U
|
¬ý°d ¼ ã & @ sÎ d dl mZ d dlmZ d dlmZ d dlZd dlZd dlmZ d dl Z d dl
|
m Z m Z m Z mZmZmZmZmZmZmZmZmZ d dlZd dlZd dlmZm Z d dl m m Z d dl!m"Z" d d l#m$Z$ d d
|
l%m&Z&m'Z'm(Z(m)Z) d d l*m+Z+ d d l,m-Z-m.Z. d d l/m0Z0 d dl1m2Z2 d dl3m4Z4m5Z5m6Z6m7Z7m8Z8m9Z9m:Z:m;Z;m<Z<m=Z=m>Z>m?Z?m@Z@ d dlAmBZBmCZC d dlDmEZE d dlFmGZGmHZHmIZI d dlJmKZK d dlLmMZMmNZNmOZOmPZPmQZQmRZR d dlSmTZTmUZUmVZVmWZW d dlXmYZY d dlZm[Z\ d dl]m^Z^ e rüd dlFm_Z_ G dd dZ`ejad d dfd d d d d!d"Zbddd#ejcd d dd$dddd ddd ddddd ddd%d d d ejadddd ddd d&e`jdjeejad'%Zfd ejafd(d d)d*d+Zgd7d(d,d-d.d/Zhd0d1 Zid2d3 Zjd d4d5d6ZkdS )8é )Ú annotations)Ú defaultdict©ÚcopyN)ÚEnum) Ú TYPE_CHECKINGÚAnyÚCallableÚHashableÚIterableÚListÚMappingÚSequenceÚTupleÚcastÚfinalÚoverload)ÚlibÚparsers)Ú STR_NA_VALUES)Úparsing)Ú ArrayLikeÚDtypeArgÚDtypeObjÚScalar)Úimport_optional_dependency)Ú ParserErrorÚ ParserWarning)Úfind_stack_level)Ú astype_array) Ú ensure_objectÚ is_bool_dtypeÚ is_dict_likeÚis_dtype_equalÚis_extension_array_dtypeÚis_float_dtypeÚ
|
is_integerÚis_integer_dtypeÚ is_list_likeÚis_object_dtypeÚ is_scalarÚis_string_dtypeÚ pandas_dtype)ÚCategoricalDtypeÚExtensionDtype)Úisna)Ú
|
ArrowDtypeÚ DatetimeIndexÚ StringDtype)Ú
|
algorithms)ÚArrowExtensionArrayÚ BooleanArrayÚ CategoricalÚExtensionArrayÚ FloatingArrayÚ IntegerArray)ÚIndexÚ
|
MultiIndexÚ default_indexÚensure_index_from_sequences©ÚSeries)Ú datetimes)Úis_potential_multi_index)Ú DataFramec @ s e Zd ZU G dd deZdZded< ded< ddd d
|
Zd d d ddZddddZ e
|
e ddddZ e
|
dddddZ e
|
dhdddddd Ze
|
did dd d d d!Ze
|
djd"d#d$d%d&Ze
|
d'd( Ze
|
d)d* Zd+d, Ze
|
dkdd.d/d0d1Ze
|
dld2dd3d4d5Ze
|
d6d d7d8d9d:Zdmdd;d<d=d>Zd?d@d?dAdBdCZed.dDdEdFdGdHZed dIdJdFdKdHZdLdMdNdFdOdHZd dPddQdRdSZedTd d7dUdVdWZ edXd dXdUdYdWZ dZd d[dUd\dWZ d]d^ Z d_d` Z daddbdcZ dndddedfdgZ d S )oÚ
|
ParserBasec @ s e Zd ZdZdZdZdS )z ParserBase.BadLineHandleMethodr é é N)Ú__name__Ú
|
__module__Ú __qualname__ÚERRORÚWARNZSKIP© rK rK úTd:\z\workplace\vscode\pyvenv\venv\Lib\site-packages\pandas/io/parsers/base_parser.pyÚBadLineHandleMethodc s rM FÚboolÚ_implicit_indexÚ _first_chunkÚNone©Úreturnc C sâ | d¡| _d | _| dd ¡| _t | _d | _d | _t| dd¡| _
|
g | _ | dt j ¡| _| dd ¡| _| dd¡| _| dd¡| _| d ¡| _| d
|
¡| _| d d¡| _| d d ¡| _t| dd ¡| _| d¡| _| d¡| _| d¡| _| d¡| _| dd ¡| _ t | j| j| j| j d| _ | d¡| _ t | j ddrª| d¡rTt!d| d¡rht!d| jd k rªt | jddrt"t#t$| jsªt$| jsªt!dd| _%d | _&| '|d ¡\| _(| _)| d| j*j+¡| _,d S ) NÚnamesÚ index_colÚ parse_datesFÚ date_parserÚ date_formatÚdayfirstÚ keep_date_colÚ na_valuesÚ
|
na_fvaluesÚ na_filterÚkeep_default_naTÚdtypeÚ
|
convertersÚ dtype_backendÚ true_valuesÚ false_valuesÚ cache_dates)rW rX rY rd Úheader)Z
