files added

.gitignore

@@ -0,0 +1,12 @@
+/getFiles/kaggleApi.py
+.env
+test.py
+langchain_folder/__pycache__
+/downloads
+lang_model.py
+/final
+__pycache__
+getOpenml.py
+/input_folder
+/processed
+/static

LICENSE

@@ -0,0 +1,674 @@
+                    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.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    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:
+
+    <program>  Copyright (C) <year>  <name of author>
+    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>.

README.md

@@ -1,10 +1 @@
----
-title: Dataset
-emoji: 👀
-colorFrom: yellow
-colorTo: indigo
-sdk: docker
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# DatasetCreator

backend.py

@@ -0,0 +1,101 @@
+from flask import Flask, request, jsonify, send_file
+from flask_cors import CORS
+import os
+from langchain_folder.main import ReturnKeywordsfromPrompt
+from dotenv import load_dotenv
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+load_dotenv()
+
+app = Flask(__name__)
+CORS(app)
+
+CSV_FILE_PATH = os.getenv('file_path')
+GRAPH_DIR = './static/graphs'
+
+
+@app.route('/api/search', methods=['POST'])
+def search():
+    data = request.get_json()
+    query = data.get('query', '')
+    keywords = ReturnKeywordsfromPrompt(query)
+    return jsonify({"status": "success", "queryReceived": query})
+
+
+def generate_graphs_from_csv(csv_path, output_dir):
+    df = pd.read_csv(csv_path)
+    os.makedirs(output_dir, exist_ok=True)
+
+    numeric_cols = df.select_dtypes(include='number').columns.tolist()
+    categorical_cols = df.select_dtypes(include='object').columns.tolist()
+    graph_paths = []
+    print (categorical_cols)
+
+    if len(numeric_cols) >= 1:
+        plt.figure(figsize=(4, 3))
+        sns.histplot(df[numeric_cols[0]], kde=True)
+        plt.title(f'{numeric_cols[0]} Distribution')
+        plt.tight_layout()
+        path = f'{output_dir}/graph_1_hist.png'
+        plt.savefig(path)
+        graph_paths.append(path)
+
+    if len(numeric_cols) >= 2 and categorical_cols:
+        plt.figure(figsize=(4, 3))
+        sns.boxplot(data=df, x=categorical_cols[0], y=numeric_cols[1])
+        plt.title(f'{numeric_cols[1]} by {categorical_cols[0]}')
+        plt.tight_layout()
+        path = f'{output_dir}/graph_2_box.png'
+        plt.savefig(path)
+        graph_paths.append(path)
+
+    if categorical_cols:
+        plt.figure(figsize=(4, 3))
+        sns.countplot(data=df, x=categorical_cols[0])
+        plt.title(f'{categorical_cols[0]} Distribution')
+        plt.tight_layout()
+        path = f'{output_dir}/graph_3_count.png'
+        plt.savefig(path)
+        graph_paths.append(path)
+
+    if len(numeric_cols) >= 2:
+        plt.figure(figsize=(4, 3))
+        sns.scatterplot(data=df, x=numeric_cols[0], y=numeric_cols[1])
+        plt.title(f'{numeric_cols[0]} vs {numeric_cols[1]}')
+        plt.tight_layout()
+        path = f'{output_dir}/graph_4_scatter.png'
+        plt.savefig(path)
+        graph_paths.append(path)
+
+    return graph_paths
+
+
+@app.route('/api/get_csv', methods=['GET'])
+def get_csv():
+    try:
+        if not os.path.exists(CSV_FILE_PATH):
+            return jsonify({"error": "CSV file not found"}), 404
+        with open(CSV_FILE_PATH, "r", encoding="utf-8") as f:
+            return f.read(), 200, {
+                "Content-Type": "text/csv",
+                "Content-Disposition": "inline; filename=dataset.csv"
+            }
+    except Exception as e:
+        return jsonify({"error": str(e)}), 500
+
+
+@app.route('/api/download_csv', methods=['GET'])
+def download_csv():
+    return send_file(CSV_FILE_PATH, as_attachment=True)
+
+
+@app.route('/api/get_graphs', methods=['GET'])
+def get_graphs():
+    paths = generate_graphs_from_csv(CSV_FILE_PATH, GRAPH_DIR)
+    return jsonify({"graphs": [p.replace("./static", "/static") for p in paths]})
+
+
+if __name__ == '__main__':
+    app.run(debug=True)

cleanDataset.py

@@ -0,0 +1,165 @@
+import pandas as pd
+import glob
+import re
+from itertools import combinations
+import os
+from rapidfuzz import process, fuzz
+import getLabels
+
+
+def get_fuzzy_common_columns(cols_list, threshold=75):
+    """
+    Given a list of sets of column names (normalized),
+    return the set of column names that are 'fuzzy common'
+    across all lists.
+    """
+    # Start with columns from the first dataset
+    base = cols_list[0]
+    common = set()
+
+    for col in base:
+        match_all = True
+        for other in cols_list[1:]:
+            match, score, _ = process.extractOne(col, other, scorer=fuzz.token_sort_ratio)
+            if score < threshold:
+                match_all = False
+                break
+        if match_all:
+            common.add(col)
+    return common
+
+
+def sortFiles(dfs):
+    unique_dfs = []
+    seen = []
+
+    for i, df1 in enumerate(dfs):
+        duplicate = False
+        for j in seen:
+            df2 = dfs[j]
+
+            # Check if same shape
+            if df1.shape != df2.shape:
+                continue
+
+            if df1.reset_index(drop=True).equals(df2.reset_index(drop=True)):
+                duplicate = True
+                break
+
+        if not duplicate:
+            unique_dfs.append(df1)
+            seen.append(i)
+
+    return unique_dfs
+
+
+def normalize(col):
+    return re.sub(r'[^a-z0-9]', '', col.lower())
+
+def clean(query):
+    os.makedirs("./final", exist_ok=True)
+
+    csv_files = glob.glob("downloads/"+query+"/*.csv")
+    if len(csv_files)<1:
+        print("No csv file found!!")
+        exit(0)
+    dfs=[]
+    skip=[]
+    for i,f in enumerate(csv_files):
+        try:
+            print(f"Reading {f}")
+            df = pd.read_csv(f)
+            dfs.append(df)
+        except Exception as e:
+            skip.append(i)
+            print(f"Failed to read {f}: {e}")
+    print(len(dfs))
+    dfs=sortFiles(dfs)
+    print(len(dfs))
+
+    labelList=getLabels.LabelsExtraction2(query,dfs,csv_files,skip)
+    print(labelList)
+    for i,df in enumerate(dfs):
+        if labelList[i] in df.columns:
+            df.rename(columns={labelList[i]:"label"},inplace=True)
+
+# Step 2: Store normalized-to-original column mappings
+    normalized_cols = []
+    orig_col_maps = []
+
+    for df in dfs:
+        norm_to_orig = {}
+        norm_cols = []
+        for col in df.columns:
+            norm = normalize(col)
+            norm_cols.append(norm)
+            norm_to_orig[norm] = col
+        normalized_cols.append(set(norm_cols))
+        orig_col_maps.append(norm_to_orig)
+
+# Step 3: Find combination with max common columns
+    max_common = set()
+    best_combo = []
+
+    for i in range(2, len(dfs) + 1):
+        for combo in combinations(range(len(dfs)), i):
+            selected_cols = [normalized_cols[j] for j in combo]
+            fuzzy_common = get_fuzzy_common_columns(selected_cols)
+            if len(fuzzy_common) >= len(max_common):
+                max_common = fuzzy_common
+                best_combo = combo
+
+  
+# Step 4: Harmonize columns and subset
+    aligned_dfs = []
+
+    for idx in best_combo:
+        df = dfs[idx]
+        original_cols = list(df.columns)
+        new_columns = {}
+        
+        for std_col in max_common:
+            # Match this standard col to the most similar original column in this DataFrame
+            match, score, _ = process.extractOne(std_col, [normalize(col) for col in original_cols], scorer=fuzz.token_sort_ratio)
+            
+            # Find the original column that corresponds to the matched normalized name
+            for col in original_cols:
+                if normalize(col) == match:
+                    new_columns[col] = std_col  # Map original -> standard
+                    break
+
+        # Subset and rename
+        df_subset = df[list(new_columns.keys())].copy()
+        df_subset.rename(columns=new_columns, inplace=True)
+        aligned_dfs.append(df_subset)
+
+# Step 5: Combine
+    combined_df = pd.concat(aligned_dfs, ignore_index=True)
+    print(best_combo)
+# print(combined_df.head())
+
+    maxCount=0
+    idx=-1
+    for i in range(len(dfs)):
+        if dfs[i].index.size > maxCount:
+            maxCount=dfs[i].index.size
+            idx=i
+
+    flag=False
+    if maxCount>combined_df.index.size and len(dfs[idx].columns)>2:
+        # print("11")
+        flag=True
+    elif combined_df.index.size>maxCount and (len(dfs[idx].columns)-len(combined_df.columns))>3 and len(dfs[idx].columns)<7:
+        # print(len(dfs[idx].columns)-len(combined_df.columns))
+        flag=True
+    
+    if flag:
+        dfs[idx].to_csv("./final/"+query+".csv", index=False)
+        print("The merge file was not upto the mark so saved a single file..."+str(idx))
+    else:
+        combined_df.to_csv("./final/"+query+".csv", index=False)
+        print("Saved Merged file...")
+
+
+
+clean("twitter sentiment analysis")

clean_openml.py

@@ -0,0 +1,49 @@
+import os
+import csv
+
+
+
+def clean(user_prompt):
+    input_directory = os.path.join("input_folder", user_prompt)
+    output_directory = "downloads/"+user_prompt
+
+# Create the output directory if it doesn't exist
+    os.makedirs(output_directory, exist_ok=True)
+
+# Loop through all files in the user-specified input directory
+    for filename in os.listdir(input_directory):
+        file_path = os.path.join(input_directory, filename)
+
+    # Skip directories or hidden files
+        if os.path.isdir(file_path) or filename.startswith("."):
+            continue
+
+    # Output file path (.csv extension added)
+        output_file = os.path.join(output_directory, filename + ".csv")
+
+        with open(file_path, "r", encoding="utf-8", errors="ignore") as file:
+            lines = file.readlines()
+
+        headers = []
+        data_rows = []
+        data_started = False
+
+        for line in lines:
+            line = line.strip()
+            if line.startswith("@ATTRIBUTE"):
+                parts = line.split()
+                if len(parts) >= 2:
+                    headers.append(parts[1])
+            elif line.startswith("@DATA"):
+                data_started = True
+            elif data_started and line:
+                data_rows.append(line.split(","))
+
+    # Write to CSV
+        with open(output_file, "w", newline="") as csvfile:
+            writer = csv.writer(csvfile)
+            writer.writerow(headers)
+            writer.writerows(data_rows)
+
+        print(f"✅ CSV file created for: {filename} → {output_file}")
+

