wrapped_print ,
)
from lkj.importing import import_object , register_namespace_forwarding
+from lkj.chunking import chunk_iterable , chunker
from lkj.misc import identity , value_in_interval
ddir = lambda obj : list ( filter ( lambda x : not x . startswith ( '_' ), dir ( obj )))
-
-
[docs]
-
def chunker ( a , chk_size , * , include_tail = True ):
-
"""Chunks an iterable into non-overlapping chunks of size chk_size.
-
-
>>> list(chunker(range(8), 3))
-
[(0, 1, 2), (3, 4, 5), (6, 7)]
-
>>> list(chunker(range(8), 3, include_tail=False))
-
[(0, 1, 2), (3, 4, 5)]
-
"""
-
from itertools import zip_longest
-
-
it = iter ( a )
-
if include_tail :
-
sentinel = object ()
-
for chunk in zip_longest ( * ([ it ] * chk_size ), fillvalue = sentinel ):
-
yield tuple ( item for item in chunk if item is not sentinel )
-
else :
-
yield from zip ( * ([ it ] * chk_size ))
[docs]
def user_machine_id ():
diff --git a/_modules/lkj/chunking.html b/_modules/lkj/chunking.html
new file mode 100644
index 0000000..64b7d17
--- /dev/null
+++ b/_modules/lkj/chunking.html
@@ -0,0 +1,237 @@
+
+
+
+
+
+
+
+
lkj.chunking — lkj 0.1.10 documentation
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ lkj
+
+
+
+
+
+
+
+
+
Source code for lkj.chunking
+"""Tools for chunking (segumentation, batching, slicing, etc.)"""
+
+from itertools import zip_longest , chain , islice
+
+from typing import (
+ Iterable ,
+ Union ,
+ Dict ,
+ List ,
+ Tuple ,
+ Mapping ,
+ TypeVar ,
+ Iterator ,
+ Callable ,
+ Optional ,
+ T ,
+)
+
+KT = TypeVar ( 'KT' ) # there's a typing.KT, but pylance won't allow me to use it!
+VT = TypeVar ( 'VT' ) # there's a typing.VT, but pylance won't allow me to use it!
+
+
+
+
[docs]
+
def chunk_iterable (
+
iterable : Union [ Iterable [ T ], Mapping [ KT , VT ]],
+
chk_size : int ,
+
* ,
+
chunk_type : Optional [ Callable [ ... , Union [ Iterable [ T ], Mapping [ KT , VT ]]]] = None ,
+
) -> Iterator [ Union [ List [ T ], Tuple [ T , ... ], Dict [ KT , VT ]]]:
+
"""
+
Divide an iterable into chunks/batches of a specific size.
+
+
Handles both mappings (e.g. dicts) and non-mappings (lists, tuples, sets...)
+
as you probably expect it to (if you give a dict input, it will chunk on the
+
(key, value) items and return dicts of these).
+
Thought note that you always can control the type of the chunks with the
+
`chunk_type` argument.
+
+
Args:
+
iterable: The iterable or mapping to divide.
+
chk_size: The size of each chunk.
+
chunk_type: The type of the chunks (list, tuple, set, dict...).
+
+
Returns:
+
An iterator of dicts if the input is a Mapping, otherwise an iterator
+
of collections (list, tuple, set...).
+
+
Examples:
+
>>> list(chunk_iterable([1, 2, 3, 4, 5], 2))
+
[[1, 2], [3, 4], [5]]
+
+
>>> list(chunk_iterable((1, 2, 3, 4, 5), 3, chunk_type=tuple))
+
[(1, 2, 3), (4, 5)]
+
+
>>> list(chunk_iterable({"a": 1, "b": 2, "c": 3}, 2))
+
[{'a': 1, 'b': 2}, {'c': 3}]
+
+
>>> list(chunk_iterable({"x": 1, "y": 2, "z": 3}, 1, chunk_type=dict))
+
[{'x': 1}, {'y': 2}, {'z': 3}]
+
"""
+
if isinstance ( iterable , Mapping ):
+
if chunk_type is None :
+
chunk_type = dict
+
it = iter ( iterable . items ())
+
for first in it :
+
yield {
+
key : value for key , value in chain ([ first ], islice ( it , chk_size - 1 ))
+
}
+
else :
+
if chunk_type is None :
+
if isinstance ( iterable , ( list , tuple , set )):
+
chunk_type = type ( iterable )
+
else :
+
chunk_type = list
+
it = iter ( iterable )
+
for first in it :
+
yield chunk_type ( chain ([ first ], islice ( it , chk_size - 1 )))
+
[docs]
+
def chunker (
+
a : Iterable [ T ],
+
chk_size : int ,
+
* ,
+
include_tail : bool = True
+
) -> Iterator [ Tuple [ T , ... ]]:
+
"""
+
Chunks an iterable into non-overlapping chunks of size `chk_size`.
