B W0d?@sddlmZddlmZddlmZddlmZddlmZddl m Z m Z m Z m Z mZmZmZmZddlZddlZddlmZdd lmZmZmZmZmZmZmZdd lm Z m!Z!m"Z"dd l#m$Z$dd l%m&Z&m'Z'm(Z(dd l)m*Z*m+Z+m,Z,m-Z-m.Z.m/Z/m0Z0m1Z1m2Z2m3Z3ddl4m5Z5m6Z6ddl7m8Z8ddl9m:Z:m;Z;ddlm?Z?ddl@mAZAmBZBmCZCddlDmEZEddlFmGZGe rddlHmIZIddlJmKZKee ee&dfZLeeMeNeOfZPedePeZQeeQeLfZRdZSddZTdjddd d!d"d#d$ZUdd%d!d&dd'd(d)ZVdkd*d+d,d-d.d/d0ZWdld1dd%d-d2d3d4ZXd5d-d6d7d8ZYdmd%d,d d?d@ZZd=d!d=d!dAdBdCdDZ[d=d!d=d!dAdBdEdFZ\d=d-dGdHdIZ]dJdKZ^edndd=d!d!d+d%d!d%d!d!dMdN dOdPZ_edodd=d!d!d+d%d!d%d!d!ddN dQdPZ_edpdRd=d!d!d+d%d!d%d!d!dSdN dTdPZ_dqd1d=d!d!d+d%d!d%d!d!dVdN dWdPZ_dXdXdYdYdZdZd[d[d\d\d]d]d^d^d^d_d_d_d`d`d`daZ`dbdcZad5d=dddedfdgZbdrdhdiZcdS)s) annotations)abc)datetime)partial)islice) TYPE_CHECKINGCallableHashableListTupleTypeVarUnionoverloadN)tslib)OutOfBoundsDatetime Timedelta Timestamp conversioniNaT nat_stringsparsing)DateParseError format_is_isoguess_datetime_format)array_strptime) AnyArrayLike ArrayLikeTimezone) ensure_objectis_datetime64_dtypeis_datetime64_ns_dtypeis_datetime64tz_dtypeis_float is_integeris_integer_dtype is_list_likeis_numeric_dtype is_scalar) ABCDataFrame ABCSeries)notna) DatetimeArray IntegerArray) algorithms)unique)maybe_convert_dtypeobjects_to_datetime64ns tz_to_dtype)Index) DatetimeIndex)NaTType)Seriesr5DatetimeScalar2cKs0t|d}t|r,t||df|SdS)Nr)r*Znonzerolenr)arrkwargsZnon_nan_elementsr;M/var/www/html/venv/lib/python3.7/site-packages/pandas/core/tools/datetimes.py _guess_datetime_format_for_array]sr=ffffff?ArrayConvertiblefloatz int | Nonebool)arg unique_share check_countreturncCsd}|dkrsz3_return_parsed_timezone_results..Ncsg|]}|qSr;) tz_convert)rbZ tz_result)rZr;r<res)rY)nparrayzipr2)r_ timezonesrZrYZ tz_resultsr;)rZr<_return_parsed_timezone_resultss rkraiseFTzTimezone | Nonestr) rMrYrZuniterrorsinfer_datetime_formatdayfirst yearfirstexactc  Cs`t|ttfrtj|dd}t|dd} t| rht|ttfsLt|||dS|dkrd| d |}|St | rt|ttfsyt|||dSt k rYqXn|r| |S|S|dk r|dk rt dt |||||St|dd d krtd |} yt|d d \}} Wnbtk rr|d krRtjdgddt|} t| |dS|dkrlt||d}|SYnXt|}d }|r|dkrt||d}|dk rt|}|r| }d}|dk rt|| |||| ||}|dk r|S|dks|st|dk}t||||||dd\}}|dk rJt|t|d}tj||dS|dk}t|||dS)aS Helper function for to_datetime. Performs the conversions of 1D listlike of dates Parameters ---------- arg : list, tuple, ndarray, Series, Index date to be parsed name : object None or string for the Index name tz : object None or 'utc' unit : str None or string of the frequency of the passed data errors : str error handing behaviors from to_datetime, 'raise', 'coerce', 'ignore' infer_datetime_format : bool, default False inferring format behavior from to_datetime dayfirst : bool dayfirst parsing behavior from to_datetime yearfirst : bool yearfirst parsing behavior from to_datetime exact : bool, default True exact format matching behavior from to_datetime Returns ------- Index-like of parsed dates O)rPrPN)rZrYrXz#cannot specify both format and unitndimrGzAarg must be a string, datetime, list, tuple, 1-d array, or SeriesF)copycoerceZNaTzdatetime64[ns])rYignore)rqT)rqrrrXrorequire_iso8601Z allow_object)rXrY) isinstancelisttuplergrhgetattrr!r+r3rfrar ValueError_to_datetime_with_unitrKr/repeatr8r2rr=r_to_datetime_with_formatrIr0r1 _simple_newr[)rBrMrYrZrnrorprqrrrsZ arg_dtypeorig_arg_ZnpvaluesidxryZformat_is_iso8601rcrXr_ tz_parseddtar;r;r<_convert_listlike_datetimess*            rz Index | None)fmtrsrorprEc Cs|dk}y6t||||d\}} d|ks.d|krt|trt ||| | }|j s| |} n | |j |}|j ||j|jd} nt|ttjfrt||| } nt|tr.t ||| | }|j st|||jd} n| |||jd} nt|ryt ||| | }Wn:tk r|dkrhdd lm}|gtd }YnX|j st||} n | ||} n| t|g|d} | S) aO Convert argument to datetime. Parameters ---------- arg : int, float, str, datetime, list, tuple, 1-d array, Series, DataFrame/dict-like The object to convert to a datetime. errors : {'ignore', 'raise', 'coerce'}, default 'raise' - If 'raise', then invalid parsing will raise an exception. - If 'coerce', then invalid parsing will be set as NaT. - If 'ignore', then invalid parsing will return the input. dayfirst : bool, default False Specify a date parse order if `arg` is str or its list-likes. If True, parses dates with the day first, eg 10/11/12 is parsed as 2012-11-10. Warning: dayfirst=True is not strict, but will prefer to parse with day first (this is a known bug, based on dateutil behavior). yearfirst : bool, default False Specify a date parse order if `arg` is str or its list-likes. - If True parses dates with the year first, eg 10/11/12 is parsed as 2010-11-12. - If both dayfirst and yearfirst are True, yearfirst is preceded (same as dateutil). Warning: yearfirst=True is not strict, but will prefer to parse with year first (this is a known bug, based on dateutil behavior). utc : bool, default None Return UTC DatetimeIndex if True (converting any tz-aware datetime.datetime objects as well). format : str, default None The strftime to parse time, eg "%d/%m/%Y", note that "%f" will parse all the way up to nanoseconds. See strftime documentation for more information on choices: https://docs.python.org/3/library/datetime.html#strftime-and-strptime-behavior. exact : bool, True by default Behaves as: - If True, require an exact format match. - If False, allow the format to match anywhere in the target string. 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' (the default), this would calculate the number of milliseconds to the unix epoch start. infer_datetime_format : bool, default False If 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. 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 'unix' (or POSIX) time; origin is set to 1970-01-01. - If 'julian', unit must be 'D', and origin is set to beginning of Julian Calendar. Julian day number 0 is assigned to the day starting at noon on January 1, 4713 BC. - If Timestamp convertible, origin is set to Timestamp identified by origin. cache : bool, default True If 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. .. versionchanged:: 0.25.0 - changed default value from False to True. Returns ------- datetime If parsing succeeded. Return type depends on input: - list-like: DatetimeIndex - Series: Series of datetime64 dtype - scalar: Timestamp In case when it is not possible to return designated types (e.g. when any element of input is before Timestamp.min or after Timestamp.max) return will have datetime.datetime type (or corresponding array/Series). See Also -------- DataFrame.astype : Cast argument to a specified dtype. to_timedelta : Convert argument to timedelta. convert_dtypes : Convert dtypes. Examples -------- Assembling a datetime from multiple columns of a 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] 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 NaT, in addition to forcing non-dates (or non-parseable dates) to NaT. >>> pd.to_datetime('13000101', format='%Y%m%d', errors='ignore') datetime.datetime(1300, 1, 1, 0, 0) >>> pd.to_datetime('13000101', format='%Y%m%d', errors='coerce') NaT Passing infer_datetime_format=True can often-times speedup a parsing if its not an ISO8601 format exactly, but in a regular format. >>> s = pd.Series(['3/11/2000', '3/12/2000', '3/13/2000'] * 1000) >>> s.head() 0 3/11/2000 1 3/12/2000 2 3/13/2000 3 3/11/2000 4 3/12/2000 dtype: object >>> %timeit pd.to_datetime(s, infer_datetime_format=True) # doctest: +SKIP 100 loops, best of 3: 10.4 ms per loop >>> %timeit pd.to_datetime(s, infer_datetime_format=False) # doctest: +SKIP 1 loop, best of 3: 471 ms per loop 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) In case input is list-like and the elements of input are of mixed timezones, return will have object type Index if utc=False. >>> pd.to_datetime(['2018-10-26 12:00 -0530', '2018-10-26 12:00 -0500']) Index([2018-10-26 12:00:00-05:30, 2018-10-26 12:00:00-05:00], dtype='object') >>> 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) NrrX)rZrnrqrrrorsrp)rQrY)rYrlr)r5)rP)rrrrzrrZrfrar)rVrr]r^Z _constructorrQrYr(rMutableMapping_assemble_from_unit_mappingsr2r`r%rrRr5rSrgrh)rBrorqrrrXrMrsrnrprrNrZrOr_rUrr5r;r;r<rs^2              yearmonthdayhmsmsusns)rZyearsrmonthsrdayshourhoursminuteminutessecondsecondsrZ millisecondZ millisecondsr microsecond microsecondsrZ nanosecond nanosecondsc 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 } yt| d|d} Wn8ttfk rp}ztd||Wdd}~XYnXxdD]}||}|dk rx||krxy| || |||d7} Wn>ttfk r}ztd|d||Wdd}~XYnXqxW| 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 'raise', then invalid parsing will raise an exception - If 'coerce', then invalid parsing will be set as NaT - If 'ignore', then invalid parsing will return the input tz : None or 'utc' Returns ------- Series r) DataFrame to_numeric to_timedeltaz#cannot assemble with duplicate keyscSs,|tkrt|S|tkr(t|S|S)N) _unit_maplower)valuer;r;r<fs   z'_assemble_from_unit_mappings..fcsi|]}||qSr;r;)rbk)rr;r< sz0_assemble_from_unit_mappings..cSsi|]\}}||qSr;r;)rbrvr;r;r<rsrrr,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)N)roint64F)rv)r$r)r)rorr;r<rws z,_assemble_from_unit_mappings..coercei'dz%Y%m%d)rMrorXzcannot assemble the datetimes: N)rrrrrr)rnrozcannot assemble the datetimes [z]: )rRrrrcolumnsrTr~keysitemssortedrJr8joinrrrrKget)rBrorZrrrnZunit_revrequiredreqZ _requiredexcessZ_excessrwrrurr;)rorrr<rsD     8"  rznp.ndarray | None)rBrorEc sfddfdd}y|tjStttfk rBYnXy|tj}||t|Stttfk rxYnXyt |t t }|||Stttfk 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:|t}t|d|dd|d}tj|ddS)Ni'r)ror)rrSrZtry_parse_year_month_dayrZarray_to_datetime)cargparsed)ror;r<calcs z_attempt_YYYYMMDD..calccsRtj|jdd}|d}t||<||tjtj}|d||<|S)NzM8[ns])rPr)rgrrrrrfloat64r)rmaskr_rZ masked_result)rr;r<calc_with_mask$s   z)_attempt_YYYYMMDD..calc_with_maskN) rrgrr~ OverflowErrorrKrr*r-isinr{r)rBrorrrr;)rror<rs"    rcCs*tjdtddddlm}|||||S)Nz{`to_time` has been moved, should be imported from pandas.core.tools.times. This alias will be removed in a future version.) stacklevelr)to_time)warningswarn FutureWarningZpandas.core.tools.timesr)rBrMZinfer_time_formatrorr;r;r<rFs  r)r>N)NN)N)NNNrlFNNT) ..........) ..........) ..........) rlFFNNTNFrT)NFrl)d __future__r collectionsrr functoolsr itertoolsrtypingrrr r r r r rrnumpyrgZ pandas._libsrZpandas._libs.tslibsrrrrrrrZpandas._libs.tslibs.parsingrrrZpandas._libs.tslibs.strptimerZpandas._typingrrrZpandas.core.dtypes.commonrrr r!r"r#r$r%r&r'Zpandas.core.dtypes.genericr(r)Zpandas.core.dtypes.missingr*Z pandas.arraysr+r,Z pandas.corer-Zpandas.core.algorithmsr.Zpandas.core.arrays.datetimesr/r0r1Zpandas.core.indexes.baser2Zpandas.core.indexes.datetimesr3Zpandas._libs.tslibs.nattyper4rRr5r?intr@rmZScalarr6r\rHr=rLrVr[r`rkrrrrrrrrrrr;r;r;r<s     (  $  0          ;,  |/0$I&&&$n\6