Bay es i an An aly si sw it h Pyth on - Thi rd Editio n: A act guide to pro babi list ic mod eli ng

• Auto : Ma , do
• Wydawnictwo: Packt Publishing
• Date of efficacyania: 2024-01-31
• Number of stron: 394
• Wymiary: 23.5 x 19.1 x 2.1
• Language: English: Published; English: Original Language; English
• BN : 9781805127161

Lea rn the fundament als of Bay es i an m od eli ng u si ng sta te-of-the- art Pyth on libr aries , ch as PyMC, ArviZ, B am bi, an d more , guided by an exp er er Bay es i an model er who c on tribute es to th es e libr aries Key Fea tur es C on duct Bay es i an data an aly si sw it h st ep -by-st ep gu ida nce Gain in si ght i nt oa mod er n, pr act ical, an d co mp ut ati onal ap proa ch to Bay es i an sta tistical mod eli ng Enh an ce your lea rn ing w it hb es t pr act ic es thro ug h sa mple pro bl em s an d pr act ice ex er ci se s Pur ch a se of the print or Kindle book includ es a free PDF eB ook. Book D es cripti on The thi rd editio of Bay es i an An aly si sw it h Pyth on se r ves as an i nt roducti on to the ma in c on c ep ts of ap plied Bay es i an mod eli ng u si ng PyMC, a sta te-of-the- art pro babi list ic pro g ram m ing library, an d oth er libr aries that support an d fa cil it ate mod eli ng like ArviZ, for explo ra tor y an aly si s of Bay es i an models; B am bi, for f lex ible an d eas y hi er ar ch ical linear m eli ng; Pr eli Z, for prior eli c it ati on ; PyMC- BAR T, for lex ible n on - para me tr ic regr es si on ; an d Kul pr it , for varia ble se lecti on . In t his updated editio n, a brief an d conceptual i nt roducti on to pro babil it y th eo ry enh an c es your lea rn ing journey by i nt roduc ing new top ics like Bay es i an ad d it ive regr es si on tr e es ( BAR T), fea tur ing updated ex am pl es . Refined ex plan ati on s, infor med by feedba ck an d exp er from previous editio ns, und er score the book's em ph as is on Bay es i an sta . You will explo various models, includ ing hi er ar ch ical models, gen er alized linear models for regr es si on an d cl as s if ic ati on, mi tur e models, Gauss i an pro c es s es , an d BAR T, u si ng sy nt hetic an d real dat as ets. By the end of t his book, you will pos se ss a functi on al und er st an d ing of pro babi list ic mod eli ng, enabl ing you to d es ign an d imp l em e nt Bay es i an models for your data science ch alleng es . You'll be we ll-pr ep a red to delve i nt o more ad v an ced ma er or specialized sta tistical mod eli ng if the need ari se s. What you will lea rn Build pro babi list ic models u si ng PyMC an d B am bi An alyze an d inter pret pro babi list ic models w it h ArviZ Acquire the skills to sa n it y- ch ck models an d mod if y th em if nec es sary Build bett er models w it h prior an d post erior p red ictive ch e ck s Lea rn the ad v an t ag es an d caveats of hi er ar ch ical models Co mp are models an d ch oo se bet we en alter n ati ve on es Inter pret r es ults an d ap ply your know led ge to real-world pro bl em s Explo re comm on models from a un if ied pro babi list ic p er spective Ap ply the Bay es i an f ram ework's f lex ibil it y for pro babi list ic thi nk ing Who t his book is for If you are a stude nt , data scie nt ist, r es e arche r, or develop er look ing to get sta rted w it h Bay es i an data an aly si s an d pro babi list ic pro g ram m ing , t his book is for you. The book is i nt roduc tor y, so no previous sta tistical know led ge is requi red , altho ug h some exp er er in u si ng Pyth on an d scie nt ific libr aries like Nu mP y is expected. Table of C on te nt s Thi nk ing Pro babi list ically Pro g ram m ing Pro babi list ically Hi er ar ch ical Models Mod eli ng w it h Lin es Co mp a ring Models Mod eli ng w it h B am bi Mi tur e Models Gauss i an Pro c es es Bay es i an Ad d it ive Regr es si on Tr es Inf er ence Engin es Wh er e to Go Next