📝 Adds paper link to readme

.gitignore

@@ -6,6 +6,7 @@ venv/
 __pycache__/
 
 results/
+paper/
 
 *.zip
 *.csv
@@ -13,6 +14,10 @@ results/
 
 *.jasp
 *.pth
+*.png
+!structure.png
+!example-graph.png
+*.drawio
 
 *.tar.gz
 *.zip

CREDITS.md

@@ -0,0 +1,19 @@
+## Credits
+
+These are the people who made this project possible:
+
+- *Mgr. Martina Šandor*
+  - primary consultant
+  - psychology consultant
+- *Ing. Martin Berki*
+  - neural network
+  - statistics consultant
+- *Ing. Mária Dvorská*
+  - economics consultant
+- *Mgr. Marcel Sokolovič*
+  - sociology consultant
+- *Georgie Polymenakou*
+  - statistics consultant
+- and everyone else who offered a helping hand
+
+I thank you all again, I couldn't have done it without you

LICENSE

@@ -0,0 +1,675 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The GNU General Public License is a free, copyleft license for
+software and other kinds of works.
+
+  The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works.  By contrast,
+the GNU General Public License is intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users.  We, the Free Software Foundation, use the
+GNU General Public License for most of our software; it applies also to
+any other work released this way by its authors.  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+  To protect your rights, we need to prevent others from denying you
+these rights or asking you to surrender the rights.  Therefore, you have
+certain responsibilities if you distribute copies of the software, or if
+you modify it: responsibilities to respect the freedom of others.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must pass on to the recipients the same
+freedoms that you received.  You must make sure that they, too, receive
+or can get the source code.  And you must show them these terms so they
+know their rights.
+
+  Developers that use the GNU GPL protect your rights with two steps:
+(1) assert copyright on the software, and (2) offer you this License
+giving you legal permission to copy, distribute and/or modify it.
+
+  For the developers' and authors' protection, the GPL clearly explains
+that there is no warranty for this free software.  For both users' and
+authors' sake, the GPL requires that modified versions be marked as
+changed, so that their problems will not be attributed erroneously to
+authors of previous versions.
+
+  Some devices are designed to deny users access to install or run
+modified versions of the software inside them, although the manufacturer
+can do so.  This is fundamentally incompatible with the aim of
+protecting users' freedom to change the software.  The systematic
+pattern of such abuse occurs in the area of products for individuals to
+use, which is precisely where it is most unacceptable.  Therefore, we
+have designed this version of the GPL to prohibit the practice for those
+products.  If such problems arise substantially in other domains, we
+stand ready to extend this provision to those domains in future versions
+of the GPL, as needed to protect the freedom of users.
+
+  Finally, every program is threatened constantly by software patents.
+States should not allow patents to restrict development and use of
+software on general-purpose computers, but in those that do, we wish to
+avoid the special danger that patents applied to a free program could
+make it effectively proprietary.  To prevent this, the GPL assures that
+patents cannot be used to render the program non-free.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                       TERMS AND CONDITIONS
+
+  0. Definitions.
+
+  "This License" refers to version 3 of the GNU General Public License.
+
+  "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+  "The Program" refers to any copyrightable work licensed under this
+License.  Each licensee is addressed as "you".  "Licensees" and
+"recipients" may be individuals or organizations.
+
+  To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy.  The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+  A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+  To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy.  Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+  To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies.  Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+  An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License.  If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+  1. Source Code.
+
+  The "source code" for a work means the preferred form of the work
+for making modifications to it.  "Object code" means any non-source
+form of a work.
+
+  A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+  The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form.  A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+  The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities.  However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work.  For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+  The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+  The Corresponding Source for a work in source code form is that
+same work.
+
+  2. Basic Permissions.
+
+  All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met.  This License explicitly affirms your unlimited
+permission to run the unmodified Program.  The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work.  This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+  You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force.  You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright.  Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+  Conveying under any other circumstances is permitted solely under
+the conditions stated below.  Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+  No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+  When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+  4. Conveying Verbatim Copies.
+
+  You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+  You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+  5. Conveying Modified Source Versions.
+
+  You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified
+    it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is
+    released under this License and any conditions added under section
+    7.  This requirement modifies the requirement in section 4 to
+    "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this
+    License to anyone who comes into possession of a copy.  This
+    License will therefore apply, along with any applicable section 7
+    additional terms, to the whole of the work, and all its parts,
+    regardless of how they are packaged.  This License gives no
+    permission to license the work in any other way, but it does not
+    invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display
+    Appropriate Legal Notices; however, if the Program has interactive
+    interfaces that do not display Appropriate Legal Notices, your
+    work need not make them do so.
+
+  A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit.  Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+  6. Conveying Non-Source Forms.
+
+  You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by the
+    Corresponding Source fixed on a durable physical medium
+    customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by a
+    written offer, valid for at least three years and valid for as
+    long as you offer spare parts or customer support for that product
+    model, to give anyone who possesses the object code either (1) a
+    copy of the Corresponding Source for all the software in the
+    product that is covered by this License, on a durable physical
+    medium customarily used for software interchange, for a price no
+    more than your reasonable cost of physically performing this
+    conveying of source, or (2) access to copy the
+    Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the
+    written offer to provide the Corresponding Source.  This
+    alternative is allowed only occasionally and noncommercially, and
+    only if you received the object code with such an offer, in accord
+    with subsection 6b.
+
+    d) Convey the object code by offering access from a designated
+    place (gratis or for a charge), and offer equivalent access to the
+    Corresponding Source in the same way through the same place at no
+    further charge.  You need not require recipients to copy the
+    Corresponding Source along with the object code.  If the place to
+    copy the object code is a network server, the Corresponding Source
+    may be on a different server (operated by you or a third party)
+    that supports equivalent copying facilities, provided you maintain
+    clear directions next to the object code saying where to find the
+    Corresponding Source.  Regardless of what server hosts the
+    Corresponding Source, you remain obligated to ensure that it is
+    available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided
+    you inform other peers where the object code and Corresponding
+    Source of the work are being offered to the general public at no
+    charge under subsection 6d.
+
+  A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+  A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling.  In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage.  For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product.  A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+  "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source.  The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+  If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information.  But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+  The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed.  Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+  Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+  7. Additional Terms.
+
+  "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law.  If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+  When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it.  (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.)  You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+  Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the
+    terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or
+    author attributions in that material or in the Appropriate Legal
+    Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or
+    requiring that modified versions of such material be marked in
+    reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or
+    authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some
+    trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that
+    material by anyone who conveys the material (or modified versions of
+    it) with contractual assumptions of liability to the recipient, for
+    any liability that these contractual assumptions directly impose on
+    those licensors and authors.
+
+  All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10.  If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term.  If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+  If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+  Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+  8. Termination.
+
+  You may not propagate or modify a covered work except as expressly
+provided under this License.  Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+  However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+  Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+  Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License.  If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+  9. Acceptance Not Required for Having Copies.
+
+  You are not required to accept this License in order to receive or
+run a copy of the Program.  Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance.  However,
+nothing other than this License grants you permission to propagate or
+modify any covered work.  These actions infringe copyright if you do
+not accept this License.  Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+  10. Automatic Licensing of Downstream Recipients.
+
+  Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License.  You are not responsible
+for enforcing compliance by third parties with this License.
+
+  An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations.  If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+  You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License.  For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+  11. Patents.
+
+  A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based.  The
+work thus licensed is called the contributor's "contributor version".
+
+  A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version.  For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+  In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement).  To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+  If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+  If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+  A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License.  You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+  Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+  12. No Surrender of Others' Freedom.
+
+  If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all.  For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+  13. Use with the GNU Affero General Public License.
+
+  Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU Affero General Public License into a single
+combined work, and to convey the resulting work.  The terms of this
+License will continue to apply to the part which is the covered work,
+but the special requirements of the GNU Affero General Public License,
+section 13, concerning interaction through a network will apply to the
+combination as such.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+the GNU General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+  Each version is given a distinguishing version number.  If the
+Program specifies that a certain numbered version of the GNU General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation.  If the Program does not specify a version number of the
+GNU General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+  If the Program specifies that a proxy can decide which future
+versions of the GNU General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+  Later license versions may give you additional or different
+permissions.  However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+  15. Disclaimer of Warranty.
+
+  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. Limitation of Liability.
+
+  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+  17. Interpretation of Sections 15 and 16.
+
+  If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    The 2024/2025 SOC Paper and the related scripts for aggregating, analyzing, and graphing the dataset.
+    Copyright (C) 2025  Daniel Svitaň
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If the program does terminal interaction, make it output a short
+notice like this when it starts in an interactive mode:
+
+    soc-2024  Copyright (C) 2025  Daniel Svitaň
+    This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, your program's commands
+might be different; for a GUI interface, you would use an "about box".
+
+  You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU GPL, see
+<https://www.gnu.org/licenses/>.
+
+  The GNU General Public License does not permit incorporating your program
+into proprietary programs.  If your program is a subroutine library, you
+may consider it more useful to permit linking proprietary applications with
+the library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.  But first, please read
+<https://www.gnu.org/licenses/why-not-lgpl.html>.
+

