├── .gitignore ├── LICENSE ├── README.md ├── data ├── .gitkeep └── ipea-20250319T124834Z-001.zip ├── dia01 ├── 01_hello_pandas.py ├── 02_series.py ├── 03_series_index.py └── 04_dataframes.py ├── dia02 ├── 01_csv.py ├── 02_clipboard.py ├── 03_html.py ├── 04_dataframes.py └── 05_colunas.py ├── dia03 ├── 01_filtro.py ├── 02_mais_filtros.py └── 03_filtros_view.py ├── dia04 ├── 01_novas_colunas.py └── 02_sort.py ├── dia05 ├── 01_conv_tipo.py ├── 02_na.py └── 03_duplicatas.py ├── dia06 ├── 01_apply.py └── 02_ufs.py ├── dia07 ├── 01_summary.py ├── 02_group.py └── 03_custom_group.py ├── dia08 ├── 01_merge.py └── 02_concat.py ├── dia09 ├── 01_db.py ├── 02_etl.py ├── etl.sql ├── pandas_sql.drawio └── pandas_sql.png └── exercicios ├── 02 └── 01.py ├── 03 └── exercicios.py ├── 04 ├── drop_duplicates.py └── exercicios.py ├── 05 └── exercicios.py ├── 06 ├── 01.py ├── 02.py ├── 03.py ├── 04.py ├── 05.py └── 06.py ├── case_cartao_credito └── cartao.py └── case_homicidios ├── 01_case.py ├── 02_stack_unstack.py └── 03_pivot.py /.gitignore: -------------------------------------------------------------------------------- 1 | *.csv 2 | *.xlsx 3 | *parquet 4 | *.db -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | GNU GENERAL PUBLIC LICENSE 2 | Version 3, 29 June 2007 3 | 4 | Copyright (C) 2007 Free Software Foundation, Inc. 5 | Everyone is permitted to copy and distribute verbatim copies 6 | of this license document, but changing it is not allowed. 7 | 8 | Preamble 9 | 10 | The GNU General Public License is a free, copyleft license for 11 | software and other kinds of works. 12 | 13 | The licenses for most software and other practical works are designed 14 | to take away your freedom to share and change the works. By contrast, 15 | the GNU General Public License is intended to guarantee your freedom to 16 | share and change all versions of a program--to make sure it remains free 17 | software for all its users. We, the Free Software Foundation, use the 18 | GNU General Public License for most of our software; it applies also to 19 | any other work released this way by its authors. You can apply it to 20 | your programs, too. 21 | 22 | When we speak of free software, we are referring to freedom, not 23 | price. Our General Public Licenses are designed to make sure that you 24 | have the freedom to distribute copies of free software (and charge for 25 | them if you wish), that you receive source code or can get it if you 26 | want it, that you can change the software or use pieces of it in new 27 | free programs, and that you know you can do these things. 28 | 29 | To protect your rights, we need to prevent others from denying you 30 | these rights or asking you to surrender the rights. Therefore, you have 31 | certain responsibilities if you distribute copies of the software, or if 32 | you modify it: responsibilities to respect the freedom of others. 33 | 34 | For example, if you distribute copies of such a program, whether 35 | gratis or for a fee, you must pass on to the recipients the same 36 | freedoms that you received. You must make sure that they, too, receive 37 | or can get the source code. And you must show them these terms so they 38 | know their rights. 39 | 40 | Developers that use the GNU GPL protect your rights with two steps: 41 | (1) assert copyright on the software, and (2) offer you this License 42 | giving you legal permission to copy, distribute and/or modify it. 43 | 44 | For the developers' and authors' protection, the GPL clearly explains 45 | that there is no warranty for this free software. For both users' and 46 | authors' sake, the GPL requires that modified versions be marked as 47 | changed, so that their problems will not be attributed erroneously to 48 | authors of previous versions. 49 | 50 | Some devices are designed to deny users access to install or run 51 | modified versions of the software inside them, although the manufacturer 52 | can do so. This is fundamentally incompatible with the aim of 53 | protecting users' freedom to change the software. The systematic 54 | pattern of such abuse occurs in the area of products for individuals to 55 | use, which is precisely where it is most unacceptable. Therefore, we 56 | have designed this version of the GPL to prohibit the practice for those 57 | products. If such problems arise substantially in other domains, we 58 | stand ready to extend this provision to those domains in future versions 59 | of the GPL, as needed to protect the freedom of users. 60 | 61 | Finally, every program is threatened constantly by software patents. 62 | States should not allow patents to restrict development and use of 63 | software on general-purpose computers, but in those that do, we wish to 64 | avoid the special danger that patents applied to a free program could 65 | make it effectively proprietary. To prevent this, the GPL assures that 66 | patents cannot be used to render the program non-free. 67 | 68 | The precise terms and conditions for copying, distribution and 69 | modification follow. 70 | 71 | TERMS AND CONDITIONS 72 | 73 | 0. Definitions. 74 | 75 | "This License" refers to version 3 of the GNU General Public License. 76 | 77 | "Copyright" also means copyright-like laws that apply to other kinds of 78 | works, such as semiconductor masks. 79 | 80 | "The Program" refers to any copyrightable work licensed under this 81 | License. Each licensee is addressed as "you". "Licensees" and 82 | "recipients" may be individuals or organizations. 83 | 84 | To "modify" a work means to copy from or adapt all or part of the work 85 | in a fashion requiring copyright permission, other than the making of an 86 | exact copy. The resulting work is called a "modified version" of the 87 | earlier work or a work "based on" the earlier work. 88 | 89 | A "covered work" means either the unmodified Program or a work based 90 | on the Program. 91 | 92 | To "propagate" a work means to do anything with it that, without 93 | permission, would make you directly or secondarily liable for 94 | infringement under applicable copyright law, except executing it on a 95 | computer or modifying a private copy. Propagation includes copying, 96 | distribution (with or without modification), making available to the 97 | public, and in some countries other activities as well. 98 | 99 | To "convey" a work means any kind of propagation that enables other 100 | parties to make or receive copies. Mere interaction with a user through 101 | a computer network, with no transfer of a copy, is not conveying. 102 | 103 | An interactive user interface displays "Appropriate Legal Notices" 104 | to the extent that it includes a convenient and prominently visible 105 | feature that (1) displays an appropriate copyright notice, and (2) 106 | tells the user that there is no warranty for the work (except to the 107 | extent that warranties are provided), that licensees may convey the 108 | work under this License, and how to view a copy of this License. If 109 | the interface presents a list of user commands or options, such as a 110 | menu, a prominent item in the list meets this criterion. 111 | 112 | 1. Source Code. 113 | 114 | The "source code" for a work means the preferred form of the work 115 | for making modifications to it. "Object code" means any non-source 116 | form of a work. 117 | 118 | A "Standard Interface" means an interface that either is an official 119 | standard defined by a recognized standards body, or, in the case of 120 | interfaces specified for a particular programming language, one that 121 | is widely used among developers working in that language. 122 | 123 | The "System Libraries" of an executable work include anything, other 124 | than the work as a whole, that (a) is included in the normal form of 125 | packaging a Major Component, but which is not part of that Major 126 | Component, and (b) serves only to enable use of the work with that 127 | Major Component, or to implement a Standard Interface for which an 128 | implementation is available to the public in source code form. A 129 | "Major Component", in this context, means a major essential component 130 | (kernel, window system, and so on) of the specific operating system 131 | (if any) on which the executable work runs, or a compiler used to 132 | produce the work, or an object code interpreter used to run it. 133 | 134 | The "Corresponding Source" for a work in object code form means all 135 | the source code needed to generate, install, and (for an executable 136 | work) run the object code and to modify the work, including scripts to 137 | control those activities. However, it does not include the work's 138 | System Libraries, or general-purpose tools or generally available free 139 | programs which are used unmodified in performing those activities but 140 | which are not part of the work. For example, Corresponding Source 141 | includes interface definition files associated with source files for 142 | the work, and the source code for shared libraries and dynamically 143 | linked subprograms that the work is specifically designed to require, 144 | such as by intimate data communication or control flow between those 145 | subprograms and other parts of the work. 146 | 147 | The Corresponding Source need not include anything that users 148 | can regenerate automatically from other parts of the Corresponding 149 | Source. 150 | 151 | The Corresponding Source for a work in source code form is that 152 | same work. 153 | 154 | 2. Basic Permissions. 