JIYIK CN >

A common concept in the field of machine learning is to normalize a vector or dataset before passing it to the algorithm.

When we talk about normalizing a vector, we say that its vector magnitude is 1, being a unit vector.

In this tutorial, we will convert a numpy array to a unit vector.

Normalize a vector in Python using mathematical formulas

In this method, we will use a mathematical formula to calculate the vector norm of an array. When we divide the array with the norm vector, we get the normalized vector. The following code achieves this.

import numpy as np

v = np.random.rand(10)

normalized_v = v / np.sqrt(np.sum(v ** 2))
print(normalized_v)

Output:

[0.10366807 0.05821296 0.11852538 0.42957961 0.27653372 0.36389277
 0.47575824 0.32059888 0.2721495  0.41856126]

Note that if the length of the vector is 0, this method will return some error.

numpy.linalg.norm()Normalize vectors in Python using function

The module in Python NumPyhas norm()a function that returns the vector norm of an array. The array is then divided by this norm vector to get a normalized vector. For example, in the following code, we will create a random array and use this method to find its normalized form.

import numpy as np

v = np.random.rand(10)
normalized_v = v / np.linalg.norm(v)
print(normalized_v)

Output:

[0.10881785 0.32038649 0.51652046 0.05670539 0.12873248 0.52460815
 0.32929967 0.32699446 0.0753471  0.32043046]

sklearn.preprocessing.normalize()Normalize vectors in Python using function

sklearnThe module has efficient methods that can be used for data preprocessing and other machine learning tools. The function in this library normalize()is usually used with 2-D matrices and provides options for L1 and L2 normalization. The following code uses this function with a 1D array and finds its normalized form.

import numpy as np
from sklearn.preprocessing import normalize

v = np.random.rand(10)
normalized_v = normalize(v[:, np.newaxis], axis=0).ravel()
print(normalized_v)

Output:

[0.19361438 0.36752554 0.26904722 0.10672546 0.32089067 0.48359538
 0.01824837 0.47591181 0.26439268 0.33180998]

The method used in the above method ravel()is used to flatten multidimensional arrays in Python.