csv_merge_openai.py

@@ -0,0 +1,133 @@
+# import os
+# import pandas as pd
+# from openai import OpenAI
+# from dotenv import load_dotenv
+
+# # Load environment variables
+# load_dotenv()
+
+# # Setup OpenAI client
+# client = OpenAI(
+#     api_key=os.getenv("OPENAI_API_KEY"),
+#     base_url=os.getenv("OPENAI_API_BASE", "")
+# )
+
+# # Set the folder containing CSV files
+# folder_path = 'house'
+# csv_files = [f for f in os.listdir(folder_path) if f.endswith(".csv")]
+
+# # Loop through each CSV file and process
+# for file in csv_files:
+#     file_path = os.path.join(folder_path, file)
+#     try:
+#         df = pd.read_csv(file_path, nrows=1)  # Read just the header row
+#         columns = df.columns.tolist()
+#         columns_str = ", ".join(columns)
+
+#         # Formulate prompt
+#         prompt = (
+#             f"The following are column labels from a dataset: {columns_str}.\n"
+#             "Among all the labels, return a list of labels which can be clubbed and merged into 1 label. Note that the lables which can be merged must belong to different datasets, do not merge lables of the same dataset"
+#         )
+
+#         # Ask OpenAI for insight
+#         response = client.chat.completions.create(
+#             model="gpt-4",
+#             messages=[
+#                 {"role": "system", "content": "You are a helpful data analyst."},
+#                 {"role": "user", "content": prompt}
+#             ],
+#             temperature=0.3
+#         )
+
+#         print(f"\n🔍 File: {file}")
+#         print("📋 Columns:", columns_str)
+#         print("💡 AI Insight:", response.choices[0].message.content)
+
+#     except Exception as e:
+#         print(f"❌ Error processing {file}: {e}")
+
+import os
+import json
+import pandas as pd
+from openai import OpenAI
+from dotenv import load_dotenv
+
+load_dotenv()
+
+client = OpenAI(
+    api_key=os.getenv("OPENAI_API_KEY"),
+    base_url=os.getenv("OPENAI_API_BASE", "")
+)
+
+folder_path = 'downloads/house'
+csv_files = [f for f in os.listdir(folder_path) if f.endswith(".csv")]
+
+# Collect all column headers
+all_columns = {}
+for file in csv_files:
+    try:
+        df = pd.read_csv(os.path.join(folder_path, file), nrows=1)
+        all_columns[file] = df.columns.tolist()
+    except Exception as e:
+        print(f"❌ Could not read {file}: {e}")
+
+flattened_cols = [f"{file}: {', '.join(cols)}" for file, cols in all_columns.items()]
+prompt = (
+    "The following are column headers from multiple CSV datasets:\n\n"
+    + f"{flattened_cols}"
+    + "\n\nIdentify which labels across different datasets can be considered equivalent and merged. "
+      "Return only a valid JSON dictionary where keys are standard labels and values are lists of corresponding labels to rename. No explanation."
+)
+
+response = client.chat.completions.create(
+    model="gpt-4",
+    messages=[
+        {"role": "system", "content": "You are a helpful data analyst."},
+        {"role": "user", "content": prompt}
+    ],
+    temperature=0.3
+)
+
+# Parse JSON dictionary
+merge_map_text = response.choices[0].message.content.strip()
+try:
+    start = merge_map_text.find("{")
+    end = merge_map_text.rfind("}") + 1
+    json_text = merge_map_text[start:end]
+    merge_map = json.loads(json_text)
+    print("\n🧠 Parsed Merge Map:")
+    print(json.dumps(merge_map, indent=2))
+except Exception as e:
+    print("❌ Could not parse merge map from GPT:", e)
+    merge_map = {}
+
+# Merge DataFrames
+merged_df = pd.DataFrame()
+
+for file in csv_files:
+    try:
+        df = pd.read_csv(os.path.join(folder_path, file), on_bad_lines='skip')
+
+        # Rename columns to standard labels
+        for standard_label, variants in merge_map.items():
+            for variant in variants:
+                if variant in df.columns:
+                    df[standard_label] = df[variant]
+        
+        # Retain only the standard columns we care about
+        df = df[list(set(df.columns) & set(merge_map.keys()))]
+
+        if not df.empty:
+            merged_df = pd.concat([merged_df, df], ignore_index=True)
+
+    except Exception as e:
+        print(f"❌ Error processing {file}: {e}")
+
+# Final clean-up
+if not merged_df.empty:
+    merged_df.drop_duplicates(inplace=True)
+    merged_df.to_csv("merged_cleaned_dataset.csv", index=False)
+    print("\n✅ Merged and cleaned dataset saved as 'merged_cleaned_dataset.csv'")
+else:
+    print("⚠️ No data was merged. Check if the merge map matches the actual columns.")

generate_graphs.py

@@ -0,0 +1,51 @@
+import pandas as pd
+import matplotlib.pyplot as plt
+import os
+
+def generate_graphs(csv_path, output_dir):
+    df = pd.read_csv(csv_path)
+
+    os.makedirs(output_dir, exist_ok=True)
+
+    # Graph 1: Line plot of Open vs Close
+    plt.figure(figsize=(6, 4))
+    plt.plot(df['Open'], label='Open', color='blue')
+    plt.plot(df['Close'], label='Close', color='green')
+    plt.title('Open vs Close Price')
+    plt.xlabel('Index')
+    plt.ylabel('Price')
+    plt.legend()
+    plt.tight_layout()
+    plt.savefig(os.path.join(output_dir, 'open_close.png'))
+    plt.close()
+
+    # Graph 2: Scatter plot of RSI vs MACD
+    plt.figure(figsize=(6, 4))
+    plt.scatter(df['RSI'], df['MACD'], alpha=0.7, color='purple')
+    plt.title('RSI vs MACD')
+    plt.xlabel('RSI')
+    plt.ylabel('MACD')
+    plt.tight_layout()
+    plt.savefig(os.path.join(output_dir, 'rsi_macd.png'))
+    plt.close()
+
+    # Graph 3: Bar chart of average Volume (chunked)
+    volume_avg = df['Volume'].head(10)  # Bar chart for first 10
+    plt.figure(figsize=(6, 4))
+    plt.bar(volume_avg.index, volume_avg.values, color='orange')
+    plt.title('Average Volume (First 10)')
+    plt.xlabel('Index')
+    plt.ylabel('Volume')
+    plt.tight_layout()
+    plt.savefig(os.path.join(output_dir, 'volume_bar.png'))
+    plt.close()
+
+    # Graph 4: Histogram of Target values
+    plt.figure(figsize=(6, 4))
+    plt.hist(df['Target'], bins=10, color='red', alpha=0.8)
+    plt.title('Distribution of Target')
+    plt.xlabel('Target Value')
+    plt.ylabel('Frequency')
+    plt.tight_layout()
+    plt.savefig(os.path.join(output_dir, 'target_hist.png'))
+    plt.close()

getDatasets.py

@@ -0,0 +1,39 @@
+import sys
+import os
+import getFiles.getKaggle as getKaggle
+import getFiles.getGoogle as getGoogle
+import getFiles.getGithub as getGithub
+import getFiles.getHuggingFace as gh
+import cleanDataset
+import openml_search
+import clean_openml
+
+sys.path.append(os.path.abspath(os.path.join(os.getcwd(), 'langchain_folder')))
+
+from langchain_folder import main as m
+import json
+
+def downloadDatasets():
+    data=input("enter query : ")
+    kag,git,hug=getGoogle.googleDatasets(data)
+    print(kag)
+    print("this is github : ")
+    print(git)
+    print(hug)
+    if(len(kag)>0):
+        for url in kag:
+            getKaggle.kaggleDataset(url,data)
+    if(len(git)>0):
+        for url in git:
+            getGithub.githubDataset(url,data)
+    if(len(hug)>0):
+        for url in hug:
+            gh.huggingDataset(url,data)
+
+    openml_search.openDataset(data)
+    clean_openml.clean(data)
+
+
+    cleanDataset.clean(data)
+    
+downloadDatasets()

getFiles/getGithub.py

@@ -0,0 +1,57 @@
+import os
+import time
+from selenium import webdriver
+from selenium.webdriver.common.by import By
+from selenium.webdriver.chrome.options import Options
+from selenium.webdriver.common.action_chains import ActionChains
+
+
+
+
+def githubDataset(url,query):
+    # time.sleep(3)  
+    download_folder = os.path.abspath(f"./downloads/{query}")
+    os.makedirs(download_folder, exist_ok=True)
+    chrome_options = Options()
+    chrome_options.add_argument("--headless")  # Uncomment to run headless (no UI)
+    chrome_options.add_experimental_option("prefs", {
+            "download.default_directory": download_folder,  # Set the custom download folder
+            "download.prompt_for_download": False,  # Don't ask for confirmation to download
+            "download.directory_upgrade": True,  # Allow downloading into the custom folder
+            "safebrowsing.enabled": True  # Enable safe browsing (to avoid warnings during download)
+        })
+    driver = webdriver.Chrome(options=chrome_options)
+
+    driver.get(url)
+    try:
+        csv_links = driver.find_elements(By.XPATH, "//a[contains(@href, '.csv')]")
+        for link in csv_links:
+            csv_file_name = link.text
+            if csv_file_name.endswith(".csv"):
+                print(f"Found CSV file: {csv_file_name}")
+                href=link.get_attribute("href")
+                # print("hello : "+href)
+                driver.get(href)
+                time.sleep(5)
+
+                download_button = driver.find_element(By.XPATH, "//button[contains(@class, 'Box-sc-g0xbh4-0 ivobqY prc-Button-ButtonBase-c50BI prc-Button-IconButton-szpyj')]")
+                href2=download_button.get_attribute("href")
+                if  href2:
+                    driver.get(href2)
+                    print("Button clicked!!")
+                else:
+                    download_button.click()
+                time.sleep(7)
+                break
+            else:
+                print("No CSV file found.")
+    except Exception as e:
+        print("No CSV File")
+        print(e)
+    finally:
+        driver.quit()
+
+    # print(f"CSV file should be downloaded to {download_folder}")
+
+# githubDataset("https://github.com/ageron/handson-ml2/tree/master/datasets/housing","housing")
+# githubDataset("https://github.com/nytimes/covid-19-data","housing")

