U f/eK@sUdZddlmZddlZddlmZmZmZmZm Z m Z ddl Z ddl mmZddlmZmZmZmZmZmZmZddlmZddlmZddlmZdd lm Z m!Z!dd l"m#Z#m$Z$m%Z%m&Z&m'Z'dd l(m)Z)m*Z*m+Z+dd l,m-Z-m.Z.dd l/m0Z0ddl1m2Z2ddl3m4Z4m5Z5m6Z6ddl7m8Z8ddl9m:Z:ddl;mm?Z?erlddlm@Z@ddlAmBZBiZCdeDd<dddddZEe dddZFGddde2ZGGdddZHGd d!d!eIZJGd"d#d#eIZKGd$d%d%eeZLGd&dde8ZMdS)'z. Base and utility classes for pandas objects. ) annotationsN) TYPE_CHECKINGAnyGenericHashableTypeVarcast) ArrayLikeDtypeDtypeObj FrameOrSeries IndexLabelShapefinal)PYPY)functionAbstractMethodError)cache_readonlydoc)is_categorical_dtype is_dict_likeis_extension_array_dtypeis_object_dtype is_scalar) ABCDataFrameABCIndex ABCSeries)isnaremove_na_arraylike) algorithms) DirNamesMixin) duplicatedunique1d value_counts)OpsMixin)ExtensionArray)!create_series_with_explicit_dtype)Literal) Categoricalzdict[str, str] _shared_docs IndexOpsMixin)klassZinplaceuniquer"_T)boundcs\eZdZUdZded<eddZdddd Zdd d d ddZddfdd Z Z S) PandasObjectz/ Baseclass for various pandas objects. zdict[str, Any]_cachecCst|S)zJ Class constructor (for this class it's just `__class__`. )typeselfr64/tmp/pip-unpacked-wheel-tiezk1ph/pandas/core/base.py _constructorZszPandasObject._constructorstrreturncCs t|S)zI Return a string representation for a particular object. )object__repr__r4r6r6r7r=aszPandasObject.__repr__Nz str | NoneNone)keyr;cCs4t|dsdS|dkr"|jn|j|ddS)zV Reset cached properties. If ``key`` is passed, only clears that key. r2N)hasattrr2clearpop)r5r?r6r6r7 _reset_cachehs   zPandasObject._reset_cacheintcs<t|dd}|r2|dd}tt|r(|n|StS)zx Generates the total memory usage for an object that returns either a value or Series of values memory_usageNTdeep)getattrrDrsumsuper __sizeof__)r5rEZmem __class__r6r7rKss   zPandasObject.__sizeof__)N) __name__ __module__ __qualname____doc____annotations__propertyr8r=rCrK __classcell__r6r6rLr7r1Rs   r1c@s&eZdZdZddZddddZdS) NoNewAttributesMixina Mixin which prevents adding new attributes. Prevents additional attributes via xxx.attribute = "something" after a call to `self.__freeze()`. Mainly used to prevent the user from using wrong attributes on an accessor (`Series.cat/.str/.dt`). If you really want to add a new attribute at a later time, you need to use `object.__setattr__(self, key, value)`. cCst|dddS)z9 Prevents setting additional attributes. __frozenTN)r< __setattr__r4r6r6r7_freezeszNoNewAttributesMixin._freezer9)r?cCsTt|ddrB|dksB|t|jksBt||ddk sBtd|dt|||dS)NrVFr2z"You cannot add any new attribute '')rHr3__dict__AttributeErrorr<rW)r5r?valuer6r6r7rWs  z NoNewAttributesMixin.__setattr__N)rNrOrPrQrXrWr6r6r6r7rUs rUc@s eZdZdS) DataErrorNrNrOrPr6r6r6r7r]sr]c@s eZdZdS)SpecificationErrorNr^r6r6r6r7r_sr_c@seZdZUdZded<dZded<ded<d d gZeeZe e d d Z e d dZ e e ddddZe e ddZddZdddddZddZeZdS)SelectionMixinz mixin implementing the selection & aggregation interface on a group-like object sub-classes need to define: obj, exclusions r objNzIndexLabel | None _selectionzfrozenset[Hashable] exclusionsr2 __setstate__cCs&t|jtttttjfs |jgS|jSN) isinstancerblisttuplerrnpndarrayr4r6r6r7_selection_lists zSelectionMixin._selection_listcCs,|jdkst|jtr|jS|j|jSdSre)rbrfrarr4r6r6r7 _selected_objszSelectionMixin._selected_objrDr:cCs|jjSre)rlndimr4r6r6r7rmszSelectionMixin.ndimcCsL|jdk r"t|jtr"|j|jSt|jdkrB|jj|jddS|jSdS)Nr)axis)rbrfrarrklenrcZdropr4r6r6r7_obj_with_exclusionss  z#SelectionMixin._obj_with_exclusionscCs|jdk rtd|jdt|tttttjfrt |j j |t |kr|tt ||j j }tdt|dd|jt|ddSt|dd s||j j krtd ||j|ddS||j krtd ||j |}|j}|j|||d SdS) Nz Column(s) z already selectedzColumns not found: rnrmZas_indexFzColumn not found: )rmsubset)rb IndexErrorrfrgrhrrrirjrpracolumns intersectionset differenceKeyErrorr9_gotitemrHrm)r5r?bad_keysrurmr6r6r7 __getitem__s      zSelectionMixin.