Evidently AI for monitoring in MLOps - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import Evidently's Report class.

MLOps

from evidently.report import [1]

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

ADashboard

BReport

CMonitor

DAnalyzer

Attempts:

3 left

💡 Hint

Common Mistakes

Importing a non-existent class like Dashboard or Monitor.

The Report class is used to create monitoring reports in Evidently.

2fill in blank

medium

Complete the code to add a data drift metric to the Evidently report.

MLOps

from evidently.metric_preset import [1]

report = Report(metrics=[DataDriftPreset()])

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

ADataDriftPreset

BClassificationPreset

CDataQualityPreset

DRegressionPreset

Attempts:

3 left

💡 Hint

Common Mistakes

Using presets for quality or model performance instead of data drift.

DataDriftPreset is the preset metric to detect data drift in Evidently reports.

3fill in blank

hard

Fix the error in the code to run the Evidently report on current and reference data.

MLOps

report.run(current_data=[1], reference_data=ref_data)

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

Acurrent_df

Bcurrent_data

Cdata_current

Dref_data

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the reference data variable as current data.

The variable holding the current dataset must be passed correctly. Here, current_df is the correct variable name.

4fill in blank

hard

Fill both blanks to save the Evidently report as an HTML file.

MLOps

with open([1], [2]) as f:
    f.write(report.as_html())

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

A'report.html'

B'w'

C'r'

D'report.json'

Attempts:

3 left

💡 Hint

Common Mistakes

Using read mode 'r' or wrong file extensions like .json.

To save the report as HTML, open a file with write mode 'w' and a filename ending with .html.

5fill in blank

hard

Fill all three blanks to create a monitoring dashboard with Evidently and save it as HTML.

MLOps

from evidently.dashboard import [1]
from evidently.dashboard.tabs import [2]

dashboard = Dashboard(tabs=[[3]()])

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

ADashboard

BDataDriftTab

DReport

Attempts:

3 left

💡 Hint

Common Mistakes

Confusing Report with Dashboard or using wrong tab names.

The Dashboard class is imported from evidently.dashboard, and the DataDriftTab tab is imported from evidently.dashboard.tabs. The dashboard is created with the DataDriftTab instance.