o
    vh#                    @   s  d dl m Z  d dlZd dlZd dlZd dlmZmZmZm	Z	m
Z
mZmZ d dlmZ d dlmZ d dlmZ ejfddZi dejd	ejd
d dejdejdejdejdejdejdejdejdejdejdd dejdejdejd ejejd ejdZejddd Zdd Zdd  Zd!d" Zejd#d$d%gd&d' Zejdd(d) Zd*d+ Z d,d- Z!d.d/ Z"ejd0d1g d2eg d3d1d4fd1d5gg d6eg d3d1d4e	g d7gfd1d8gg d9eg d3d1d4eg d3d1d4gfgejd:d$d%gd;d< Z#d=d> Z$d?d@ Z%dAdB Z&ejd#d$d%gejdCd$d%gejdDd$d%gdEdF Z'dGdH Z(dIdJ Z)dKdL Z*dMdN Z+dOdP Z,ejdQdRgee-dSd dTgdUdVgdWfee-dS.dXdY dVgd dUgdWfee-dZd dTgdUdVgdWfgd[d\ Z/d]d^ Z0d_d` Z1dadb Z2ejdcddddgfddedfgfddedgfddddfgfgdgdh Z3didj Z4dkdl Z5dmdn Z6ejd#d$d%gdodp Z7ejd#d$d%gdqdr Z8dsdt Z9dudv Z:dwdx Z;ejdyd$ee
j<eg dzd{d|g d}gd1d5gd~g d3ddfd%eeg dzd{d|g d}g d3dfgdd Z=ejddejej>gdd Z?ej@dd ZAejdddgdd ZBejdddgejdCd%dgdd ZCejdd$e
<e	dgdS dgdS  d{dde	g dd{dde	ddgdS gg dfd%e
jDeddgd%deg dd%de	ddggg dd~dVdVdSdSejejdUdUejejdTdTgfde
jDeddgd%deg dd%de	ddggg dd~dVdVdSdSejejdUdUejejdTdTgfgdd ZEdd ZFejdg dg dgdd ZGdd ZHdd ZIdd ZJdd ZKdd ZLejdCd%dgdd ZMejddd ZNejdejOg dzfejPg d}fgdd ZQdd ZRejdddgdd ZSdd ZTdd ZUdd ZVdd ZWddÄ ZXejdddgdeYdCeZfddńZ[ejdddgdeYdCeZfddǄZ\ddɄ Z]ejdddgdd˄ Z^dd̈́ Z_ddτ Z`ddф Zaejdg dӢejd#d$d%gddՄ Zbejdddgejd#d$d%gddل Zcejdg dӢejdddgejd#d$d%gddބ Zdejdg dӢejdg dߢejd#d$d%gdd Zeejdg dӢdd Zfejdd1d5d1d5ggejdd1d5d1d5ggdd Zgejd:d$d%gejddgdd8ggdd ZhdS )    )datetimeN)CategoricalCategoricalIndex	DataFrameIndex
MultiIndexSeriesqcut)SeriesGroupBy)get_groupby_method_argsc                 C   s.   dd }t jt|||d}| j||d S )zpReindex to a cartesian production for the groupers,
    preserving the nature (Categorical) of each grouper
    c                 S   s4   t | ttfr| j}tjtt||| jd} | S )N
categoriesordered)	
isinstancer   r   r   
from_codesnparangelenr   )ar    r   c/var/www/html/hyperkenya/venv/lib/python3.10/site-packages/pandas/tests/groupby/test_categorical.pyf   s   z)cartesian_product_for_groupers.<locals>.fnames
fill_value)r   from_productmapreindex
sort_index)resultargsr   r   r   indexr   r   r   cartesian_product_for_groupers   s   r#   allanycountcorrwithfirstidxmaxidxminlastmaxmeanmedianminnthnuniqueprodquantilesem)sizeskewstdsumvarz7ignore:invalid value encountered in cast:RuntimeWarningc                 C   sB   t | jd}dd }| j|ddj|}|jjd dksJ d S )N   c                 S   s   |   |  |  |  dS )Nr/   r,   r&   r-   r;   )groupr   r   r   	get_statsJ   s
   z2test_apply_use_categorical_name.<locals>.get_statsFobservedr   C)r	   r@   groupbyDapplyr"   r   )dfcatsr=   r    r   r   r   test_apply_use_categorical_nameF   s   rF   c                  C   sV  t g dg ddd}tg d|d}ttdddd	}td
dddtjgi|d}|jddd }t	|| t g dg ddd}t g dg ddd}t||g dd}|jddd}	tg dddd	}
tdt
g d|
di}|	jdd}t	|| tddgddgddggddgd}t |j|d< |jdgdd}|d d! }t	||dg  |d}|jd"dg }t	|| d#d$ }d%}tjt|d& ||}W d    n1 sw   Y  |jd"dg  }tddgdd'|_| rd(nt}|d ||d< t	|| td
g d)i}tj|jg d*d+}d,}tjt|d& |jj|ddt}W d    n	1 s>w   Y  t||d
  t|jj|ddd-d! |d
  d.}tjt|d& |j|ddt}W d    n	1 s}w   Y  |d
g }t	|| |j|dd}|d/d! }t	||d
g  |d0d! }d1}tjt|d& |t}W d    n	1 sw   Y  |tjj}|d2d! }tj	||d
g dd3 tj	||d
g dd3 t	||d
g  t	||d
g  t|jj|ddtj |d
  t	|j|ddtj | td
g d4i}tj|jg d5d+}d,}tjt|d& |jj|ddt}W d    n	1 sSw   Y  t||d
  t|jj|ddd6d! |d
  d.}tjt|d& |j|ddt}W d    n	1 sw   Y  |d
g }t	|| t	|j|ddd7d! |d
g  td
g d8i}tj|jg d9t tdd:}|j|ddt!}t|j"j#|j"j$d;}t
g d8|d}d
|j_%t|| g d<}tj&'dj(d"dd=d>}t j)||dd;}ttj&'d*d?}|j|dd }|jt+|dd }t||j#dd}
|,|
}t	|| |j|dd}|- }|j./ }t+|0|}|0|}t |dg d<d@}|j|dddA- }t	|| t j)t1d2dB|dd;}t|}t3|j4ddCj5d"| tg dDd }t3|j4ddCj5d| d S )EN	r   r   r   brH   rH   crI   rI   r   rH   rI   dTr   	   rM   rM      rN   rN      r:      r   rH   abcdrH   namer   r   rM   rN   r:   r"   Fr>   r   r   rH   rH   r   rH   zrI   rK   rI   rK   rI   rK   yrM   rN   rO   r:   ABvaluesr^   r`   )rO      r   numeric_onlyzJohn P. Doez	Jane Dove	person_idperson_namecolumnsc                 S   s   | S Nr   xr   r   r   <lambda>v       ztest_basic.<locals>.<lambda>r   c                 S   s   |  djd S )Nre   r   )drop_duplicatesilocri   r   r   r   r   }   s   ztest_basic.<locals>.f7DataFrameGroupBy.apply operated on the grouping columnsmatchrT   str)rP         )r   
         (   )binsusing SeriesGroupBy.sumc                 S   
   t | S rh   r   r8   xsr   r   r   rk         
 zusing DataFrameGroupBy.sumc                 S      t j| ddS Nr   axisr   r,   r~   r   r   r   rk          c                 S   r   r   r   r~   r   r   r   rk      r   zusing DataFrameGroupBy.maxc                 S   s   t j| S rh   )r   maximumreducer~   r   r   r   rk          )check_dtype)rP   rt   ru   )ir   rv   rw   rx   ry   c                 S   r|   rh   r}   r~   r   r   r   rk      r   c                 S   r|   rh   r}   r~   r   r   r   rk      r   )rM   r   r   r   r   rM   rN   rO   r:   )labelsr   foobarbazquxd   r5   r   r:   )r   r   sortr?      future_stackr&   r-   r7   r/   z25%z50%z75%r,   )6r   r   r   listr   nanrA   r-   tmassert_frame_equalr   r8   re   	transformrm   rn   assert_produces_warningFutureWarningrC   copyr   r"   objectastypepdcutr   assert_series_equalr,   r   r   filterr$   r   r`   r   r   rT   randomdefault_rngintegersr   standard_normalasarrayr   describecodesargsorttaker   repeatassert_index_equalstackget_level_values) using_infer_stringrE   data	exp_indexexpectedr    cat1cat2rD   gbexp_idxrj   gr   msgdtyperI   gbcresult2result3result4result5levelsr   groupeddesc_resultidx
ord_labelsord_dataexp_catsexpcexpr   r   r   
test_basicV   s   