__getitem__rtcCs t|dS)a sub-classes to define return a sliced object Parameters ---------- key : str / list of selections ndim : {1, 2} requested ndim of result subset : object, default None subset to act on Nr)r5r?rmrur6r6r7r|s zSelectionMixin._gotitemcOs t|dSrer)r5funcargskwargsr6r6r7 aggregateszSelectionMixin.aggregate)N)rNrOrPrQrRrbZ_internal_namesryZ_internal_names_setrrSrkrrlrmrqr~r|rZaggr6r6r6r7r`s*     r`c@seZdZUdZdZedgZded<edddd Z ed dd d Z d d dddZ ee ddZ eddddZ ddddZeddddZddZeddddZedddd Zed!dd"d#Zd$d%ejfd&d'd(d)d*d+Zed'dd,d-Zdwd'd/d0d1Zed2d3d4d5dxd'dd6d7d8Zdyd'd/d9d:Zeed3d2d;d5dzdddd?ZeZd@dAZe d'ddBdCZ!dDdEZ"dFd.d$d$dGdHdIdJdKZ#d{dLdMZ$d|d'd'd'd'dNdOdPZ%dQdRZ&d}d'ddSdTdUZ'ed'ddVdWZ(ed'ddXdYZ)ed'ddZd[Z*ed'dd\d]Z+d~d'dd^d_d`Z,ee-j.dadadae/0dbdcdd'dedfdgdhZ.die1dj<ee1djdkdldd(ddndoZ2ddqdrZ3e4ddsd(dtdudvZ5d$S)r+zS Common ops mixin to support a unified interface / docs for Series / Index itolistzfrozenset[str] _hidden_attrsr r:cCs t|dSrerr4r6r6r7dtype szIndexOpsMixin.dtypezExtensionArray | np.ndarraycCs t|dSrerr4r6r6r7_valuesszIndexOpsMixin._valuesr/)r5r;cOst|||S)zw Return the transpose, which is by definition self. Returns ------- %(klass)s )nvZvalidate_transpose)r5rrr6r6r7 transposes zIndexOpsMixin.transposezD Return the transpose, which is by definition self. )rrcCs|jjS)zE Return a tuple of the shape of the underlying data. )rshaper4r6r6r7r)szIndexOpsMixin.shaperDcCs t|dSrerr4r6r6r7__len__0szIndexOpsMixin.__len__cCsdS)zO Number of dimensions of the underlying data, by definition 1. rnr6r4r6r6r7rm4szIndexOpsMixin.ndimcCs$t|dkrtt|StddS)a  Return the first element of the underlying data as a Python scalar. Returns ------- scalar The first element of %(klass)s. Raises ------ ValueError If the data is not length-1. rnz6can only convert an array of size 1 to a Python scalarN)rpnextiter ValueErrorr4r6r6r7item;s  zIndexOpsMixin.itemcCs|jjS)zD Return the number of bytes in the underlying data. )rnbytesr4r6r6r7rMszIndexOpsMixin.nbytescCs t|jS)zG Return the number of elements in the underlying data. )rprr4r6r6r7sizeTszIndexOpsMixin.sizer&cCs t|dS)aM The ExtensionArray of the data backing this Series or Index. Returns ------- ExtensionArray An ExtensionArray of the values stored within. For extension types, this is the actual array. For NumPy native types, this is a thin (no copy) wrapper around :class:`numpy.ndarray`. ``.array`` differs ``.values`` which may require converting the data to a different form. See Also -------- Index.to_numpy : Similar method that always returns a NumPy array. Series.to_numpy : Similar method that always returns a NumPy array. Notes ----- This table lays out the different array types for each extension dtype within pandas. ================== ============================= dtype array type ================== ============================= category Categorical period PeriodArray interval IntervalArray IntegerNA IntegerArray string StringArray boolean BooleanArray datetime64[ns, tz] DatetimeArray ================== ============================= For any 3rd-party extension types, the array type will be an ExtensionArray. For all remaining dtypes ``.array`` will be a :class:`arrays.NumpyExtensionArray` wrapping the actual ndarray stored within. If you absolutely need a NumPy array (possibly with copying / coercing data), then use :meth:`Series.to_numpy` instead. Examples -------- For regular NumPy types like int, and float, a PandasArray is returned. >>> pd.Series([1, 2, 3]).array [1, 2, 3] Length: 3, dtype: int64 For extension types, like Categorical, the actual ExtensionArray is returned >>> ser = pd.Series(pd.Categorical(['a', 'b', 'a'])) >>> ser.array ['a', 'b', 'a'] Categories (2, object): ['a', 'b'] Nrr4r6r6r7array[s?zIndexOpsMixin.arrayNFz Dtype | Noneboolz np.ndarray)rcopyr;cKst|jr$|jj|f||d|S|rHt|d}td|dtj|j |d}|sf|t j k r| }|t j k r||| <|S)a A NumPy ndarray representing the values in this Series or Index. Parameters ---------- dtype : str or numpy.dtype, optional The dtype to pass to :meth:`numpy.asarray`. copy : bool, default False Whether to ensure that the returned value is not a view on another array. Note that ``copy=False`` does not *ensure* that ``to_numpy()`` is no-copy. Rather, ``copy=True`` ensure that a copy is made, even if not strictly necessary. na_value : Any, optional The value to use for missing values. The default value depends on `dtype` and the type of the array. .. versionadded:: 1.0.0 **kwargs Additional keywords passed through to the ``to_numpy`` method of the underlying array (for extension arrays). .. versionadded:: 1.0.0 Returns ------- numpy.ndarray See Also -------- Series.array : Get the actual data stored within. Index.array : Get the actual data stored within. DataFrame.to_numpy : Similar method for DataFrame. Notes ----- The returned array will be the same up to equality (values equal in `self` will be equal in the returned array; likewise for values that are not equal). When `self` contains an ExtensionArray, the dtype may be different. For example, for a category-dtype Series, ``to_numpy()`` will return a NumPy array and the categorical dtype will be lost. For NumPy dtypes, this will be a reference to the actual data stored in this Series or Index (assuming ``copy=False``). Modifying the result in place will modify the data stored in the Series or Index (not that we recommend doing that). For extension types, ``to_numpy()`` *may* require copying data and coercing the result to a NumPy type (possibly object), which may be expensive. When you need a no-copy reference to the underlying data, :attr:`Series.array` should be used instead. This table lays out the different dtypes and default return types of ``to_numpy()`` for various dtypes within pandas. ================== ================================ dtype array type ================== ================================ category[T] ndarray[T] (same dtype as input) period ndarray[object] (Periods) interval ndarray[object] (Intervals) IntegerNA ndarray[object] datetime64[ns] datetime64[ns] datetime64[ns, tz] ndarray[object] (Timestamps) ================== ================================ Examples -------- >>> ser = pd.Series(pd.Categorical(['a', 'b', 'a'])) >>> ser.to_numpy() array(['a', 'b', 'a'], dtype=object) Specify the `dtype` to control how datetime-aware data is represented. Use ``dtype=object`` to return an ndarray of pandas :class:`Timestamp` objects, each with the correct ``tz``. >>> ser = pd.Series(pd.date_range('2000', periods=2, tz="CET")) >>> ser.to_numpy(dtype=object) array([Timestamp('2000-01-01 00:00:00+0100', tz='CET'), Timestamp('2000-01-02 