Created
June 14, 2021 22:25
-
-
Save isVoid/8eb9c806bafa36d1665d50a4dde63b04 to your computer and use it in GitHub Desktop.
Using cupy/numpy in get_loc
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import cupy as cp | |
import pandas as pd | |
import cudf | |
def make_non_monotonic_non_unique_multiindex(N): | |
half_n = int(N / 2) | |
l0 = cp.concatenate([cp.arange(0, half_n), cp.full(half_n, 42)]) | |
l1 = cp.concatenate([cp.arange(half_n, N), cp.full(half_n, 42)]) | |
random_order = cp.arange(0, N) | |
cp.random.shuffle(random_order) | |
l0[random_order] = l0 | |
l1[random_order] = l1 | |
l0_arr = l0.get() | |
l1_arr = l1.get() | |
return pd.MultiIndex.from_arrays([l0_arr, l1_arr]) | |
cp.random.seed(0) # reproducibility | |
target = (42, 42) | |
for N in [10**5, 10**6, 10**7, 10**8]: | |
print (N) | |
pidx = make_non_monotonic_non_unique_multiindex(N) | |
gidx = cudf.from_pandas(pidx) | |
gidx.get_loc(target) | |
del pidx, gidx |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment