Uth؉UddlmZddlZddlZddlmZmZmZmZm Z ddl m Z ddl m ZGdde Zed d ZdGdZdHdZddgfdIdZdJdKdZddgfdIdZdGdZdGdZdGdZdGdZdGdZdGd ZdLd$ZddgfdMd'ZdGd(ZdNd*ZdOd.Z dPd0Z!dQd2Z"dRd4Z#dSd6Z$dTd8Z%dUd9Z&dVdWd=Z'd>Z(d?e)d@<dXdBZ*dYdFZ+dS)Z) annotationsN)AnyTypeVarCallableOptional NamedTuple) TypeAlias)pandascneZdZUded<dZded<dZded<dZded<dZded <dZded <dZ ded <dS) RemediationstrnameNz Optional[str] immediate_msg necessary_msgzOptional[Callable[[Any], Any]] necessary_fn optional_msg optional_fn error_msg) __name__ __module__ __qualname____annotations__rrrrrrj/var/www/html/mycamper/aliexpress-site/backend/venv/lib/python3.11/site-packages/openai/lib/_validators.pyr r s III#'M''''#'M''''37L7777"&L&&&&26K6666#I######rr OptionalDataFrameTzOptional[pd.DataFrame])bounddf pd.DataFramereturncd}t||krdnd}dt|d|}td|S)z This validator will only print out the number of examples and recommend to the user to increase the number of examples if less than 100. dz. In general, we recommend having at least a few hundred examples. We've found that performance tends to linearly increase for every doubling of the number of examplesz - Your file contains z prompt-completion pairs num_examplesrr)lenr )r MIN_EXAMPLESoptional_suggestionrs rnum_examples_validatorr*s`L r77l " " w ec"ggddObddM N- H H HHrnecessary_columnrcddd}d}d}d}|jvr/d|jDvrdfd }|}d d }d d }nd d}td||||S)z[ This validator will ensure that the necessary column is present in the dataframe. rr columnrr!cfd|jD}||did|S)Nc^g|])}t|k'|*Srrlower).0cr-s r zInecessary_column_validator..lower_case_column..-s1BBBaQ6)A)A)A)A)ArrT)columnsinplace)r5renamer1)rr-colss ` rlower_case_columnz5necessary_column_validator..lower_case_column,sJBBBB2:BBB 47FLLNN3T BBB rNcPg|]#}t|$Srr0r2r3s rr4z.necessary_column_validator..7s&CCC1A CCCrc|SNr)rr9r+s rlower_case_column_creatorz=necessary_column_validator..lower_case_column_creator9s((-=>>>rz - The `z ` column/key should be lowercasezLower case column name to ``z^` column/key is missing. Please make sure you name your columns/keys appropriately, then retryr+)rrrrr)rr r-rr!r )rr r!r )r5r )rr+rrrrr>r9s ` @rnecessary_column_validatorr@'s  MLMIrz)) CC CCC C C ? ? ? ? ? ? ?5LZ(8ZZZMM:JMMMMMM,MMMI  ##!    rprompt completionfields list[str]cg}d}d}d}t|jdkrYfd|jD}d}|D]/fd|D}t|dkr |ddd z }0d ||}d |}dfd }td|||S)zK This validator will remove additional columns from the dataframe. Nr cg|]}|v| Srr)r2r3rCs rr4z/additional_column_validator..UsGGGAqarr$cg|]}|v| Srr)r2r3acs rr4z/additional_column_validator..Xs===!R1WWAWWWrrz9 WARNING: Some of the additional columns/keys contain `z<` in their name. These will be ignored, and the column/key `z`` will be used instead. This could also result from a duplicate column/key in the provided file.zh - The input file should contain exactly two columns/keys per row. Additional columns/keys present are: z Remove additional columns/keys: xrr!c|Sr=rrIrCs rrz1additional_column_validator..necessary_fn^s V9 radditional_columnrrrrrIrr!r)r'r5r ) rrCadditional_columnsrrr warn_messagedupsrHs ` @radditional_column_validatorrRKs<MML 2:GGGGGGG $ B BB====1===D4yy1}}!B]_!B!B^`!B!B!BB gEWgYegg O;MOO         ##!    