Published on August 3, 2022

By Jayant Verma

Developer and author at DigitalOcean.

While we believe that this content benefits our community, we have not yet thoroughly reviewed it. If you have any suggestions for improvements, please let us know by clicking the “report an issue“ button at the bottom of the tutorial.

This is a tutorial on Bootstrap Sampling in Python. In this tutorial, we will learn what is bootstrapping and then see how to implement it.

Let’s get started.

The definition for bootstrap sampling is as follows :

In statistics, Bootstrap Sampling is a method that involves drawing of sample data repeatedly with replacement from a data source to estimate a population parameter.

This basically means that bootstrap sampling is a technique using which you can estimate parameters like mean for an entire population without explicitly considering each and every data point in the population.

Instead of looking at the entire population, we look at multiple subsets all of the same size taken from the population.

For example, if your population size is **1000.** Then to find the mean, instead of considering all the 1000 entries you can take **50 samples of size 4 each** and calculate the mean for each sample. This way you will be taking an average of **200 entries** (50X4) chosen randomly.

A similar strategy is used by market researchers to carry out research in a huge population.

Now let’s look at how to implement bootstrap sampling in python.

We will generate some random data with a predetermined mean. To do that we are going to use the NumPy module in Python.

Let’s start by importing the necessary modules.

The modules we need are :

- Numpy
- Random

To import these modules, use :

```
import numpy as np
import random
```

In the next step, we need to generate some random data. Let’s do that using the Numpy module.

Let’s generate a normal distribution with a mean of **300** and with **1000** entries.

The code for that is given below:

```
x = np.random.normal(loc= 300.0, size=1000)
```

We can calculate the mean of this data using :

```
print (np.mean(x))
```

Output :

```
300.01293472373254
```

Note that this is the actual mean of the population.

Let’s create 50 samples of size 4 each to estimate the mean.

The code for doing that is :

```
sample_mean = []
for i in range(50):
y = random.sample(x.tolist(), 4)
avg = np.mean(y)
sample_mean.append(avg)
```

The list *sample_mean* will contain the mean for all the 50 samples. For estimating the mean of the population we need to calculate the mean for *sample_mean*.

You can do that using :

```
print(np.mean(sample_mean))
```

Output :

```
300.07261467146867
```

Now if we run the code in this section again then we will get a different output. This is because each time we run the code, we will generate new samples. However, each time the output will be close to the actual mean (300).

On running the code in this section again, we get the following output :

```
299.99137705245636
```

Running it again, we get:

```
300.13411004148315
```

Here’s the complete code for this tutorial :

```
import numpy as np
import random
x = np.random.normal(loc= 300.0, size=1000)
print(np.mean(x))
sample_mean = []
for i in range(50):
y = random.sample(x.tolist(), 4)
avg = np.mean(y)
sample_mean.append(avg)
print(np.mean(sample_mean))
```

This tutorial was about Bootstrap Sampling in Python. We learned how to estimate the mean of a population by creating smaller samples. This is very useful in the world of Machine Learning to avoid overfitting. Hope you had fun learning with us!

If you’ve enjoyed this tutorial and our broader community, consider checking out our DigitalOcean products which can also help you achieve your development goals.