Explainability requirements in MLOps - Mini Project: Build & Apply

Explainability Requirements in MLOps

📖 Scenario: You are working in a team that builds machine learning models for a healthcare application. The team needs to ensure that the model's decisions can be explained clearly to doctors and patients. This helps build trust and meets regulatory rules.

🎯 Goal: Build a simple Python dictionary that stores model predictions and their explanations. Then, filter explanations based on a confidence threshold and display the filtered results.

📋 What You'll Learn

Create a dictionary called predictions with exact keys and values

Add a confidence threshold variable called confidence_threshold

Use a dictionary comprehension to filter explanations with confidence above the threshold

Print the filtered explanations exactly as specified

💡 Why This Matters

🌍 Real World

In healthcare and other sensitive fields, explaining machine learning model decisions clearly is critical for trust and compliance.

💼 Career

Understanding explainability requirements helps MLOps engineers build transparent and trustworthy AI systems that meet legal and ethical standards.

1

Create the initial predictions dictionary

Create a dictionary called predictions with these exact entries: 'patient_1': {'prediction': 'disease', 'confidence': 0.85, 'explanation': 'High risk due to age and symptoms'}, 'patient_2': {'prediction': 'no_disease', 'confidence': 0.65, 'explanation': 'Low risk based on test results'}, 'patient_3': {'prediction': 'disease', 'confidence': 0.90, 'explanation': 'Strong indicators from lab tests'}

MLOps

# Create the predictions dictionary with exact entries
# Your code here

Need a hint?

Use a dictionary with patient IDs as keys and another dictionary as values containing prediction, confidence, and explanation.

2

Add a confidence threshold variable

Add a variable called confidence_threshold and set it to 0.80 to filter predictions with confidence above this value.

MLOps

predictions = {
    'patient_1': {'prediction': 'disease', 'confidence': 0.85, 'explanation': 'High risk due to age and symptoms'},
    'patient_2': {'prediction': 'no_disease', 'confidence': 0.65, 'explanation': 'Low risk based on test results'},
    'patient_3': {'prediction': 'disease', 'confidence': 0.90, 'explanation': 'Strong indicators from lab tests'}
}
# Add confidence_threshold variable below
# Your code here

Need a hint?

Just create a variable named confidence_threshold and assign it the value 0.80.

3

Filter explanations with confidence above threshold

Use a dictionary comprehension to create a new dictionary called filtered_explanations that includes only patients from predictions whose confidence is greater than confidence_threshold. The values should be the explanation strings.

MLOps

predictions = {
    'patient_1': {'prediction': 'disease', 'confidence': 0.85, 'explanation': 'High risk due to age and symptoms'},
    'patient_2': {'prediction': 'no_disease', 'confidence': 0.65, 'explanation': 'Low risk based on test results'},
    'patient_3': {'prediction': 'disease', 'confidence': 0.90, 'explanation': 'Strong indicators from lab tests'}
}
confidence_threshold = 0.80
# Create filtered_explanations dictionary below
# Your code here

Need a hint?

Use a dictionary comprehension with for patient, info in predictions.items() and filter by info['confidence'] > confidence_threshold.

4

Print the filtered explanations

Write a print statement to display the filtered_explanations dictionary.

MLOps

predictions = {
    'patient_1': {'prediction': 'disease', 'confidence': 0.85, 'explanation': 'High risk due to age and symptoms'},
    'patient_2': {'prediction': 'no_disease', 'confidence': 0.65, 'explanation': 'Low risk based on test results'},
    'patient_3': {'prediction': 'disease', 'confidence': 0.90, 'explanation': 'Strong indicators from lab tests'}
}
confidence_threshold = 0.80
filtered_explanations = {patient: info['explanation'] for patient, info in predictions.items() if info['confidence'] > confidence_threshold}
# Print filtered_explanations below
# Your code here

Need a hint?

Use print(filtered_explanations) to show the filtered dictionary.