1. Question 1

Which function identifies missing values in each column?

• ❌ df.info()

• ❌ df.missing_values()

• ✅ df.isnull().sum()

• ❌ df.describe()

Explanation:

isnull().sum() counts missing values per column.

---

2. Question 2

Visualize distribution of a categorical variable:

• ❌ scatterplot

• ❌ lineplot

• ❌ histplot (best for numeric)

• ✅ countplot

Explanation:

countplot shows frequency counts of categories.

---

3. Question 3

Function for cross-tabulations:

• ❌ pd.correlation()

• ❌ pd.merge()

• ✅ pd.crosstab()

• ❌ pd.groupby()

Explanation:

pd.crosstab() creates contingency tables.

---

4. Question 4

Median ConvertedCompYearly (from the dataset used in the lab):

• ❌ 55,000

• ❌ 50,000

• ❌ 65,000

• ✅ 60,000

Explanation:

The median yearly compensation ≈ 60,000 in the dataset.

---

5. Question 5

Method to detect outliers via 25th–75th percentile range:

• ❌ Standard deviation

• ✅ Interquartile Range (IQR)

• ❌ Mean absolute deviation

• ❌ Z-score

Explanation:

IQR = Q3 − Q1 → common method for outlier detection.

---

6. Question 6

Function to calculate skewness:

• ❌ df.corr()

• ❌ df.describe()

• ❌ df.var()

• ✅ df.skew()

Explanation:

df.skew() measures asymmetry in distribution.

---

7. Question 7

Best practice for handling extreme outliers in compensation data:

• ✅ Remove the outliers to prevent skewing the analysis

• ❌ Replace with NaN

• ❌ Set to max within 1.5×IQR

• ❌ Ignore them

Explanation:

Compensation data is highly skewed—removing extreme outliers improves representation.

---

8. Question 8

Identify median compensation for full-time employees:

• ❌ Use mode

• ❌ Use mean

• ✅ Filter for full-time employees → then calculate median

• ❌ Remove all outliers first

---

9. Question 9

Correlation between Age and WorkExp:

• ❌ No impact

• ❌ Work experience unrelated

• ❌ Experience decreases

• ✅ There is a strong relationship, but it is not perfect

Explanation:

As age increases, work experience also increases → positive correlation, but not 1.0.

---

10. Question 10

Purpose of removing outliers before analyzing salary trends:

• ❌ Ensure unique data

• ✅ Focus on common salary values & reduce skewness

• ❌ Decrease dataset size

• ❌ Increase median salary

---

🧾 Summary Table

---