$




r   c                 C   s   t tdddttddgtdgdgd dgd  tdgd	d
gdd}|jd	g| d}t tdddttddgtdgdgd tdgd	d
gdd}d}tjt	|d |
d}W d    n1 shw   Y  t|| d S )NrN      r   rH   rv   r   rP   rM   Index1Index2)r   r   r   r   r"   levelr?      z&you will need to pass a length-1 tuplerp   )r   r   r   r   r   rangerA   r   r   r   	get_groupr   )r?   rD   r   r   r   r    r   r   r   test_level_get_group   s,   r   c                  C   s   t dgd dgd  g dd tdd} t| jg dd	d
| _| dd  }|jdd	d}g d}t|g dd	d
}g dt|g}t	j
|ddgd}tdgd |dd}t|| d S )Nr^      r_   )highmedlowr:   g      (@)r<   doseoutcomes)r   r   r   Tr   r<   r   r   )r   sort_remaining)r   r   r   r   r   r   )r^   r^   r^   r_   r_   r_   r   rN   r&   r"   rT   )r   r   r   r   r   rA   value_countsr   r   r   from_arraysr   r   r   rD   r    r"   r   r   r   r   (test_sorting_with_different_categoricals  s   
r   r   TFc           
      C   sj  t td| d}t tdddg| d}tt|}t|||d}|jdd	gd
d}tj||gdd	gd}tg d|dgd}|	dd }t
|| | }t
|| d}	t
jt|	d |tj}W d    n1 sqw   Y  t
|| tj||gdd	gd}td|d}d}	t
jt|	d |	dd }W d    n1 sw   Y  t
|| d S )Nabcr   aaar   rH   r   )missingdenser`   r   r   Tr>   r   )r   rM          @r`   )r"   rg   c                 S   r   r   )r   r-   ri   r   r   r   rk   A  r   ztest_apply.<locals>.<lambda>zusing DataFrameGroupBy.meanrp   rM   rU   ro   c                 S   s   dS NrM   r   ri   r   r   r   rk   R  rl   )r   r   r   r   r   r   rA   r   r   rC   r   r   r-   r   r   aggr   r   )
r   r   r   r`   rD   r   r   r   r    r   r   r   r   
test_apply1  s.   r   c                 C   s\  |r|s|  tjjdd tg dg ddd}tg dg ddd}t||g d	d
}ddgd |d< |jg d|d}tj||ddgd gg dd}tdt	g d	|di
 }| }	|srt|||ddggtddd}t|	| |jddg|d}tj||gddgd}tg d	g dd|d}| }	|st|||gtddd}t|	| tg dg dddg dg dd }
t|
}|jd!|d}| }	ttd"d!td#dd$}td%d%gd&d'gd(|d}|sttd#d!td#dd$}||}t|	| |jd!d)g|d}|d*}	tg d+tg dg dddg d,d-d!d)g}|s>t||jjd.dggd!d)g}t|	| d/D ]}|\}}||}	||j|k|j|k@  }t|	| qFg d0g d1g d2d3}
t|
}t|d tdd4d5}||d6< |jd6d7gd8|d9}|d*}	|jd6d7gd|d9}|d* }t|	| d S ):NzTODO(infer_string)reasonrV   rW   Tr   rY   rZ   r\   r]   r   r   rN   r@   )r^   r_   r@   r>   r   r`   rU   ABCr   r   r^   r_   )r   r   r   r   )r`   r@   AB)r   rH   r   rH   r   rH   rI   rM   rM   rN   rN   rv   rw   rx   ry   )catintsvalr   abr   )rT   r   r   g      ?      4@rx   )r   r   r   r-   )      $@g      >@r   g      D@rM   rN   rM   rN   )r   r   r   rM   ))r   rM   )rH   rN   )rH   rM   )r   rN   )rv   r   r:   r   r:   rM   rM   rv   rw   rx   ry   2   <   F   )rK   rI   er   r   rK   rI   r   r   r   rv   rO   r   r   Fas_indexr?   )applymarkerpytestmarkxfailr   r   rA   r   r   r   r   r8   r#   r   r   r   r-   r   r   r   	set_indexr   r`   r   r   r   r   r   linspacereset_index)requestr   r?   r   r   rD   r   r   r   r    rK   groups_single_keyr"   groups_double_keykeyrI   ir   groupsgroups2r   r   r   test_observedV  s   	


