U MZf@sNddlmZddlmZddlmZddlmZddlmZddl m Z m Z m Z m Z mZmZmZmZmZddlZddlZddlmZmZdd lmZmZmZmZmZmZm Z m!Z!m"Z"m#Z$dd l%m&Z&dd l'm(Z(m)Z)dd l*m+Z+dd l,m-Z-m.Z.m/Z/m0Z0ddl1m2Z2ddl3m4Z4m5Z5m6Z6m7Z7m8Z8m9Z9m:Z:m;Z;mZ>m?Z?ddl@mAZAddlBmCZCmDZDmEZEddlFmGZGddlHmIZIddlJmKZKddlLmMZMmNZNmOZOddlPmQZQddlRmSZSddlTmUZUe rddlVmWZWddlXmYZYddlZm[Z[m\Z\ee ee-fZ]ee^e_fZ`ee`efZaeeae]fZbee e`ee`dfe-fZcGddded d!ZdGd"d#d#edd$d!Zeeeed%fZfd&Zgdzd'd(d)d*d+Zhd{d-d.d/d0d1d2d3Zid-d(d0d4d5d6d7d8Zjd|d9d0d:d;d<d=d>Zkd}d?d5d@d;dAdBdCZldDd0d;dEdFdGZmd~d(d:d0d(dId'd'd0dJdKdLZnd0dMd0dMd;dNdOdPZod0dMd;dQdRdSZpdTdUZqeddVdId0d0d0d(d0d(d0d0dWdX dYdZZredd[dId0d0d0d(d0d(d0d0d5dX d\dZZredd]dId0d0d0d(d0d(d0d0d^dX d_dZZrdHd$d$d$dejsdejsd`d f dadId0d0d0d(dbd(dcdMd0ddde dfdZZrdgdgdhdhdididjdjdkdkdldldmdmdmdndndndodododpZtdId0dqdrdsZudtdMdudvdwdxZvdyd3dZgZwdS)) annotations)abc)datetime)partial)islice) TYPE_CHECKINGCallableHashableListTuple TypedDictUnioncastoverloadN)libtslib) OutOfBoundsDatetime Timedelta Timestampastype_overflowsafeget_unit_from_dtypeiNaTis_supported_unit nat_stringsparsing timezones)precision_from_unit)DateParseErrorguess_datetime_format)array_strptime) AnyArrayLike ArrayLikeDateTimeErrorChoicesnpt)find_stack_level) ensure_objectis_datetime64_dtypeis_datetime64tz_dtypeis_float is_integeris_integer_dtype is_list_likeis_numeric_dtype is_scalar) ABCDataFrame ABCSeries)notna) DatetimeArray IntegerArray PandasArray) algorithms)unique)ExtensionArray)maybe_convert_dtypeobjects_to_datetime64ns tz_to_dtype) extract_array)Index) DatetimeIndex)NaTType) UnitChoices) DataFrameSeries.c@s&eZdZUded<ded<ded<dS)YearMonthDayDictDatetimeDictArgyearmonthdayN__name__ __module__ __qualname____annotations__rKrK?/tmp/pip-unpacked-wheel-nbcvw55c/pandas/core/tools/datetimes.pyrAks rAT)totalc@sVeZdZUded<ded<ded<ded<ded<ded<ded<ded <ded <d S) FulldatetimeDictrBhourhoursminuteminutessecondsecondsmsusnsNrFrKrKrKrLrNqs rNFr?2z bool | Nonez str | None)dayfirstreturncCsnt|}dkrjt||}tkrjt||d}|dk r>|St||dddkrjtjdttddS)NrYzCould not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format. stacklevel) rfirst_non_nulltypestrrwarningswarn UserWarningr$)arrrYr`Zfirst_non_nan_elementZguessed_formatrKrKrL _guess_datetime_format_for_arraysrgffffff?ArrayConvertiblefloatz int | Nonebool)arg unique_share check_countrZcCsd}|dkrsz0_array_strptime_with_fallback..r)ranyrr)rlrrrrrrrrKrKrLrs r)rrrZc Cs t|dd}t|tr0|d|d}d}nht|}|jjdkr|jd|ddd}zt|td dd}Wn8t k r|d kr|t }t |||||YSXd}n|jjd krvt |\}}t ||tkB} ||jd dd} d | | <| tjjks| tjjkrR|d krB|t }t |||||St d|d| jd dd}tdd|| <d}n"|jt dd}tj|||d\}}|dkrtj||d} n t||d} t| ts| S| d|} |r| jdkr| d} n | d} | S)zF to_datetime specalized to the case where a 'unit' is passed. T)Z extract_numpyz datetime64[]N)iuFr}M8[ns]rfZf8rz cannot convert input with unit ''rrWrrrUTCr)r:rr2astyperrr{kindrrrrrisnanrrmin_valuermaxZ datetime64rZarray_with_unit_to_datetimer;Z _with_inferr<rrr) rlrrrrrfrZmultrrZfvaluesrrKrKrLrsV               rc Cs|dkr|}td}|dkr(tdz ||}Wn,tk r`}ztd|W5d}~XYnXtj|}tj|}t||kst||krt|dn t |rt |st |st t |std|d |d zt||d }Wnjtk r.