+
+
Note: This chunker is simpler, but also less efficient than `chunk_iterable`.
+
It does have the extra `include_tail` argument, though.
+
Though note that you can get the effect of `include_tail=False` in `chunk_iterable`
+
by using `filter(lambda x: len(x) == chk_size, chunk_iterable(...))`.
+
+
Args:
+
a: The iterable to be chunked.
+
chk_size: The size of each chunk.
+
include_tail: If True, includes the remaining elements as the last chunk
+
even if they are fewer than `chk_size`. Defaults to True.
+
+
Returns:
+
An iterator of tuples, where each tuple is a chunk of size `chk_size`
+
(or fewer elements if `include_tail` is True).
+
+
Examples:
+
>>> list(chunker(range(8), 3))
+
[(0, 1, 2), (3, 4, 5), (6, 7)]
+
>>> list(chunker(range(8), 3, include_tail=False))
+
[(0, 1, 2), (3, 4, 5)]
+
"""
+
it = iter ( a )
+
if include_tail :
+
sentinel = object ()
+
for chunk in zip_longest ( * ([ it ] * chk_size ), fillvalue = sentinel ):
+
yield tuple ( item for item in chunk if item is not sentinel )
+
else :
+
yield from zip ( * ([ it ] * chk_size ))
+
+
+
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/_modules/lkj/dicts.html b/_modules/lkj/dicts.html
index 30c7db5..157fc2c 100644
--- a/_modules/lkj/dicts.html
+++ b/_modules/lkj/dicts.html
@@ -47,6 +47,7 @@
Contents:
lkj lkj.chunking lkj.dicts lkj.filesys lkj.funcs Contents:
lkj lkj.chunking lkj.dicts lkj.filesys lkj.funcs Contents:
lkj lkj.chunking lkj.dicts lkj.filesys lkj.funcs Contents:
lkj lkj.chunking lkj.dicts lkj.filesys lkj.funcs Contents:
lkj lkj.chunking lkj.dicts lkj.filesys lkj.funcs Contents:
lkj lkj.chunking lkj.dicts lkj.filesys lkj.funcs Contents:
lkj lkj.chunking lkj.dicts lkj.filesys lkj.funcs Contents:
lkj lkj.chunking lkj.dicts lkj.filesys lkj.funcs Contents:
lkj lkj.chunking lkj.dicts lkj.filesys lkj.funcs C
@@ -227,6 +230,13 @@ L
+
+ lkj.chunking
+
+
@@ -250,6 +260,8 @@ L
module
+
lkj.importing
@@ -257,8 +269,6 @@ L
module
-
Release: 0.1.10
-Last change: Dec 07, 2024
+Last change: Dec 13, 2024
diff --git a/module_docs/lkj.html b/module_docs/lkj.html
index 5b75065..4dc762f 100644
--- a/module_docs/lkj.html
+++ b/module_docs/lkj.html
@@ -24,7 +24,7 @@
lkj
lkj.chunking lkj.dicts lkj.filesys lkj.funcs
-
-lkj. chunker ( a chk_size * include_tail = True ) [source]
-Chunks an iterable into non-overlapping chunks of size chk_size.
->>> list ( chunker ( range ( 8 ), 3 ))
-[(0, 1, 2), (3, 4, 5), (6, 7)]
->>> list ( chunker ( range ( 8 ), 3 , include_tail = False ))
-[(0, 1, 2), (3, 4, 5)]
-
-
-
lkj. get_caller_package_name ( default = None ) [source]
@@ -238,7 +226,7 @@
lkj.chunking — lkj 0.1.10 documentation
+
+
+
+
+
+
+ lkj
+
+
+
+
+
+
+
+
+
+lkj.chunking
+Tools for chunking (segumentation, batching, slicing, etc.)
+
+
+lkj.chunking. chunk_iterable ( iterable : Iterable | Mapping [ KT , VT ] chk_size : int * chunk_type : Callable [ [ ... ] , Iterable | Mapping [ KT , VT ] ] | None = None ) → Iterator [ List | Tuple [ T , ... ] | Dict [ KT , VT ] ] [source]
+Divide an iterable into chunks/batches of a specific size.