getFiles/getGoogle.py

@@ -0,0 +1,119 @@
+import re
+from selenium import webdriver
+from selenium.webdriver.common.by import By
+from selenium.webdriver.common.keys import Keys
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.chrome.options import Options
+import time
+import getFiles.getKaggle as getKaggle
+import getFiles.getGithub as getGithub
+import os
+
+times=15
+
+
+def googleDatasets(query):
+    # query="Covid 19"
+    download_folder = "./downloads/"+query
+    kag=[]
+    git=[]
+    hug=[]
+    count=0
+    if not os.path.exists(download_folder):
+        os.makedirs(download_folder)
+
+    chrome_options = Options()
+    chrome_options.add_argument("--headless")  # Uncomment to run headless (no UI)
+    chrome_options.add_experimental_option("prefs", {
+        "download.default_directory": download_folder,  # Set the custom download folder
+        "download.prompt_for_download": False,  # Don't ask for confirmation to download
+        "download.directory_upgrade": True,  # Allow downloading into the custom folder
+        "safebrowsing.enabled": True  # Enable safe browsing (to avoid warnings during download)
+    })
+    driver = webdriver.Chrome(options=chrome_options)
+
+    driver.get("https://datasetsearch.research.google.com/")
+
+    try:
+        WebDriverWait(driver, 20).until(
+        EC.presence_of_element_located((By.TAG_NAME, "c-wiz"))
+    )
+
+        search = WebDriverWait(driver, 20).until(
+        EC.element_to_be_clickable((By.CSS_SELECTOR, "input[aria-label='Dataset Search']"))
+    )
+
+        search.send_keys(query)
+        search.send_keys(Keys.RETURN)
+
+        WebDriverWait(driver, 10).until(
+        EC.presence_of_element_located((By.CSS_SELECTOR, "div[jscontroller]"))
+    )
+    
+        WebDriverWait(driver,10).until(
+        EC.presence_of_element_located((By.TAG_NAME,"c-wiz"))
+    )
+    
+        WebDriverWait(driver,10).until(
+        EC.presence_of_element_located((By.CSS_SELECTOR,"ol.VAt4"))
+    )
+    
+        links=driver.find_elements(By.CSS_SELECTOR,"li.UnWQ5")
+        for link in links:
+            if count==times:
+                break
+        # print(link)
+            link.click()
+            time.sleep(2)
+            WebDriverWait(driver,10).until(
+            EC.presence_of_element_located((By.CSS_SELECTOR,"ul.eEUDce"))
+        )
+        
+            downloads=driver.find_elements(By.CSS_SELECTOR,"li.dy4aPc")
+            dataset=downloads[0]
+        # dataset_url = dataset.get_attribute("href")
+        # print("Dataset URL:", dataset_url)
+        # print(dataset.get_attribute("href"))
+            tag=dataset.find_element(By.TAG_NAME,"a")
+            url=tag.get_attribute("href")
+        # print(url)
+        # print(driver.current_url)
+            try:
+                if "kaggle" in url:
+                    match=re.search(r'datasets\/(.*)',url)
+                    print(match)
+                    string=match.group(1)
+                    print("This is "+string)
+                    kag.append(string)
+                # getKaggle.kaggleDataset(string,query)
+                # time.sleep(5)
+                    continue
+                elif "github" in url:
+                    print("This is "+url)
+                    git.append(url)
+                    # getGithub.githubDataset(url,query)
+                    # time.sleep(5)
+                    continue
+                elif "huggingface" in url and "turkish" not in url and "spanish" not in url:
+                    match=re.search(r'datasets\/(.*)',url)
+                    string=match.group(1)
+                    print("Again "+string)
+                    hug.append(string)
+                    continue
+            except:
+                continue
+            dataset.click()
+            count+=1
+            time.sleep(5)
+        time.sleep(5)
+
+    except Exception as e:
+        print("Error:", e)
+
+    finally:
+        driver.quit()
+    
+    return kag,git,hug
+# 
+# googleDatasets("house predictions")

getFiles/getHuggingFace.py

@@ -0,0 +1,18 @@
+from datasets import load_dataset
+import os
+
+def huggingDataset(url,query):
+    try:
+        # query="sentiment analysis"
+        # url="cornell-movie-review-data/rotten_tomatoes"
+        dataset = load_dataset(url)
+        print("Started downloading.....")
+        os.makedirs("./downloads/"+query,exist_ok=True)
+
+        dataset['train'].to_csv("./downloads/"+query+"/"+url[:5]+"train.csv")
+        dataset['test'].to_csv("./downloads/"+query+"/"+url[:5]+"test.csv")
+    except:
+        print("couldn't download hugging face dataset")
+
+# huggingDataset("cornell-movie-review-data/rotten_tomatoes","sentiment analysis")
+

getFiles/getKaggle.py

@@ -0,0 +1,19 @@
+import os
+from kaggle.api.kaggle_api_extended import KaggleApi
+import sys
+
+
+# Initialize
+api = KaggleApi()
+api.authenticate()
+
+# Download dataset to current dir
+def kaggleDataset(url,query):
+    try:
+        print(f"{url} started downloading")
+        os.makedirs("./downloads/"+query, exist_ok=True)
+        api.dataset_download_files(url, path='./downloads/'+query, unzip=True)
+    except Exception as e:
+        print("Dataset not found")
+
+# kaggleDataset('zynicide/wine-reviews')

getFiles/getSklearn.py

@@ -0,0 +1,33 @@
+import os
+import pandas as pd
+import sklearn.datasets as skd
+from pathlib import Path
+
+def sklearnDatasets(url,query):
+    try:
+        current_directory = os.getcwd()
+        downloads_folder = os.path.join(current_directory, query)
+        print(f"{url} started downloading")
+        os.makedirs(downloads_folder, exist_ok=True)
+
+        dataset_func = getattr(skd, url, None)
+
+        if dataset_func:
+            dataset = dataset_func(data_home=downloads_folder)
+
+            X, y = dataset.data, dataset.target
+
+            df = pd.DataFrame(X, columns=dataset.feature_names)
+            df['Target'] = y
+
+            csv_file_path = os.path.join(downloads_folder, f"{url}.csv")
+            df.to_csv(csv_file_path, index=False)
+
+            # print(f"Dataset '{url}' downloaded and saved to {csv_file_path}")
+        else:
+            print(f"Unknown dataset function: {url}. Please check the URL.")
+    except Exception as e:
+        print(f"Dataset Not found")
+    
+
+# sklearnDatasets("fetch_california_housing")

getLabels.py

@@ -0,0 +1,97 @@
+import os
+import pandas as pd
+from openai import OpenAI
+from dotenv import load_dotenv
+import google.generativeai as genai
+import ast
+load_dotenv()
+
+def LabelsExtraction(query,dfs,csv_files,skip):
+
+    columnNames={}
+    j=0
+    for i,df in enumerate(dfs):
+        if j in skip:
+            j+=1
+        name=os.path.basename(csv_files[j]).lower()
+        columnNames[name]=df.columns
+        j+=1
+
+
+# print(columnNames)
+    client = OpenAI(
+    api_key=os.getenv("OPENAI_API_KEY"),
+    base_url=os.getenv("OPENAI_API_BASE_URL", "")
+    )
+    prompt = (
+    "The following is a dictionary with key as name of csv file and value as array of their column headers:\n\n"
+    "Eg: {'21754539_dataset.csv': Index(['Id', 'MSSubClass', 'MSZoning', 'LotFrontage', 'LotArea', 'Street','Alley', 'LotShape', 'LandContour', 'Utilities', 'LotConfig', 'LandSlope', 'Neighborhood', 'Condition1', 'Condition2', 'BldgType','HouseStyle', 'OverallQual', 'OverallCond', 'YearBuilt'])}"
+    + "The content in the Index([]) is the list of the headers"
+    + f"{columnNames}"
+    + "\n\nwith this info try to figure out which column in each file represents its label and also indentify if there is any file with no label"
+      "Return an array with column name that represents the label in that file and if there is no label return 0 in that place. Match the indexes as given in the dictionary, do not return any other content, just reutrn the array"
+    + f"the labels which you will return must in context with this query {query}, so return the most relevant labels"
+)
+
+    response = client.chat.completions.create(
+    model="gpt-4",
+    messages=[
+        {"role": "system", "content": "You are a helpful data analyst."},
+        {"role": "user", "content": prompt}
+    ],
+    temperature=0.3
+)
+
+    merge_map_text = response.choices[0].message.content.strip()
+    stripped=merge_map_text.split("```python")[1].replace("[","").replace("]","").replace("```","").split(",")
+    array=[str1.replace("\n","").strip() for str1 in stripped]
+    print(array)
+    arr2=[arr.strip("'") for arr in array]
+    print(arr2)
+# print(arr2)
+    return arr2
+
+
+def LabelsExtraction2(query,dfs,csv_files,skip):
+
+    columnNames={}
+    j=0
+    for i,df in enumerate(dfs):
+        if j in skip:
+            j+=1
+        name=os.path.basename(csv_files[j]).lower()
+        columnNames[name]=df.columns
+        j+=1
+
+
+# print(columnNames)
+    prompt = (
+    "You are given a dictionary where each key is the name of a CSV file, and the value is an array (in pandas Index format) representing the column headers of that file.\n\n"
+    "Example format:\n"
+    "{'21754539_dataset.csv': Index(['Id', 'MSSubClass', 'MSZoning', 'LotFrontage', 'LotArea', 'Street', 'Alley', "
+    "'LotShape', 'LandContour', 'Utilities', 'LotConfig', 'LandSlope', 'Neighborhood', 'Condition1', 'Condition2', "
+    "'BldgType', 'HouseStyle', 'OverallQual', 'OverallCond', 'YearBuilt'])}\n\n"
+    "Your task is to analyze this dictionary and, for each file, determine which column is most likely to represent the "
+    "**label** (i.e., the target variable) relevant to the following query:\n\n"
+    f"{query}\n\n"
+    "If you believe a file has **no clear label** based on the column names and the query, return **0** for that file.\n\n"
+    "Return your response as a **Python list**, maintaining the **same order as the keys in the input dictionary**. Each "
+    "entry in the list should be either:\n"
+    "- the column name (string) that most likely represents the label for that file, or\n"
+    "- the integer `0` if no label can be identified.\n\n"
+    "⚠️ Do not return any explanation, reasoning, or code. Only return the final list of labels, e.g.:\n"
+    "```python\n['SalePrice', 0, 'target_column_name']\n```\n\n"
+    "Now use the following data to generate your answer:\n"
+    f"{columnNames}"
+)
+
+    genai.configure(api_key=os.getenv("gemini_api"))
+
+    model = genai.GenerativeModel("gemini-2.0-flash")
+    response = model.generate_content(prompt)
+    merge_map_text = response.text.strip()
+    print(merge_map_text)
+    str1=merge_map_text.replace("```","").replace("python","")
+    actual_list = ast.literal_eval(str1)
+    return actual_list
+

