Cluster evaluation metrics in SciPy - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the function for calculating the silhouette score.

SciPy

from sklearn.metrics import [1]

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

Asilhouette_score

Bconfusion_matrix

Cmean_squared_error

Daccuracy_score

Attempts:

3 left

💡 Hint

Common Mistakes

Importing classification metrics like accuracy_score instead of clustering metrics.

Confusing silhouette_score with confusion_matrix.

The silhouette_score function is used to evaluate clustering quality by measuring how similar an object is to its own cluster compared to other clusters.

2fill in blank

medium

Complete the code to calculate the silhouette score for data X with labels y_pred.

SciPy

score = silhouette_score([1], y_pred)

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

Ay_pred

BX_train

Clabels_true

DX

Attempts:

3 left

💡 Hint

Common Mistakes

Passing cluster labels as the first argument instead of data.

Using training data variable names that are not defined.

The silhouette score requires the original data points X and the predicted cluster labels y_pred to compute the score.

3fill in blank

hard

Fix the error in the code to compute the adjusted Rand index between true labels and predicted labels.

SciPy

from sklearn.metrics import adjusted_rand_score
ari = adjusted_rand_score([1], y_pred)

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

Ay_pred

BX

Clabels_true

DX_train

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the data points instead of true labels.

Passing predicted labels twice.

The adjusted Rand index compares the true labels labels_true with the predicted labels y_pred. Passing the data X or predicted labels twice is incorrect.

4fill in blank

hard

Fill both blanks to create a dictionary of cluster sizes for each cluster label in y_pred.

SciPy

cluster_sizes = {label: y_pred.count([1]) for label in [2]

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

Alabel

By_pred

Cset(y_pred)

Dlabels_true

Attempts:

3 left

💡 Hint

Common Mistakes

Using the wrong variable for keys or count.

Not converting to set to get unique labels.

We count how many times each label appears in y_pred. The dictionary keys are the unique labels, which we get using set(y_pred).

5fill in blank

hard

Fill all three blanks to compute the completeness score between true labels and predicted labels.

SciPy

from sklearn.metrics import [1]
score = [1]([2], [3])

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

Acompleteness_score

Blabels_true

Cy_pred

Dadjusted_rand_score

Attempts:

3 left

💡 Hint

Common Mistakes

Using adjusted_rand_score instead of completeness_score.

Swapping the order of true and predicted labels.

The completeness_score function measures how well all members of a given class are assigned to the same cluster. It takes true labels and predicted labels as arguments.