diff options
Diffstat (limited to 'Doc')
| -rw-r--r-- | Doc/lib/libitertools.tex | 60 |
1 files changed, 60 insertions, 0 deletions
diff --git a/Doc/lib/libitertools.tex b/Doc/lib/libitertools.tex index 6f9f5c6..82912b0 100644 --- a/Doc/lib/libitertools.tex +++ b/Doc/lib/libitertools.tex @@ -130,6 +130,54 @@ by functions or loops that truncate the stream. \end{verbatim} \end{funcdesc} +\begin{funcdesc}{groupby}{iterable\optional{, key}} + Make an iterator that returns consecutive keys and groups from the + \var{iterable}. \var{key} is function computing a key value for each + element. If not specified or is \code{None}, \var{key} defaults to an + identity function (returning the element unchanged). Generally, the + iterable needs to already be sorted on the same key function. + + 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 = [] + 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 = xrange(0) + def __iter__(self): + return self + def next(self): + while self.currkey == self.tgtkey: + self.currvalue = self.it.next() # 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 = self.it.next() # 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}. @@ -346,6 +394,18 @@ Martin Walter Samuele +# 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 = list.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'] + + \end{verbatim} This section shows how itertools can be combined to create other more |