forked from apache/arrow
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy patharray.py
More file actions
82 lines (61 loc) · 2.51 KB
/
array.py
File metadata and controls
82 lines (61 loc) · 2.51 KB
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
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
import numpy as np
import pandas as pd
import pyarrow as A
class PyListConversions(object):
param_names = ('size',)
params = (1, 10 ** 5, 10 ** 6, 10 ** 7)
def setup(self, n):
self.data = list(range(n))
def time_from_pylist(self, n):
A.from_pylist(self.data)
def peakmem_from_pylist(self, n):
A.from_pylist(self.data)
class PandasConversionsBase(object):
def setup(self, n, dtype):
if dtype == 'float64_nans':
arr = np.arange(n).astype('float64')
arr[arr % 10 == 0] = np.nan
else:
arr = np.arange(n).astype(dtype)
self.data = pd.DataFrame({'column': arr})
class PandasConversionsToArrow(PandasConversionsBase):
param_names = ('size', 'dtype')
params = ((1, 10 ** 5, 10 ** 6, 10 ** 7), ('int64', 'float64', 'float64_nans', 'str'))
def time_from_series(self, n, dtype):
A.Table.from_pandas(self.data)
def peakmem_from_series(self, n, dtype):
A.Table.from_pandas(self.data)
class PandasConversionsFromArrow(PandasConversionsBase):
param_names = ('size', 'dtype')
params = ((1, 10 ** 5, 10 ** 6, 10 ** 7), ('int64', 'float64', 'float64_nans', 'str'))
def setup(self, n, dtype):
super(PandasConversionsFromArrow, self).setup(n, dtype)
self.arrow_data = A.Table.from_pandas(self.data)
def time_to_series(self, n, dtype):
self.arrow_data.to_pandas()
def peakmem_to_series(self, n, dtype):
self.arrow_data.to_pandas()
class ScalarAccess(object):
param_names = ('size',)
params = (1, 10 ** 5, 10 ** 6, 10 ** 7)
def setUp(self, n):
self._array = A.from_pylist(list(range(n)))
def time_as_py(self, n):
for i in range(n):
self._array[i].as_py()