Challenge - 5 Problems

🎖️

Logistic Regression Mastery

Get all challenges correct to earn this badge!

Test your skills under time pressure!

🧠 Conceptual

intermediate

2:00remaining

Understanding the output of logistic regression

What does the output of a logistic regression model represent?

AThe probability that the input belongs to the positive class

BThe exact class label predicted by the model

CThe distance of the input from the decision boundary in feature space

DThe sum of squared errors between predicted and actual values

Attempts:

2 left

❓ Predict Output

intermediate

2:00remaining

Output of logistic regression prediction code

What is the output of this Python code using scikit-learn's LogisticRegression?

ML Python

from sklearn.linear_model import LogisticRegression
import numpy as np

X = np.array([[1, 2], [2, 3], [3, 4], [4, 5]])
y = np.array([0, 0, 1, 1])
model = LogisticRegression()
model.fit(X, y)
preds = model.predict(np.array([[1, 2], [3, 5]]))
print(preds.tolist())

A[1, 1]

B[1, 0]

C[0, 0]

D[0, 1]

Attempts:

2 left

❓ Hyperparameter

advanced

2:00remaining

Choosing the regularization parameter in logistic regression

Which effect does increasing the regularization strength (C parameter) in scikit-learn's LogisticRegression have?

AIt decreases regularization, allowing the model to fit training data more closely

BIt changes the number of iterations during training

CIt changes the learning rate of the model

DIt increases regularization, forcing the model to be simpler

Attempts:

2 left

❓ Metrics

advanced

2:00remaining

Interpreting logistic regression evaluation metrics

If a logistic regression model has a high accuracy but low recall on the positive class, what does this imply?

AThe model performs well on both positive and negative classes

BThe model correctly identifies most positive cases but misclassifies many negatives

CThe model misses many positive cases but correctly identifies most negatives

DThe model has overfitted the training data

Attempts:

2 left

🔧 Debug

expert

2:00remaining

Identifying the cause of poor logistic regression convergence

Given this code snippet, why might the logistic regression model fail to converge?

ML Python

from sklearn.linear_model import LogisticRegression
import numpy as np

X = np.random.rand(1000, 50)
y = np.random.randint(0, 2, 1000)
model = LogisticRegression(max_iter=10)
model.fit(X, y)

AThe input features X contain random values causing errors

Bmax_iter is too low for the model to converge on this data

CThe target y has only two classes which logistic regression cannot handle

DThe model requires normalization of X before fitting

Attempts:

2 left