}ztd |d |W5d}~XYn6tk rb}ztd |d|W5d}~XYnX|jdk rtd|d|td} | td|d } t|rt|tttjfst |}|| }|S)a Helper function for to_datetime. Adjust input argument to the specified origin Parameters ---------- arg : list, tuple, ndarray, Series, Index date to be adjusted origin : 'julian' or Timestamp origin offset for the arg unit : str passed unit from to_datetime, must be 'D' Returns ------- ndarray or scalar of adjusted date(s) ZjulianrDz$unit must be 'D' for origin='julian'z3incompatible 'arg' type for given 'origin'='julian'Nz% is Out of Bounds for origin='julian'rz!' is not compatible with origin='z+'; it must be numeric with a unit specified)rzorigin z is Out of Boundsz# cannot be converted to a Timestampzorigin offset z must be tz-naiver])rZto_julian_daterrtrrrrrr-r)r(r,rrrr+rr/r;ndarray) rloriginroriginalZj0errZj_maxZj_minoffsetZ td_offsetZioffsetrKrKrL_adjust_to_origin3s`   "    rDatetimeScalarr) rlrrYrrrvrrinfer_datetime_formatrwrZc CsdSrrK rlrrYrrrvrrrrrwrKrKrL to_datetime|srzSeries | DictConvertiblec CsdSrrKrrKrKrLrsz list | tuple | Index | ArrayLiker<c CsdSrrKrrKrKrLrsunixz2DatetimeScalarOrArrayConvertible | DictConvertiblezbool | lib.NoDefaultzlib.NoDefault | boolz8DatetimeIndex | Series | DatetimeScalar | NaTType | None) rlrrYrrrvrrrrrwrZc  Cs&|tjk r|dkrtd|tjk r4tjdtd|dkr@dS| dkrTt|| |}tt||||||d} t |t r|} |r|j dk r| d} n | d} nt |trt||| | } | js|| } n | |j|}|j||j|jd } n4t |ttjfrt|||} nt |trVt||| | } | jsDt|| |jd } n| |||jd } nt|rz.tttt t!t"j#d tf|}t||| | } Wn:t$k r|d krd dl%m&}|gt'd} YnX| jst|| } n | ||} n8| t"(|g|d } t |t)r"t | t"j*r"t)| } | S)u5 Convert argument to datetime. This function converts a scalar, array-like, :class:`Series` or :class:`DataFrame`/dict-like to a pandas datetime object. Parameters ---------- arg : int, float, str, datetime, list, tuple, 1-d array, Series, DataFrame/dict-like The object to convert to a datetime. If a :class:`DataFrame` is provided, the method expects minimally the following columns: :const:`"year"`, :const:`"month"`, :const:`"day"`. errors : {'ignore', 'raise', 'coerce'}, default 'raise' - If :const:`'raise'`, then invalid parsing will raise an exception. - If :const:`'coerce'`, then invalid parsing will be set as :const:`NaT`. - If :const:`'ignore'`, then invalid parsing will return the input. dayfirst : bool, default False Specify a date parse order if `arg` is str or is list-like. If :const:`True`, parses dates with the day first, e.g. :const:`"10/11/12"` is parsed as :const:`2012-11-10`. .. warning:: ``dayfirst=True`` is not strict, but will prefer to parse with day first. yearfirst : bool, default False Specify a date parse order if `arg` is str or is list-like. - If :const:`True` parses dates with the year first, e.g. :const:`"10/11/12"` is parsed as :const:`2010-11-12`. - If both `dayfirst` and `yearfirst` are :const:`True`, `yearfirst` is preceded (same as :mod:`dateutil`). .. warning:: ``yearfirst=True`` is not strict, but will prefer to parse with year first. utc : bool, default False Control timezone-related parsing, localization and conversion. - If :const:`True`, the function *always* returns a timezone-aware UTC-localized :class:`Timestamp`, :class:`Series` or :class:`DatetimeIndex`. To do this, timezone-naive inputs are *localized* as UTC, while timezone-aware inputs are *converted* to UTC. - If :const:`False` (default), inputs will not be coerced to UTC. Timezone-naive inputs will remain naive, while timezone-aware ones will keep their time offsets. Limitations exist for mixed offsets (typically, daylight