summaryrefslogtreecommitdiff
path: root/bench/timeit.py
blob: 7db0dd4fef5cc86e13eb0dd1815033943fc100cb (plain)
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
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
#! /usr/bin/env python

"""Tool for measuring execution time of small code snippets.

This module avoids a number of common traps for measuring execution
times.  See also Tim Peters' introduction to the Algorithms chapter in
the Python Cookbook, published by O'Reilly.

Library usage: see the Timer class.

Command line usage:
    python timeit.py [-n N] [-r N] [-s S] [-t] [-c] [-h] [statement]

Options:
  -n/--number N: how many times to execute 'statement' (default: see below)
  -r/--repeat N: how many times to repeat the timer (default 3)
  -s/--setup S: statement to be executed once initially (default 'pass')
  -t/--time: use time.time() (default on Unix)
  -c/--clock: use time.clock() (default on Windows)
  -v/--verbose: print raw timing results; repeat for more digits precision
  -h/--help: print this usage message and exit
  statement: statement to be timed (default 'pass')

A multi-line statement may be given by specifying each line as a
separate argument; indented lines are possible by enclosing an
argument in quotes and using leading spaces.  Multiple -s options are
treated similarly.

If -n is not given, a suitable number of loops is calculated by trying
successive powers of 10 until the total time is at least 0.2 seconds.

The difference in default timer function is because on Windows,
clock() has microsecond granularity but time()'s granularity is 1/60th
of a second; on Unix, clock() has 1/100th of a second granularity and
time() is much more precise.  On either platform, the default timer
functions measure wall clock time, not the CPU time.  This means that
other processes running on the same computer may interfere with the
timing.  The best thing to do when accurate timing is necessary is to
repeat the timing a few times and use the best time.  The -r option is
good for this; the default of 3 repetitions is probably enough in most
cases.  On Unix, you can use clock() to measure CPU time.

Note: there is a certain baseline overhead associated with executing a
pass statement.  The code here doesn't try to hide it, but you should
be aware of it.  The baseline overhead can be measured by invoking the
program without arguments.  The baseline overhead differs between
Python versions!
"""
from __future__ import division, print_function

try:
    import gc
except ImportError:
    class _fake_gc(object):
        def isenabled(self):
            return None
        def enable(self):
            pass
        def disable(self):
            pass
    gc = _fake_gc()
import sys
import time
try:
    import itertools
except ImportError:
    # Must be an older Python version (see timeit() below)
    itertools = None

__all__ = ["Timer"]

dummy_src_name = "<timeit-src>"
default_number = 1000000
default_repeat = 3

if sys.platform == "win32":
    # On Windows, the best timer is time.clock()
    default_timer = time.clock
else:
    # On most other platforms the best timer is time.time()
    default_timer = time.time

# Don't change the indentation of the template; the reindent() calls
# in Timer.__init__() depend on setup being indented 4 spaces and stmt
# being indented 8 spaces.
template = """
def inner(_it, _timer):
    %(setup)s
    _t0 = _timer()
    for _i in _it:
        %(stmt)s
    _t1 = _timer()
    return _t1 - _t0
"""

def reindent(src, indent):
    """Helper to reindent a multi-line statement."""
    return src.replace("\n", "\n" + " "*indent)

class Timer(object):
    """Class for timing execution speed of small code snippets.

    The constructor takes a statement to be timed, an additional
    statement used for setup, and a timer function.  Both statements
    default to 'pass'; the timer function is platform-dependent (see
    module doc string).

    To measure the execution time of the first statement, use the
    timeit() method.  The repeat() method is a convenience to call
    timeit() multiple times and return a list of results.

    The statements may contain newlines, as long as they don't contain
    multi-line string literals.
    """

    def __init__(self, stmt="pass", setup="pass", timer=default_timer):
        """Constructor.  See class doc string."""
        self.timer = timer
        stmt = reindent(stmt, 8)
        setup = reindent(setup, 4)
        src = template % {'stmt': stmt, 'setup': setup}
        self.src = src # Save for traceback display
        code = compile(src, dummy_src_name, "exec")
        ns = {}
        exec(code, globals(), ns)
        self.inner = ns["inner"]

    def print_exc(self, file=None):
        """Helper to print a traceback from the timed code.

        Typical use:

            t = Timer(...)       # outside the try/except
            try:
                t.timeit(...)    # or t.repeat(...)
            except:
                t.print_exc()

        The advantage over the standard traceback is that source lines
        in the compiled template will be displayed.

