay_delay_eight_months",
+ 9: "pay_delay_nine_months_above",
+ 0: "payed",
+ }
+ )
+ training_dataset["X11"] = training_dataset["X11"].map(
+ {
+ -2: "pay_duty_t",
+ -1: "pay_duty",
+ 1: "pay_delay_one_month",
+ 2: "pay_delay_two_months",
+ 3: "pay_delay_three_months",
+ 4: "pay_delay_four_months",
+ 5: "pay_delay_five_months",
+ 6: "pay_delay_six_months",
+ 7: "pay_delay_seven_months",
+ 8: "pay_delay_eight_months",
+ 9: "pay_delay_nine_months_above",
+ 0: "payed",
+ }
+ )
# Amount of bill statement (NT dollar) in September 2005-August2005-...-April2005
- training_dataset['X12']= pd.qcut(training_dataset['X12'], [0, .25, .5, .75, 1], labels=[
- '(-165580.001, 3558.75]', '(3558.75, 22381.5]', '(22381.5, 67091.0]', '(67091.0, 964511.0]'
- ]
+ training_dataset["X12"] = pd.qcut(
+ training_dataset["X12"],
+ [0, 0.25, 0.5, 0.75, 1],
+ labels=[
+ "(-165580.001, 3558.75]",
+ "(3558.75, 22381.5]",
+ "(22381.5, 67091.0]",
+ "(67091.0, 964511.0]",
+ ],
)
- training_dataset['X13']= pd.qcut(training_dataset['X13'], [0, .25, .5, .75, 1], labels=[
- '(-157264.001, 2666.25]', '(2666.25, 20088.5]', '(20088.5, 60164.75]', '(60164.75, 1664089.0]'
- ]
+ training_dataset["X13"] = pd.qcut(
+ training_dataset["X13"],
+ [0, 0.25, 0.5, 0.75, 1],
+ labels=[
+ "(-157264.001, 2666.25]",
+ "(2666.25, 20088.5]",
+ "(20088.5, 60164.75]",
+ "(60164.75, 1664089.0]",
+ ],
)
- training_dataset['X14']= pd.qcut(training_dataset['X14'], [0, .25, .5, .75, 1], labels=[
- '(-157264.001, 2666.25]', '(2666.25, 20088.5]', '20088.5, 60164.75]', '(60164.75, 1664089.0]'
- ]
+ training_dataset["X14"] = pd.qcut(
+ training_dataset["X14"],
+ [0, 0.25, 0.5, 0.75, 1],
+ labels=[
+ "(-157264.001, 2666.25]",
+ "(2666.25, 20088.5]",
+ "20088.5, 60164.75]",
+ "(60164.75, 1664089.0]",
+ ],
)
- training_dataset['X15']= pd.qcut(training_dataset['X15'], [0, .25, .5, .75, 1], labels=[
- '(-170000.001, 2326.75]', '(2326.75, 19052.0]', '19052.0, 54506.0]', '(54506.0, 891586.0]'
- ]
+ training_dataset["X15"] = pd.qcut(
+ training_dataset["X15"],
+ [0, 0.25, 0.5, 0.75, 1],
+ labels=[
+ "(-170000.001, 2326.75]",
+ "(2326.75, 19052.0]",
+ "19052.0, 54506.0]",
+ "(54506.0, 891586.0]",
+ ],
)
- training_dataset['X16']= pd.qcut(training_dataset['X16'], [0, .25, .5, .75, 1], labels=[
- '(-81334.001, 1763.0]', '(1763.0, 18104.5]', '(18104.5, 50190.5]', '50190.5, 927171.0]'
- ]
+ training_dataset["X16"] = pd.qcut(
+ training_dataset["X16"],
+ [0, 0.25, 0.5, 0.75, 1],
+ labels=[
+ "(-81334.001, 1763.0]",
+ "(1763.0, 18104.5]",
+ "(18104.5, 50190.5]",
+ "50190.5, 927171.0]",
+ ],
)
- training_dataset['X17']= pd.qcut(training_dataset['X17'], [0, .25, .5, .75, 1], labels=[
- '(-339603.001, 1256.0]', '(1256.0, 17071.0]', '17071.0, 49198.25]', '(49198.25, 961664.0]'
- ]
+ training_dataset["X17"] = pd.qcut(
+ training_dataset["X17"],
+ [0, 0.25, 0.5, 0.75, 1],
+ labels=[
+ "(-339603.001, 1256.0]",
+ "(1256.0, 17071.0]",
+ "17071.0, 49198.25]",
+ "(49198.25, 961664.0]",
+ ],
)
# Amount of previous payment(NT dollar) in September 2005-...-April 2005
- training_dataset['X18']= pd.qcut(training_dataset['X18'], [0, .25, .5, .75, 1], labels=[
- '(-0.001, 1000.0]', '(1000.0, 2100.0]', '(2100.0, 5006.0]', '5006.0, 873552.0]'
- ]
+ training_dataset["X18"] = pd.qcut(
+ training_dataset["X18"],
+ [0, 0.25, 0.5, 0.75, 1],
+ labels=[
+ "(-0.001, 1000.0]",
+ "(1000.0, 2100.0]",
+ "(2100.0, 5006.0]",
+ "5006.0, 873552.0]",
+ ],
)
- training_dataset['X19']= pd.qcut(training_dataset['X19'], [0, .25, .5, .75, 1], labels=[
- '(-0.001, 833.0]', '(833.0, 2009.0]', '(2009.0, 5000.0]', '5000.0, 1684259.0]'
- ]
+ training_dataset["X19"] = pd.qcut(
+ training_dataset["X19"],
+ [0, 0.25, 0.5, 0.75, 1],
+ labels=[
+ "(-0.001, 833.0]",
+ "(833.0, 2009.0]",
+ "(2009.0, 5000.0]",
+ "5000.0, 1684259.0]",
+ ],
)
- training_dataset['X20']= pd.qcut(training_dataset['X20'], [0, .25, .5, .75, 1], labels=[
- '(-0.001, 390.0]', '(390.0, 1800.0]', '(1800.0, 4505.0]', '4505.0, 896040.0]'
- ]
+ training_dataset["X20"] = pd.qcut(
+ training_dataset["X20"],
+ [0, 0.25, 0.5, 0.75, 1],
+ labels=[
+ "(-0.001, 390.0]",
+ "(390.0, 1800.0]",
+ "(1800.0, 4505.0]",
+ "4505.0, 896040.0]",
+ ],
)
- training_dataset['X21']= pd.qcut(training_dataset['X21'], [0, .25, .5, .75, 1], labels=[
- '(-0.001, 296.0]', '(296.0, 1500.0]', '(1500.0, 4013.25]', '4013.25, 621000.0]'
- ]
+ training_dataset["X21"] = pd.qcut(
+ training_dataset["X21"],
+ [0, 0.25, 0.5, 0.75, 1],
+ labels=[
+ "(-0.001, 296.0]",
+ "(296.0, 1500.0]",
+ "(1500.0, 4013.25]",
+ "4013.25, 621000.0]",
+ ],
)
- training_dataset['X22']= pd.qcut(training_dataset['X22'], [0, .25, .5, .75, 1], labels=[
- '(-0.001, 252.5]', '(252.5, 1500.0]', '(1500.0, 4031.5]', '4031.5, 426529.0]'
- ]
+ training_dataset["X22"] = pd.qcut(
+ training_dataset["X22"],
+ [0, 0.25, 0.5, 0.75, 1],
+ labels=[
+ "(-0.001, 252.5]",
+ "(252.5, 1500.0]",
+ "(1500.0, 4031.5]",
+ "4031.5, 426529.0]",
+ ],
)
- training_dataset['X23']= pd.qcut(training_dataset['X23'], [0, .25, .5, .75, 1], labels=[
- '(-0.001, 117.75]', '(117.75, 1500.0]', '(1500.0, 4000.0]', '4000.0, 528666.0]'
- ]
+ training_dataset["X23"] = pd.qcut(
+ training_dataset["X23"],
+ [0, 0.25, 0.5, 0.75, 1],
+ labels=[
+ "(-0.001, 117.75]",
+ "(117.75, 1500.0]",
+ "(1500.0, 4000.0]",
+ "4000.0, 528666.0]",
+ ],
)
return training_dataset
-
-
diff --git a/flextrees/datasets/tabular_datasets.py b/flextrees/datasets/tabular_datasets.py
index ccdb126..42a1bd9 100644
--- a/flextrees/datasets/tabular_datasets.py
+++ b/flextrees/datasets/tabular_datasets.py
@@ -1,3 +1,19 @@
+"""
+Copyright (C) 2024 Instituto Andaluz Interuniversitario en Ciencia de Datos e Inteligencia Computacional (DaSCI)
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU Affero 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 Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License
+ along with this program. If not, see .
+"""
from flex.data import Dataset
from flextrees.datasets.preprocessing_utils import preprocess_credit2, preprocess_adult
diff --git a/flextrees/pool/__init__.py b/flextrees/pool/__init__.py
index 0033519..1453b31 100644
--- a/flextrees/pool/__init__.py
+++ b/flextrees/pool/__init__.py
@@ -1,3 +1,19 @@
+"""
+Copyright (C) 2024 Instituto Andaluz Interuniversitario en Ciencia de Datos e Inteligencia Computacional (DaSCI)
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU Affero 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 Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License
+ along with this program. If not, see .
+"""
from __future__ import division
from __future__ import print_function
from __future__ import absolute_import
diff --git a/flextrees/pool/aggregators_fedid3.py b/flextrees/pool/aggregators_fedid3.py
index 1489863..42883e9 100644
--- a/flextrees/pool/aggregators_fedid3.py
+++ b/flextrees/pool/aggregators_fedid3.py
@@ -1,56 +1,75 @@
+"""
+Copyright (C) 2024 Instituto Andaluz Interuniversitario en Ciencia de Datos e Inteligencia Computacional (DaSCI).
