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
|
import warnings
import numpy as np
from pandas import DataFrame, Panel, date_range, HDFStore, read_hdf
import pandas.util.testing as tm
from ..pandas_vb_common import BaseIO, setup # noqa
class HDFStoreDataFrame(BaseIO):
goal_time = 0.2
def setup(self):
N = 25000
index = tm.makeStringIndex(N)
self.df = DataFrame({'float1': np.random.randn(N),
'float2': np.random.randn(N)},
index=index)
self.df_mixed = DataFrame({'float1': np.random.randn(N),
'float2': np.random.randn(N),
'string1': ['foo'] * N,
'bool1': [True] * N,
'int1': np.random.randint(0, N, size=N)},
index=index)
self.df_wide = DataFrame(np.random.randn(N, 100))
self.start_wide = self.df_wide.index[10000]
self.stop_wide = self.df_wide.index[15000]
self.df2 = DataFrame({'float1': np.random.randn(N),
'float2': np.random.randn(N)},
index=date_range('1/1/2000', periods=N))
self.start = self.df2.index[10000]
self.stop = self.df2.index[15000]
self.df_wide2 = DataFrame(np.random.randn(N, 100),
index=date_range('1/1/2000', periods=N))
self.df_dc = DataFrame(np.random.randn(N, 10),
columns=['C%03d' % i for i in range(10)])
self.fname = '__test__.h5'
self.store = HDFStore(self.fname)
self.store.put('fixed', self.df)
self.store.put('fixed_mixed', self.df_mixed)
self.store.append('table', self.df2)
self.store.append('table_mixed', self.df_mixed)
self.store.append('table_wide', self.df_wide)
self.store.append('table_wide2', self.df_wide2)
def teardown(self):
self.store.close()
self.remove(self.fname)
def time_read_store(self):
self.store.get('fixed')
def time_read_store_mixed(self):
self.store.get('fixed_mixed')
def time_write_store(self):
self.store.put('fixed_write', self.df)
def time_write_store_mixed(self):
self.store.put('fixed_mixed_write', self.df_mixed)
def time_read_store_table_mixed(self):
self.store.select('table_mixed')
def time_write_store_table_mixed(self):
self.store.append('table_mixed_write', self.df_mixed)
def time_read_store_table(self):
self.store.select('table')
def time_write_store_table(self):
self.store.append('table_write', self.df)
def time_read_store_table_wide(self):
self.store.select('table_wide')
def time_write_store_table_wide(self):
self.store.append('table_wide_write', self.df_wide)
def time_write_store_table_dc(self):
self.store.append('table_dc_write', self.df_dc, data_columns=True)
def time_query_store_table_wide(self):
self.store.select('table_wide', where="index > self.start_wide and "
"index < self.stop_wide")
def time_query_store_table(self):
self.store.select('table', where="index > self.start and "
"index < self.stop")
def time_store_repr(self):
repr(self.store)
def time_store_str(self):
str(self.store)
def time_store_info(self):
self.store.info()
class HDFStorePanel(BaseIO):
goal_time = 0.2
def setup(self):
self.fname = '__test__.h5'
with warnings.catch_warnings(record=True):
self.p = Panel(np.random.randn(20, 1000, 25),
items=['Item%03d' % i for i in range(20)],
major_axis=date_range('1/1/2000', periods=1000),
minor_axis=['E%03d' % i for i in range(25)])
self.store = HDFStore(self.fname)
self.store.append('p1', self.p)
def teardown(self):
self.store.close()
self.remove(self.fname)
def time_read_store_table_panel(self):
with warnings.catch_warnings(record=True):
self.store.select('p1')
def time_write_store_table_panel(self):
with warnings.catch_warnings(record=True):
self.store.append('p2', self.p)
class HDF(BaseIO):
goal_time = 0.2
params = ['table', 'fixed']
param_names = ['format']
def setup(self, format):
self.fname = '__test__.h5'
N = 100000
C = 5
self.df = DataFrame(np.random.randn(N, C),
columns=['float{}'.format(i) for i in range(C)],
index=date_range('20000101', periods=N, freq='H'))
self.df['object'] = tm.makeStringIndex(N)
self.df.to_hdf(self.fname, 'df', format=format)
def time_read_hdf(self, format):
read_hdf(self.fname, 'df')
def time_write_hdf(self, format):
self.df.to_hdf(self.fname, 'df', format=format)
|
