When calling describe() on object (string) columns, which statistics are included?

When calling describe() on object (string) columns, which statistics are included?

• A. COUNT, MIN, MAX
• B. COUNT, TOP, UNIQUE
• C. COUNT, MEAN, STD, MAX, TOP, UNIQUE, FREQ
• D. COUNT, MEAN, MEDIAN, MODE

Answer: (C)

describe() on string/object columns provides a mix of statistics that summarize the data, combining both counts and distribution details. It includes a count of rows and also metrics that apply to the category of values: the most frequent value (top) and how often that value occurs (freq), plus how many distinct values exist (unique). It can also show a maximum value in the lexicographic sense and, where applicable, numeric-like aggregates such as mean and standard deviation. This combination gives a fuller picture of a string column’s distribution, which is why the option listing COUNT, MEAN, STD, MAX, TOP, UNIQUE, and FREQ is the best fit. Other options omit one or more of these statistics, so they don’t fully describe string/object columns.

describe() on string/object columns provides a mix of statistics that summarize the data, combining both counts and distribution details. It includes a count of rows and also metrics that apply to the category of values: the most frequent value (top) and how often that value occurs (freq), plus how many distinct values exist (unique). It can also show a maximum value in the lexicographic sense and, where applicable, numeric-like aggregates such as mean and standard deviation. This combination gives a fuller picture of a string column’s distribution, which is why the option listing COUNT, MEAN, STD, MAX, TOP, UNIQUE, and FREQ is the best fit. Other options omit one or more of these statistics, so they don’t fully describe string/object columns.