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU Affero 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 Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License
+ along with this program. If not, see .
+"""
import collections
+
from flex.pool.decorators import aggregate_weights
@aggregate_weights
def id3_aggegate_class_counts(aggregated_weights_as_list, *args, **kwargs):
"""Function to aggregate the class probabilities of a leaf node.
- # Arguments:
- params: Client class counts.
- # Returns:
- class_probs: Returns the class probabilities for the node.
- """
+ # Arguments:
+ params: Client class counts.
+ # Returns:
+ class_probs: Returns the class probabilities for the node.
+ """
agg_as_list = False
if isinstance(aggregated_weights_as_list, list):
aggregated_weights_as_list = aggregated_weights_as_list[0]
agg_as_list = True
- # breakpoint()
+ # breakpoint()
res = collections.Counter()
for k, weights in aggregated_weights_as_list.items():
- res.update({k:weights})
- # res |= weights
+ res.update({k: weights})
+ # res |= weights
if agg_as_list:
- return -1 if sum(res.values()) == 0 else max(res.keys(), key=lambda x:res[x])
+ return -1 if sum(res.values()) == 0 else max(res.keys(), key=lambda x: res[x])
+
+ key1 = max(res.keys(), key=lambda x: res[x])
+ return {key1: res[key1]}
- key1 = max(res.keys(), key=lambda x:res[x])
- return {key1:res[key1]}
@aggregate_weights
def id3_aggregate_counts(aggregated_weights_as_list, *args, **kwargs):
"""Function to aggregate the information gain for the available features
- at the client to select the best that will be chosen to split.
- # Arguments:
- params: Client info gain for the remaining features.
- # Returns:
- feature: Returns the feature with the maximum information gain.
- """
+ at the client to select the best that will be chosen to split.
+ # Arguments:
+ params: Client info gain for the remaining features.
+ # Returns:
+ feature: Returns the feature with the maximum information gain.
+ """
res = collections.Counter()
for weights in aggregated_weights_as_list:
- res.update(weights) # Keep .update for Python 3.8
- return -1 if sum(res.values()) == 0 else max(res.keys(), key=lambda x:res[x])
+ res.update(weights) # Keep .update for Python 3.8
+ return -1 if sum(res.values()) == 0 else max(res.keys(), key=lambda x: res[x])
+
@aggregate_weights
def id3_aggregate_class_counts_sum(aggregated_wegiths_as_list, *args, **kwargs):
"""Function to aggregate the information gain for the available features
- at the client to select the best that will be chosen to split.
- # Arguments:
- params: Client info gain for the remaining features.
- # Returns:
- info_gain: Returns the info_gain for the feature indicated
- """
+ at the client to select the best that will be chosen to split.
+ # Arguments:
+ params: Client info gain for the remaining features.
+ # Returns:
+ info_gain: Returns the info_gain for the feature indicated
+ """
res = collections.Counter()
if isinstance(aggregated_wegiths_as_list, list):
aggregated_wegiths_as_list = aggregated_wegiths_as_list[0]
for k, v in aggregated_wegiths_as_list.items():
- res.update({k:v})
- return res
\ No newline at end of file
+ res.update({k: v})
+ return res
diff --git a/flextrees/pool/aggregators_fedrf.py b/flextrees/pool/aggregators_fedrf.py
index e10d863..05d151a 100644
--- a/flextrees/pool/aggregators_fedrf.py
+++ b/flextrees/pool/aggregators_fedrf.py
@@ -1,3 +1,19 @@
+"""
+Copyright (C) 2024 Instituto Andaluz Interuniversitario en Ciencia de Datos e Inteligencia Computacional (DaSCI).
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU Affero 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 Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License
+ along with this program. If not, see .
+"""
import numpy as np
from flex.pool.decorators import aggregate_weights
@@ -14,4 +30,4 @@ def aggregate_trees_from_rf(aggregated_trees, *args, **kwargs):
"""
# Make the aggregator to append all the trees in a list
aggregated_trees = [tree for trees in aggregated_trees for tree in trees]
- return aggregated_trees
\ No newline at end of file
+ return aggregated_trees
diff --git a/flextrees/pool/aggregators_fegbdt.py b/flextrees/pool/aggregators_fegbdt.py
index 21b934e..b40013c 100644
--- a/flextrees/pool/aggregators_fegbdt.py
+++ b/flextrees/pool/aggregators_fegbdt.py
@@ -1,3 +1,19 @@
+"""
+Copyright (C) 2024 Instituto Andaluz Interuniversitario en Ciencia de Datos e Inteligencia Computacional (DaSCI).
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU Affero 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 Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License
+ along with this program. If not, see .