rfieldcd}d}d}|ds,|r||dk|z}|j|}dd|}dfd }d t |d d }td |||S)zA This validator will ensure that no completion is empty. Nc|dkS)Nr$rrIs rz+non_empty_field_validator..qs brr$z - `z?` column/key should not contain empty strings. These are rows: rIrr!cR||dkgS)Nr$subset)dropna)rIrSs rrz/non_empty_field_validator..necessary_fnvs)QuX^$++E7+;; ;rRemove z rows with empty sempty_rMrN)applyanyisnull reset_indexindextolistr'r )rrSrrr empty_rows empty_indexess ` rnon_empty_field_validatorrgis(MLM %y(())--//P2e93C3C3E3E3I3I3K3KPi2o"U)*:*:*<*<= ((.z:AACC uuufsuu  < < < < < <P#m"4"4OOuOOO  e  ##!    rcr|}|j|}d}d}d}t |dkrDdt |ddd|}dt |d }dfd }t d|||S)zY This validator will suggest to the user to remove duplicate rows if they exist. rYNr - There are z duplicated -z sets. These are rows: r\z duplicate rowsrIrr!c0|S)NrY)drop_duplicatesrKs rrz.duplicated_rows_validator..optional_fns$$F$33 3rduplicated_rowsrrrrrN) duplicatedrbrcrdr'joinr )rrCrmduplicated_indexesrrrs ` rduplicated_rows_validatorrrsmm6m22O))/@GGIIMLK ""L-?)@)@LLchhW]N^N^LLxJLL I%7!8!8III  4 4 4 4 4 4  #!    rcd}d}d}t|}|dkrRdd|tdkr0d td d }d td }dfd }td|||S)zW This validator will suggest to the user to remove examples that are too long. Nopen-ended generationdr r!rc|dd}|j|S)Nc\t|jt|jzdkS)Ni')r'rArBrVs rrWzClong_examples_validator..get_long_indexes..s#c!(mmc!,>O>O.ORW.Wr)axis)r_rbrcrd)ru long_exampless rget_long_indexesz1long_examples_validator..get_long_indexess>GG$W$W^_G``M==??(7>>@@ @rrriz. examples that are very long. These are rows: zf For conditional generation, and for classification the examples shouldn't be longer than 2048 tokens.r\z long examplesrIc|}|kr3tjdt|d|d||S)NzeThe indices of the long examples has changed as a result of a previously applied recommendation. The z? long examples to be dropped are now at the following indices:  )sysstdoutwriter'drop)rIlong_indexes_to_dropr{ long_indexess rrz,long_examples_validator..optional_fns'7'7':':$#777J$$tBEFZB[B[tt\ptttvv2333rrzrn)rur r!rrN)infer_task_typer'r )rrrrft_typer{rs @@rlong_examples_validatorrsMLKb!!G))) A A A A('++ |  q dS->->ddnzdddMFS%6%6FFFL 4 4 4 4 4 4 4  #!    rc d}d}d}d}d gd}|D]p}|dkr2|jjdr:|jj|drn|  dd}t |}|d krt d Sd"d t|jd} |j| krd| d}t d |S| dkr| dd} d| d}t| dkr |d|dz }|jjdt|  j| dr |d| dz }nd}| dkr d|d}d# fd }t d ||||!S)$z This validator will suggest to add a common suffix to the prompt if one doesn't already exist in case of classification or conditional generation. Nz ### => ) ->z ### z === z --- z ===> z ---> rr}Fregex\nrt common_suffixrrIrsuffixr!c&|dxx|z cc<|SNrArrIrs r add_suffixz2common_prompt_suffix_validator..add_suffixs ( v rxfixzAll prompts are identical: `zt` Consider leaving the prompts blank if you want to do open-ended generation, otherwise ensure prompts are differentrrr$z - All prompts