*j=QddlmZddlmZmZddlZddlmZmZm Z m Z ddl Z ddl mZddlmZddlmZddlZddlmZmZerdd lmZdd lmZmZdd Ze d dd Ze d dd Z d ddZ ddZddZ d ddZ ddZ!ed d d!dZ"y)") annotations)abc defaultdictN) TYPE_CHECKINGAny DefaultDictoverloadconvert_json_to_lines) set_module) is_scalar) DataFrameSeries)Iterable) IgnoreRaiseScalarcF|ddk(s |ddk(r|S|dd}t|S)zJ Helper function that converts JSON lists to line delimited JSON. r[]r )ss ;C:\FundamentalWorkbench\vendor\pandas\io\json\_normalize.pyconvert_to_line_delimitsr's4 Q43;1R5C< !BA  ##cyNdsprefixseplevel max_levels rnested_to_recordr%4srcyrrrs rr%r%>src d}t|tr|g}d}g}|D]}tj|}|j D]\} } t| t s t | } |dk(r| } n||z| z} t| tr|!||k\r|dk7r|j | } | || <d|j | } |jt| | ||dz||j||r|dS|S)a A simplified json_normalize Converts a nested dict into a flat dict ("record"), unlike json_normalize, it does not attempt to extract a subset of the data. Parameters ---------- ds : dict or list of dicts prefix: the prefix, optional, default: "" sep : str, default '.' Nested records will generate names separated by sep, e.g., for sep='.', { 'foo' : { 'bar' : 0 } } -> foo.bar level: int, optional, default: 0 The number of levels in the json string. max_level: int, optional, default: None The max depth to normalize. Returns ------- d - dict or list of dicts, matching `ds` Examples -------- >>> nested_to_record( ... dict(flat1=1, dict1=dict(c=1, d=2), nested=dict(e=dict(c=1, d=2), d=2)) ... ) {'flat1': 1, 'dict1.c': 1, 'dict1.d': 2, 'nested.e.c': 1, 'nested.e.d': 2, 'nested.d': 2} FTrr) isinstancedictcopydeepcopyitemsstrpopupdater%append) r r!r"r#r$ singletonnew_dsdnew_dkvnewkeys rr%r%HsXI"dT F  a GGIDAqa%Fz#) a&%%9*<A: ! A$%E&M ! A LL)!VS%!)YO P-.  e36ay Mrct|trD|jD]/\}}|||}|s|j|}t ||||1|S|||<|S)a3 Main recursive function Designed for the most basic use case of pd.json_normalize(data) intended as a performance improvement, see #15621 Parameters ---------- data : Any Type dependent on types contained within nested Json key_string : str New key (with separator(s) in) for data normalized_dict : dict The new normalized/flattened Json dict separator : str, default '.' Nested records will generate names separated by sep, e.g., for sep='.', { 'foo' : { 'bar' : 0 } } -> foo.bar data key_stringnormalized_dict separator)r(r)r, removeprefix_normalize_json)r:r;r<r=keyvaluenew_keys rr?r?su.$**,JC# YKu5G!..y9 " /#   ' '+ # rc |jDcic]\}}t|tr||}}}t|jDcic]\}}t|ts||c}}di|}i||Scc}}wcc}}w)aw Order the top level keys and then recursively go to depth Parameters ---------- data : dict or list of dicts separator : str, default '.' Nested records will generate names separated by sep, e.g., for sep='.', { 'foo' : { 'bar' : 0 } } -> foo.bar Returns ------- dict or list of dicts, matching `normalized_json_object` r9)r,r(r)r?)r:r=r5r6 top_dict_ nested_dict_s r_normalize_json_orderedrGs#'**,J,$!QjD6IA,IJ"#zz| C|tq!z!T/Bad| C L )i (< ((K CsA=A= B &B ci}t|trt||}|St|tr|Dcgc]}t ||}}|S|Scc}w)a An optimized basic json_normalize Converts a nested dict into a