langchain_folder/llm_helper.py

@@ -0,0 +1,8 @@
+from dotenv import load_dotenv
+from langchain_groq import ChatGroq
+import os
+
+load_dotenv()
+llm = ChatGroq(groq_api_key = os.getenv('groq_api'), model_name = "llama-3.1-8b-instant")
+
+#llm = ChatGroq(groq_api_key = os.getenv('groq_deepseek_api'), model_name = "DeepSeek R1 Distill Llama 70B")

langchain_folder/main.py

@@ -0,0 +1,14 @@
+from langchain_core.prompts import PromptTemplate
+from langchain_folder.llm_helper import llm
+
+def ReturnKeywordsfromPrompt(query):
+    prompt = """You are a model and your job is the extract the keywords from the query which will be passed to you.
+    For Eg: If the query is -> Provide me with a combined dataset for house price prediction.
+    Your answer should be 'house price'. Do not return anything else, just the keywords, note that the queries can be for various datasets,
+    not jsut for house price prediction, go it?
+    Query: {query}"""
+
+    pt = PromptTemplate.from_template(prompt)
+    chain = pt | llm
+    response = chain.invoke({'query': query})
+    return response.content

openai_openml.py

@@ -0,0 +1,48 @@
+import os
+from selenium import webdriver
+from selenium.webdriver.common.by import By
+from selenium.webdriver.common.keys import Keys
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.chrome.options import Options
+from selenium.webdriver.chrome.service import Service
+import requests
+import time
+
+count=4
+
+def openDataset(user_prompt):
+    chrome_options = Options()
+    chrome_options.add_argument("--headless")  # Uncomment to run headless (no UI)
+    driver = webdriver.Chrome(options=chrome_options)
+    try:
+        driver.get('https://www.openml.org/search?type=data&status=active')
+        
+        time.sleep(5)
+        
+        search = WebDriverWait(driver, 20).until(
+        EC.presence_of_element_located((By.CSS_SELECTOR, "input.MuiInputBase-input.css-mnn31")))
+        search.send_keys(user_prompt)
+        search.send_keys(Keys.RETURN)
+        time.sleep(4)
+
+        divs = driver.find_elements(By.CSS_SELECTOR, "div.MuiPaper-root.MuiPaper-elevation.MuiPaper-elevation1.MuiCard-root.sc-gFAWRd.gJoEXx.css-1xol7fw")
+        a=0
+        urls=[]
+        for div in divs:
+            a+=1
+            if a>count:
+                break
+            div.click()
+            urls.append(driver.current_url)
+            # print(driver.current_url)
+            driver.back()
+            time.sleep(2)
+            
+        driver.quit()
+        return urls
+    except:
+        print("Internet Issue driver crashed")
+        return []
+
+# openDataset("stock price prediction")

openml_search.py

@@ -0,0 +1,96 @@
+import openml
+from langchain_core.prompts import PromptTemplate
+from langchain_folder.llm_helper import llm
+from dotenv import load_dotenv
+import os
+from selenium import webdriver
+from selenium.webdriver.common.by import By
+from selenium.webdriver.common.keys import Keys
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.chrome.options import Options
+from selenium.webdriver.chrome.service import Service
+import requests
+import openai_openml as oo
+
+
+load_dotenv()
+url_list = []
+api_key = os.getenv('openml_api')
+openml.config.apikey = api_key
+
+def extract_keywords(query):
+    prompt = PromptTemplate.from_template("""
+        You are an assistant whose job is to extract the keywords from the query and return it:
+        Query = "{query}"
+        For example, if the query is Generate a list of links to datasets related to house price prediction
+        your response should be -> "house price".
+        Note that the query might not always be related to house price predictions, it can be related to other things as well.
+        return only the keywords do not return anything else
+    """)
+    rendered_prompt = prompt.format(query=query)
+    response = llm.invoke(rendered_prompt)
+    return response.content
+
+def fetch_dataset_urls(query, limit=4):
+    print(f"Searching for datasets related to: {query}")
+    # datasets = openml.datasets.list_datasets(output_format="dataframe")
+    # matching_datasets = datasets[datasets['name'].str.contains(query, case=False, na=False)]
+    # if matching_datasets.empty:
+    #     keywords = query.lower().split()
+    #     mask = datasets['name'].apply(lambda name: all(kw in str(name).lower() for kw in keywords))
+    #     matching_datasets = datasets[mask]
+
+    # if matching_datasets.empty:
+    #     print("No datasets found for the query.")
+    # else:
+    #     matching_datasets = matching_datasets.head(limit)
+    #     for index, row in matching_datasets.iterrows():
+    #         print(f"📌 Dataset: {row['name']}")
+    #         dataset_url = f"https://www.openml.org/d/{row['did']}"
+    #         url_list.append(dataset_url)
+    #         print(f"🔗 URL: https://www.openml.org/d/{row['did']}\n")
+    global url_list
+    url_list=oo.openDataset(query)
+
+
+def openDataset(user_prompt):
+    # user_prompt = input("Enter user prompt: ")
+    extracted_keywords = extract_keywords(user_prompt)
+    print(extracted_keywords)
+    fetch_dataset_urls(extracted_keywords)
+
+    download_folder = "./input_folder/"+user_prompt
+    if not os.path.exists(download_folder):
+        os.makedirs(download_folder)
+
+    chrome_options = Options()
+    chrome_options.add_argument("--headless")  # Uncomment to run headless (no UI)
+    chrome_options.add_experimental_option("prefs", {
+        "download.default_directory": download_folder,  # Set the custom download folder
+        "download.prompt_for_download": False,  # Don't ask for confirmation to download
+        "download.directory_upgrade": True,  # Allow downloading into the custom folder
+        "safebrowsing.enabled": True  # Enable safe browsing (to avoid warnings during download)
+    })
+    driver = webdriver.Chrome(options=chrome_options)
+    for url in url_list:
+        driver.get(url)
+        try:
+            download_button = WebDriverWait(driver, 10).until(
+            EC.presence_of_element_located((By.CSS_SELECTOR, "a[aria-label='Download dataset']"))
+        )
+            actual_download_url = download_button.get_attribute("href")
+            filename = actual_download_url.split("/")[-2] + "_" + actual_download_url.split("/")[-1]
+            file_path = os.path.join(download_folder, filename)
+        
+            print(f"⬇️ Downloading from {actual_download_url}")
+            response = requests.get(actual_download_url)
+            with open(file_path, "wb") as f:
+                f.write(response.content)
+            print(f"✅ Saved to {file_path}\n")
+    
+        except Exception as e:
+            print(f"❌ Failed to fetch or download from {url}: {e}")
+
+# openDataset("stock market predictions")
+

preprocessing/getNLP.py

@@ -0,0 +1,25 @@
+import spacy
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+nlp=spacy.load("en_core_web_lg")
+MAX_LENGTH=10
+
+def preprocess_texts(texts):
+    sentence_vectors = []
+
+    # Use nlp.pipe() to process texts in batch (much faster)
+    for doc in nlp.pipe(texts, batch_size=1000):
+        vectors = [token.vector for token in doc if token.has_vector]  # Extract word vectors
+        sentence_vectors.append(vectors)
+
+    # Pad all vectors to fixed length
+    return pad_sequences(sentence_vectors, maxlen=MAX_LENGTH, dtype='float32', padding='post', truncating='post')
+
+def wordEmbed(df,columns):
+    for col in columns:
+        processed_array = preprocess_texts(df[col].tolist()) 
+        df["processed"+col] = [processed_array[i] for i in range(len(df))]
+    df.drop(columns=columns,inplace=True)
+    # print(df.head())
+    return df
+    
+

preprocessing/getString.py

@@ -0,0 +1,72 @@
+import os
+import pandas as pd
+import ast
+import google.generativeai as genai
+from dotenv import load_dotenv
+
+load_dotenv()
+
+def extract_column_samples(df, n=5):
+    samples = {}
+    for col in df.columns:
+        samples[col] = df[col].head(n).tolist()
+    return samples
+
+def getCodes(query):
+    # query = "covid 19"
+    path="final/"+query+".csv"
+    df = pd.read_csv(path)
+
+    samples = extract_column_samples(df)
+
+    prompt = (
+    "You are a data analyst. I will give you a dictionary containing column names with example values from a dataset.\n\n"
+    "Your task is to:\n"
+    "1. Identify columns where one-hot encoding is *not suitable*.\n"
+    "2. For each of these, determine if it requires:\n"
+    "   - feature extraction (e.g., from datetime or strings), or\n"
+    "   - use of word embeddings (e.g., for free text or high-cardinality text).\n\n"
+    "For feature extraction columns:\n"
+    "- Create a **Python dictionary** where:\n"
+    "  * Each key is a new, meaningful column name.\n"
+    "  * Each value is a **valid Pandas expression string** that derives the new column from the original `df` DataFrame.\n"
+    "- Also return a **Python list** of original column names that were used in this dictionary.\n\n"
+    "For columns requiring word embeddings:\n"
+    "- Return a separate **Python list** of these column names.\n"
+    "- If any column appears in both cases, include it *only* in the word embedding list.\n\n"
+    "Your output **must follow this exact format** with no additional explanation or markdown. Only return the following inside a single Python code block:\n"
+    "```python\n"
+    "# Dictionary of transformations\n"
+    "{'new_col1': \"some pandas expression\", 'new_col2': \"some other pandas expression\"}\n\n"
+    "# Array of columns used in the dictionary\n"
+    "['col1', 'col2']\n"
+    "# Array of columns that require the use of word embeddings\n"
+    "['col3', 'col4']\n"
+    "```\n\n"
+    "**DO NOT** include any explanation, reasoning, extra code, or markdown outside of the code block. Only return the exact format shown above. Do not generate or describe functions.\n\n"
+    f"Here is the input :\n{samples}\n"
+)
+
+
+    genai.configure(api_key=os.getenv("gemini_api"))
+
+    model = genai.GenerativeModel("gemini-2.0-flash")
+    response = model.generate_content(prompt)
+
+    merge_map_text = response.text.strip()
+    print(merge_map_text)
+
+    str1 = merge_map_text.split("```python")[1].split("# Array of columns used in the dictionary")[0].strip()
+    str2 = merge_map_text.split("# Array of columns used in the dictionary")[1].split("# Array of columns that require the use of word embeddings")[0].strip()
+    str3 = merge_map_text.split("# Array of columns used in the dictionary")[1].split("# Array of columns that require the use of word embeddings")[1].replace("```","").strip()
+
+    preprocessing_code = ast.literal_eval(str1)
+    actual_list = ast.literal_eval(str2)
+    nlp=ast.literal_eval(str3)
+    # print("Parsed dict:\n", preprocessing_code)
+    # print("Columns changed:\n", actual_list)
+    # print("for nlp : ",nlp)
+    return preprocessing_code,actual_list,nlp
+
+# getCodes(extract_column_samples)
+