end with suffix `r? R. This suffix seems very long. Consider replacing with a shorter suffix, such as `z5 WARNING: Some of your prompts contain the suffix `zZ` more than once. We strongly suggest that you review your prompts and add a unique suffixa - Your data does not contain a common separator at the end of your prompts. Having a separator string appended to the end of the prompt makes it clearer to the fine-tuned model where the completion should begin. See https://platform.openai.com/docs/guides/fine-tuning/preparing-your-dataset for more detail and examples. If you intend to do open-ended generation, then you should leave the prompts emptyzAdd a suffix separator `z` to all promptsc|Sr=rrIrsuggested_suffixs rrz3common_prompt_suffix_validator..optional_fn:a!122 2rcommon_completion_suffixrrrrrrIrrrr!rrN) rArcontainsr`replacerr get_common_xfixallr') rrrrrsuffix_options suffix_optiondisplay_suggested_suffixrrcommon_suffix_new_line_handledrrs @@rcommon_prompt_suffix_validatorrsIMLK(N( E ! !y}%%d++//11  9= ! !-u ! = = A A C C  ( /77eDDb!!G)))0000$BIH===M ]"''))Fx=xxx 9EEEE)6)>)>tU)K)K&].remove_common_prefixs%koc&kkmm4( rz" - All prompts start with prefix `r?z. Fine-tuning doesn't require the instruction specifying the task, or a few-shot example scenario. Most of the time you should only add the input data into the prompt, and the desired output into the completionRemove prefix `z` from all promptsc|Sr=r)rIrrs rrz3common_prompt_prefix_validator..optional_fn!s++A}===rcommon_prompt_prefixrn)rIrrrr!rrN)rrAr rr')rMAX_PREFIX_LENrrrrrs @@rcommon_prompt_prefix_validatorrs#NMLK#BIH===M0000 ]"''))10000NmNNN C .. . . r rMN]NNNL > > > > > > >  ##!    rcld}t|jdtdko ddkt|krtdSdd |jkrtdSd d}dd}dfd }td|||S)zh This validator will suggest to remove a common prefix from the completion if a long one exist. rrr rrrIr ws_prefixr!cp|djt|d|d<|rd|d|d<|S)NrBrr)rIrrs rrz@common_completion_prefix_validator..remove_common_prefix7sCL/-c&kkmm<,  43!L/33AlOrz& - All completions start with prefix `z_`. Most of the time you should only add the output data into the completion, without any prefixrz` from all completionsc|Sr=r)rIrrrs rrz7common_completion_prefix_validator..optional_fnEs##A}i@@@rcommon_completion_prefixrn)rIrrrrrr!rrN)rrBr'r r)rrrrrrrrs @@@r"common_completion_prefix_validatorr,s(N#BMAAAMM""Q&B=+;s+BI =N**0000 &++--10000mmmmmMJ]JJJLAAAAAAAA  '#!    rc: d}d}d}d}t|}|dks|dkrtdSt|jd}|j|krd|d |d }td| Sd gd }|D]8}|jj|dr6|  dd} d"d |dkr|dd} d| d }t|dkr |d| d z }|jjdt| j|dr |d|dz }nd}|dkr d| d}d# fd }td ||||!S)$z This validator will suggest to add a common suffix to the completion if one doesn't already exist in case of classification or conditional generation. Nrtclassificationrrrrz All completions are identical: `zJ` Ensure completions are different, otherwise the model will just repeat `r?rz [END]) r}.z ENDz***z+++z&&&z$$$z@@@z%%%Frr}rrIrr!c&|dxx|z cc<|SNrBrrs rrz6common_completion_suffix_validator..add_suffixvs ,6!rr$z$ - All completions end with suffix `rrz9 WARNING: Some of your completions contain the suffix `zU` more than once. We suggest that you review your completions and add a unique endingaH - Your data does not contain a common ending at the end of your completions. Having a common ending string appended to the end of the completion makes it clearer to the fine-tuned model where the completion should end. See https://platform.openai.com/docs/guides/fine-tuning/preparing-your-dataset for more detail and examples.zAdd a suffix ending `z` to all completionsc|Sr=rrs rrz7common_completion_suffix_validator..optional_fnrrrrrrN) rr rrBrrrr`rr') rrrrrrrrrrrrrs @@r"common_completion_suffix_validatorrPsIMLKb!!G)))W8H-H-H0000#BMAAAM &++--Fb}bbR_bbb 9EEEE    N( =  % %m5 % A A E E G G  ( /77eDD)6)>)>tU)K)K&a@^aaa }   " " NsKNNN NM = 2M 2 222 3 7 @ @V[ @ \ \ ` ` b b  Zg Md ]/G]]]  3 3 3 3 3 3 3  '#!    rcd d}d}d}d}|jjdddks|jjdddkrd }d }|}t d ||| S)z This validator will suggest to add a space at the start of the completion if it doesn't already exist. This helps with tokenization. rIrr!cD|dd|d<|S)NrBc:|drdnd|zS)Nrr$) startswith)r]s rrWzLcompletions_space_start_validator..add_space_start..s"cARAR;[22X[_`:`r)r_rVs radd_space_startz:completions_space_start_validator..add_space_starts&L///0`0`aa,rNrxrrz - The completion should start with a whitespace character (` `). This tends to produce better results due to the tokenization we use. See https://platform.openai.com/docs/guides/fine-tuning/preparing-your-dataset for more detailsz=Add a whitespace character to the beginning of the completioncompletion_space_startrnrN)rBrnuniquevaluesr )rrrrrs r!completions_space_start_validatorrs LKM }!$$&&!++r}/CA/Fq/IS/P/PB V %  %#!    rr-rRemediation | Nonecdfd }|d}|d}|dz|krtdd d d d d |SdS)zt This validator will suggest to lowercase the column values, if more than a third of letters are uppercase. rIrr!cL|j|<|Sr=r0)rIr-s r lower_casez(lower_case_validator..lower_cases#fIM''))& rc4td|DS)Nc3jK|].}||*dV/dSrxN)isalphaisupperr;s r z9lower_case_validator....A0]0]q0]QRQZQZQ\Q\0]0]0]0]0]0]0]rsumrVs rrWz&lower_case_validator..S0]0]A0]0]0]-]-]rc4td|DS)Nc3jK|].}||*dV/dSr)rislowerr;s rrz9lower_case_validator....rrrrVs rrWz&lower_case_validator..rrr rz - More than a third of your `z%` column/key is uppercase. Uppercase zs tends to perform worse than a mixture of case encountered in normal language. We recommend to lower case the data if that makes sense in your domain. See https://platform.openai.com/docs/guides/fine-tuning/preparing-your-dataset for more detailsz'Lowercase all your data in column/key `r?rnNrN)r_rr )rr-r count_upper count_lowers ` rlower_case_validatorrs V*""#]#]^^bbddKV*""#]#]^^bbddKQ$$iFiiioiiiL6LLL"     4rfname'tuple[pd.DataFrame | None, Remediation]cd}d}d}d}d}tj|r |ds'|drk|drdnd\}}d|d}d|d }t j||t d }n|d rgd }d}t j |} | j } t| dkr|dz }t j |td }ne|drd}d}t|d5} | } t jd| dD|td }dddn #1swxYwYn|drxt j|dtd }t|dkr4d}d}t j|td }nn|dr t j|dtd }t|dkr/t j|td }nd}d}ns#t$$r1t j|td }Yn9wxYwd }d!