# Covariance in Python Numpy

This tutorial will introduce the method to calculate the covariance between two NumPy arrays in Python.

## Covariance With the `numpy.cov()`

Function

In statistics, covariance is the measure of change in one variable with the change in the other variable. Covariance tells us how much one variable changes if another variable is changed. We can calculate the covariance between two NumPy arrays with the `numpy.cov(a1, a2)`

function in Python.

Here, `a1`

represents a collection of values of the first variable, and `a2`

represents a collection of values of the second variable. The `numpy.cov()`

function returns a 2D array in which the value at index `[0][0]`

is the covariance between `a1`

and `a1`

, the value at index `[0][1]`

is the covariance between `a1`

and `a2`

, the value at index `[1][0]`

is the covariance between `a2`

and `a1`

, and the value at index `[1][1]`

is the covariance between `a2`

and `a2`

. See the following code example.

```
import numpy as np
array1 = np.array([1,2,3])
array2 = np.array([2,4,5])
covariance = np.cov(array1, array2)[0][1]
print(covariance)
```

Output:

```
1.5
```

We first created the two NumPy arrays `array1`

and `array2`

with the `np.array()`

function. Then we calculated the covariance with the `np.cov(array1, array2)[0][1]`

and saved the result in the `covariance`

variable. In the end, we printed the value inside the `covariance`

variable.