summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorRaymond Hettinger <python@rcn.com>2004-12-02 08:59:14 (GMT)
committerRaymond Hettinger <python@rcn.com>2004-12-02 08:59:14 (GMT)
commit4901a1f267e9d632f85054ce8b21ff23bff305e1 (patch)
tree27fdb176c85c194cc32d9a72d4812860bd2c4fb6
parentde7b99045d6ee40c2f6b0abbf9d1b5345d9cf15e (diff)
downloadcpython-4901a1f267e9d632f85054ce8b21ff23bff305e1.zip
cpython-4901a1f267e9d632f85054ce8b21ff23bff305e1.tar.gz
cpython-4901a1f267e9d632f85054ce8b21ff23bff305e1.tar.bz2
Add key= argument to heapq.nsmallest() and heapq.nlargest().
-rw-r--r--Doc/lib/libheapq.tex20
-rw-r--r--Lib/heapq.py30
-rw-r--r--Lib/test/test_heapq.py8
-rw-r--r--Misc/NEWS40
4 files changed, 90 insertions, 8 deletions
diff --git a/Doc/lib/libheapq.tex b/Doc/lib/libheapq.tex
index 55ef641..eaf7051 100644
--- a/Doc/lib/libheapq.tex
+++ b/Doc/lib/libheapq.tex
@@ -90,16 +90,24 @@ True
The module also offers two general purpose functions based on heaps.
-\begin{funcdesc}{nlargest}{n, iterable}
+\begin{funcdesc}{nlargest}{n, iterable\optional{, key}}
Return a list with the \var{n} largest elements from the dataset defined
-by \var{iterable}. Equivalent to: \code{sorted(iterable, reverse=True)[:n]}
-\versionadded{2.4}
+by \var{iterable}. \var{key}, if provided, specifies a function of one
+argument that is used to extract a comparison key from each element
+in the iterable: \samp{\var{key}=\function{str.lower}}
+Equivalent to: \samp{sorted(iterable, key=key, reverse=True)[:n]}
+\versionadded{2.4}
+\versionchanged[Added the optional \var{key} argument]{2.5}
\end{funcdesc}
-\begin{funcdesc}{nsmallest}{n, iterable}
+\begin{funcdesc}{nsmallest}{n, iterable\optional{, key}}
Return a list with the \var{n} smallest elements from the dataset defined
-by \var{iterable}. Equivalent to: \code{sorted(iterable)[:n]}
-\versionadded{2.4}
+by \var{iterable}. \var{key}, if provided, specifies a function of one
+argument that is used to extract a comparison key from each element
+in the iterable: \samp{\var{key}=\function{str.lower}}
+Equivalent to: \samp{sorted(iterable, key=key)[:n]}
+\versionadded{2.4}
+\versionchanged[Added the optional \var{key} argument]{2.5}
\end{funcdesc}
Both functions perform best for smaller values of \var{n}. For larger
diff --git a/Lib/heapq.py b/Lib/heapq.py
index b4ebb91..04725cd 100644
--- a/Lib/heapq.py
+++ b/Lib/heapq.py
@@ -129,7 +129,8 @@ From all times, sorting has always been a Great Art! :-)
__all__ = ['heappush', 'heappop', 'heapify', 'heapreplace', 'nlargest',
'nsmallest']
-from itertools import islice, repeat
+from itertools import islice, repeat, count, imap, izip, tee
+from operator import itemgetter
import bisect
def heappush(heap, item):
@@ -307,6 +308,33 @@ try:
except ImportError:
pass
+# Extend the implementations of nsmallest and nlargest to use a key= argument
+_nsmallest = nsmallest
+def nsmallest(n, iterable, key=None):
+ """Find the n smallest elements in a dataset.
+
+ Equivalent to: sorted(iterable, key=key)[:n]
+ """
+ if key is None:
+ return _nsmallest(n, iterable)
+ in1, in2 = tee(iterable)
+ it = izip(imap(key, in1), count(), in2) # decorate
+ result = _nsmallest(n, it)
+ return map(itemgetter(2), result) # undecorate
+
+_nlargest = nlargest
+def nlargest(n, iterable, key=None):
+ """Find the n largest elements in a dataset.
+
+ Equivalent to: sorted(iterable, key=key, reverse=True)[:n]
+ """
+ if key is None:
+ return _nlargest(n, iterable)
+ in1, in2 = tee(iterable)
+ it = izip(imap(key, in1), count(), in2) # decorate
+ result = _nlargest(n, it)
+ return map(itemgetter(2), result) # undecorate
+
if __name__ == "__main__":
# Simple sanity test
heap = []
diff --git a/Lib/test/test_heapq.py b/Lib/test/test_heapq.py
index 68003e7..2da4f8c 100644
--- a/Lib/test/test_heapq.py
+++ b/Lib/test/test_heapq.py
@@ -105,13 +105,19 @@ class TestHeap(unittest.TestCase):
def test_nsmallest(self):
data = [random.randrange(2000) for i in range(1000)]
+ f = lambda x: x * 547 % 2000
for n in (0, 1, 2, 10, 100, 400, 999, 1000, 1100):
self.assertEqual(nsmallest(n, data), sorted(data)[:n])
+ self.assertEqual(nsmallest(n, data, key=f),
+ sorted(data, key=f)[:n])
- def test_largest(self):
+ def test_nlargest(self):
data = [random.randrange(2000) for i in range(1000)]
+ f = lambda x: x * 547 % 2000
for n in (0, 1, 2, 10, 100, 400, 999, 1000, 1100):
self.assertEqual(nlargest(n, data), sorted(data, reverse=True)[:n])
+ self.assertEqual(nlargest(n, data, key=f),
+ sorted(data, key=f, reverse=True)[:n])
#==============================================================================
diff --git a/Misc/NEWS b/Misc/NEWS
index d200265..4029c1d 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -4,6 +4,46 @@ Python News
(editors: check NEWS.help for information about editing NEWS using ReST.)
+What's New in Python 2.5 alpha 1?
+=================================
+
+Core and builtins
+-----------------
+
+
+Extension Modules
+-----------------
+
+
+Library
+-------
+
+- heapq.nsmallest() and heapq.nlargest() now support key= arguments with
+ the same meaning as for list.sort().
+
+
+Build
+-----
+
+
+C API
+-----
+
+
+Tests
+-----
+
+
+Mac
+---
+
+
+
+Tools/Demos
+-----------
+
+
+
What's New in Python 2.4 final?
===============================