mirror of
https://github.com/python/cpython.git
synced 2025-10-18 04:38:07 +00:00

svn+ssh://pythondev@svn.python.org/python/branches/p3yk ................ r56322 | kurt.kaiser | 2007-07-12 11:35:03 -0700 (Thu, 12 Jul 2007) | 2 lines Replace obscure code which was failing in py3k. ................ r56323 | kurt.kaiser | 2007-07-12 11:44:12 -0700 (Thu, 12 Jul 2007) | 3 lines 1. Remove new division option 2. Update IDLE version to 3.0x ................ r56327 | kurt.kaiser | 2007-07-12 12:20:20 -0700 (Thu, 12 Jul 2007) | 5 lines Fix another instance of this defect in Tkinter, and one in IDLE. Patch 1724999 by Ali Gholami Rudi -- avoid complaints about dict size change during iter in destroy call. ................ r56339 | georg.brandl | 2007-07-13 03:07:25 -0700 (Fri, 13 Jul 2007) | 2 lines Fix #1753310: regrtest -x doesn't work anymore ................ r56361 | kurt.kaiser | 2007-07-13 18:25:24 -0700 (Fri, 13 Jul 2007) | 2 lines convert a map() iterator to a list to get this working. ................ r56362 | kurt.kaiser | 2007-07-13 18:53:45 -0700 (Fri, 13 Jul 2007) | 2 lines Was modifying dict during iteration. ................ r56376 | collin.winter | 2007-07-14 11:56:19 -0700 (Sat, 14 Jul 2007) | 1 line Add an example of class decorators to test_grammar. ................ r56377 | collin.winter | 2007-07-14 12:00:17 -0700 (Sat, 14 Jul 2007) | 1 line Add a basic example of dictcomps to test_grammar. ................ r56413 | neal.norwitz | 2007-07-17 00:21:18 -0700 (Tue, 17 Jul 2007) | 149 lines Merged revisions 56202-56412 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r56204 | ronald.oussoren | 2007-07-08 23:02:21 -0700 (Sun, 08 Jul 2007) | 2 lines Patch 1693258: Fix for duplicate "preferences" menu-OS X ........ r56207 | ronald.oussoren | 2007-07-09 01:41:15 -0700 (Mon, 09 Jul 2007) | 4 lines Patch 1673122: be explicit about which libtool to use, to avoid name clashes when a users install GNU libtool early in his PATH ........ r56280 | georg.brandl | 2007-07-11 12:41:49 -0700 (Wed, 11 Jul 2007) | 2 lines Fix #1752132: wrong comment in opcode description. ........ r56293 | georg.brandl | 2007-07-12 01:05:45 -0700 (Thu, 12 Jul 2007) | 3 lines Patch #1752270, #1750931: complain if urllib2 add_handler called without handler. ........ r56296 | georg.brandl | 2007-07-12 01:11:29 -0700 (Thu, 12 Jul 2007) | 2 lines Patch #1739696: use code.co_code only if really necessary ........ r56298 | georg.brandl | 2007-07-12 01:38:00 -0700 (Thu, 12 Jul 2007) | 3 lines Patch #1673759: add a missing overflow check when formatting floats with %G. ........ r56302 | georg.brandl | 2007-07-12 02:06:41 -0700 (Thu, 12 Jul 2007) | 2 lines Patch #1731659: improve time.strptime docs. ........ r56304 | georg.brandl | 2007-07-12 02:24:04 -0700 (Thu, 12 Jul 2007) | 2 lines Patch #1731169: clean up expected skips list. ........ r56306 | georg.brandl | 2007-07-12 02:37:49 -0700 (Thu, 12 Jul 2007) | 3 lines Bug #1637365: add subsection about "__name__ == __main__" to the Python tutorial. ........ r56308 | georg.brandl | 2007-07-12 02:59:22 -0700 (Thu, 12 Jul 2007) | 5 lines Patch #1675424: Added tests for uncovered code in the zipfile module. The KeyError raised by Zipfile.getinfo for nonexistent names now has a descriptive message. ........ r56340 | facundo.batista | 2007-07-13 03:43:44 -0700 (Fri, 13 Jul 2007) | 6 lines Added tests for basic behavior of DateTime, Binary, and Fault classes and the escape function. Check that marshalling recursive sequences & dicts raises TypeError. Check that marshalling out-of-range ints raises OverflowError [Alan McIntyre - GSoC] ........ r56345 | raymond.hettinger | 2007-07-13 05:09:41 -0700 (Fri, 13 Jul 2007) | 1 line Correct the docs for takewhile(). Improve the recipe for nth(). Should be backported ........ r56348 | thomas.heller | 2007-07-13 06:59:39 -0700 (Fri, 13 Jul 2007) | 4 lines Repair COMError. Since exceptions are new style classes now, setting the methods and docstring after the type creation does not work, they must be in the dictionary before creating the type. ........ r56349 | thomas.heller | 2007-07-13 07:18:06 -0700 (Fri, 13 Jul 2007) | 1 line Add tests for _ctypes.COMError. ........ r56350 | thomas.heller | 2007-07-13 09:50:43 -0700 (Fri, 13 Jul 2007) | 4 lines Do not try to load the GLUT library in the ctypes tests. This test adds little value, but has a large problem on OS X, as explained in SF# 1581906. ........ r56352 | thomas.heller | 2007-07-13 10:12:23 -0700 (Fri, 13 Jul 2007) | 3 lines Fix for SF# 1701409: segfault in c_char_p of ctypes. The repr output of c_char_p and c_wchar_p has changed as a sideeffect. ........ r56355 | thomas.heller | 2007-07-13 10:46:54 -0700 (Fri, 13 Jul 2007) | 3 lines Fix for SF# 1649098: avoid zero-sized array declaration in structure. ........ r56357 | thomas.heller | 2007-07-13 12:51:55 -0700 (Fri, 13 Jul 2007) | 3 lines PyType_stgdict() returns a borrowed reference which must not be Py_DECREF'd. ........ r56360 | barry.warsaw | 2007-07-13 15:12:58 -0700 (Fri, 13 Jul 2007) | 10 lines In response to this SF bug: [ 1752723 ] email.message_from_string: initial line gets discarded I added a test to assert that when the first line of text passed to message_from_string() contains a leading space, the message ends up with the appropriate FirstHeaderLineIsContinuationDefect on its defects list. The bug is invalid. ........ r56364 | georg.brandl | 2007-07-14 10:12:23 -0700 (Sat, 14 Jul 2007) | 2 lines Bug #1753406: missing \versionadded for subprocess.check_call. ........ r56366 | georg.brandl | 2007-07-14 10:32:41 -0700 (Sat, 14 Jul 2007) | 2 lines Clarify webbrowser.open description. ........ r56380 | andrew.kuchling | 2007-07-14 13:58:21 -0700 (Sat, 14 Jul 2007) | 1 line Typo fix ........ r56382 | andrew.kuchling | 2007-07-14 14:56:19 -0700 (Sat, 14 Jul 2007) | 7 lines Avoid exception if there's a stray directory inside a Maildir folder. The Maildir specification doesn't seem to say anything about this situation, and it can happen if you're keeping a Maildir mailbox in Subversion (.svn directories) or some similar system. The patch just ignores directories in the cur/, new/, tmp/ folders. ........ r56392 | facundo.batista | 2007-07-14 15:41:45 -0700 (Sat, 14 Jul 2007) | 6 lines First version. Includes tests for helper functions: read, write, _exception, readwrite, closeall, compact_traceback; and for classes dispatcher, dispatcher_with_send, and file_wrapper. [Alan McIntyre - GSoC] ........ r56399 | facundo.batista | 2007-07-15 13:30:39 -0700 (Sun, 15 Jul 2007) | 5 lines Changed the used port and commented out some tests that uses a non documented function that appers to uses resources not present in Windows. ........ r56412 | facundo.batista | 2007-07-16 19:19:39 -0700 (Mon, 16 Jul 2007) | 6 lines Prevent asyncore.dispatcher tests from hanging by adding loop counters to server & client, and by adding asyncore.close_all calls in tearDown. Also choose correct expected logging results based on the value of __debug__ [Alan McIntyre - GSoC] ........ ................ r56442 | guido.van.rossum | 2007-07-18 10:26:38 -0700 (Wed, 18 Jul 2007) | 14 lines Merged revisions 56413-56441 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r56439 | georg.brandl | 2007-07-17 23:37:55 -0700 (Tue, 17 Jul 2007) | 2 lines Use "Unix" as platform name, not "UNIX". ........ r56441 | guido.van.rossum | 2007-07-18 10:19:14 -0700 (Wed, 18 Jul 2007) | 3 lines SF patch# 1755885 by Kurt Kaiser: show location of Unicode escape errors. (Slightly tweaked for style and refcounts.) ........ ................