flat dict ("record"), unlike json_normalize and nested_to_record it doesn't do anything clever. But for the most basic use cases it enhances performance. E.g. pd.json_normalize(data) Parameters ---------- ds : dict or list of dicts sep : str, default '.' Nested records will generate names separated by sep, e.g., for sep='.', { 'foo' : { 'bar' : 0 } } -> foo.bar Returns ------- frame : DataFrame d - dict or list of dicts, matching `normalized_json_object` Examples -------- >>> _simple_json_normalize( ... { ... "flat1": 1, ... "dict1": {"c": 1, "d": 2}, ... "nested": {"e": {"c": 1, "d": 2}, "d": 2}, ... } ... ) {'flat1': 1, 'dict1.c': 1, 'dict1.d': 2, 'nested.e.c': 1, 'nested.e.d': 2, 'nested.d': 2} )r:r=r")r(r)rGlist_simple_json_normalize)r r"normalized_json_objectrownormalized_json_lists rrKrKsgV "d!8bC!P "! B PRSPR 6s DPRS## !! TsAc:|yt|try|D]}t|tr<|D]6}t|trtdt |j d|Ot|tr`tdt |j d|y)aD Validate that meta parameter contains only strings or lists of strings. Parameters ---------- meta : str or list of str or list of list of str or None The meta parameter to validate. Raises ------ TypeError If meta contains elements that are not strings or lists of strings. Nz9All elements in nested meta paths must be strings. Found z: zBAll elements in 'meta' must be strings or lists of strings. Found )r(r-rJ TypeErrortype__name__)metaitemsubitems r_validate_metarVs |$ dD !!'3/#!!%g!7!7 87+G D#&d,,-Rx9 rpandasc :t| d dfd dfd t|tr |j}nd}t|tr |s t St|t r|g}nt|tjrt|tsxt |}t|D]^\} } t| t rt| rtj| ri|| <=dt| j} t!| nt"| ||t t%||S|Ft'd|Drt)|}t ||} | j+fd  } | St|ts|g}|g}nt|ts|g}|D cgc]} t| tr| n| gc} ggt-tDcgc]}j/|c}ddf d ||id t } | j+fd } j1D]\}}|||z}|| vrt3d|dt5j6|t8}|j:dkDr=t5j<t?|ft8}t|D] \} }||| < |jA| |<||jA| _| Scc} wcc}w)a> Normalize semi-structured JSON data into a flat table. This method is designed to transform semi-structured JSON data, such as nested dictionaries or lists, into a flat table. This is particularly useful when handling JSON-like data structures that contain deeply nested fields. Parameters ---------- data : dict, list of dicts, or Series of dicts Unserialized JSON objects. record_path : str or list of str, default None Path in each object to list of records. If not passed, data will be assumed to be an array of records. meta : list of paths (str or list of str), default None Fields to use as metadata for each record in resulting table. meta_prefix : str, default None String to prefix records with dotted path, e.g. foo.bar.field if meta is ['foo', 'bar']. record_prefix : str, default None String to prefix records with dotted path, e.g. foo.bar.field if path to records is ['foo', 'bar']. errors : {'raise', 'ignore'}, default 'raise' Configures error handling. * 'ignore' : will ignore KeyError if keys listed in meta are not always present. * 'raise' : will raise KeyError if keys listed in meta are not always present. sep : str, default '.' Nested records will generate names separated by sep. e.g., for