def make_large_ngroups_bmark(ngroups, func_name, func_args=''):
bmark_name = 'groupby_ngroups_%s_%s' % (ngroups, func_name)
stmt = _stmt_template % ('%s(%s)' % (func_name, func_args))
setup = _setup_template % ngroups
bmark = Benchmark(stmt, setup, start_date=START_DATE)
# MUST set name
bmark.name = bmark_name
return bmark
def make_large_ngroups_bmark(ngroups, func_name, func_args=''):
bmark_name = 'groupby_ngroups_%s_%s' % (ngroups, func_name)
stmt = _stmt_template % ('%s(%s)' % (func_name, func_args))
setup = _setup_template % ngroups
bmark = Benchmark(stmt, setup, start_date=START_DATE)
# MUST set name
bmark.name = bmark_name
return bmark
#### test all groupby funcs ####
setup = basic + """
@test_parallel(num_threads=2)
def pg2():
df.groupby('key')['data'].func()
"""
for f in ['sum','prod','var','count','min','max','mean','last']:
name = "nogil_groupby_{f}_2".format(f=f)
bmark = Benchmark('pg2()', setup.replace('func',f), start_date=datetime(2015, 1, 1))
bmark.name = name
globals()[name] = bmark
del bmark
#### test take_1d ####
setup = basic + """
from pandas.core import common as com
N = 1e7
df = DataFrame({'int64' : np.arange(N,dtype='int64'),
'float64' : np.arange(N,dtype='float64')})
indexer = np.arange(100,len(df)-100)
@test_parallel(num_threads=2)
#### test all groupby funcs ####
setup = basic + """
@test_parallel(num_threads=2)
def pg2():
df.groupby('key')['data'].func()
"""
for f in ['sum','prod','var','count','min','max','mean','last']:
name = "nogil_groupby_{f}_2".format(f=f)
bmark = Benchmark('pg2()', setup.replace('func',f), start_date=datetime(2015, 1, 1))
bmark.name = name
globals()[name] = bmark
del bmark
#### test take_1d ####
setup = basic + """
from pandas.core import common as com
N = 1e7
df = DataFrame({'int64' : np.arange(N,dtype='int64'),
'float64' : np.arange(N,dtype='float64')})
indexer = np.arange(100,len(df)-100)
@test_parallel(num_threads=2)