preprocessing/process.py

@@ -0,0 +1,48 @@
+import pandas as pd
+import getString
+import getNLP
+import os
+
+def one_hot_encode_objects(df,nlp,columns):
+    object_cols = df.select_dtypes(include='object').columns
+    for col in object_cols:
+        if col not in nlp and col not in columns and "label" not in col:
+            if df[col].apply(lambda x: isinstance(x, (list, tuple, dict, set)) or hasattr(x, '__array__')).any():
+                print(f"Skipping column '{col}' due to unhashable values.")
+                continue
+            dummies = pd.get_dummies(df[col], prefix=col).astype(int)
+            df = pd.concat([df, dummies], axis=1)
+            df = df.drop(columns=[col])
+    print(df.columns)
+    return df
+
+def fixEmpty(df):
+    df.replace(['undefined', 'null', 'NaN', 'None'], pd.NA, inplace=True)
+    for col in df.columns:
+        if df[col].dtype == 'object':
+            df[col] = df[col].fillna('Unknown')
+        else:
+            df[col] = df[col].fillna(df[col].mean())
+    
+    return df
+
+def preprocessing(query):
+    os.makedirs("./processed",exist_ok=True)
+    df=pd.read_csv("final/"+query+".csv")
+    # print(df.head())
+    df=fixEmpty(df)
+    preDict,col,nlp=getString.getCodes(query)
+    if len(col)>0:
+        for new_col, expr in preDict.items():
+            df[new_col] = eval(expr)
+        df.drop(columns=col, inplace=True)
+    if len(nlp)>0:
+        df=getNLP.wordEmbed(df,nlp)
+        # print(df.columns)
+    df=one_hot_encode_objects(df,nlp,col)
+    # df = df.astype('float32')
+    df.to_csv("./processed/"+query+".csv", index=False)
+    # print(df.head())
+    # print(df.info())
+    
+# preprocessing("twitter sentiment analysis")