sep='.', {'foo': {'bar': 0}} -> foo.bar. max_level : int, default None Max number of levels(depth of dict) to normalize. if None, normalizes all levels. Returns ------- DataFrame The normalized data, represented as a pandas DataFrame. See Also -------- DataFrame : Two-dimensional, size-mutable, potentially heterogeneous tabular data. Series : One-dimensional ndarray with axis labels (including time series). Examples -------- >>> data = [ ... {"id": 1, "name": {"first": "Coleen", "last": "Volk"}}, ... {"name": {"given": "Mark", "family": "Regner"}}, ... {"id": 2, "name": "Faye Raker"}, ... ] >>> pd.json_normalize(data) id name.first name.last name.given name.family name 0 1.0 Coleen Volk NaN NaN NaN 1 NaN NaN NaN Mark Regner NaN 2 2.0 NaN NaN NaN NaN Faye Raker >>> data = [ ... { ... "id": 1, ... "name": "Cole Volk", ... "fitness": {"height": 130, "weight": 60}, ... }, ... {"name": "Mark Reg", "fitness": {"height": 130, "weight": 60}}, ... { ... "id": 2, ... "name": "Faye Raker", ... "fitness": {"height": 130, "weight": 60}, ... }, ... ] >>> pd.json_normalize(data, max_level=0) id name fitness 0 1.0 Cole Volk {'height': 130, 'weight': 60} 1 NaN Mark Reg {'height': 130, 'weight': 60} 2 2.0 Faye Raker {'height': 130, 'weight': 60} Normalizes nested data up to level 1. >>> data = [ ... { ... "id": 1, ... "name": "Cole Volk", ... "fitness": {"height": 130, "weight": 60}, ... }, ... {"name": "Mark Reg", "fitness": {"height": 130, "weight": 60}}, ... { ... "id": 2, ... "name": "Faye Raker", ... "fitness": {"height": 130, "weight": 60}, ... }, ... ] >>> pd.json_normalize(data, max_level=1) id name fitness.height fitness.weight 0 1.0 Cole Volk 130 60 1 NaN Mark Reg 130 60 2 2.0 Faye Raker 130 60 >>> data = [ ... { ... "id": 1, ... "name": "Cole Volk", ... "fitness": {"height": 130, "weight": 60}, ... }, ... {"name": "Mark Reg", "fitness": {"height": 130, "weight": 60}}, ... { ... "id": 2, ... "name": "Faye Raker", ... "fitness": {"height": 130, "weight": 60}, ... }, ... ] >>> series = pd.Series(data, index=pd.Index(["a", "b", "c"])) >>> pd.json_normalize(series) id name fitness.height fitness.weight a 1.0 Cole Volk 130 60 b NaN Mark Reg 130 60 c 2.0 Faye Raker 130 60 >>> data = [ ... { ... "state": "Florida", ... "shortname": "FL", ... "info": {"governor": "Rick Scott"}, ... "counties": [ ... {"name": "Dade", "population": 12345}, ... {"name": "Broward", "population": 40000}, ... {"name": "Palm Beach", "population": 60000}, ... ], ... }, ... { ... "state": "Ohio", ... "shortname": "OH", ... "info": {"governor": "John Kasich"}, ... "counties": [ ... {"name": "Summit", "population": 1234}, ... {"name": "Cuyahoga", "population": 1337}, ... ], ... }, ... ] >>> result = pd.json_normalize( ... data, "counties", ["state", "shortname", ["info", "governor"]] ... ) >>> result name population state shortname info.governor 0 Dade 12345 Florida FL Rick Scott 1 Broward 40000 Florida FL Rick Scott 2 Palm Beach 60000 Florida FL Rick Scott 3 Summit 