|
allow_setsÚusecolsz;cannot specify usecols when specifying a multi-index headerz9cannot specify names when specifying a multi-index headerzLindex_col must only contain row numbers when specifying a multi-index headerÚ on_bad_lines)-ÚgetrT Ú
|
orig_namesrU ÚsetÚ unnamed_colsÚ index_namesÚ col_namesÚ_validate_parse_dates_argÚpoprV Ú_parse_date_colsr Ú
|
no_defaultrW rX rY rZ r[ r\ r] r^ r r_ r` ra rb rc rd Ú_make_date_converterÚ
|
_date_convre r( Ú
|
ValueErrorÚallÚmapr& Ú_name_processedrP Ú_validate_usecols_argrf Ú usecols_dtyperM rI rg )ÚselfÚkwdsrK rK rL Ú__init__k sh ü ÿ ÿ ÿþýÿzParserBase.__init__zSequence[Hashable]r )ÚcolumnsrS c s t | jr tj| j ¡ }n(t| jr@tj dd | jD ¡}ng }t|}d t fdd|D ¡}|r|t
|
d| d fdd |D S )
|
a
|
Check if parse_dates are in columns.
|
|
If user has provided names for parse_dates, check if those columns
|
are available.
|
|
Parameters
|
----------
|
columns : list
|
List of names of the dataframe.
|
|
Returns
|
-------
|
The names of the columns which will get parsed later if a dict or list
|
is given as specification.
|
|
Raises
|
------
|
ValueError
|
If column to parse_date is not in dataframe.
|
|
c s s* | ]"}t |r t|ts |n|gV qd S ©N)r( Ú
|
isinstanceÚtuple©Ú.0ÚcolrK rK rL Ú <genexpr>Ñ s ÿz<ParserBase._validate_parse_dates_presence.<locals>.<genexpr>z, c s" h | ]}t |tr| kr|qS rK ©r Ústrr ©r} rK rL Ú <setcomp>Ý s
|
þz<ParserBase._validate_parse_dates_presence.<locals>.<setcomp>z+Missing column provided to 'parse_dates': 'ú'c s* g | ]"}t |ts| kr |n | qS rK r
r r rK rL Ú
|
<listcomp>é s ÿz=ParserBase._validate_parse_dates_presence.<locals>.<listcomp>) r" rV Ú itertoolsÚchainÚvaluesr( Ú from_iterableÚlistÚjoinÚsortedrt )rz r} Z cols_neededZ missing_colsrK r rL Ú _validate_parse_dates_presence± s,
|
|
þ
|
|
þÿÿ
|
ÿ
|
þz)ParserBase._validate_parse_dates_presencec C s d S r~ rK ©rz rK rK rL Úcloseî s zParserBase.closec C s6 t | jtp4t | jto4t| jdko4t | jd tS )Nr )r rV Údictr Úlenr rK rK rL Ú_has_complex_date_colñ s ÿýz ParserBase._has_complex_date_colÚint)ÚirS c C s t | jtr| jS | jd k r(| j| }nd }| jd kr:|n| j| }t| jrj|| jkph|d k oh|| jkS || jkp|d k o|| jkS d S r~ )r rV rN rl rU r* )rz r ÚnameÚjrK rK rL Ú_should_parse_datesú s
|
|
|
ÿ
|
ÿz ParserBase._should_parse_dateszSequence[Hashable] | NonezUtuple[Sequence[Hashable], Sequence[Hashable] | None, Sequence[Hashable] | None, bool])rl Ú passed_namesrS c s& t |dk r |d |d|fS jdkr.g ttttjfsFgt| d¡} |j¡\}}}t |d t
|
fdd|dd
D st dfd d
|
tt fd d|D }| ¡ }tD ]}| ||¡ qÖt rfd d |D }ndgt | }d}||||fS )a
|
Extract and return the names, index_names, col_names if the column
|
names are a MultiIndex.