|vr&|d"|d#|d!d$d%z }n |d"|d&z }nV#t$t&f$r<|d!d$}d'|d(|d)|d*}Yn wxYwd+|d,}t+d-|||.}||fS)/z This function will read a file saved in .csv, .json, .txt, .xlsx or .tsv format using pandas. - for .xlsx it will read the first sheet - for .txt it will assume completions and split on newline Nz.csvz.tsv)CSV,)TSV z= - Based on your file extension, your file is formatted as a z filez Your format `z` will be converted to `JSONL`)sepdtyper$z.xlsxzH - Based on your file extension, your file is formatted as an Excel filez/Your format `XLSX` will be converted to `JSONL`rxz - Your Excel file contains more than one sheet. Please either save as csv or ensure all data is present in the first sheet. WARNING: Reading only the first sheet...)rz.txtz9 - Based on your file extension, you provided a text filez.Your format `TXT` will be converted to `JSONL`rcg|]}d|gS)r$r)r2lines rr4z#read_any_format..sDDD"dDDDrr})r5r.jsonlT)linesrz^ - Your JSONL file appears to be in a JSON format. Your file will be converted to JSONL formatz/Your format `JSON` will be converted to `JSONL`z.jsonz^ - Your JSON file appears to be in a JSONL format. Your file will be converted to JSONL formatz]Your file must have one of the following extensions: .CSV, .TSV, .XLSX, .TXT, .JSON or .JSONLrz Your file `z` ends with the extension `.z` which is not supported.z` is missing a file extension.z Your file `z!` does not appear to be in valid z9 format. Please ensure your file is formatted as a valid z file.zFile z does not exist.read_any_format)rrrr)ospathisfiler1endswithpdread_csvrfillna ExcelFile sheet_namesr' read_excelopenread DataFramesplit read_json ValueError TypeErrorupperr ) rrC remediationrrrrfile_extension_str separatorxlssheetsfcontents rrrsKMMI B w~~e@4< v{{}}%%f--7 V1G1G1O1O7 V@E @V@VW]@^@^0q dq-"InUgnnn!c0B b b b [ISAAAHHLL''000 V k Q l5))v;;??!&NNM]5444;;B??''//( V \ P %%%!ffhhGDD d0C0CDDD &!fRjj !!!!!!!!!!!!!!!''11 V\%t3???FFrJJr77a<<%FM$UMe3777>>rBBBB''00 V Ce4sCCCJJ2NNB2ww!||\%s;;;BB2FF)J (Y !CCCe3777>>rBBBBBC t%<<"C"C"CSXS^S^_bScScdfSg"C"C"CCII!U!U!U!UUII& v v v!&S!1!1"!5!;!;!=!= vevvN`vv\nvvvIII v 4E333  ## K {?s^FO.A!H OHO"H#C O/A5M%$O%8N ON  8OA P&%P&c^t|}d}|dkrd|d}td|S)z This validator will infer the likely fine-tuning format of the data, and display it to the user if it is classification. It will also suggest to use ada and explain train/validation split benefits. NrzK - Based on your data it seems like you're trying to fine-tune a model for z - For classification, we recommend you try one of the faster and cheaper models, such as `ada` - For classification, you can estimate the expected model performance by keeping a held out dataset, which is not used for trainingr%r&)rr )rrrs rformat_inferrer_validatorr sR b!!GM"""VgnVVV N- H H HHrrc*|jDtjd|jd|jdtjd|j$tj|j|j||}|S)zs This function will apply a necessary remediation to a dataframe, or print