How can I obtain the row indices of column-wise maximum values in a 2D NumPy array?

To get the row indices of the maximum elements in each column, you can use NumPy's argmax function along axis 0:

PYTHONCopied
import numpy as np

a = np.array([[2, 3, 1, 9],
              [0, 5, 4, 7],
              [2, 4, 6, 8]])

# Get the index of the maximum element in each column
max_row_indices = np.argmax(a, axis=0)
print(max_row_indices)  # Output: [0 1 2 0]

Here's what's happening:

• np.argmax(a, axis=0) returns the indices of the maximum value along each column (vertical axis).
• In the example array 'a', the maximum values appear in rows 0, 1, 2, and 0 for the first, second, third, and fourth columns respectively.

This concise line is the "numpy magic" to achieve what you're looking for.