Makefile

@@ -0,0 +1,2 @@
+make analyze:
+	./analyze.sh

README.md

@@ -1,22 +1,139 @@
 # Hello!
 
-Welcome, you either don't know what the hell this is or know exactly what the hell this is. Either way, here's a quick
-explanation:
+Welcome to the technical repository for my 2024/2025 SOC paper,
+this is where I keep all my scripts, scientific tests, algorithms, and graphing programs,
+let me walk you through how it works, I've split it into multiple sections:
 
-I decided to write a special paper at my highschool - why? It's kind of a competition, a bunch of students submit their
-SOC paper and the best one wins. They're actually graded by a whole ahh comittee and it's a big deal and whatever.
-Anyway, I'm here cuz it's fun, not cuz I wanna win (obviously I wanna win but that's not why I decided to do the SOC)
+1. [Tools and libraries](#tools-and-libraries)
+2. [Dataset](#dataset)
+3. [Distribution](#distribution)
+4. [Analysis and scientific tests](#analysis-and-scientific-tests)
+5. [Graphing](#graphing)
+6. [Neural network](#neural-network)
 
-I will eventually (probably Feb 2025) publish the paper, which I will also send to everyone who participated in the
-survey (fr thanks to everyone who did). Here I wanna keep all the scripts I used while writing the paper, it's mostly
-stuff for cleaning, analyzing, and graphing the dataset
+Don't forget to check out the [conclusion](#conclusion) and the [credits](CREDITS.md)
 
