tbl_df: Create a data frame tbl.

Description Usage Arguments Examples

View source: R/tbl-df.r

Description

Forwards the argument to as_data_frame, see tibble-package for more details.

Usage

1

Arguments

data

a data frame

Examples

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
ds <- tbl_df(mtcars)
ds
as.data.frame(ds)

if (require("Lahman") && packageVersion("Lahman") >= "3.0.1") {
batting <- tbl_df(Batting)
dim(batting)
colnames(batting)
head(batting)

# Data manipulation verbs ---------------------------------------------------
filter(batting, yearID > 2005, G > 130)
select(batting, playerID:lgID)
arrange(batting, playerID, desc(yearID))
summarise(batting, G = mean(G), n = n())
mutate(batting, rbi2 = if(is.null(AB)) 1.0 * R / AB else 0)

# Group by operations -------------------------------------------------------
# To perform operations by group, create a grouped object with group_by
players <- group_by(batting, playerID)
head(group_size(players), 100)

summarise(players, mean_g = mean(G), best_ab = max(AB))
best_year <- filter(players, AB == max(AB) | G == max(G))
progress <- mutate(players, cyear = yearID - min(yearID) + 1,
 rank(desc(AB)), cumsum(AB))

# When you group by multiple level, each summarise peels off one level

per_year <- group_by(batting, playerID, yearID)
stints <- summarise(per_year, stints = max(stint))
filter(stints, stints > 3)
summarise(stints, max(stints))
mutate(stints, cumsum(stints))


# Joins ---------------------------------------------------------------------
player_info <- select(tbl_df(Master), playerID, birthYear)
hof <- select(filter(tbl_df(HallOfFame), inducted == "Y"),
 playerID, votedBy, category)

# Match players and their hall of fame data
inner_join(player_info, hof)
# Keep all players, match hof data where available
left_join(player_info, hof)
# Find only players in hof
semi_join(player_info, hof)
# Find players not in hof
anti_join(player_info, hof)
}

sctyner/dplyr050 documentation built on May 17, 2019, 2:22 p.m.