التنقية المنطقية والفهرسة المتقدمة

import numpy as np

a = np.array([5, 3, 8, 1, 9, 2, 7])
mask = a > 4
print(mask)       # [ True False  True False  True False  True]
print(a[mask])    # [5 8 9 7]

import numpy as np

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

# Elements between 4 and 8 inclusive
result = a[(a >= 4) & (a <= 8)]
print(result)   # [7 6 4 8]

# Elements less than 3 or greater than 7
result2 = a[(a < 3) | (a > 7)]
print(result2)  # [2 9 1 8]

import numpy as np

a = np.array([5, -3, 8, -1, 2, -7])
a[a < 0] = 0    # zero out negatives in-place
print(a)        # [5 0 8 0 2 0]

# Cap values above 6
a[a > 6] = 6
print(a)        # [5 0 6 0 2 0]

import numpy as np

m = np.array([[1, 5], [3, 2], [8, 4], [6, 7]])
# Select rows where first column > 4
mask = m[:, 0] > 4
print(mask)     # [False False  True  True]
print(m[mask])  # [[8 4] [6 7]]

import numpy as np

a = np.array([3, -1, 5, -2, 4])
result = np.where(a >= 0, a, 0)  # keep positives, replace negatives
print(result)  # [3 0 5 0 4]

# Recode: above-average -> 'high', else -> 'low'
labels = np.where(a >= a.mean(), 'high', 'low')
print(labels)  # ['high' 'low' 'high' 'low' 'high']

import numpy as np

a = np.array([10, 20, 30, 40, 50])
idx = np.array([4, 1, 1, 3])
print(a[idx])   # [50 20 20 40]

# 2D index shape -> 2D output
idx2d = np.array([[0, 2], [4, 1]])
print(a[idx2d])  # [[10 30] [50 20]]

import numpy as np

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

# Select elements at (0,2), (1,0), (2,1)
rows = [0, 1, 2]
cols = [2, 0, 1]
print(m[rows, cols])  # [3 4 8]

import numpy as np

m = np.arange(16).reshape(4, 4)
print(m)

# Select rows 0,2 and columns 1,3
ix = np.ix_([0, 2], [1, 3])
print(m[ix])
# [[ 1  3]
#  [ 9 11]]

import numpy as np

a = np.array([0, 3, 0, 5, 0, 7])
print(np.nonzero(a))       # (array([1, 3, 5]),)
print(np.argwhere(a > 0))  # [[1] [3] [5]]

import numpy as np

data = np.array([[1, 2, 3],
                 [4, 5, 6],
                 [7, 8, 9]])
scores = np.array([0.9, 0.3, 0.8])

# Keep high-scoring rows, reorder columns to [2, 0, 1]
high = data[scores > 0.5]
reordered = high[:, [2, 0, 1]]
print(reordered)

import numpy as np

a = np.random.rand(1_000_000)

# Boolean mask -- readable and fast
result = a[a > 0.5]
print('filtered size:', result.size)  # ~500000

# Equivalent with np.where + fancy index
idx = np.where(a > 0.5)[0]
result2 = a[idx]
print('same result:', np.array_equal(result, result2))