155 | 156 | All rights granted under this License are granted for the term of 157 | copyright on the Program, and are irrevocable provided the stated 158 | conditions are met. This License explicitly affirms your unlimited 159 | permission to run the unmodified Program. The output from running a 160 | covered work is covered by this License only if the output, given its 161 | content, constitutes a covered work. This License acknowledges your 162 | rights of fair use or other equivalent, as provided by copyright law. 163 | 164 | You may make, run and propagate covered works that you do not 165 | convey, without conditions so long as your license otherwise remains 166 | in force. You may convey covered works to others for the sole purpose 167 | of having them make modifications exclusively for you, or provide you 168 | with facilities for running those works, provided that you comply with 169 | the terms of this License in conveying all material for which you do 170 | not control copyright. Those thus making or running the covered works 171 | for you must do so exclusively on your behalf, under your direction 172 | and control, on terms that prohibit them from making any copies of 173 | your copyrighted material outside their relationship with you. 174 | 175 | Conveying under any other circumstances is permitted solely under 176 | the conditions stated below. Sublicensing is not allowed; section 10 177 | makes it unnecessary. 178 | 179 | 3. Protecting Users' Legal Rights From Anti-Circumvention Law. 180 | 181 | No covered work shall be deemed part of an effective technological 182 | measure under any applicable law fulfilling obligations under article 183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or 184 | similar laws prohibiting or restricting circumvention of such 185 | measures. 186 | 187 | When you convey a covered work, you waive any legal power to forbid 188 | circumvention of technological measures to the extent such circumvention 189 | is effected by exercising rights under this License with respect to 190 | the covered work, and you disclaim any intention to limit operation or 191 | modification of the work as a means of enforcing, against the work's 192 | users, your or third parties' legal rights to forbid circumvention of 193 | technological measures. 194 | 195 | 4. Conveying Verbatim Copies. 196 | 197 | You may convey verbatim copies of the Program's source code as you 198 | receive it, in any medium, provided that you conspicuously and 199 | appropriately publish on each copy an appropriate copyright notice; 200 | keep intact all notices stating that this License and any 201 | non-permissive terms added in accord with section 7 apply to the code; 202 | keep intact all notices of the absence of any warranty; and give all 203 | recipients a copy of this License along with the Program. 204 | 205 | You may charge any price or no price for each copy that you convey, 206 | and you may offer support or warranty protection for a fee. 207 | 208 | 5. Conveying Modified Source Versions. 209 | 210 | You may convey a work based on the Program, or the modifications to 211 | produce it from the Program, in the form of source code under the 212 | terms of section 4, provided that you also meet all of these conditions: 213 | 214 | a) The work must carry prominent notices stating that you modified 215 | it, and giving a relevant date. 216 | 217 | b) The work must carry prominent notices stating that it is 218 | released under this License and any conditions added under section 219 | 7. This requirement modifies the requirement in section 4 to 220 | "keep intact all notices". 221 | 222 | c) You must license the entire work, as a whole, under this 223 | License to anyone who comes into possession of a copy. This 224 | License will therefore apply, along with any applicable section 7 225 | additional terms, to the whole of the work, and all its parts, 226 | regardless of how they are packaged. This License gives no 227 | permission to license the work in any other way, but it does not 228 | invalidate such permission if you have separately received it. 229 | 230 | d) If the work has interactive user interfaces, each must display 231 | Appropriate Legal Notices; however, if the Program has interactive 232 | interfaces that do not display Appropriate Legal Notices, your 233 | work need not make them do so. 234 | 235 | A compilation of a covered work with other separate and independent 236 | works, which are not by their nature extensions of the covered work, 237 | and which are not combined with it such as to form a larger program, 238 | in or on a volume of a storage or distribution medium, is called an 239 | "aggregate" if the compilation and its resulting copyright are not 240 | used to limit the access or legal rights of the compilation's users 241 | beyond what the individual works permit. Inclusion of a covered work 242 | in an aggregate does not cause this License to apply to the other 243 | parts of the aggregate. 244 | 245 | 6. Conveying Non-Source Forms. 246 | 247 | You may convey a covered work in object code form under the terms 248 | of sections 4 and 5, provided that you also convey the 249 | machine-readable Corresponding Source under the terms of this License, 250 | in one of these ways: 251 | 252 | a) Convey the object code in, or embodied in, a physical product 253 | (including a physical distribution medium), accompanied by the 254 | Corresponding Source fixed on a durable physical medium 255 | customarily used for software interchange. 256 | 257 | b) Convey the object code in, or embodied in, a physical product 258 | (including a physical distribution medium), accompanied by a 259 | written offer, valid for at least three years and valid for as 260 | long as you offer spare parts or customer support for that product 261 | model, to give anyone who possesses the object code either (1) a 262 | copy of the Corresponding Source for all the software in the 263 | product that is covered by this License, on a durable physical 264 | medium customarily used for software interchange, for a price no 265 | more than your reasonable cost of physically performing this 266 | conveying of source, or (2) access to copy the 267 | Corresponding Source from a network server at no charge. 268 | 269 | c) Convey individual copies of the object code with a copy of the 270 | written offer to provide the Corresponding Source. This 271 | alternative is allowed only occasionally and noncommercially, and 272 | only if you received the object code with such an offer, in accord 273 | with subsection 6b. 274 | 275 | d) Convey the object code by offering access from a designated 276 | place (gratis or for a charge), and offer equivalent access to the 277 | Corresponding Source in the same way through the same place at no 278 | further charge. You need not require recipients to copy the 279 | Corresponding Source along with the object code. If the place to 280 | copy the object code is a network server, the Corresponding Source 281 | may be on a different server (operated by you or a third party) 282 | that supports equivalent copying facilities, provided you maintain 283 | clear directions next to the object code saying where to find the 284 | Corresponding Source. Regardless of what server hosts the 285 | Corresponding Source, you remain obligated to ensure that it is 286 | available for as long as needed to satisfy these requirements. 287 | 288 | e) Convey the object code using peer-to-peer transmission, provided 289 | you inform other peers where the object code and Corresponding 290 | Source of the work are being offered to the general public at no 291 | charge under subsection 6d. 292 | 293 | A separable portion of the object code, whose source code is excluded 294 | from the Corresponding Source as a System Library, need not be 295 | included in conveying the object code work. 296 | 297 | A "User Product" is either (1) a "consumer product", which means any 298 | tangible personal property which is normally used for personal, family, 299 | or household purposes, or (2) anything designed or sold for incorporation 300 | into a dwelling. In determining whether a product is a consumer product, 301 | doubtful cases shall be resolved in favor of coverage. For a particular 302 | product received by a particular user, "normally used" refers to a 303 | typical or common use of that class of product, regardless of the status 304 | of the particular user or of the way in which the particular user 305 | actually uses, or expects or is expected to use, the product. A product 306 | is a consumer product regardless of whether the product has substantial 307 | commercial, industrial or non-consumer uses, unless such uses represent 308 | the only significant mode of use of the product. 309 | 310 | "Installation Information" for a User Product means any methods, 311 | procedures, authorization keys, or other information required to install 312 | and execute modified versions of a covered work in that User Product from 313 | a modified version of its Corresponding Source. The information must 314 | suffice to ensure that the continued functioning of the modified object 315 | code is in no case prevented or interfered with solely because 316 | modification has been made. 317 | 318 | If you convey an object code work under this section in, or with, or 319 | specifically for use in, a User Product, and the conveying occurs as 320 | part of a transaction in which the right of possession and use of the 321 | User Product is transferred to the recipient in perpetuity or for a 322 | fixed term (regardless of how the transaction is characterized), the 323 | Corresponding Source conveyed under this section must be accompanied 324 | by the Installation Information. But this requirement does not apply 325 | if neither you nor any third party retains the ability to install 326 | modified object code on the User Product (for example, the work has 327 | been installed in ROM). 