Skip to content

TST: made pytables vbench much faster #2833

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

TST: made pytables vbench much faster #2833

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
115 changes: 64 additions & 51 deletions vb_suite/hdfstore_bench.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,9 +19,9 @@ def remove(f):
# get from a store

setup1 = common_setup + """
index = [rands(10) for _ in xrange(100000)]
df = DataFrame({'float1' : randn(100000),
'float2' : randn(100000)},
index = [rands(10) for _ in xrange(25000)]
df = DataFrame({'float1' : randn(25000),
'float2' : randn(25000)},
index=index)
remove(f)
store = HDFStore(f)
Expand All @@ -36,9 +36,9 @@ def remove(f):
# write to a store

setup2 = common_setup + """
index = [rands(10) for _ in xrange(100000)]
df = DataFrame({'float1' : randn(100000),
'float2' : randn(100000)},
index = [rands(10) for _ in xrange(25000)]
df = DataFrame({'float1' : randn(25000),
'float2' : randn(25000)},
index=index)
remove(f)
store = HDFStore(f)
Expand All @@ -52,12 +52,12 @@ def remove(f):
# get from a store (mixed)

setup3 = common_setup + """
index = [rands(10) for _ in xrange(100000)]
df = DataFrame({'float1' : randn(100000),
'float2' : randn(100000),
'string1' : ['foo'] * 100000,
'bool1' : [True] * 100000,
'int1' : np.random.randint(0, 1000000, size=100000)},
index = [rands(10) for _ in xrange(25000)]
df = DataFrame({'float1' : randn(25000),
'float2' : randn(25000),
'string1' : ['foo'] * 25000,
'bool1' : [True] * 25000,
'int1' : np.random.randint(0, 250000, size=25000)},
index=index)
remove(f)
store = HDFStore(f)
Expand All @@ -73,12 +73,12 @@ def remove(f):
# write to a store (mixed)

setup4 = common_setup + """
index = [rands(10) for _ in xrange(100000)]
df = DataFrame({'float1' : randn(100000),
'float2' : randn(100000),
'string1' : ['foo'] * 100000,
'bool1' : [True] * 100000,
'int1' : np.random.randint(0, 1000000, size=100000)},
index = [rands(10) for _ in xrange(25000)]
df = DataFrame({'float1' : randn(25000),
'float2' : randn(25000),
'string1' : ['foo'] * 25000,
'bool1' : [True] * 25000,
'int1' : np.random.randint(0, 250000, size=25000)},
index=index)
remove(f)
store = HDFStore(f)
Expand All @@ -92,12 +92,12 @@ def remove(f):
# get from a table (mixed)

setup5 = common_setup + """
index = [rands(10) for _ in xrange(100000)]
df = DataFrame({'float1' : randn(100000),
'float2' : randn(100000),
'string1' : ['foo'] * 100000,
'bool1' : [True] * 100000,
'int1' : np.random.randint(0, 1000000, size=100000)},
index = [rands(10) for _ in xrange(25000)]
df = DataFrame({'float1' : randn(25000),
'float2' : randn(25000),
'string1' : ['foo'] * 25000,
'bool1' : [True] * 25000,
'int1' : np.random.randint(0, 250000, size=25000)},
index=index)

remove(f)
Expand All @@ -114,12 +114,12 @@ def remove(f):
# write to a table (mixed)

setup6 = common_setup + """
index = [rands(10) for _ in xrange(100000)]
df = DataFrame({'float1' : randn(100000),
'float2' : randn(100000),
'string1' : ['foo'] * 100000,
'bool1' : [True] * 100000,
'int1' : np.random.randint(0, 100000, size=100000)},
index = [rands(10) for _ in xrange(25000)]
df = DataFrame({'float1' : randn(25000),
'float2' : randn(25000),
'string1' : ['foo'] * 25000,
'bool1' : [True] * 25000,
'int1' : np.random.randint(0, 25000, size=25000)},
index=index)
remove(f)
store = HDFStore(f)
Expand All @@ -133,9 +133,9 @@ def remove(f):
# select from a table

setup7 = common_setup + """
index = [rands(10) for _ in xrange(100000)]
df = DataFrame({'float1' : randn(100000),
'float2' : randn(100000) },
index = [rands(10) for _ in xrange(25000)]
df = DataFrame({'float1' : randn(25000),
'float2' : randn(25000) },
index=index)

