/usr/share/doc/python-tables-doc/bench/evaluate.py is in python-tables-doc 3.3.0-5.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | from __future__ import print_function
import sys
from time import time
import numpy as np
import tables as tb
from numexpr.necompiler import (
getContext, getExprNames, getType, NumExpr)
shape = (1000, 160000)
#shape = (10,1600)
filters = tb.Filters(complevel=1, complib="blosc", shuffle=0)
ofilters = tb.Filters(complevel=1, complib="blosc", shuffle=0)
#filters = tb.Filters(complevel=1, complib="lzo", shuffle=0)
#ofilters = tb.Filters(complevel=1, complib="lzo", shuffle=0)
# TODO: Makes it sense to add a 's'tring typecode here?
typecode_to_dtype = {'b': 'bool', 'i': 'int32', 'l': 'int64', 'f': 'float32',
'd': 'float64', 'c': 'complex128'}
def _compute(result, function, arguments,
start=None, stop=None, step=None):
"""Compute the `function` over the `arguments` and put the outcome in
`result`"""
arg0 = arguments[0]
if hasattr(arg0, 'maindim'):
maindim = arg0.maindim
(start, stop, step) = arg0._process_range_read(start, stop, step)
nrowsinbuf = arg0.nrowsinbuf
print("nrowsinbuf-->", nrowsinbuf)
else:
maindim = 0
(start, stop, step) = (0, len(arg0), 1)
nrowsinbuf = len(arg0)
shape = list(arg0.shape)
shape[maindim] = len(range(start, stop, step))
# The slices parameter for arg0.__getitem__
slices = [slice(0, dim, 1) for dim in arg0.shape]
# This is a hack to prevent doing unnecessary conversions
# when copying buffers
if hasattr(arg0, 'maindim'):
for arg in arguments:
arg._v_convert = False
# Start the computation itself
for start2 in range(start, stop, step * nrowsinbuf):
# Save the records on disk
stop2 = start2 + step * nrowsinbuf
if stop2 > stop:
stop2 = stop
# Set the proper slice in the main dimension
slices[maindim] = slice(start2, stop2, step)
start3 = (start2 - start) / step
stop3 = start3 + nrowsinbuf
if stop3 > shape[maindim]:
stop3 = shape[maindim]
# Compute the slice to be filled in destination
sl = []
for i in range(maindim):
sl.append(slice(None, None, None))
sl.append(slice(start3, stop3, None))
# Get the values for computing the buffer
values = [arg.__getitem__(tuple(slices)) for arg in arguments]
result[tuple(sl)] = function(*values)
# Activate the conversion again (default)
if hasattr(arg0, 'maindim'):
for arg in arguments:
arg._v_convert = True
return result
def evaluate(ex, out=None, local_dict=None, global_dict=None, **kwargs):
"""Evaluate expression and return an array."""
# First, get the signature for the arrays in expression
context = getContext(kwargs)
names, _ = getExprNames(ex, context)
# Get the arguments based on the names.
call_frame = sys._getframe(1)
if local_dict is None:
local_dict = call_frame.f_locals
if global_dict is None:
global_dict = call_frame.f_globals
arguments = []
types = []
for name in names:
try:
a = local_dict[name]
except KeyError:
a = global_dict[name]
arguments.append(a)
if hasattr(a, 'atom'):
types.append(a.atom)
else:
types.append(a)
# Create a signature
signature = [(name, getType(type_)) for (name, type_) in zip(names, types)]
print("signature-->", signature)
# Compile the expression
compiled_ex = NumExpr(ex, signature, [], **kwargs)
print("fullsig-->", compiled_ex.fullsig)
_compute(out, compiled_ex, arguments)
return
if __name__ == "__main__":
iarrays = 0
oarrays = 0
doprofile = 1
dokprofile = 0
f = tb.open_file("/scratch2/faltet/evaluate.h5", "w")
# Create some arrays
if iarrays:
a = np.ones(shape, dtype='float32')
b = np.ones(shape, dtype='float32') * 2
c = np.ones(shape, dtype='float32') * 3
else:
a = f.create_carray(f.root, 'a', tb.Float32Atom(dflt=1.),
shape=shape, filters=filters)
a[:] = 1.
b = f.create_carray(f.root, 'b', tb.Float32Atom(dflt=2.),
shape=shape, filters=filters)
b[:] = 2.
c = f.create_carray(f.root, 'c', tb.Float32Atom(dflt=3.),
shape=shape, filters=filters)
c[:] = 3.
if oarrays:
out = np.empty(shape, dtype='float32')
else:
out = f.create_carray(f.root, 'out', tb.Float32Atom(),
shape=shape, filters=ofilters)
t0 = time()
if iarrays and oarrays:
#out = ne.evaluate("a*b+c")
out = a * b + c
elif doprofile:
import cProfile as prof
import pstats
prof.run('evaluate("a*b+c", out)', 'evaluate.prof')
stats = pstats.Stats('evaluate.prof')
stats.strip_dirs()
stats.sort_stats('time', 'calls')
stats.print_stats(20)
elif dokprofile:
from cProfile import Profile
import lsprofcalltree
prof = Profile()
prof.run('evaluate("a*b+c", out)')
kcg = lsprofcalltree.KCacheGrind(prof)
ofile = open('evaluate.kcg', 'w')
kcg.output(ofile)
ofile.close()
else:
evaluate("a*b+c", out)
print("Time for evaluate-->", round(time() - t0, 3))
# print "out-->", `out`
# print `out[:]`
f.close()
|