DDMA Level III

Data Management and Analytics flashcards

Read the question, say the answer to yourself, then turn the card to check. The first 10 of 50 cards are free; the rest come with the subject.

Card 1 of 50

Jump to a card

Complete Flashcard Reference

Review every card in this deck. Open any card to reveal its answer. The first 10 are free; the other 40 come with the subject.

What are the five Vs of big data?

Volume: the sheer scale of data generated and stored. Velocity: the speed at which data is generated and must be processed. Variety: the range of formats and types data arrives in. Veracity: the trustworthiness and accuracy of the data. Value: the business or analytical worth that can be extracted from it.

How do structured, semi-structured and unstructured data differ?

Structured: fits a fixed schema of rows and columns, such as a relational database table. Semi-structured: has some organisational structure without a rigid schema, such as JSON or XML. Unstructured: has no predefined format, such as free text, images and video.

How does a cartogram differ from a dot distribution map?

Cartogram: a map whose regions are resized according to a data variable rather than their true geographic area. Dot distribution map: places one dot per unit of data at its geographic location, showing density.

What does a bullet graph show?

A compact chart comparing an actual value against a target and qualitative ranges, for example sales against a monthly target with bands for poor, fair and good.

Which measure of centre should a skewed dataset with outliers use, and why does it matter?

The median rather than the mean. Checking a dataset's properties before analysis directly decides which technique is appropriate later.

What is the difference between a bivariate and a multivariate dataset?

Bivariate: exactly two variables, often analysed for the relationship between them. Multivariate: three or more variables.

What is an R data frame, and what sets it apart from a vector or a matrix?

A table in which each column can hold a different data type, the structure most real analysis is done in. A vector holds values of one type and every element of a matrix shares one type, so the data frame is the only one of the three that can mix types column by column.

How are variables assigned in R, and how is a comment written?

Variables are assigned with <-, the conventional R assignment operator, or with =. A comment starts with #. Example: x <- 5

How does the MapReduce programming model work?

It splits a computation into two steps: Map: processes data in parallel across the cluster. Reduce: combines those partial results into a final answer. This lets a single logical computation run across many machines at once.

Hive and Pig both save writing MapReduce directly. How do they differ?

Hive: a SQL-like query interface over data in Hadoop, suited to analysts already comfortable with SQL. Pig: a high-level scripting language for data transformation pipelines, suited to multi-step workflows.

What is big data?