328 | 329 | The requirement to provide Installation Information does not include a 330 | requirement to continue to provide support service, warranty, or updates 331 | for a work that has been modified or installed by the recipient, or for 332 | the User Product in which it has been modified or installed. Access to a 333 | network may be denied when the modification itself materially and 334 | adversely affects the operation of the network or violates the rules and 335 | protocols for communication across the network. 336 | 337 | Corresponding Source conveyed, and Installation Information provided, 338 | in accord with this section must be in a format that is publicly 339 | documented (and with an implementation available to the public in 340 | source code form), and must require no special password or key for 341 | unpacking, reading or copying. 342 | 343 | 7. Additional Terms. 344 | 345 | "Additional permissions" are terms that supplement the terms of this 346 | License by making exceptions from one or more of its conditions. 347 | Additional permissions that are applicable to the entire Program shall 348 | be treated as though they were included in this License, to the extent 349 | that they are valid under applicable law. If additional permissions 350 | apply only to part of the Program, that part may be used separately 351 | under those permissions, but the entire Program remains governed by 352 | this License without regard to the additional permissions. 353 | 354 | When you convey a copy of a covered work, you may at your option 355 | remove any additional permissions from that copy, or from any part of 356 | it. (Additional permissions may be written to require their own 357 | removal in certain cases when you modify the work.) You may place 358 | additional permissions on material, added by you to a covered work, 359 | for which you have or can give appropriate copyright permission. 360 | 361 | Notwithstanding any other provision of this License, for material you 362 | add to a covered work, you may (if authorized by the copyright holders of 363 | that material) supplement the terms of this License with terms: 364 | 365 | a) Disclaiming warranty or limiting liability differently from the 366 | terms of sections 15 and 16 of this License; or 367 | 368 | b) Requiring preservation of specified reasonable legal notices or 369 | author attributions in that material or in the Appropriate Legal 370 | Notices displayed by works containing it; or 371 | 372 | c) Prohibiting misrepresentation of the origin of that material, or 373 | requiring that modified versions of such material be marked in 374 | reasonable ways as different from the original version; or 375 | 376 | d) Limiting the use for publicity purposes of names of licensors or 377 | authors of the material; or 378 | 379 | e) Declining to grant rights under trademark law for use of some 380 | trade names, trademarks, or service marks; or 381 | 382 | f) Requiring indemnification of licensors and authors of that 383 | material by anyone who conveys the material (or modified versions of 384 | it) with contractual assumptions of liability to the recipient, for 385 | any liability that these contractual assumptions directly impose on 386 | those licensors and authors. 387 | 388 | All other non-permissive additional terms are considered "further 389 | restrictions" within the meaning of section 10. If the Program as you 390 | received it, or any part of it, contains a notice stating that it is 391 | governed by this License along with a term that is a further 392 | restriction, you may remove that term. If a license document contains 393 | a further restriction but permits relicensing or conveying under this 394 | License, you may add to a covered work material governed by the terms 395 | of that license document, provided that the further restriction does 396 | not survive such relicensing or conveying. 397 | 398 | If you add terms to a covered work in accord with this section, you 399 | must place, in the relevant source files, a statement of the 400 | additional terms that apply to those files, or a notice indicating 401 | where to find the applicable terms. 402 | 403 | Additional terms, permissive or non-permissive, may be stated in the 404 | form of a separately written license, or stated as exceptions; 405 | the above requirements apply either way. 406 | 407 | 8. Termination. 408 | 409 | You may not propagate or modify a covered work except as expressly 410 | provided under this License. Any attempt otherwise to propagate or 411 | modify it is void, and will automatically terminate your rights under 412 | this License (including any patent licenses granted under the third 413 | paragraph of section 11). 414 | 415 | However, if you cease all violation of this License, then your 416 | license from a particular copyright holder is reinstated (a) 417 | provisionally, unless and until the copyright holder explicitly and 418 | finally terminates your license, and (b) permanently, if the copyright 419 | holder fails to notify you of the violation by some reasonable means 420 | prior to 60 days after the cessation. 421 | 422 | Moreover, your license from a particular copyright holder is 423 | reinstated permanently if the copyright holder notifies you of the 424 | violation by some reasonable means, this is the first time you have 425 | received notice of violation of this License (for any work) from that 426 | copyright holder, and you cure the violation prior to 30 days after 427 | your receipt of the notice. 428 | 429 | Termination of your rights under this section does not terminate the 430 | licenses of parties who have received copies or rights from you under 431 | this License. If your rights have been terminated and not permanently 432 | reinstated, you do not qualify to receive new licenses for the same 433 | material under section 10. 434 | 435 | 9. Acceptance Not Required for Having Copies. 436 | 437 | You are not required to accept this License in order to receive or 438 | run a copy of the Program. Ancillary propagation of a covered work 439 | occurring solely as a consequence of using peer-to-peer transmission 440 | to receive a copy likewise does not require acceptance. However, 441 | nothing other than this License grants you permission to propagate or 442 | modify any covered work. These actions infringe copyright if you do 443 | not accept this License. Therefore, by modifying or propagating a 444 | covered work, you indicate your acceptance of this License to do so. 445 | 446 | 10. Automatic Licensing of Downstream Recipients. 447 | 448 | Each time you convey a covered work, the recipient automatically 449 | receives a license from the original licensors, to run, modify and 450 | propagate that work, subject to this License. You are not responsible 451 | for enforcing compliance by third parties with this License. 452 | 453 | An "entity transaction" is a transaction transferring control of an 454 | organization, or substantially all assets of one, or subdividing an 455 | organization, or merging organizations. If propagation of a covered 456 | work results from an entity transaction, each party to that 457 | transaction who receives a copy of the work also receives whatever 458 | licenses to the work the party's predecessor in interest had or could 459 | give under the previous paragraph, plus a right to possession of the 460 | Corresponding Source of the work from the predecessor in interest, if 461 | the predecessor has it or can get it with reasonable efforts. 462 | 463 | You may not impose any further restrictions on the exercise of the 464 | rights granted or affirmed under this License. For example, you may 465 | not impose a license fee, royalty, or other charge for exercise of 466 | rights granted under this License, and you may not initiate litigation 467 | (including a cross-claim or counterclaim in a lawsuit) alleging that 468 | any patent claim is infringed by making, using, selling, offering for 469 | sale, or importing the Program or any portion of it. 470 | 471 | 11. Patents. 472 | 473 | A "contributor" is a copyright holder who authorizes use under this 474 | License of the Program or a work on which the Program is based. The 475 | work thus licensed is called the contributor's "contributor version". 476 | 477 | A contributor's "essential patent claims" are all patent claims 478 | owned or controlled by the contributor, whether already acquired or 479 | hereafter acquired, that would be infringed by some manner, permitted 480 | by this License, of making, using, or selling its contributor version, 481 | but do not include claims that would be infringed only as a 482 | consequence of further modification of the contributor version. For 483 | purposes of this definition, "control" includes the right to grant 484 | patent sublicenses in a manner consistent with the requirements of 485 | this License. 486 | 487 | Each contributor grants you a non-exclusive, worldwide, royalty-free 488 | patent license under the contributor's essential patent claims, to 489 | make, use, sell, offer for sale, import and otherwise run, modify and 490 | propagate the contents of its contributor version. 491 | 492 | In the following three paragraphs, a "patent license" is any express 493 | agreement or commitment, however denominated, not to enforce a patent 494 | (such as an express permission to practice a patent or covenant not to 495 | sue for patent infringement). To "grant" such a patent license to a 496 | party means to make such an agreement or commitment not to enforce a 497 | patent against the party. 