-I will also probably send out a link to this repo along with the paper, so if you got here from that link, welcome!
-Thanks so much for participating in the survey, you can check out the scripts and the other markdowns (to be added)
-where I explain what I did in a slightly more friendly way
+The actual paper can be found [here](Daniel%20Svitan%20SOC%202025.pdf)
 
-And if you're interested in the dataset, no I'm not publishing it, sorry (mom said no)
+### Tools and libraries
+
+Basically all scripts are written in [python](https://www.python.org/), except for one shell script, and these are the
+libraries that were used: 
+
+- [numpy](https://numpy.org/) - to load and manipulate the data
+- [pandas](https://pandas.pydata.org/) - to construct tables
+- [scipy](https://scipy.org/) - to perform statistical tests
+- [matplotlib](https://matplotlib.org/) - to create and render graphs
+- [pytorch](https://pytorch.org/) - to model and train the neural network
+
+Google Forms provides the data as a `.csv` file, which is converted into a `.npy` (numpy) file
 
 ### Dataset
 
-The documentation for the dataset structure can be found [here](https://github.com/Streamer272/soc-2024/blob/main/DATASET.md)
+The documentation for the dataset structure can be found in [DATASET.md](DATASET.md),
+this is only interesting for the nerds
+
+### Distribution
+
+This is probably the easiest part of this whole thing, it's basically just making charts and computing percentages,
+say you have 12 male and 15 female respondents, what is the distribution? It's quite simple, here:
+
+`(number of elements in a group) / (number of elements in the dataset)`
+
+So in this case, the distribution of male respondents would be `(12) / (12 + 15) = ~44%`, and female `(15) / (12 + 15) = ~56%`,
+now that we know this, we can make a pretty pie graph! The script that does all of this is [distribution.py](distribution.py)
+
+### Analysis and scientific tests
+
+This is where stuff gets interesting, the script that does all the heavy lifting is [analyze.py](analyze.py),
+then, you have the specified analysis scripts, like [analyze_sex.py](analyze_sex.py)
+(which, surprisingly, only analyzes sex)
+
+[analyze_sex.py](analyze_sex.py) only picks out its data from the dataset and passes it down to [analyze.py](analyze.py) to do all the analyses, where the following things happen:
+
+1. the received data is put into groups, each receiving an assigned letter (A, B, C, etc), groups of insufficient size are removed
+2. if there are less than 2 groups, analysis aborts
+3. [Kruskal-Wallis test](https://en.wikipedia.org/wiki/Kruskal%E2%80%93Wallis_test) is performed and `F` and `p` values are received
+4. if `p` is greater than 0.05, the difference between those groups is not statistically significant and analysis aborts
+5. post-hoc [Dunn test](https://www.statology.org/dunns-test/) is performed and `p` values are saved
+6. a result table is created, a comparison between each group is added as well as their [rank-biserial correlation](https://www.statisticshowto.com/rank-biserial-correlation/), difference in medians, difference in means, and post-hoc `p` value
+
+Problem solved!
+If the difference is statistically insignificant,
+or we don't have sufficient data to perform a statistical test, the analysis aborts,
+otherwise, we get our `F` value, `p` value, and the result table, which could look something like this:
+
+| Skupina 1 | Skupina 2 | Veľkosť účinku | Rozdiel priemerov | Rozdiel mediánov | Post-Hoc p-hodnota |
+|-----------|-----------|----------------|-------------------|------------------|--------------------|
+| A         | B         | 0.0440         | 0.4198            | 0.0000           | 0.0497             |
+| A         | C         | 0.0399         | 0.2723            | 0.0000           | 0.5239             |
+| B         | C         | -0.0084        | -0.1475           | 0.0000           | 0.3706             |
+
+### Graphing
+
+Once the analysis is complete, successful or not, we can graph the data, we mostly use violin plots,
+which are quite easy to understand and interpret, it goes like this:
+
+1. the window is split into four subplots, top left for average grade, top right for math grade, bottom left for slovak grade, and bottom right for english grade
+2. all groups get added to each subplot as a violin plot, so for sex, each subplot would contain a violin plot for males and a violin plot for females
+3. the `F` and `p` values get added to the top left corner of each subplot
+4. the legend gets added to the top right corner of each subplot and axes are marked
+5. each violin plot contains five pieces of valuable information:
+   1. the shaded background that shows the distribution of the data
+   2. the gray line that represents the data between the first and third quartile
+   3. the red mean line with the mean value on the left
+   4. the green median line with the median value on the right
+   5. the minimum and maximum bounds
+6. labels get added to each violin plot
+
+Quite complicated, right? A ton of data packed into one small image, which could look something like this:
+
+![example graph](example-graph.png)
+
+It can be overwhelming to look at at first, but once you understand what's going on, it's quite intuitive, anyway,
+the function that does all this is also saved in [analyze.py](analyze.py)
+
+All the graphs are saved in the archives, which you can download, [results.tar.gz](results.tar.gz) and [results.zip](results.zip)
+
+### Neural network
+
+Ah!
+AI stuff!
+Well, it didn't work in the end because of the abysmal amount of data, but the structure and
+the training process is still here and can be looked at
+
+The script that trains the neural network is [train_nn.py](train_nn.py) (yes, I am very creative when it comes to
+naming stuff, I am aware), it uses the [pytorch](https://pytorch.org/) library to do all the math stuff that goes on
+behind the scenes, but the important part is the structure of the neural network, right here:
+
+![structure of a neural network](structure.png)
+
+Of course, we have to use the `.npy` file format to load the data into our program, so how do we convert the `.csv`
+data provided by the Google Forms into a `.npy`?
+The answer lies in [clean.py](clean.py), but I'm not going to go
+into how it all works, since the script just cleans the data
+
+The whole training thing is pretty complicated, so if you don't know anything about neural networks, just forget about
+it and attribute it to magic, but if you do, read through [train_nn.py](train_nn.py),
+it's a pretty clean and readable code
+
+## Conclusion
+
+Hopefully you learned something when you read through this README or the various scripts, because that's the main
+reason why I decided to make this repository public, so folks can look at this and learn new stuff
+
+I had a lot of fun on this project, gathering data, writing scripts, conducting scientific tests, and writing the paper,
+it was an unforgettable experience, and even though it was really hard, it was definitely worth it and I would
+definitely do it again, and I recommend you try this sort of thing as well
+
+If you have read this whole README till the end, I thank you, because it took a Saturday afternoon to write that I
+could've spent playing video games, but it was worth it as long as at least one person took a quick glance at it
+
+If you have any questions about the paper, this repository, the technical details and the specific techniques, or even
+if you're thinking about writing a paper yourself, feel free to reach out to me at
+[daniel@svitan.dev](mailto:daniel@svitan.dev) or send me a message on discord (Streamer272), I will gladly answer
+any questions and talk about this project for hours
+
+### License
+
+This project is licensed under the [GNU GPLv3](LICENSE) license

