Question 1

Fill in the blank: N/A and NaN are terms used to describe _____ data.

• nominal ❌

• qualitative ❌

• string ❌

• missing ✅

Explanation:
N/A (“not available”) and NaN (“not a number”) are standard indicators of missing data.

---

Question 2

Strategies to solve missing data problems (Select all that apply):

• Ask the film studio to fill in the missing values. ✅

• Create a NaN category. ✅

• Use their best judgment to add in values themselves. ❌

• Add in missing values using the average values from existing data. ✅

Explanation:
Appropriate approaches include: asking the data owner, imputing using statistical methods, or treating missingness as its own category.
Using “best judgment” without justification introduces bias.

---

Question 3

Which part refers to the dataframe being merged with df?

• df_zip ✅

• how=’left’ ❌

• merge ❌

• center_point_geom ❌

Explanation:
The syntax df.merge(df_zip, ...) merges df_zip into df.

---

Question 4

Which pandas function pulls all missing values?

• pd.isnull() ✅

• pd.ofnull() ❌

• pd.findnull() ❌

• pd.getnull() ❌

Explanation:
isnull() identifies all NaN and None values.

---

Question 5

Type of outliers that form a group with similar abnormal behavior:

• Global outliers ❌

• Collective outliers ✅

• Contextual outliers ❌

• Atypical outliers ❌

Explanation:
Collective outliers occur when a group of points jointly appear abnormal.

---

Question 6

Assigning numbers to categories (dog=1, cat=2, etc.) is:

• Data blending ❌

• Aliasing ❌

• Data partitioning ❌

• Label encoding ✅

Explanation:
Label encoding converts categories into numerical labels.

---

Question 7

Heat map displays values using:

• a series of markers ❌

• slices ❌

• colors ✅

• vertical bars ❌

Explanation:
Heat maps express intensity or concentration using color gradients.

---

Question 8

What does pd.duplicated() return for non-duplicate values?

• Unique ❌

• False ✅

• Duplicate ❌

• True ❌

Explanation:
duplicated() returns False when the value is NOT a duplicate.

---

Question 9

A duplicate should be _____ if it is valid and meaningful.

• keep ✅

• eliminate ❌

• emphasize ❌

• filter ❌

Explanation:
Some datasets legitimately contain repeated entries (e.g., returning customers, repeated transactions).

---

Question 10

Term for thoroughly analyzing data to ensure it is complete and error-free:

• Input validation ❌

• Normalization ❌

• Data mapping ❌

• Verification ✅

Explanation:
Verification ensures data accuracy, completeness, and quality.

---

🧾 Summary Table

---