575 lines
20 KiB
TeX
575 lines
20 KiB
TeX
\section{\module{itertools} ---
|
|
Functions creating iterators for efficient looping}
|
|
|
|
\declaremodule{standard}{itertools}
|
|
\modulesynopsis{Functions creating iterators for efficient looping.}
|
|
\moduleauthor{Raymond Hettinger}{python@rcn.com}
|
|
\sectionauthor{Raymond Hettinger}{python@rcn.com}
|
|
\versionadded{2.3}
|
|
|
|
|
|
This module implements a number of iterator building blocks inspired
|
|
by constructs from the Haskell and SML programming languages. Each
|
|
has been recast in a form suitable for Python.
|
|
|
|
The module standardizes a core set of fast, memory efficient tools
|
|
that are useful by themselves or in combination. Standardization helps
|
|
avoid the readability and reliability problems which arise when many
|
|
different individuals create their own slightly varying implementations,
|
|
each with their own quirks and naming conventions.
|
|
|
|
The tools are designed to combine readily with one another. This makes
|
|
it easy to construct more specialized tools succinctly and efficiently
|
|
in pure Python.
|
|
|
|
For instance, SML provides a tabulation tool: \code{tabulate(f)}
|
|
which produces a sequence \code{f(0), f(1), ...}. This toolbox
|
|
provides \function{imap()} and \function{count()} which can be combined
|
|
to form \code{imap(f, count())} and produce an equivalent result.
|
|
|
|
Likewise, the functional tools are designed to work well with the
|
|
high-speed functions provided by the \refmodule{operator} module.
|
|
|
|
The module author welcomes suggestions for other basic building blocks
|
|
to be added to future versions of the module.
|
|
|
|
Whether cast in pure python form or compiled code, tools that use iterators
|
|
are more memory efficient (and faster) than their list based counterparts.
|
|
Adopting the principles of just-in-time manufacturing, they create
|
|
data when and where needed instead of consuming memory with the
|
|
computer equivalent of ``inventory''.
|
|
|
|
The performance advantage of iterators becomes more acute as the number
|
|
of elements increases -- at some point, lists grow large enough to
|
|
severely impact memory cache performance and start running slowly.
|
|
|
|
\begin{seealso}
|
|
\seetext{The Standard ML Basis Library,
|
|
\citetitle[http://www.standardml.org/Basis/]
|
|
{The Standard ML Basis Library}.}
|
|
|
|
\seetext{Haskell, A Purely Functional Language,
|
|
\citetitle[http://www.haskell.org/definition/]
|
|
{Definition of Haskell and the Standard Libraries}.}
|
|
\end{seealso}
|
|
|
|
|
|
\subsection{Itertool functions \label{itertools-functions}}
|
|
|
|
The following module functions all construct and return iterators.
|
|
Some provide streams of infinite length, so they should only be accessed
|
|
by functions or loops that truncate the stream.
|
|
|
|
\begin{funcdesc}{chain}{*iterables}
|
|
Make an iterator that returns elements from the first iterable until
|
|
it is exhausted, then proceeds to the next iterable, until all of the
|
|
iterables are exhausted. Used for treating consecutive sequences as
|
|
a single sequence. Equivalent to:
|
|
|
|
\begin{verbatim}
|
|
def chain(*iterables):
|
|
for it in iterables:
|
|
for element in it:
|
|
yield element
|
|
\end{verbatim}
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{count}{\optional{n}}
|
|
Make an iterator that returns consecutive integers starting with \var{n}.
|
|
If not specified \var{n} defaults to zero.
|
|
Does not currently support python long integers. Often used as an
|
|
argument to \function{imap()} to generate consecutive data points.
|
|
Also, used with \function{izip()} to add sequence numbers. Equivalent to:
|
|
|
|
\begin{verbatim}
|
|
def count(n=0):
|
|
while True:
|
|
yield n
|
|
n += 1
|
|
\end{verbatim}
|
|
|
|
Note, \function{count()} does not check for overflow and will return
|
|
negative numbers after exceeding \code{sys.maxint}. This behavior
|
|
may change in the future.
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{cycle}{iterable}
|
|
Make an iterator returning elements from the iterable and saving a
|
|
copy of each. When the iterable is exhausted, return elements from
|
|
the saved copy. Repeats indefinitely. Equivalent to:
|
|
|
|
\begin{verbatim}
|
|
def cycle(iterable):
|
|
saved = []
|
|
for element in iterable:
|
|
yield element
|
|
saved.append(element)
|
|
while saved:
|
|
for element in saved:
|
|
yield element
|
|
\end{verbatim}
|
|
|
|
Note, this member of the toolkit may require significant
|
|
auxiliary storage (depending on the length of the iterable).
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{dropwhile}{predicate, iterable}
|
|
Make an iterator that drops elements from the iterable as long as
|
|
the predicate is true; afterwards, returns every element. Note,
|
|
the iterator does not produce \emph{any} output until the predicate
|
|
first becomes false, so it may have a lengthy start-up time. Equivalent to:
|
|
|
|
\begin{verbatim}
|
|
def dropwhile(predicate, iterable):
|
|
iterable = iter(iterable)
|
|
for x in iterable:
|
|
if not predicate(x):
|
|
yield x
|
|
break
|
|
for x in iterable:
|
|
yield x
|
|
\end{verbatim}
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{groupby}{iterable\optional{, key}}
|
|
Make an iterator that returns consecutive keys and groups from the
|
|
\var{iterable}. The \var{key} is a function computing a key value for each
|
|
element. If not specified or is \code{None}, \var{key} defaults to an
|
|
identity function and returns the element unchanged. Generally, the
|
|
iterable needs to already be sorted on the same key function.
|
|
|
|
The operation of \function{groupby()} is similar to the \code{uniq} filter
|
|
in \UNIX{}. It generates a break or new group every time the value
|
|
of the key function changes (which is why it is usually necessary
|
|
to have sorted the data using the same key function). That behavior
|
|
differs from SQL's GROUP BY which aggregates common elements regardless
|
|
of their input order.
|
|
|
|
The returned group is itself an iterator that shares the underlying
|
|
iterable with \function{groupby()}. Because the source is shared, when
|
|
the \function{groupby} object is advanced, the previous group is no
|
|
longer visible. So, if that data is needed later, it should be stored
|
|
as a list:
|
|
|
|
\begin{verbatim}
|
|
groups = []
|
|
uniquekeys = []
|
|
data = sorted(data, key=keyfunc)
|
|
for k, g in groupby(data, keyfunc):
|
|
groups.append(list(g)) # Store group iterator as a list
|
|
uniquekeys.append(k)
|
|
\end{verbatim}
|
|
|
|
\function{groupby()} is equivalent to:
|
|
|
|
\begin{verbatim}
|
|
class groupby(object):
|
|
def __init__(self, iterable, key=None):
|
|
if key is None:
|
|
key = lambda x: x
|
|
self.keyfunc = key
|
|
self.it = iter(iterable)
|
|
self.tgtkey = self.currkey = self.currvalue = []
|
|
def __iter__(self):
|
|
return self
|
|
def __next__(self):
|
|
while self.currkey == self.tgtkey:
|
|
self.currvalue = next(self.it) # Exit on StopIteration
|
|
self.currkey = self.keyfunc(self.currvalue)
|
|
self.tgtkey = self.currkey
|
|
return (self.currkey, self._grouper(self.tgtkey))
|
|
def _grouper(self, tgtkey):
|
|
while self.currkey == tgtkey:
|
|
yield self.currvalue
|
|
self.currvalue = next(self.it) # Exit on StopIteration
|
|
self.currkey = self.keyfunc(self.currvalue)
|
|
\end{verbatim}
|
|
\versionadded{2.4}
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{ifilter}{predicate, iterable}
|
|
Make an iterator that filters elements from iterable returning only
|
|
those for which the predicate is \code{True}.
