Distance metrics (euclidean, cosine, manhattan) in SciPy - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the euclidean distance function from scipy.

SciPy

from scipy.spatial.distance import [1]

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

Amanhattan

Bcosine

Ceuclidean

Dhamming

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing cosine or manhattan which are different distance metrics.

Trying to import a function not available in scipy.spatial.distance.

The euclidean function calculates the straight-line distance between two points.

2fill in blank

medium

Complete the code to calculate the cosine distance between vectors a and b.

SciPy

distance = [1](a, b)

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

Acosine

Bmanhattan

Ceuclidean

Dhamming

Attempts:

3 left

💡 Hint

Common Mistakes

Using euclidean distance which measures straight-line distance, not angle.

Using manhattan distance which sums absolute differences.

The cosine function measures the cosine distance, which reflects the angle difference between vectors.

3fill in blank

hard

Fix the error in the code to correctly calculate Manhattan distance between x and y.

SciPy

dist = [1](x, y)

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

Acosine

Bmanhattan

Cminkowski

Deuclidean

Attempts:

3 left

💡 Hint

Common Mistakes

Using euclidean distance which calculates straight-line distance.

Using minkowski without specifying the order parameter.

The manhattan function calculates the sum of absolute differences between coordinates.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps each vector to its Euclidean distance from a reference vector ref_vec.

SciPy

distances = {vec: [1](vec, ref_vec) for vec in vectors if [2](vec, ref_vec) < 5}

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

Aeuclidean

Bcosine

Cmanhattan

Dlen

Attempts:

3 left

💡 Hint

Common Mistakes

Using different distance functions in the two blanks.

Using len() which returns length, not distance.

We use euclidean to calculate distances and to filter vectors closer than 5 units.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps each vector to its Manhattan distance from ref_vec, but only include vectors with cosine distance less than 0.5.

SciPy

distances = {vec: [1](vec, ref_vec) for vec in vectors if [2](vec, ref_vec) [3] 0.5}

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

Aeuclidean

Bmanhattan

Ccosine

D<

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up distance functions in the blanks.

Using wrong comparison operator like > instead of <.

We calculate Manhattan distance for values, but filter vectors where cosine distance is less than 0.5.