jjerphan

jjerphan

jjerphan

Does self.distance_metric.rdist use a v-table look up? (I am curious. This may not be actionable)

Yes, it does.

---

V-table implementation details

jjerphan

import sys                                                                                                                                                                                                                                                    
import cudf                                                                                                                                                                                                                                                   
import joblib                                                                                                                                                                                                                                                 
import numpy as np                                                                                                                                                                                                                                            
impo

jjerphan

%%cython --annotate
#cython: boundscheck=False
#cython: wraparound=False
#cython: cdivision=True

## Adapted from sklearn.neighbors.Mahalanobis
# https://github.com/scikit-learn/scikit-learn/blob/main/sklearn/neighbors/_dist_metrics.pyx#L669

import numpy as np
cimport numpy as np

jjerphan

# Cython compile instructions
import numpy
from setuptools import setup, Extension
from Cython.Build import build_ext

# To compile, use
# python setup.py build --inplace

extensions = [
        Extension("stdvect_to_ndarray",

jjerphan

import numpy as np
from sklearn.neighbors import DistanceMetric
from .common import Benchmark

class DistanceMetricBenchmark(Benchmark):

    param_names = ["n", "d"]
    params = ([100, 1000, 10_000], [5, 10, 100])

    def setup(self, n, d):

jjerphan

from sklearn.feature_selection import mutual_info_regression, mutual_info_classif
from sklearn.neighbors import KernelDensity, NearestNeighbors
from .common import Benchmark
from sklearn.datasets import make_classification, make_regression


class RemovedCheckBenchmarks(Benchmark):

    param_names = ['n', 'd']
    params = (

jjerphan

import numpy as np
from scipy.linalg import cho_solve, cholesky
from sklearn.gaussian_process.kernels import RBF
from sklearn.datasets import make_regression
from sklearn.model_selection import train_test_split

kernel = RBF(length_scale=1.0)
X, y = make_regression()

X_train, X_test, y_train, y_test = train_test_split(X, y)

jjerphan

import numpy as np

from sklearn.neighbors import KDTree, BallTree
from .common import Benchmark


class BinaryTreeStatsBenchmark(Benchmark):
    """
    Base class for BinaryTree benchmarks for removing statistics.
    """