2 Working with Data and Data Types Online Quiz Questions

Rows are variables and columns are observations; all columns must have the same data type.

Rows are observations and columns are variables; different columns can have different data types.

Rows are data types and columns are observations; each row can have a different structure.

Rows and columns both represent observations; each DataFrame stores only one data type.

True

False

Treat the codes as measurements and calculate their average.

Convert the codes to temperatures because both contain digits.

Treat the codes as identifiers rather than quantities.

Treat the codes as dates because they label customer records.

Use measurements["location"].value_counts(dropna=False) to review location counts while keeping missing values visible.

Use measurements.shape to count missing values separately in every column.

Use measurements.isna().sum() to count missing values per column.

Use measurements.head() to standardize inconsistent category capitalization automatically.

True

False

Convert every value immediately and discard any entry that fails.

Check the format and decide how to handle entries that do not convert.

Assume that every value containing digits is already stored as a number.

Replace all nonnumeric values with zero before checking the column.

Review the column’s distinct values for differences such as North and NORTH.

Compare values with the data dictionary, expected units, and plausible ranges.

Rely only on the count of missing values to detect all inconsistent entries.

Automatically change every unusual number without investigating it.

Store the ratings as dates because they have a meaningful sequence.

Treat the ratings as numeric measurements because the categories are ordered.

Treat the ratings as categorical values, recognizing that plain text does not express their order.

Treat the ratings as identifiers because they distinguish one response from another.

A Series, because it contains multiple labeled columns

A DataFrame, because it is a two-dimensional table with labeled columns

A categorical value, because the table has labels

A Boolean, because each row is one observation

Treat it as a quantity and calculate its mean

Treat it as a measurement because it contains digits

Treat it as an identifier rather than a quantity

Treat it as a date because it identifies a customer

Check whether “unknown” is a missing-value marker in this dataset before passing it to na_values

Always include “unknown” in na_values because it is never a meaningful category

Convert every text value in the file to a missing value

Use head() to tell pandas that “unknown” means missing

Convert it immediately and discard any entries that cause errors

Keep it as text permanently because dates cannot be analyzed chronologically

Replace every value that does not look like a date with zero

Check the format and plan how to handle entries that do not convert

True

False