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
|
import numpy as np
import pandas as pd
try:
import pandas.core.computation.expressions as expr
except ImportError:
import pandas.computation.expressions as expr
class Eval:
params = [["numexpr", "python"], [1, "all"]]
param_names = ["engine", "threads"]
def setup(self, engine, threads):
self.df = pd.DataFrame(np.random.randn(20000, 100))
self.df2 = pd.DataFrame(np.random.randn(20000, 100))
self.df3 = pd.DataFrame(np.random.randn(20000, 100))
self.df4 = pd.DataFrame(np.random.randn(20000, 100))
if threads == 1:
expr.set_numexpr_threads(1)
def time_add(self, engine, threads):
pd.eval("self.df + self.df2 + self.df3 + self.df4", engine=engine)
def time_and(self, engine, threads):
pd.eval(
"(self.df > 0) & (self.df2 > 0) & (self.df3 > 0) & (self.df4 > 0)",
engine=engine,
)
def time_chained_cmp(self, engine, threads):
pd.eval("self.df < self.df2 < self.df3 < self.df4", engine=engine)
def time_mult(self, engine, threads):
pd.eval("self.df * self.df2 * self.df3 * self.df4", engine=engine)
def teardown(self, engine, threads):
expr.set_numexpr_threads()
class Query:
def setup(self):
N = 10**6
halfway = (N // 2) - 1
index = pd.date_range("20010101", periods=N, freq="min")
s = pd.Series(index)
self.ts = s.iloc[halfway]
self.df = pd.DataFrame({"a": np.random.randn(N), "dates": index}, index=index)
data = np.random.randn(N)
self.min_val = data.min()
self.max_val = data.max()
def time_query_datetime_index(self):
self.df.query("index < @self.ts")
def time_query_datetime_column(self):
self.df.query("dates < @self.ts")
def time_query_with_boolean_selection(self):
self.df.query("(a >= @self.min_val) & (a <= @self.max_val)")
from .pandas_vb_common import setup # noqa: F401 isort:skip
|
