+ }i)^RIt^RIt^RIHt^RIHtHtHtHtH t H t H t H t H t ^RIt] !R4t] ]]3,t!RR4t!RR4tR R ltR R ltR RltRRltRRltRRltR# ]d^RItLZi;i)NPath) AnyDictIterableListOptionalSequenceTupleTypeVarUnionTca]tRt^toRtV3RlRltV3RlRltV3RlRltV3RlR ltV3R lR lt ] V3R lR l4t ] V3RlRl4t ] V3RlRl4t RtVtR#) BayesianNodezk Implementation of a single node in a bayesian network allowing sampling from its conditional distribution c6<V^8dQhRS[S[S[3,/#)node_definitionrstrr)format __classdict__s"o/Users/ahmad/.openclaw/workspace/my-crawler/.venv/lib/python3.14/site-packages/browserforge/bayesian_network.py __annotate__BayesianNode.__annotate__s//S#X/cWnR#Nr)selfrs&&r__init__BayesianNode.__init__s.rcR<V^8dQhRS[S[S[3,RS[S[S[3,/#r parent_valuesreturn)rrrfloat)rrs"rrrs.  !#s(^  c5j  rc VPR,pVPFNpVPV4pWBPR/49dVR,V,pK<VPR/4pKP V#)zZ Extracts unconditional probabilities of node values given the values of the parent nodes conditionalProbabilitiesdeeperskip)r parent_namesget)rr$ probabilities parent_name parent_values&& r$get_probabilities_given_known_values1BayesianNode.get_probabilities_given_known_valuessq ,,-GH ,,K(,,[9L002>> -h 7 E - 1 1&" = - rcR<V^8dQhRS[S[,RS[S[S[3,RS[/#)rpossible_valuesr-r%)rrrr&r)rrs"rrr&s2""#Cy"9=c5j9I" "rc \P!4pRpVFpWBV,, pWC8gKVu# V^,#)zF Randomly samples from the given values using the given probabilities g)random)rr3r-anchorcumulative_probabilitypossible_values&&& r&sample_random_value_from_possibilities3BayesianNode.sample_random_value_from_possibilities&sF!$-N "N&C C "%.%%. q!!rc<<V^8dQhRS[S[S[3,RS[/#r#r)rrs"rrr7s#  DcN s rc vVPV4pVP\VP44V4#)zY Randomly samples from the conditional distribution of this node given values of parents )r0r9listkeys)rr$r-s&& rsampleBayesianNode.sample7s:AA-P :: ##% &   rc x<V^8dQhRS[S[S[3,RS[S[,RS[S[,RS[S[,/#)rr$value_possibilities banned_valuesr%)rrrrrr )rrs"rrr@sGCH~&c]Cy  # rc VPV4pVUu.uFpWS9gK WT9gKVNK ppV'dVPWd4#R#uupi)z Randomly samples from the conditional distribution of this node given restrictions on the possible values and the values of the parents. N)r0r9)rr$rBrCr-value valid_valuess&&&& r sample_according_to_restrictions-BayesianNode.sample_according_to_restrictions@sgAA-P - ,) .3.D E,  >>|[ [ sAAAc <V^8dQhRS[/#rr%)r)rrs"rrrUs,,c,rc(VPR,#)namerrs&rrLBayesianNode.nameTs##F++rc0<V^8dQhRS[S[,/#rJrr)rrs"rrrYs;;d3i;rc:VPPR.4#) parentNamesrr,rMs&rr+BayesianNode.parent_namesXs##'' r::rc0<V^8dQhRS[S[,/#rJrP)rrs"rrr]s>>c>rc:VPPR.4#)possibleValuesrSrMs&rr3BayesianNode.possible_values\s##''(8"==rrN)__name__ __module__ __qualname____firstlineno____doc__r r0r9r?rGpropertyrLr+r3__static_attributes____classdictcell__rs@rrrsx//  """  (,,;;>>rrcpa]tRt^atoRtV3RlRltR V3RlRlltV3RlRltV3R lR ltR t Vt R#) BayesianNetworkzY Implementation of a bayesian network capable of randomly sampling from its distribution c$<V^8dQhRS[RR/#)rpathr%Nr)rrs"rrBayesianNetwork.__annotate__fsXXTXdXrc\V4pVR,Uu.uFp\V4NK upVnVPUu/uFqDPVbK upVnR#uupiuupi)nodesN) extract_jsonrnodes_in_sampling_orderrL nodes_by_name)rrenetwork_definitionnode_defnodes&& rr BayesianNetwork.__init__fsf)$/3Eg3N( 3NxL "3N( $;?:V:VW:V$iio:VW( Xs A A%Ncb<V^8dQhRS[S[S[S[3,,RS[S[S[3,/#)r input_valuesr%)r rrr)rrs"rrrfms5  HT#s(^,D PTUXZ]U]P^ rc Vf/pVP4pVPF3pVPV9gKVPV4W#P&K5 V#)zM Randomly samples from the distribution represented by the bayesian network. )copyrjrLr?)rrqr?rns&& rgenerate_sampleBayesianNetwork.generate_samplemsU  L""$00Dyy&$(KK$7yy!1 rcr<V^8dQhRS[S[S[S[,3,RS[S[S[S[3,,/#)rrBr%)rrrr r)rrs"rrrfys<ee#'Xc](:#;e $sCx. !erc (VP/V^4#)z Randomly samples values from the distribution represented by the bayesian network, making sure the sample is consistent with the provided restrictions on value possibilities. Returns None if no such sample can be generated. )4recursively_generate_consistent_sample_when_possible)rrBs&&r(generate_consistent_sample_when_possible8BayesianNetwork.generate_consistent_sample_when_possibleysHHM`bcddrc <V^8dQhRS[S[S[3,RS[S[S[S[,3,RS[RS[S[S[S[3,,/#)r sample_so_farrBdepthr%)rrrrintr )rrs"rrrfsVCH~"#x}"45  $sCx. ! rc ~V\VP48XdV#VPV,p.pRpVPVVPVPVP 4V4pVfR#WaVP&VP WV^,4pVeV#VPV4WPK)zb Recursively generates a random sample consistent with the given restrictions on possible values. N)lenrjrGr,rLr3rxappend)rr|rBr}rnrC sample_value next_samples&&&& rrxDBayesianNetwork.recursively_generate_consistent_sample_when_possibles C445 5 ++E2#%  @@#'' 43G3GHL #(4$)) $SSEAIK&""   .ii(r)rkrjr) rYrZr[r\r]r rtryrxr_r`ras@rrcrcas6XX  eerrcc~V^8dQhR\\,R\\,R\\,/#)rabr%)r rr)rs"rrrs-(((1+((1+($q'(rcV\V4pVUu.uF q3V9gK VNK up#uupi)z: Performs a set "intersection" on the given (flat) arrays )set)rrset_bxs&& rarray_intersectionrs+ FE 'q!JAAq '' 's&&c V^8dQhR\\\R3,,R\\\R3,,R\\\R3,,/#)rr.rr%)rr r)rs"rrrsH : :eAsFm$ :eAsFm)< :eAsFmAT :rc \W4UUu.uF(wr#\\V4PV44NK* upp#uuppi)z Combines two arrays into a single array using the set union Args: a: First array to be combined. b: Second array to be combined. Returns: Zipped (multi-dimensional) array. )ziptuplerunion)rrrys&& r array_ziprs3031y 9ytqE#a&,,q/ "y 99 9s.ActV^8dQhR\\\3,R\\\3,/#)robjr%r)rs"rrrs*$sCx.T#s(^rc\V\4'gV#/pVP4F>wr#VR8XdKVR8XdVP\ V44K1\ V4W&K@ V#)zM Removes the "deeper/skip" structures from the conditional probability table r*r)) isinstancedictitemsupdateundeeper)rresultkeyrEs& rrrs` c4  Fiik  &=  (? MM(5/ *"5/FK " Mrc V^8dQhR\\\3,R\R\\ \R3,,/#)rtree valid_keysr%.)rrrMaprr )rs"rrrs9DcNUSVX[S[_H]rc4aa.oRVV3RlloS!W.4S#)z Performs DFS on the Tree and returns values of the nodes on the paths that end with the given keys (stored by levels - first level is the root) ``` 1 / \ 2 3 / \ / \ 4 5 6 7 ``` filter_by_last_level_keys(tree, ['4', '7']) => [[1], [2,3]] cV^8dQhR\\\3,R\\\R3,\ \,3,R\ \,RR/#)rtvk.accr%N)rrrr r r)rs"rr/filter_by_last_level_keys..__annotate__sL 1 14S> 1uU38_d3i-G'H 1tTWy 1]a 1rcP<VP4Fp\W,\4'd W,fGW19d?\S4^8XdVUu.uFqD3NK upM\ SVUu.uFqD3NK up4oKoS!W,WV.,4K R#uupiuupir)r>rrrr)rrrrroutrecurses&&& rr*filter_by_last_level_keys..recurses668Cafd++qv~9s8q=(++s!s+&s3,?3aT3,?@ 3%K0 ,,?s  B- B# )rrrrs&&@@rfilter_by_last_level_keysrs%"$C 1 1 Db! Jrc V^8dQhRRR\\\\\R3,\\,3,3,R\\\ \,3,/#)rnetworkrcr3.r%)rrr r rr )rs"rrrsU$$ $15c5sCxRVWZR[A[;\6\1]$ #x} $rc N.pVP4Fwr4\V\\34'gK#\ V4^8Xd \ R4hVP V,p\VPR,4p\Wd4pVP/\\VPV44CW4/C4K /pVF[p V P4FDpW89d2\W,W,4p V 'g \ R4hWV&K:W,W&KF K] V#)z Given a `generative-bayesian-network` instance and a set of user constraints, returns an extended set of constraints **induced** by the original constraints and network structure zgThe current constraints are too restrictive. No possible values can be found for the given constraints.r()rrr=rr ValueErrorrkrrrrrrr+r>r) rr3setsrrErnr zipped_valuesrset_dictintersected_valuess && rget_possible_valuesrs D%++- %$//  u:?y $$S),,-GHI1$>  OtC 1 1=ABOCOP.(*F==?C}%7 v{%S")$B1s &m # Mrc0V^8dQhR\R\/#)rrer%)rr)rs"rrrs((t((rc VPR8wdD\VR4;_uu_4p\P!VP 44uuRRR4#\ P !VR4;_uu_4p\RVP444pTPT4;_uu_4p\P!TP 44uuRRR4uuRRR4# +'giL;i \d/uuuRRR4#i;i +'giM;iRRR4R# +'giR#;i)z Unzips a zip file if the path points to a zip file, otherwise directly loads a JSON file. Parameters: path: The path to the zip file or JSON file. Returns: A dictionary representing the JSON content. z.ziprbNrc3V"TFqPR4'gKVxK! R#5i)z.jsonN)endswith).0files& r extract_json..#sU]TmmG>TDD]s) )) suffixopenjsonloadsreadzipfileZipFilenextnamelist StopIteration)rerzffilenamefs& rriris {{f $  ::diik*  s # #r UR[[]UUHWWX  !::affh'  $ #  I $ #     $ # # #sS$C(4D66 C;D6/$D  D6( C8 ; DD6DD6 D( #D66 E )r5rpathlibrtypingrrrrr r r r r orjsonr ImportErrorrr=rrrrcrrrrrrirrrrs WWW CL D%KO>O>d@@F( :"B$N(SsA77 BB