g ddlmZddlmZddlmZddlmZddlmZddlmZddlm Z ddl m Z dd l m Z dd l mZdd l mZdd lmZdd lmZerddlmZddlmZddlmZddlmZddlmZddiZGddZddZ ddZy)) annotations)copy)partial) TYPE_CHECKING)Any)Callable)Sequence)is_simple_aggregation)parse_into_exprs)_std)_var) parse_version) remove_prefix)Column) GroupedDataSparkLikeLazyFrame)IntoSparkLikeExpr) CompliantExprlencountc@eZdZ ddZ ddZddZy)SparkLikeLazyGroupByc"||_||_|rM|jjj|jj|j|_y|jjj|j|_y)N)subset)_df_keys _native_framedropnagroupBy_grouped)selfdfkeysdrop_null_keyss R/var/www/openai/venv/lib/python3.12/site-packages/narwhals/_spark_like/group_by.py__init__zSparkLikeLazyGroupBy.__init__sp  TDHH22999LTTDM;DHH22::DJJGDMcDt|d|jji|}t|j}|D]6}|j d}t ||j|j 8t|j||j|jS)N namespacezAnonymous expressions are not supported in group_by.agg. Instead of `nw.all()`, try using a named expression, such as `nw.col('a', 'b')` ) r r__narwhals_namespace__rr _output_names ValueErrorextend agg_pysparkr!_from_native_frame)r"aggs named_aggsexprs output_namesexprmsgs r&aggzSparkLikeLazyGroupBy.agg-s !  hh557   #'tzz"2 D!!)+ !o%    2 2 3 MM  JJ  # #   r(ctddlm}|||jj|jjS)Nrr)backend_versionversion)narwhals._spark_like.dataframerr_backend_version_version)r"r#rs r&r0z'SparkLikeLazyGroupBy._from_native_frameJs-E!  9 9488CTCT  r(N)r#rr$ list[str]r%boolreturnNone)r1rr2rr@r)r#rr@r)__name__ __module__ __qualname__r'r7r0r(r&rrsX H  H H H  H   (    : r(rc |dvrDddl}t|dk(rtnt|j ddt |j Sddlm}t||S)N>stdvarrrGddof)rI np_version) functions) numpyrr r getr __version__ pyspark.sqlrLgetattr) function_namekwargsnpFs r&get_spark_functionrVRsR&!U*DFA&$R^^4  + 1m $$r(c |D]}t|rd}t|i}|D]^}|jdk(r|j d}t |t j |j|j}t|fi|j}|j|jD cic]} | ||dc} |jdk7s|j |j d}t |t|jd}t j ||} t| fi|j}|jt|j|jD cic]\} } | || c} } a|jD cgc]\} } | j| }} } |j |}||Scc} wcc} } wcc} } w#t$r}d}t#||d}~wwxYw)NavNon-trivial complex aggregation found. Hint: you were probably trying to apply a non-elementary aggregation with a dask dataframe. Please rewrite your query such that group-by aggregations are elementary. For example, instead of: df.group_by('a').agg(nw.col('b').round(2).mean()) use: df.with_columns(nw.col('b').round(2)).group_by('a').agg(nw.col('b').mean()) rz_Safety assertion failed, please report a bug to https://github.com/narwhals-dev/narwhals/issuesrJzcol->zFailed to aggregated - does your aggregation function return a scalar? Please see: https://narwhals-dev.github.io/narwhals/pandas_like_concepts/improve_group_by_operation/)r r-_depthr,AssertionErrorPOLARS_TO_PYSPARK_AGGREGATIONSrN_function_namerV_kwargsupdate _root_namesrzipitemsaliasr7 RuntimeError)groupedr3r$from_dataframer5r6simple_aggregationsrRagg_func output_namepyspark_function root_namenamecol_ agg_columns result_simpleexcs r&r/r/`s! $T*f S/ !.0 ;;! !!)w$S)):>>##T%8%8M*-H4<<HH  & &CGCUCUVCUKhtAw//CUV   KK1  0 0 8Drdz#Callable[[Any], SparkLikeLazyFrame]r@r) __future__rr functoolsrtypingrrrr narwhals._expression_parsingr r narwhals._spark_like.utilsr r narwhals.utilsrrrPrrr;rnarwhals._spark_like.typingrnarwhals.typingrrZrrVr/rEr(r&rxs" >9++(("'A=-#(!12 2 j %@) @) *@) @)8 @)  @)r(