test.ipynb

@@ -0,0 +1,1115 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "4b227ed2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import glob\n",
+    "import re\n",
+    "# from collections import defaultdict\n",
+    "from itertools import combinations\n",
+    "import os"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "9a976256",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query=\"house predictions\"\n",
+    "\n",
+    "\n",
+    "# Helper: Standardize column names\n",
+    "def normalize(col):\n",
+    "    return re.sub(r'[^a-z0-9]', '', col.lower())\n",
+    "\n",
+    "# Step 1: Read CSVs\n",
+    "csv_files = glob.glob(\"downloads/covid 19/*.csv\")\n",
+    "dfs = [pd.read_csv(f) for f in csv_files]\n",
+    "\n",
+    "# Step 2: Store normalized-to-original column mappings\n",
+    "normalized_cols = []\n",
+    "orig_col_maps = []\n",
+    "\n",
+    "for df in dfs:\n",
+    "    norm_to_orig = {}\n",
+    "    norm_cols = []\n",
+    "    for col in df.columns:\n",
+    "        norm = normalize(col)\n",
+    "        norm_cols.append(norm)\n",
+    "        norm_to_orig[norm] = col\n",
+    "    normalized_cols.append(set(norm_cols))\n",
+    "    orig_col_maps.append(norm_to_orig)\n",
+    "\n",
+    "\n",
+    "# normalized_cols,orig_col_maps"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d82953b5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from rapidfuzz import process, fuzz\n",
+    "\n",
+    "def get_fuzzy_common_columns(cols_list, threshold=85):\n",
+    "    \"\"\"\n",
+    "    Given a list of sets of column names (normalized),\n",
+    "    return the set of column names that are 'fuzzy common'\n",
+    "    across all lists.\n",
+    "    \"\"\"\n",
+    "    # Start with columns from the first dataset\n",
+    "    base = cols_list[0]\n",
+    "    common = set()\n",
+    "\n",
+    "    for col in base:\n",
+    "        match_all = True\n",
+    "        for other in cols_list[1:]:\n",
+    "            match, score, _ = process.extractOne(col, other, scorer=fuzz.token_sort_ratio)\n",
+    "            if score < threshold:\n",
+    "                match_all = False\n",
+    "                break\n",
+    "        if match_all:\n",
+    "            common.add(col)\n",
+    "    return common\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0eb8e3d5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[{'max', 'prcp', 'min', 'lat', 'long', 'temp', 'provincestate', 'dayfromjanfirst', 'date', 'wdsp', 'fog', 'fatalities', 'ah', 'stp', 'confirmedcases', 'countryregion', 'rh', 'slp', 'dewp', 'id'}, {'max', 'prcp', 'min', 'lat', 'long', 'temp', 'provincestate', 'dayfromjanfirst', 'date', 'wdsp', 'fog', 'fatalities', 'ah', 'stp', 'countryprovince', 'confirmedcases', 'countryregion', 'rh', 'slp', 'dewp', 'id'}]\n",
+      "[{'max', 'prcp', 'min', 'lat', 'long', 'temp', 'provincestate', 'dayfromjanfirst', 'date', 'wdsp', 'fog', 'fatalities', 'ah', 'stp', 'confirmedcases', 'countryregion', 'rh', 'slp', 'dewp', 'id'}, {'cumulativecases', 'datereported', 'newdeaths', 'countrycode', 'cumulativedeaths', 'whoregion', 'country', 'newcases'}]\n",
+      "[{'max', 'prcp', 'min', 'lat', 'long', 'temp', 'provincestate', 'dayfromjanfirst', 'date', 'wdsp', 'fog', 'fatalities', 'ah', 'stp', 'countryprovince', 'confirmedcases', 'countryregion', 'rh', 'slp', 'dewp', 'id'}, {'cumulativecases', 'datereported', 'newdeaths', 'countrycode', 'cumulativedeaths', 'whoregion', 'country', 'newcases'}]\n",
+      "[{'max', 'prcp', 'min', 'lat', 'long', 'temp', 'provincestate', 'dayfromjanfirst', 'date', 'wdsp', 'fog', 'fatalities', 'ah', 'stp', 'confirmedcases', 'countryregion', 'rh', 'slp', 'dewp', 'id'}, {'max', 'prcp', 'min', 'lat', 'long', 'temp', 'provincestate', 'dayfromjanfirst', 'date', 'wdsp', 'fog', 'fatalities', 'ah', 'stp', 'countryprovince', 'confirmedcases', 'countryregion', 'rh', 'slp', 'dewp', 'id'}, {'cumulativecases', 'datereported', 'newdeaths', 'countrycode', 'cumulativedeaths', 'whoregion', 'country', 'newcases'}]\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "(set(), [])"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "max_common = set()\n",
+    "best_combo = []\n",
+    "\n",
+    "for i in range(2, len(dfs) + 1):\n",
+    "    for combo in combinations(range(len(dfs)), i):\n",
+    "        common = set.intersection(*[normalized_cols[i] for i in combo])\n",
+    "        # some=[normalized_cols[i] for i in combo]\n",
+    "        # print(some)\n",
+    "        if len(common) > len(max_common):\n",
+    "            max_common = common\n",
+    "            best_combo = combo\n",
+    "\n",
+    "max_common,best_combo"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "b72d4152",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "aligned_dfs = []\n",
+    "for idx in best_combo:\n",
+    "    df = dfs[idx]\n",
+    "    norm_to_orig = orig_col_maps[idx]\n",
+    "    selected_cols = [norm_to_orig[col] for col in max_common]\n",
+    "    df_subset = df[selected_cols].copy()\n",
+    "    df_subset.columns = [col for col in max_common]  # unify column names\n",
+    "    aligned_dfs.append(df_subset)\n",
+    "\n",
+    "# Step 5: Combine\n",
+    "combined_df = pd.concat(aligned_dfs, ignore_index=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b0768203",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "f315dfad",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "17892\n",
+      "24414\n",
+      "54960\n"
+     ]
+    }
+   ],
+   "source": [
+    "for df in dfs:\n",
+    "    print(df.index.size)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "7972a696",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[17892, 24414]\n",
+      "[17892, 54960]\n",
+      "[24414, 54960]\n",
+      "[17892, 24414, 54960]\n"
+     ]
+    }
+   ],
+   "source": [
+    "for i in range(2, len(dfs) + 1):\n",
+    "    for combo in combinations(range(len(dfs)), i):\n",
+    "        counts=[dfs[i].index.size for i in combo]\n",
+    "        print(counts)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "1a0f8006",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(54960, 2)"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "maxCount=0\n",
+    "idx=-1\n",
+    "for i in range(len(dfs)):\n",
+    "    if dfs[i].index.size > maxCount:\n",
+    "        maxCount=dfs[i].index.size\n",
+    "        idx=i\n",
+    "\n",
+    "maxCount,idx"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "240d4fd1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(42306, 54960)"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "combined_df.index.size,maxCount"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "5eba3fe9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'hello'"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "str=\"hello and \"\n",
+    "str[:5]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "94dac715",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>fixed acidity</th>\n",
+       "      <th>volatile acidity</th>\n",
+       "      <th>citric acid</th>\n",
+       "      <th>residual sugar</th>\n",
+       "      <th>chlorides</th>\n",
+       "      <th>free sulfur dioxide</th>\n",
+       "      <th>total sulfur dioxide</th>\n",
+       "      <th>density</th>\n",
+       "      <th>pH</th>\n",
+       "      <th>sulphates</th>\n",
+       "      <th>alcohol</th>\n",
+       "      <th>quality</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>7.4</td>\n",
+       "      <td>0.70</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1.9</td>\n",
+       "      <td>0.076</td>\n",
+       "      <td>11.0</td>\n",
+       "      <td>34.0</td>\n",
+       "      <td>0.9978</td>\n",
+       "      <td>3.51</td>\n",
+       "      <td>0.56</td>\n",
+       "      <td>9.4</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>7.8</td>\n",
+       "      <td>0.88</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>2.6</td>\n",
+       "      <td>0.098</td>\n",
+       "      <td>25.0</td>\n",
+       "      <td>67.0</td>\n",
+       "      <td>0.9968</td>\n",
+       "      <td>3.20</td>\n",
+       "      <td>0.68</td>\n",
+       "      <td>9.8</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>7.8</td>\n",
+       "      <td>0.76</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>2.3</td>\n",
+       "      <td>0.092</td>\n",
+       "      <td>15.0</td>\n",
+       "      <td>54.0</td>\n",
+       "      <td>0.9970</td>\n",
+       "      <td>3.26</td>\n",
+       "      <td>0.65</td>\n",
+       "      <td>9.8</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>11.2</td>\n",
+       "      <td>0.28</td>\n",
+       "      <td>0.56</td>\n",
+       "      <td>1.9</td>\n",
+       "      <td>0.075</td>\n",
+       "      <td>17.0</td>\n",
+       "      <td>60.0</td>\n",
+       "      <td>0.9980</td>\n",
+       "      <td>3.16</td>\n",
+       "      <td>0.58</td>\n",
+       "      <td>9.8</td>\n",
+       "      <td>6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>7.4</td>\n",
+       "      <td>0.70</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1.9</td>\n",
+       "      <td>0.076</td>\n",
+       "      <td>11.0</td>\n",
+       "      <td>34.0</td>\n",
+       "      <td>0.9978</td>\n",
+       "      <td>3.51</td>\n",
+       "      <td>0.56</td>\n",
+       "      <td>9.4</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   fixed acidity  volatile acidity  citric acid  residual sugar  chlorides  \\\n",
+       "0            7.4              0.70         0.00             1.9      0.076   \n",
+       "1            7.8              0.88         0.00             2.6      0.098   \n",
+       "2            7.8              0.76         0.04             2.3      0.092   \n",
+       "3           11.2              0.28         0.56             1.9      0.075   \n",
+       "4            7.4              0.70         0.00             1.9      0.076   \n",
+       "\n",
+       "   free sulfur dioxide  total sulfur dioxide  density    pH  sulphates  \\\n",
+       "0                 11.0                  34.0   0.9978  3.51       0.56   \n",
+       "1                 25.0                  67.0   0.9968  3.20       0.68   \n",
+       "2                 15.0                  54.0   0.9970  3.26       0.65   \n",
+       "3                 17.0                  60.0   0.9980  3.16       0.58   \n",
+       "4                 11.0                  34.0   0.9978  3.51       0.56   \n",
+       "\n",
+       "   alcohol  quality  \n",
+       "0      9.4        5  \n",
+       "1      9.8        5  \n",
+       "2      9.8        5  \n",
+       "3      9.8        6  \n",
+       "4      9.4        5  "
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "df=pd.read_csv(\"downloads/wine quality prediction/redwine.csv\")\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "d0947632",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'downloads/wine quality prediction\\\\redwine.csv'"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import glob\n",
+    "csv_files = glob.glob(\"downloads/\"+\"wine quality prediction\"+\"/*.csv\")\n",
+    "csv_files[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "22e2e148",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>fixed acidity</th>\n",
+       "      <th>volatile acidity</th>\n",
+       "      <th>citric acid</th>\n",
+       "      <th>residual sugar</th>\n",
+       "      <th>chlorides</th>\n",
+       "      <th>free sulfur dioxide</th>\n",
+       "      <th>total sulfur dioxide</th>\n",
+       "      <th>density</th>\n",
+       "      <th>pH</th>\n",
+       "      <th>sulphates</th>\n",
+       "      <th>alcohol</th>\n",
+       "      <th>quality</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>7.4</td>\n",
+       "      <td>0.70</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1.9</td>\n",
+       "      <td>0.076</td>\n",
+       "      <td>11.0</td>\n",
+       "      <td>34.0</td>\n",
+       "      <td>0.9978</td>\n",
+       "      <td>3.51</td>\n",
+       "      <td>0.56</td>\n",
+       "      <td>9.4</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>7.8</td>\n",
+       "      <td>0.88</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>2.6</td>\n",
+       "      <td>0.098</td>\n",
+       "      <td>25.0</td>\n",
+       "      <td>67.0</td>\n",
+       "      <td>0.9968</td>\n",
+       "      <td>3.20</td>\n",
+       "      <td>0.68</td>\n",
+       "      <td>9.8</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>7.8</td>\n",
+       "      <td>0.76</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>2.3</td>\n",
+       "      <td>0.092</td>\n",
+       "      <td>15.0</td>\n",
+       "      <td>54.0</td>\n",
+       "      <td>0.9970</td>\n",
+       "      <td>3.26</td>\n",
+       "      <td>0.65</td>\n",
+       "      <td>9.8</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>11.2</td>\n",
+       "      <td>0.28</td>\n",
+       "      <td>0.56</td>\n",
+       "      <td>1.9</td>\n",
+       "      <td>0.075</td>\n",
+       "      <td>17.0</td>\n",
+       "      <td>60.0</td>\n",
+       "      <td>0.9980</td>\n",
+       "      <td>3.16</td>\n",
+       "      <td>0.58</td>\n",
+       "      <td>9.8</td>\n",
+       "      <td>6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>7.4</td>\n",
+       "      <td>0.70</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1.9</td>\n",
+       "      <td>0.076</td>\n",
+       "      <td>11.0</td>\n",
+       "      <td>34.0</td>\n",
+       "      <td>0.9978</td>\n",
+       "      <td>3.51</td>\n",
+       "      <td>0.56</td>\n",
+       "      <td>9.4</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   fixed acidity  volatile acidity  citric acid  residual sugar  chlorides  \\\n",
+       "0            7.4              0.70         0.00             1.9      0.076   \n",
+       "1            7.8              0.88         0.00             2.6      0.098   \n",
+       "2            7.8              0.76         0.04             2.3      0.092   \n",
+       "3           11.2              0.28         0.56             1.9      0.075   \n",
+       "4            7.4              0.70         0.00             1.9      0.076   \n",
+       "\n",
+       "   free sulfur dioxide  total sulfur dioxide  density    pH  sulphates  \\\n",