        The optional file argument directs where the traceback is
        sent; it defaults to sys.stderr.
        """
        import linecache, traceback
        linecache.cache[dummy_src_name] = (len(self.src),
                                           None,
                                           self.src.split("\n"),
                                           dummy_src_name)
        traceback.print_exc(file=file)

    def timeit(self, number=default_number):
        """Time 'number' executions of the main statement.

        To be precise, this executes the setup statement once, and
        then returns the time it takes to execute the main statement
        a number of times, as a float measured in seconds.  The
        argument is the number of times through the loop, defaulting
        to one million.  The main statement, the setup statement and
        the timer function to be used are passed to the constructor.
        """
        if itertools:
            it = itertools.repeat(None, number)
        else:
            it = [None] * number
        gcold = gc.isenabled()
        gc.disable()
        timing = self.inner(it, self.timer)
        if gcold:
            gc.enable()
        return timing

    def repeat(self, repeat=default_repeat, number=default_number):
        """Call timeit() a few times.

        This is a convenience function that calls the timeit()
        repeatedly, returning a list of results.  The first argument
        specifies how many times to call timeit(), defaulting to 3;
        the second argument specifies the timer argument, defaulting
        to one million.

        Note: it's tempting to calculate mean and standard deviation
        from the result vector and report these.  However, this is not
        very useful.  In a typical case, the lowest value gives a
        lower bound for how fast your machine can run the given code
        snippet; higher values in the result vector are typically not
        caused by variability in Python's speed, but by other
        processes interfering with your timing accuracy.  So the min()
        of the result is probably the only number you should be
        interested in.  After that, you should look at the entire
        vector and apply common sense rather than statistics.
        """
        r = []
        for i in range(repeat):
            t = self.timeit(number)
            r.append(t)
        return r

def main(args=None):
    """Main program, used when run as a script.

    The optional argument specifies the command line to be parsed,
    defaulting to sys.argv[1:].

    The return value is an exit code to be passed to sys.exit(); it
    may be None to indicate success.

    When an exception happens during timing, a traceback is printed to
    stderr and the return value is 1.  Exceptions at other times
    (including the template compilation) are not caught.
    """
    if args is None:
        args = sys.argv[1:]
    import getopt
    try:
        opts, args = getopt.getopt(args, "n:s:r:tcvh",
                                   ["number=", "setup=", "repeat=",
                                    "time", "clock", "verbose", "help"])
    except getopt.error as err:
        print(err)
        print("use -h/--help for command line help")
        return 2
    timer = default_timer
    stmt = "\n".join(args) or "pass"
    number = 0 # auto-determine
    setup = []
    repeat = default_repeat
    verbose = 0
    precision = 3
    for o, a in opts:
        if o in ("-n", "--number"):
            number = int(a)
        if o in ("-s", "--setup"):
            setup.append(a)
        if o in ("-r", "--repeat"):
            repeat = int(a)
            if repeat <= 0:
                repeat = 1
        if o in ("-t", "--time"):
            timer = time.time
        if o in ("-c", "--clock"):
            timer = time.clock
        if o in ("-v", "--verbose"):
            if verbose:
                precision = precision + 1
            verbose = precision + 1
        if o in ("-h", "--help"):
            print(__doc__)
            return 0
    setup = "\n".join(setup) or "pass"
    # Include the current directory, so that local imports work (sys.path
    # contains the directory of this script, rather than the current
    # directory)
    import os
    sys.path.insert(0, os.curdir)
    t = Timer(stmt, setup, timer)
    if number == 0:
        # determine number so that 0.2 <= total time < 2.0
        for i in range(1, 10):
            number = 10**i
            try:
                x = t.timeit(number)
            except:
                t.print_exc()
                return 1
            if verbose:
                print("%d loops -> %.*g secs" % (number, precision, x))
            if x >= 0.2:
                break
    try:
        r = t.repeat(repeat, number)
    except:
        t.print_exc()
        return 1
    best = min(r)
    if verbose:
        print("raw times:", ' '.join(["%.*g" % (precision, x) for x in r]))
    print("%d loops," % number, end=' ')
    usec = best * 1e6 / number
    if usec < 1000:
        print("best of %d: %.*g usec per loop" % (repeat, precision, usec))
    else:
        msec = usec / 1000
        if msec < 1000:
            print("best of %d: %.*g msec per loop" % (repeat, precision, msec))
        else:
            sec = msec / 1000
            print("best of %d: %.*g sec per loop" % (repeat, precision, sec))
    return None

if __name__ == "__main__":
    sys.exit(main())

# Local Variables:
# tab-width:4
# indent-tabs-mode:nil
# End:
# vim: set expandtab tabstop=4 shiftwidth=4: