U f/eY @sdZddlmZddlmZddlmZmZmZm Z m Z m Z ddl Z ddlmZddlmZmZddlmZdd lmZmZdd lmZdd lmZmZddlmmZ dd l!m"Z"m#Z#m$Z$m%Z%m&Z&m'Z'ddl(mm)m*Z+dd l,m-Z-erddl.m/Z/m0Z0ddl1m2Z2e d*ddddddddddZ3e d+ddddddddddZ3eddgdd,dddddddd dZ3Gd!d"d"Z4d#d$d%d&Z5d-d'd$d(d)Z6dS).z Concat routines. ) annotations)abc) TYPE_CHECKINGHashableIterableMappingcastoverloadN)FrameOrSeriesUnion)cache_readonlydeprecate_nonkeyword_arguments) concat_compat) ABCDataFrame ABCSeries)isna)factorize_from_iterablefactorize_from_iterables)Index MultiIndexall_indexes_same ensure_indexget_objs_combined_axisget_unanimous_names)concatenate_managers) DataFrameSeries)NDFrameouterFTz2Iterable[DataFrame] | Mapping[Hashable, DataFrame]strboolr)objsjoin ignore_indexverify_integritysortcopyreturnc CsdSN r axisr!r"keyslevelsnamesr#r$r%r(r(>/tmp/pip-unpacked-wheel-tiezk1ph/pandas/core/reshape/concat.pyconcat:s r/.Iterable[NDFrame] | Mapping[Hashable, NDFrame]r c CsdSr'r(r)r(r(r.r/Js r )versionZ allowed_args)r r"r#r$r%r&c Cs$t||||||||| |d } | S)a Concatenate pandas objects along a particular axis with optional set logic along the other axes. Can also add a layer of hierarchical indexing on the concatenation axis, which may be useful if the labels are the same (or overlapping) on the passed axis number. Parameters ---------- objs : a sequence or mapping of Series or DataFrame objects If a mapping is passed, the sorted keys will be used as the `keys` argument, unless it is passed, in which case the values will be selected (see below). Any None objects will be dropped silently unless they are all None in which case a ValueError will be raised. axis : {0/'index', 1/'columns'}, default 0 The axis to concatenate along. join : {'inner', 'outer'}, default 'outer' How to handle indexes on other axis (or axes). ignore_index : bool, default False If True, do not use the index values along the concatenation axis. The resulting axis will be labeled 0, ..., n - 1. This is useful if you are concatenating objects where the concatenation axis does not have meaningful indexing information. Note the index values on the other axes are still respected in the join. keys : sequence, default None If multiple levels passed, should contain tuples. Construct hierarchical index using the passed keys as the outermost level. levels : list of sequences, default None Specific levels (unique values) to use for constructing a MultiIndex. Otherwise they will be inferred from the keys. names : list, default None Names for the levels in the resulting hierarchical index. verify_integrity : bool, default False Check whether the new concatenated axis contains duplicates. This can be very expensive relative to the actual data concatenation. sort : bool, default False Sort non-concatenation axis if it is not already aligned when `join` is 'outer'. This has no effect when ``join='inner'``, which already preserves the order of the non-concatenation axis. .. versionchanged:: 1.0.0 Changed to not sort by default. copy : bool, default True If False, do not copy data unnecessarily. Returns ------- object, type of objs When concatenating all ``Series`` along the index (axis=0), a ``Series`` is returned. When ``objs`` contains at least one ``DataFrame``, a ``DataFrame`` is returned. When concatenating along the columns (axis=1), a ``DataFrame`` is returned. See Also -------- Series.append : Concatenate Series. DataFrame.append : Concatenate DataFrames. DataFrame.join : Join DataFrames using indexes. DataFrame.merge : Merge DataFrames by indexes or columns. Notes ----- The keys, levels, and names arguments are all optional. A walkthrough of how this method fits in with other tools for combining pandas objects can be found `here `__. Examples -------- Combine two ``Series``. >>> s1 = pd.Series(['a', 'b']) >>> s2 = pd.Series(['c', 'd']) >>> pd.concat([s1, s2]) 0 a 1 b 0 c 1 d dtype: object Clear the existing index and reset it in the result by setting the ``ignore_index`` option to ``True``. >>> pd.concat([s1, s2], ignore_index=True) 0 a 1 b 2 c 3 d dtype: object Add a hierarchical index at the outermost level of the data with the ``keys`` option. >>> pd.concat([s1, s2], keys=['s1', 's2']) s1 0 a 1 b s2 0 c 1 d dtype: object Label the index keys you create with the ``names`` option. >>> pd.concat([s1, s2], keys=['s1', 's2'], ... names=['Series name', 'Row ID']) Series name Row ID s1 0 a 1 b s2 0 c 1 d dtype: object Combine two ``DataFrame`` objects with identical columns. >>> df1 = pd.DataFrame([['a', 1], ['b', 2]], ... columns=['letter', 'number']) >>> df1 letter number 0 a 1 1 b 2 >>> df2 = pd.DataFrame([['c', 3], ['d', 4]], ... columns=['letter', 'number']) >>> df2 letter number 0 c 3 1 d 4 >>> pd.concat([df1, df2]) letter number 0 a 1 1 b 2 0 c 3 1 d 4 Combine ``DataFrame`` objects with overlapping columns and return everything. Columns outside the intersection will be filled with ``NaN`` values. >>> df3 = pd.DataFrame([['c', 3, 'cat'], ['d', 4, 'dog']], ... columns=['letter', 'number', 'animal']) >>> df3 letter number animal 0 c 3 cat 1 d 4 dog >>> pd.concat([df1, df3], sort=False) letter number animal 0 a 1 NaN 1 b 2 NaN 0 c 3 cat 1 d 4 dog Combine ``DataFrame`` objects with overlapping columns and return only those that are shared by passing ``inner`` to the ``join`` keyword argument. >>> pd.concat([df1, df3], join="inner") letter number 0 a 1 1 b 2 0 c 3 1 d 4 Combine ``DataFrame`` objects horizontally along the x axis by passing in ``axis=1``. >>> df4 = pd.DataFrame([['bird', 'polly'], ['monkey', 'george']], ... columns=['animal', 'name']) >>> pd.concat([df1, df4], axis=1) letter number animal name 0 a 1 bird polly 1 b 2 monkey george Prevent the result from including duplicate index values with the ``verify_integrity`` option. >>> df5 = pd.DataFrame([1], index=['a']) >>> df5 0 a 1 >>> df6 = pd.DataFrame([2], index=['a']) >>> df6 0 a 2 >>> pd.concat([df5, df6], verify_integrity=True) Traceback (most recent call last): ... ValueError: Indexes have overlapping values: ['a'] ) r*r"r!r+r,r-r#r%r$) _Concatenator get_result) r r*r!r"r+r,r-r#r$r%opr(r(r.r/ZsM c @s|eZdZdZdddd d d d d d Zd dZddddZddddZdddddZe ddddZ ddddZ dS) r2zB Orchestrates a concatenation operation for BlockManagers rrNFTr0rr)r r!r"r#r%c sttttfr&tdtjd|dkr6d|_n|dkrFd|_ntdtt j r|dkrnt }fdd |Dnt t d krtd |dkrt tjnxg} g} t|D]&\} }|dkrq| | | |q| t|trt|j| |jd }nt|d d}t| |d}t d krDtdt}D]:}t|ttfszdt|d}t|||jqNd}t |dkrt|}D]*}|j|krt|jr|}q qnJdd D}t |r |dkr |dkr |dkr |js |d }|dkr2d }|_t|trR|j |}n | |}t|t|_!|j!rz|"|}t|t|_#d |kr|jksnt$d|jd|t |dkrvd }|j}g|j|_D]}|j}||krnn||dkrtdnVt|d d}|s,|dkr8|}|d7}|j!rN|dkrNd }t%d|}|&||i}|j|q||_'|j!rd|j'nd |_(||_ |pt|dd|_||_)| |_*||_+||_,| |_-|.|_/dS)NzTfirst argument must be an iterable of pandas objects, you passed an object of type ""rFinnerTz?Only can inner (intersect) or outer (union) join the other axiscsg|] }|qSr(r().0kr r(r. Zsz*_Concatenator.__init__..rzNo objects to concatenate)r-name)r;zAll objects passed were Nonez#cannot concatenate object of type 'z+'; only Series and DataFrame objs are validcSs(g|] }t|jdks t|tr|qS)r)sumshape isinstancer)r7objr(r(r.r:s zaxis must be between 0 and z , input was z>cannot concatenate unaligned mixed dimensional NDFrame objectsr r-)0r?rrr TypeErrortype__name__ intersect ValueErrorrrlistr+lencomZnot_nonezipappendr from_tuplesr-getattrrsetaddndimmaxnpr=r>r _constructor_expanddimZ_get_axis_numberZ _is_frame_get_block_manager_axis _is_seriesAssertionErrorr _constructorbm_axisr*r,r$r"r#r% _get_new_axesnew_axes)selfr r*r!r+r,r-r"r#r%r$Z clean_keysZ clean_objsr8vr;Zndimsr@msgsampleZmax_ndimZ non_emptiesZcurrent_columnrOr(r9r.__init__;s                    z_Concatenator.__init__cCs~|jrtd|jd}|jdkrtt|j}|j}dd|jD}t|dd}|||jd||j d}|j |ddSt t t t|j|j}|j}|j\}} |||d } | | _| j |ddSntd |jd}g} |jD]`} i} t|jD]<\}}||jkrq| jd |}||s||| |<q| | j| fqt| |j|j|jd }|jsb||j}||j |ddSdS) NrrcSsg|] }|jqSr()Z_values)r7Zserr(r(r.r:sz,_Concatenator.get_result..)r*)indexr;dtyper/)methodr_rr<) concat_axisr%)rTrr rWrHZconsensus_name_attrrVr rYr`Z __finalize__dictrIrangerGrRcolumns enumerateaxesequals get_indexerrJZ_mgrrr%Z_consolidate_inplace)rZr]r;ZconsZarrsresresultdatar_rfZdfZ mgrs_indexersr@ZindexersZaxZ new_labelsZ obj_labelsZnew_datar(r(r.r3sH        z_Concatenator.get_resultintr&cCs$|jr|jdkrdS|jdjSdS)Nr<r)rTrWr rOrZr(r(r._get_result_dimsz_Concatenator._get_result_dimz list[Index]cs}fddt|DS)Ncs&g|]}|jkrjn|qSr()rW_get_concat_axis_get_comb_axisr7irqr(r.r:%sz/_Concatenator._get_new_axes..)rrre)rZrOr(rqr.rX#s z_Concatenator._get_new_axesr)rvr&cCs*|jd|}t|j||j|j|jdS)Nr)r*rDr$r%)r rSrrDr$r%)rZrvZ data_axisr(r(r.rt*sz_Concatenator._get_comb_axisc s^jrjdkr"ddjD}nʈjr.NFz6Cannot concatenate type 'Series' with object of type ''Tr<csg|]}|jjqSr()rhr*rwrqr(r.r:Vscss|]}t|VqdSr')rGrur(r(r. Ysz1_Concatenator._get_concat_axis..)rTrWr r"ibaseZ default_indexrGr+rgr?rrArBrCr;rrZ set_namesr-r=_concat_indexes_make_concat_multiindexr,_maybe_check_integrity) rZindexesidxr-numZ has_namesrvrxrcr(rqr.rs4sL         z_Concatenator._get_concat_axis) concat_indexcCs.|jr*|js*||}td|dS)Nz!Indexes have overlapping values: )r#Z is_uniqueZ duplicateduniquerE)rZroverlapr(r(r.r~gsz$_Concatenator._maybe_check_integrity) rrNNNFFTF) rC __module__ __qualname____doc__r^r3rrrXrtr rsr~r(r(r(r.r26s&'< 2r2rrocCs|d|ddS)Nrr<)rJ)rr(r(r.r|nsr|rc s |dkrt|dts*|dk rrt|dkrrtt|}|dkrLdgt|}|dkrbt|\}}qdd|D}n6|g}|dkrdg}|dkrt|g}ndd|D}t|sg}t||D]\}}g} t||D]f\} } t|t| @|| kB} | st d| d|t | dd} | t | t| q| t | qt|}t|tr~||j||jn t|\}}| || |t|t|krt|}n4tdd |Ddkstd t|tt|}t|||d d S|d}t|}t|t|}t|}g}t||D]R\}}t|}||}|d k} | rrt d|| | t ||q4t|tr||j|fdd|jDn"| || t t |t|t|kr||jt|||d d S)Nrr<cSsg|] }t|qSr(rrwr(r(r.r:~sz+_make_concat_multiindex..cSsg|] }t|qSr(rrwr(r(r.r:szKey z not in level cSsh|] }|jqSr()Znlevels)r7rr(r(r. sz*_make_concat_multiindex..z@Cannot concat indices that do not have the same number of levelsF)r,codesr-r#z"Values not found in passed level: csg|]}t|qSr()rQtile)r7ZlabZkpiecesr(r.r:s)r?tuplerGrFrIrrrranyrErQZnonzerorJrepeatZ concatenater|rextendr,rrrUrrjrZaranger-)rr+r,r-Zzipped_Z codes_listZhlevellevelZ to_concatkeyr_maskrvrr categoriesZ new_indexnZ new_namesZ new_levelsZ new_codesZmappedr(rr.r}rs                 r}) rrFNNNFFT) rrFNNNFFT) rrFNNNFFT)NN)7r __future__r collectionsrtypingrrrrrr ZnumpyrQZpandas._typingr Zpandas.util._decoratorsr r Zpandas.core.dtypes.concatr Zpandas.core.dtypes.genericrrZpandas.core.dtypes.missingrZpandas.core.arrays.categoricalrrZpandas.core.commoncorecommonrHZpandas.core.indexes.apirrrrrrZpandas.core.indexes.baserbaser{Zpandas.core.internalsrZpandasrrZpandas.core.genericrr/r2r|r}r(r(r(r.sp          \: