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
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
|
import warnings
import numpy as np
from pandas import DataFrame, Series
from .pandas_vb_common import tm
class Construction:
params = ["str", "string"]
param_names = ["dtype"]
def setup(self, dtype):
self.data = tm.rands_array(nchars=10 ** 5, size=10)
def time_construction(self, dtype):
Series(self.data, dtype=dtype)
def peakmem_construction(self, dtype):
Series(self.data, dtype=dtype)
class Methods:
def setup(self):
self.s = Series(tm.makeStringIndex(10 ** 5))
def time_center(self):
self.s.str.center(100)
def time_count(self):
self.s.str.count("A")
def time_endswith(self):
self.s.str.endswith("A")
def time_extract(self):
with warnings.catch_warnings(record=True):
self.s.str.extract("(\\w*)A(\\w*)")
def time_findall(self):
self.s.str.findall("[A-Z]+")
def time_find(self):
self.s.str.find("[A-Z]+")
def time_rfind(self):
self.s.str.rfind("[A-Z]+")
def time_get(self):
self.s.str.get(0)
def time_len(self):
self.s.str.len()
def time_join(self):
self.s.str.join(" ")
def time_match(self):
self.s.str.match("A")
def time_normalize(self):
self.s.str.normalize("NFC")
def time_pad(self):
self.s.str.pad(100, side="both")
def time_partition(self):
self.s.str.partition("A")
def time_rpartition(self):
self.s.str.rpartition("A")
def time_replace(self):
self.s.str.replace("A", "\x01\x01")
def time_translate(self):
self.s.str.translate({"A": "\x01\x01"})
def time_slice(self):
self.s.str.slice(5, 15, 2)
def time_startswith(self):
self.s.str.startswith("A")
def time_strip(self):
self.s.str.strip("A")
def time_rstrip(self):
self.s.str.rstrip("A")
def time_lstrip(self):
self.s.str.lstrip("A")
def time_title(self):
self.s.str.title()
def time_upper(self):
self.s.str.upper()
def time_lower(self):
self.s.str.lower()
def time_wrap(self):
self.s.str.wrap(10)
def time_zfill(self):
self.s.str.zfill(10)
class Repeat:
params = ["int", "array"]
param_names = ["repeats"]
def setup(self, repeats):
N = 10 ** 5
self.s = Series(tm.makeStringIndex(N))
repeat = {"int": 1, "array": np.random.randint(1, 3, N)}
self.values = repeat[repeats]
def time_repeat(self, repeats):
self.s.str.repeat(self.values)
class Cat:
params = ([0, 3], [None, ","], [None, "-"], [0.0, 0.001, 0.15])
param_names = ["other_cols", "sep", "na_rep", "na_frac"]
def setup(self, other_cols, sep, na_rep, na_frac):
N = 10 ** 5
mask_gen = lambda: np.random.choice([True, False], N, p=[1 - na_frac, na_frac])
self.s = Series(tm.makeStringIndex(N)).where(mask_gen())
if other_cols == 0:
# str.cat self-concatenates only for others=None
self.others = None
else:
self.others = DataFrame(
{i: tm.makeStringIndex(N).where(mask_gen()) for i in range(other_cols)}
)
def time_cat(self, other_cols, sep, na_rep, na_frac):
# before the concatenation (one caller + other_cols columns), the total
# expected fraction of rows containing any NaN is:
# reduce(lambda t, _: t + (1 - t) * na_frac, range(other_cols + 1), 0)
# for other_cols=3 and na_frac=0.15, this works out to ~48%
self.s.str.cat(others=self.others, sep=sep, na_rep=na_rep)
class Contains:
params = [True, False]
param_names = ["regex"]
def setup(self, regex):
self.s = Series(tm.makeStringIndex(10 ** 5))
def time_contains(self, regex):
self.s.str.contains("A", regex=regex)
class Split:
params = [True, False]
param_names = ["expand"]
def setup(self, expand):
self.s = Series(tm.makeStringIndex(10 ** 5)).str.join("--")
def time_split(self, expand):
self.s.str.split("--", expand=expand)
def time_rsplit(self, expand):
self.s.str.rsplit("--", expand=expand)
class Dummies:
def setup(self):
self.s = Series(tm.makeStringIndex(10 ** 5)).str.join("|")
def time_get_dummies(self):
self.s.str.get_dummies("|")
class Encode:
def setup(self):
self.ser = Series(tm.makeUnicodeIndex())
def time_encode_decode(self):
self.ser.str.encode("utf-8").str.decode("utf-8")
class Slice:
def setup(self):
self.s = Series(["abcdefg", np.nan] * 500000)
def time_vector_slice(self):
# GH 2602
self.s.str[:5]
|