savings), see :ref:`Examples ` section for details. See also: pandas general documentation about `timezone conversion and localization `_. format : str, default None The strftime to parse time, e.g. :const:`"%d/%m/%Y"`. See `strftime documentation `_ for more information on choices, though note that :const:`"%f"` will parse all the way up to nanoseconds. You can also pass: - "ISO8601", to parse any `ISO8601 `_ time string (not necessarily in exactly the same format); - "mixed", to infer the format for each element individually. This is risky, and you should probably use it along with `dayfirst`. exact : bool, default True Control how `format` is used: - If :const:`True`, require an exact `format` match. - If :const:`False`, allow the `format` to match anywhere in the target string. Cannot be used alongside ``format='ISO8601'`` or ``format='mixed'``. unit : str, default 'ns' The unit of the arg (D,s,ms,us,ns) denote the unit, which is an integer or float number. This will be based off the origin. Example, with ``unit='ms'`` and ``origin='unix'``, this would calculate the number of milliseconds to the unix epoch start. infer_datetime_format : bool, default False If :const:`True` and no `format` is given, attempt to infer the format of the datetime strings based on the first non-NaN element, and if it can be inferred, switch to a faster method of parsing them. In some cases this can increase the parsing speed by ~5-10x. .. deprecated:: 2.0.0 A strict version of this argument is now the default, passing it has no effect. origin : scalar, default 'unix' Define the reference date. The numeric values would be parsed as number of units (defined by `unit`) since this reference date. - If :const:`'unix'` (or POSIX) time; origin is set to 1970-01-01. - If :const:`'julian'`, unit must be :const:`'D'`, and origin is set to beginning of Julian Calendar. Julian day number :const:`0` is assigned to the day starting at noon on January 1, 4713 BC. - If Timestamp convertible (Timestamp, dt.datetime, np.datetimt64 or date string), origin is set to Timestamp identified by origin. - If a float or integer, origin is the millisecond difference relative to 1970-01-01. cache : bool, default True If :const:`True`, use a cache of unique, converted dates to apply the datetime conversion. May produce significant speed-up when parsing duplicate date strings, especially ones with timezone offsets. The cache is only used when there are at least 50 values. The presence of out-of-bounds values will render the cache unusable and may slow down parsing. Returns ------- datetime If parsing succeeded. Return type depends on input (types in parenthesis correspond to fallback in case of unsuccessful timezone or out-of-range timestamp parsing): - scalar: :class:`Timestamp` (or :class:`datetime.datetime`) - array-like: :class:`DatetimeIndex` (or :class:`Series` with :class:`object` dtype containing :class:`datetime.datetime`) - Series: :class:`Series` of :class:`datetime64` dtype (or :class:`Series` of :class:`object` dtype containing :class:`datetime.datetime`) - DataFrame: :class:`Series` of :class:`datetime64` dtype (or :class:`Series` of :class:`object` dtype containing :class:`datetime.datetime`) Raises ------ ParserError When parsing a date