498 | 499 | If you convey a covered work, knowingly relying on a patent license, 500 | and the Corresponding Source of the work is not available for anyone 501 | to copy, free of charge and under the terms of this License, through a 502 | publicly available network server or other readily accessible means, 503 | then you must either (1) cause the Corresponding Source to be so 504 | available, or (2) arrange to deprive yourself of the benefit of the 505 | patent license for this particular work, or (3) arrange, in a manner 506 | consistent with the requirements of this License, to extend the patent 507 | license to downstream recipients. "Knowingly relying" means you have 508 | actual knowledge that, but for the patent license, your conveying the 509 | covered work in a country, or your recipient's use of the covered work 510 | in a country, would infringe one or more identifiable patents in that 511 | country that you have reason to believe are valid. 512 | 513 | If, pursuant to or in connection with a single transaction or 514 | arrangement, you convey, or propagate by procuring conveyance of, a 515 | covered work, and grant a patent license to some of the parties 516 | receiving the covered work authorizing them to use, propagate, modify 517 | or convey a specific copy of the covered work, then the patent license 518 | you grant is automatically extended to all recipients of the covered 519 | work and works based on it. 520 | 521 | A patent license is "discriminatory" if it does not include within 522 | the scope of its coverage, prohibits the exercise of, or is 523 | conditioned on the non-exercise of one or more of the rights that are 524 | specifically granted under this License. You may not convey a covered 525 | work if you are a party to an arrangement with a third party that is 526 | in the business of distributing software, under which you make payment 527 | to the third party based on the extent of your activity of conveying 528 | the work, and under which the third party grants, to any of the 529 | parties who would receive the covered work from you, a discriminatory 530 | patent license (a) in connection with copies of the covered work 531 | conveyed by you (or copies made from those copies), or (b) primarily 532 | for and in connection with specific products or compilations that 533 | contain the covered work, unless you entered into that arrangement, 534 | or that patent license was granted, prior to 28 March 2007. 535 | 536 | Nothing in this License shall be construed as excluding or limiting 537 | any implied license or other defenses to infringement that may 538 | otherwise be available to you under applicable patent law. 539 | 540 | 12. No Surrender of Others' Freedom. 541 | 542 | If conditions are imposed on you (whether by court order, agreement or 543 | otherwise) that contradict the conditions of this License, they do not 544 | excuse you from the conditions of this License. If you cannot convey a 545 | covered work so as to satisfy simultaneously your obligations under this 546 | License and any other pertinent obligations, then as a consequence you may 547 | not convey it at all. For example, if you agree to terms that obligate you 548 | to collect a royalty for further conveying from those to whom you convey 549 | the Program, the only way you could satisfy both those terms and this 550 | License would be to refrain entirely from conveying the Program. 551 | 552 | 13. Use with the GNU Affero General Public License. 553 | 554 | Notwithstanding any other provision of this License, you have 555 | permission to link or combine any covered work with a work licensed 556 | under version 3 of the GNU Affero General Public License into a single 557 | combined work, and to convey the resulting work. The terms of this 558 | License will continue to apply to the part which is the covered work, 559 | but the special requirements of the GNU Affero General Public License, 560 | section 13, concerning interaction through a network will apply to the 561 | combination as such. 562 | 563 | 14. Revised Versions of this License. 564 | 565 | The Free Software Foundation may publish revised and/or new versions of 566 | the GNU General Public License from time to time. Such new versions will 567 | be similar in spirit to the present version, but may differ in detail to 568 | address new problems or concerns. 569 | 570 | Each version is given a distinguishing version number. If the 571 | Program specifies that a certain numbered version of the GNU General 572 | Public License "or any later version" applies to it, you have the 573 | option of following the terms and conditions either of that numbered 574 | version or of any later version published by the Free Software 575 | Foundation. If the Program does not specify a version number of the 576 | GNU General Public License, you may choose any version ever published 577 | by the Free Software Foundation. 578 | 579 | If the Program specifies that a proxy can decide which future 580 | versions of the GNU General Public License can be used, that proxy's 581 | public statement of acceptance of a version permanently authorizes you 582 | to choose that version for the Program. 583 | 584 | Later license versions may give you additional or different 585 | permissions. However, no additional obligations are imposed on any 586 | author or copyright holder as a result of your choosing to follow a 587 | later version. 588 | 589 | 15. Disclaimer of Warranty. 590 | 591 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY 592 | APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT 593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY 594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, 595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 596 | PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM 597 | IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF 598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 599 | 600 | 16. Limitation of Liability. 601 | 602 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING 603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS 604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY 605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE 606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF 607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD 608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), 609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF 610 | SUCH DAMAGES. 611 | 612 | 17. Interpretation of Sections 15 and 16. 613 | 614 | If the disclaimer of warranty and limitation of liability provided 615 | above cannot be given local legal effect according to their terms, 616 | reviewing courts shall apply local law that most closely approximates 617 | an absolute waiver of all civil liability in connection with the 618 | Program, unless a warranty or assumption of liability accompanies a 619 | copy of the Program in return for a fee. 620 | 621 | END OF TERMS AND CONDITIONS 622 | 623 | How to Apply These Terms to Your New Programs 624 | 625 | If you develop a new program, and you want it to be of the greatest 626 | possible use to the public, the best way to achieve this is to make it 627 | free software which everyone can redistribute and change under these terms. 628 | 629 | To do so, attach the following notices to the program. It is safest 630 | to attach them to the start of each source file to most effectively 631 | state the exclusion of warranty; and each file should have at least 632 | the "copyright" line and a pointer to where the full notice is found. 633 | 634 | 635 | Copyright (C) 636 | 637 | This program is free software: you can redistribute it and/or modify 638 | it under the terms of the GNU General Public License as published by 639 | the Free Software Foundation, either version 3 of the License, or 640 | (at your option) any later version. 641 | 642 | This program is distributed in the hope that it will be useful, 643 | but WITHOUT ANY WARRANTY; without even the implied warranty of 644 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 645 | GNU General Public License for more details. 646 | 647 | You should have received a copy of the GNU General Public License 648 | along with this program. If not, see . 649 | 650 | Also add information on how to contact you by electronic and paper mail. 651 | 652 | If the program does terminal interaction, make it output a short 653 | notice like this when it starts in an interactive mode: 654 | 655 | Copyright (C) 656 | This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. 657 | This is free software, and you are welcome to redistribute it 658 | under certain conditions; type `show c' for details. 659 | 660 | The hypothetical commands `show w' and `show c' should show the appropriate 661 | parts of the General Public License. Of course, your program's commands 662 | might be different; for a GUI interface, you would use an "about box". 663 | 664 | You should also get your employer (if you work as a programmer) or school, 665 | if any, to sign a "copyright disclaimer" for the program, if necessary. 666 | For more information on this, and how to apply and follow the GNU GPL, see 667 | . 668 | 669 | The GNU General Public License does not permit incorporating your program 670 | into proprietary programs. If your program is a subroutine library, you 671 | may consider it more useful to permit linking proprietary applications with 672 | the library. If this is what you want to do, use the GNU Lesser General 673 | Public License instead of this License. But first, please read 674 | . 