Data Science with Python Certification Data Science with Python Exploratory Data Analysis 4 — Questions and Answers
Question 1: Which pandas method is used to compute pairwise correlations between all numeric columns of a DataFrame?
- df.cov()
- df.corr() (Correct answer)
- df.dot()
- df.corrwith()
Correct answer: df.corr()
df.corr() computes pairwise Pearson (or other) correlation coefficients between all numeric columns and returns a correlation matrix.
Question 2: In a heatmap created with seaborn's sns.heatmap(), what does the annot=True parameter do?
- Adds axis labels automatically
- Annotates each cell with its numeric value (Correct answer)
- Highlights cells above a threshold
- Adds a title to the heatmap
Correct answer: Annotates each cell with its numeric value
annot=True prints the data value inside each cell of the heatmap for easy reading.
Question 3: What is the purpose of using pd.cut() during EDA?
- To drop rows outside a specified range
- To bin a continuous variable into discrete intervals (Correct answer)
- To filter columns based on data type
- To remove duplicate values from a Series
Correct answer: To bin a continuous variable into discrete intervals
pd.cut() segments and sorts data values into discrete bins, converting a continuous variable into an ordinal categorical one.
Question 4: Which of the following correctly identifies a bimodal distribution in a histogram?
- A single tall peak near the center
- Two distinct peaks in the frequency distribution (Correct answer)
- A long tail extending to the right
- A uniform flat distribution across all bins
Correct answer: Two distinct peaks in the frequency distribution
A bimodal distribution has two local maxima (peaks), suggesting the data may come from two different subpopulations.
Question 5: When using matplotlib's plt.subplots(2, 3), what is the shape of the returned axes object?
- A flat list of 6 Axes objects
- A 2D NumPy array of shape (2, 3) (Correct answer)
- A single Axes object
- A tuple of (figure, axes_list)
Correct answer: A 2D NumPy array of shape (2, 3)
plt.subplots(nrows, ncols) returns a Figure and a 2D array of Axes objects with shape (nrows, ncols).
Question 6: What does df.pivot_table(values='sales', index='region', columns='quarter', aggfunc='sum') produce?
- A long-format DataFrame with one row per combination
- A cross-tabulation showing total sales per region per quarter (Correct answer)
- A Series of total sales grouped by region only
- A heatmap of the sales data
Correct answer: A cross-tabulation showing total sales per region per quarter
pivot_table() creates a 2D summary table where rows are regions, columns are quarters, and cells contain summed sales values.
Question 7: What does a scatter plot with a visible funnel shape (variance increasing with the x-variable) indicate?
- A strong negative correlation
- Heteroscedasticity — non-constant variance in the residuals (Correct answer)
- A perfect linear relationship
- Multicollinearity between variables
Correct answer: Heteroscedasticity — non-constant variance in the residuals
A funnel-shaped scatter plot reveals heteroscedasticity, where the spread of values changes across the range of the predictor.
Data Science with Python Certification Data Science with Python Exploratory Data Analysis 4
Which pandas method is used to compute pairwise correlations between all numeric columns of a DataFrame?