Data Science with Python Certification Data Science with Python Exploratory Data Analysis 5

Question 1

Which pandas method efficiently identifies columns with more than 50% missing values?

Accepted Answer

df.isnull().mean() > 0.5

Answer

df.isnull().mean() computes the fraction of missing values per column; comparing to 0.5 returns a boolean mask of columns exceeding 50% nulls.

Question 2

In EDA, what is the main advantage of using a pair plot (sns.pairplot()) over individual scatter plots?

Accepted Answer

It shows all pairwise relationships and univariate distributions in a single grid

Answer

sns.pairplot() creates a grid of scatter plots for every pair of numeric variables and histograms/KDEs on the diagonal, giving a comprehensive overview.

Question 3

What does df.astype({'age': 'int32', 'score': 'float32'}) accomplish?

Accepted Answer

Casts the specified columns to new data types to reduce memory usage

Answer

astype() with a dict changes each named column to the specified dtype, which can significantly reduce memory footprint.

Question 4

Which statistic is most resistant to the influence of outliers when describing the center of a distribution?

Accepted Answer

Median

Answer

The median is the middle value and is not pulled by extreme outliers, making it a robust measure of central tendency.

Question 5

What is the purpose of applying Z-score standardization during EDA before visualization?

Accepted Answer

To place variables on a common scale for fair comparison

Answer

Z-score standardization (subtracting the mean and dividing by std) rescales features to have mean 0 and std 1, enabling meaningful comparison across different scales.

Data Science with Python Certification Practice Test

Data Science with Python Certification Practice Test

Data Science with Python Certification Data Science with Python Exploratory Data Analysis 5