675 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Pandas 2025 2 | 3 | Curso renovado de Pandas realizado ao vivo de form gratuita, com gravação disponível no [YouTube](youtube.com/@teomewhy). 4 | 5 | ## Pré-requisito 6 | 7 | - Ter Python instalado. Sugestão de vídeo para instalação, [clique aqui](https://youtu.be/OeKzVjiiRm4?si=PT0v4LwNE9SUL-2m). 8 | - Python Básico: sintaxe da linguagem e lógica de programação. [Conheça mais aqui](https://www.youtube.com/playlist?list=PLvlkVRRKOYFSpRkqnR0p2A-eaVlpLnN3D). 9 | 10 | ## Material de apoio 11 | 12 | Temos um material de apoio para nosso treinamento, contendo algumas orientações e exercícios. [Confira aqui](https://docs.google.com/presentation/d/10_lCOieWozst3t2ldGaY78vxh4mOGkplHqXBQ7M3eDo/edit?usp=sharing). 13 | 14 | ## Dados 15 | 16 | Utilizaremos dados reais durante o nosso curso. Acesse os [dados aqui](https://www.kaggle.com/datasets/teocalvo/teomewhy-loyalty-system). 17 | 18 | ## Ementa 19 | 20 | 1. Principais objetos do Pandas 21 | - Series 22 | - Dataframes 23 | 24 | 2. Importando arquivos com pandas 25 | - csv; xlsx; parquet 26 | 27 | 3. Navegando pelos dados: 28 | - Informações básicas 29 | - Tipos de colunas 30 | - Navegação em linhas e colunas 31 | - Renomeando colunas 32 | 33 | 4. Filtrando dados 34 | - Condições lógicas 35 | 36 | 5. Transformações e remoções 37 | - Criação de novas colunas 38 | - Ordenação 39 | - Conversão de tipos 40 | - Aplicando funções em linhas e colunas 41 | - Removendo Duplicatas 42 | - Trabalhando com NAs 43 | 44 | 6. GroupBy 45 | - Agregando dados 46 | - O método agg 47 | - Agregações personalizadas 48 | 49 | 7. Cruzamento de dados 50 | - Merge 51 | - Concat 52 | 53 | 8. Manipulações adicionais 54 | - Stack 55 | - Unstack 56 | - Pivot Table 57 | - Explode 58 | 59 | 9. Conectando com Bancos SQL 60 | - Importando dados 61 | - Executando Queries 62 | - Escrevendo dados 63 | 64 | 65 | -------------------------------------------------------------------------------- /data/.gitkeep: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TeoMeWhy/pandas-2025/1f56a6f461ca014c36acdab69832e19e25216f30/data/.gitkeep -------------------------------------------------------------------------------- /data/ipea-20250319T124834Z-001.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TeoMeWhy/pandas-2025/1f56a6f461ca014c36acdab69832e19e25216f30/data/ipea-20250319T124834Z-001.zip -------------------------------------------------------------------------------- /dia01/01_hello_pandas.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | 5 | # %% 6 | 7 | pd.Series() -------------------------------------------------------------------------------- /dia01/02_series.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | idades = [ 4 | 32, 38, 30, 30, 31, 5 | 35, 25, 29, 31, 37, 6 | 27, 23, 36, 33, 32, 7 | ] 8 | 9 | media = sum(idades) / len(idades) 10 | print("Media:",media) 11 | 12 | diffs = 0 13 | for i in idades: 14 | diffs += (i - media) ** 2 15 | 16 | variancia = diffs / (len(idades)-1) 17 | 18 | print("Variância:", variancia) 19 | 20 | # %% 21 | 22 | import pandas as pd 23 | 24 | idades = [ 25 | 32, 38, 30, 30, 31, 26 | 35, 25, 29, 31, 37, 27 | 27, 23, 36, 33, 32, 28 | ] 29 | 30 | series_idades = pd.Series(idades) 31 | series_idades 32 | 33 | # %% 34 | # Estatísticas da séries 35 | media_idades = series_idades.mean() 36 | var_idades = series_idades.var() 37 | summary_idades = series_idades.describe() 38 | summary_idades -------------------------------------------------------------------------------- /dia01/03_series_index.py: -------------------------------------------------------------------------------- 1 | # %% 2 | import pandas as pd 3 | 4 | idades = [ 5 | 32, 38, 30, 30, 31, 6 | 35, 25, 29, 31, 37, 7 | 27, 23, 36, 33, 39, 8 | ] 9 | 10 | series_idades = pd.Series(idades) 11 | series_idades 12 | 13 | # %% 14 | idades[0] 15 | series_idades[0] 16 | 17 | # %% 18 | series_idades[-1] 19 | 20 | # %% 21 | series_idades = series_idades.sort_values() 22 | series_idades 23 | 24 | # %% 25 | series_idades[0] 26 | 27 | # %% 28 | 29 | series_idades.iloc[0] 30 | 31 | # %% 32 | series_idades.iloc[-1] 33 | 34 | # %% 35 | 36 | series_idades.iloc[:3] 37 | # %% 38 | 39 | series_idades.iloc[::-1] 40 | 41 | # %% 42 | 43 | idades = [ 44 | 32, 38, 30, 30, 31, 45 | 35, 25, 29, 31, 37, 46 | 27, 23, 36, 33, 39, 47 | ] 48 | 49 | indexs = [ 50 | "Téo", "Maria", "Jose", "Luis", "Ana", 51 | "Nah", "Dani", "Mah", "Fer", "Nanda", 52 | "Naty", "Nih", "Pedro", "Kozato", "Kozato", 53 | ] 54 | 55 | series_idades = pd.Series(idades, index=indexs) 56 | series_idades 57 | 58 | # %% 59 | series_idades.iloc[-1] -------------------------------------------------------------------------------- /dia01/04_dataframes.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | 5 | idades = [ 6 | 32, 38, 30, 30, 31, 7 | 35, 25, 29, 31, 37, 8 | 27, 23, 36, 33, 39, 9 | ] 10 | 11 | nomes = [ 12 | "Téo", "Maria", "Jose", "Luis", "Ana", 13 | "Nah", "Dani", "Mah", "Fer", "Nanda", 14 | "Naty", "Nih", "Pedro", "Kozato", "Kozato", 15 | ] 16 | 17 | series_idades = pd.Series(idades) 18 | series_nomes = pd.Series(nomes) 19 | 20 | # %% 21 | 22 | df = pd.DataFrame() 23 | df["idades"] = series_idades 24 | df["nomes"] = series_nomes 25 | df 26 | 27 | # %% 28 | 29 | df.iloc[0]["nomes"] 30 | 31 | # %% 32 | 33 | df.iloc[-1]["idades"] -------------------------------------------------------------------------------- /dia02/01_csv.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | 5 | df = pd.read_csv("../data/clientes.csv") 6 | df 7 | 8 | # %% 9 | 10 | df.to_csv("clientes.csv", index=False) 11 | 12 | # %% 13 | 14 | df.to_parquet("clientes.parquet", index=False) 15 | 16 | # %% 17 | 18 | df_2 = pd.read_parquet("clientes.parquet") 19 | df_2 20 | 21 | # %% 22 | 23 | df.to_excel("clientes.xlsx", index=False) 24 | 25 | # %% 26 | 27 | df_3 = pd.read_excel("clientes.xlsx") 28 | df_3 29 | 30 | # %% 31 | 32 | df_bobo = pd.read_csv("../data/bobo.csv", sep=";") 33 | df_bobo 34 | -------------------------------------------------------------------------------- /dia02/02_clipboard.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | 5 | df = pd.read_clipboard(sep=";") 6 | df -------------------------------------------------------------------------------- /dia02/03_html.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | 5 | url = "https://pt.wikipedia.org/wiki/Unidades_federativas_do_Brasil" 6 | dfs = pd.read_html(url) 7 | dfs 8 | 9 | # %% 10 | 11 | df_uf = dfs[1] 12 | df_uf.to_csv("ufs.csv", sep=";", index=False) -------------------------------------------------------------------------------- /dia02/04_dataframes.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | 5 | df_clientes = pd.read_csv("../data/clientes.csv") 6 | df_clientes 7 | 8 | 9 | # %% 10 | ## AMOSTRAS 11 | 12 | df_clientes.head(n=10) 13 | 14 | # %% 15 | df_clientes.tail(10) 16 | 17 | # %% 18 | df_clientes.sample(10) 19 | 20 | # %% 21 | df_clientes.shape 22 | 23 | # %% 24 | df_clientes.columns 25 | 26 | # %% 27 | df_clientes.index 28 | 29 | # %% 30 | df_clientes.info(memory_usage='deep', max_cols=2) 31 | 32 | # %% 33 | df_clientes.dtypes -------------------------------------------------------------------------------- /dia02/05_colunas.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | 5 | df = pd.read_csv("../data/transacoes.csv") 6 | df 7 | 8 | # %% 9 | df.shape 10 | 11 | # %% 12 | df.info(memory_usage="deep") 13 | 14 | # %% 15 | df.dtypes 16 | 17 | # %% 18 | 19 | renamed_columns = { 20 | "qtdePontos": "qtPontos", 21 | "descSistemaOrigem": "SistemaOrigem" 22 | } 23 | 24 | # df = df.rename(columns=renamed_columns) 25 | df.rename(columns=renamed_columns, inplace=True) 26 | 27 | # %% 28 | 29 | colunas = ["idCliente", "qtPontos"] 30 | df[colunas] 31 | 32 | # %% 33 | # SELECT * FROM df 34 | df 35 | 36 | # %% 37 | # SELECT idCliente FROM df 38 | 39 | df[["idCliente"]] 40 | 41 | # %% 42 | 43 | # SELECT idCliente, qtPontos FROM df LIMIT 5 44 | df[["idCliente", "qtPontos"]].tail(5) 45 | 46 | # %% 47 | 48 | # SELECT idCliente, idTransacao, qtPontos 49 | # FROM df 50 | # LIMIT 5 51 | 52 | df[["idCliente", "idTransacao", "qtPontos"]].head(5) 53 | 54 | # %% 55 | 56 | colunas = list(df.columns) 57 | colunas.sort() 58 | colunas 59 | 60 | df = df[colunas] 61 | df -------------------------------------------------------------------------------- /dia03/01_filtro.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | 5 | # %% 6 | 7 | pontos = [10, 1, 1, 1, 50, 100, 130, 30, 25, 50] 8 | filtro = [] 9 | 10 | valores_50_mais = [] 11 | for i in pontos: 12 | filtro.append(i>=50) 13 | 14 | 15 | resultado = [] 16 | for i in range(len(pontos)): 17 | if filtro[i]: 18 | resultado.append(pontos[i]) 19 | 20 | 21 | resultado 22 | filtro 23 | # %% 24 | 25 | brinquedo = pd.DataFrame( 26 | { 27 | "nome": ["teo", "nah", "mah"], 28 | "idade": [32,35,14], 29 | "uf": ["sp", "pr", "rj"], 30 | } 31 | ) 32 | 33 | filtro = brinquedo["idade"] >= 18 34 | brinquedo[filtro] 35 | 36 | # %% 37 | 38 | df = pd.read_csv("../data/transacoes.csv") 39 | df.head() 40 | 41 | # %% 42 | 43 | # valores maiores que 50 44 | filtro = df["qtdePontos"] >= 50 45 | df[filtro] 46 | 47 | # %% 48 | # valores entre 50 (inclusive) e 100 49 | filtro = (df["qtdePontos"] >= 50) & (df["qtdePontos"] < 100) 50 | filtro 51 | df[filtro] 52 | 53 | # %% 54 | 55 | filtro = (df["qtdePontos"] == 1) | (df["qtdePontos"] == 100) 56 | df[filtro] 57 | 58 | # %% 59 | # pontos entre 0 e 50 ou do ano de 2025 para frente 60 | 61 | filtro = (df["qtdePontos"] > 0) & (df["qtdePontos"]<=50) | (df["dtCriacao"]>='2025-01-01') 62 | df[filtro] 63 | 64 | # %% 65 | 66 | True and True = True 67 | True and False = False 68 | False and True = False 69 | False and False = False 70 | 71 | True or True = True 72 | True or False = True 73 | False or True = True 74 | False or False = False -------------------------------------------------------------------------------- /dia03/02_mais_filtros.py: -------------------------------------------------------------------------------- 1 | # %% 2 | import pandas as pd 3 | 4 | df = pd.read_csv("../data/transacao_produto.csv") 5 | df 6 | 7 | # %% 8 | 9 | filtro = (df["idProduto"] == 5) | (df["idProduto"] == 11) 10 | df[filtro] 11 | 12 | # %% 13 | 14 | filtro = df["idProduto"].isin([5,11]) 15 | df[filtro] 16 | 17 | # %% 18 | 19 | clientes = pd.read_csv("../data/clientes.csv") 20 | clientes.head() 21 | 22 | filtro = clientes["dtCriacao"].notna() 23 | clientes[filtro] 24 | 25 | # %% 26 | 27 | ~clientes["dtCriacao"].isna() 28 | clientes["dtCriacao"].notna() -------------------------------------------------------------------------------- /dia03/03_filtros_view.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | 5 | clientes = pd.read_csv("../data/clientes.csv") 6 | clientes.head() 7 | 8 | # %% 9 | 10 | filtro = clientes["qtdePontos"] == 0 11 | clientes_0 = clientes[filtro].copy() 12 | 13 | clientes_0["flag_1"] = 1 14 | clientes_0 15 | 16 | # %% 17 | 18 | A = [1,2] 19 | B = A.copy() 20 | print("A:", A) 21 | print("B:", B) 22 | 23 | B.append("fodase") 24 | print("A:", A) 25 | print("B:", B) 26 | -------------------------------------------------------------------------------- /dia04/01_novas_colunas.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | import numpy as np 5 | 6 | df = pd.read_csv("../data/clientes.csv") 7 | df.head() 8 | 9 | # %% 10 | 11 | df["pontos_100"] = df["qtdePontos"] + 100 12 | df.head() 13 | 14 | # %% 15 | 16 | nova_coluna = [] 17 | for i in df["qtdePontos"]: 18 | nova_coluna.append( i+100) 19 | 20 | nova_coluna 21 | 22 | # %% 23 | 24 | df["emailTwitch"] = df["flEmail"] + df["flTwitch"] 25 | df.head() 26 | 27 | # %% 28 | df["flEmail"] * df["flTwitch"] 29 | 30 | # %% 31 | 32 | df["qtdeSocial"] = df["flEmail"] + df["flTwitch"] + df["flYouTube"] + df["flBlueSky"] + df["flInstagram"] 33 | df 34 | 35 | # %% 36 | 37 | df["todas_social"] = df["flEmail"] * df["flTwitch"] * df["flYouTube"] * df["flBlueSky"] * df["flInstagram"] 38 | df 39 | 40 | # %% 41 | df["qtdePontos"] 42 | 43 | # %% 44 | 45 | df["logPontos"] = np.log(df["qtdePontos"]+1) 46 | df["logPontos"].describe() 47 | 48 | # %% 49 | 50 | import matplotlib.pyplot as plt 51 | 52 | plt.grid(True) 53 | plt.hist(df["logPontos"]) 54 | plt.show() -------------------------------------------------------------------------------- /dia04/02_sort.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | 5 | clientes = pd.read_csv("../data/clientes.csv") 6 | 7 | max_ponto = clientes["qtdePontos"].max() 8 | filtro = clientes["qtdePontos"] == max_ponto 9 | clientes[filtro] 10 | 11 | # %% 12 | 13 | top_5 = (clientes.sort_values(by="qtdePontos", ascending=False) 14 | .head(5)["idCliente"] ) 15 | 16 | type(top_5) 17 | 18 | # %% 19 | clientes 20 | 21 | # %% 22 | 23 | brinquedo = pd.DataFrame( 24 | { 25 | "nome": ["teo", "ana", "nah", "jose"], 26 | "idade": [32, 43, 35, 42], 27 | "salario":[2345, 4533, 3245, 4533], 28 | } 29 | ) 30 | 31 | brinquedo 32 | 33 | # %% 34 | 35 | brinquedo.sort_values(by=["salario", "idade"], ascending=[False, True]) -------------------------------------------------------------------------------- /dia05/01_conv_tipo.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | 5 | # %% 6 | 7 | df = pd.read_csv("../data/clientes.csv") 8 | 9 | # %% 10 | 11 | df["qtdePontos"].astype(float).astype(str) 12 | 13 | # %% 14 | 15 | replace = {"0000-00-00 00:00:00.000": "2024-02-01 09:00:00.000"} 16 | 17 | df["dtCriacao"] = pd.to_datetime(df["dtCriacao"].replace(replace)) 18 | 19 | # %% 20 | 21 | df["dtCriacao"].dt.month -------------------------------------------------------------------------------- /dia05/02_na.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | 5 | clientes = pd.read_csv("../data/clientes.csv") 6 | clientes 7 | 8 | # %% 9 | 10 | clientes.dropna(how="any") 11 | 12 | # %% 13 | 14 | df = pd.DataFrame( 15 | { 16 | "nome": ["Téo", None, "Nah", "Marcio"], 17 | "idade": [None, None, 43, 52], 18 | "salario": [3453,4324,None,5423] 19 | } 20 | ) 21 | 22 | # df 23 | df.dropna(how="all", subset=["idade", "nome"]) 24 | 25 | # %% 26 | 27 | df["idade"] = df["idade"].fillna(0) 28 | df 29 | 30 | # %% 31 | 32 | df.fillna({"nome": "alguem", "idade": 0}) 33 | 34 | # %% 35 | medias = df[['idade', 'salario']].mean() 36 | df.fillna(medias) 37 | 38 | # %% 39 | 40 | df["idade"].fillna(df["idade"].mean()).mean() -------------------------------------------------------------------------------- /dia05/03_duplicatas.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | 5 | # %% 6 | 7 | df = pd.DataFrame({ 8 | "nome": ['teo', 'lara', 'nah', 'bia', 'mah', 'lara', 'mah', 'mah'], 9 | "sobrenome": ['calvo', 'calvo', 'ataide', 'ataide', 'silva', 'silva', 'silva', 'silva'], 10 | "salario": [2132, 1231, 454, 6543, 6532, 4322, 987, 2134], 11 | }) 12 | 13 | df 14 | 15 | # %% 16 | 17 | df = (df.sort_values("salario", ascending=False) 18 | .drop_duplicates(keep='last', subset=["nome", "sobrenome"])) 19 | 20 | df -------------------------------------------------------------------------------- /dia06/01_apply.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | 5 | df = pd.read_csv("../data/clientes.csv") 6 | df.head() 7 | 8 | # %% 9 | 10 | def get_last_id(idCliente): 11 | return idCliente.split("-")[-1] 12 | 13 | # %% 14 | 15 | get_last_id("0033b737-8235-4c0f-9801-dc4ca185af00") 16 | 17 | # %% 18 | 19 | id_novo = [] 20 | 21 | for i in df["idCliente"]: 22 | novo = get_last_id(i) 23 | id_novo.append(novo) 24 | 25 | df["novo_id"] = id_novo 26 | df.head() 27 | 28 | # %% 29 | 30 | df["idCliente"].apply(get_last_id) 31 | 32 | 33 | # %% 34 | -------------------------------------------------------------------------------- /dia06/02_ufs.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | 5 | url = "https://pt.wikipedia.org/wiki/Unidades_federativas_do_Brasil" 6 | 7 | dfs = pd.read_html(url) 8 | uf = dfs[1] 9 | uf 10 | # %% 11 | 12 | def str_to_float(x:str): 13 | x = (x.replace(" ", "") 14 | .replace(",", ".") 15 | .replace("\xa0", "") 16 | ) 17 | return float(x) 18 | 19 | # %% 20 | 21 | uf["Área (km²)"] = uf["Área (km²)"].apply(str_to_float) 22 | uf["População (Censo 2022)"] = uf["População (Censo 2022)"].apply(str_to_float) 23 | uf["PIB (2015)"] = uf["PIB (2015)"].apply(str_to_float) 24 | uf["PIB per capita (R$) (2015)"] = uf["PIB per capita (R$) (2015)"].apply(str_to_float) 25 | 26 | # %% 27 | 28 | def exp_to_anos(exp:str): 29 | return float(exp.replace(",", ".") 30 | .replace(" anos", "")) 31 | 32 | uf["Expectativa de vida (2016)"] = uf["Expectativa de vida (2016)"].apply(exp_to_anos) 33 | 34 | # %% 35 | 36 | def uf_to_regiao(uf): 37 | 38 | # tartar uf 39 | # uf = uf 40 | 41 | if uf in ["Distrito Federal", "Goiás", "Mato Grosso", "Mato Grosso do Sul"]: 42 | return "Centro-Oeste" 43 | elif uf in ["Alagoas","Bahia", "Ceará", "Maranhão", "Paraíba", "Pernambuco", "Piauí", "Rio Grande do Norte", "Sergipe"]: 44 | return "Nordeste" 45 | elif uf in ["Acre", "Amapá", "Amazonas", "Pará", "Rondônia", "Roraima", "Tocantins"]: 46 | return "Norte" 47 | elif uf in ["Espírito Santo","Minas Gerais", "Rio de Janeiro", "São Paulo"]: 48 | return "Sudeste" 49 | elif uf in ["Paraná", "Rio Grande do Sul", "Santa Catarina"]: 50 | return "Sul" 51 | 52 | uf["Região"] = uf["Unidade federativa"].apply(uf_to_regiao) 53 | 54 | # %% 55 | 56 | def mortalidade_to_float(x:str): 57 | x = float(x.replace("‰", "") 58 | .replace(",", ".") 59 | ) 60 | return x 61 | 62 | uf["Mortalidade infantil (/1000)"] = uf["Mortalidade infantil (2016)"].apply(mortalidade_to_float) 63 | 64 | # %% 65 | 66 | # %% 67 | 68 | # Se PIB / Capita > 30.000 69 | # + 70 | # Mort Infantil < 15 / 1000 71 | # + 72 | # IDH (2010) > 700 73 | # -> "Parece bom" 74 | 75 | # Nao parece bom 76 | 77 | # %% 78 | 79 | def classifica_bom(linha): 80 | return (linha["PIB per capita (R$) (2015)"] > 30000 and 81 | linha["Mortalidade infantil (/1000)"] < 15 and 82 | linha["IDH (2010)"] > 700) 83 | 84 | # %% 85 | 86 | uf.apply(classifica_bom, axis=1) 87 | 88 | # %% 89 | 90 | uf.apply(lambda x: x["PIB per capita (R$) (2015)"], axis=1) -------------------------------------------------------------------------------- /dia07/01_summary.py: -------------------------------------------------------------------------------- 1 | # %% 2 | import pandas as pd 3 | 4 | idades = [32,44,12,54,67,32,23,34,32,12,45,43,28,73,29] 5 | idades = pd.Series(idades) 6 | idades.sum() 7 | idades.min() 8 | idades.max() 9 | idades.mean() 10 | idades.describe() 11 | 12 | # %% 13 | clientes = pd.read_csv("../data/clientes.csv") 14 | clientes 15 | 16 | # %% 17 | clientes["flTwitch"].sum() 18 | clientes["flTwitch"].mean() 19 | 20 | # %% 21 | redes_sociais = ["flEmail","flTwitch","flYouTube","flBlueSky","flInstagram"] 22 | clientes[redes_sociais].sum() 23 | 24 | # %% 25 | num_columns = clientes.dtypes[~(clientes.dtypes == "object")].index.tolist() 26 | clientes[num_columns].mean() 27 | 28 | # %% 29 | clientes[num_columns].describe() 30 | 31 | # %% 32 | clientes[["flTwitch", "flEmail"]].describe() -------------------------------------------------------------------------------- /dia07/02_group.