Benchmark datasets in Prompt Engineering / GenAI - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load the popular MNIST dataset using TensorFlow.

Prompt Engineering / GenAI

import tensorflow as tf
mnist = tf.keras.datasets.[1].load_data()

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

Afashion_mnist

Bcifar10

Cimagenet

Dmnist

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'cifar10' instead of 'mnist' will load a different dataset.

Using 'imagenet' requires different loading methods.

The MNIST dataset is loaded using tf.keras.datasets.mnist.load_data().

2fill in blank

medium

Complete the code to split the dataset into training and testing sets using scikit-learn.

Prompt Engineering / GenAI

from sklearn.model_selection import [1]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

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

Atrain_test_split

Bcross_val_score

CGridSearchCV

DKFold

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'cross_val_score' does not split data but evaluates models.

Using 'GridSearchCV' is for hyperparameter tuning.

The function train_test_split splits data into training and testing sets.

3fill in blank

hard

Fix the error in the code to load the CIFAR-10 dataset correctly using PyTorch.

Prompt Engineering / GenAI

import torchvision.datasets as datasets
cifar10 = datasets.CIFAR10(root='./data', train=True, download=True, transform=[1])

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

ANone

Btransforms.ToTensor()

Ctorch.Tensor

Dtransform.ToTensor()

Attempts:

3 left

💡 Hint

Common Mistakes

Passing None disables transformations and causes errors later.

Using 'transform.ToTensor()' is incorrect syntax.

The transform argument requires a callable like transforms.ToTensor() to convert images to tensors.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps dataset names to their sample counts.

Prompt Engineering / GenAI

dataset_sizes = {name: len([1]) for name, [2] in datasets.items()}

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

Adata

Bdataset

Cvalue

Dsample

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'dataset' or 'sample' as variable names that don't match the iteration.

In the dictionary datasets, each value is a dataset object or list named data or value. Using len(data) or len(value) gets sample counts.

5fill in blank

hard

Fill all three blanks to filter datasets with more than 10,000 samples and create a new dictionary.

Prompt Engineering / GenAI

large_datasets = {name: [1] for name, [2] in datasets.items() if len([3]) > 10000}

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

Avalue

Bdata

Ddataset

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing variable names inconsistently causes errors.

Using the wrong variable in the length check.

The comprehension uses datasets.items() with variables name and value. The dictionary stores value as values. The filter checks len(value) > 10000.