|
|
Parameters
|
----------
|
header: list of lists
|
The header rows
|
index_names: list, optional
|
The names of the future index
|
passed_names: bool, default False
|
A flag specifying if names where passed
|
|
rE r Néÿÿÿÿc 3 s | ]}t | kV qd S r~ )r )r Z header_iter)Ú field_countrK rL r ; s z<ParserBase._extract_multi_indexer_columns.<locals>.<genexpr>rD z1Header rows must have an equal number of columns.c s t fddtD S )Nc 3 s | ]}|kr | V qd S r~ rK )r r )ÚrÚsicrK rL r ? s zMParserBase._extract_multi_indexer_columns.<locals>.extract.<locals>.<genexpr>)r Úrange©r )r r¡ r£ rL Úextract> s z:ParserBase._extract_multi_indexer_columns.<locals>.extractc 3 s | ]} |V qd S r~ rK ©r r )r¤ rK rL r A s c s> g | ]6}| d dk r6| d j kr6| d ndqS )r N)rk r¥ )Úicrz rK rL r H s þÿÿz=ParserBase._extract_multi_indexer_columns.<locals>.<listcomp>T)r rU r r r ÚnpÚndarrayrj ro Ú_clean_index_namesru r Úzipr r Úinsert) rz re rl r Ú_r} rT Z single_icrm rK )r¤ r r¦ rz r¡ rL Ú _extract_multi_indexer_columns s2
|
|
üz)ParserBase._extract_multi_indexer_columnsNz Sequence[Hashable] | MultiIndex)r} rm rS c C s( t |r$ttt |}tj||dS |S )N©rT )rA r r r r; Ú from_tuples)rz r} rm Z list_columnsrK rK rL Ú _maybe_make_multi_index_columnsU s z*ParserBase._maybe_make_multi_index_columnszlist[Scalar] | Nonez4tuple[Index | None, Sequence[Hashable] | MultiIndex])Ú indexnamerowrS c
|
C sÄ t | jr| jsd }nf| js4| ||¡}| |¡}nH| jr|| jsb| t|| j¡\| _}| _d| _| ||¡}| j|dd}|r®t
|
|t
|
| } |d k st | |d |
¡}| || j¡}||fS )NTF)Útry_parse_dates)Ú is_index_colrU r Ú_get_simple_indexÚ
|
_agg_indexrw r© r rl Ú_get_complex_date_indexr ÚAssertionErrorZ set_namesr° rm )
|
rz ÚdataZalldatar} r± ÚindexZ simple_indexr¬ Z
|
date_indexZcoffsetrK rK rL Ú _make_indexa s( ÿ zParserBase._make_indexc C sl dd }g }g }| j D ]$}||}| |¡ | || ¡ qt|ddD ] }| |¡ | jsH| |¡ qH|S )Nc S s" t | ts| S td| dd S )NzIndex z invalid)r r rt ©r rK rK rL Úix s
|
z(ParserBase._get_simple_index.<locals>.ixT©Úreverse)rU Úappendr ro rO )rz r¸ r} r¼ Ú to_remover¹ Úidxr rK rK rL r´ s
|
|
|
z ParserBase._get_simple_indexc sj fdd}g }g }| j D ]$}||}| |¡ | || ¡ qt|ddD ]}| |¡ |¡ qL|S )Nc sL t | tr| S d kr&td| dt D ]\}}|| kr.| S q.d S )Nz Must supply column order to use z as index)r r rt Ú enumerate)Zicolr Úc©rm rK rL Ú _get_name s
|
z5ParserBase._get_complex_date_index.<locals>._get_nameTr½ )rU r¿ r ro Úremove) rz r¸ rm rÅ rÀ r¹ rÁ r rà rK rÄ rL r¶ s
|
|
|
z"ParserBase._get_complex_date_indexc s t ts S i }| jdk s t ¡ D ].\}}t |trN|| jkrN| j| }|||< q(t trt| jt| ¡ }| fdd|D ¡ |S )z converts col numbers to namesNc s i | ]}| | qS rK rK r ©ÚmappingrK rL Ú