an error message if one exists. Nz ERROR in z validator: z Aborting...rx) rr~stderrrrexitrrr)rrs rapply_necessary_remediationr(s( m)9mm{G\mmmnnn   , 2333+  % %b ) ) Ir input_text auto_acceptboolctj||r!tjddStdkS)NzY Tn)r~rrinputr1)rrs raccept_suggestionr6sRJZ    t 77==??c !!rtuple[pd.DataFrame, bool]cd}d|jd}|j0t||r |jJ||}d}|j(tjd|jd||fS)zc This function will apply an optional remediation to a dataframe, based on the user input. Fz- [Recommended] z [Y/n]: NTz- [Necessary] r})rrrrr~rr)rrroptional_appliedrs rapply_optional_remediationr>s FK$<FFFJ+ Z 5 5 $*666((,,B#  , G+*CGGGHHH  rNonec"t|}d}|dkrt|}|dz}n-|d}|dz}dd }||d z}tjd |ddS)z? Estimate the time it'll take to fine-tune the dataset g?rg ףp= ?T)rcg|?5^?timefloatr!rc|dkrt|ddS|dkrt|dz ddS|dkrt|dz ddSt|dz ddS) N<r z secondsiz minutesiQz hoursz days)round)rs r format_timez.estimate_fine_tuning_time..format_time]s "99D!nn... . D[[D2Iq))333 3 E\\D4K++333 3D5L!,,333 3rz:Once your model starts training, it'll approximately take z~ to train a `curie` model, and less for `ada` and `babbage`. Queue will approximately take half an hour per job ahead of you. N)rrr!r)rr' memory_usagerr~rr)r ft_format expected_timer%sizer! time_strings restimate_fine_tuning_timer(Ps ##IM$$$2ww $t+ T**..00v 4444+mc122KJ R[ R R Rrrc|rddgndg}d} |dkrd|dndfd|D}td |Ds|S|d z }>) N_train_validr$rTz ()cjg|]/}tjdd|d0S)r _preparedr)rrsplitext)r2rr index_suffixs rr4z!get_outfnames..rsExxxekrw//66q9``F`L```xxxrc3TK|]#}tj|V$dSr=)rrr)r2rs rrz get_outfnames..ss0??27>>!$$??????rrx)r`)rrsuffixesicandidate_fnamesr0s` @r get_outfnamesr5ms',6(##2$H A$%EEyAyyyyr xxxxxowxxx??.>????? $# # Q rtuple[int, object]c|j}d}|dkr$|jjd}||fS)Nr r)rBr value_countsrc)r n_classes pos_classs rget_classification_hyperparamsr;xsI %%''IIA~~M..006q9 i rany_remediationsc  t|}t|jd}t|jd}d}d}|dkrt ||rd}d} |dd } |dd } t | d krd | d nd} d }|s?|s=tj d|d| d| d| d t|dSt ||rt||} |rt | dkrd| d vr d| dvsJd}tt ||z tt |dz}||d}||j}|ddg| d dddd|ddg| dddddt%|\}}| dz } |dkr | d |dz } nF| d!|z } n=t | dksJ|ddg| d dddd|rd"ndd#zd$| z}|r d%| ddnd}t | d krdnd&| d}tj d'|d(| d d|| d)|| d t|dStj d*dS)+aQ This function will write out a dataframe to a file, if the user would like to proceed, and also offer a fine-tuning command with the newly created file. For classification it will optionally ask the user if they would like to split the data into train/valid files, and modify the suggested command to include the valid set. rrFzQ- [Recommended] Would you like to split into training and validation set? [Y/n]: rTr$r}rrz Make sure to include `stop=["z;"]` so that the generated texts ends at the expected place.z@ Your data will be written to a new JSONL file. Proceed [Y/n]: zK You can use your file for fine-tuning: > openai api fine_tunes.create -t ""ue After you’ve fine-tuned a model, remember that your prompt has to end with the indicator string `zX` for the model to start generating completions, rather than continuing with the prompt.r trainvalidrxig?