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | 5 | transacoes = pd.read_csv("../data/transacoes.csv") 6 | transacoes.head() 7 | 8 | # %% 9 | transacoes.groupby(by=["idCliente"]).count() 10 | 11 | # %% 12 | transacoes.groupby(by=["idCliente"], as_index=False)[["idTransacao"]].count() 13 | 14 | # %% 15 | # qtde_transacoes 16 | # total_pontos 17 | # pontos / transacoes 18 | 19 | summary = (transacoes.groupby(by=["idCliente"], as_index=False) 20 | .agg({ 21 | "idTransacao": ['count'], 22 | "qtdePontos": ['sum', 'mean'] 23 | })) 24 | 25 | summary 26 | 27 | # %% 28 | summary[('qtdePontos','mean')] 29 | 30 | # %% 31 | summary.columns = ['idCliente', 'qtdeTransacao', "totalPontos", "avgPontos"] 32 | summary -------------------------------------------------------------------------------- /dia07/03_custom_group.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | import numpy as np 5 | 6 | transacoes = pd.read_csv("../data/transacoes.csv") 7 | transacoes.head() 8 | 9 | # %% 10 | 11 | def diff_amp(x: pd.Series): 12 | amplitude = x.max() - x.min() 13 | media = x.mean() 14 | return np.sqrt((amplitude-media)**2) 15 | 16 | 17 | def life_time(x: pd.Series): 18 | dt = pd.to_datetime(x) 19 | return (dt.max() - dt.min()).days 20 | 21 | idades = pd.Series([21,32,43,32,14,65,78,34,19]) 22 | 23 | # %% 24 | 25 | summary = (transacoes.groupby(by=["idCliente"], as_index=False) 26 | .agg({ 27 | "idTransacao": ['count'], 28 | "qtdePontos": ["sum", "mean", diff_amp], 29 | "dtCriacao": [life_time] 30 | }) 31 | ) 32 | 33 | summary.columns = [ 34 | "idCliente", 35 | "qtdeTransacao", 36 | "totalPontos", 37 | "mediaPontos", 38 | "ampMeanDiff", 39 | "lifeTime", 40 | ] 41 | 42 | summary 43 | # %% 44 | -------------------------------------------------------------------------------- /dia08/01_merge.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | 5 | transacoes = pd.read_csv("../data/transacoes.csv") 6 | transacoes.head() 7 | 8 | # %% 9 | clientes = pd.read_csv("../data/clientes.csv") 10 | clientes.head() 11 | 12 | # %% 13 | 14 | transacoes.merge( 15 | right=clientes, 16 | how='left', 17 | on=['idCliente'], 18 | suffixes=["Transacao", "Cliente"], 19 | ) 20 | 21 | # %% 22 | 23 | df_1 = pd.DataFrame({ 24 | "transacao": [1,2,3,4,5], 25 | "nome": ["t1", "t2", "t3", "t4", "t5"], 26 | "idCliente": [1,2,3,2,2], 27 | "valor": [10,45,32,17,87], 28 | }) 29 | 30 | df_2 = pd.DataFrame({ 31 | "id": [1,2,3,4], 32 | "nome": ["teo", "nah", "mah", "jose"], 33 | }) 34 | 35 | df_1.merge( 36 | df_2, 37 | left_on=["idCliente"], 38 | right_on=["id"], 39 | how='left', 40 | suffixes=["Transacao", "Cliente"], 41 | ) 42 | 43 | # %% 44 | -------------------------------------------------------------------------------- /dia08/02_concat.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | 5 | df = pd.DataFrame({ 6 | "cliente": [1,2,3,4,5], 7 | "nome": ["teo", "jose", "nah", "mah", "lah"], 8 | }) 9 | 10 | df_02 = pd.DataFrame({ 11 | "cliente": [6,7,8], 12 | "nome": ["kozato", "laura", "dan",], 13 | "idade":[32,29,31], 14 | }) 15 | 16 | df_03 = pd.DataFrame({ 17 | "idade": [32,34,19,54,33] 18 | }) 19 | 20 | # %% 21 | 22 | dfs = [df, df_02] 23 | 24 | pd.concat(dfs, ignore_index=True) 25 | 26 | # %% 27 | 28 | df_03 = df_03.sort_values(by='idade').reset_index(drop=True) 29 | df_03 30 | 31 | # %% 32 | 33 | pd.concat([df, df_03], axis=1) -------------------------------------------------------------------------------- /dia09/01_db.py: -------------------------------------------------------------------------------- 1 | # %% 2 | import pandas as pd 3 | import sqlalchemy 4 | 5 | # %% 6 | 7 | engine = sqlalchemy.create_engine("sqlite:///../data/olist.db") 8 | 9 | # %% 10 | clientes = pd.read_sql_table(table_name="tb_customers", 11 | con=engine) 12 | 13 | # %% 14 | clientes.shape 15 | 16 | # %% 17 | 18 | query = "SELECT * FROM tb_customers LIMIT 100" 19 | 20 | df_100 = pd.read_sql_query(query, con=engine) 21 | df_100 22 | 23 | # %% 24 | 25 | -------------------------------------------------------------------------------- /dia09/02_etl.py: -------------------------------------------------------------------------------- 1 | # %% 2 | import pandas as pd 3 | import sqlalchemy 4 | from sklearn import cluster 5 | 6 | # %% 7 | with open("etl.sql") as open_file: 8 | query = open_file.read() 9 | 10 | print(query) 11 | 12 | # %% 13 | engine = sqlalchemy.create_engine("sqlite:///../data/olist.db") 14 | df = pd.read_sql_query(query, con=engine) 15 | df 16 | 17 | # %% 18 | ## Treina modelo de cluster 19 | kmean = cluster.KMeans(n_clusters=4) 20 | kmean.fit(df[['totalRevenue','qtSalles']]) 21 | 22 | df["cluster"] = kmean.labels_ 23 | df 24 | 25 | # %% 26 | df.to_sql( 27 | "sellers_cluster", 28 | con=engine, 29 | index=False, 30 | if_exists="replace", 31 | ) 32 | -------------------------------------------------------------------------------- /dia09/etl.sql: -------------------------------------------------------------------------------- 1 | SELECT seller_id, 2 | sum(t1.price) As totalRevenue, 3 | count(distinct t1.order_id) AS qtSalles 4 | 5 | FROM tb_order_items AS t1 6 | 7 | GROUP BY seller_id -------------------------------------------------------------------------------- /dia09/pandas_sql.drawio: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 | 15 | 16 | 17 | 18 | 19 | 20 | 21 | 22 | 23 | 24 | 25 | 26 | 27 | 28 | 29 | 30 | 31 | 32 | 33 | 34 | 35 | 36 | 37 | 38 | 39 | 40 | 41 | 42 | 43 | 44 | 45 | 46 | 47 | 48 | 49 | 50 | 51 | 52 | 53 | 54 | 55 | 56 | 57 | 58 | 59 | 60 | 61 | 62 | 63 | 64 | 65 | 66 | 67 | 68 | 69 | 70 | 71 | 72 | 73 | 74 | 75 | 76 | 77 | 78 | 79 | 80 | 81 | 82 | 83 | 84 | 85 | 86 | 87 | 88 | 89 | 90 | 91 | 92 | 93 | 94 | -------------------------------------------------------------------------------- /dia09/pandas_sql.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TeoMeWhy/pandas-2025/1f56a6f461ca014c36acdab69832e19e25216f30/dia09/pandas_sql.png -------------------------------------------------------------------------------- /exercicios/02/01.py: -------------------------------------------------------------------------------- 1 | # Leia o arquivo transacoes.csv com a formatação correta; 2 | # Adicione uma coluna com valores 1; 3 | # Salve o dataframe com nome: transacoes_1.csv 4 | 5 | # %% 6 | 7 | import pandas as pd 8 | 9 | df = pd.read_csv("../../data/transacoes.csv") 10 | 11 | df["valor 1"] = 1 12 | df.head(5) 13 | 14 | df.to_csv("transacoes_1.csv", index=False) -------------------------------------------------------------------------------- /exercicios/03/exercicios.py: -------------------------------------------------------------------------------- 1 | # %% 2 | # 03.01 - Quantas linhas há no arquivo clientes.csv ? 3 | import pandas as pd 4 | 5 | df_clientes = pd.read_csv("../../data/clientes.csv") 6 | linhas = df_clientes.shape[0] 7 | 8 | print(f"O arquivo de clientes.csv tem {linhas} linhas") 9 | 10 | 11 | # %% 12 | # 03.02 - Quantas colunas do tipo int há no arquivo transacoes.csv ? 13 | 14 | df_transacoes = pd.read_csv("../../data/transacoes.csv") 15 | df_transacoes.dtypes 16 | 17 | print("O arquivo transacoes.csv tem uma coluna do tipo int (qtdePontos)") 18 | 19 | 20 | # %% 21 | # 03.03 - Quantas colunas do tipo object há no arquivo produtos.csv ? 22 | df_produtos = pd.read_csv("../../data/produtos.csv") 23 | df_produtos.dtypes 24 | 25 | print("O arquivo produtos.csv tem 1 coluna do tipo object (descProduto)") 26 | 27 | # %% 28 | # 03.04 - Qual o id do cliente no índice 4 no arquivo clientes.csv ? 29 | 30 | # df_clientes['idCliente'][4] 31 | df_clientes.loc[4]["idCliente"] 32 | 33 | # %% 34 | # 03.05 - Qual o saldo de pontos do cliente na 10a posição (sem ordenar) do arquivo clientes.csv ? 35 | 36 | df_clientes.iloc[9]["qtdePontos"] -------------------------------------------------------------------------------- /exercicios/04/drop_duplicates.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | # Obtenha a última linha de transacao de cada cliente 4 | # Obtenha a primeira 5 | 6 | import pandas as pd 7 | 8 | df = pd.read_csv("../../data/transacoes.csv") 9 | df.head() 10 | 11 | # %% 12 | 13 | # ultima 14 | ultima_transacao = (df.sort_values(by="dtCriacao") 15 | .drop_duplicates(subset=['idCliente'], keep='last')) 16 | 17 | # %% 18 | primeira_transacao = (df.sort_values(by="dtCriacao") 19 | .drop_duplicates(subset=['idCliente'], keep='first')) -------------------------------------------------------------------------------- /exercicios/04/exercicios.py: -------------------------------------------------------------------------------- 1 | # %% 2 | import pandas as pd 3 | 4 | # %% 5 | # 04.01 - Quantos clientes tem vínculo com a Twitch? 6 | 7 | clientes = pd.read_csv("../../data/clientes.csv") 8 | clientes.head() 9 | 10 | filtro = clientes["flTwitch"] == 1 11 | qtde_twitch = clientes[filtro].shape[0] 12 | 13 | print(f"Temos {qtde_twitch} usuários com twitch") 14 | 15 | # %% 16 | # 04.02 - Quantos clientes tem um saldo de pontos maior que 1000? 17 | 18 | clientes.head() 19 | 20 | filtro = clientes["qtdePontos"] > 1000 21 | qtde_1000 = clientes[filtro].shape[0] 22 | print(f"Temos {qtde_1000} clientes com mais de 1000 pontos") 23 | 24 | # %% 25 | # 04.03 - Quantas transações ocorreram no dia 2025-02-01? 26 | 27 | transacoes = pd.read_csv("../../data/transacoes.csv") 28 | transacoes.head() 29 | filtro = (transacoes['dtCriacao'] >= '2025-02-01') & (transacoes['dtCriacao'] < '2025-02-02') 30 | qtde_dia_2025_02_01 = transacoes[filtro].shape[0] 31 | print(f"No dia 2025-02-01 tivemos {qtde_dia_2025_02_01} transacoes") 32 | -------------------------------------------------------------------------------- /exercicios/05/exercicios.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | import numpy as np 5 | 6 | # %% 7 | # 05.01 - Crie uma coluna nova “twitch_points” que á 8 | # resultado da multiplicação do saldo de pontos e a marcação da twitch 9 | 10 | clientes = pd.read_csv("../../data/clientes.csv") 11 | 12 | clientes["twitch_points"] = clientes["qtdePontos"] * clientes["flTwitch"] 13 | clientes.head() 14 | 15 | # %% 16 | # 05.02 - Aplique o log na coluna de saldo de pontos, criando uma coluna nova 17 | 18 | clientes["logPontos"] = np.log(clientes["qtdePontos"]) 19 | clientes.head() 20 | 21 | # %% 22 | # 05.03 - Crie uma coluna que sinalize se a 23 | # pessoa tem vínculo com alguma (qualquer uma) 24 | # plataforma de rede social. 