from string fails. ValueError When another datetime conversion error happens. For example when one of 'year', 'month', day' columns is missing in a :class:`DataFrame`, or when a Timezone-aware :class:`datetime.datetime` is found in an array-like of mixed time offsets, and ``utc=False``. See Also -------- DataFrame.astype : Cast argument to a specified dtype. to_timedelta : Convert argument to timedelta. convert_dtypes : Convert dtypes. Notes ----- Many input types are supported, and lead to different output types: - **scalars** can be int, float, str, datetime object (from stdlib :mod:`datetime` module or :mod:`numpy`). They are converted to :class:`Timestamp` when possible, otherwise they are converted to :class:`datetime.datetime`. None/NaN/null scalars are converted to :const:`NaT`. - **array-like** can contain int, float, str, datetime objects. They are converted to :class:`DatetimeIndex` when possible, otherwise they are converted to :class:`Index` with :class:`object` dtype, containing :class:`datetime.datetime`. None/NaN/null entries are converted to :const:`NaT` in both cases. - **Series** are converted to :class:`Series` with :class:`datetime64` dtype when possible, otherwise they are converted to :class:`Series` with :class:`object` dtype, containing :class:`datetime.datetime`. None/NaN/null entries are converted to :const:`NaT` in both cases. - **DataFrame/dict-like** are converted to :class:`Series` with :class:`datetime64` dtype. For each row a datetime is created from assembling the various dataframe columns. Column keys can be common abbreviations like [‘year’, ‘month’, ‘day’, ‘minute’, ‘second’, ‘ms’, ‘us’, ‘ns’]) or plurals of the same. The following causes are responsible for :class:`datetime.datetime` objects being returned (possibly inside an :class:`Index` or a :class:`Series` with :class:`object` dtype) instead of a proper pandas designated type (:class:`Timestamp`, :class:`DatetimeIndex` or :class:`Series` with :class:`datetime64` dtype): - when any input element is before :const:`Timestamp.min` or after :const:`Timestamp.max`, see `timestamp limitations `_. - when ``utc=False`` (default) and the input is an array-like or :class:`Series` containing mixed naive/aware datetime, or aware with mixed time offsets. Note that this happens in the (quite frequent) situation when the timezone has a daylight savings policy. In that case you may wish to use ``utc=True``. Examples -------- **Handling various input formats** Assembling a datetime from multiple columns of a :class:`DataFrame`. The keys can be common abbreviations like ['year', 'month', 'day', 'minute', 'second', 'ms', 'us', 'ns']) or plurals of the same >>> df = pd.DataFrame({'year': [2015, 2016], ... 'month': [2, 3], ... 'day': [4, 5]}) >>> pd.to_datetime(df) 0 2015-02-04 1 2016-03-05 dtype: datetime64[ns] Using a unix epoch time >>> pd.to_datetime(1490195805, unit='s') Timestamp('2017-03-22 15:16:45') >>> pd.to_datetime(1490195805433502912, unit='ns') Timestamp('2017-03-22 15:16:45.433502912') .. warning:: For float arg, precision rounding might happen. To prevent unexpected behavior use a fixed-width exact type. Using a non-unix epoch origin >>> pd.to_datetime([1, 2, 3], unit='D', ... origin=pd.Timestamp('1960-01-01')) DatetimeIndex(['1960-01-02', '1960-01-03', '1960-01-04'], dtype='datetime64[ns]', freq=None) **Differences with strptime behavior** :const:`"%f"` will parse all the way up to nanoseconds. >>> pd.to_datetime('2018-10-26 12:00:00.0000000011', ... format='%Y-%m-%d %H:%M:%S.