+"""
import random
from flex.pool.decorators import aggregate_weights
diff --git a/flextrees/pool/pool_functions.py b/flextrees/pool/pool_functions.py
index fb7a6af..485bccc 100644
--- a/flextrees/pool/pool_functions.py
+++ b/flextrees/pool/pool_functions.py
@@ -1,3 +1,19 @@
+"""
+Copyright (C) 2024 Instituto Andaluz Interuniversitario en Ciencia de Datos e Inteligencia Computacional (DaSCI).
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU Affero 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 Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License
+ along with this program. If not, see .
+"""
from flex.actors.role_manager import FlexRoleManager
diff --git a/flextrees/pool/primitives_fedgbdt.py b/flextrees/pool/primitives_fedgbdt.py
index f11e755..1a198da 100644
--- a/flextrees/pool/primitives_fedgbdt.py
+++ b/flextrees/pool/primitives_fedgbdt.py
@@ -1,3 +1,19 @@
+"""
+Copyright (C) 2024 Instituto Andaluz Interuniversitario en Ciencia de Datos e Inteligencia Computacional (DaSCI)
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU Affero 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 Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License
+ along with this program. If not, see .
+"""
import random
from copy import deepcopy
diff --git a/flextrees/pool/primitives_fedid3.py b/flextrees/pool/primitives_fedid3.py
index 5448d59..74333c6 100644
--- a/flextrees/pool/primitives_fedid3.py
+++ b/flextrees/pool/primitives_fedid3.py
@@ -1,3 +1,19 @@
+"""
+Copyright (C) 2024 Instituto Andaluz Interuniversitario en Ciencia de Datos e Inteligencia Computacional (DaSCI)
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU Affero 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 Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License
+ along with this program. If not, see .
+"""
import random
from copy import deepcopy
diff --git a/flextrees/pool/primitives_fedrf.py b/flextrees/pool/primitives_fedrf.py
index ce3b4a8..4dd6bd2 100644
--- a/flextrees/pool/primitives_fedrf.py
+++ b/flextrees/pool/primitives_fedrf.py
@@ -1,3 +1,19 @@
+"""
+Copyright (C) 2024 Instituto Andaluz Interuniversitario en Ciencia de Datos e Inteligencia Computacional (DaSCI)
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU Affero 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 Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License
+ along with this program. If not, see .
+"""
import random
from copy import deepcopy
diff --git a/flextrees/utils/__init__.py b/flextrees/utils/__init__.py
index ab8914a..c123289 100644
--- a/flextrees/utils/__init__.py
+++ b/flextrees/utils/__init__.py
@@ -1,3 +1,19 @@
+"""
+Copyright (C) 2024 Instituto Andaluz Interuniversitario en Ciencia de Datos e Inteligencia Computacional (DaSCI)
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU Affero 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 Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License
+ along with this program. If not, see .
+"""
from __future__ import division
from __future__ import print_function
from __future__ import absolute_import
diff --git a/flextrees/utils/trees_metrics.py b/flextrees/utils/trees_metrics.py
index d93105a..dc191e2 100644
--- a/flextrees/utils/trees_metrics.py
+++ b/flextrees/utils/trees_metrics.py
@@ -1,8 +1,25 @@
-import os
+"""
+Copyright (C) 2024 Instituto Andaluz Interuniversitario en Ciencia de Datos e Inteligencia Computacional (DaSCI).
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU Affero 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 Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License
+ along with this program. If not, see .
+"""
import csv
import math
+import os
from collections import deque
+
def get_feature_with_max_information_gain(X, y, x_ids, feature_ids, _features):
"""Function that calculate the information gian for all the features available
and return that feature.
@@ -13,14 +30,16 @@ def get_feature_with_max_information_gain(X, y, x_ids, feature_ids, _features):
feature_ids: ids of the available features
"""
# print('Get feature max info gain')
- features_info_gain = [information_gain(X, y, x_ids, feature_id)
- for feature_id in feature_ids]
+ features_info_gain = [
+ information_gain(X, y, x_ids, feature_id) for feature_id in feature_ids
+ ]
split = {
- _features[feature_id]:features_info_gain[i]
+ _features[feature_id]: features_info_gain[i]
for i, feature_id in enumerate(feature_ids)
}
return split
+
def information_gain(X, y, x_ids, feature_id):
"""Calculate information gain for the remaining data for a feature
@@ -37,9 +56,7 @@ def information_gain(X, y, x_ids, feature_id):
feature_set_values = list(set(feature_values))
feature_val_count = [feature_values.count(x) for x in feature_set_values]
feature_val_id = [
- [x_ids[i]
- for i, x in enumerate(feature_values)
- if x == feat]
+ [x_ids[i] for i, x in enumerate(feature_values) if x == feat]
for feat in feature_set_values
]
info_gain_feature = sum(
@@ -50,6 +67,7 @@ def information_gain(X, y, x_ids, feature_id):
return info_gain
+
def entropy(x_ids, y):
"""Calculates the entropy
@@ -65,12 +83,12 @@ def entropy(x_ids, y):
label_count = [labels.count(x) for x in set(y)]
# Calculate the entropy of each category and sum them
entropy = sum(
- -count / len(x_ids) * math.log(count / len(x_ids), 2)
- if count else 0
+ -count / len(x_ids) * math.log(count / len(x_ids), 2) if count else 0
for count in label_count
)
return entropy
+
def reach_root_node(node):
"""Function to reach root node in a tree.