00:00:00+0100', tz='CET')], dtype=object) Or ``dtype='datetime64[ns]'`` to return an ndarray of native datetime64 values. The values are converted to UTC and the timezone info is dropped. >>> ser.to_numpy(dtype="datetime64[ns]") ... # doctest: +ELLIPSIS array(['1999-12-31T23:00:00.000000000', '2000-01-01T23:00:00...'], dtype='datetime64[ns]') )rna_valuerz/to_numpy() got an unexpected keyword argument 'rY)r)rrrto_numpyrgkeys TypeErrorriasarrayrlib no_defaultrr)r5rrrrr}resultr6r6r7rs(c     zIndexOpsMixin.to_numpycCs|j Sre)rr4r6r6r7emptyszIndexOpsMixin.emptyTskipnacOs&t|t||tj|j|dS)a Return the maximum value of the Index. Parameters ---------- axis : int, optional For compatibility with NumPy. Only 0 or None are allowed. skipna : bool, default True Exclude NA/null values when showing the result. *args, **kwargs Additional arguments and keywords for compatibility with NumPy. Returns ------- scalar Maximum value. See Also -------- Index.min : Return the minimum value in an Index. Series.max : Return the maximum value in a Series. DataFrame.max : Return the maximum values in a DataFrame. Examples -------- >>> idx = pd.Index([3, 2, 1]) >>> idx.max() 3 >>> idx = pd.Index(['c', 'b', 'a']) >>> idx.max() 'c' For a MultiIndex, the maximum is determined lexicographically. >>> idx = pd.MultiIndex.from_product([('a', 'b'), (2, 1)]) >>> idx.max() ('b', 2) r)rvalidate_minmax_axisZ validate_maxnanopsZnanmaxrr5rorrrr6r6r7maxs(  zIndexOpsMixin.maxrminlargest)opZopposer\)rr;cOsX|j}t|t|||}t|trF|s<|r>> s = pd.Series({{'Corn Flakes': 100.0, 'Almond Delight': 110.0, ... 'Cinnamon Toast Crunch': 120.0, 'Cocoa Puff': 110.0}}) >>> s Corn Flakes 100.0 Almond Delight 110.0 Cinnamon Toast Crunch 120.0 Cocoa Puff 110.0 dtype: float64 >>> s.argmax() 2 >>> s.argmin() 0 The maximum cereal calories is the third element and the minimum cereal calories is the first element, since series is zero-indexed. rrrN) rrrZvalidate_argmax_with_skipnarfr&ranyargmaxrZ nanargmaxr5rorrrZdelegater6r6r7rGs4   zIndexOpsMixin.argmaxcOs&t|t||tj|j|dS)a Return the minimum value of the Index. Parameters ---------- axis : {None} Dummy argument for consistency with Series. skipna : bool, default True Exclude NA/null values when showing the result. *args, **kwargs Additional arguments and keywords for compatibility with NumPy. Returns ------- scalar Minimum value. See Also -------- Index.max : Return the maximum value of the object. Series.min : Return the minimum value in a Series. DataFrame.min : Return the minimum values in a DataFrame. Examples -------- >>> idx = pd.Index([3, 2, 1]) >>> idx.min() 1 >>> idx = pd.Index(['c', 'b', 'a']) >>> idx.min() 'a' For a MultiIndex, the minimum is determined lexicographically. >>> idx = pd.MultiIndex.from_product([('a', 'b'), (2, 1)]) >>> idx.min() ('a', 1) r)rrZ validate_minrZnanminrrr6r6r7rs(  zIndexOpsMixin.minsmallestcOsX|j}t|t|||}t|trF|s<|rt||d}|dkr,tt|jd||fd|i|S)zA Perform the reduction type operation if we can. Nz cannot perform the operation r)rHrr3rN) r5rrrorrrkwdsrr6r6r7_reduces  zIndexOpsMixin._reducec s t|r/z+IndexOpsMixin._map_values..)Zdtype_if_emptyr)rNcSs ||Sre)rvaluesfr6r6r7rUrignorecSst||t|tjSre)rZmap_infer_maskrviewriZuint8rr6r6r7rYsz+na_action must either be 'ignore' or None, z was passed)rrfdictr@r'riZfloat64rrrrrrindexZ get_indexerr Ztake_ndrNotImplementedErrorZastyper<rZ map_inferr) r5ZmapperZ na_actioncatrZindexerZ new_valuesZmap_fmsgr6rr7 _map_valuess>           zIndexOpsMixin._map_values) normalizesort ascendingdropnacCst||||||dS)a Return a Series containing counts of unique values. The resulting object will be in descending order so that the first element is the most frequently-occurring element. Excludes NA values by default. Parameters ---------- normalize : bool, default False If True then the object returned will contain the relative frequencies of the unique values. sort : bool, default True Sort by frequencies. ascending : bool, default False Sort in ascending order. bins : int, optional Rather than count values, group them into half-open bins, a convenience for ``pd.cut``, only works with numeric data. dropna : bool, default True Don't include counts of NaN. Returns ------- Series See Also -------- Series.count: Number of non-NA elements in a Series. DataFrame.count: Number of non-NA elements in a DataFrame. DataFrame.value_counts: Equivalent method on DataFrames. Examples -------- >>> index = pd.Index([3, 1, 2, 3, 4, np.nan]) >>> index.value_counts() 3.0 2 1.0 1 2.0 1 4.0 1 dtype: int64 With `normalize` set to `True`, returns the relative frequency by dividing all values by the sum of values. >>> s = pd.Series([3, 1, 2, 3, 4, np.nan]) >>> s.value_counts(normalize=True) 3.0 0.4 1.0 0.2 2.0 0.2 4.0 0.2 dtype: float64 **bins** Bins can be useful for going from a continuous variable to a categorical variable; instead of counting unique apparitions of values, divide the index in the specified number of half-open bins. >>> s.value_counts(bins=3) (0.996, 2.0] 2 (2.0, 3.0] 2 (3.0, 4.0] 1 dtype: int64 **dropna** With `dropna` set to `False` we can also see NaN index values. >>> s.value_counts(dropna=False) 3.0 2 1.0 1 2.0 1 4.0 1 NaN 1 dtype: int64 )rrrbinsr)r$)r5rrrrrr6r6r7r$jsVzIndexOpsMixin.value_countscCsZ|j}t|tjsN|}|jjdkrVt|trVt|jdddkrVt |}nt |}|S)N)mMtz) rrfrirjr.rkindrrHrr#)r5rrr6r6r7r.s  zIndexOpsMixin.unique)rr;cCs|}|rt|}t|S)a Return number of unique elements in the object. Excludes NA values by default. Parameters ---------- dropna : bool, default True Don't include NaN in the count. Returns ------- int See Also -------- DataFrame.nunique: Method nunique for DataFrame. Series.count: Count non-NA/null observations in the Series. Examples -------- >>> s = pd.Series([1, 3, 5, 7, 7]) >>> s 0 1 1 3 2 5 3 7 4 7 dtype: int64 >>> s.nunique() 4 )r.rrp)r5rZuniqsr6r6r7nuniques"zIndexOpsMixin.nuniquecCs|jddt|kS)zr Return boolean if values in the object are unique. Returns ------- bool F)r)rrpr4r6r6r7 is_uniques zIndexOpsMixin.is_uniquecCsddlm}||jS)z Return boolean if values in the object are monotonic_increasing. Returns ------- bool rIndex)pandasr is_monotonicr5rr6r6r7r s zIndexOpsMixin.is_monotoniccCs|jS)z) Alias for is_monotonic. )rr4r6r6r7is_monotonic_increasingsz%IndexOpsMixin.is_monotonic_increasingcCsddlm}||jS)z Return boolean if values in the object are monotonic_decreasing. Returns ------- bool rr)rris_monotonic_decreasingrr6r6r7rs z%IndexOpsMixin.is_monotonic_decreasing)rGr;cCsRt|jdr|jj|dS|jj}|rNt|rNtsNttj|j }|t |7}|S)aN Memory usage of the values. Parameters ---------- deep : bool, default False Introspect the data deeply, interrogate `object` dtypes for system-level memory consumption. Returns ------- bytes used See Also -------- numpy.ndarray.nbytes : Total bytes consumed by the elements of the array. Notes ----- Memory usage does not include memory consumed by elements that are not components