dBddlmZddlmZmZddlZddlZddlmZm Z m Z ddl Z ddl mZddlmZmZddlZddlmZd-d Z d.d/dZd0dZd1dZ d2d3d Z d4d5d,ZdS)6) annotations)abc defaultdictN)Any DefaultDictIterableconvert_json_to_lines) IgnoreRaiseScalar) DataFramesstrreturnch|ddks|ddkr|S|dd}t|S)zJ Helper function that converts JSON lists to line delimited JSON. r[]r )rs U/var/www/html/t/fyr/venv311/lib/python3.11/site-packages/pandas/io/json/_normalize.pyconvert_to_line_delimitsrs= Q43;;1R5C<< !B$A  # ##.prefixseplevelint max_level int | Nonec Hd}t|tr|g}d}g}|D]}tj|}|D]\} } t| t st | } |dkr| } n||z| z} t| tr|'||kr!|dkr|| } | || <x|| } |t| | ||dz|| ||r|dS|S)a A simplified json_normalize Converts a nested dict into a flat dict ("record"), unlike json_normalize, it does not attempt to extract a subset of the data. Parameters ---------- ds : dict or list of dicts prefix: the prefix, optional, default: "" sep : str, default '.' Nested records will generate names separated by sep, e.g., for sep='.', { 'foo' : { 'bar' : 0 } } -> foo.bar level: int, optional, default: 0 The number of levels in the json string. max_level: int, optional, default: None The max depth to normalize. Returns ------- d - dict or list of dicts, matching `ds` Examples -------- >>> nested_to_record( ... dict(flat1=1, dict1=dict(c=1, d=2), nested=dict(e=dict(c=1, d=2), d=2)) ... ) {'flat1': 1, 'dict1.c': 1, 'dict1.d': 2, 'nested.e.c': 1, 'nested.e.d': 2, 'nested.d': 2} FTrNr) isinstancedictcopydeepcopyitemsrpopupdatenested_to_recordappend) dsrrrr singletonnew_dsdnew_dkvnewkeys rr)r)*sPXI"dT F  a  GGII Q QDAqa%% FFzz#) a&& %%9*<*<A:: ! A$%E&M ! A LL)!VS%!)YOO P P P P eay Mrdatar key_stringnormalized_dictdict[str, Any] separatorct|trp|D]Z\}}|||}|s8tjdkrddlm}|||}n||}t||||[n|||<|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 ) r) removeprefixr3r4r5r7)r"r#r&sys version_infopandas.util._str_methodsr;_normalise_json)r3r4r5r7keyvaluenew_keyr;s rr@r@{s.$+**,,  JC#5Y555G >#f,,EEEEEE*l7I>>GG%229==G " /#       $'+ # rcd|D}td|Ddi|}i||S)aw Order the top level keys and then recursively go to depth Parameters ---------- data : dict or list of dicts separator : str, default '.' Nested records will generate names separated by sep, e.g., for sep='.', { 'foo' : { 'bar' : 0 } } -> foo.bar Returns ------- dict or list of dicts, matching `normalised_json_object` cDi|]\}}t|t||Sr"r#.0r0r1s r z+_normalise_json_ordered..s-JJJ$!QjD6I6IJAJJJrcDi|]\}}t|t||SrFrGrHs rrJz+_normalise_json_ordered..s- C C Ctq!z!T/B/B Ca C C Crrr<)r&r@)r3r7 top_dict_ nested_dict_s r_normalise_json_orderedrNshKJ$**,,JJJI" C Ctzz|| C C C L )i (< ((rr+dict | list[dict]dict | list[dict] | Anyci}t|trt|}n%t|trfd|D}|S|S)a A optimized basic json_normalize Converts a nested dict into a flat dict ("record"), unlike json_normalize and nested_to_record it doesn't do anything clever. But for the most basic use cases it enhances performance. E.g. pd.json_normalize(data) Parameters ---------- ds : dict or list of dicts sep : str, default '.' Nested records will generate names separated by sep, e.g., for sep='.', { 'foo' : { 'bar' : 0 } } -> foo.bar Returns ------- frame : DataFrame d - dict or list of dicts, matching `normalised_json_object` Examples -------- >>> _simple_json_normalize( ... { ... "flat1": 1, ... "dict1": {"c": 1, "d": 2}, ... "nested": {"e": {"c": 1, "d": 2}, "d": 2}, ... } ... ) {'flat1': 1, 'dict1.c': 1, 'dict1.d': 2, 'nested.e.c': 1, 'nested.e.d': 2, 'nested.d': 2} )r3r7c2g|]}t|S)r)_simple_json_normalize)rIrowrs r z*_simple_json_normalize..s'SSS 6s D D DSSSr)r"r#rNlist)r+rnormalised_json_objectnormalised_json_lists ` rrTrTsmV "d$!8bC!P!P!P B  $SSSSPRSSS## !!rraise record_pathstr | list | Nonemeta"str | list[str | list[str]] | None meta_prefix str | None record_prefixerrorsr r c <  ddfd d fd t|tr|stSt|tr|g}nFt|tjr%t|t st|}nt|&|$|" tt|S|:td|Drt|}t|St|ts|g}|g}nt|ts|g}d|D ggttfd Dd!d" f d ||idt}| fd} D]T\} } ||| z} | |vrtd| dtj| t"|| <U|S)#a Normalize semi-structured JSON data into a flat table. Parameters ---------- data : dict or list 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 If True, prefix records with dotted (?) path, e.g. foo.bar.field if meta is ['foo', 'bar']. record_prefix : str, default None If True, 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 ------- frame : DataFrame Normalize semi-structured JSON data into a flat table. 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 = [ ... { ... "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. Fjsr6spec list | strextract_recordboolrScalar | Iterablec4|} t|tr|D]}|t|||}n||}nV#t$rI}|rtd|d|dkrtjcYd}~Std|d|d|d}~wwxYw|S)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"rWKeyErrornpnan)rdrergresultfielderbs r _pull_fieldz#json_normalize.._pull_fields $%% &!++E~&uoo-#E]FF+      21222!!v 7177q777  s#._pull_recordss Rd;;;&$'' y   ,,v,,,,, rNrSc3RK|]"}d|DV#dS)c8g|]}t|tSrFrG)rIxs rrVz,json_normalize...s"888 1d##888rN)values)rIys r z!json_normalize..s9GGQ88QXXZZ888GGGGGGrrrcBg|]}t|tr|n|gSrF)r"rW)rIms rrVz"json_normalize..s- = = =1*Q%% .QQA3 = = =rc:g|]}|SrF)join)rIvalrs rrVz"json_normalize..s#0003#000rrrrNonec t|tr|g}t|dkrn|D]i}t D]0\}}|dzt|kr ||d||<1 ||d|dd||dzjdS|D]} ||d}fd|D} t|t D]S\}}|dzt|kr ||}n |||d}||T|dS)Nrrrrcbg|]+}t|trt|n|,S)r~)r"r#r))rIrrrs rrVz>json_normalize.._recursive_extract..sR"!T**$QC9EEEEr)r"r#lenzipr*extend)r3path seen_metarobjrrArecsmeta_val_metarrrw_recursive_extractlengthsr meta_keys meta_valsrecordsrs rrz*json_normalize.._recursive_extracts dD ! ! 6D t99q== W W #E9 5 5CCHCqyCHH,,)4S#b')B)B #""3tAw<abb9ETUIVVVVV  W W % %$}S$q'22" s4yy))) #E9 5 544HCqy3s88++#,S>#.;sCK#@#@cN))(3333t$$$$# % %rrc|S)NrF)rzras rz json_normalize.. sM1F11F1Fr)columnszConflicting metadata name z, need distinguishing prefix )dtype)F)rdr6rerfrgrhrri)rdr6rerfrrW)r)rrrr)r"rWr r#rrrNotImplementedErrorrTanyr)rrenamer& ValueErrorrmarrayobjectrepeat)r3r[r]r_rarbrrror0r1rrrrwrrrrrs ```` @@@@@@@@rjson_normalizers\FK:($ "d "{{ D$  "v D#, ' '" 40E0E"Dzz!!  L    !  /#>>>??? GG$GGG G G H$DcYGGGD  T * *$"m  | d # #v = = = = =EGG(..I0000%000I%%%%%%%%%%%%%%%%<t["A6666 w  F 'F'F'F'FGG!!>>1  "aA ;;MQMMM HQf---44W==q Mr)rrrr)rrrN)rrrrrrrr ) r3rr4rr5r6r7rrr6)r3r6r7rrr6)r)r+rOrrrrP)NNNNrZrN)r3rOr[r\r]r^r_r`rar`rbr rrrr rr ) __future__r collectionsrrr$r=typingrrrnumpyrmpandas._libs.writersr pandas._typingr r pandasrtr rr)r@rNrTrrFrrrs#"""""  666666  $ $ $ $ NNNNNb++++\))))62"2"2"2"2"n&*/3" $! aaaaaaar