Calculating correlation for data with NaN using multiple cores

nancorrmp_correlation.py

import pandas as pd
import numpy as np

from nancorrmp.nancorrmp import NaNCorrMp

dataset = pd.DataFrame([
    [2, 3000, 0, 0],
    [10, 0, 100, float('inf')],
    [1, 0, -1150, float('-inf')],
    [1, 0, 0, float('NaN')],
    [4, 4000, -800, -0.2]
])

NaNCorrMp.calculate(dataset, n_jobs=4)
# >>>
#            0         1         2    3
#  0  1.000000 -0.108525  0.385631 -1.0
#  1 -0.108525  1.000000 -0.137864 -1.0
#  2  0.385631 -0.137864  1.000000  1.0
#  3 -1.000000 -1.000000  1.000000  1.0

       
dataset.corr()
#  >>>
#            0         1         2    3
#  0  1.000000 -0.108525  0.385631 -1.0
#  1 -0.108525  1.000000 -0.137864 -1.0
#  2  0.385631 -0.137864  1.000000  1.0
#  3 -1.000000 -1.000000  1.000000  1.0