3
���h�, � @ s� d dl mZmZ d dlZd dlmZmZmZmZm Z m
Z
d dl m Z d dl
mZmZ d dlmZ d dlmZ d dlmZ er�d d lmZ e
eef eed
�d d �Ze
ee f eed
�dd�Z G dd� ded�Z G dd� de �Z dS )� )�ABCMeta�abstractmethodN)�IO�
TYPE_CHECKING�List�Optional�Tuple�Union)�
get_option)�Dtype�
FrameOrSeries)�Index)�format)� pprint_thing)�Series)�s�space�returnc C s t | �d|� j|�S )a�
Make string of specified length, padding to the right if necessary.
Parameters
----------
s : Union[str, Dtype]
String to be formatted.
space : int
Length to force string to be of.
Returns
-------
str
String coerced to given length.
Examples
--------
>>> pd.io.formats.info._put_str("panda", 6)
'panda '
>>> pd.io.formats.info._put_str("panda", 4)
'pand'
N)�str�ljust)r r � r �8/tmp/pip-build-5_djhm0z/pandas/pandas/io/formats/info.py�_put_str s r )�num�size_qualifierr c C sB x0d
D ](}| dk r&| d�|� d|� �S | d } qW | d�|� d �S ) a{
Return size in human readable format.
Parameters
----------
num : int
Size in bytes.
size_qualifier : str
Either empty, or '+' (if lower bound).
Returns
-------
str
Size in human readable format.
Examples
--------
>>> _sizeof_fmt(23028, '')
'22.5 KB'
>>> _sizeof_fmt(23028, '+')
'22.5+ KB'
�bytes�KB�MB�GB�TBg �@z3.1f� z PB)r r r r r r )r r �xr r r � _sizeof_fmt, s
r" c @ s� e Zd Zdeee eee ee ee eef ee d�dd�Z
e eed�dd��Z e e
d d
�d d ��Ze ee dd edd
�dd��Ze ee ddd�dd��Zdd
�dd�ZdS )�BaseInfoN)�data�verbose�buf�max_cols� memory_usage� null_countsc C sF |d krt j}|d kr td�}|| _|| _|| _|| _|| _|| _d S )Nzdisplay.memory_usage) �sys�stdoutr
r$ r% r& r' r( r) )�selfr$ r% r& r' r( r) r r r �__init__L s zBaseInfo.__init__)�deepr c C s dS )a�
Get memory usage in bytes.
Parameters
----------
deep : bool
If True, introspect the data deeply by interrogating object dtypes
for system-level memory consumption, and include it in the returned
values.
Returns
-------
mem_usage : int
Object's total memory usage in bytes.
Nr )r, r. r r r �_get_mem_usagea s zBaseInfo._get_mem_usager
r )r c C s dS )z�
Get column names and dtypes.
Returns
-------
ids : Index
DataFrame's column names.
dtypes : Series
Dtype of each of the DataFrame's columns.
Nr )r, r r r �_get_ids_and_dtypest s z BaseInfo._get_ids_and_dtypes)�lines�ids�dtypes� show_countsr c C s dS )a�
Append name, non-null count (optional), and dtype for each column to `lines`.
Parameters
----------
lines : List[str]
Lines that will contain `info` representation.
ids : Index
The DataFrame's column names.
dtypes : Series
The DataFrame's columns' dtypes.
show_counts : bool
If True, count of non-NA cells for each column will be appended to `lines`.
Nr )r, r1 r2 r3 r4 r r r �
_verbose_repr� s zBaseInfo._verbose_repr)r1 r2 r c C s dS )z�
Append short summary of columns' names to `lines`.
Parameters
----------
lines : List[str]
Lines that will contain `info` representation.
ids : Index
The DataFrame's column names.
Nr )r, r1 r2 r r r �_non_verbose_repr� s zBaseInfo._non_verbose_reprc C s� g }|j tt| j��� |j | jjj� � | j� \}}t|�}|dkrp|j dt| j�j� �� t j
| j |� dS | j }|dkr�t
d|d �}t
dt| j�d �}| jdkr�||ko�t| j�|k }n| j}||k}| jr�| j||||� n>| jdk�r| j||� n$|�r| j||� n| j||||� |j� jdd � �j� } d
d � t| j� �D �}
|j d d
j|
�� �� | j�r�d} | jdk�r�d} n d} d| k�s�| jjj� �r�d} | j| d�}
|j dt|
| �� d�� t j
| j |� dS )a�
Print a concise summary of a %(klass)s.
This method prints information about a %(klass)s including
the index dtype%(type_sub)s, non-null values and memory usage.
Parameters
----------
data : %(klass)s
%(klass)s to print information about.
verbose : bool, optional
Whether to print the full summary. By default, the setting in
``pandas.options.display.max_info_columns`` is followed.
buf : writable buffer, defaults to sys.stdout
Where to send the output. By default, the output is printed to
sys.stdout. Pass a writable buffer if you need to further process
the output.