|
|
If \var{predicate} is \code{None}, return the items that are true.
|
|
Equivalent to:
|
|
|
|
\begin{verbatim}
|
|
def ifilter(predicate, iterable):
|
|
if predicate is None:
|
|
predicate = bool
|
|
for x in iterable:
|
|
if predicate(x):
|
|
yield x
|
|
\end{verbatim}
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{ifilterfalse}{predicate, iterable}
|
|
Make an iterator that filters elements from iterable returning only
|
|
those for which the predicate is \code{False}.
|
|
If \var{predicate} is \code{None}, return the items that are false.
|
|
Equivalent to:
|
|
|
|
\begin{verbatim}
|
|
def ifilterfalse(predicate, iterable):
|
|
if predicate is None:
|
|
predicate = bool
|
|
for x in iterable:
|
|
if not predicate(x):
|
|
yield x
|
|
\end{verbatim}
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{imap}{function, *iterables}
|
|
Make an iterator that computes the function using arguments from
|
|
each of the iterables. If \var{function} is set to \code{None}, then
|
|
\function{imap()} returns the arguments as a tuple. Like
|
|
\function{map()} but stops when the shortest iterable is exhausted
|
|
instead of filling in \code{None} for shorter iterables. The reason
|
|
for the difference is that infinite iterator arguments are typically
|
|
an error for \function{map()} (because the output is fully evaluated)
|
|
but represent a common and useful way of supplying arguments to
|
|
\function{imap()}.
|
|
Equivalent to:
|
|
|
|
\begin{verbatim}
|
|
def imap(function, *iterables):
|
|
iterables = map(iter, iterables)
|
|
while True:
|
|
args = [next(i) for i in iterables]
|
|
if function is None:
|
|
yield tuple(args)
|
|
else:
|
|
yield function(*args)
|
|
\end{verbatim}
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{islice}{iterable, \optional{start,} stop \optional{, step}}
|
|
Make an iterator that returns selected elements from the iterable.
|
|
If \var{start} is non-zero, then elements from the iterable are skipped
|
|
until start is reached. Afterward, elements are returned consecutively
|
|
unless \var{step} is set higher than one which results in items being
|
|
skipped. If \var{stop} is \code{None}, then iteration continues until
|
|
the iterator is exhausted, if at all; otherwise, it stops at the specified
|
|
position. Unlike regular slicing,
|
|
\function{islice()} does not support negative values for \var{start},
|
|
\var{stop}, or \var{step}. Can be used to extract related fields
|
|
from data where the internal structure has been flattened (for
|
|
example, a multi-line report may list a name field on every
|
|
third line). Equivalent to:
|
|
|
|
\begin{verbatim}
|
|
def islice(iterable, *args):
|
|
s = slice(*args)
|
|
it = iter(range(s.start or 0, s.stop or sys.maxint, s.step or 1))
|
|
nexti = next(it)
|
|
for i, element in enumerate(iterable):
|
|
if i == nexti:
|
|
yield element
|
|
nexti = next(it)
|
|
\end{verbatim}
|
|
|
|
If \var{start} is \code{None}, then iteration starts at zero.
|
|
If \var{step} is \code{None}, then the step defaults to one.