remove(f)
Expand All @@ -152,9 +152,9 @@ def remove(f):
# write to a table

setup8 = common_setup + """
index = [rands(10) for _ in xrange(100000)]
df = DataFrame({'float1' : randn(100000),
'float2' : randn(100000) },
index = [rands(10) for _ in xrange(25000)]
df = DataFrame({'float1' : randn(25000),
'float2' : randn(25000) },
index=index)
remove(f)
store = HDFStore(f)
Expand All @@ -168,7 +168,7 @@ def remove(f):
# get from a table (wide)

setup9 = common_setup + """
df = DataFrame(np.random.randn(100000,200))
df = DataFrame(np.random.randn(25000,100))

remove(f)
store = HDFStore(f)
Expand All @@ -184,7 +184,7 @@ def remove(f):
# write to a table (wide)

setup10 = common_setup + """
df = DataFrame(np.random.randn(100000,200))
df = DataFrame(np.random.randn(25000,100))

remove(f)
store = HDFStore(f)
Expand All @@ -195,16 +195,15 @@ def remove(f):
start_date=start_date)

#----------------------------------------------------------------------
# get from a table (wide) (indexed)
# get from a table (wide)

setup11 = common_setup + """
index = date_range('1/1/2000', periods = 100000)
df = DataFrame(np.random.randn(100000,200), index = index)
index = date_range('1/1/2000', periods = 25000)
df = DataFrame(np.random.randn(25000,100), index = index)

remove(f)
store = HDFStore(f)
store.append('df11',df)
store.create_table_index('df11')
"""

query_store_table_wide = Benchmark(
Expand All @@ -213,18 +212,17 @@ def remove(f):


#----------------------------------------------------------------------
# query from a table (indexed)
# query from a table

setup12 = common_setup + """
index = date_range('1/1/2000', periods = 100000)
df = DataFrame({'float1' : randn(100000),
'float2' : randn(100000) },
index = date_range('1/1/2000', periods = 25000)
df = DataFrame({'float1' : randn(25000),
'float2' : randn(25000) },
index=index)

remove(f)
store = HDFStore(f)
store.append('df12',df)
store.create_table_index('df12')
"""

query_store_table = Benchmark(
Expand All @@ -235,8 +233,8 @@ def remove(f):
# select from a panel table

setup13 = common_setup + """
p = Panel(randn(20, 1000, 1000), items= [ 'Item%03d' % i for i in xrange(20) ],
major_axis=date_range('1/1/2000', periods=1000), minor_axis = [ 'E%03d' % i for i in xrange(1000) ])
p = Panel(randn(20, 1000, 25), items= [ 'Item%03d' % i for i in xrange(20) ],
major_axis=date_range('1/1/2000', periods=1000), minor_axis = [ 'E%03d' % i for i in xrange(25) ])

remove(f)
store = HDFStore(f)
Expand All @@ -252,8 +250,8 @@ def remove(f):
# write to a panel table

setup14 = common_setup + """
p = Panel(randn(20, 1000, 1000), items= [ 'Item%03d' % i for i in xrange(20) ],
major_axis=date_range('1/1/2000', periods=1000), minor_axis = [ 'E%03d' % i for i in xrange(1000) ])
p = Panel(randn(20, 1000, 25), items= [ 'Item%03d' % i for i in xrange(20) ],
major_axis=date_range('1/1/2000', periods=1000), minor_axis = [ 'E%03d' % i for i in xrange(25) ])

remove(f)
store = HDFStore(f)
Expand All @@ -262,3 +260,18 @@ def remove(f):
write_store_table_panel = Benchmark(
"store.append('p2',p)", setup14, cleanup="store.close()",
start_date=start_date)

#----------------------------------------------------------------------
# write to a table (data_columns)

setup15 = common_setup + """
df = DataFrame(np.random.randn(25000,10),columns = [ 'C%03d' % i for i in xrange(10) ])

remove(f)
store = HDFStore(f)
"""

write_store_table_dc = Benchmark(
"store.append('df15',df,data_columns=True)", setup15, cleanup="store.close()",
start_date=start_date)