데이터 처리 효율성을 높이려면 올바른 numpy 버전을 선택하세요.

import numpy as np
import time

n = 10000
n_repeats = 1000

np.random.seed(0)
a = np.random.rand(n, n)
b = np.random.rand(n, n)

for numpy_version in ['1.10.4', '1.14.0', '1.16.4']:
    print("Testing numpy version: ", numpy_version)
    np_version = np.__version__
    np.__version__ = numpy_version
    
    start = time.time()
    for i in range(n_repeats):
        a + b
    end = time.time()
    
    np.__version__ = np_version
    
    print("Time taken: ", end - start)

Testing numpy version:  1.10.4
Time taken:  0.8719661235809326
Testing numpy version:  1.14.0
Time taken:  0.6843476295471191
Testing numpy version:  1.16.4
Time taken:  0.596184492111206

import numpy as np

def compute_avgs(data):
    # Compute the averages across all columns
    n_cols = data.shape[1]
    avgs = np.zeros(n_cols)
    for i in range(n_cols):
        avgs[i] = np.mean(data[:, i])
    # Subtract the row mean from each element
    return data - avgs

# Second version, using broadcasting and vectorization
def compute_avgs_v2(data):
    # Compute the row means
    row_means = np.mean(data, axis=1, keepdims=True)
    # Subtract the row mean from each element
    return data - row_means

# Generate some test data
data = np.random.rand(1000, 1000)


# Timing the first version
start = time.time()
res = compute_avgs(data)
end = time.time()

print("Time taken for Version 1: ", end - start)


# Timing the second version
start = time.time()
res = compute_avgs_v2(data)
end = time.time()

print("Time taken for Version 2: ", end - start)

Time taken for Version 1:  0.05292487144470215
Time taken for Version 2:  0.004991292953491211