R tips
21 April 2023
Contents
1 Set-up
devtools::load_all("~/utils.tool")## ℹ Loading utils.tool## Warning in .recacheSubclasses(def@className, def, env): undefined subclass "ggraph" of class
## "gg.obj"; definition not updatedlibrary(ggplot2)
# knitr::opts_chunk$set(echo = F)2 Overview
x <- seq(1, 10, by = .05)
work2time <- data.frame(Time = x, Work = -x^2 + 100)
p <- ggplot(work2time) +
geom_line(aes(x = Work, y = Time)) +
theme_classic() +
theme(text = element_text(family = "Times"))
p
Figure 1: Learning Curve of R
3 Data structure (S3)
3.1 ‘character’
x <- "this is character"
y <- "this is \"character\""
print(x)## [1] "this is character"print(y)## [1] "this is \"character\""cat(x, "\n")## this is charactercat(y, "\n")## this is "character"3.2 ‘numeric’
x <- 1
y <- 1:10
z <- seq(1, 10, by = .5)
x## [1] 1y## [1] 1 2 3 4 5 6 7 8 9 10z## [1] 1.0 1.5 2.0 2.5 3.0 3.5 4.0 4.5 5.0 5.5 6.0 6.5 7.0 7.5 8.0 8.5 9.0 9.5 10.03.3 ‘data.frame’
data <- data.frame(x = 1:10, y = 10:1, z = rep("character", 10))
data## x y z
## 1 1 10 character
## 2 2 9 character
## 3 3 8 character
## 4 4 7 character
## 5 5 6 character
## 6 6 5 character
## 7 7 4 character
## 8 8 3 character
## 9 9 2 character
## 10 10 1 charactertibble::as_tibble(data)## # A tibble: 10 × 3
## x y z
## <int> <int> <chr>
## 1 1 10 character
## 2 2 9 character
## 3 3 8 character
## 4 4 7 character
## 5 5 6 character
## 6 6 5 character
## 7 7 4 character
## 8 8 3 character
## 9 9 2 character
## 10 10 1 character## a inst data.frame
tibble::as_tibble(mtcars)## # A tibble: 32 × 11
## mpg cyl disp hp drat wt qsec vs am gear carb
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 21 6 160 110 3.9 2.62 16.5 0 1 4 4
## 2 21 6 160 110 3.9 2.88 17.0 0 1 4 4
## 3 22.8 4 108 93 3.85 2.32 18.6 1 1 4 1
## 4 21.4 6 258 110 3.08 3.22 19.4 1 0 3 1
## 5 18.7 8 360 175 3.15 3.44 17.0 0 0 3 2
## 6 18.1 6 225 105 2.76 3.46 20.2 1 0 3 1
## 7 14.3 8 360 245 3.21 3.57 15.8 0 0 3 4
## 8 24.4 4 147. 62 3.69 3.19 20 1 0 4 2
## 9 22.8 4 141. 95 3.92 3.15 22.9 1 0 4 2
## 10 19.2 6 168. 123 3.92 3.44 18.3 1 0 4 4
## # … with 22 more rows3.4 ‘list’
lst1 <- list(x = 1, y = 1:3)
lst1## $x
## [1] 1
##
## $y
## [1] 1 2 3lst2 <- list(
x = 1:10,
y = rep("character", 20), z = tibble::as_tibble(mtcars)
)
lst2## $x
## [1] 1 2 3 4 5 6 7 8 9 10
##
## $y
## [1] "character" "character" "character" "character" "character" "character" "character"
## [8] "character" "character" "character" "character" "character" "character" "character"
## [15] "character" "character" "character" "character" "character" "character"
##
## $z
## # A tibble: 32 × 11
## mpg cyl disp hp drat wt qsec vs am gear carb
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 21 6 160 110 3.9 2.62 16.5 0 1 4 4
## 2 21 6 160 110 3.9 2.88 17.0 0 1 4 4
## 3 22.8 4 108 93 3.85 2.32 18.6 1 1 4 1
## 4 21.4 6 258 110 3.08 3.22 19.4 1 0 3 1
## 5 18.7 8 360 175 3.15 3.44 17.0 0 0 3 2
## 6 18.1 6 225 105 2.76 3.46 20.2 1 0 3 1
## 7 14.3 8 360 245 3.21 3.57 15.8 0 0 3 4
## 8 24.4 4 147. 62 3.69 3.19 20 1 0 4 2
## 9 22.8 4 141. 95 3.92 3.15 22.9 1 0 4 2
## 10 19.2 6 168. 123 3.92 3.44 18.3 1 0 4 4
## # … with 22 more rows4 Packages and Functions
4.1 Package
4.2 Function
fun <- function(x = 1, y = 2) {
x + y
}
res <- fun()
res## [1] 3fun2 <- function(x = seq(0.01, .99, length.out = 100)) {
df <- data.frame(
x = rep(x, 2),
y = c(qlogis(x), 2 * qlogis(x)),
group = rep(c("a","b"),
each = 100)
)
p <- ggplot(df, aes(x=x, y=y, group=group))
# These work
p + geom_line(linetype = 2)
}
p <- fun2()
Figure 2: Demo figure
5 Regex match
5.1 grep
letters## [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w"
## [24] "x" "y" "z"grep("[a-z]", letters)## [1] 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 26txt <- c("arm","foot","lefroo", "bafoobar")
if(length(i <- grep("foo", txt)))
cat("'foo' appears at least once in\n\t", txt, "\n")## 'foo' appears at least once in