25 | clientes["ao_menos_uma_social"] = clientes["flTwitch"] + clientes["flYouTube"] + clientes["flBlueSky"] + clientes["flInstagram"] 26 | clientes.head() 27 | 28 | # 05.04 - Qual é o id de cliente que tem maior saldo de pontos? 29 | # E o menor? 30 | 31 | clientes.sort_values(by="qtdePontos", ascending=False).head(1)["idCliente"] 32 | 33 | clientes.sort_values(by="qtdePontos", ascending=True).head(1)["idCliente"] 34 | 35 | # %% 36 | # 05.05 - Selecione a primeira transação diária de cada cliente. 37 | 38 | import pandas as pd 39 | 40 | transacoes = pd.read_csv("../../data/transacoes.csv") 41 | transacoes.head() 42 | 43 | transacoes["data"] = pd.to_datetime(transacoes["dtCriacao"]).dt.date 44 | transacoes = transacoes.sort_values("dtCriacao") 45 | 46 | # %% 47 | 48 | first = transacoes.drop_duplicates(keep="first", subset=["idCliente", "data"]) 49 | last = transacoes.drop_duplicates(keep="last", subset=["idCliente", "data"]) 50 | 51 | pd.concat([last, first]) -------------------------------------------------------------------------------- /exercicios/06/01.py: -------------------------------------------------------------------------------- 1 | # %% 2 | # 06.01 - Qual a quantidade média de redes sociais dos usuários? 3 | # E a Variância? E o máximo? 4 | 5 | import pandas as pd 6 | 7 | clientes = pd.read_csv("../../data/clientes.csv") 8 | clientes 9 | 10 | # %% 11 | 12 | clientes["totalRedes"] = (clientes['flEmail'] + 13 | clientes['flTwitch'] + 14 | clientes['flYouTube'] + 15 | clientes['flBlueSky'] + 16 | clientes['flInstagram']) 17 | 18 | media = clientes["totalRedes"].mean() 19 | variancia = clientes["totalRedes"].var() 20 | maximo = clientes["totalRedes"].max() 21 | 22 | print("media:",media) 23 | print("variancia:",variancia) 24 | print("maximo:",maximo) 25 | 26 | # %% 27 | 28 | redes = [ 29 | "flEmail", 30 | "flTwitch", 31 | "flYouTube", 32 | "flBlueSky", 33 | "flInstagram", 34 | ] 35 | 36 | clientes[redes].sum(axis=1).describe() -------------------------------------------------------------------------------- /exercicios/06/02.py: -------------------------------------------------------------------------------- 1 | # %% 2 | # 06.02 - Quais são os usuários que mais fizeram transações? 3 | # Considere os 10 primeiros. 4 | 5 | import pandas as pd 6 | 7 | df = pd.read_csv("../../data/transacoes.csv") 8 | 9 | (df.groupby(by=['idCliente'])['idTransacao'] 10 | .count() 11 | .sort_values(ascending=False) 12 | .head(10)) 13 | 14 | -------------------------------------------------------------------------------- /exercicios/06/03.py: -------------------------------------------------------------------------------- 1 | # %% 2 | # 06.03 - Qual usuário teve maior quantidade de pontos debitados? 3 | 4 | import pandas as pd 5 | 6 | transacoes = pd.read_csv("../../data/transacoes.csv") 7 | transacoes.head() 8 | 9 | # %% 10 | 11 | filtro = transacoes['qtdePontos'] < 0 12 | 13 | (transacoes[filtro].groupby(by='idCliente')['qtdePontos'] 14 | .sum() 15 | .sort_values(ascending=True) 16 | .head(1)) -------------------------------------------------------------------------------- /exercicios/06/04.py: -------------------------------------------------------------------------------- 1 | # %% 2 | # 06.04 - Quem teve mais transações de Streak? 3 | 4 | import pandas as pd 5 | 6 | # %% 7 | 8 | transacoes = pd.read_csv("../../data/transacoes.csv") 9 | transacoes.head() 10 | 11 | # %% 12 | transacao_produto = pd.read_csv("../../data/transacao_produto.csv") 13 | transacao_produto.head() 14 | 15 | # %% 16 | produtos = pd.read_csv("../../data/produtos.csv") 17 | produtos.head() 18 | 19 | # %% 20 | 21 | cliente_transacao_produto = transacoes.merge( 22 | transacao_produto, 23 | on="idTransacao", 24 | how="left", 25 | )[['idTransacao', "idCliente", "idProduto"]] 26 | 27 | df_full = cliente_transacao_produto.merge( 28 | produtos, 29 | on=['idProduto'], 30 | how='left', 31 | ) 32 | 33 | df_full = df_full[df_full["descProduto"]=="Presença Streak"] 34 | 35 | (df_full.groupby(by=["idCliente"])["idTransacao"] 36 | .count() 37 | .sort_values(ascending=False) 38 | .head(1) 39 | ) 40 | 41 | # %% 42 | 43 | produtos = produtos[produtos["descProduto"]=="Presença Streak"] 44 | 45 | (transacoes.merge(transacao_produto, on=["idTransacao"], how="left") 46 | .merge(produtos, on=["idProduto"], how="inner") 47 | .groupby(by="idCliente")["idTransacao"] 48 | .count() 49 | .sort_values(ascending=False) 50 | .head(1) 51 | ) -------------------------------------------------------------------------------- /exercicios/06/05.py: -------------------------------------------------------------------------------- 1 | # %% 2 | # 06.05 - Qual a média de transações / dia? 3 | 4 | import pandas as pd 5 | 6 | df = pd.read_csv("../../data/transacoes.csv") 7 | df.head() 8 | 9 | # %% 10 | df["dtDia"] = pd.to_datetime(df["dtCriacao"]).dt.date 11 | 12 | summary = df.agg({ 13 | "idTransacao": 'count', 14 | "dtDia": 'nunique', 15 | }) 16 | 17 | transacoe_dia = summary["idTransacao"] / summary["dtDia"] 18 | transacoe_dia 19 | 20 | # %% 21 | -------------------------------------------------------------------------------- /exercicios/06/06.py: -------------------------------------------------------------------------------- 1 | # %% 2 | # 06.06 - Como podemos calcular as estatísticas descritivas 3 | # dos pontos das transações de cada usuário? 4 | 5 | import pandas as pd 6 | 7 | transacoes = pd.read_csv("../../data/transacoes.csv") 8 | transacoes.head() 9 | # %% 10 | 11 | (transacoes.groupby(by=['idCliente'], as_index=False)['qtdePontos'] 12 | .describe()) 13 | 14 | -------------------------------------------------------------------------------- /exercicios/case_cartao_credito/cartao.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | 5 | df = pd.read_csv("dados_cartao.csv", sep=";") 6 | df 7 | # %% 8 | 9 | df["dtTransacao"] = pd.to_datetime(df["dtTransacao"]) 10 | df 11 | 12 | # %% 13 | 14 | df["vlParcela"] = df["vlVenda"] / df["qtParcelas"] 15 | df 16 | 17 | # %% 18 | 19 | df["ordemParcela"] = df.apply(lambda row: [i for i in range(row['qtParcelas'])], axis=1) 20 | df 21 | 22 | # %% 23 | 24 | df_explode = df.explode("ordemParcela") 25 | df_explode 26 | 27 | # %% 28 | 29 | def calcDtParcela(row): 30 | dt = row["dtTransacao"] + pd.DateOffset(months=row["ordemParcela"]) 31 | dt = f"{dt.year}-{dt.month}" 32 | return dt 33 | 34 | df_explode["dtParcela"] = df_explode.apply(calcDtParcela, axis=1) 35 | df_explode 36 | # %% 37 | 38 | (df_explode.groupby(["idCliente", "dtParcela"]) 39 | ['vlParcela'].sum() 40 | .reset_index() 41 | .pivot_table(index='idCliente', 42 | columns='dtParcela', 43 | values='vlParcela', 44 | fill_value=0)) 45 | 46 | -------------------------------------------------------------------------------- /exercicios/case_homicidios/01_case.py: -------------------------------------------------------------------------------- 1 | # %% 2 | import pandas as pd 3 | import os 4 | 5 | def read_file(file_name:str): 6 | df = (pd.read_csv(f"../../data/ipea/{file_name}.csv", sep=";") 7 | .rename(columns={"valor":file_name}) 8 | .set_index(["nome", "período"]) 9 | .drop(["cod"],axis=1)) 10 | 11 | return df 12 | 13 | # %% 14 | file_names = os.listdir("../../data/ipea/") 15 | 16 | dfs = [] 17 | for i in file_names: 18 | file_name = i.split(".")[0] 19 | dfs.append(read_file(file_name)) 20 | 21 | 22 | df_full = (pd.concat(dfs, axis=1) 23 | .reset_index() 24 | .sort_values(["período", "nome"])) 25 | 26 | df_full.to_csv("homicios_consolidado.csv", index=False, sep=";") -------------------------------------------------------------------------------- /exercicios/case_homicidios/02_stack_unstack.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | 5 | df = pd.read_csv("homicidios_consolidado.csv", sep=";") 6 | df.head() 7 | 8 | # %% 9 | 10 | df_stack = (df.set_index(["nome", "período"]) 11 | .stack()) 12 | df_stack = df_stack.reset_index() 13 | df_stack.columns = ["nome", "período", "metrica", "valor"] 14 | df_stack 15 | 16 | # %% 17 | 18 | df_unstack = (df_stack.set_index(["nome", "período", "metrica"]) 19 | .unstack() 20 | .reset_index()) 21 | 22 | df_unstack 23 | # %% 24 | 25 | df_unstack.columns.droplevel(0).tolist()[2:] 26 | 27 | # %% 28 | 29 | metricas = df_unstack.columns.droplevel(0)[2:].tolist() 30 | df_unstack.columns = ['nome', 'período'] + metricas 31 | df_unstack -------------------------------------------------------------------------------- /exercicios/case_homicidios/03_pivot.py: -------------------------------------------------------------------------------- 1 | # %% 2 | 3 | import pandas as pd 4 | 5 | df = pd.read_csv("homicidios_consolidado.csv", sep=";") 6 | df.head() 7 | 8 | # %% 9 | 10 | df_stack = (df.set_index(["nome", "período"]) 11 | .stack() 12 | .reset_index()) 13 | 14 | df_stack.columns = ["nome", "periodo", "metrica", "valor"] 15 | 16 | df_stack 17 | 18 | # %% 19 | 20 | (df_stack.pivot_table(values="valor", 21 | index=["nome", "periodo"], 22 | columns="metrica") 23 | .reset_index()) 24 | 25 | # %% 26 | 27 | df_stack.pivot_table(values="valor", 28 | index=["nome"], 29 | columns="metrica", 30 | aggfunc='min') 31 | 32 | # %% 33 | 34 | (df_stack.pivot_table(values="valor", 35 | index=["nome", "periodo"], 36 | columns="metrica") 37 | .stack() 38 | ) 39 | 40 | # %% 41 | 42 | df_stack --------------------------------------------------------------------------------