Lab6 - data manipulation

Question 1

What is data manipulation?

Answer 1

Cleaning, transforming, organising data for analysis.

Question 2

Why manipulate data?

Answer 2

Make raw data suitable for analytics tasks.

Question 3

Give examples of manipulation processes.

Answer 3

Filter, create variables, summarise, impute, reorder observations.

Question 4

List out example of Narrowing observations?

Answer 4

Select recent year products or subset by condition.

Question 5

List out example of Variable creation

Answer 5

Compute BMI from weight and height

Question 6

List out example of summarising

Answer 6

Calculate counts, means, or group summaries.

Question 7

List out example of Imputation

Answer 7

Add or update values to fill missing data.

Question 8

What is the tbl class (tidyverse)?

Answer 8

A tidy data frame variant with improved behavior and printing

Question 9

How do tibbles print?

Answer 9

Show first 10 rows; truncate columns for legibility.

Question 10

Name behaviours tibbles have vs data.frames.

Answer 10

1. Easier to work with list
2. Doesn’t change column name ( read.csv() does )
3. Evaluates sequentially column to column
4. Displays more useful information
5. Subsetting consistently returns tbl’s
6. Extraction requires complete column names

Question 11

What does cbind() do?

Answer 11

Column-bind objects ( matr -> matrices ) and joining data frames -> df ) ; rows count must match.

Question 12

What does rbind() do?.

Answer 12

Row-bind objects ( matr -> matrices ) and joining data frames -> df ); columns must match names and count

Question 13

Which join merges carrier names into flights?

Answer 13

left_join(flights, airlines, by=\"carrier\")

Question 14

What does left_join keep?

Answer 14

All left table rows; matched right table values added.

Question 15

What must match for rbind()?

Answer 15

Same columns and names across data frames.

Question 16

What must match for cbind()?

Answer 16

Same number of rows across objects.