|
|
\versionchanged[accept \code{None} values for default \var{start} and
|
|
\var{step}]{2.5}
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{izip}{*iterables}
|
|
Make an iterator that aggregates elements from each of the iterables.
|
|
Like \function{zip()} except that it returns an iterator instead of
|
|
a list. Used for lock-step iteration over several iterables at a
|
|
time. Equivalent to:
|
|
|
|
\begin{verbatim}
|
|
def izip(*iterables):
|
|
iterables = map(iter, iterables)
|
|
while iterables:
|
|
result = [next(it) for it in iterables]
|
|
yield tuple(result)
|
|
\end{verbatim}
|
|
|
|
\versionchanged[When no iterables are specified, returns a zero length
|
|
iterator instead of raising a \exception{TypeError}
|
|
exception]{2.4}
|
|
|
|
Note, the left-to-right evaluation order of the iterables is guaranteed.
|
|
This makes possible an idiom for clustering a data series into n-length
|
|
groups using \samp{izip(*[iter(s)]*n)}. For data that doesn't fit
|
|
n-length groups exactly, the last tuple can be pre-padded with fill
|
|
values using \samp{izip(*[chain(s, [None]*(n-1))]*n)}.
|
|
|
|
Note, when \function{izip()} is used with unequal length inputs, subsequent
|
|
iteration over the longer iterables cannot reliably be continued after
|
|
\function{izip()} terminates. Potentially, up to one entry will be missing
|
|
from each of the left-over iterables. This occurs because a value is fetched
|
|
from each iterator in-turn, but the process ends when one of the iterators
|
|
terminates. This leaves the last fetched values in limbo (they cannot be
|
|
returned in a final, incomplete tuple and they are cannot be pushed back
|
|
into the iterator for retrieval with \code{next(it)}). In general,
|
|
\function{izip()} should only be used with unequal length inputs when you
|
|
don't care about trailing, unmatched values from the longer iterables.
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{izip_longest}{*iterables\optional{, fillvalue}}
|
|
Make an iterator that aggregates elements from each of the iterables.
|
|
If the iterables are of uneven length, missing values are filled-in
|
|
with \var{fillvalue}. Iteration continues until the longest iterable
|
|
is exhausted. Equivalent to:
|
|
|
|
\begin{verbatim}
|
|
def izip_longest(*args, **kwds):
|
|
fillvalue = kwds.get('fillvalue')
|
|
def sentinel(counter = ([fillvalue]*(len(args)-1)).pop):
|
|
yield counter() # yields the fillvalue, or raises IndexError
|
|
fillers = repeat(fillvalue)
|
|
iters = [chain(it, sentinel(), fillers) for it in args]
|
|
try:
|
|
for tup in izip(*iters):
|
|
yield tup
|
|
except IndexError:
|
|
pass
|
|
\end{verbatim}
|
|
|
|
If one of the iterables is potentially infinite, then the
|
|
\function{izip_longest()} function should be wrapped with something
|
|
that limits the number of calls (for example \function{islice()} or
|
|
\function{take()}).
|
|
\versionadded{2.6}
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{repeat}{object\optional{, times}}
|
|
Make an iterator that returns \var{object} over and over again.
|
|
Runs indefinitely unless the \var{times} argument is specified.
|
|
Used as argument to \function{imap()} for invariant parameters
|
|
to the called function. Also used with \function{izip()} to create
|
|
an invariant part of a tuple record. Equivalent to:
|
|
|
|
\begin{verbatim}
|
|
def repeat(object, times=None):
|
|
if times is None:
|
|
while True:
|
|
yield object
|
|
else:
|
|
for i in range(times):
|
|
yield object
|
|
\end{verbatim}
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{starmap}{function, iterable}
|
|
Make an iterator that computes the function using arguments tuples
|
|
obtained from the iterable. Used instead of \function{imap()} when
|
|
argument parameters are already grouped in tuples from a single iterable
|
|
(the data has been ``pre-zipped''). The difference between
|
|
\function{imap()} and \function{starmap()} parallels the distinction
|
|
between \code{function(a,b)} and \code{function(*c)}.
