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
|
from vbench.api import Benchmark, GitRepo
from datetime import datetime
import os
modules = ['attrs_caching',
'binary_ops',
'ctors',
'frame_ctor',
'frame_methods',
'groupby',
'index_object',
'indexing',
'io_bench',
'hdfstore_bench',
'join_merge',
'miscellaneous',
'panel_ctor',
'packers',
'parser_vb',
'plotting',
'reindex',
'replace',
'sparse',
'strings',
'reshape',
'stat_ops',
'timeseries',
'eval']
by_module = {}
benchmarks = []
for modname in modules:
ref = __import__(modname)
by_module[modname] = [v for v in ref.__dict__.values()
if isinstance(v, Benchmark)]
benchmarks.extend(by_module[modname])
for bm in benchmarks:
assert(bm.name is not None)
import getpass
import sys
USERNAME = getpass.getuser()
if sys.platform == 'darwin':
HOME = '/Users/%s' % USERNAME
else:
HOME = '/home/%s' % USERNAME
try:
import ConfigParser
config = ConfigParser.ConfigParser()
config.readfp(open(os.path.expanduser('~/.vbenchcfg')))
REPO_PATH = config.get('setup', 'repo_path')
REPO_URL = config.get('setup', 'repo_url')
DB_PATH = config.get('setup', 'db_path')
TMP_DIR = config.get('setup', 'tmp_dir')
except:
REPO_PATH = os.path.abspath(os.path.join(os.path.dirname(__file__), "../"))
REPO_URL = 'git@github.com:pydata/pandas.git'
DB_PATH = os.path.join(REPO_PATH, 'vb_suite/benchmarks.db')
TMP_DIR = os.path.join(HOME, 'tmp/vb_pandas')
PREPARE = """
python setup.py clean
"""
BUILD = """
python setup.py build_ext --inplace
"""
dependencies = ['pandas_vb_common.py']
START_DATE = datetime(2010, 6, 1)
# repo = GitRepo(REPO_PATH)
RST_BASE = 'source'
# HACK!
# timespan = [datetime(2011, 1, 1), datetime(2012, 1, 1)]
def generate_rst_files(benchmarks):
import matplotlib as mpl
mpl.use('Agg')
import matplotlib.pyplot as plt
vb_path = os.path.join(RST_BASE, 'vbench')
fig_base_path = os.path.join(vb_path, 'figures')
if not os.path.exists(vb_path):
print('creating %s' % vb_path)
os.makedirs(vb_path)
if not os.path.exists(fig_base_path):
print('creating %s' % fig_base_path)
os.makedirs(fig_base_path)
for bmk in benchmarks:
print('Generating rst file for %s' % bmk.name)
rst_path = os.path.join(RST_BASE, 'vbench/%s.txt' % bmk.name)
fig_full_path = os.path.join(fig_base_path, '%s.png' % bmk.name)
# make the figure
plt.figure(figsize=(10, 6))
ax = plt.gca()
bmk.plot(DB_PATH, ax=ax)
start, end = ax.get_xlim()
plt.xlim([start - 30, end + 30])
plt.savefig(fig_full_path, bbox_inches='tight')
plt.close('all')
fig_rel_path = 'vbench/figures/%s.png' % bmk.name
rst_text = bmk.to_rst(image_path=fig_rel_path)
with open(rst_path, 'w') as f:
f.write(rst_text)
with open(os.path.join(RST_BASE, 'index.rst'), 'w') as f:
print >> f, """
Performance Benchmarks
======================
These historical benchmark graphs were produced with `vbench
<http://github.com/pydata/vbench>`__.
The ``pandas_vb_common`` setup script can be found here_
.. _here: https://github.com/pydata/pandas/tree/master/vb_suite
Produced on a machine with
- Intel Core i7 950 processor
- (K)ubuntu Linux 12.10
- Python 2.7.2 64-bit (Enthought Python Distribution 7.1-2)
- NumPy 1.6.1
.. toctree::
:hidden:
:maxdepth: 3
"""
for modname, mod_bmks in sorted(by_module.items()):
print >> f, ' vb_%s' % modname
modpath = os.path.join(RST_BASE, 'vb_%s.rst' % modname)
with open(modpath, 'w') as mh:
header = '%s\n%s\n\n' % (modname, '=' * len(modname))
print >> mh, header
for bmk in mod_bmks:
print >> mh, bmk.name
print >> mh, '-' * len(bmk.name)
print >> mh, '.. include:: vbench/%s.txt\n' % bmk.name
|