	

r  c                 C   s   g dg dg dd}t |}t|d g d}d|_|j|dg| d	}tj|g dgddgd
}t g dg dd|d}| sOt||jg dgddg}|	d}t
|| d S )N)rO   rO   r:   rP   r\   )rv   r      "   )C1C2C3r  )rM   rN   rO   r   r   r  r>   r   )      @r  g      @g      @)r   g      Y@g      i@g      A@)r  r  rU   r-   )r   r   r   rT   rA   r   r   r#   r`   r   r   r   )r?   rK   rD   r`   r  r   r   r    r   r   r   test_observed_codes_remap  s   
r  c                  C   s   t tjdjddddtjdjddddtjdjdddddd} | jtd| d	< | jg d
dd}|	 }|j
jd  | j ksNJ |j
jd  | j ks]J |j
jd  | j kslJ d S )NrN   r      i0u  r   '  )r   int_idother_idr   categoryr   )r   r  r  Tr>   rM   )r   r   r   r   r   r   r   rs   rA   r&   r"   r   r1   r  r  )rD   r   r    r   r   r   test_observed_perf  s   "r!  c                 C   s   t g dg dd}t|g dd}|jd| d}|j}| r0tdd	gd
dtdgd
dd}ntdd	gd
dtg d
dtdgd
dd}t|| d S )N)r   rI   r   r   r   rM   rN   rO   r   valsr   r>   r   rN   int64r   rM   )r   rI   )r   r   rA   r  r   r   assert_dict_equal)r?   r   rD   r   r    r   r   r   r   test_observed_groups  s   "
r)  z,keys, expected_values, expected_index_levelsr   )rt   	   r   r#  rr   rH   )	ra   r   r   r   r   r*  r   r   r   r:   rP   r   a2)	rt   r   r   r   r*  r   r   r   r   test_seriesc           
      C   s   t tg dg ddtg dg ddg dg ddddg}d	| vr,|jd	d
}|j| dd}|r9|d }| }t| dkrF|}ng ddg d g}t||| d}t d|i|d}	|re|	d }	t	||	 d S )NrM   rM   rN   r#  r"  r+  )ra   r   r*  )r   r,  rH   rI   r   r,  rH   rf   Fr>   rI   rM   	r   r   r   rM   rM   rM   rN   rN   rN   rO   r   rM   rN   )r   r   rU   )
r   r   r
  droprA   r8   r   r   r   assert_equal)
keysexpected_valuesexpected_index_levelsr-  rD   r   r    r"   r   r   r   r   r   test_unobserved_in_index  s6   
r6  c                 C   s   t tdtjdgg ddg dd}|jd| d}|j}| r*dtdd	gd
di}ntdd	gd
dtg d
dtg d
dd}t|| d S )Nr   )r   rH   rK   r"  r#  r$  r   r>   r   rN   r&  r'  )	r   r   r   r   rA   r  r   r   r(  )r?   rD   r   r    r   r   r   r   test_observed_groups_with_nan=  s   

r7  c                  C   sl   t dtjtjgg dd} tg d}t| |d}|jdddd	 d
}|d	 jd
g }t	|| d S )Nr   r   r"  r#  )r   serr   Fr>   r8  r   )
r   r   r   r   r   rA   r0   rn   r   r   )r   r8  rD   r    r   r   r   r   test_observed_nthR  s   r9  c                 C   s   t tjdtjdgg dd}tg d}t||d}|jd| d  }| r8tt dgg dddgd}ntt g dg dddtjtjgd}t	|| d S )	Nr   r   r"  r\   )s1s2r:  r>   rN   )
r   r   r   r   r   rA   r(   r  r   r   )r?   r:  r;  rD   r    r   r   r   r   #test_dataframe_categorical_with_nan]  s   r<  r?   r   c           	      C   s   t g dg d| d}tg d}t||d}|jd||dd d}t|jjd	d
}t|j}|s:d|| < t||ksRd|  d| d| d| }J |d S )N)rK   r   rH   r   rK   rH   )r   rH   r   rK   r   )labelr   r=  )r?   r   r   r(   r   r'  r   zDLabels and aggregation results not consistently sorted
for (ordered=z, observed=z, sort=z
)
Result:
)	r   r   r   rA   	aggregater"   arrayisnar$   )	r   r?   r   r=  r   rD   r    aggrr   r   r   r   0test_dataframe_categorical_ordered_observed_sortq  s2   	
rB  c                  C   s  t jddd} tjdjdddd}tj|| dd	}ttjd	d
}|j
|dd }|j
t|dd }|| }t|j|jdd|_t|| |j
|dd}| }|j }||}	||}
|
j
|	dd }t|| t|j|j t|jd|jd tjtdd| dd	}t|}t|jddjd| tg dd }t|jddjd| d S )Nz
2014-01-01r:   )periodsrN   r   r   r   Tr   r   Fr>   r   r   r   r   rM   )r   
date_ranger   r   r   r   r   r   r   r   rA   r-   r   r   r   r"   r   r   r   r   r   r   r   r   r   r   r   r   )r   r   rE   r   r    r   r   r   r   r   r   r   r   r   r   r   test_datetime  s>   




rE  c                  C   s  t jd} g d}| jdddd}tj||dd}tt t dd	d	dt
d
d}||d< |djddd }|t
d
 j|jdd }ttjg d|dddd|_t|| |jddd }|t
d
 j|jdd }ttjg d|dddd|_t|| d S )NrN   r   r   r:   rw   r   Tr   rR   rf   rE   Fr   r>   r   rM   rN   rO   rr   )r   r   r   r   r   r   r   r   r   reshaper   r
  rA   r8   r   r   r"   r   r   )sr   r   rE   rD   r    r   r   r   r   test_categorical_index  s$   &rJ  c                  C   sz   t g dg ddd} ttjdd| d}|g dd	  }t	|j
dd
j|  t|j
dd
jj| j d S )N)r   r   r   r   r   Tr   rN   )rw   r:   rf   r\   rP   r   )r   r   r   r   r   r   rA   r   r   r   r   rg   assert_categorical_equalr`   )rE   rD   r    r   r   r   !test_describe_categorical_columns  s   rL  c                  C   s   t tdddgd tdd d} | d d	| d< | jd
dgddd   }| }tddgddd}t	
|j| t	|jj|j |d |d  }tddgtddgd
dd}t	|| d S )Nrv   r^   r_   rP   XYXXYrN   )r   mediumartistrN  r   rO  Fr>   r   r   rT   r   r:   XYrr   rU   )r   r   r   r   rA   r&   unstackr   r   r   r   rg   rK  r`   r   r   r   )rD   gcatr    exp_columnsr   r   r   r   test_unstack_categorical  s   rV  c                  C   st   t tjtjddddddddg
} t|  jd}tjt	dd | 
|  W d    d S 1 s3w   Y  d S )NrM   rN   rO   r:   z$Grouper and axis must be same lengthrp   )r   r   r   r   r   dropnar`   r  raises
ValueErrorrA   r-   )seriesrz   r   r   r   test_bins_unequal_len  s
    "r[  rZ  r   r:   rO   rM   rN   r^   r_   c                 C   s   | d S r   r   )r   r   r   r   rk     s    rk   ra   c                 C   sH   | j ttddddd}|t}t|t| d}t|| d S )NABBAr   r'  Fr>   rU   )rA   r   r   r>  r   r3  r   r   )rZ  r   rA   r    r   r   r   r   test_categorical_series  s   
r^  c                     s  t tg dg dg dg dd  jddgdd	d
 } t tddg jjjdddgddgdg dd}t| |  fdd}d}tjt	|d  jd|gdd	d
 } W d    n1 sdw   Y  t tddg jjjdddgddgdg dd}t| | t
g ddd}d}tjt	|d  jd|gdd	d
 } W d    n1 sw   Y  t| | ddg}t tddg jjjdddgddgdg dd}dD ]}ttd|d _ j|dd	d
 } t| | qd S )NrM   rN   rN   r#  )rv      r`  )e   f   g   )r   r^   r_   r   r^   FTr  rM   rN   r"  rv   r`  ra     rf   c                    s    j | df S )Nr^   )loc)rrD   r   r   rk   0  r   ztest_as_index.<locals>.<lambda>z*A grouping .* was excluded from the resultrp   r   )r   rH   rH   rr   )NrQ  r_   r   )r   r   rA   r8   r   r   r   r   r   r   r   r   r   r"   )r    r   r   r   rI  group_columnsrT   r   rg  r   test_as_index  s^   	ri  c                  C   s  t d} tdtt d| ddi}t| | ddd}tt d| ddd}t|jdddd	 j| t|jdddd	 j| tdtt d| ddi}t| | ddd}tt dt dddd}t|jdddd	 j| t|jdddd	 j| d S )
Nr   r^   baTr   rP  bacFr   )	r   r   r   r   r   r   rA   r(   r"   )r   rD   r   nosort_indexr   r   r   test_preserve_categoriesW  s&   rm  c               	   C   s   t g dg dttdtdddttdtdddd} t d	d
tjgddtjgttdtdddttdtdddd}dD ]/}| j|dddjdd}| j|dddjdd }|j|j	d}t
|| t
|| qDd S )N)rM   rN   rM   rM   rN   )rv      r      r  abaabrk  Fr   T)r^   r_   r  r  r   g      ?g      9@r   )r  r  byr  r?   rb   rf   )r   r   r   r   r   rA   r-   r  r   rg   r   r   )rD   exp_fullcolresult1r   r   r   r   r   test_preserve_categorical_dtypeu  s6   	

rv  zfunc, valuessecondfourththirdc                 C   s   t g ddd}tg d|d}|d}t||  }tddgt||jd	dd}t|| |dd
 }t||  }|d
 }t	|| d S )N)r(   rw  ry  rx  Tr   )rF  rF  rz  )payloadrt  r{  rz  rF  r'  rt  )
r   r   rA   getattrr   r   r
  r   r   r   )funcr`   rI   rD   r   r    r   sgbr   r   r   test_preserve_on_ordered_ops  s   
r  c                  C   sV  t tjdd} tg d}tj|g ddd}| j|dd	 }| j|dd	 }t
|j|j|jd	|_t|| tg d
}tj|g ddd}| j|dd	 }| j|dd	 |j}t
|j|j|jd	|_t|| tg dg ddd	}tg d|d} | jddd	 }|d j}tdddtjg}t|| d S )NrN   r*  r/  r0  Tr   Fr>   r   )	r   r   r   rM   rM   rM   rO   rO   rO   rG  rG   rJ   rL   rQ   rH   r   rM   r:   )r   r   r   r   r   r?  r   r   rA   r-   r   r"   r   r   r   r   r   r   r`   r   assert_numpy_array_equal)r   r   rE   r    r   r   r   r   test_categorical_no_compress  s6   
r  c                  C   sb   t d gd tg dd} | d d }ttg ddgdtg d	dd
dd}t|| d S )NrO   )trainr  testr\  r^   r_   r  r  r"  r   r   rT   r   )r   r   rA   r(   r   r   r   rD   r    r   r   r   r    test_groupby_empty_with_category  s   r  c                  C   s   t dtjddddi} dd tdddD }t||}| jdgd	d
} tj	| j
tdddd|d| d< | jdgddd  }|t|jdd d }t|j|jjd|_t|| d S )NvaluerN   r   r  r   c                 S   s   g | ]}| d |d  qS )z - i  r   ).0r  r   r   r   
<listcomp>  s    ztest_sort.<locals>.<listcomp>i  T)rr  	ascendingi)  F)rightr   value_groupr>   c                 S   s   t |  d S )Nr   )floatsplitri   r   r   r   rk     s    ztest_sort.<locals>.<lambda>)r  rr   )r   r   r   r   r   r   r   sort_valuesr   r   r  rA   r&   sortedr"   r   rT   r   r   )rD   r   
cat_labelsresr   r   r   r   	test_sort  s   

