Why clustering groups similar data in SciPy - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the clustering function from scipy.

SciPy

from scipy.cluster import [1]

Drag options to blanks, or click blank then click option'

Acluster

Bhierarchy

Cspatial

Doptimize

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing unrelated modules like 'optimize' or 'spatial'.

Choosing 'cluster', the package containing the hierarchy module.

The hierarchy module in scipy contains clustering algorithms.

2fill in blank

medium

Complete the code to create a linkage matrix for clustering.

SciPy

linkage_matrix = hierarchy.[1](data, method='ward')

Drag options to blanks, or click blank then click option'

Alinkage

Bdendrogram

Ckmeans

Dfcluster

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'dendrogram' which is for plotting, not creating linkage.

Using 'kmeans' which is a different clustering method.

The linkage function creates a linkage matrix used for hierarchical clustering.

3fill in blank

hard

Fix the error in the code to plot a dendrogram using the linkage matrix.

SciPy

hierarchy.[1](linkage_matrix)
plt.show()

Drag options to blanks, or click blank then click option'

Afcluster

Blinkage

Cdendrogram

Dplot

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'linkage' which returns data, not a plot.

Using 'plot' which is not a scipy.cluster function.

The dendrogram function plots the hierarchical clustering as a tree.

4fill in blank

hard

Fill both blanks to create a dictionary of cluster labels for data points with distance threshold 5.

SciPy

labels = hierarchy.[1](linkage_matrix, t=[2], criterion='distance')

Drag options to blanks, or click blank then click option'

Afcluster

B3

C5

Dlinkage

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'linkage' instead of 'fcluster' for flat clusters.

Choosing wrong threshold values like 3 instead of 5.

The fcluster function forms flat clusters from the linkage matrix using a distance threshold.

5fill in blank

hard

Fill the two blanks to create a dictionary of cluster sizes for clusters with labels greater than 1.

SciPy

cluster_sizes = {label: sum(labels == label) for label in set(labels) if label [1] [2] }

Drag options to blanks, or click blank then click option'

A1

B==

C>

D!=

Attempts:

3 left

💡 Hint

Common Mistakes

Using '==' instead of '>' in the condition.

Using wrong label value like 0 instead of 1.

This dictionary comprehension counts points in clusters with labels greater than 1.