# Arguments:
@@ -86,6 +104,7 @@ def reach_root_node(node):
stack.reverse()
return stack
+
def get_df_cut(df_, stack):
"""Function that receive a stack and get the dataframe cut to the values
of the features.
@@ -95,7 +114,7 @@ def get_df_cut(df_, stack):
stack: stack with the path from the node to the root path.
"""
# Transform the stack into a list that contains tuples (feature, value).
- root_path = [(stack[i], stack[i+1]) for i in range(0, len(stack), 2)]
+ root_path = [(stack[i], stack[i + 1]) for i in range(0, len(stack), 2)]
# Query method can be faster then the for loop.
# query = ' and '.join(feature+"=="+'"'+str(value)+'"' for feature, value in root_path)
# df = self._df.query(query) if root_path else self._df
@@ -106,26 +125,34 @@ def get_df_cut(df_, stack):
x_ids = list(df_.index)
return x_ids, df_
-def client_write_results(filename, client_id, acc_local, f1_local,
- tam_test_data):
+
+def client_write_results(filename, client_id, acc_local, f1_local, tam_test_data):
if not os.path.exists(filename):
- header = ['client_id', 'local_model_acc', 'local_model_f1', 'tam_test_data']
- with open(filename, 'a', newline='', encoding='utf-8') as f:
+ header = ["client_id", "local_model_acc", "local_model_f1", "tam_test_data"]
+ with open(filename, "a", newline="", encoding="utf-8") as f:
wr = csv.writer(f)
wr.writerow(header)
results = [client_id, acc_local, f1_local, tam_test_data]
- with open(filename, 'a', newline='', encoding='utf-8') as f:
+ with open(filename, "a", newline="", encoding="utf-8") as f:
wr = csv.writer(f)
wr.writerow(results)
-def server_write_results(filename, client_id, acc_local, f1_local,
- tam_test_data, etime):
+
+def server_write_results(
+ filename, client_id, acc_local, f1_local, tam_test_data, etime
+):
if not os.path.exists(filename):
- header = ['client_id', 'local_model_acc', 'local_model_f1', 'tam_test_data', 'time']
- with open(filename, 'a', newline='', encoding='utf-8') as f:
+ header = [
+ "client_id",
+ "local_model_acc",
+ "local_model_f1",
+ "tam_test_data",
+ "time",
+ ]
+ with open(filename, "a", newline="", encoding="utf-8") as f:
wr = csv.writer(f)
wr.writerow(header)
results = [client_id, acc_local, f1_local, tam_test_data, etime]
- with open(filename, 'a', newline='', encoding='utf-8') as f:
+ with open(filename, "a", newline="", encoding="utf-8") as f:
wr = csv.writer(f)
wr.writerow(results)
diff --git a/flextrees/utils/utils_gbdt.py b/flextrees/utils/utils_gbdt.py
index ec0a50b..20e6758 100644
--- a/flextrees/utils/utils_gbdt.py
+++ b/flextrees/utils/utils_gbdt.py
@@ -1,3 +1,19 @@
+"""
+Copyright (C) 2024 Instituto Andaluz Interuniversitario en Ciencia de Datos e Inteligencia Computacional (DaSCI)
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU Affero 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 Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License
+ along with this program. If not, see .
+"""
# lshash/lshash.py
# Copyright 2012 Kay Zhu (a.k.a He Zhu) and contributors (see CONTRIBUTORS.txt)
#
diff --git a/flextrees/utils/utils_rf.py b/flextrees/utils/utils_rf.py
index 7399516..3b0ed52 100644
--- a/flextrees/utils/utils_rf.py
+++ b/flextrees/utils/utils_rf.py
@@ -1,8 +1,24 @@
+"""
+Copyright (C) 2024 Instituto Andaluz Interuniversitario en Ciencia de Datos e Inteligencia Computacional (DaSCI).
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU Affero 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 Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License
+ along with this program. If not, see .
+"""
from copy import deepcopy
class GlobalRandomForest:
- def __init__(self, max_depth=5, n_estimators=10, estimators_ = None) -> None:
+ def __init__(self, max_depth=5, n_estimators=10, estimators_=None) -> None:
self.max_depth = max_depth
self.n_estimators = n_estimators
self.estimators_ = [] if estimators_ is None else estimators_
@@ -24,8 +40,10 @@ def predict(self, X):
if i not in predictions:
predictions[i] = []
predictions[i].append(p)
+
def most_common(lst):
return max(set(lst), key=lst.count)
+
predictions = [most_common(predictions[i]) for i in range(len(predictions))]
return predictions
diff --git a/flextrees/utils/utils_trees.py b/flextrees/utils/utils_trees.py
index abaa959..11b433c 100644
--- a/flextrees/utils/utils_trees.py
+++ b/flextrees/utils/utils_trees.py
@@ -1,6 +1,22 @@
+"""
+Copyright (C) 2024 Instituto Andaluz Interuniversitario en Ciencia de Datos e Inteligencia Computacional (DaSCI).
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU Affero 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 Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License
+ along with this program. If not, see .
+"""
import time
-from copy import deepcopy
from collections import deque
+
import numpy as np
from numpy.lib import math
from sklearn.exceptions import NotFittedError
@@ -32,7 +48,7 @@ def __init__(self):
self.right = None
self.available_features = None
# criterion value
- self.criterion_value = None # Used in ID3Classifier
+ self.criterion_value = None # Used in ID3Classifier
self.value_proba = None
# To simulate sklearn atributes
self.n_classes = None
@@ -49,7 +65,7 @@ class ID3:
Actually, this model only supports categorical data, as we have used it only with Nursery.
In the future it will support discrete and continuous data too.
-
+
This model is the one used in the Federated ID3 method.
# Arguments:
@@ -69,19 +85,16 @@ def __init__(self, max_depth, feature_names):
@property
def max_depth_(self):
- """Property to get the maximum depth of the tree
- """
+ """Property to get the maximum depth of the tree"""
return self._max_depth
@property
def tree(self):
- """Property that returns the root from the tree
- """
+ """Property that returns the root from the tree"""
return self._node
def set_root(self, node):
- """Set the root node for the ID3 tree
- """
+ """Set the root node for the ID3 tree"""
self._node = node
def predict(self, data):
@@ -93,12 +106,11 @@ def predict(self, data):
"""
if not self._node:
- raise NotFittedError('No se ha entrenado el modelo.')
+ raise NotFittedError("No se ha entrenado el modelo.")
return np.array([self._predict_node(self._node, row) for row in data])
def _predict_node(self, node, row):
- """Predict the row if node is leaf, else keep moving up the tree
- """
+ """Predict the row if node is leaf, else keep moving up the tree"""
if not node.childs:
return node.value
index = self.feature_names.index(node.value)
@@ -109,8 +121,7 @@ def _predict_node(self, node, row):
return self._predict_node(next_child, row)
def print_tree_(self):
- """Function to print an ID3 tree. This functions add depth times a '\t'.
- """
+ """Function to print an ID3 tree. This functions add depth times a '\t'."""
if not self._node:
return
nodes = deque()
@@ -120,15 +131,18 @@ def print_tree_(self):
# print(f'The value of the node is: {node.value}')
# print(f'This node has depth: {node.depth}')
if node:
- times = '\t'*node.depth
- print(times, node.value, ' parent: ', node.dad.dad.value) if (node.dad and node) else print(times, node.value)
+ times = "\t" * node.depth
+ print(times, node.value, " parent: ", node.dad.dad.value) if (
+ node.dad and node
+ ) else print(times, node.value)
if node.childs:
for child in node.childs:
nodes.append(child.next)
+
class CART:
"""Class containing the tree structure of the CART model.
-
+
This model is used in the Federated Extra-Trees method, where it builds
multiple CARTs. The Federated Extra-Trees method is based on the Extra-Trees
method, and will be added in the future.
@@ -137,19 +151,18 @@ class CART:
node: root node
feature_names: Names of the features used in the training stage
"""
+
def __init__(self, feature_names):
self._node = None
self.feature_names = feature_names
@property
def tree(self):
- """Property that returns the root from the tree
- """
+ """Property that returns the root from the tree"""
return self._node
def set_root(self, node):
- """Set the root node for the ID3 tree
- """
+ """Set the root node for the ID3 tree"""
self._node = node
def predict(self, data):
@@ -161,7 +174,7 @@ def predict(self, data):
"""
if not self._node:
- raise NotFittedError('No se ha entrenado el modelo.')
+ raise NotFittedError("No se ha entrenado el modelo.")
return np.array([self._predict_node(self._node, row) for row in data])
def _predict_node(self, node, row): # sourcery skip: merge-else-if-into-elif
@@ -170,7 +183,7 @@ def _predict_node(self, node, row): # sourcery skip: merge-else-if-into-elif
node (Node): Actual node that will be tested.
row (np.array): row to be predicted
Returns:
- Node or Value: If node is leaf returns prediction else returns the next
+ Node or Value: If node is leaf returns prediction else returns the next
child based on the feature.