r  c              	   C   s   t g dg dg dg dg dg dg dgg dd	}t|d
 |d|d
< |jd
| dd }| rFddgddgddgddgg}g d}nddgddgddgddgg}g d}t |ddgt|d
|dd}t|| d S )N)	(7.5, 10]rv   rv   )r  r   rw   )(2.5, 5]rP   rx   )(5, 7.5]r   ry   )r  r:   r   )(0, 2.5]rM   r   )r  ra   r  )r   r   r   rf   r   r   Fr   rM   r   rP   rx   r   ry   rv   )r  r  r  r  )r  r  r  r  r   r   rS   rg   r"   )r   r   rA   r(   r   r   r   )r   r   rD   r    data_valuesindex_valuesr   r   r   r   
test_sort2  s0   	
r  c                 C   sP  t tdddtdddtdddtdddtdddtdddtdddgg dg ddg dd	}t|d
 |d|d
< | rdddgddgddgddgg}tdddtdddtdddtdddg}n$ddgddgddgddgg}tdddtdddtdddtdddg}t |ddgt|d
|dd}|jd
| dd }t|| d S )Ni  ra   rM   rN   rP   )rv   r   rP   r   r:   rM   ra   r   )dtr   r   rf   r  r   r   rx   r   ry   rv   r   r   rS   r  Fr   )r   r   r   r   rA   r(   r   r   )r   r   rD   r  r  r   r    r   r   r   test_sort_datetimelike  sF   






	







r  c                  C   s  t tg dg ddg dd} tg ddd}| jddd	j }tg d
|dd}t|| | jddd	jjdd}tg d
|dd}t|| | jddd	jjdd}tddt	j
g|dd}t|| | jddd	jjdd}tdt	j
t	j
g|dd}t|| d S )Nr   r   rH   r   r"  rM   rN   rM   r\  r^   rr   Fr>   )rO   rM   r   r_   r   	min_countrM   rO   rN   )r   r   r   rA   r_   r8   r   r   r   r   r   rD   expected_idxr    r   r   r   r   test_empty_sumQ  s    r  c                  C   s   t tg dg ddg dd} tg ddd}| jddd	j }tg d
|dd}t|| | jddd	jjdd}tg d
|dd}t|| | jddd	jjdd}tddt	j
g|dd}t|| d S )Nr  r   r"  r  r\  r^   rr   Fr>   )rN   rM   rM   r_   r   r  rM   rN   )r   r   r   rA   r_   r2   r   r   r   r   r   r  r   r   r   test_empty_prodm  s   r  c                  C   s   t ttdtttjddddd tdd} | jdd	gd
d }t	j
tg dttjddddgdd	gd}t ddddddddtjdg	i|d}t|| d S )N	abcbabcbaz2018-06-01 001minrO   )freqrC  r*  )key1key2r`   r  r  Fr>   r   r   r`   r   r:   r   rP   r   rN   rU   )r   r   r   r   rD  r   r   rA   r-   r   r   r   r   r   )rD   r    r   r   r   r   r   ,test_groupby_multiindex_categorical_datetime  s"   
	
$r  zas_index, expectedr.  r   r'  r_  r   rj   )r"   r   rT   r   rH   rj   c                 C   sP   t tg dddg dg dd}|jddg| d	d
d  }t|| d S )Nr.  r   r'  r_  r#  r  r   rH   Tr  rj   )r   r   rA   r8   r   r2  )r  r   rD   r    r   r   r   ,test_groupby_agg_observed_true_single_column  s
   r  r   c                 C   sJ   t g dg ddd}t g dg ddd}|jd| d}t|| d S )NrJ   Fr   )Nr   rH   rI   rM   r   )r   shiftr   r2  )r   ctr   r  r   r   r   
test_shift  s   r  c                 C   sX   |   dd }|d d|d< |d d|d< tg d|d< |jdgd	d
}|S )a  
    DataFrame with multiple categorical columns and a column of integers.
    Shortened so as not to contain all possible combinations of categories.
    Useful for testing `observed` kwarg functionality on GroupBy objects.

    Parameters
    ----------
    df: DataFrame
        Non-categorical, longer DataFrame from another fixture, used to derive
        this one

    Returns
    -------
    df_cat: DataFrame
    Nr:   r^   r   r_   r\   r@   rB   rM   r   )r   r   r   r1  )rD   df_catr   r   r   r    s   r  	operationr   rC   c           	      C   s   t g d| d jdd}t g d| d jdd}t||g}tg d|dd }| jddgd	d
d }|dkr;dnd}tjt	|d t
||t}W d    n1 sVw   Y  t|| d S )N)r   r   r   r   r^   r  )onethreer  twor_   )rN   r:   rM   rO   r@   r   r"   rT   Tr>   rC   using np.sumr{   rp   )r   r   r   r   r   r   rA   r   r   r   r|  r8   r   )	r  r  lev_alev_br"   r   r   r   r    r   r   r    test_seriesgroupby_observed_true  s   r  c           	      C   s  t jtddgddtg dddgddgd \}}td	d
tjdtjdg|dd}|dkrNd}tjt	|d |j
ddd}W d    n1 sIw   Y  | jddg|dd }|dkr_dnd}tjt	|d t||t}W d    n1 szw   Y  t|| d S )Nr   r   Fr   r  r  r  r^   r_   r   rN   r:   rM   rO   r@   r  r   z.The 'downcast' keyword in fillna is deprecatedrp   r   infer)downcastr>   r{   r  )r   r   r   	sortlevelr   r   r   r   r   r   fillnarA   r|  r8   r   )	r  r?   r  r"   _r   r   r   r    r   r   r   )test_seriesgroupby_observed_false_or_none  s(   r  zobserved, index, datar   r   r^   r  )r  r  r  r  r  r  r  r  r_   )rN   rN   r:   r:   rM   rM   rO   rO   r   r  )r^   r_   Nc                 C   s>   t ||dd}| jddg|dd dd }t|| d S )Nr@   r  r^   r_   r>   c                 S   s   |   |  dS )Nr/   r,   r  ri   r   r   r   rk   B  s    z8test_seriesgroupby_observed_apply_dict.<locals>.<lambda>)r   rA   rC   r   r   )r  r?   r"   r   r   r    r   r   r   &test_seriesgroupby_observed_apply_dict  s
   .r  c                 C   sD   | j ddgddd  }| j ddgdd d }t|| d S )Nr^   r_   Fr>   r@   )rA   r-   r   r   )r  r   r    r   r   r   4test_groupby_categorical_series_dataframe_consistentG  s   r  code)rM   r   r   )r   r   r   c                 C   s   t g dg dg dd}tj| tdd}d}tjt|d |j|d	d
d}W d    n1 s3w   Y  | }d}tjt|d |j	j|dd
d}W d    n1 sYw   Y  | j	}t
|| d S )Nr\   )rF  rz  )rP   r   ra   r   r   r   r"  z+DataFrame.groupby with axis=1 is deprecatedrp   rM   F)r   r?   z5The 'axis' keyword in DataFrame.groupby is deprecatedr   )r   r   r   r   r   r   r   rA   r-   Tr   )r  rD   r   r   r   r    gb2r   r   r   r   test_groupby_categorical_axis_1N  s   
r  c                 C   s\   t tddg|dddgdddgd	}| }|jd| d
jt jdd }t|| d S )NBobGregr   rM   rN   )NameItemr  r  rf   r>   T)skipna)	r   r   r   rA   r   r8   r  r   r   )r?   r   rD   r   r    r   r   r   $test_groupby_cat_preserves_structure^  s   r  c                  C   s^   t g dtdd} tjtdd | ddd  W d    d S 1 s(w   Y  d S )	NrV   r:   r9   r   z'vau'rp   r9   c                 S   s&   t | jd d g| jd d gdS )NrF  r9   vaur  )r   rn   )rowsr   r   r   rk   t  s     z/test_get_nonexistent_category.<locals>.<lambda>)r   r   r  rX  KeyErrorrA   rC   rg  r   r   r   test_get_nonexistent_categoryo  s   
"r  c                 C   s   | dkr	t d tttdtddttdd tdddgd	 d
}t| |}|r/d	nd}|jddg|dd }| dkrIt|| rGJ d S t|| }|sr| dv rrt j	t
dd ||  W d    d S 1 skw   Y  d S || }t||ks~J d S )Nngroupngroup is not truly a reductionAABBABCDr"  r   rN   皙?r:   cat_1cat_2r  rn  r  r  r>   r  r'   r*   r)   (empty group due to unobserved categoriesrp   )r  skipr   r   r   r   rA   hasattrr|  rX  rY  r   )reduction_funcr?   rD   r!   expected_lengthseries_groupbyr   r    r   r   r   0test_series_groupby_on_2_categoricals_unobservedz  s4   




