B Y0d-B @s ddlmZddlmZmZddlZddlmZmZm Z ddl Z ddl m Z ddlmZddlmZddlZddlmZd d d d d Zd,d d dddddZdd dd ddddZdd ddddZd-dd dddd Zd.dd"d#d$d$d d dd%d& d'd(Zed)ed*d+ZdS)/) annotations)abc defaultdictN)Any DefaultDictIterable)convert_json_to_lines)Scalar) deprecate) DataFramestr)sreturncCs0|ddks|ddkr|S|dd}t|S)zJ Helper function that converts JSON lists to line delimited JSON. r[])r)r rK/var/www/html/venv/lib/python3.7/site-packages/pandas/io/json/_normalize.pyconvert_to_line_delimitss r.intz int | None)prefixseplevel max_levelc Csd}t|tr|g}d}g}x|D]}t|}x|D]\} } t| tsTt| } |dkrb| } n ||| } t| tr|dk r||kr|dkr:|| } | || <q:q:|| } |t| | ||d|q:W| |q"W|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. .. versionadded:: 0.25.0 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) isinstancedictcopydeepcopyitemsr popupdatenested_to_recordappend) dsrrrrZ singletonZnew_dsdZnew_dkvZnewkeyrrrr$'s2.        r$rzdict[str, Any])data key_stringnormalized_dict separatorrcCsrt|trfxb|D]L\}}|||}t||t|d|krH|n|t|d||dqWn|||<|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 rN)r*r+r,r-)rrr!_normalise_jsonlen)r*r+r,r-keyvalueZnew_keyrrrr.zs r.)r*r-rcCs8dd|D}tdd|Ddi|d}||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||qSr)rr).0r(r)rrr sz+_normalise_json_ordered..cSs i|]\}}t|tr||qSr)rr)r2r(r)rrrr3sr)r*r+r,r-)r!r.)r*r-Z top_dict_Z nested_dict_rrr_normalise_json_orderedsr4zdict | list[dict]zdict | list[dict] | Any)r&rrcs@i}t|trt|d}n t|tr<fdd|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*r-csg|]}t|dqS))r)_simple_json_normalize)r2row)rrr sz*_simple_json_normalize..)rrr4list)r&rZnormalised_json_objectZnormalised_json_listr)rrr5s+  r5raisezstr | list | Nonez"str | list[str | list[str]] | Nonez str | Noner ) r* record_pathmeta meta_prefix record_prefixerrorsrrrc sddddddddddfdd t|tr<|s foo.bar. max_level : int, default None Max number of levels(depth of dict) to normalize. if None, normalizes all levels. .. versionadded:: 0.25.0 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. zdict[str, Any]z list | strzScalar | Iterable)jsspecrcSs2|}t|tr&x|D] }||}qWn||}|S)zInternal function to pull field)rr8)r?r@resultfieldrrr _pull_fields   z$_json_normalize.._pull_fieldr8csB||}t|ts>t|r$g}nt|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. z has non list value z for path z. Must be list or null.)rr8pdZisnull TypeError)r?r@rA)rCrr _pull_recordss   z&_json_normalize.._pull_recordsN)rcss |]}dd|DVqdS)cSsg|]}t|tqSr)rr)r2xrrrr7sz-_json_normalize...N)values)r2yrrr sz"_json_normalize..)rrcSs g|]}t|tr|n|gqSr)rr8)r2mrrrr7sz#_json_normalize..csg|]}|qSr)join)r2val)rrrr7src svt|tr|g}t|dkrxj|D]b}x8tD]*\}}|dt|kr2||d||<q2W||d|dd||ddq"Wnx|D]}||d} fdd|D}t|xtD]\}}|dt|kr||}n`y|||d}WnHtk rP} z(dkr.tj}ntd| d | Wdd} ~ XYnX||qW |qWdS) Nrrr)rcs(g|] }t|tr t|dn|qS))rr)rrr$)r2r)rrrrr7sz?_json_normalize.._recursive_extract..ignorez(Try running with errors='ignore' as key z is not always present) rrr/zipr%KeyErrornpnanextend) r*pathZ seen_metarobjrMr0ZrecsZmeta_vale) _metarCrF_recursive_extractr>lengthsr meta_keys meta_valsrecordsrrrrYs4   *     z+_json_normalize.._recursive_extract)rcs |S)Nr)rG)r=rrz!_json_normalize..)columnszConflicting metadata name z, need distinguishing prefix )Zdtype)r)rr8r rrrr NotImplementedErrorr5anyr$rrenamer! ValueErrorrRarrayobjectrepeat) r*r:r;r<r=r>rrrAr(r)r) rXrCrFrYr>rZrr[r\r=r]rr_json_normalizesX     "'   rhzpandas.io.json.json_normalizez1.0.0zpandas.json_normalize)rrrN)r)NNNNr9rN) __future__r collectionsrrrtypingrrrnumpyrRZpandas._libs.writersrZpandas._typingr Zpandas.util._decoratorsr ZpandasrDr rr$r.r4r5rhZjson_normalizerrrrs8     N(5