forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathinference.py
164 lines (125 loc) · 9.33 KB
/
inference.py
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
152
153
154
155
156
157
158
159
160
161
162
163
164
from .pandas_vb_common import *
import pandas as pd
class dtype_infer_datetime64(object):
goal_time = 0.2
def setup(self):
self.N = 500000
self.df_int64 = DataFrame(dict(A=np.arange(self.N, dtype='int64'), B=np.arange(self.N, dtype='int64')))
self.df_int32 = DataFrame(dict(A=np.arange(self.N, dtype='int32'), B=np.arange(self.N, dtype='int32')))
self.df_uint32 = DataFrame(dict(A=np.arange(self.N, dtype='uint32'), B=np.arange(self.N, dtype='uint32')))
self.df_float64 = DataFrame(dict(A=np.arange(self.N, dtype='float64'), B=np.arange(self.N, dtype='float64')))
self.df_float32 = DataFrame(dict(A=np.arange(self.N, dtype='float32'), B=np.arange(self.N, dtype='float32')))
self.df_datetime64 = DataFrame(dict(A=pd.to_datetime(np.arange(self.N, dtype='int64'), unit='ms'), B=pd.to_datetime(np.arange(self.N, dtype='int64'), unit='ms')))
self.df_timedelta64 = DataFrame(dict(A=(self.df_datetime64['A'] - self.df_datetime64['B']), B=self.df_datetime64['B']))
def time_dtype_infer_datetime64(self):
(self.df_datetime64['A'] - self.df_datetime64['B'])
class dtype_infer_float32(object):
goal_time = 0.2
def setup(self):
self.N = 500000
self.df_int64 = DataFrame(dict(A=np.arange(self.N, dtype='int64'), B=np.arange(self.N, dtype='int64')))
self.df_int32 = DataFrame(dict(A=np.arange(self.N, dtype='int32'), B=np.arange(self.N, dtype='int32')))
self.df_uint32 = DataFrame(dict(A=np.arange(self.N, dtype='uint32'), B=np.arange(self.N, dtype='uint32')))
self.df_float64 = DataFrame(dict(A=np.arange(self.N, dtype='float64'), B=np.arange(self.N, dtype='float64')))
self.df_float32 = DataFrame(dict(A=np.arange(self.N, dtype='float32'), B=np.arange(self.N, dtype='float32')))
self.df_datetime64 = DataFrame(dict(A=pd.to_datetime(np.arange(self.N, dtype='int64'), unit='ms'), B=pd.to_datetime(np.arange(self.N, dtype='int64'), unit='ms')))
self.df_timedelta64 = DataFrame(dict(A=(self.df_datetime64['A'] - self.df_datetime64['B']), B=self.df_datetime64['B']))
def time_dtype_infer_float32(self):
(self.df_float32['A'] + self.df_float32['B'])
class dtype_infer_float64(object):
goal_time = 0.2
def setup(self):
self.N = 500000
self.df_int64 = DataFrame(dict(A=np.arange(self.N, dtype='int64'), B=np.arange(self.N, dtype='int64')))
self.df_int32 = DataFrame(dict(A=np.arange(self.N, dtype='int32'), B=np.arange(self.N, dtype='int32')))
self.df_uint32 = DataFrame(dict(A=np.arange(self.N, dtype='uint32'), B=np.arange(self.N, dtype='uint32')))
self.df_float64 = DataFrame(dict(A=np.arange(self.N, dtype='float64'), B=np.arange(self.N, dtype='float64')))
self.df_float32 = DataFrame(dict(A=np.arange(self.N, dtype='float32'), B=np.arange(self.N, dtype='float32')))
self.df_datetime64 = DataFrame(dict(A=pd.to_datetime(np.arange(self.N, dtype='int64'), unit='ms'), B=pd.to_datetime(np.arange(self.N, dtype='int64'), unit='ms')))
