Comparing Different Dimensionality Reduction Techniques

Now that we have learned different dimensionality reduction techniques, let's apply all of these techniques to a new dataset that we will create from the existing ads dataset.

We will randomly sample some data points from a known distribution and then add these random samples to the existing dataset to create a new dataset. Let's carry out an experiment to see how a new dataset can be created from an existing dataset.

We import the necessary libraries:

import pandas as pd
import numpy as np

Next, we create a dummy data frame.

We will use a small dataset with two rows and three columns for this example. We use the pd.np.array() function to create a data frame:

# Creating a simple data frame
df = pd.np.array([[1, 2, 3], [4, 5, 6]])
print(df.shape)
df

You should get the following output:

Figure 14.36: Sample data frame

What we will do next is sample some data points with the...