|
|
Equivalent to:
|
|
|
|
\begin{verbatim}
|
|
def starmap(function, iterable):
|
|
iterable = iter(iterable)
|
|
while True:
|
|
yield function(*next(iterable))
|
|
\end{verbatim}
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{takewhile}{predicate, iterable}
|
|
Make an iterator that returns elements from the iterable as long as
|
|
the predicate is true. Equivalent to:
|
|
|
|
\begin{verbatim}
|
|
def takewhile(predicate, iterable):
|
|
for x in iterable:
|
|
if predicate(x):
|
|
yield x
|
|
else:
|
|
break
|
|
\end{verbatim}
|
|
\end{funcdesc}
|
|
|
|
\begin{funcdesc}{tee}{iterable\optional{, n=2}}
|
|
Return \var{n} independent iterators from a single iterable.
|
|
The case where \code{n==2} is equivalent to:
|
|
|
|
\begin{verbatim}
|
|
def tee(iterable):
|
|
def gen(next, data={}, cnt=[0]):
|
|
for i in count():
|
|
if i == cnt[0]:
|
|
item = data[i] = next()
|
|
cnt[0] += 1
|
|
else:
|
|
item = data.pop(i)
|
|
yield item
|
|
it = iter(iterable)
|
|
return (gen(it.__next__), gen(it.__next__))
|
|
\end{verbatim}
|
|
|
|
Note, once \function{tee()} has made a split, the original \var{iterable}
|
|
should not be used anywhere else; otherwise, the \var{iterable} could get
|
|
advanced without the tee objects being informed.
|
|
|
|
Note, this member of the toolkit may require significant auxiliary
|
|
storage (depending on how much temporary data needs to be stored).
|
|
In general, if one iterator is going to use most or all of the data before
|
|
the other iterator, it is faster to use \function{list()} instead of
|
|
\function{tee()}.
|
|
\versionadded{2.4}
|
|
\end{funcdesc}
|
|
|
|
|
|
\subsection{Examples \label{itertools-example}}
|
|
|
|
The following examples show common uses for each tool and
|
|
demonstrate ways they can be combined.
|
|
|
|
\begin{verbatim}
|
|
|
|
>>> amounts = [120.15, 764.05, 823.14]
|
|
>>> for checknum, amount in izip(count(1200), amounts):
|
|
... print 'Check %d is for $%.2f' % (checknum, amount)
|
|
...
|
|
Check 1200 is for $120.15
|
|
Check 1201 is for $764.05
|
|
Check 1202 is for $823.14
|
|
|
|
>>> import operator
|
|
>>> for cube in imap(operator.pow, range(1,5), repeat(3)):
|
|
... print cube
|
|
...
|
|
1
|
|
8
|
|
27
|
|
64
|
|
|
|
>>> reportlines = ['EuroPython', 'Roster', '', 'alex', '', 'laura',
|
|
'', 'martin', '', 'walter', '', 'mark']
|
|
>>> for name in islice(reportlines, 3, None, 2):
|
|
... print name.title()
|
|
...
|
|
Alex
|
|
Laura
|
|
Martin
|
|
Walter
|
|
Mark
|
|
|
|
# Show a dictionary sorted and grouped by value
|
|
>>> from operator import itemgetter
|
|
>>> d = dict(a=1, b=2, c=1, d=2, e=1, f=2, g=3)
|
|
>>> di = sorted(d.iteritems(), key=itemgetter(1))
|
|
>>> for k, g in groupby(di, key=itemgetter(1)):
|
|
... print k, map(itemgetter(0), g)
|
|
...
|
|
1 ['a', 'c', 'e']
|
|
2 ['b', 'd', 'f']
|
|
3 ['g']
|
|
|
|
# Find runs of consecutive numbers using groupby. The key to the solution
|
|
# is differencing with a range so that consecutive numbers all appear in
|
|
# same group.
|
|
>>> data = [ 1, 4,5,6, 10, 15,16,17,18, 22, 25,26,27,28]
|
|
>>> for k, g in groupby(enumerate(data), lambda t:t[0]-t[1]):
|
|
... print map(operator.itemgetter(1), g)
|
|
...
