Validation split in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to split the data into training and validation sets using Keras model.fit.

TensorFlow

model.fit(x_train, y_train, epochs=10, batch_size=32, validation_split=[1])

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

ANone

B2

C20

D0.2

Attempts:

3 left

💡 Hint

Common Mistakes

Using an integer like 2 or 20 instead of a fraction.

Setting validation_split to None which disables validation.

The validation_split parameter expects a float between 0 and 1 representing the fraction of data to use for validation. Here, 0.2 means 20% of the training data is used for validation.

2fill in blank

medium

Complete the code to create a validation set from training data using sklearn's train_test_split.

TensorFlow

from sklearn.model_selection import train_test_split
x_train, x_val, y_train, y_val = train_test_split(x, y, test_size=[1], random_state=42)

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

A10

B0.1

C0.5

DNone

Attempts:

3 left

💡 Hint

Common Mistakes

Using an integer like 10 instead of a fraction.

Setting test_size to None which causes an error.

The test_size parameter defines the fraction of data to use as validation. 0.1 means 10% of the data is used for validation.

3fill in blank

hard

Fix the error in the code to correctly use validation_split in model.fit.

TensorFlow

history = model.fit(x_train, y_train, epochs=5, validation_split=[1])

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

A0.2

BNone

C'0.2'

D20

Attempts:

3 left

💡 Hint

Common Mistakes

Passing validation_split as a string like '0.2'.

Passing an integer like 20 instead of a fraction.

The validation_split must be a float between 0 and 1, not a string or integer. Using 0.2 correctly reserves 20% of data for validation.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps words to their lengths only if length is greater than 3.

TensorFlow

lengths = {word: [1] for word in words if len(word) [2] 3}

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

Alen(word)

B>

C<

Dword

Attempts:

3 left

💡 Hint

Common Mistakes

Using the word itself as the value instead of its length.

Using less than (<) instead of greater than (>) in the condition.

The dictionary comprehension maps each word to its length using len(word). The condition len(word) > 3 filters words longer than 3 characters.

5fill in blank

hard

Fill all three blanks to create a filtered dictionary with uppercase keys, values, and a condition.

TensorFlow

result = [1]: [2] for k, v in data.items() if v [3] 0}

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

Ak.upper()

Bv

C>

Dk

Attempts:

3 left

💡 Hint

Common Mistakes

Using original keys without uppercase.

Using incorrect comparison operators like < or ==.

This comprehension creates a dictionary with keys as uppercase strings (k.upper()), values as v, and includes only items where v > 0.