%(max_cols_sub)s
memory_usage : bool, str, optional
Specifies whether total memory usage of the %(klass)s
elements (including the index) should be displayed. By default,
this follows the ``pandas.options.display.memory_usage`` setting.
True always show memory usage. False never shows memory usage.
A value of 'deep' is equivalent to "True with deep introspection".
Memory usage is shown in human-readable units (base-2
representation). Without deep introspection a memory estimation is
made based in column dtype and number of rows assuming values
consume the same memory amount for corresponding dtypes. With deep
memory introspection, a real memory usage calculation is performed
at the cost of computational resources.
null_counts : bool, optional
Whether to show the non-null counts. By default, this is shown
only if the %(klass)s is smaller than
``pandas.options.display.max_info_rows`` and
``pandas.options.display.max_info_columns``. A value of True always
shows the counts, and False never shows the counts.
Returns
-------
None
This method prints a summary of a %(klass)s and returns None.
See Also
--------
%(see_also_sub)s
Examples
--------
%(examples_sub)s
r zEmpty Nzdisplay.max_info_columns� zdisplay.max_info_rowsFc S s | j S )N)�name)r! r r r �<lambda>� s z BaseInfo.info.<locals>.<lambda>c S s& g | ] }|d � d|d d�d��qS )r �(r7 �d�)r )�.0�kr r r �
<listcomp>� s z!BaseInfo.info.<locals>.<listcomp>zdtypes: z, � r. T�object�+)r. zmemory usage: �
) �appendr �typer$ �index�_summaryr0 �len�__name__�fmtZbuffer_put_linesr& r' r
r) r% r5 r6 Z value_counts�groupby�sum�sorted�items�joinr( Z_is_memory_usage_qualifiedr/ r" )r, r1 r2 r3 � col_countr' Zmax_rowsr4 Zexceeds_info_cols�countsZcollected_dtypesr r. Z mem_usager r r �info� sJ 4
z
BaseInfo.info)NNNNN)r
r )rI �
__module__� __qualname__r r �boolr r �intr r- r r/ r r0 r r5 r6 rR r r r r r# K s :
r# )� metaclassc @ s^ e Zd Zeed�dd�Zed d�dd�Zee dded d
�d d �Z
ee dd d
�dd�Z d S )�
DataFrameInfo)r. r c C s | j jd|d�j� S )NT)rF r. )r$ r( rL )r, r. r r r r/ s z DataFrameInfo._get_mem_usager
r )r c C s | j j| j jfS )N)r$ �columnsr3 )r, r r r r0 s z!DataFrameInfo._get_ids_and_dtypesN)r1 r2 r3 r4 r c C s" t |�}|jd|� d�� d}d}d}tdd� |D ��} t t|��}
t| |
�| } t t|��} t t|��}
t| |
�| }t||�t|| � }|�r| jj� }|t |�kr�td|� d t |�� d
���d }t |�}d }td
d� |D ��t |� }t||�| }d| }nd}t |�}|}d}d}t |�}tdd� |D ��}t||�}|t||�t||� 7 }|j|� |jtd|
|�td|
| � td| |� td| |� � x|t|�D ]p\}} |j | } t| �} td|� �|�} d} |�r�|j | } |j| t| | � t|j
| d�|� t| |� � �q�W d S )NzData columns (total z
columns):z # ZColumn� c s s | ]}t t|��V qd S )N)rH r )r= r> r r r � <genexpr># s z.DataFrameInfo._verbose_repr.<locals>.<genexpr>zColumns must equal counts (z != r< zNon-Null Countz non-nullc s s | ]}t t|��V qd S )N)rH r )r= r> r r r r[ 5 s z{count}r@ r c s s | ]}t t|��V qd S )N)rH r )r= r> r r r r[ @ s �-r )�count) rH rD �maxr r r$ r] �AssertionError� enumerateZilocr ) r, r1 r2 r3 r4 rP Zid_headZ column_headZ col_spaceZmax_colZ
len_columnr Zmax_idZlen_idZ space_num�headerrQ Z count_headerZ len_countZnon_null� max_countZ space_countZ
count_tempZ dtype_headerZ len_dtypeZ
max_dtypesZ space_dtype�i�colZdtypeZline_nor] r r r r5 sZ
:
zDataFrameInfo._verbose_repr)r1 r2 r c C s |j |jdd�� d S )NZColumns)r8 )rD rG )r, r1 r2 r r r r6 ^ s z DataFrameInfo._non_verbose_repr)r
r ) rI rS rT rU rV r/ r r0 r r r5 r6 r r r r rX s
CrX ) �abcr r r* Ztypingr r r r r r Zpandas._configr
Zpandas._typingr r Zpandas.core.indexes.apir
Zpandas.io.formatsr rJ Zpandas.io.formats.printingr Zpandas.core.seriesr r rV r �floatr" r# rX r r r r �<module> s H |