Data drift detection basics in MLOps - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the library used for data drift detection.

MLOps

from evidently import [1]

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

Adashboard

Bprofile

Cmetrics

Dreport

Attempts:

3 left

💡 Hint

Common Mistakes

Importing the wrong module like 'dashboard' which is for visualization.

Using 'report' which is for generating reports, not profiles.

The profile module from Evidently is used to create data drift profiles.

2fill in blank

medium

Complete the code to create a data drift profile object.

MLOps

data_drift_profile = profile.[1]()

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

ADashboard

BReport

CProfile

DAnalyzer

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'Dashboard' which is for interactive visualization.

Using 'Report' which is for generating reports.

The Profile class is used to create a data drift profile object.

3fill in blank

hard

Fix the error in the code to run the data drift profile on reference and current data.

MLOps

data_drift_profile.[1](reference_data=ref_data, current_data=curr_data)

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

Acalculate

Bexecute

Capply

Dstart

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'run' which is a method of Report objects.

Using 'apply' which is unrelated here.

The calculate method executes the profile analysis on the given datasets.

4fill in blank

hard

Fill both blanks to create a dictionary with drift metrics from the profile results.

MLOps

drift_metrics = data_drift_profile.[1]()['[2]']

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

Aas_dict

Bmetrics

Cdata_drift

Dresults

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'json' instead of 'as_dict' for the first blank, as json() returns a string.

Using 'results' instead of 'data_drift' for the second blank.

The as_dict method returns the profile results as a dictionary, and 'data_drift' key holds the drift metrics.

5fill in blank

hard

Fill all three blanks to check if data drift is detected and print a message.

MLOps

if drift_metrics['[1]'] [2] [3]:
    print('Data drift detected!')
else:
    print('No data drift.')

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

Adataset_drift

B==

CTrue

D!=

Attempts:

3 left

💡 Hint

Common Mistakes

Using '!=' instead of '==' causing wrong condition.

Checking for 'False' instead of 'True'.

The key 'dataset_drift' indicates if drift is detected. We check if it is == True to print the message.