|
<dictcomp>Á s z-ParserBase._clean_mapping.<locals>.<dictcomp>)
|
r r ri r· Úitemsr r rj ÚkeysÚupdate)rz rÈ Úcleanr ÚvZremaining_colsrK rÇ rL Ú_clean_mapping³ s
|
|
|
|
zParserBase._clean_mappingTr: )r² rS c C sd g }| | j¡}t|D ]4\}}|rR| |¡rR| j|| jd k rJ| j| nd d}| jrf| j}| j}n t }t }t
|
| jt r¶| jd k st | j| } | d k r¶t | | j| j| j\}}| | j¡}
|
d } d} | jd k rt
|
|
|
t rò|
|
| j| d ¡} t
|
|t r| | j| ¡d k } | r"t| p$| } | |||B | d k| ¡\}}| |¡ q| j}t||}|S )Nr» F)rÏ r` r r rs rl r] r[ r\ rj r r r· Ú_get_na_valuesr^ r_ rh r+ Ú _infer_typesr¿ r= )rz r¹ r² Zarraysr` r ÚarrÚ col_na_valuesÚcol_na_fvaluesÚcol_nameZ clean_dtypesÚ cast_typeZindex_converterÚ try_num_boolr¬ rT rK rK rL rµ Ä sV þ
|
ÿ
|
ÿ ÿ
|
zParserBase._agg_indexr )ÚdctÚverbosec C s i }| ¡ D ]ø\}} |d kr"d n
|
| |d ¡}
|
t|trF| |d ¡} n|} | jrft|||| j\} } nt t } } || jkr¬t
|
| t| | B ¡}t | |t j ¡ | ||< q |
|
d k rJ| d k rØtjd| dtt d zt | |
|
¡} W n< tk
|
r$ t
|
| t|¡ t j¡}t | |
|
|¡} Y nX | j| t| | B | d kdd\}}nt| }|p^t| }| oh| }| | t| | B | d k|¡\}}| rât || r¤|râ|sÌ|dkrÌt | rÌtd| t | } | || |¡}|||< |r |r t d| d | q |S )
|
Nz5Both a converter and dtype were specified for column z# - only the converter will be used.©Ú
|
stacklevelF)r× r z$Bool column has NA values in column zFilled z NA values in column )!rÊ rh r r r] rÐ r^ rj rp r3 Úisinr§ ÚputmaskÚnanÚwarningsÚwarnr r r Z map_inferrt r ÚviewÚuint8Zmap_infer_maskrÑ r$ r+ r# r! r, Ú _cast_typesÚprint)rz rØ r[ r\ rÙ r` ZdtypesÚresultrà r Zconv_frÖ rÓ rÔ ÚmaskZcvalsÚna_countZis_eaZis_str_or_ea_dtyper× rK rK rL Ú_convert_to_ndarraysø sz
|
|
ÿ
|
|
|
|
ú ÿþ
|
ü
|
ü
|
z ParserBase._convert_to_ndarraysz list[int]zset[int])Ú col_indicesrT rS c s@ t }| jdkr t| jn t| js0| jdkr6 nddd fdd }t| jtr| jD ]6}t|tr|D ]}| ||¡ qtqb| ||¡ qbn t| jt rì| j
|
¡ D ]6}t|trÚ|D ]}| ||¡ qÄq²| ||¡ q²nP| jr<t| j tr | j D ]}| ||¡ qn | j dk r<| || j ¡ |S )a
|
Set the columns that should not undergo dtype conversions.
|
|
Currently, any column that is involved with date parsing will not
|
undergo such conversions. If usecols is specified, the positions of the columns
|
not to cast is relative to the usecols not to all columns.
|
|
Parameters
|
----------
|
col_indices: The indices specifying order and positions of the columns
|
names: The column names which order is corresponding with the order
|
of col_indices
|
|
Returns
|
-------
|
A set of integers containing the positions of the columns not to convert.