self.df_timedelta64 = DataFrame(dict(A=(self.df_datetime64['A'] - self.df_datetime64['B']), B=self.df_datetime64['B']))
def time_dtype_infer_float64(self):
(self.df_float64['A'] + self.df_float64['B'])
class dtype_infer_int32(object):
goal_time = 0.2
def setup(self):
self.N = 500000
self.df_int64 = DataFrame(dict(A=np.arange(self.N, dtype='int64'), B=np.arange(self.N, dtype='int64')))
self.df_int32 = DataFrame(dict(A=np.arange(self.N, dtype='int32'), B=np.arange(self.N, dtype='int32')))
self.df_uint32 = DataFrame(dict(A=np.arange(self.N, dtype='uint32'), B=np.arange(self.N, dtype='uint32')))
self.df_float64 = DataFrame(dict(A=np.arange(self.N, dtype='float64'), B=np.arange(self.N, dtype='float64')))
self.df_float32 = DataFrame(dict(A=np.arange(self.N, dtype='float32'), B=np.arange(self.N, dtype='float32')))
self.df_datetime64 = DataFrame(dict(A=pd.to_datetime(np.arange(self.N, dtype='int64'), unit='ms'), B=pd.to_datetime(np.arange(self.N, dtype='int64'), unit='ms')))
self.df_timedelta64 = DataFrame(dict(A=(self.df_datetime64['A'] - self.df_datetime64['B']), B=self.df_datetime64['B']))
def time_dtype_infer_int32(self):
(self.df_int32['A'] + self.df_int32['B'])
class dtype_infer_int64(object):
goal_time = 0.2
def setup(self):
self.N = 500000
self.df_int64 = DataFrame(dict(A=np.arange(self.N, dtype='int64'), B=np.arange(self.N, dtype='int64')))
self.df_int32 = DataFrame(dict(A=np.arange(self.N, dtype='int32'), B=np.arange(self.N, dtype='int32')))
self.df_uint32 = DataFrame(dict(A=np.arange(self.N, dtype='uint32'), B=np.arange(self.N, dtype='uint32')))
self.df_float64 = DataFrame(dict(A=np.arange(self.N, dtype='float64'), B=np.arange(self.N, dtype='float64')))
self.df_float32 = DataFrame(dict(A=np.arange(self.N, dtype='float32'), B=np.arange(self.N, dtype='float32')))
self.df_datetime64 = DataFrame(dict(A=pd.to_datetime(np.arange(self.N, dtype='int64'), unit='ms'), B=pd.to_datetime(np.arange(self.N, dtype='int64'), unit='ms')))
self.df_timedelta64 = DataFrame(dict(A=(self.df_datetime64['A'] - self.df_datetime64['B']), B=self.df_datetime64['B']))
def time_dtype_infer_int64(self):
(self.df_int64['A'] + self.df_int64['B'])
class dtype_infer_timedelta64_1(object):
goal_time = 0.2
def setup(self):
self.N = 500000
self.df_int64 = DataFrame(dict(A=np.arange(self.N, dtype='int64'), B=np.arange(self.N, dtype='int64')))
self.df_int32 = DataFrame(dict(A=np.arange(self.N, dtype='int32'), B=np.arange(self.N, dtype='int32')))
self.df_uint32 = DataFrame(dict(A=np.arange(self.N, dtype='uint32'), B=np.arange(self.N, dtype='uint32')))
self.df_float64 = DataFrame(dict(A=np.arange(self.N, dtype='float64'), B=np.arange(self.N, dtype='float64')))
self.df_float32 = DataFrame(dict(A=np.arange(self.N, dtype='float32'), B=np.arange(self.N, dtype='float32')))
self.df_datetime64 = DataFrame(dict(A=pd.to_datetime(np.arange(self.N, dtype='int64'), unit='ms'), B=pd.to_datetime(np.arange(self.N, dtype='int64'), unit='ms')))
