Polynomial regression pipeline in ML Python - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of polynomial regression prediction

Given the following code that fits a polynomial regression model and predicts a value, what is the output?

ML Python

from sklearn.preprocessing import PolynomialFeatures
from sklearn.linear_model import LinearRegression
import numpy as np

X = np.array([[1], [2], [3], [4], [5]])
y = np.array([1, 4, 9, 16, 25])  # y = x^2

poly = PolynomialFeatures(degree=2)
X_poly = poly.fit_transform(X)

model = LinearRegression()
model.fit(X_poly, y)

pred = model.predict(poly.transform([[6]]))
print(round(pred[0], 2))

A 36.0

B 35.0

C 30.0

D 42.0

💡 Hint

Remember that the model fits y = x^2, so predicting for x=6 should be close to 36.

The model fits a polynomial of degree 2 to the data y = x^2. Predicting for x=6 gives approximately 36.

❓ Model Choice

intermediate

Best model choice for polynomial regression pipeline

You want to build a pipeline that fits a polynomial regression model to data. Which of the following pipeline components is the correct choice to transform the input features before fitting a linear regression?

A MinMaxScaler followed by LinearRegression

B StandardScaler followed by LinearRegression

C PolynomialFeatures followed by LinearRegression

D PCA followed by LinearRegression

💡 Hint

Polynomial regression requires creating polynomial features before fitting a linear model.

PolynomialFeatures generates polynomial terms needed for polynomial regression. The other options do not create polynomial features.

❓ Hyperparameter

advanced

Choosing the polynomial degree hyperparameter

In a polynomial regression pipeline, which effect does increasing the degree hyperparameter have on the model?

A It has no effect on model complexity

B It increases model complexity and may cause overfitting

C It decreases model complexity and reduces overfitting

D It always improves model generalization

💡 Hint

Higher degree polynomials can fit data more closely but risk fitting noise.

Increasing degree adds more polynomial terms, making the model more flexible and prone to overfitting.

❓ Metrics

advanced

Evaluating polynomial regression with R² score

After fitting a polynomial regression model, you compute the R² score on test data and get 0.95. What does this value indicate?

A The model explains 95% of the variance in the test data

B The model has 95% accuracy in classification

C The model's predictions are 95% correct on average

D The model has 95% error rate

💡 Hint

R² score measures how well the model explains variance in continuous data.

R² of 0.95 means the model explains 95% of the variance in the target variable on test data.

🔧 Debug

expert

Debugging pipeline with incorrect feature transformation

You build a pipeline with PolynomialFeatures(degree=3) and LinearRegression. After training, predictions are constant and do not change with input. What is the most likely cause?

A PolynomialFeatures was not fitted before transforming the input

B LinearRegression was not fitted with the transformed features

C Degree parameter was set to 1 instead of 3

D Input data was not reshaped to 2D array before transformation

💡 Hint

PolynomialFeatures expects 2D input; wrong shape can cause incorrect transformations.

If input is 1D array, PolynomialFeatures treats it incorrectly, leading to constant predictions.