forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathalgorithms.py
124 lines (89 loc) · 3.53 KB
/
algorithms.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
from importlib import import_module
import numpy as np
import pandas as pd
from pandas.util import testing as tm
for imp in ['pandas.util', 'pandas.tools.hashing']:
try:
hashing = import_module(imp)
break
except:
pass
class Algorithms(object):
goal_time = 0.2
def setup(self):
N = 100000
np.random.seed(1234)
self.int_unique = pd.Int64Index(np.arange(N * 5))
# cache is_unique
self.int_unique.is_unique
self.int = pd.Int64Index(np.arange(N).repeat(5))
self.float = pd.Float64Index(np.random.randn(N).repeat(5))
# Convenience naming.
self.checked_add = pd.core.algorithms.checked_add_with_arr
self.arr = np.arange(1000000)
self.arrpos = np.arange(1000000)
self.arrneg = np.arange(-1000000, 0)
self.arrmixed = np.array([1, -1]).repeat(500000)
self.strings = tm.makeStringIndex(100000)
self.arr_nan = np.random.choice([True, False], size=1000000)
self.arrmixed_nan = np.random.choice([True, False], size=1000000)
# match
self.uniques = tm.makeStringIndex(1000).values
self.all = self.uniques.repeat(10)
def time_factorize_string(self):
self.strings.factorize()
def time_factorize_int(self):
self.int.factorize()
def time_factorize_float(self):
self.int.factorize()
def time_duplicated_int_unique(self):
self.int_unique.duplicated()
def time_duplicated_int(self):
self.int.duplicated()
def time_duplicated_float(self):
self.float.duplicated()
def time_match_strings(self):
pd.match(self.all, self.uniques)
def time_add_overflow_pos_scalar(self):
self.checked_add(self.arr, 1)
def time_add_overflow_neg_scalar(self):
self.checked_add(self.arr, -1)
def time_add_overflow_zero_scalar(self):
self.checked_add(self.arr, 0)
def time_add_overflow_pos_arr(self):
self.checked_add(self.arr, self.arrpos)
def time_add_overflow_neg_arr(self):
self.checked_add(self.arr, self.arrneg)
def time_add_overflow_mixed_arr(self):
self.checked_add(self.arr, self.arrmixed)
def time_add_overflow_first_arg_nan(self):
self.checked_add(self.arr, self.arrmixed, arr_mask=self.arr_nan)
def time_add_overflow_second_arg_nan(self):
self.checked_add(self.arr, self.arrmixed, b_mask=self.arrmixed_nan)
def time_add_overflow_both_arg_nan(self):
self.checked_add(self.arr, self.arrmixed, arr_mask=self.arr_nan,
b_mask=self.arrmixed_nan)
class Hashing(object):
goal_time = 0.2
def setup(self):
N = 100000
self.df = pd.DataFrame(
{'A': pd.Series(tm.makeStringIndex(100).take(
np.random.randint(0, 100, size=N))),
'B': pd.Series(tm.makeStringIndex(10000).take(
np.random.randint(0, 10000, size=N))),
'D': np.random.randn(N),
'E': np.arange(N),
'F': pd.date_range('20110101', freq='s', periods=N),
'G': pd.timedelta_range('1 day', freq='s', periods=N),
})
self.df['C'] = self.df['B'].astype('category')
self.df.iloc[10:20] = np.nan
def time_frame(self):
hashing.hash_pandas_object(self.df)
def time_series_int(self):
hashing.hash_pandas_object(self.df.E)
def time_series_string(self):
hashing.hash_pandas_object(self.df.B)
def time_series_categorical(self):
hashing.hash_pandas_object(self.df.C)