r  c                 C   sp  | dkr	t d | dkrt jjdd}|| tttdtddttd	d
 tdddgd d}tdtdtdtdtdg}t	| |}|j
ddgddd }t|| }| dv r~t jtdd ||  W d    d S 1 sww   Y  d S || }t|  }	|D ]}
|j|
 }t|	rt|s||	ksJ q|	dkr| dkrt|jtjsJ d S d S d S )Nr  r  r'   z6TODO: implemented SeriesGroupBy.corrwith. See GH 32293r   r  r   r"  r   rN   r  r:   r  ACBCCACBCCr  r  Fr>   r  r  r  rp   r   r8   )r  r  r  r	  r  r   r   r   tupler   rA   r|  rX  rY  -_results_for_groupbys_with_missing_categoriesre  r   r@  r   
issubdtyper   integer)r  r  r  rD   
unobservedr!   r  r   r    zero_or_nanr   r   r   r   r   ?test_series_groupby_on_2_categoricals_unobserved_zeroes_or_nans  sH   

"




 r  c                 C   s   | dkr	t d tttdtddttdtddg dd	}g d
}|jddgdd}t| |}t|| | }|D ]	}||jvsGJ q>d S )Nr  2ngroup does not return the Categories on the indexr  r   r"  111112r  r  r  r  r  )r^   2)r_   r  )r@   1)r@   r  r  r  Tr>   )	r  r  r   r   r   rA   r   r|  r"   )r  rD   unobserved_catsdf_grpr!   r  r   r   r   r   >test_dataframe_groupby_on_2_categoricals_when_observed_is_true  s   

r  c                 C   s  | dkr	t d tttdtddttdtddg dd	}g d
}|jddg|d}t| |}|s\| dv r\t jtdd t	|| |  W d    d S 1 sUw   Y  d S t	|| | }t
|  }|tju r{|j|    syJ d S |j| |k  sJ d S )Nr  r  r  r   r"  r  r  r  r  r  r  r  r>   r  r  rp   )r  r  r   r   r   rA   r   rX  rY  r|  r  r   r   re  isnullr$   )r  r?   rD   r  r  r!   r  r   r   r   r   ?test_dataframe_groupby_on_2_categoricals_when_observed_is_false  s2   	