analyze.py

@@ -1,8 +1,11 @@
 from typing import List
+import itertools
 import argparse
 
 import numpy as np
+import pandas as pd
 import scipy.stats as stats
+import scikit_posthocs as sp
 import matplotlib.pyplot as plt
 
 parser = argparse.ArgumentParser()
@@ -12,34 +15,84 @@ args = parser.parse_args()
 graph = args.graph
 save = args.save
 
+colors = ["lightblue", "lightgreen", "lightcoral"]
+edge_colors = ["blue", "green", "red"]
 
+
+# source: mostly ChatGPT (ain't no way i'm writing this shit myself)
 def analyze(name: str, data: List[np.ndarray]):
-    #print(f"Checking if normally distributed for {name}")
-    #for i in range(len(data)):
-    #    _, normal_p = stats.shapiro(data[i])
-    #    if normal_p > 0.05:
-    #        print(f"\tGroup {i}: normally distributed")
-    #    else:
-    #        print(f"\tGroup {i}: NOT normally distributed")
-
     filtered_data = []
+    group_names = []
+    all_values = []
     for index, item in enumerate(data):
-        if len(item) > 5:
-            filtered_data.append(item)
+        numeric_data = [x for x in item if isinstance(x, (int, float))]
+        if len(numeric_data) > 5:
+            filtered_data.append(numeric_data)
+            group_names.append(chr(65 + index))
+            all_values.extend(numeric_data)
         else:
-            print(f"Data group at index {index} removed due to insufficient size ({len(item)})")
+            print(f"Data group at index {index} removed due to insufficient size ({len(numeric_data)})")
 
+    if len(filtered_data) < 2:
+        print(f"Insufficient number of groups for Kruskal-Wallis test in {name}")
+        return None, None
+
+    # Kruskal-Wallis Test
     F, p = stats.kruskal(*filtered_data)
-    print(f"F-stats for {name}: {F}")
-    print(f"p-value for {name}: {p}")
+    print(f"\nF-stats for {name}: {F:.8f}")
+    print(f"p-value for {name}: {p:.8f}")
 
-    if round(p, 4) > 0.05:
+    if p > 0.05:
         print("statistically insignificant\n")
         return F, p
 
     print("statistically significant")
-    tukey_results = stats.tukey_hsd(*filtered_data)
-    print(tukey_results)
+
+    # Post-Hoc Dunn Test (Bonferroni-adjusted p-values)
+    all_ranks = stats.rankdata(all_values)  # Rank all values together
+    group_ranks = [all_ranks[start:start + len(group)] for start, group in
+                   zip(np.cumsum([0] + [len(g) for g in filtered_data[:-1]]), filtered_data)]
+    posthoc_results = sp.posthoc_conover(filtered_data, p_adjust='bonferroni')
+
+    results = []
+    total_sample_size = len(all_values)
+    for group1, group2 in itertools.combinations(group_names, 2):
+        idx1 = group_names.index(group1)
+        idx2 = group_names.index(group2)
+
+        mean_rank_1 = np.mean(group_ranks[idx1])
+        mean_rank_2 = np.mean(group_ranks[idx2])
+        rank_diff = mean_rank_1 - mean_rank_2
+
+        n1 = len(filtered_data[idx1])
+        n2 = len(filtered_data[idx2])
+
+        # Effect size (Rank-Biserial Correlation)
+        z_stat = rank_diff / np.sqrt((n1 + n2) * (n1 * n2) / total_sample_size)
+        effect_size = z_stat / np.sqrt(total_sample_size)
+
+        # Mean difference
+        mean_diff = np.mean(filtered_data[idx1]) - np.mean(filtered_data[idx2])
+
+        # Median difference
+        median_diff = np.median(filtered_data[idx1]) - np.median(filtered_data[idx2])
+
+        # Post-Hoc Dunn p-value
+        p_value = posthoc_results.loc[idx1 + 1, idx2 + 1]
+
+        results.append({
+            "Skupina 1": group1,
+            "Skupina 2": group2,
+            "Veľkosť účinku": f"{effect_size:.4f}",
+            "Rozdiel priemerov": f"{mean_diff:.4f}",
+            "Rozdiel mediánov": f"{median_diff:.4f}",
+            "Post-Hoc p-hodnota": f"{p_value:.4f}"
+        })
+
+    results_df = pd.DataFrame(results, dtype="object")
+    print("\nSummary Table of Effect Size, Mean, and Median Differences:")
+    print(results_df.to_markdown(index=False, tablefmt="github", disable_numparse=True))
+    print("")
 