*)r random_staterArBrecordsN)rorient force_asciiindentz! --compute_classification_metricsz" --classification_positive_class "z --classification_n_classes r]z to `z` and `z -v "ucAfter you’ve fine-tuned a model, remember that your prompt has to end with the indicator string `z Wrote modified filezd` Feel free to take a look! Now use that file when fine-tuning: > openai api fine_tunes.create -t "z z#Aborting... did not write the file )rrrArBrrr'r~rrr(r5maxintsamplerrcto_jsonr;rp)rrr<rr$common_prompt_suffixrrradditional_params%common_prompt_suffix_new_line_handled)common_completion_suffix_new_line_handledoptional_ending_stringfnamesMAX_VALID_EXAMPLESn_traindf_traindf_validr9r: files_string valid_stringseparator_reminders rwrite_out_filerXs  ##I*298DDD.r}8LLL EdJ$$$ Z 5 5 E,@,H,Hu,U,U)0H0P0PQUW\0]0]- 8 9 9A = = P)R P P P P  VJ .AE.A  x\a x xdu x x_D x x^t x x x    ""%%%%% :{ 3 3(Aue,,  v;;!##6!9(<(<FSTIAUAUAUU!% #b''$66CGGcM8J8JKKGyy7y<>&;Q;QR /4<+vay++++" 899Q>> Bwx]www   zL z z[abc[d z zgs zuF z zL^ z`v z z z    ""%%%%% ?@@@@@rcd}t|jjdkrdSt|jt||z krdSdS)z> Infer the likely fine-tuning task type from the data rrtrzconditional generation)rrArr'rBunique)rCLASSIFICATION_THRESHOLDs rrrsl ! 29=    1$$&& 2=   ! !""SWW/G%GGG # #rrseriesrcd} |dkr |jt|dz dn|jdt|dz}|dkrn ||jdkrn|jd}~|S)zQ Finds the longest common suffix or prefix of all the values in a series r$TrrxNr)rr'rr)r]r common_xfix common_xfixess rrrsK 259X5E5EFJ[))A-.00 1 16:VlX[\gXhXhklXlVlKm   " "a ' '  M03 3 3 '.q1K 2 rz,Callable[[pd.DataFrame], Remediation | None]r Validatorlist[Validator]ctddttttt ddt ttttgS)Nc"t|dSrr@rVs rrWz get_validators..s,Q99rc"t|dSrrerVs rrWz get_validators..s,Q ==rc"t|dSrrrVs rrWz get_validators..s&q(33rc"t|dSrrhrVs rrWz get_validators..s&q,77r) r*rRrgr rrrrrrrrrrrget_validatorsrjsE99==#!!!3377&&**) r validatorswrite_out_file_funcCallable[..., Any]cg}||||D]4}||}|%||t||}5td|D}td|D} d} |r=tjd|D]}t |||\}} | p| } ntjd| p| } |||| |dS)Nc.g|]}|j|j|Sr=)rrr2rs rr4z$apply_validators..s3   '3{7P7\ 7\7\7\rc g|] }|j | Sr=)rrps rr4z$apply_validators..s gggAZAfAfAfAfrFz? Based on the analysis we will perform the following actions: z No remediations found. )appendrr`r~rrr) rrrrkrrloptional_remediations validator&any_optional_or_necessary_remediationsany_necessary_appliedany_optional_appliedr!any_optional_or_necessary_applieds rapply_validatorsrysa02$$[111>> imm  " ! ( ( 5 5 5,R==B-0  4   ..* gg(=ggg!-9 ]^^^0 L LK#=b+{#[#[ B #7#K;K  L 7888(<(U@U%E#DkRRRRRr)rr r!r )rr r+rr!r )rr rCrDr!r )rB)rr rSrr!r )rr r-rr!r)rrrCrDr!r)rrrr r!r)rrrrr!r)rr rr rrr!r)rr r!r)rrrrr!rD)rr r!r6) rr rrr<rrrr!r)rr r!r)r)r]rrrr!r)r!rb)rr rrrrrkrbrrrlrmr!r), __future__rrr~typingrrrrrtyping_extensionsr _extrasr rr rr*r@rRrgrrrrrrrrrrr rrrr(r5r;rXrrrarrjryrrrr~s6""""""" ??????????????''''''""""""$$$$$*$$$W19QRRR I I I I!!!!HHPQ]F^<4FN|D\2""""JAAAAH$$$$N!!!!HAAAAH2.&.|$<VVVVVr I I I I    """"    $:    HAHAHAHAV $ $ $ $$F EEEE('S'S'S'S'S'Sr