r  c                  C   s   g dg dg dd} t | }t|d tddd}||d	< |jd	d
gdddd}|d d}|dd }t|| d S )N)rv   r   r:   rM   r   )rK   rI   rK   rI   r  r   r   rw   rP   r   r   TFr  r   r?   r-   )	r   r   r   r   r  rA   r   r   r   )rK   rD   r   r  r    r   r   r   r   3test_series_groupby_categorical_aggregation_getitem  s   r  zfunc, expected_valuesc                 C   sb   t g dg dtg ddd}|d| }t d|itg ddd	d
}t|| d S )Nr   )r   rM   rM   rN   rN   )r   r   r   r   rM   )idr  r  r   r  r  r0  rr   rU   )r   r   r
  rA   r   r   r   r   )r}  r4  rD   r    r   r   r   r   $test_groupby_agg_categorical_columns&  s   
r  c                  C   s~   t dtg dg ddi} t dddgitddgd}| g dtj}t	|| | g d }t	|| d S )	Nr^   r  r   r"  rN   rM   rU   r  )
r   r   r   r?  rA   r   r   r1   r   r   rD   r   r    r   r   r   test_groupby_agg_non_numeric;  s   r  r}  c                 C   sl   t dgtdgddj d}|dd }t||  }tdgtdgddd|d jd	}t	|| d S )
Ni  rH   r   r'  r\  r^   r_   rr   r"   rT   r   )
r   r   r   
as_orderedrA   r|  r   r   r   r   )r}  rD   
df_groupedr    r   r   r   r   <test_groupby_first_returned_categorical_instead_of_dataframeF  s    r  c                  C   sx   t ddg} d| j_tg dtg dt| dd}tdd	d
git| ddd}|jdddd	 }t
|| d S )NrM   rN   F)rM   rO   rP   ra   r   r"  rQ   r   r   g      @rH   rr   r   r   )r   r?  flags	writeabler   r   r   r   rA   r-   r   r   )rE   rD   r   r    r   r   r   test_read_only_category_no_sortU  s   r
  c                  C   s   t g dg dd} | d djjg ddd| d< t d	d	d
d	dd
ddd
ddd
d}|jddd}tg dg ddddd|_| jddgdd 	 }t
|| d S )N)smalllarger  r  rN  r  r  rN  )r@   r^   r^   r@   r^   r@   r^   r@   )r   r   r   r   )tinyr  rN  r  Tr   r   )r^   r@   rM   rO   rN   r   r"   r   )r   r   rT   r   Fr>   )r   r   r   set_categoriesrename_axisr   rg   rA   r5   rS  r   r   r  r   r   r   #test_sorted_missing_category_valuesa  s6   
r  c                  C   s   t dg di} | d d| d< | dj }tg dtg dddd| d jd}t	|| | d
ddi}| }t|| d S )	Ncol_numrM   rM   rN   rO   r   col_catr#  rr   r  r(   )r   r   rA   r  r(   r   r   r   r   r   r   to_framer   r  r   r   r   1test_agg_cython_category_not_implemented_fallback  s   r  c                  C   s   t g dg dddtjdgg dg dd} | dd	i} | d
dgdd }tjddgddggdd}t ddgddgddgd|d}t	|| d S )N)rM   rM   rM   rM   r   r  g?g333333?)r   r   r   fee)r^   r_   numerical_col
object_colcategorical_colr  r   r^   r_   c                 S   s   |    S rh   )r@  r8   rg  r   r   r   rk     r   z7test_aggregate_categorical_with_isnan.<locals>.<lambda>rM   rN   r\  r   r   )r  r  r  r   )
r   r   r   r   rA   r   r   r   r   r   r   r   r   r   %test_aggregate_categorical_with_isnan  s&   
r  c                  C   s   t g dg dd} tjg ddd}| d || d< d}tjt|d	 | d
d t	| d< W d    n1 s=w   Y  | 
 }t g dg dg dd}|d ||d< |d ||d< t|| d S )N)rM   rM   rM   rN   rN   rO   )WaitingOnTheWay	Deliveredr  r  r  )
package_idstatus)r  r  r  Tr   r  zusing SeriesGroupBy.maxrp   r  last_status)r  r  r  r  r  r  )r  r  r   )r   r   CategoricalDtyper   r   r   r   rA   r   r,   r   r   )rD   delivery_status_typer   r    r   r   r   r   test_categorical_transform  s.   r#  c                 C   s   t g d}g d}t|||d}t ddg}tj||gddgd}tdtjtjdg|d	d
tdtjtjdg|d	d
d}||  }|rL| tj	}|j
ddg|dd	 }	t|	|  }
t|
| d S N)r   r   rM   rM   )r   rM   rM   r   r   r   rM   r   rH   r   rI   rr   )r(   r+   r>   )r   r   r   r   r   r   r   rW  r   r&  rA   r|  r   r   )r}  r?   r   r   rD   r   r   expected_dictr   srs_grpr    r   r   r   Ftest_series_groupby_first_on_categorical_col_grouped_on_2_categoricals  s   r'  c                 C   s   t g d}g d}t|||d}t ddg}tj||gddgd}tdtjtjdg|d	d
tdtjtjdg|d	d
d}||   }|rN| 	tj
}|jddg|d}	t|	|  }
t|
| d S r$  )r   r   r   r   r   r   r   r  rW  r   r&  rA   r|  r   r   )r}  r?   r   r   rD   r   r   r%  r   r  r    r   r   r   Btest_df_groupby_first_on_categorical_col_grouped_on_2_categoricals  s   r(  c                  C   s   t tg dg ddtdd} | jdddd}|j}tjd	d
gddtjdgddtjg ddd}| | ks>J | D ]}t	|| ||  qBd S )N)rH   rH   r   r   r"  rO   )r  rt  r  Fr   r   rM   intpr'  rN   )rH   r   rI   )
r   r   r   rA   indicesr   r?  r3  r   r  )rD   r   r    r   r  r   r   r   2test_groupby_categorical_indices_unused_categories)  s   r+  c                 C   sj   t dg di}|d d|d< t|dd |  }ttg ddtg dddd}t|| d S )Nr   r#  r   rH   rr   )rT   r"   )	r   r   r|  rA   r   r   r   r   r   )r}  rD   r    r   r   r   r   1test_groupby_last_first_preserve_categoricaldtype=  s   r,  c               	   C   s   t ddgddgddgd} | jdddd} | jd	d
gdd d }tddgttddgd	dtddgd
dgdd}t	|| d S )NrM   rN   rv   r`  r   r   rQ   r'  r   rH   Tr>   rI   rr   r   )
r   r   rA   r1   r   r   r   r   r   r   r  r   r   r   )test_groupby_categorical_observed_nuniqueI  s   r-  c                  C   s   t jddgdd} tddgddgddggddgd	d| i}|dd  }tddgtddgdd
dt jddgddd}t	|| d S )Nr  bigTr   rM   rN   grpdescriptionrf   rr   r  )
r   r!  r   r   rA   r,   r   r   r   r   )r   rD   r    r   r   r   r   ,test_groupby_categorical_aggregate_functionsX  s   
r1  c                 C   s   t ddgg dd}tt ddgg ddddgd}|jd| |d	}| }| r4td
ddgi|d}ntg dg d}td
g di|d}d|j_t|| d S )NrM   rN   r#  r"  rO   r:   )rj   r[   rj   )r?   rW  r[   rU   )rO   r:   r   )	r   r   rA   r8   r   r"   rT   r   r   )r?   rW  r   rD   r   r    r   r"   r   r   r   test_groupby_categorical_dropnaj  s   "r2  
index_kind)r   singlemultic                 C   s  |dkr|sd}|  tjj|d n|dkr|stjdd ttg dg d|dtd	d
}|dkr9dg}	n |dkrFdg}	||	}n|dkrYddg}	|d |d< ||	}t	||}
|j
|	|||d}|s|dv rtjtdd t|||
  W d    d S 1 sw   Y  d S t|||
 }|r|jdj}n|d jj}tg d}t|| |dkr|jdj}t|| d S d S )Nr'   zDGH#49950 - corrwith with as_index=False may not have grouping columnr   r   /Result doesn't have categories, nothing to testrN   rM   rN   rO   rM   r:   rO   rN   r   r:   rQ   r   r4  r5  r,  r  r  r  rp   )r  r  r  r	  r  r   r   r   r
  r   rA   rX  rY  r|  r"   r   r   r   r   r   r   )r  r  r   r?   r  r3  r   r   rD   r3  r!   r   	op_resultr    r   r   r   r   test_category_order_reducer{  sP   