"""
if not node.childs:
@@ -178,22 +191,23 @@ def _predict_node(self, node, row): # sourcery skip: merge-else-if-into-elif
index = self.feature_names.index(node.value)
test_value = row[index]
for child in node.childs:
- sign, value = child.value.split(',')
- value = float(value)
- if child.next and ((sign == '<=' and test_value <= value) or sign == '>'):
+ sign, value = child.value.split(",")
+ value = float(value)
+ if child.next and ((sign == "<=" and test_value <= value) or sign == ">"):
return self._predict_node(child.next, row)
def print_tree_(self):
- """Function to print a Cart tree. This functions add depth times a '\t'.
- """
+ """Function to print a Cart tree. This functions add depth times a '\t'."""
if not self._node:
return
nodes = deque()
nodes.append(self._node)
while len(nodes) > 0:
node = nodes.popleft()
- times = '\t'*node.depth
- print(times, node.value, ' parent: ', node.dad.dad.value) if node.dad else print(times, node.value)
+ times = "\t" * node.depth
+ print(
+ times, node.value, " parent: ", node.dad.dad.value
+ ) if node.dad else print(times, node.value)
if node.childs:
for child in node.childs:
nodes.append(child.next)
@@ -204,8 +218,17 @@ class TreeBoosting:
Class used to build a CART deccision tree model with the boosting method. This method
is called at level client at the Federated Gradient Boosting Decision Trees.
"""
- def __init__(self, subsample_cols=0.8, min_leaf=5, min_child_weight=1,
- max_deph=8, lambda_=1, gamma=1, eps=0.1):
+
+ def __init__(
+ self,
+ subsample_cols=0.8,
+ min_leaf=5,
+ min_child_weight=1,
+ max_deph=8,
+ lambda_=1,
+ gamma=1,
+ eps=0.1,
+ ):
self.max_depth = max_deph
self.min_leaf = min_leaf
self.lambda_ = lambda_
@@ -216,16 +239,16 @@ def __init__(self, subsample_cols=0.8, min_leaf=5, min_child_weight=1,
self.subsample_cols = subsample_cols
self.eps = eps
self.val = None
- self.score = float('-inf')
+ self.score = float("-inf")
self.root = None
self.split_value = None
self.depth = -1
self.var_id = None
def compute_gamma(self, gradient, hessian):
- '''
+ """
Calculates the optimal leaf value equation (5) in "XGBoost: A Scalable Tree Boosting System"
- '''
+ """
return -np.sum(gradient) / (np.sum(hessian) + self.lambda_)
def gain(self, lhs, rhs, gradient, hessian, x_ids):
@@ -248,82 +271,128 @@ def gain(self, lhs, rhs, gradient, hessian, x_ids):
rhs_gradient = gradient_[rhs].sum()
rhs_hessian = hessian_[rhs].sum()
- gain = 0.5 * (
- (lhs_gradient**2/(lhs_hessian+self.lambda_)) +
- (rhs_gradient**2/(rhs_hessian+self.lambda_)) -
- (
- (lhs_gradient + rhs_gradient)**2/(lhs_hessian + rhs_hessian + self.lambda_)
+ gain = (
+ 0.5
+ * (
+ (lhs_gradient**2 / (lhs_hessian + self.lambda_))
+ + (rhs_gradient**2 / (rhs_hessian + self.lambda_))
+ - (
+ (lhs_gradient + rhs_gradient) ** 2
+ / (lhs_hessian + rhs_hessian + self.lambda_)
+ )
)
- ) - self.gamma
+ - self.gamma
+ )
return gain
def fit(self, x, gradient, hessian, x_ids, depth=1):
self.col_count = x.shape[1]
self.row_count = len(x_ids)
- self.column_subsample = np.random.permutation(self.col_count)[:round(self.subsample_cols*self.col_count)]
+ self.column_subsample = np.random.permutation(self.col_count)[
+ : round(self.subsample_cols * self.col_count)
+ ]
self.val = self.compute_gamma(gradient[x_ids], hessian[x_ids])
- self.depth=depth
+ self.depth = depth
# self.root = self.split(x, gradient, hessian, x_ids)
self.split(x, gradient, hessian, x_ids)
return self
def find_greedy_split(self, x, x_ids, var_id, gradient, hessian):
- x_ = x[x_ids,var_id]
-
+ x_ = x[x_ids, var_id]
+
for r in range(self.row_count):
lhs = x_ <= x_[r]
rhs = x_ > x_[r]
lhs_indices = np.nonzero(x_ <= x_[r])[0]
rhs_indices = np.nonzero(x_ > x_[r])[0]
- if lhs.sum() < self.min_leaf or rhs.sum() < self.min_leaf or hessian[lhs_indices].sum() < self.min_child_weight or hessian[rhs_indices].sum() < self.min_child_weight:
+ if (
+ lhs.sum() < self.min_leaf
+ or rhs.sum() < self.min_leaf
+ or hessian[lhs_indices].sum() < self.min_child_weight
+ or hessian[rhs_indices].sum() < self.min_child_weight
+ ):
continue
- curr_score = self.gain(lhs=lhs, rhs=rhs, gradient=gradient, hessian=hessian, x_ids=x_ids)
+ curr_score = self.gain(
+ lhs=lhs, rhs=rhs, gradient=gradient, hessian=hessian, x_ids=x_ids
+ )
if curr_score > self.score:
self.var_id = var_id
self.score = curr_score
self.split_value = x_[r]
def find_greedy_split_improved(self, x, x_ids, var_id, gradient, hessian):
- x_ = x[x_ids,var_id]
+ x_ = x[x_ids, var_id]
# Get unique values for the actual node
values = np.unique(x_)
-
+
for val in values:
lhs = x_ <= val
rhs = x_ > val
-
+
lhs_indices = np.nonzero(x_ <= val)[0]
rhs_indices = np.nonzero(x_ > val)[0]
- if lhs.sum() < self.min_leaf or rhs.sum() < self.min_leaf or hessian[lhs_indices].sum() < self.min_child_weight or hessian[rhs_indices].sum() < self.min_child_weight:
+ if (
+ lhs.sum() < self.min_leaf
+ or rhs.sum() < self.min_leaf
+ or hessian[lhs_indices].sum() < self.min_child_weight
+ or hessian[rhs_indices].sum() < self.min_child_weight
+ ):
continue
- curr_score = self.gain(lhs=lhs, rhs=rhs, gradient=gradient, hessian=hessian, x_ids=x_ids)
+ curr_score = self.gain(
+ lhs=lhs, rhs=rhs, gradient=gradient, hessian=hessian, x_ids=x_ids
+ )
if curr_score > self.score:
self.var_id = var_id
self.score = curr_score
self.split_value = val
- def split(self, x, gradient, hessian, x_ids): # , depth=1):
- """Builds the decision tree
- """
- for c in self.column_subsample: self.find_greedy_split_improved(x=x, x_ids=x_ids, var_id=c, gradient=gradient,
- hessian=hessian)
- if self.is_leaf: return
+ def split(self, x, gradient, hessian, x_ids): # , depth=1):
+ """Builds the decision tree"""
+ for c in self.column_subsample:
+ self.find_greedy_split_improved(
+ x=x, x_ids=x_ids, var_id=c, gradient=gradient, hessian=hessian
+ )
+ if self.is_leaf:
+ return
x_ = self.split_col(x, x_ids)
-
lhs = np.nonzero(x_ <= self.split_value)[0]
rhs = np.nonzero(x_ > self.split_value)[0]
- self.lhs = TreeBoosting(subsample_cols=self.subsample_cols, min_leaf=self.min_leaf, min_child_weight=self.min_child_weight,
- max_deph=self.max_depth, lambda_=self.lambda_, gamma=self.gamma,
- eps=self.eps).fit(x=x, gradient=gradient, hessian=hessian, x_ids=x_ids[lhs], depth=self.depth+1)
- self.rhs = TreeBoosting(subsample_cols=self.subsample_cols, min_leaf=self.min_leaf, min_child_weight=self.min_child_weight,
- max_deph=self.max_depth, lambda_=self.lambda_, gamma=self.gamma,
- eps=self.eps).fit(x=x, gradient=gradient, hessian=hessian, x_ids=x_ids[rhs], depth=self.depth+1)
+ self.lhs = TreeBoosting(
+ subsample_cols=self.subsample_cols,
+ min_leaf=self.min_leaf,
+ min_child_weight=self.min_child_weight,
+ max_deph=self.max_depth,
+ lambda_=self.lambda_,
+ gamma=self.gamma,
+ eps=self.eps,
+ ).fit(
+ x=x,
+ gradient=gradient,
+ hessian=hessian,
+ x_ids=x_ids[lhs],
+ depth=self.depth + 1,
+ )
+ self.rhs = TreeBoosting(
+ subsample_cols=self.subsample_cols,
+ min_leaf=self.min_leaf,
+ min_child_weight=self.min_child_weight,
+ max_deph=self.max_depth,
+ lambda_=self.lambda_,
+ gamma=self.gamma,
+ eps=self.eps,
+ ).fit(
+ x=x,
+ gradient=gradient,
+ hessian=hessian,
+ x_ids=x_ids[rhs],
+ depth=self.depth + 1,
+ )
def split_col(self, x, x_ids):
"""Function that splits a column
@@ -340,7 +409,7 @@ def is_leaf(self):
Args:
depth (int): actual depth of the tree
"""
- return self.score == float('-inf') or self.depth >= self.max_depth
+ return self.score == float("-inf") or self.depth >= self.max_depth
def predict_row(self, xi):
if self.is_leaf:
diff --git a/setup.py b/setup.py
index 26ba9c1..0097746 100644
--- a/setup.py
+++ b/setup.py
@@ -1,3 +1,19 @@
+"""
+Copyright (C) 2024 Instituto Andaluz Interuniversitario en Ciencia de Datos e Inteligencia Computacional (DaSCI)
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU Affero 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 Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License
+ along with this program. If not, see .
+"""
from setuptools import find_packages, setup
setup(