1234 Ohio OH John Kasich 4 Cuyahoga 1337 Ohio OH John Kasich >>> data = {"A": [1, 2]} >>> pd.json_normalize(data, "A", record_prefix="Prefix.") Prefix.0 0 1 1 2 Returns normalized data with columns prefixed with the given string. c|} t|tr|D]}| t|||} |S||} |S#t$rD}|rtd|d|dk(rtjcYd}~Std|d|d|d}~wwxYw)zInternal function to pull fieldNzKey zS not found. If specifying a record_path, all elements of data should have the path.ignorez) not found. To replace missing values of z% with np.nan, pass in errors='ignore')r(rJKeyErrornpnan)jsspecextract_recordresultfieldeerrorss r _pull_fieldz#json_normalize.._pull_fields $%!E~&uo-#E]F"(    1#12!vv 1#FqcJ67 s%)99 B&B(B.BBc||d}t|ts=tj|rg}|St dt |j d||S)z Internal function to pull field for records, and similar to _pull_field, but require to return list. And will raise error if has non iterable value. T)r`z(Path must contain list or null, but got z at )r(rJpdisnullrPrQrR)r^r_rares r _pull_recordsz%json_normalize.._pull_recordssn Rd;&$'yy    #F|445T$C rNz9All items in data must be of type dict or NA-like, found rI)indexc3~K|]0}|jDcgc]}t|tc}2ycc}wwr)valuesr(r)).0yxs r z!json_normalize..5s0G$QQXXZ8Z 1d#Z8$8s =8 =r"r$c|Srrro record_prefixs rz json_normalize..@s qc5Jr)columnsrc p t|tr|g}t|dkDrW|D]Q}t dD]&\}}|dzt|k(s ||d||<( ||d|dd||dzSy|D]} ||d}|Dcgc]"}t|trt |n|$}}j t|t dD]<\}}|dzt|kDr||} n  |||d} |j | >j |ycc}w)NrT)strictrrr#rq)r(r)lenzipr%r0extend)r:path seen_metar#objvalr@recsrmeta_val_metareri_recursive_extractlengthsr$ meta_keys meta_valsrecordsr"s rrz*json_normalize.._recursive_extractSsa dD !6D t9q= #E9T BHCqyCH,)4S#b')B #!C#3tAw<ab9ETUIV $S$q'2 " ""!T*%QC9E" s4y) #E9T BHCqy3s8+#,S>#.sCK#@cN))(3 !C t$#s'D3ryc|Srrrss rruz json_normalize..vsM?1#1FrzConflicting metadata name z, need distinguishing prefix )dtyper)F)r^dict[str, Any]r_ list | strr`boolreturnzScalar | Iterable)r^rr_rrrJ)r)r#intrNone)!rVr(rrjrJrr)rrr- enumerater rgisnarQrRrPNotImplementedErrorrKanyr%renamerjoinr, ValueErrorr\arrayobjectndimemptyrzrepeat)r: record_pathrS meta_prefixrtrdr"r$rjirTmsgramrr5r6rlrrerirrrrrs ```` @@@@@@@@rjson_normalizer/sT4FK ",>B :($ $d{ D$ v D#,, ' 40EDz GAt$%2774=Q!$Z0013 n$'"!  L    !  /#>eLL G$G G$DcYGD4u-  $]]+J]KF  T *"m  | d #v8< =1*Q%QA3 . =EGG(.I*/0%3#%0I%%<t["A6 w F 'FG!1  "aA ;,QC/LM  !6* ;;?XXs1viv6F#A,3q 'MM'*q %"& ||G, MI >1s =L3L)rr-rr-)....) r r)r!r-r"r-r#rr$ int | Nonerr) r z list[dict]r!r-r"r-r#rr$rrzlist[dict[str, Any]])rD.rN) r dict | list[dict]r!r-r"r-r#rr$rrz%dict[str, Any] | list[dict[str, Any]]) r:rr;r-r<rr=r-rr)r:rr=r-rr)r)r rr"r-rzdict | list[dict] | Any)rS"str | list[str | list[str]] | Nonerr)NNNNraiserN)r:zdict | list[dict] | Seriesrzstr | list | NonerSrr str | Nonertrrdrr"r-r$rrr)# __future__r collectionsrrr*typingrrrr numpyr\pandas._libs.writersr pandas.util._decoratorsr pandas.core.dtypes.commonr rWrgrrcollections.abcrpandas._typingrrrr%r?rGrKrVrrrrrsA# 6./ ( $                        NN N N  N  N + Nb& &&$& &  &R)62"2" 2"2"j> H&*/3" $! ^ $^"^ -^ ^  ^  ^ ^^^^r