r:  r4  r5  c                 C   s   t tg dg d|dtdd}|dkrdg}||}n|dkr2dd	g}|d |d	< ||}t||}|j|| ||d
}	|dkrFtnd }
d}tj|
|d t	|	|| }W d    n1 scw   Y  |j
dj}tg d}t|| |dkr|j
d	j}t|| d S d S )Nr7  r8  r   r:   rQ   r4  r   r5  r,  r  r  z%DataFrameGroupBy.fillna is deprecatedrp   )r   r   r   r
  r   rA   r   r   r   r|  r"   r   r   r   r   )r  r   r?   transformation_funcr3  r   rD   r3  r!   r   warnr   r9  r    r   r   r   r   test_category_order_transformer  s4   

r=  methodheadtailc                 C   s   t tg dg d|dtdd}|dkrdg}n |dkr'dg}||}n|d	kr:dd
g}|d |d
< ||}|j|| ||d}t|| }	|dkrT|	d jj}
n|	j	dj}
t
g d}t|
| |d	krz|	j	d
j}
t|
| d S d S )Nr7  r8  r   r:   rQ   r   r   r4  r5  r,  r  )r   r   r   r
  rA   r|  r   r   r"   r   r   r   r   )r  r   r?   r>  r3  r   rD   r3  r   r9  r    r   r   r   r   test_category_order_head_tail  s2   
rA  )rC   r   r   c                 C   sz  |dkr|dks| s|dkrt d ttg dg d|dtdd}|dkr-d	g}n |d
kr:d	g}||}n|dkrMd	dg}|d	 |d< ||}|j|| ||d}|dkr`|dkr`tnd }	d}
tj	|	|
d t
||dd }W d    n1 sw   Y  |dks| s|dkr|d	 jj}n|jd	j}tg d}t|| |dkr|jdj}t|| d S d S )Nr   r   z(No categories in result, nothing to testr7  r8  r   r:   rQ   r   r4  r5  r,  r  rC   ro   rp   c                 S   s   | j ddS )NTrb   )r8   ri   r   r   r   rk     r   z+test_category_order_apply.<locals>.<lambda>)r  r  r   r   r   r
  rA   r   r   r   r|  r   r   r"   r   r   r   )r  r   r?   r>  r3  r   rD   r3  r   r<  r   r9  r    r   r   r   r   test_category_order_apply  sD   

rB  c                 C   sV  |dkr| st jdd tddd}tg d||d}t|tdd	}|dkr-d
g}n |dkr:d
g}||}n|dkrMd
dg}|d
 |d< ||}|j|| |dd}|	 }	|r`g dng d}
t
|
|j|d
d}| rtd|
i}|dkrtt||d|_n||_n|dkrtt|t||
d}n	tt||
d	}t|	| d S )Nr   r6  r   i'  rF  r7  r   r:   rQ   r   r4  r5  r,  Tr  )rO   rN   rM   )rN   rM   rO   )r   r   rT   rH   )r   r,  )r   r,  rH   )r  r  r   r   r   r   r   r
  rA   r8   r   r   r   
from_framer"   r   r   r   )r  r   r3  r   r   grouperrD   r3  r   r    r   r"   r   r   r   r   test_many_categories  s:   

rE  cat_columnsr3  c                 C   s   t g dg dd}||  d|| < d}t| t|@ r tnd }tj||d || W d    d S 1 s:w   Y  d S )Nr  )r:   rP   r   ra   rQ   r   z+The default of observed=False is deprecatedrp   )r   r   setr   r   r   rA   )rF  r3  rD   r   klassr   r   r   test_groupby_default_deprD  s   "rI  a1c                 C   s  |r|dkrt tdrJ td n-|dkr$d}| tjj|d n|dkr@|s@t|dkr@|s@|s@d}| tjj|d tg dg d	g d
d}|	ddd}d|vr`|j
dd}|j|||d}|rn|d }t||}	|s|dv r|ddgkrtjtdd |j|gg|	R   W d    d S 1 sw   Y  d S |j|gg|	R  }
t|||	 }|r|s|dkr||}|stdd |jd d D d|fg |_n|s||g |_t|
| d S )Nr'   z*corrwith not implemented for SeriesGroupByz1GH#32293: attempts to call SeriesGroupBy.corrwithr   r1   rM   zGH#52848 - raises a ValueError)r   r   rM   )rN   rO   rO   r+  )rJ  r,  rH   r   )rJ  r,  r,  rf   rq  rH   r  rJ  r  rp   r5   c                 S   s   g | ]}|d fqS ) r   )r  indr   r   r   r  {  s    z!test_agg_list.<locals>.<listcomp>rF  )r  r
   r  r  r  r  r	  r   r   r   r1  rA   r   rX  rY  r   r|  r  r   from_tuplesrg   r   r2  )r  r  r?   r  r-  r3  r   rD   r   r!   r    r   r   r   r   test_agg_listP  sX   


 rN  )ir   numpyr   r  pandasr   r   r   r   r   r   r   r	   pandas._testing_testingr   pandas.api.typingr
   pandas.tests.groupbyr   r   r#   r  r  filterwarningsrF   r   r   r   parametrizer   r  r  r!  r)  r6  r7  r9  r<  rB  rE  rJ  rL  rV  r[  r   renamer^  ri  rm  rv  r  r  r  r  r  r  r  r  r  r   r  NaTr  fixturer  r  r  r   r  r  r  r  r  r  r  r  r  r  r1   r&   r  r  r  r
  r  r  r  r#  rs   boolr'  r(  r+  r,  r-  r1  r2  r:  r=  rA  rB  rE  rI  rN  r   r   r   r   <module>   s    $		

 
 (

$
r" +
$

<!




	%
"
2




"
"
,	
&4

*


-8
0 !&
'