+Handles both mappings (e.g. dicts) and non-mappings (lists, tuples, sets…)
+as you probably expect it to (if you give a dict input, it will chunk on the
+(key, value) items and return dicts of these).
+Thought note that you always can control the type of the chunks with the
+chunk_type argument.
+
+Parameters:
+
+iterable – The iterable or mapping to divide.
chk_size – The size of each chunk.
chunk_type – The type of the chunks (list, tuple, set, dict…).
+Returns:
+An iterator of dicts if the input is a Mapping, otherwise an iterator
+of collections (list, tuple, set…).
+
+Examples
+>>> list ( chunk_iterable ([ 1 , 2 , 3 , 4 , 5 ], 2 ))
+[[1, 2], [3, 4], [5]]
+
+
>>> list ( chunk_iterable (( 1 , 2 , 3 , 4 , 5 ), 3 , chunk_type = tuple ))
+[(1, 2, 3), (4, 5)]
+
+
>>> list ( chunk_iterable ({ "a" : 1 , "b" : 2 , "c" : 3 }, 2 ))
+[{'a': 1, 'b': 2}, {'c': 3}]
+
+
>>> list ( chunk_iterable ({ "x" : 1 , "y" : 2 , "z" : 3 }, 1 , chunk_type = dict ))
+[{'x': 1}, {'y': 2}, {'z': 3}]
+
+
+
+
+
+lkj.chunking. chunker ( a : Iterable chk_size : int * include_tail : bool = True ) → Iterator [ Tuple [ T , ... ] ] [source]
+Chunks an iterable into non-overlapping chunks of size chk_size .
+Note: This chunker is simpler, but also less efficient than chunk_iterable .
+It does have the extra include_tail argument, though.
+Though note that you can get the effect of include_tail=False in chunk_iterable
+by using filter(lambda x: len(x) == chk_size, chunk_iterable(…)) .
+
+Parameters:
+
+a – The iterable to be chunked.
chk_size – The size of each chunk.
include_tail – If True, includes the remaining elements as the last chunk
+even if they are fewer than chk_size . Defaults to True.
+Returns:
+An iterator of tuples, where each tuple is a chunk of size chk_size
+(or fewer elements if include_tail is True).
+
+Examples
+>>> list ( chunker ( range ( 8 ), 3 ))
+[(0, 1, 2), (3, 4, 5), (6, 7)]
+>>> list ( chunker ( range ( 8 ), 3 , include_tail = False ))
+[(0, 1, 2), (3, 4, 5)]
+
+
+
+
+
+
+
+
+
+
+
+
Contents:
lkj lkj.chunking lkj.dicts
exclusive_subdict() inclusive_subdict()
diff --git a/module_docs/lkj/filesys.html b/module_docs/lkj/filesys.html
index 9b8ad1f..9e64021 100644
--- a/module_docs/lkj/filesys.html
+++ b/module_docs/lkj/filesys.html
@@ -50,6 +50,7 @@
Contents:
lkj lkj.chunking lkj.dicts lkj.filesys
do_nothing() Contents:
lkj lkj.chunking lkj.dicts lkj.filesys lkj.funcs
diff --git a/module_docs/lkj/importing.html b/module_docs/lkj/importing.html
index 5ca01be..6815bf5 100644
--- a/module_docs/lkj/importing.html
+++ b/module_docs/lkj/importing.html
@@ -50,6 +50,7 @@
Contents:
lkj lkj.chunking lkj.dicts lkj.filesys lkj.funcs Contents:
lkj lkj.chunking lkj.dicts lkj.filesys lkj.funcs Contents:
lkj lkj.chunking lkj.dicts lkj.filesys lkj.funcs Contents:
lkj lkj.chunking lkj.dicts lkj.filesys lkj.funcs Contents:
lkj lkj.chunking lkj.dicts lkj.filesys lkj.funcs Contents:
lkj lkj.chunking lkj.dicts lkj.filesys lkj.funcs Python Module Index
lkj
+
+
+ lkj.chunking
+
diff --git a/search.html b/search.html
index 3a82daf..78b1901 100644
--- a/search.html
+++ b/search.html
@@ -50,6 +50,7 @@
Contents:
lkj lkj.chunking lkj.dicts lkj.filesys lkj.funcs Contents: