Random forest classifier in ML Python - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

How does a random forest reduce overfitting compared to a single decision tree?

Random forests use many decision trees to make predictions. Which of the following best explains how this helps reduce overfitting?

A By pruning each tree to a single node, it simplifies the model and prevents overfitting.

B By using only one tree with the deepest splits, it captures all data patterns perfectly, avoiding overfitting.

C By training all trees on the same data and features, it ensures consistent predictions and reduces overfitting.

D By averaging predictions from many trees trained on different random subsets of data and features, it reduces variance and overfitting.

❓ Predict Output

intermediate

Output of random forest prediction probabilities

What is the output of the following Python code using scikit-learn's RandomForestClassifier?

ML Python

from sklearn.ensemble import RandomForestClassifier
import numpy as np

X_train = np.array([[1, 2], [3, 4], [5, 6], [7, 8]])
y_train = np.array([0, 1, 0, 1])
model = RandomForestClassifier(random_state=42)
model.fit(X_train, y_train)

X_test = np.array([[2, 3]])
pred_probs = model.predict_proba(X_test)
print(pred_probs)

A [[0.5 0.5]]

B [[0. 1.]]

C [[1. 0.]]

D [[0.75 0.25]]

❓ Hyperparameter

advanced

Effect of increasing n_estimators in RandomForestClassifier

What is the most likely effect of increasing the n_estimators parameter (number of trees) in a RandomForestClassifier?

A It generally improves model stability and accuracy but increases training time.

B It has no effect on model performance or training time.

C It reduces training time by using fewer trees to make predictions.

D It decreases model accuracy because too many trees cause overfitting.

❓ Metrics

advanced

Choosing the best metric for imbalanced classification with Random Forest

You train a RandomForestClassifier on a dataset where 95% of samples belong to class 0 and 5% to class 1. Which metric is best to evaluate your model's performance?

A F1-score, because it balances precision and recall for imbalanced data.

B Precision, because it measures how many predicted positives are correct.

C Recall, because it measures how many actual positives are found.

D Accuracy, because it shows overall correct predictions.

🔧 Debug

expert

Debugging RandomForestClassifier training error

What error will this code raise when training a RandomForestClassifier, and why?

ML Python

from sklearn.ensemble import RandomForestClassifier

X_train = [[1, 2], [3, 4], [5, 6]]
y_train = [0, 1]
model = RandomForestClassifier()
model.fit(X_train, y_train)

A AttributeError: 'RandomForestClassifier' object has no attribute 'fit'

B TypeError: 'list' object is not callable

C ValueError: Found input variables with inconsistent numbers of samples

D No error, model trains successfully