Vbench performance benchmarks for pandas

io_bench

write_csv_standard

Benchmark setup

from pandas_vb_common import *

index = [rands(10) for _ in xrange(10000)]
df = DataFrame({'float1' : randn(10000),
                'float2' : randn(10000),
                'string1' : ['foo'] * 10000,
                'bool1' : [True] * 10000,
                'int1' : np.random.randint(0, 100000, size=10000)},
               index=index)

Benchmark statement

df.to_csv('__test__.csv')

Performance graph

_images/write_csv_standard.png

read_csv_standard

Benchmark setup

from pandas_vb_common import *

index = [rands(10) for _ in xrange(10000)]
df = DataFrame({'float1' : randn(10000),
                'float2' : randn(10000),
                'string1' : ['foo'] * 10000,
                'bool1' : [True] * 10000,
                'int1' : np.random.randint(0, 100000, size=10000)},
               index=index)
df.to_csv('__test__.csv')

Benchmark statement

read_csv('__test__.csv')

Performance graph

_images/read_csv_standard.png