of the array if deep=False or if used on PyPy rErF) r@rrErrrrrirjrrZmemory_usage_of_objects)r5rGvrr6r6r7 _memory_usage-s zIndexOpsMixin._memory_usager,z sort : bool, default False Sort `uniques` and shuffle `codes` to maintain the relationship. )rorderZ size_hintrrrz int | Noner na_sentinelcCstj|||dS)Nr)r factorize)r5rrr6r6r7rOszIndexOpsMixin.factorizea Find indices where elements should be inserted to maintain order. Find the indices into a sorted {klass} `self` such that, if the corresponding elements in `value` were inserted before the indices, the order of `self` would be preserved. .. note:: The {klass} *must* be monotonically sorted, otherwise wrong locations will likely be returned. Pandas does *not* check this for you. Parameters ---------- value : array-like Values to insert into `self`. side : {{'left', 'right'}}, optional If 'left', the index of the first suitable location found is given. If 'right', return the last such index. If there is no suitable index, return either 0 or N (where N is the length of `self`). sorter : 1-D array-like, optional Optional array of integer indices that sort `self` into ascending order. They are typically the result of ``np.argsort``. Returns ------- int or array of int A scalar or array of insertion points with the same shape as `value`. See Also -------- sort_values : Sort by the values along either axis. numpy.searchsorted : Similar method from NumPy. Notes ----- Binary search is used to find the required insertion points. Examples -------- >>> ser = pd.Series([1, 2, 3]) >>> ser 0 1 1 2 2 3 dtype: int64 >>> ser.searchsorted(4) 3 >>> ser.searchsorted([0, 4]) array([0, 3]) >>> ser.searchsorted([1, 3], side='left') array([0, 2]) >>> ser.searchsorted([1, 3], side='right') array([1, 3]) >>> ser = pd.Series(pd.to_datetime(['3/11/2000', '3/12/2000', '3/13/2000'])) >>> ser 0 2000-03-11 1 2000-03-12 2 2000-03-13 dtype: datetime64[ns] >>> ser.searchsorted('3/14/2000') 3 >>> ser = pd.Categorical( ... ['apple', 'bread', 'bread', 'cheese', 'milk'], ordered=True ... ) >>> ser ['apple', 'bread', 'bread', 'cheese', 'milk'] Categories (4, object): ['apple' < 'bread' < 'cheese' < 'milk'] >>> ser.searchsorted('bread') 1 >>> ser.searchsorted(['bread'], side='right') array([3]) If the values are not monotonically sorted, wrong locations may be returned: >>> ser = pd.Series([2, 1, 3]) >>> ser 0 2 1 1 2 3 dtype: int64 >>> ser.searchsorted(1) # doctest: +SKIP 0 # wrong result, correct would be 1 searchsortedr)r-leftcCstj|j|||dS)N)sidesorter)r rr)r5r\rrr6r6r7rszIndexOpsMixin.searchsortedfirstcCs|j|d}||SN)keep) _duplicated)r5rr"r6r6r7drop_duplicatess zIndexOpsMixin.drop_duplicatesz!Literal[('first', 'last', False)])rr;cCst|j|dSr)r"r)r5rr6r6r7rszIndexOpsMixin._duplicated)NT)NT)NT)NT)N)FTFNT)T)F)Frr)rN)r)r)6rNrOrPrQZ__array_priority__ frozensetrrRrSrrrTrrrmrrrrrrrrrrrrrrZto_listrrrrrrr$r.rrrrrrr rtextwrapdedentr*rrrrr6r6r6r7r+s   B{, C, Y_'   " d )NrQ __future__rrtypingrrrrrrZnumpyriZpandas._libs.libZ_libsrZpandas._typingr r r r r rrZ pandas.compatrZpandas.compat.numpyrrZ pandas.errorsrZpandas.util._decoratorsrrZpandas.core.dtypes.commonrrrrrZpandas.core.dtypes.genericrrrZpandas.core.dtypes.missingrrZ pandas.corer Zpandas.core.accessorr!Zpandas.core.algorithmsr"r#r$Zpandas.core.arrayliker%Zpandas.core.arraysr&Zpandas.core.constructionr'Zpandas.core.nanopscorerr(rr)r*rRZ_indexops_doc_kwargsr/r1rU Exceptionr]r_r`r+r6r6r6r7sH  $            /"W