+       "0                 11.0                  34.0   0.9978  3.51       0.56   \n",
+       "1                 25.0                  67.0   0.9968  3.20       0.68   \n",
+       "2                 15.0                  54.0   0.9970  3.26       0.65   \n",
+       "3                 17.0                  60.0   0.9980  3.16       0.58   \n",
+       "4                 11.0                  34.0   0.9978  3.51       0.56   \n",
+       "\n",
+       "   alcohol  quality  \n",
+       "0      9.4        5  \n",
+       "1      9.8        5  \n",
+       "2      9.8        5  \n",
+       "3      9.8        6  \n",
+       "4      9.4        5  "
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df=pd.read_csv(csv_files[0])\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1553de09",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>fixed acidity</th>\n",
+       "      <th>volatile acidity</th>\n",
+       "      <th>citric acid</th>\n",
+       "      <th>residual sugar</th>\n",
+       "      <th>chlorides</th>\n",
+       "      <th>free sulfur dioxide</th>\n",
+       "      <th>total sulfur dioxide</th>\n",
+       "      <th>density</th>\n",
+       "      <th>pH</th>\n",
+       "      <th>sulphates</th>\n",
+       "      <th>alcohol</th>\n",
+       "      <th>quality</th>\n",
+       "      <th>label</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>7.4</td>\n",
+       "      <td>0.70</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1.9</td>\n",
+       "      <td>0.076</td>\n",
+       "      <td>11.0</td>\n",
+       "      <td>34.0</td>\n",
+       "      <td>0.9978</td>\n",
+       "      <td>3.51</td>\n",
+       "      <td>0.56</td>\n",
+       "      <td>9.4</td>\n",
+       "      <td>5</td>\n",
+       "      <td>red</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>7.8</td>\n",
+       "      <td>0.88</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>2.6</td>\n",
+       "      <td>0.098</td>\n",
+       "      <td>25.0</td>\n",
+       "      <td>67.0</td>\n",
+       "      <td>0.9968</td>\n",
+       "      <td>3.20</td>\n",
+       "      <td>0.68</td>\n",
+       "      <td>9.8</td>\n",
+       "      <td>5</td>\n",
+       "      <td>red</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>7.8</td>\n",
+       "      <td>0.76</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>2.3</td>\n",
+       "      <td>0.092</td>\n",
+       "      <td>15.0</td>\n",
+       "      <td>54.0</td>\n",
+       "      <td>0.9970</td>\n",
+       "      <td>3.26</td>\n",
+       "      <td>0.65</td>\n",
+       "      <td>9.8</td>\n",
+       "      <td>5</td>\n",
+       "      <td>red</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>11.2</td>\n",
+       "      <td>0.28</td>\n",
+       "      <td>0.56</td>\n",
+       "      <td>1.9</td>\n",
+       "      <td>0.075</td>\n",
+       "      <td>17.0</td>\n",
+       "      <td>60.0</td>\n",
+       "      <td>0.9980</td>\n",
+       "      <td>3.16</td>\n",
+       "      <td>0.58</td>\n",
+       "      <td>9.8</td>\n",
+       "      <td>6</td>\n",
+       "      <td>red</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>7.4</td>\n",
+       "      <td>0.70</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1.9</td>\n",
+       "      <td>0.076</td>\n",
+       "      <td>11.0</td>\n",
+       "      <td>34.0</td>\n",
+       "      <td>0.9978</td>\n",
+       "      <td>3.51</td>\n",
+       "      <td>0.56</td>\n",
+       "      <td>9.4</td>\n",
+       "      <td>5</td>\n",
+       "      <td>red</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   fixed acidity  volatile acidity  citric acid  residual sugar  chlorides  \\\n",
+       "0            7.4              0.70         0.00             1.9      0.076   \n",
+       "1            7.8              0.88         0.00             2.6      0.098   \n",
+       "2            7.8              0.76         0.04             2.3      0.092   \n",
+       "3           11.2              0.28         0.56             1.9      0.075   \n",
+       "4            7.4              0.70         0.00             1.9      0.076   \n",
+       "\n",
+       "   free sulfur dioxide  total sulfur dioxide  density    pH  sulphates  \\\n",
+       "0                 11.0                  34.0   0.9978  3.51       0.56   \n",
+       "1                 25.0                  67.0   0.9968  3.20       0.68   \n",
+       "2                 15.0                  54.0   0.9970  3.26       0.65   \n",
+       "3                 17.0                  60.0   0.9980  3.16       0.58   \n",
+       "4                 11.0                  34.0   0.9978  3.51       0.56   \n",
+       "\n",
+       "   alcohol  quality label  \n",
+       "0      9.4        5   red  \n",
+       "1      9.8        5   red  \n",
+       "2      9.8        5   red  \n",
+       "3      9.8        6   red  \n",
+       "4      9.4        5   red  "
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import os\n",
+    "newName=os.path.basename(csv_files[0]).lower().split(\".\")[0]\n",
+    "query=\"wine quality prediction\"\n",
+    "\n",
+    "words=set(query.lower().split())\n",
+    "\n",
+    "for word in words:\n",
+    "    if word in newName:\n",
+    "        newName=newName.replace(word,\"\")\n",
+    "\n",
+    "df['label']=newName\n",
+    "\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "8c258b22",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Date_reported</th>\n",
+       "      <th>Country_code</th>\n",
+       "      <th>Country</th>\n",
+       "      <th>WHO_region</th>\n",
+       "      <th>New_cases</th>\n",
+       "      <th>Cumulative_cases</th>\n",
+       "      <th>New_deaths</th>\n",
+       "      <th>Cumulative_deaths</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>2020-01-05</td>\n",
+       "      <td>AF</td>\n",
+       "      <td>Afghanistan</td>\n",
+       "      <td>EMRO</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2020-01-12</td>\n",
+       "      <td>AF</td>\n",
+       "      <td>Afghanistan</td>\n",
+       "      <td>EMRO</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2020-01-19</td>\n",
+       "      <td>AF</td>\n",
+       "      <td>Afghanistan</td>\n",
+       "      <td>EMRO</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2020-01-26</td>\n",
+       "      <td>AF</td>\n",
+       "      <td>Afghanistan</td>\n",
+       "      <td>EMRO</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2020-02-02</td>\n",
+       "      <td>AF</td>\n",
+       "      <td>Afghanistan</td>\n",
+       "      <td>EMRO</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  Date_reported Country_code      Country WHO_region  New_cases  \\\n",
+       "0    2020-01-05           AF  Afghanistan       EMRO        NaN   \n",
+       "1    2020-01-12           AF  Afghanistan       EMRO        NaN   \n",
+       "2    2020-01-19           AF  Afghanistan       EMRO        NaN   \n",
+       "3    2020-01-26           AF  Afghanistan       EMRO        NaN   \n",
+       "4    2020-02-02           AF  Afghanistan       EMRO        NaN   \n",
+       "\n",
+       "   Cumulative_cases  New_deaths  Cumulative_deaths  \n",
+       "0                 0         NaN                  0  \n",
+       "1                 0         NaN                  0  \n",
+       "2                 0         NaN                  0  \n",
+       "3                 0         NaN                  0  \n",
+       "4                 0         NaN                  0  "
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "df=pd.read_csv(\"final/covid 19.csv\")\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "6b43c357",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 54960 entries, 0 to 54959\n",
+      "Data columns (total 8 columns):\n",
+      " #   Column             Non-Null Count  Dtype  \n",
+      "---  ------             --------------  -----  \n",
+      " 0   Date_reported      54960 non-null  object \n",
+      " 1   Country_code       54731 non-null  object \n",
+      " 2   Country            54960 non-null  object \n",
+      " 3   WHO_region         50838 non-null  object \n",
+      " 4   New_cases          38082 non-null  float64\n",
+      " 5   Cumulative_cases   54960 non-null  int64  \n",
+      " 6   New_deaths         24747 non-null  float64\n",
+      " 7   Cumulative_deaths  54960 non-null  int64  \n",
+      "dtypes: float64(2), int64(2), object(4)\n",
+      "memory usage: 3.4+ MB\n"
+     ]
+    }
+   ],
+   "source": [
+    "df.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "ab7a92d8",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['Date_reported', 'Country_code', 'Country', 'WHO_region']"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "object_columns = df.dtypes[df.dtypes == 'object'].index.tolist()\n",
+    "object_columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "ae0b8edb",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "   New_cases  Cumulative_cases  New_deaths  Cumulative_deaths  \\\n",
+      "0        NaN                 0         NaN                  0   \n",
+      "1        NaN                 0         NaN                  0   \n",
+      "2        NaN                 0         NaN                  0   \n",
+      "3        NaN                 0         NaN                  0   \n",
+      "4        NaN                 0         NaN                  0   \n",
+      "\n",
+      "   Date_reported_2020-01-05  Date_reported_2020-01-12  \\\n",
+      "0                         1                         0   \n",
+      "1                         0                         1   \n",
+      "2                         0                         0   \n",
+      "3                         0                         0   \n",
+      "4                         0                         0   \n",
+      "\n",
+      "   Date_reported_2020-01-19  Date_reported_2020-01-26  \\\n",
+      "0                         0                         0   \n",
+      "1                         0                         0   \n",
+      "2                         1                         0   \n",
+      "3                         0                         1   \n",
+      "4                         0                         0   \n",
+      "\n",
+      "   Date_reported_2020-02-02  Date_reported_2020-02-09  ...  Country_Zambia  \\\n",
+      "0                         0                         0  ...               0   \n",
+      "1                         0                         0  ...               0   \n",
+      "2                         0                         0  ...               0   \n",
+      "3                         0                         0  ...               0   \n",
+      "4                         1                         0  ...               0   \n",
+      "\n",
+      "   Country_Zimbabwe  \\\n",
+      "0                 0   \n",
+      "1                 0   \n",
+      "2                 0   \n",
+      "3                 0   \n",
+      "4                 0   \n",
+      "\n",
+      "   Country_occupied Palestinian territory, including east Jerusalem  \\\n",
+      "0                                                  0                  \n",
+      "1                                                  0                  \n",
+      "2                                                  0                  \n",
+      "3                                                  0                  \n",
+      "4                                                  0                  \n",
+      "\n",
+      "   WHO_region_AFRO  WHO_region_AMRO  WHO_region_EMRO  WHO_region_EURO  \\\n",
+      "0                0                0                1                0   \n",
+      "1                0                0                1                0   \n",
+      "2                0                0                1                0   \n",
+      "3                0                0                1                0   \n",
+      "4                0                0                1                0   \n",
+      "\n",
+      "   WHO_region_OTHER  WHO_region_SEARO  WHO_region_WPRO  \n",
+      "0                 0                 0                0  \n",
+      "1                 0                 0                0  \n",
+      "2                 0                 0                0  \n",
+      "3                 0                 0                0  \n",
+      "4                 0                 0                0  \n",
+      "\n",
+      "[5 rows x 719 columns]\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "def one_hot_encode_objects(df):\n",
+    "    object_cols = df.select_dtypes(include='object').columns\n",
+    "\n",
+    "    for col in object_cols:\n",
+    "        if \"date\" in col:\n",
+    "            continue\n",
+    "\n",
+    "        # Perform one-hot encoding\n",
+    "        dummies = pd.get_dummies(df[col], prefix=col).astype(int)\n",
+    "        df = pd.concat([df, dummies], axis=1)\n",
+    "        \n",
+    "    df = df.drop(columns=object_cols)\n",
+    "    return df\n",
+    "\n",
+    "\n",
+    "def preprocessing(query):\n",
+    "    df=pd.read_csv(\"final/\"+query+\".csv\")\n",
+    "    # print(df.head())\n",
+    "    df=one_hot_encode_objects(df)\n",
+    "    print(df.head())\n",
+    "    \n",
+    "    \n",
+    "preprocessing(\"covid 19\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "f4ab7ad9",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Reduced file saved to: final/twitter sentiment analysis.csv\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "def reduce_csv_to_10_percent(file_path):\n",
+    "    # Read the original CSV\n",
+    "    df = pd.read_csv(file_path)\n",
+    "\n",
+    "    # Sample 10% of the rows\n",
+    "    reduced_df = df.sample(frac=0.1, random_state=42)\n",
+    "\n",
+    "    # Save back to the original file path, overwriting it\n",
+    "    reduced_df.to_csv(file_path, index=False)\n",
+    "    print(f\"Reduced file saved to: {file_path}\")\n",
+    "\n",
+    "# Example usage\n",
+    "reduce_csv_to_10_percent(\"final/twitter sentiment analysis.csv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5644317d",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

workflow.txt

@@ -0,0 +1,377 @@
+1. seprate attributes and data
+2. remove the datatypes from the attributes
+C:\Users\Niall Dcunha\DatasetCreator\house price prediction\21754539_dataset
+
+# import os
+# import glob
+# import pandas as pd
+# import openai
+# from openai import OpenAI
+# from dotenv import load_dotenv
+# import ast
+# import re
+
+# def extract_dict_from_response(response: str) -> dict:
+#     # Try extracting code block content containing the dictionary
+#     match = re.search(r"```(?:python)?\s*(\{.*?\})\s*```", response, re.DOTALL)
+#     if match:
+#         mapping_str = match.group(1)
+#     else:
+#         # Try extracting dictionary directly if it's not in code block
+#         match = re.search(r"(\{.*\})", response, re.DOTALL)
+#         if not match:
+#             raise ValueError("❌ Could not find a Python dictionary in the response.")
+#         mapping_str = match.group(1)
+    
+#     try:
+#         return ast.literal_eval(mapping_str)
+#     except Exception as e:
+#         print("⚠️ Failed to evaluate extracted dictionary string.")
+#         print("String:", mapping_str)
+#         raise e
+
+# # Load environment variables
+# load_dotenv()
+# client = OpenAI(
+#     api_key=os.getenv("OPENAI_API_KEY"),
+#     base_url=os.getenv("OPENAI_API_BASE")  # Optional: for Azure or self-hosted
+# )
+
+# def load_csv_files(folder_path):
+#     csv_files = glob.glob(os.path.join(folder_path, "*.csv"))
+#     dataframes = []
+#     column_sets = []
+#     valid_paths = []
+
+#     print("📥 Reading CSV files...")
+
+#     for file in csv_files:
+#         try:
+#             df = pd.read_csv(file)
+#             dataframes.append(df)
+#             column_sets.append(list(df.columns))
+#             valid_paths.append(file)
+#             print(f"✅ Loaded: {os.path.basename(file)}")
+#         except pd.errors.ParserError as e:
+#             print(f"❌ Skipping file due to parsing error: {os.path.basename(file)}")
+#             print(f"   ↳ {e}")
+#         except Exception as e:
+#             print(f"⚠️ Unexpected error with file {os.path.basename(file)}: {e}")
+
+#     return dataframes, column_sets, valid_paths
+
+# def generate_mapping_prompt(column_sets):
+#     prompt = (
+#         "You are a data scientist helping to merge multiple ML prediction datasets. "
+#         "Each CSV may have different or similar column names. I need a unified mapping to standardize these datasets. "
+#         "Also, please identify likely prediction label columns (e.g., price, quality, outcome).\n\n"
+#         "Here are the column headers from each CSV:\n"
+#     )
+#     for i, columns in enumerate(column_sets):
+#         prompt += f"CSV {i+1}: {columns}\n"
+#     prompt += (
+#         "\nPlease provide:\n"
+#         "1. A Python dictionary mapping similar columns across these CSVs.\n"
+#         "2. A list of columns most likely to represent prediction labels.\n\n"
+#         "Format your response as:\n"
+#         "```python\n"
+#         "column_mapping = { ... }\n"
+#         "label_columns = [ ... ]\n"
+#         "```"
+#     )
+#     return prompt
+
+# def get_column_mapping_from_openai(column_sets):
+#     prompt = generate_mapping_prompt(column_sets)
+
+#     response = client.chat.completions.create(
+#         model="gpt-4",
+#         messages=[
+#             {"role": "system", "content": "You are a helpful data scientist."},
+#             {"role": "user", "content": prompt}
+#         ],
+#         temperature=0.3
+#     )
+
+#     content = response.choices[0].message.content
+#     print("\n📩 Received response from OpenAI.")
+
+#     try:
+#         # Try parsing both dictionary and label list from the response
+#         column_mapping_match = re.search(r"column_mapping\s*=\s*(\{.*?\})", content, re.DOTALL)
+#         label_columns_match = re.search(r"label_columns\s*=\s*(\[.*?\])", content, re.DOTALL)
+
+#         if column_mapping_match:
+#             mapping = ast.literal_eval(column_mapping_match.group(1))
+#         else:
+#             raise ValueError("❌ Could not find `column_mapping` in the response.")
+
+#         if label_columns_match:
+#             label_columns = ast.literal_eval(label_columns_match.group(1))
+#         else:
+#             label_columns = []
+
+#     except Exception as e:
+#         print("⚠️ Error parsing OpenAI response:")
+#         print(content)
+#         raise e
+
+#     return mapping, label_columns
+
+# def standardize_columns(df, mapping):
+#     new_columns = {col: mapping.get(col, col) for col in df.columns}
+#     return df.rename(columns=new_columns)
+
+# def merge_csvs(folder_path, output_file="merged_dataset.csv"):
+#     dfs, column_sets, csv_paths = load_csv_files(folder_path)
+
+#     if not dfs:
+#         print("❌ No valid CSVs found to merge.")
+#         return
+
+#     print("\n🧠 Requesting column mapping from OpenAI...")
+#     mapping, label_columns = get_column_mapping_from_openai(column_sets)
+
+#     print("\n📌 Column Mapping:")
+#     for k, v in mapping.items():
+#         print(f"  '{k}' -> '{v}'")
+
+#     print("\n🏷️  Suggested Label Columns:")
+#     for label in label_columns:
+#         print(f"  - {label}")
+
+#     standardized_dfs = [standardize_columns(df, mapping) for df in dfs]
+#     merged_df = pd.concat(standardized_dfs, ignore_index=True, sort=False)
+
+#     merged_df.to_csv(output_file, index=False)
+#     print(f"\n✅ Merged dataset saved as '{output_file}'")
+
+# if __name__ == "__main__":
+#     folder_path = "house"
+
+
+import os
+import glob
+import pandas as pd
+import ast
+import re
+from itertools import combinations
+from rapidfuzz import fuzz, process
+from dotenv import load_dotenv
+from openai import OpenAI
+
+# Manual rename map to standardize some known variations
+manual_rename_map = {
+    "review": "text",
+    "text": "text",
+    "NumBedrooms": "bedrooms",
+    "HousePrice": "price",
+    "TARGET(PRICE_IN_LACS)": "price",
+    "SquareFootage": "area",
+    "SQUARE_FT": "area",
+    "sentiment": "label",
+    "target": "label",
+    "type": "label",
+    "variety": "label",
+    "class": "label",
+    "HeartDisease": "label",
+    "Heart Attack Risk (Binary)": "label",
+    "Heart Attack Risk": "label"
+}
+
+
+def normalize(col):
+    return re.sub(r'[^a-z0-9]', '', col.lower())
+
+def apply_manual_renaming(df, rename_map):
+    renamed = {}
+    for col in df.columns:
+        if col in rename_map:
+            renamed[col] = rename_map[col]
+    return df.rename(columns=renamed)
+
+def get_fuzzy_common_columns(cols_list, threshold=75):
+    base = cols_list[0]
+    common = set()
+    for col in base:
+        match_all = True
+        for other in cols_list[1:]:
+            match, score, _ = process.extractOne(col, other, scorer=fuzz.token_sort_ratio)
+            if score < threshold:
+                match_all = False
+                break
+        if match_all:
+            common.add(col)
+    return common
+
+def sortFiles(dfs):
+    unique_dfs = []
+    seen = []
+    for i, df1 in enumerate(dfs):
+        duplicate = False
+        for j in seen:
+            df2 = dfs[j]
+            if df1.shape != df2.shape:
+                continue
+            if df1.reset_index(drop=True).equals(df2.reset_index(drop=True)):
+                duplicate = True
+                break
+        if not duplicate:
+            unique_dfs.append(df1)
+            seen.append(i)
+    return unique_dfs
+
+def load_csv_files(folder_path):
+    csv_files = glob.glob(os.path.join(folder_path, "*.csv"))
+    dfs = []
+    column_sets = []
+    paths = []
+
+    for file in csv_files:
+        try:
+            df = pd.read_csv(file)
+            dfs.append(df)
+            column_sets.append(list(df.columns))
+            paths.append(file)
+            print(f"✅ Loaded: {os.path.basename(file)}")
+        except Exception as e:
+            print(f"❌ Failed to load {file}: {e}")
+    return dfs, column_sets, paths
+
+def generate_mapping_prompt(column_sets):
+    prompt = (
+    "You are a data scientist helping to merge multiple machine learning prediction datasets. "
+    "Each CSV file may have different column names, even if they represent similar types of data. "
+    "Your task is to identify and map these similar columns across datasets to a common, unified name. "
+    "Columns with clearly similar features (e.g., 'Bedrooms' and 'BedroomsAbvGr') should be merged into one column with a relevant name like 'bedrooms'.\n\n"
+    "Avoid keeping redundant or unique columns that do not have any logical counterpart in other datasets unless they are essential. "
+    "The goal is not to maximize the number of columns or rows, but to create a clean, consistent dataset for training ML models.\n\n"
+    "Examples:\n"
+    "- Dataset1: 'Locality' -> Mumbai, Delhi\n"
+    "- Dataset2: 'Places' -> Goa, Singapore\n"
+    "→ Merge both into a common column like 'location'.\n\n"
+    "Please also identify likely label or target columns that are typically used for prediction (e.g., price, sentiment, outcome, quality).\n\n"
+)
+
+    for i, cols in enumerate(column_sets):
+        prompt += f"CSV {i+1}: {cols}\n"
+    prompt += "\nPlease return:\n```python\ncolumn_mapping = { ... }\nlabel_columns = [ ... ]\n```"
+    return prompt
+
+def get_column_mapping_from_openai(column_sets):
+    load_dotenv()
+    client = OpenAI(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        base_url=os.getenv("OPENAI_API_BASE", "")
+    )
+
+    prompt = generate_mapping_prompt(column_sets)
+
+    response = client.chat.completions.create(
+        model="gpt-4",
+        messages=[
+            {"role": "system", "content": "You are a helpful data scientist."},
+            {"role": "user", "content": prompt}
+        ],
+        temperature=0.3
+    )
+
+    content = response.choices[0].message.content
+
+    try:
+        column_mapping_match = re.search(r"column_mapping\s*=\s*(\{.*?\})", content, re.DOTALL)
+        label_columns_match = re.search(r"label_columns\s*=\s*(\[.*?\])", content, re.DOTALL)
+        column_mapping = ast.literal_eval(column_mapping_match.group(1)) if column_mapping_match else {}
+        label_columns = ast.literal_eval(label_columns_match.group(1)) if label_columns_match else []
+    except Exception as e:
+        print("⚠️ Error parsing OpenAI response:")
+        print(content)
+        raise e
+
+    return column_mapping, label_columns
+
+def clean_and_merge(folder, query=None, use_ai=True):
+    os.makedirs("./final", exist_ok=True)
+    dfs, column_sets, csv_paths = load_csv_files(folder)
+
+    if not dfs:
+        print("No valid CSVs found.")
+        return
+
+    dfs = sortFiles(dfs)
+    dfs = [apply_manual_renaming(df, manual_rename_map) for df in dfs]
+
+    if use_ai:
+        try:
+            column_mapping, label_columns = get_column_mapping_from_openai(column_sets)
+            dfs = [df.rename(columns={col: column_mapping.get(col, col) for col in df.columns}) for df in dfs]
+        except Exception as e:
+            print("Falling back to fuzzy matching due to OpenAI error:", e)
+            use_ai = False
+
+    if not use_ai:
+        # Normalize columns for fuzzy match fallback
+        normalized_cols = []
+        for df in dfs:
+            normalized_cols.append({normalize(col) for col in df.columns})
+
+        # Get best combination with fuzzy common columns
+        max_common = set()
+        best_combo = []
+        for i in range(2, len(dfs)+1):
+            for combo in combinations(range(len(dfs)), i):
+                selected = [normalized_cols[j] for j in combo]
+                fuzzy_common = get_fuzzy_common_columns(selected)
+                if len(fuzzy_common) >= len(max_common):
+                    max_common = fuzzy_common
+                    best_combo = combo
+
+        # Harmonize and align
+        aligned_dfs = []
+        for idx in best_combo:
+            df = dfs[idx]
+            col_map = {}
+            for std_col in max_common:
+                match, _, _ = process.extractOne(std_col, [normalize(col) for col in df.columns])
+                for col in df.columns:
+                    if normalize(col) == match:
+                        col_map[col] = std_col
+                        break
+            df_subset = df[list(col_map.keys())].rename(columns=col_map)
+            aligned_dfs.append(df_subset)
+
+        combined_df = pd.concat(aligned_dfs, ignore_index=True)
+    else:
+        combined_df = pd.concat(dfs, ignore_index=True)
+
+    # Label assignment fallback
+    for i, df in enumerate(dfs):
+        if 'label' not in df.columns:
+            name = os.path.basename(csv_paths[i]).split(".")[0].lower()
+            name_cleaned = name
+            if query:
+                words = set(re.sub(r'[^a-z]', ' ', query.lower()).split())
+                for word in words:
+                    name_cleaned = name_cleaned.replace(word, "")
+            df['label'] = name_cleaned
+
+    # Decide best final file
+    largest_df = max(dfs, key=lambda df: len(df))
+    flag = False
+
+    if len(largest_df) > len(combined_df) and len(largest_df.columns) > 2:
+        flag = True
+    elif len(combined_df) > len(largest_df) and (len(largest_df.columns) - len(combined_df.columns)) > 3 and len(largest_df.columns) < 7:
+        flag = True
+
+    output_file = f"./final/{query or os.path.basename(folder)}.csv"
+    if flag:
+        largest_df.to_csv(output_file, index=False)
+        print(f"⚠️ Saved fallback single file due to poor merge: {output_file}")
+    else:
+        combined_df.to_csv(output_file, index=False)
+        print(f"✅ Saved merged file: {output_file}")
+
+# Example usage:
+clean_and_merge("house", query="house", use_ai=True)
+#     merge_csvs(folder_path)