o dB@sddlmZddlmZmZddlZddlZddlmZm Z m Z ddl Z ddl mZddlmZmZddlZddlmZd3d d Z  d4d5ddZd6ddZd7dd Z d8d9d$d%Z     &  d:d;d1d2ZdS)<) annotations)abc defaultdictN)Any DefaultDictIterableconvert_json_to_lines) IgnoreRaiseScalar) DataFramesstrreturncCs0|ddks|ddkr|S|dd}t|S)zJ Helper function that converts JSON lists to line delimited JSON. r[]r)r rM/app/.heroku/python/lib/python3.10/site-packages/pandas/io/json/_normalize.pyconvert_to_line_delimitss r.prefixseplevelint max_level int | Nonec Csd}t|tr |g}d}g}|D]X}t|}|D]G\} } t| ts(t| } |dkr/| } n||| } t| trB|durP||krP|dkrO|| } | || <q|| } |t| | ||d|q| |q|ro|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) dsrrrrZ singletonZnew_dsdZnew_dkvZnewkeyrrrr&*s8,        r&datar key_stringnormalized_dictdict[str, Any] separatorcCs|t|tr8|D],\}}|||}|s-tjdkr(ddlm}|||}n||}t||||dq |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 ) r) removeprefixr,r-r.r0)rr r#sys version_infoZpandas.util._str_methodsr3_normalise_json)r,r-r.r0keyvalueZnew_keyr3rrrr7{s"     r7cCs<dd|D}tdd|Ddi|d}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` cSs i|] \}}t|ts||qSrrr .0r*r+rrr  z+_normalise_json_ordered..cSs i|] \}}t|tr||qSrr:r;rrrr=r>rr4)r#r7)r,r0Z top_dict_Z nested_dict_rrr_normalise_json_ordereds r?r(dict | list[dict]dict | list[dict] | AnycsBi}t|trt|d}|St|trfdd|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} )r,r0csg|]}t|dqS)r)_simple_json_normalize)r<rowrBrr sz*_simple_json_normalize..)rr r?list)r(rZnormalised_json_objectZnormalised_json_listrrBrrCs+   rCraise record_pathstr | list | Nonemeta"str | list[str | list[str]] | None meta_prefix str | None record_prefixerrorsr r c s d$d%fd d d&fd d t|tr|stSt|tr#|g}nt|tjr3t|ts3t|}nt|durQ|durQ|durQ durQdurQtt| dS|durit dd|Dret | d}t|St|tsq|g}|durxg}nt|ts|g}dd|Dg gt t fddDd'd( f dd ||iddt } dur|j fddd } D]$\} } |dur|| } | |vrtd!| d"tj| td#|| <q|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. Fjsr/spec list | strextract_recordboolrScalar | Iterablec s|}z t|tr|D]}|durt|||}q W|S||}W|StyR}z$|r5td|d|dkrBtjWYd}~Std|d|d|d}~ww)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')rrFKeyErrornpnan)rPrQrSresultfielde)rOrr _pull_fields6    z#json_normalize.._pull_fieldrFcsH||dd}t|ts"t|rg}|St|d|d|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)rSz has non list value z for path z. Must be list or null.)rrFpdZisnull TypeError)rPrQrZ)r]rr _pull_recordss  z%json_normalize.._pull_recordsNrBcss"|] }dd|DVqdS)cSsg|]}t|tqSrr:)r<xrrrrEz,json_normalize...N)values)r<yrrr s z!json_normalize..rrcSs g|] }t|tr |n|gqSr)rrF)r<mrrrrEr>z"json_normalize..csg|]}|qSr)join)r<valrBrrrErbrrrNonec st|tr|g}t|dkrB|D]/}tD]\}}|dt|kr,||d||<q||d|dd||ddqdS|D]F}||d} fdd|D}t|tD]!\}}|dt|krt||}n |||d}||qc|qDdS)Nrrrrcs(g|]}t|trt|dn|qS)rf)rr r&)r<r)rrrrrEs z>json_normalize.._recursive_extract..)rr lenzipr'extend) r,pathZ seen_metarobjrir8ZrecsZmeta_val) _metar]r`_recursive_extractlengthsr meta_keys meta_valsrecordsrrrrss.  &   z*json_normalize.._recursive_extractrkcs |S)Nr)ra)rNrr s z json_normalize..)columnszConflicting metadata name z, need distinguishing prefix )Zdtype)F)rPr/rQrRrSrTrrU)rPr/rQrRrrF)r)rrrrj)rrFr r rrrNotImplementedErrorrCanyr&rrenamer# ValueErrorrXarrayobjectrepeat) r,rHrJrLrNrOrrrZr*r+r) rrr]r`rsrOrtrrurvrNrwrrjson_normalizesf    " r)r rrr)rrrN)rrrrrrrr) r,rr-rr.r/r0rrr/)r,r/r0rrr/)r)r(r@rrrrA)NNNNrGrN)r,r@rHrIrJrKrLrMrNrMrOr rrrrrr ) __future__r collectionsrrr!r5typingrrrnumpyrXZpandas._libs.writersr Zpandas._typingr r Zpandasr^r rr&r7r?rCrrrrrs8     Q . 7