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
|
from datetime import datetime
import numpy as np
import pandas.util.testing as tm
from pandas import Series, date_range, NaT
from .pandas_vb_common import setup # noqa
class SeriesConstructor(object):
goal_time = 0.2
params = [None, 'dict']
param_names = ['data']
def setup(self, data):
self.idx = date_range(start=datetime(2015, 10, 26),
end=datetime(2016, 1, 1),
freq='50s')
dict_data = dict(zip(self.idx, range(len(self.idx))))
self.data = None if data is None else dict_data
def time_constructor(self, data):
Series(data=self.data, index=self.idx)
class IsIn(object):
goal_time = 0.2
params = ['int64', 'object']
param_names = ['dtype']
def setup(self, dtype):
self.s = Series(np.random.randint(1, 10, 100000)).astype(dtype)
self.values = [1, 2]
def time_isin(self, dtypes):
self.s.isin(self.values)
class NSort(object):
goal_time = 0.2
params = ['last', 'first']
param_names = ['keep']
def setup(self, keep):
self.s = Series(np.random.randint(1, 10, 100000))
def time_nlargest(self, keep):
self.s.nlargest(3, keep=keep)
def time_nsmallest(self, keep):
self.s.nsmallest(3, keep=keep)
class Dropna(object):
goal_time = 0.2
params = ['int', 'datetime']
param_names = ['dtype']
def setup(self, dtype):
N = 10**6
data = {'int': np.random.randint(1, 10, N),
'datetime': date_range('2000-01-01', freq='S', periods=N)}
self.s = Series(data[dtype])
if dtype == 'datetime':
self.s[np.random.randint(1, N, 100)] = NaT
def time_dropna(self, dtype):
self.s.dropna()
class Map(object):
goal_time = 0.2
params = ['dict', 'Series']
param_names = 'mapper'
def setup(self, mapper):
map_size = 1000
map_data = Series(map_size - np.arange(map_size))
self.map_data = map_data if mapper == 'Series' else map_data.to_dict()
self.s = Series(np.random.randint(0, map_size, 10000))
def time_map(self, mapper):
self.s.map(self.map_data)
class Clip(object):
goal_time = 0.2
def setup(self):
self.s = Series(np.random.randn(50))
def time_clip(self):
self.s.clip(0, 1)
class ValueCounts(object):
goal_time = 0.2
params = ['int', 'float', 'object']
param_names = ['dtype']
def setup(self, dtype):
self.s = Series(np.random.randint(0, 1000, size=100000)).astype(dtype)
def time_value_counts(self, dtype):
self.s.value_counts()
class Dir(object):
goal_time = 0.2
def setup(self):
self.s = Series(index=tm.makeStringIndex(10000))
def time_dir_strings(self):
dir(self.s)
class SeriesGetattr(object):
# https://github.com/pandas-dev/pandas/issues/19764
goal_time = 0.2
def setup(self):
self.s = Series(1,
index=date_range("2012-01-01", freq='s',
periods=int(1e6)))
def time_series_datetimeindex_repr(self):
getattr(self.s, 'a', None)
|