|
|
[1]
|
|
[4, 5, 6]
|
|
[10]
|
|
[15, 16, 17, 18]
|
|
[22]
|
|
[25, 26, 27, 28]
|
|
|
|
\end{verbatim}
|
|
|
|
|
|
\subsection{Recipes \label{itertools-recipes}}
|
|
|
|
This section shows recipes for creating an extended toolset using the
|
|
existing itertools as building blocks.
|
|
|
|
The extended tools offer the same high performance as the underlying
|
|
toolset. The superior memory performance is kept by processing elements one
|
|
at a time rather than bringing the whole iterable into memory all at once.
|
|
Code volume is kept small by linking the tools together in a functional style
|
|
which helps eliminate temporary variables. High speed is retained by
|
|
preferring ``vectorized'' building blocks over the use of for-loops and
|
|
generators which incur interpreter overhead.
|
|
|
|
|
|
\begin{verbatim}
|
|
def take(n, seq):
|
|
return list(islice(seq, n))
|
|
|
|
def enumerate(iterable):
|
|
return izip(count(), iterable)
|
|
|
|
def tabulate(function):
|
|
"Return function(0), function(1), ..."
|
|
return imap(function, count())
|
|
|
|
def iteritems(mapping):
|
|
return izip(mapping.iterkeys(), mapping.itervalues())
|
|
|
|
def nth(iterable, n):
|
|
"Returns the nth item or raise StopIteration"
|
|
return islice(iterable, n, None).next()
|
|
|
|
def all(seq, pred=None):
|
|
"Returns True if pred(x) is true for every element in the iterable"
|
|
for elem in ifilterfalse(pred, seq):
|
|
return False
|
|
return True
|
|
|
|
def any(seq, pred=None):
|
|
"Returns True if pred(x) is true for at least one element in the iterable"
|
|
for elem in ifilter(pred, seq):
|
|
return True
|
|
return False
|
|
|
|
def no(seq, pred=None):
|
|
"Returns True if pred(x) is false for every element in the iterable"
|
|
for elem in ifilter(pred, seq):
|
|
return False
|
|
return True
|
|
|
|
def quantify(seq, pred=None):
|
|
"Count how many times the predicate is true in the sequence"
|
|
return sum(imap(pred, seq))
|
|
|
|
def padnone(seq):
|
|
"""Returns the sequence elements and then returns None indefinitely.
|
|
|
|
Useful for emulating the behavior of the built-in map() function.
|
|
"""
|
|
return chain(seq, repeat(None))
|
|
|
|
def ncycles(seq, n):
|
|
"Returns the sequence elements n times"
|
|
return chain(*repeat(seq, n))
|
|
|
|
def dotproduct(vec1, vec2):
|
|
return sum(imap(operator.mul, vec1, vec2))
|
|
|
|
def flatten(listOfLists):
|
|
return list(chain(*listOfLists))
|
|
|
|
def repeatfunc(func, times=None, *args):
|
|
"""Repeat calls to func with specified arguments.
|
|
|
|
Example: repeatfunc(random.random)
|
|
"""
|
|
if times is None:
|
|
return starmap(func, repeat(args))
|
|
else:
|
|
return starmap(func, repeat(args, times))
|
|
|
|
def pairwise(iterable):
|
|
"s -> (s0,s1), (s1,s2), (s2, s3), ..."
|
|
a, b = tee(iterable)
|
|
next(b, None)
|
|
return izip(a, b)
|
|
|
|
def grouper(n, iterable, padvalue=None):
|
|
"grouper(3, 'abcdefg', 'x') --> ('a','b','c'), ('d','e','f'), ('g','x','x')"
|
|
return izip(*[chain(iterable, repeat(padvalue, n-1))]*n)
|
|
|
|
|
|
\end{verbatim}
|