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
|
from importlib import import_module
import numpy as np
import pandas as pd
from .pandas_vb_common import tm
for imp in ["pandas.util", "pandas.tools.hashing"]:
try:
hashing = import_module(imp)
break
except (ImportError, TypeError, ValueError):
pass
class Factorize:
params = [
[True, False],
[True, False],
[
"int",
"uint",
"float",
"object",
"datetime64[ns]",
"datetime64[ns, tz]",
"Int64",
"boolean",
"string[pyarrow]",
],
]
param_names = ["unique", "sort", "dtype"]
def setup(self, unique, sort, dtype):
N = 10**5
string_index = tm.makeStringIndex(N)
string_arrow = None
if dtype == "string[pyarrow]":
try:
string_arrow = pd.array(string_index, dtype="string[pyarrow]")
except ImportError:
raise NotImplementedError
data = {
"int": pd.Index(np.arange(N), dtype="int64"),
"uint": pd.Index(np.arange(N), dtype="uint64"),
"float": pd.Index(np.random.randn(N), dtype="float64"),
"object": string_index,
"datetime64[ns]": pd.date_range("2011-01-01", freq="H", periods=N),
"datetime64[ns, tz]": pd.date_range(
"2011-01-01", freq="H", periods=N, tz="Asia/Tokyo"
),
"Int64": pd.array(np.arange(N), dtype="Int64"),
"boolean": pd.array(np.random.randint(0, 2, N), dtype="boolean"),
"string[pyarrow]": string_arrow,
}[dtype]
if not unique:
data = data.repeat(5)
self.data = data
def time_factorize(self, unique, sort, dtype):
pd.factorize(self.data, sort=sort)
class Duplicated:
params = [
[True, False],
["first", "last", False],
["int", "uint", "float", "string", "datetime64[ns]", "datetime64[ns, tz]"],
]
param_names = ["unique", "keep", "dtype"]
def setup(self, unique, keep, dtype):
N = 10**5
data = {
"int": pd.Index(np.arange(N), dtype="int64"),
"uint": pd.Index(np.arange(N), dtype="uint64"),
"float": pd.Index(np.random.randn(N), dtype="float64"),
"string": tm.makeStringIndex(N),
"datetime64[ns]": pd.date_range("2011-01-01", freq="H", periods=N),
"datetime64[ns, tz]": pd.date_range(
"2011-01-01", freq="H", periods=N, tz="Asia/Tokyo"
),
}[dtype]
if not unique:
data = data.repeat(5)
self.idx = data
# cache is_unique
self.idx.is_unique
def time_duplicated(self, unique, keep, dtype):
self.idx.duplicated(keep=keep)
class Hashing:
def setup_cache(self):
N = 10**5
df = pd.DataFrame(
{
"strings": pd.Series(
tm.makeStringIndex(10000).take(np.random.randint(0, 10000, size=N))
),
"floats": np.random.randn(N),
"ints": np.arange(N),
"dates": pd.date_range("20110101", freq="s", periods=N),
"timedeltas": pd.timedelta_range("1 day", freq="s", periods=N),
}
)
df["categories"] = df["strings"].astype("category")
df.iloc[10:20] = np.nan
return df
def time_frame(self, df):
hashing.hash_pandas_object(df)
def time_series_int(self, df):
hashing.hash_pandas_object(df["ints"])
def time_series_string(self, df):
hashing.hash_pandas_object(df["strings"])
def time_series_float(self, df):
hashing.hash_pandas_object(df["floats"])
def time_series_categorical(self, df):
hashing.hash_pandas_object(df["categories"])
def time_series_timedeltas(self, df):
hashing.hash_pandas_object(df["timedeltas"])
def time_series_dates(self, df):
hashing.hash_pandas_object(df["dates"])
class Quantile:
params = [
[0, 0.5, 1],
["linear", "nearest", "lower", "higher", "midpoint"],
["float", "int", "uint"],
]
param_names = ["quantile", "interpolation", "dtype"]
def setup(self, quantile, interpolation, dtype):
N = 10**5
data = {
"int": np.arange(N),
"uint": np.arange(N).astype(np.uint64),
"float": np.random.randn(N),
}
self.idx = pd.Series(data[dtype].repeat(5))
def time_quantile(self, quantile, interpolation, dtype):
self.idx.quantile(quantile, interpolation=interpolation)
class SortIntegerArray:
params = [10**3, 10**5]
def setup(self, N):
data = np.arange(N, dtype=float)
data[40] = np.nan
self.array = pd.array(data, dtype="Int64")
def time_argsort(self, N):
self.array.argsort()
from .pandas_vb_common import setup # noqa: F401 isort:skip
|
