Data Science Data Cleaning and Preparation 2

Question 1

In pandas, what does df.dropna(thresh=3) do?

Accepted Answer

Drops rows that have fewer than 3 non-null values

Answer

Drops the first 3 rows with any NaN

Answer

Drops columns with more than 3 NaN values

Answer

Replaces NaN with the value 3

Question 2

Which technique replaces missing numeric values with the column average?

Accepted Answer

Mean imputation

Answer

One-hot encoding

Answer

Min-max scaling

Answer

Label encoding

Question 3

A 'duplicate record' in a dataset is best defined as a row that:

Accepted Answer

Has identical values across the columns used to identify uniqueness

Answer

Contains any null value

Answer

Appears in two different files

Answer

Has a numeric outlier

Question 4

Which pandas method removes duplicate rows?

Accepted Answer

df.drop_duplicates()

Answer

df.dropna()

Answer

df.unique()

Answer

df.distinct()

Question 5

Converting a column stored as text '2024-01-15' into a datetime type is an example of:

Accepted Answer

Type casting / parsing

Answer

Normalization

Answer

Binning

Answer

Deduplication

Question 6

What is the main risk of dropping all rows containing any missing value?

Accepted Answer

Significant loss of usable data and potential bias

Answer

It always improves model accuracy

Answer

It encrypts the dataset

Answer

It creates duplicate rows

Question 7

Standardizing inconsistent category labels like 'USA', 'U.S.A.', and 'United States' is called:

Accepted Answer

Data standardization / canonicalization

Answer

Sampling

Answer

Cross-validation

Answer

Feature extraction