-
Notifications
You must be signed in to change notification settings - Fork 1
/
simplefctmr.py
224 lines (182 loc) · 6.07 KB
/
simplefctmr.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
"""
Simple *mapper* and *reducer* implemented in :epkg:`Python`
"""
from typing import Callable, Iterable
from itertools import groupby
def mapper(fct: Callable, gen: Iterable) -> Iterable:
"""
Applies function *fct* to a generator.
:param fct: function
:param gen: generator
:return: generator
.. exref::
:title: mapper
:tag: progfonc
.. runpython::
:showcode:
from teachcompute.fctmr import mapper
res = mapper(lambda x: x + 1, [4, 5])
print(list(res))
.. faqref::
:title: Différence entre un itérateur et un générateur ?
:tag: faqprogfonc
Un :epkg:`itérateur` et un :epkg:`générateur` produisent
tous deux des éléments issus d'un ensemble. La différence
vient du fait que qu'un :epkg:`itérateur` parcourt les
éléments d'un ensemble qui existe en mémoire. Un :epkg:`générateur`
produit ou calcule des éléments d'un ensemble qui n'existe
pas en mémoire. Par conséquent, parcourir deux fois un ensemble
avec un itérateur a un coût en :math:`O(n)` alors que pour
un générateur, il faut ajouter le calcul de l'élément une
seconde fois. Le coût est imprévisible et parfois il est
préférable de :epkg:`cacher` les éléments pour le parcourir
plusieurs fois : cela revient à transformer un :epkg:`générateur`
en :epkg:`itérateur`. Un générateur est souvent défini comme suit
en :epkg:`Python` :
.. runpython::
:showcode:
def generate(some_iterator):
for el in some_iterator:
yield el
g = generate([4, 5])
print(list(g))
print(g.__class__.__name__)
"""
return map(fct, gen)
def take(gen: Iterable, count: int = 5, skip: int = 0) -> Iterable:
"""
Skips and takes elements from a generator.
:param gen: generator
:param count: number of elements to consider
:param skip: skip the first elements
:return: generator
.. exref::
:title: take
:tag: progfonc
.. runpython::
:showcode:
from teachcompute.fctmr import take
res = take([4, 5, 6, 7, 8, 9], 2, 2)
print(list(res))
"""
took = 0
for i, el in enumerate(gen):
if i < skip:
continue
if took >= count:
break
yield el
took += 1
def ffilter(fct: Callable, gen: Iterable) -> Iterable:
"""
Filters out elements from a generator.
:param fct: function
:param gen: generator
:return: generator
.. exref::
:title: filter
:tag: progfonc
.. runpython::
:showcode:
from teachcompute.fctmr import ffilter
res = ffilter(lambda x: x % 2 == 0, [4, 5])
print(list(res))
"""
return filter(fct, gen)
def reducer(
fctkey: Callable, gen: Iterable, asiter: bool = True, sort: bool = True
) -> Iterable:
"""
Implements a reducer.
:param fctkey: function which returns the key
:param gen: generator
:param asiter: returns an iterator on each element of the group
of the group itself
:param sort: sort elements by key before grouping
:return: generator
.. exref::
:title: reducer
:tag: progfonc
.. runpython::
:showcode:
from teachcompute.fctmr import reducer
res = reducer(lambda x: x[0], [
('a', 1), ('b', 2), ('a', 3)], asiter=False)
print(list(res))
"""
if sort:
new_gen = map(lambda x: x[1], sorted(map(lambda el: (fctkey(el), el), gen)))
gr = groupby(new_gen, fctkey)
else:
gr = groupby(gen, fctkey)
if asiter:
# Cannot return gr. Python is confused when yield and return
# are used in the same function.
for _ in gr:
yield _
else:
for key, it in gr:
yield key, list(it)
def combiner(
fctkey1: Callable,
gen1: Iterable,
fctkey2: Callable,
gen2: Iterable,
how: str = "inner",
) -> Iterable:
"""
Joins (or combines) two generators.
The function is written based on two reducers.
The function is more efficient if the groups
of the second ensemble *gen2* are shorter
as each of them will be held in memory.
:param fctkey1: function which returns the key for gen1
:param gen1: generator for the first element
:param fctkey2: function which returns the key for gen2
:param gen2: generator for the second element
:param how: *inner*, *outer*, *left*, right*
:return: generator
.. exref::
:title: combiner or join
:tag: progfonc
.. runpython::
:showcode:
from teachcompute.fctmr import combiner
def c0(el):
return el[0]
ens1 = [('a', 1), ('b', 2), ('a', 3)]
ens2 = [('a', 10), ('b', 20), ('a', 30)]
res = combiner(c0, ens1, c0, ens2)
print(list(res))
"""
gr1 = reducer(fctkey1, gen1, asiter=True, sort=True)
gr2 = reducer(fctkey2, gen2, asiter=False, sort=True)
def fetch_next(it):
"local function"
try:
return next(it)
except StopIteration:
return None, None
k1, g1 = fetch_next(gr1)
k2, g2 = fetch_next(gr2)
while k1 is not None or k2 is not None:
if k1 is None or (k2 is not None and k2 < k1):
if how in ("outer", "right"):
for el in g2:
yield None, el
k2, g2 = fetch_next(gr2)
else:
break
elif k2 is None or k1 < k2:
if how in ("outer", "left"):
for el in g1:
yield el, None
k1, g1 = fetch_next(gr1)
else:
break
elif k1 == k2:
for el1 in g1:
for el2 in g2:
yield el1, el2
k1, g1 = fetch_next(gr1)
k2, g2 = fetch_next(gr2)