self.df_timedelta64 = DataFrame(dict(A=(self.df_datetime64['A'] - self.df_datetime64['B']), B=self.df_datetime64['B']))
def time_dtype_infer_timedelta64_1(self):
(self.df_timedelta64['A'] + self.df_timedelta64['B'])
class dtype_infer_timedelta64_2(object):
goal_time = 0.2
def setup(self):
self.N = 500000
self.df_int64 = DataFrame(dict(A=np.arange(self.N, dtype='int64'), B=np.arange(self.N, dtype='int64')))
self.df_int32 = DataFrame(dict(A=np.arange(self.N, dtype='int32'), B=np.arange(self.N, dtype='int32')))
self.df_uint32 = DataFrame(dict(A=np.arange(self.N, dtype='uint32'), B=np.arange(self.N, dtype='uint32')))
self.df_float64 = DataFrame(dict(A=np.arange(self.N, dtype='float64'), B=np.arange(self.N, dtype='float64')))
self.df_float32 = DataFrame(dict(A=np.arange(self.N, dtype='float32'), B=np.arange(self.N, dtype='float32')))
self.df_datetime64 = DataFrame(dict(A=pd.to_datetime(np.arange(self.N, dtype='int64'), unit='ms'), B=pd.to_datetime(np.arange(self.N, dtype='int64'), unit='ms')))
self.df_timedelta64 = DataFrame(dict(A=(self.df_datetime64['A'] - self.df_datetime64['B']), B=self.df_datetime64['B']))
def time_dtype_infer_timedelta64_2(self):
(self.df_timedelta64['A'] + self.df_timedelta64['A'])
class dtype_infer_uint32(object):
goal_time = 0.2
def setup(self):
self.N = 500000
self.df_int64 = DataFrame(dict(A=np.arange(self.N, dtype='int64'), B=np.arange(self.N, dtype='int64')))
self.df_int32 = DataFrame(dict(A=np.arange(self.N, dtype='int32'), B=np.arange(self.N, dtype='int32')))
self.df_uint32 = DataFrame(dict(A=np.arange(self.N, dtype='uint32'), B=np.arange(self.N, dtype='uint32')))
self.df_float64 = DataFrame(dict(A=np.arange(self.N, dtype='float64'), B=np.arange(self.N, dtype='float64')))
self.df_float32 = DataFrame(dict(A=np.arange(self.N, dtype='float32'), B=np.arange(self.N, dtype='float32')))
self.df_datetime64 = DataFrame(dict(A=pd.to_datetime(np.arange(self.N, dtype='int64'), unit='ms'), B=pd.to_datetime(np.arange(self.N, dtype='int64'), unit='ms')))
self.df_timedelta64 = DataFrame(dict(A=(self.df_datetime64['A'] - self.df_datetime64['B']), B=self.df_datetime64['B']))
def time_dtype_infer_uint32(self):
(self.df_uint32['A'] + self.df_uint32['B'])
class to_numeric(object):
param_names = ['dtype', 'downcast']
params = [['string-float', 'string-int', 'string-nint', 'datetime64',
'int-list', 'int32'],
[None, 'integer', 'signed', 'unsigned', 'float']]
N = 500000
data_dict = {
'string-int': (['1'] * (N // 2)) + ([2] * (N // 2)),
'string-nint': (['-1'] * (N // 2)) + ([2] * (N // 2)),
'datetime64': np.repeat(np.array(['1970-01-01', '1970-01-02'],
dtype='datetime64[D]'), N),
'string-float': (['1.1'] * (N // 2)) + ([2] * (N // 2)),
'int-list': ([1] * (N // 2)) + ([2] * (N // 2)),
'int32': np.repeat(np.int32(1), N)
}
def setup(self, dtype, downcast):
self.data = self.data_dict[dtype]
def time_downcast(self, dtype, downcast):
pd.to_numeric(self.data, downcast=downcast)