     return F, p
 
@@ -52,7 +105,7 @@ def plot_violin(data, labels, Fs, ps, title):
     grade_name_labels = ["Priemer známok", "Známka z matematiky", "Známka zo slovenčiny", "Známka z angličtiny"]
 
     fig, axs = plt.subplots(2, 2)
-    fig.suptitle(title)
+    fig.suptitle(title, fontsize=18)
     fig.set_size_inches(12, 9)
 
     for j in range(2):
@@ -60,25 +113,57 @@ def plot_violin(data, labels, Fs, ps, title):
             index = j * 2 + k
             step = 1 if index > 0 else 0.5
 
-            axs[j, k].violinplot(data[index], showmedians=True)
-            axs[j, k].set_title(grade_names[index])
-            axs[j, k].set_xlabel(title, fontweight="bold")
-            axs[j, k].set_ylabel(grade_name_labels[index], fontweight="bold")
+            parts = axs[j, k].violinplot(data[index], showmedians=True, showmeans=True)
+            axs[j, k].set_title(grade_names[index], fontsize=16)
+            axs[j, k].set_xlabel(title, fontweight="bold", fontsize=14)
+            axs[j, k].set_ylabel(grade_name_labels[index], fontweight="bold", fontsize=14)
+
+            # q1-q3 lines
+            for ind, vec in enumerate(data[index]):
+                quartile1, median, quartile3 = np.percentile(vec, [25, 50, 75])
+                if quartile1 == quartile3:
+                    if quartile1 >= 0.1:
+                        quartile1 -= 0.1
+                    if quartile3 <= max(vec) - 0.1:
+                        quartile3 += 0.1
+                axs[j, k].vlines(ind + 1, quartile1, quartile3, color="gray", linewidths=3)
+
             axs[j, k].set_xticks(np.arange(1, len(labels) + 1), labels=labels)
             axs[j, k].set_yticks(np.arange(1, 5.01, step))
 
-            F = round(Fs[index], 2)
-            p = round(ps[index], 4)
-            axs[j, k].text(0.01, 0.99, f"F-stat: {F:.2f}\np-val: {p:.4f}", ha="left", va="top", transform=axs[j, k].transAxes,
-                           fontweight="bold")
+            parts["cmeans"].set_color("red")
+            parts["cmedians"].set_color("green")
+
+            for i, part in enumerate(parts["bodies"]):
+                part.set_facecolor(colors[i % len(colors)])
+                part.set_edgecolor(edge_colors[i % len(edge_colors)])
+
+            F = Fs[index]
+            p = ps[index]
+            axs[j, k].text(0.01, 0.99, f"F-stat: {F:.4f}\np-val: {p:.4f}", ha="left", va="top",
+                           transform=axs[j, k].transAxes,
+                           fontweight="bold",
+                           fontsize=12)
+            axs[j, k].text(0.99, 0.99,
+                           f"Na ľavo - priemer (červená)\nNa pravo - medián (zelená)\nSivá - medzi kvartilom 1 a 3",
+                           ha="right",
+                           va="top",
+                           transform=axs[j, k].transAxes,
+                           fontsize=12)
 
             medians = list([np.median(a) for a in data[index]])
-            for l in range(len(medians)):
-                median = round(medians[l], 2)
-                axs[j, k].text(l + 1.05, median + 0.05, f"{median}")
+            means = list([a.mean() for a in data[index]])
+            for l in range(len(data[index])):
+                median = medians[l]
+                mean = means[l]
+                # left - mean, right - median
+                axs[j, k].text(l + 1.13, median - 0.05, f"{median:.2f}", color="green", fontsize=12, fontweight="bold")
+                axs[j, k].text(l + 0.87 - len(labels) * 0.065, mean - 0.05, f"{mean:.2f}", color="red", fontsize=12, fontweight="bold")
+
+            if p < 0.05:
+                axs[j, k].set_facecolor("#ffff99")
 
     fig.tight_layout()
-    fig.show()
     if save != "":
         plt.savefig(save)
     else:

analyze.sh

@@ -0,0 +1,25 @@
+#!/usr/bin/bash
+
+rm results/*
+
+./venv/bin/python3 distribution.py --graph --save | tee results/distribution.txt
+echo -e "\n\n\n\n"
+./venv/bin/python3 analyze_sex.py --graph --save "results/Figure_13.png" | tee results/sex.txt
+echo -e "\n\n\n\n"
+./venv/bin/python3 analyze_ses.py --graph --save "results/Figure_14.png" | tee results/ses.txt
+echo -e "\n\n\n\n"
+./venv/bin/python3 analyze_occupation.py --graph --save "results/Figure_15.png" | tee results/occupation.txt
+echo -e "\n\n\n\n"
+./venv/bin/python3 analyze_living.py --graph --save "results/Figure_16.png" | tee results/living.txt
+echo -e "\n\n\n\n"
+./venv/bin/python3 analyze_commute.py --graph --save "results/Figure_17.png" | tee results/commute.txt
+echo -e "\n\n\n\n"
+./venv/bin/python3 analyze_sleep.py --graph --save "results/Figure_18.png" | tee results/sleep.txt
+echo -e "\n\n\n\n"
+./venv/bin/python3 analyze_absence.py --graph --save "results/Figure_19.png" | tee results/absence.txt
+echo -e "\n\n\n\n"
+./venv/bin/python3 train_nn.py --graph --save "results/Figure_20.png" | tee results/train.txt
+echo -e "\n\n\n\n"
+
+tar cvzf results.tar.gz results/
+zip results.zip results/*

analyze_absence.py

@@ -6,8 +6,13 @@ import matplotlib.pyplot as plt
 
 parser = argparse.ArgumentParser()
 parser.add_argument("-g", "--graph", action="store_true", default=False, help="Plot graph")
+parser.add_argument("-s", "--save", default="", help="Graph save location")
 args = parser.parse_args()
 graph = args.graph
+save = args.save
+
+colors = ["lightblue", "lightgreen", "lightcoral"]
+edge_colors = ["blue", "green", "red"]
 
 dataset = np.load("clean.npy")
 print(f"dataset shape: {dataset.shape}; analyzing column 11 (absence)")
@@ -44,7 +49,7 @@ grade_names = ["Priemer", "Matematika", "Slovenčina", "Angličtina"]
 grade_name_labels = ["Priemer známok", "Známka z matematiky", "Známka zo slovenčiny", "Známka z angličtiny"]
 
 fig, axs = plt.subplots(2, 2)
-fig.suptitle("Absencia")
+fig.suptitle("Absencia", fontsize=18)
 fig.set_size_inches(12, 9)
 
 for j in range(2):
@@ -52,31 +57,43 @@ for j in range(2):
         index = j * 2 + k
         step = 1 if index > 0 else 0.5
 
-        if index == 0:
-            axs[j, k].scatter(dataset[:, 11], dataset[:, 2])
-            axs[j, k].set_xlabel("Počet vymeškaných hodín")
-            axs[j, k].set_ylabel(grade_name_labels[index])
+        if not index:
+            x = data[index][0]  # absence
+            y = data[index][1]  # grade
+            axs[j, k].scatter(x, y)
+            axs[j, k].set_xlabel("Počet vymeškaných hodín", fontweight="bold", fontsize=14)
+            axs[j, k].set_ylabel(grade_name_labels[index], fontweight="bold", fontsize=14)
+            axs[j, k].set_yticks(np.arange(1, 6))
+
+            # trendline
+            z = np.polyfit(x, y, 1)
+            p = np.poly1d(z)
+
+            axs[j, k].plot(x, p(x), color="gray")
         else:
-            current = list([data[index][0][data[index][1] == i + 1] for i in range(5)])  # i wanna kms
-            axs[j, k].violinplot(list(filter(lambda x: len(x), current)), showmeans=True)
-            axs[j, k].set_xticks(np.arange(1, 6, 1), labels=["1", "2", "3", "4", "5"])
-            axs[j, k].set_xlabel(grade_name_labels[index])
-            axs[j, k].set_ylabel("Počet vymeškaných hodín")
+            by_grade = list([data[index][0][data[index][1] == i + 1] for i in range(5)])
+            # data[index][0] - absences
+            # data[index][1] - grades
+            # data[index][0][specific grade] - absences for that specific grande
+            # loop 1 through 5 plug in ^^
+            axs[j, k].set_xlabel(grade_name_labels[index], fontweight="bold", fontsize=14)
+            axs[j, k].set_ylabel("Počet vymeškaných hodín", fontweight="bold", fontsize=14)
+            axs[j, k].boxplot(by_grade, tick_labels=["1", "2", "3", "4", "5"])
 
-        axs[j, k].set_title(grade_names[index])
+        axs[j, k].set_title(grade_names[index], fontsize=16)
 
-        tau = round(taus[index], 2)
-        p = round(ps[index], 4)
-        axs[j, k].text(0.01, 0.99, f"Tau τ: {tau:.2f}\np-val: {p:.4f}", ha="left", va="top", transform=axs[j, k].transAxes,
-                       fontweight="bold")
+        tau = taus[index]
+        p = ps[index]
+        axs[j, k].text(0.01, 0.99, f"Tau τ: {tau:.4f}\np-val: {p:.4f}", ha="left", va="top",
+                       transform=axs[j, k].transAxes,
+                       fontweight="bold",
+                       fontsize=12)
 
