LightGBM in ML Python - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the LightGBM library.

ML Python

import [1] as lgb

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

Atensorflow

Bsklearn

Cxgboost

Dlightgbm

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'sklearn' instead of 'lightgbm'.

Trying to import 'xgboost' which is a different library.

The LightGBM library is imported using import lightgbm as lgb.

2fill in blank

medium

Complete the code to create a LightGBM dataset from features X and labels y.

ML Python

train_data = lgb.Dataset([1], label=y)

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

AX

By

Ctrain

Ddata

Attempts:

3 left

💡 Hint

Common Mistakes

Passing labels y as the first argument instead of features X.

Using an undefined variable like 'train'.

The features are passed as the first argument to lgb.Dataset, so we use X.

3fill in blank

hard

Fix the error in the code to train a LightGBM model with 100 boosting rounds.

ML Python

model = lgb.train(params, train_data, num_boost_round=[1])

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

A10

B1000

C100

D1

Attempts:

3 left

💡 Hint

Common Mistakes

Using too few boosting rounds like 1 or 10.

Using an excessively large number like 1000 without reason.

The num_boost_round parameter controls the number of boosting iterations. 100 is a common choice for training.

4fill in blank

hard

Fill both blanks to set LightGBM parameters for binary classification with learning rate 0.05.

ML Python

params = {'objective': [1], 'learning_rate': [2]

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

A'binary'

B'multiclass'

C0.05

D0.1

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'multiclass' for binary classification.

Setting learning rate too high like 0.1.

The objective for binary classification is 'binary', and the learning rate is set to 0.05.

5fill in blank

hard

Fill all three blanks to predict with the model and calculate accuracy score.

ML Python

y_pred = model.predict([1])
y_pred_labels = (y_pred > [2]).astype(int)
accuracy = sum(y_pred_labels == [3]) / len(y_pred_labels)

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

AX_test

B0.5

Cy_test

DX_train

Attempts:

3 left

💡 Hint

Common Mistakes

Predicting on training data instead of test data.

Using wrong threshold values.

Comparing predictions with features instead of true labels.

We predict on X_test, use 0.5 as threshold to get labels, and compare with true labels y_test to compute accuracy.