|
Úinteger)ÚemptyNNr rR c s2 d k rt | r| } t | s. | ¡ } | S r~ )r& r¹ )Úx©ré rT rf rK rL Ú_setu s
|
z5ParserBase._set_noconvert_dtype_columns.<locals>._set) rj ry r rf Úcallabler rV r Úaddr r rU )rz ré rT Znoconvert_columnsrî ÚvalÚkrK rí rL Ú _set_noconvert_dtype_columnsR s4
|
|
|
|
|
z'ParserBase._set_noconvert_dtype_columnsztuple[ArrayLike, int])r× rS c C s d}t |jjtjtjfrt dd |D ¡}t ||¡}|j ddd
|
¡ }|dkrxt |rh| tj ¡}t ||tj¡ ||fS | j}|o|tjk }|rt|jrztj||d|d\} }
|
W n( ttfk
|
rè t ||¡}|} Y nX |rz|
|
dkr tj| jtjd }
|
|
|
¡ r0ttj |
|
jtj d |
|
} n@t | rFt| |
|
} n*t | r\t | |
|
} nt | rpt!| |
|
} |
|
|
¡ }n t"|
|
¡ }n |} |jtj#kr¦t ||¡}| jtj#krN|rNt$j%t &|¡| j'| j(|d
|
\} } | jtjkr|r| dkr
|
tj| jtjd } t | | } n8| jtj#krN|rNt )| ¡} | d krNt* +¡ ,|¡} |d krt-d } t.| tj/rt0| j| d d} nt0| j| 1¡ d d} | |fS )a«
|
Infer types of values, possibly casting
|
|
Parameters
|
----------
|
values : ndarray
|
na_values : set
|
no_dtype_specified: Specifies if we want to cast explicitly
|
try_num_bool : bool, default try
|
try to cast values to numeric (first preference) or boolean
|
|
Returns
|
-------
|
converted : ndarray or ExtensionArray
|
na_count : int
|
r c S s g | ]}t |ts|qS rK r
)r rñ rK rK rL r s
|
z+ParserBase._infer_types.<locals>.<listcomp>râ Fr )Úconvert_to_masked_nullableN©r_ )rb rc rô ÚdatetimeÚpyarrowT)Z from_pandas)2Ú
|
issubclassr_ Útyper§ ÚnumberZbool_Úarrayr3 rÜ ÚastypeÚsumr' Úfloat64rÝ rÞ ra r rq r) Zmaybe_convert_numericrt Ú TypeErrorr Zsanitize_objectsÚzerosÚshaperu r9 ZonesÚint64r! r5 r% r8 r/ Zobject_ÚlibopsZmaybe_convert_boolÚasarrayrb rc Ú infer_dtyper2 Úconstruct_array_typeZ_from_sequencer r r¨ r4 Úto_numpy)rz r r[ Zno_dtype_specifiedr× rç ræ ra Znon_default_dtype_backendrå Z result_maskZ bool_maskZ inferred_typeÚparK rK rL rÑ s ÿü
|
|
|
ÿ
|
|
|
|
|
ü
|
|
|
|
|
ÿzParserBase._infer_typesr r )r rÖ rS c
|
C sj t |tr`|jdk }t|js2|s2tj|ddd}t| ¡ ¡ }t
|
j || |¡|| j d}nt |trÞ| ¡ }z4t|r|j||| j | jdW S |j||dW S W n4 tk
|
rÚ } ztd| d|W 5 d}~X Y nX nt |trø|j|dd }nnt|jtrtj|d
|
dd}nNzt||d
|
d }W n: tk
|
rd } ztd | d | |W 5 d}~X Y nX |S ) ar
|
Cast values to specified type
|
|
Parameters
|
----------
|
values : ndarray or ExtensionArray
|
cast_type : np.dtype or ExtensionDtype
|
dtype to cast values to
|
column : string
|
column name - used only for error reporting
|
|
Returns
|
-------
|
converted : ndarray or ExtensionArray
|
NF)ÚskipnaZconvert_na_value)rb )r_ rb rc rõ zExtension Array: zO must implement _from_sequence_of_strings in order to be used in parser methodsr TzUnable to convert column z to type )r r- Ú
|
categoriesr) r_ r Zensure_string_arrayr: ÚuniqueZdropnar6 Z_from_inferred_categoriesZ get_indexerrb r. r r! Z_from_sequence_of_stringsrc ÚNotImplementedErrorr7 rü rø rù r r rt )rz r rÖ ÚcolumnZ
|
known_catsZcatsZ
|
array_typeÚerrrK rK rL rã ÿ sb
|
|
ÿ ÿ
|
|
ü
|
ÿý
|
ÿÿþzParserBase._cast_typesrB z,tuple[Sequence[Hashable] | Index, DataFrame])rT r¸ rS c C s d S r~ rK ©rz rT r¸ rK rK rL Ú_do_date_conversionsF s z ParserBase._do_date_conversionsz Mapping[Hashable, ArrayLike]z7tuple[Sequence[Hashable], Mapping[Hashable, ArrayLike]]c C s d S r~ rK r rK rK rL r N s zSequence[Hashable] | Indexz(Mapping[Hashable, ArrayLike] | DataFramezKtuple[Sequence[Hashable] | Index, Mapping[Hashable, ArrayLike] | DataFrame]c
|
C s: | j d k r2t|| j| j | j| j|| j| jd\}}||fS )N)rZ ra )rV Ú_process_date_conversionrs rU rl rZ ra r rK rK rL r V s
|
ø
|
zSequence[ArrayLike])r} r¸ rS c C sz | j svt|t|krv|rvt|d o0|d dk}|t|d B }t|t|d krdt |¡rddS tjdtt d dS )ae Checks if length of data is equal to length of column names.
|
|
One set of trailing commas is allowed. self.index_col not False
|
results in a ParserError previously when lengths do not match.
|
|
Parameters
|
----------
|
columns: list of column names
|
data: list of array-likes containing the data column-wise.
|
r Ú rD NzkLength of header or names does not match length of data. This leads to a loss of data with index_col=False.rÚ )
|
rU r r) r/ r§ ru rß rà r r )rz r} r¸ Z empty_strZempty_str_or_narK rK rL Ú_check_data_lengthk s üz ParserBase._check_data_lengthz'set[int] | Callable[[Hashable], object])rf rT rS c C s d S r~ rK ©rz rf rT rK rK rL Ú_evaluate_usecols s z ParserBase._evaluate_usecolszset[str]c C s d S r~ rK r rK rK rL r s z2Callable[[Hashable], object] | set[str] | set[int]zset[str] | set[int]c s" t r fddt|D S S )a
|
Check whether or not the 'usecols' parameter
|
is a callable. If so, enumerates the 'names'
|
parameter and returns a set of indices for
|
each entry in 'names' that evaluates to True.
|
If not a callable, returns 'usecols'.
|
c s h | ]\}} |r|qS rK rK )r r r ©rf rK rL r £ s z/ParserBase._evaluate_usecols.<locals>.<setcomp>)rï r r rK r rL r s c s0 fdd|D }t |dkr,td| |S )ai
|
Validates that all usecols are present in a given
|
list of names. If not, raise a ValueError that
|
shows what usecols are missing.
|
|
Parameters
|
----------
|
usecols : iterable of usecols
|
The columns to validate are present in names.
|
names : iterable of names
|
The column names to check against.
|
|
Returns
|
-------
|
usecols : iterable of usecols
|
The `usecols` parameter if the validation succeeds.
|
|
Raises
|
------
|
ValueError : Columns were missing. Error message will list them.
|
c s g | ]}| kr|qS rK rK ©r rà r® rK rL r ¼ s z6ParserBase._validate_usecols_names.<locals>.<listcomp>r z>Usecols do not match columns, columns expected but not found: )r rt )rz rf rT ÚmissingrK r® rL Ú_validate_usecols_names¦ s ÿz"ParserBase._validate_usecols_namesc C sb d}|dk rZt |r |dfS t|s,t|tj|dd}|dkrJt|t|}||fS |dfS )as
|
Validate the 'usecols' parameter.
|
|
Checks whether or not the 'usecols' parameter contains all integers
|
(column selection by index), strings (column by name) or is a callable.
|
Raises a ValueError if that is not the case.
|
|
Parameters
|
----------
|
usecols : list-like, callable, or None
|
List of columns to use when parsing or a callable that can be used
|
to filter a list of table columns.
|
|
Returns
|
-------
|
usecols_tuple : tuple
|
A tuple of (verified_usecols, usecols_dtype).
|
|
'verified_usecols' is either a set if an array-like is passed in or
|
'usecols' if a callable or None is passed in.
|
|
'usecols_dtype` is the inferred dtype of 'usecols' if an array-like
|
is passed in or None if a callable or None is passed in.