-        if index:
-            by_grade = [data[index][0][data[index][1] == i + 1] for i in range(5)]
-            means = list([a.mean() for a in filter(lambda b: len(b), by_grade)])
-            for l in range(len(means)):
-                mean = round(means[l], 2)
-                axs[j, k].text(l + 1.02, mean + 5, f"{mean}")
+        if p < 0.05:
+            axs[j, k].set_facecolor("#ffff99")
 
 fig.tight_layout()
-fig.show()
+if save != "":
+    plt.savefig(save)
+else:
     plt.show()

distribution.py

@@ -7,8 +7,11 @@ parser = argparse.ArgumentParser(
     prog="distribution"
 )
 parser.add_argument("-g", "--graph", action="store_true", default=False, help="Display graphs")
+parser.add_argument("-s", "--save", action="store_true", default=False, help="Save graphs")
 args = parser.parse_args()
 graph = args.graph
+save = args.save
+graph_index = 1
 
 dataset = np.load("clean.npy")
 print(f"dataset shape: {dataset.shape}; analyzing distribution\n")
@@ -19,6 +22,10 @@ def percent(fraction: float) -> str:
 
 
 def plot_pie(data, labels, title, explode=None):
+    global graph_index
+    if not graph:
+        return
+
     i = 0
     while i < len(data):
         if data[i] == 0:
@@ -28,21 +35,33 @@ def plot_pie(data, labels, title, explode=None):
             i += 1
 
     plt.figure(figsize=(8, 6))
-    plt.pie(np.array(data), labels=labels, autopct=lambda pct: percent(pct / 100), explode=explode)
-    plt.title(title)
+    plt.pie(np.array(data), labels=labels, autopct=lambda pct: percent(pct / 100), explode=explode, textprops={"fontsize": 16})
+    plt.title(title, fontsize=20)
 
     plt.tight_layout()
+    if save:
+        plt.savefig(f"results/Figure_{graph_index}.png")
+        graph_index += 1
+    else:
         plt.show()
 
 
 def plot_hist(data, title, xlabel, ylabel):
+    global graph_index
+    if not graph:
+        return
+
     plt.figure(figsize=(8, 6))
     plt.hist(data, 25, edgecolor="black")
-    plt.title(title)
-    plt.xlabel(xlabel)
-    plt.ylabel(ylabel)
+    plt.title(title, fontsize=20)
+    plt.xlabel(xlabel, fontsize=16)
+    plt.ylabel(ylabel, fontsize=16)
 
     plt.tight_layout()
+    if save:
+        plt.savefig(f"results/Figure_{graph_index}.png")
+        graph_index += 1
+    else:
         plt.show()
 
 
@@ -62,7 +81,6 @@ print(f"4st year: {percent(grade_dist[3])}")
 print(f"5st year: {percent(grade_dist[4])}")
 print("")
 
-if graph:
 plot_pie(
     grade_dist,
     ["Prvý ročník", "Druhý ročník", "Tretí ročník", "Štvrtý ročník", "Piaty ročník"],
@@ -79,15 +97,13 @@ print(f"Female: {percent(sex_dist[0])}")
 print(f"Male: {percent(sex_dist[1])}")
 print("")
 
-if graph:
 plot_pie(sex_dist, ["Ženy", "Muži"], "Distribúcia pohlavia")
 
 print("--- GPA ---")
 print("n/a")
 print("")
 
-if graph:
-    plot_hist(dataset[:, 2], "Distribúcia piemernu známok", "Piemerná známka", "Počet študentov/tiek")
+plot_hist(dataset[:, 2], "Distribúcia piemernu známok", "Piemerná známka", "Počet študent*iek")
 
 math = dataset[:, 3]
 math_dist = [
@@ -105,7 +121,6 @@ print(f"4: {percent(math_dist[3])}")
 print(f"5: {percent(math_dist[4])}")
 print("")
 
-if graph:
 plot_pie(math_dist, ["1", "2", "3", "4", "5"], "Distribúcia známok z matematiky")
 
 slovak = dataset[:, 4]
@@ -124,7 +139,6 @@ print(f"4: {percent(slovak_dist[3])}")
 print(f"5: {percent(slovak_dist[4])}")
 print("")
 
-if graph:
 plot_pie(slovak_dist, ["1", "2", "3", "4", "5"], "Distribúcia známok zo slovenčiny", (0, 0, 0, 0.25, 0.5))
 
 english = dataset[:, 5]
@@ -143,7 +157,6 @@ print(f"4: {percent(english_dist[3])}")
 print(f"5: {percent(english_dist[4])}")
 print("")
 
-if graph:
 plot_pie(english_dist, ["1", "2", "3", "4", "5"], "Distribúcia známok z angličtiny")
 
 ses = dataset[:, 6]
@@ -158,7 +171,6 @@ print(f"Middle: {percent(ses_dist[1])}")
 print(f"Upper: {percent(ses_dist[2])}")
 print("")
 
-if graph:
 plot_pie(ses_dist, ["Nižšia trieda", "Stredná trieda", "Vyššia trieda"], "Distribúcia socio-ekonomických tried")
 
 occupation = dataset[:, 7]
@@ -179,9 +191,8 @@ print(f"other                  : {percent(occupation_dist[4])}")
 print(f"none                   : {percent(occupation_dist[5])}")
 print("")
 
-if graph:
 plot_pie(occupation_dist,
-             ["Práca 10 a viac hodín týždenne", "Práca menej ako 10 hodín týždenne", "Šport", "Hudba", "Niečo iné",
+         ["Práca 10 a viac\nhodín týždenne", "Práca menej ako\n10 hodín týždenne", "Šport", "Hudba", "Niečo iné",
           "Žiadne"], "Distribúcia práce a aktivít")
 
 living = dataset[:, 8]
@@ -200,9 +211,8 @@ print(f"dorms             : {percent(living_dist[3])}")
 print(f"other             : {percent(living_dist[4])}")
 print("")
 