%f') Timestamp('2018-10-26 12:00:00.000000001') **Non-convertible date/times** If a date does not meet the `timestamp limitations `_, passing ``errors='ignore'`` will return the original input instead of raising any exception. Passing ``errors='coerce'`` will force an out-of-bounds date to :const:`NaT`, in addition to forcing non-dates (or non-parseable dates) to :const:`NaT`. >>> pd.to_datetime('13000101', format='%Y%m%d', errors='ignore') '13000101' >>> pd.to_datetime('13000101', format='%Y%m%d', errors='coerce') NaT .. _to_datetime_tz_examples: **Timezones and time offsets** The default behaviour (``utc=False``) is as follows: - Timezone-naive inputs are converted to timezone-naive :class:`DatetimeIndex`: >>> pd.to_datetime(['2018-10-26 12:00:00', '2018-10-26 13:00:15']) DatetimeIndex(['2018-10-26 12:00:00', '2018-10-26 13:00:15'], dtype='datetime64[ns]', freq=None) - Timezone-aware inputs *with constant time offset* are converted to timezone-aware :class:`DatetimeIndex`: >>> pd.to_datetime(['2018-10-26 12:00 -0500', '2018-10-26 13:00 -0500']) DatetimeIndex(['2018-10-26 12:00:00-05:00', '2018-10-26 13:00:00-05:00'], dtype='datetime64[ns, UTC-05:00]', freq=None) - However, timezone-aware inputs *with mixed time offsets* (for example issued from a timezone with daylight savings, such as Europe/Paris) are **not successfully converted** to a :class:`DatetimeIndex`. Instead a simple :class:`Index` containing :class:`datetime.datetime` objects is returned: >>> pd.to_datetime(['2020-10-25 02:00 +0200', '2020-10-25 04:00 +0100']) Index([2020-10-25 02:00:00+02:00, 2020-10-25 04:00:00+01:00], dtype='object') - A mix of timezone-aware and timezone-naive inputs is also converted to a simple :class:`Index` containing :class:`datetime.datetime` objects: >>> from datetime import datetime >>> pd.to_datetime(["2020-01-01 01:00:00-01:00", datetime(2020, 1, 1, 3, 0)]) Index([2020-01-01 01:00:00-01:00, 2020-01-01 03:00:00], dtype='object') | Setting ``utc=True`` solves most of the above issues: - Timezone-naive inputs are *localized* as UTC >>> pd.to_datetime(['2018-10-26 12:00', '2018-10-26 13:00'], utc=True) DatetimeIndex(['2018-10-26 12:00:00+00:00', '2018-10-26 13:00:00+00:00'], dtype='datetime64[ns, UTC]', freq=None) - Timezone-aware inputs are *converted* to UTC (the output represents the exact same datetime, but viewed from the UTC time offset `+00:00`). >>> pd.to_datetime(['2018-10-26 12:00 -0530', '2018-10-26 12:00 -0500'], ... utc=True) DatetimeIndex(['2018-10-26 17:30:00+00:00', '2018-10-26 17:00:00+00:00'], dtype='datetime64[ns, UTC]', freq=None) - Inputs can contain both string or datetime, the above rules still apply >>> pd.to_datetime(['2018-10-26 12:00', datetime(2020, 1, 1, 18)], utc=True) DatetimeIndex(['2018-10-26 12:00:00+00:00', '2020-01-01 18:00:00+00:00'], dtype='datetime64[ns, UTC]', freq=None) >ISO8601rz8Cannot use 'exact' when 'format' is 'mixed' or 'ISO8601'zThe argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.r^Nr)rrrYrrrr)r|rrr@rrryrz)+r