|
z['usecols' must either be list-like of all strings, all unicode, all integers or a callable.NF)r )rë rê Ústring)rï r( rt r r rj )rz rf Úmsgry rK rK rL rx Å s ÿz ParserBase._validate_usecols_argz tuple[list | None, list, list]c C sò t |sd ||fS t|}|s2d gt| ||fS t|}g }t|}t|D ]j\}}t|tr| |¡ t|D ]&\}}||krr|||< | |¡ q¸qrqN|| }| |¡ | |¡ qNt|D ]$\}}t|trÂ|| jkrÂd ||< qÂ|||fS r~ ) r³ r r r r r r¿ rÆ rk ) rz r} rU Zcp_colsrl r rà r r rK rK rL r© ö s.
|
|
|
|
|
|
z ParserBase._clean_index_nameszDtypeArg | Nonerõ c
|
sØ t t|s*|pttfddn*tt|}tdd fdd| ¡ D |d ksl|dksl|d krvtd}nFfdd |D }t||d
|
}| ¡ t
|
|D ]\}} || ¡ q¤fd d D } | | fS ) Nc s S r~ rK rK )Ú default_dtyperK rL Ú<lambda>' ó z,ParserBase._get_empty_meta.<locals>.<lambda>c S s t S r~ )ÚobjectrK rK rK rL r + r c s& i | ] \}}t |r | n||qS rK )r& )r rò rÎ r rK rL rÉ , s z.ParserBase._get_empty_meta.<locals>.<dictcomp>Fr c s g | ]}t g | d qS ©rõ r> )r r ©Ú
|
dtype_dictrK rL r < s z.ParserBase._get_empty_meta.<locals>.<listcomp>r® c s i | ]}|t g | d qS r r> )r rÕ r! rK rL rÉ C s ) r r" r r r r rÊ r< r= Úsortr ro )
|
rz r} rU rl r_ r¹ r¸ r ÚnZcol_dictrK )r} r r" rL Ú_get_empty_meta s(
|
þ
|
|
ÿzParserBase._get_empty_meta)F)N)N)T)FNN)T)N)!rF rG rH r rM rO Ú__annotations__r| r r r Úpropertyr r r r° rº r´ r¶ rÏ rµ rè ró rÑ rã r r r r r rx r© r% rK rK rK rL rC b sj
|
F= üF ý ÿ
|
|
3 ùYE ÿhG 1& ÿrC FTrN z dict[Hashable, str] | str | None)rY rd rX c sR t jk r tjdtt d t jk r6d k r6tddd fdd }|S )Nz·The argument 'date_parser' is deprecated and will be removed in a future version. Please use 'date_format' instead, or read your data in as 'object' dtype and then call 'to_datetime'.rÚ z/Cannot use both 'date_parser' and 'date_format'r
|
r» c sÐ t jkrjt |¡}ttr( | ¡n}tjt ||dd d}t|t
|
rd| ¡ }d|j _ |S |jS z.tj| d d}t|tjrtd|W S tk
|
rÊ tjtjt |¡ddd Y S X d S ) NFÚignore)ÚformatÚutcrY ÚerrorsÚcacheT)r+ r, z scalar parser)Úparser)r+ )r rq r Zconcat_date_colsr r rh ÚtoolsÚ to_datetimer r1 r ÚflagsZ writeableZ_valuesrö Ú Exceptionr² )r Ú date_colsÚstrsZdate_fmtrå rÒ ©rd rX rW rY rK rL Ú converter\ sD
|
|
ÿú
|
ÿ þûz'_make_date_converter.<locals>.converter)r rq rß rà Ú FutureWarningr rÿ )rW rY rd rX r5 rK r4 rL rr J s
|
ú%rr ú"ZinferÚ.Ústrict)%Ú delimiterÚ
|
escapecharÚ quotecharÚquotingÚ doublequoteÚskipinitialspaceÚlineterminatorre rU rT ZskiprowsZ
|
skipfooterZnrowsr[ r^ rb rc r` r_ rd Z thousandsÚcommentÚdecimalrV rZ rY rW rX rf Ú chunksizerÙ ÚencodingÚ compressionZskip_blank_linesZencoding_errorsrg ra r )r5 rZ c s fdd}g } i }
|
|} t |}t } |d ks:t|trB| |fS t|t r8|D ]â} t| sht| trìt| tr| | kr| | } || rqRnB|dkrÐdd l}| | j}t|t rÐ|j
|
|j ¡sR|j
|
|j ¡rÐqR|t | | ¡| d| | < qRt|| | | \}}}|| krtd| ||
|
|< | |¡ | |¡ qRnt|trÀ| ¡ D ]r\}} || krntd| dt|| | | |d \}}}||
|
|< t| d
|
kr¨||
|
| d < | |¡ | |¡ qL| |
|
