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
|
from vbench.benchmark import Benchmark
from datetime import datetime
common_setup = """from pandas_vb_common import *
"""
#----------------------------------------------------------------------
# Creation from nested dict
setup = common_setup + """
N, K = 5000, 50
index = [rands(10) for _ in xrange(N)]
columns = [rands(10) for _ in xrange(K)]
frame = DataFrame(np.random.randn(N, K), index=index, columns=columns)
try:
data = frame.to_dict()
except:
data = frame.toDict()
some_dict = data.values()[0]
dict_list = [dict(zip(columns, row)) for row in frame.values]
"""
frame_ctor_nested_dict = Benchmark("DataFrame(data)", setup)
# From JSON-like stuff
frame_ctor_list_of_dict = Benchmark("DataFrame(dict_list)", setup,
start_date=datetime(2011, 12, 20))
series_ctor_from_dict = Benchmark("Series(some_dict)", setup)
# nested dict, integer indexes, regression described in #621
setup = common_setup + """
data = dict((i,dict((j,float(j)) for j in xrange(100))) for i in xrange(2000))
"""
frame_ctor_nested_dict_int64 = Benchmark("DataFrame(data)", setup)
# from a mi-series
setup = common_setup + """
mi = MultiIndex.from_tuples([(x,y) for x in range(100) for y in range(100)])
s = Series(randn(10000), index=mi)
"""
frame_from_series = Benchmark("DataFrame(s)", setup)
#----------------------------------------------------------------------
# get_numeric_data
setup = common_setup + """
df = DataFrame(randn(10000, 25))
df['foo'] = 'bar'
df['bar'] = 'baz'
df = df.consolidate()
"""
frame_get_numeric_data = Benchmark('df._get_numeric_data()', setup,
start_date=datetime(2011, 11, 1))
|