-if graph:
 plot_pie(living_dist,
-             ["S rodinou", "S rodinným príslušníkom/ou", "Sám/a alebo so spolubývajúcim/ou", "Intrák", "Iné"],
+         ["S rodinou", "\nS rodinnou príslušní*čkou", "Sám*a alebo so\nspolubývajúc*ou", "Intrák", "Iné"],
          "Distribúcia životných situácií")
 
 commute = dataset[:, 9]
@@ -221,7 +231,6 @@ print(f"<= 1h : {percent(commute_dist[3])}")
 print(f"> 1h  : {percent(commute_dist[4])}")
 print("")
 
-if graph:
 plot_pie(commute_dist,
          ["Intrák", "Menej ako 15 minút", "Menej ako 30 minút", "Menej ako hodinu", "Viac ako hodinu"],
          "Distribúcia dochádzania")
@@ -238,12 +247,10 @@ print(f"medium sleepers: {percent(sleep_dist[1])}")
 print(f"long sleepers  : {percent(sleep_dist[2])}")
 print("")
 
-if graph:
 plot_pie(sleep_dist, ["6 hodín a menej", "7 až 8 hodín", "9 a viac hodín"], "Distribúcia spánku")
 
 print("--- ABSENCE ---")
 print("n/a")
 print("")
 
-if graph:
-    plot_hist(dataset[:, 11], "Distribúcia absencií", "Počet neprítomných hodín", "Počet študentov/tiek")
+plot_hist(dataset[:, 11], "Distribúcia absencií", "Počet neprítomných hodín", "Počet študent*iek")

requirements.txt

@@ -1,40 +1,9 @@
-contourpy==1.3.1
-cycler==0.12.1
-filelock==3.16.1
-fonttools==4.55.3
-fsspec==2024.12.0
-Jinja2==3.1.5
-joblib==1.4.2
-kiwisolver==1.4.7
-MarkupSafe==3.0.2
-matplotlib==3.10.0
-mpmath==1.3.0
-networkx==3.4.2
-numpy==2.2.1
-nvidia-cublas-cu12==12.4.5.8
-nvidia-cuda-cupti-cu12==12.4.127
-nvidia-cuda-nvrtc-cu12==12.4.127
-nvidia-cuda-runtime-cu12==12.4.127
-nvidia-cudnn-cu12==9.1.0.70
-nvidia-cufft-cu12==11.2.1.3
-nvidia-curand-cu12==10.3.5.147
-nvidia-cusolver-cu12==11.6.1.9
-nvidia-cusparse-cu12==12.3.1.170
-nvidia-nccl-cu12==2.21.5
-nvidia-nvjitlink-cu12==12.4.127
-nvidia-nvtx-cu12==12.4.127
-packaging==24.2
-pandas==2.2.3
-pillow==11.0.0
-pyparsing==3.2.0
-python-dateutil==2.9.0.post0
-pytz==2024.2
-scikit-learn==1.6.0
-scipy==1.14.1
-setuptools==75.6.0
-six==1.17.0
-sympy==1.13.1
-threadpoolctl==3.5.0
-torch==2.5.1
-typing_extensions==4.12.2
-tzdata==2024.2
+numpy
+matplotlib
+PyQt6
+pandas
+scipy
+scikit_posthocs
+tabulate
+torch
+scikit-learn

train_nn.py

@@ -11,8 +11,10 @@ parser = argparse.ArgumentParser(
     prog="train_nn"
 )
 parser.add_argument("-g", "--graph", action="store_true", default=False, help="Graph losses")
+parser.add_argument("-s", "--save", default="", help="Graph save location")
 args = parser.parse_args()
 graph = args.graph
+save = args.save
 
 
 class NeuralNetwork(nn.Module):
@@ -119,7 +121,7 @@ for epoch in range(epochs):
             pred = model(X)
             loss = loss_fn(pred, y)
 
-            test_loss = loss.item() * X.size(0)
+            test_loss += loss.item() * X.size(0)
 
     test_loss /= len(test_dataset)
     test_losses.append(test_loss)
@@ -169,14 +171,17 @@ if graph:
     plt.plot(x, train_losses, color="red", label="Strata trénovania")
     plt.plot(x, test_losses, color="blue", label="Strata testovania")
 
-    plt.xlabel("Epocha")
-    plt.ylabel("Strata")
-    plt.title("Priebeh trénovania")
+    plt.xlabel("Epocha", fontweight="bold", fontsize=14)
+    plt.ylabel("Strata", fontweight="bold", fontsize=14)
+    plt.title("Priebeh trénovania", fontsize=20)
 
     plt.text(0.99, 0.99,
              f"Presnosť: {accuracy:.4f}\nPrecíznosť: {precision:.4f}\nOdvolanie: {recall:.4f}\nF1 skóre: {f1:.4f}",
-             ha="right", va="top", transform=plt.gca().transAxes, fontweight="bold")
+             ha="right", va="top", transform=plt.gca().transAxes, fontweight="bold", fontsize=14)
 
     plt.legend()
     plt.tight_layout()
+    if save != "":
+        plt.savefig(save)
+    else:
         plt.show()