Dsci 100 Final Study Guide

DSCI 100 FINAL STUDY GUIDE


load repr library - Answers - library(repr)

filter does what - Answers - gets a subset of rows from data frame meeting criteria

what does mutate do - Answers - - adds a new column from data frame
- overwrites/changes a column to a data frame

how do you make data reproducible? - Answers - use code to perform an analysis of the
data. all analysis should be done and stored with code, as opposed to excel.

advantages of a relative path - Answers - - reproducible
works from another computer without changes

tbl(conn, "projects") - Answers - gets table "projects" from conn connection in database.
creates usable data frame in R

fill in for planes that do NOT have 55 seats but who's year is earlier than 2000

tailnum_df <- planes|>
...(...)|>
filter(...&...) - Answers - - select
- tailnum
- seats!=55
- year<2000

fill in for the tailnum of planes that have 55 seats who's year is earlier than 2000
planes|> filter(...)|> select(...) - Answers - seats==55, year<2000
tailnum

trying to determine island from beak_depth and beak_length
penguins<-penguins|>
mutate(island=...(island))

knn_recipe<-recipe(...~..., ...=...) |>
...(all_predictors()) - Answers - - as_factor
- island
- beak_length+beak_width
- data
- penguins

when to use classification - Answers - when you're trying to find a categorical value