One-hot encoding in ML Python - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the one-hot encoder from scikit-learn.

ML Python

from sklearn.preprocessing import [1]

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

AMinMaxScaler

BLabelEncoder

CStandardScaler

DOneHotEncoder

Attempts:

3 left

💡 Hint

Common Mistakes

Using LabelEncoder instead of OneHotEncoder, which encodes labels as integers, not one-hot vectors.

The OneHotEncoder is the correct class to perform one-hot encoding in scikit-learn.

2fill in blank

medium

Complete the code to create a one-hot encoder that outputs dense arrays.

ML Python

encoder = OneHotEncoder(sparse=[1])

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

AFalse

B0

CNone

DTrue

Attempts:

3 left

💡 Hint

Common Mistakes

Leaving sparse as True, which returns a sparse matrix instead of a dense array.

Setting sparse=False makes the encoder output dense numpy arrays instead of sparse matrices.

3fill in blank

hard

Fix the error in the code to fit the encoder to the data.

ML Python

encoder.fit([1])

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

Alabels

BX_train

Cdata

Dy_train

Attempts:

3 left

💡 Hint

Common Mistakes

Fitting the encoder on labels or target variables instead of features.

The encoder should be fit on the feature data, usually named X_train, not labels or target variables.

4fill in blank

hard

Fill both blanks to transform the data and convert the result to an array.

ML Python

encoded = encoder.[1]([2]).toarray()

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

Atransform

Bfit_transform

CX_test

DX_train

Attempts:

3 left

💡 Hint

Common Mistakes

Using transform instead of fit_transform on training data.

Applying fit_transform on test data instead of training data.

Using fit_transform on X_train fits the encoder and transforms the training data in one step. The toarray() converts the sparse matrix to a dense array.

5fill in blank

hard

Fill all three blanks to create a one-hot encoded DataFrame with proper column names.

ML Python

import pandas as pd
encoded_array = encoder.[1](X).toarray()
columns = encoder.get_feature_names_out([2])
encoded_df = pd.DataFrame(encoded_array, columns=[3])

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

Afit_transform

BX

Ccolumns

Dtransform

Attempts:

3 left

💡 Hint

Common Mistakes

Using transform instead of fit_transform on the data.

Passing wrong argument to get_feature_names_out.

Not assigning column names when creating the DataFrame.

First, use fit_transform on the data X. Then get the feature names with get_feature_names_out passing the original column names columns. Finally, create a DataFrame with the encoded array and column names.