¡ | |¡ |sþt | D ]}| |¡ | |¡ qâ| | fS ) Nc s$ t tr| kp"t to"| kS r~ )r r )Úcolspec©rU rl rK rL Ú_isindex¹ s ÿz*_process_date_conversion.<locals>._isindexr÷ r r» z New date column already in dict z Date column z already in dict)Ú target_namerD )r rj r rN r* r r r÷ r_ r0 ÚtypesZ is_timestampZ pyarrow_dtypeZis_dater§ r Ú_try_convert_datesrt r¿ rÌ r rÊ r Úextendro rÆ )Ú data_dictr5 Z
|
parse_specrU rl r} rZ ra rH Znew_colsZnew_datari r2 rF r r_ Únew_namer Z old_namesr¬ rà rK rG rL r ¯ s|
|
|
|
ÿ þ ÿ ÿ
|
|
|
|
û
|
|
|
|
r z
|
str | None)r- rI c sÈ t |}g }|D ]D}||kr(| |¡ qt|trJ||krJ| || ¡ q| |¡ qtdd |D r~ttdjt| }nd dd |D ¡} fdd|D } | | d|d kr¶|n|i}
|
||
|
|fS )Nc s s | ]}t |tV qd S r~ )r r ©r rì rK rK rL r s z%_try_convert_dates.<locals>.<genexpr>r¬ c S s g | ] }t |qS rK )r rO rK rK rL r s z&_try_convert_dates.<locals>.<listcomp>c s" g | ]}| krt | ¡qS rK )r§ r r ©rM rK rL r s r ) rj r¿ r r ru r rv r rª ) r- rF rM r} rI ZcolsetZcolnamesrà rN Zto_parseZnew_colrK rP rL rK s rK c C sJ t |tr>| |kr"|| || fS |r0tt fS t t fS n||fS dS )a
|
Get the NaN values for a given column.
|
|
Parameters
|
----------
|
col : str
|
The name of the column.
|
na_values : array-like, dict
|
The object listing the NaN values as strings.
|
na_fvalues : array-like, dict
|
The object listing the NaN values as floats.
|
keep_default_na : bool
|
If `na_values` is a dict, and the column is not mapped in the
|
dictionary, whether to return the default NaN values or the empty set.
|
|
Returns
|
-------
|
nan_tuple : A length-two tuple composed of
|
|
1) na_values : the string NaN values for that column.
|
2) na_fvalues : the float NaN values for that column.
|
N)r r r rj )r r[ r\ r^ rK rK rL rÐ & s
|
|
rÐ c C sB d}| dk r>t | r(t | ¡s>t|nt| ttfs>t|| S )z
|
Check whether or not the 'parse_dates' parameter
|
is a non-boolean scalar. Raises a ValueError if
|
that is the case.
|
zSOnly booleans, lists, and dictionaries are accepted for the 'parse_dates' parameterN)r* r Zis_boolrÿ r r r )rV r rK rK rL rn I s ÿ
|
|
rn rR c C s | d k o| dk S )NFrK r» rK rK rL r³ _ s r³ )N)lÚ
|
__future__r Ú collectionsr r Úcsvrö Úenumr r Útypingr r r r
|
r r r r r r r r rß Únumpyr§ Z pandas._libsr r Zpandas._libs.opsZ_libsÚopsr Zpandas._libs.parsersr Zpandas._libs.tslibsr Zpandas._typingr r r r Zpandas.compat._optionalr Z pandas.errorsr r Zpandas.util._exceptionsr Zpandas.core.dtypes.astyper Zpandas.core.dtypes.commonr r! r" r# r$ r% r& r' r( r) r* r+ r, Zpandas.core.dtypes.dtypesr- r. Zpandas.core.dtypes.missingr/ Zpandasr0 r1 r2 Z pandas.corer3 Zpandas.core.arraysr4 r5 r6 r7 r8 r9 Zpandas.core.indexes.apir: r; r< r= Zpandas.core.seriesr? Zpandas.core.toolsr@ r. Zpandas.io.commonrA rB rC rq rr Ú QUOTE_MINIMALrM rI Zparser_defaultsr rK rÐ rn r³ rK rK rK rL Ú<module> s² 8 < pü;Ù2ø_ ÿ#
|