no_defaultrrcrdr$rrrrrrrrr/rrrrZ _constructorr|rr.rMutableMapping_assemble_from_unit_mappingsr;rr+rr rrr6rrrr~r@rrrkZbool_)rlrrYrrrvrrrrrwrxrrvaluesZargcr@rKrKrLrsxD              rCrDrEhmsrUrVrW)rCZyearsrDmonthsrEdaysrOrPrQrRrSrTrUZ millisecondZ millisecondsrV microsecond microsecondsrWZ nanosecondZ nanoseconds)rrc sddlm}mm}||}|jjs,tdddfdd|D}dd|D}d d d g}t t |t |}t |rd |} td | dt t |t t } t | rd | } td| dfdd} | ||d d| ||d d| ||d } zt| d|d} Wn8ttfk rp}ztd||W5d}~XYnXddddddg}|D]}||}|dk r||krz| || |||d7} Wn>ttfk r}ztd |d!||W5d}~XYnXq| S)"a. assemble the unit specified fields from the arg (DataFrame) Return a Series for actual parsing Parameters ---------- arg : DataFrame errors : {'ignore', 'raise', 'coerce'}, default 'raise' - If :const:`'raise'`, then invalid parsing will raise an exception - If :const:`'coerce'`, then invalid parsing will be set as :const:`NaT` - If :const:`'ignore'`, then invalid parsing will return the input utc : bool Whether to convert/localize timestamps to UTC. Returns ------- Series r)r? to_numeric to_timedeltaz#cannot assemble with duplicate keyscSs,|tkrt|S|tkr(t|S|Sr) _unit_maplower)valuerKrKrLrs   z'_assemble_from_unit_mappings..fcsi|]}||qSrKrK)rk)rrKrL sz0_assemble_from_unit_mappings..cSsi|]\}}||qSrKrK)rrvrKrKrLrsrCrDrE,zNto assemble mappings requires at least that [year, month, day] be specified: [z ] is missingz9extra keys have been passed to the datetime assemblage: [rcs&|d}t|r"|jddd}|S)Nrint64Fr)r*r)r)rrrKrLrs z,_assemble_from_unit_mappings..coerce'dz%Y%m%d)rvrrzcannot assemble the datetimes: NrrrrUrVrW)rrzcannot assemble the datetimes [z]: )r~r?rrcolumnsrrkeysitemssortedrsrpjoinrrrrtget)rlrrr?rrZunit_revrequiredreqZ _requiredZexcessZ_excessrrrZunitsrrrK)rrrrLr`sX       " rznpt.NDArray[np.object_]znp.ndarray | None)rlrrZc sfddfdd}z|tjWStttfk rDYnXz|tj}||t|WStttfk r|YnXzt |t t }|||WStttfk rYnXdS)a* try to parse the YYYYMMDD/%Y%m%d format, try to deal with NaT-like, arg is a passed in as an object dtype, but could really be ints/strings with nan-like/or floats (e.g. with nan) Parameters ---------- arg : np.ndarray[object] errors : {'raise','ignore','coerce'} cs>|jtdd}t|d|dd|d}tj|ddS)NFrrrrr)rrrZtry_parse_year_month_dayrZarray_to_datetime)cargparsedrrKrLcalcs z_attempt_YYYYMMDD..calccsRtj|jdd}|d}t||<||tjtj}|d||<|S)Nrrzi8)rrshapeviewrrfloat64r)rrrZiresultZ masked_result)rrKrLcalc_with_masks   z)_attempt_YYYYMMDD..calc_with_maskN) rrrr OverflowErrorrtrr0r4isinrr)rlrrrrrK)rrrL_attempt_YYYYMMDDs"    rr)F)rhN)FN)N)NFNrNNT) ..........) ..........) ..........)x __future__r collectionsrr functoolsr itertoolsrtypingrrr r r r r rrrcZnumpyrZ pandas._libsrrZpandas._libs.tslibsrrrrrrrrrrrZpandas._libs.tslibs.conversionrZpandas._libs.tslibs.parsingrrZpandas._libs.tslibs.strptimerZpandas._typingr r!r"r#Zpandas.util._exceptionsr$Zpandas.core.dtypes.commonr%r&r'r(r)r*r+r,r-Zpandas.core.dtypes.genericr.r/Zpandas.core.dtypes.missingr0Z pandas.arraysr1r2r3Z pandas.corer4Zpandas.core.algorithmsr5Zpandas.core.arrays.baser6Zpandas.core.arrays.datetimesr7r8r9Zpandas.core.constructionr:Zpandas.core.indexes.baser;Zpandas.core.indexes.datetimesr<Zpandas._libs.tslibs.nattyper=Zpandas._libs.tslibs.timedeltasr>r~r?r@rirjrbZScalarrrrBrArNZDictConvertiblerqrgrurrrrrrrrrrrrr__all__rKrKrKrLs     , 0   ,              <0 &yHI&&&&^7