## arm foot lefroo bafoobari## [1] 2 4txt[i]## [1] "foot" "bafoobar"5.2 stringr::str_extract
shopping_list <- c("apples x4", "bag of flour", "bag of sugar", "milk x2")
stringr::str_extract(shopping_list, "\\d")## [1] "4" NA NA "2"stringr::str_extract(shopping_list, "[a-z]+")## [1] "apples" "bag" "bag" "milk"stringr::str_extract(shopping_list, "[a-z]{1,4}")## [1] "appl" "bag" "bag" "milk"stringr::str_extract(shopping_list, "\\b[a-z]{1,4}\\b")## [1] NA "bag" "bag" "milk"6 Common Packages
data <- tibble::tribble(
~ Name, ~ Description, ~ Function,
"base", "data", "data.frame, c, list, ...",
"base", "Expression", "if, else ...",
"base", "String", "paste0, paste, print, cat, ...",
"base", "Match string", "grep, grepl, sub, gsub ...",
"base", "Loop", "for, lapply, apply, mapply ...",
"data.table", "For fast read and write table", "fread, fwrite",
"dplyr", "Modify table", "select, filter, arrange, distinct, slice, mutate ...",
"ggplot2", "Visualization", "...",
"stringr", "Match strings", "str_extract ..."
)
data <- dplyr::relocate(data, Name, Function)
pretty_flex2(data, "Common Packages and Functions",
weight = c(
Description = 1.5, Name = .7))Name | Function | Description |
|---|---|---|
base | data.frame, c, list, ... | data |
base | if, else ... | Expression |
base | paste0, paste, print, cat, ... | String |
base | grep, grepl, sub, gsub ... | Match string |
base | for, lapply, apply, mapply ... | Loop |
data.table | fread, fwrite | For fast read and write table |
dplyr | select, filter, arrange, distinct, slice, mutate ... | Modify table |
ggplot2 | ... | Visualization |
stringr | str_extract ... | Match strings |
7 * S4: Classes and Methods
7.1 Classes
library(MCnebula2)
mcn <- mcnebula()
slotNames(mcn)## [1] "creation_time" "ion_mode" "melody" "mcn_dataset"
## [5] "statistic_set" "project_version" "project_path" "project_conformation"
## [9] "project_metadata" "project_api" "project_dataset" "parent_nebula"
## [13] "child_nebulae" "export_path" "export_name"mcn@mcn_dataset## An object of class "mcn_dataset"
## Slot "dataset":
## list()
##
## Slot "reference":
## list()
##
## Slot "backtrack":
## list()mcn_dataset(mcn)## An object of class "mcn_dataset"
## Slot "dataset":
## list()
##
## Slot "reference":
## list()
##
## Slot "backtrack":
## list()7.2 Methods
7.2.1 Demo (Not Run)
mcn <- mcn_5features
mcn1 <- filter_structure(mcn)
mcn1 <- create_reference(mcn1)
mcn1 <- filter_formula(mcn1, by_reference = T)
mcn1 <- create_stardust_classes(mcn1)
mcn1 <- create_features_annotation(mcn1)
mcn1 <- cross_filter_stardust(mcn1, 2, 1)
mcn1 <- create_nebula_index(mcn1)
mcn1 <- compute_spectral_similarity(mcn1)
mcn1 <- create_parent_nebula(mcn1, 0.01)
mcn1 <- create_child_nebulae(mcn1, 0.01)
mcn1 <- create_parent_layout(mcn1)
mcn1 <- create_child_layouts(mcn1)
mcn1 <- activate_nebulae(mcn1)
## optional Child-Nebulae
visualize(mcn1)
visualize(mcn1, "parent")
visualize(mcn1, 1)
visualize_all(mcn1)7.2.2 Demo (Run)
mcn <- mcn_5features
mcn1 <- filter_structure(mcn)## [INFO] MCnebula2: filter_structure## ## msframe: filter_msframe group_by: ~ .features_idmcn1 <- create_reference(mcn1)## [INFO] MCnebula2: create_reference## ## create_reference: fill == T
## filling missing features with filtered formula## [INFO] MCnebula2: filter_formula## ## msframe: filter_msframe group_by: ~ .features_idmcn1 <- filter_formula(mcn1, by_reference = T)## [INFO] MCnebula2: filter_formula## ## filter_formula: by_reference == T
## case formula, ignore `fun_filter`mcn1 <- create_stardust_classes(mcn1)## [INFO] MCnebula2: create_stardust_classes## [INFO] MCnebula2: filter_ppcp## ## filter_ppcp: by_reference == T## ## filter_ppcp: validate annotation data .canopus >>> .f3_canopus## ## msframe: filter_msframe group_by: ~ paste0(.features_id, "_", .candidates_id)mcn1 <- create_features_annotation(mcn1)## [INFO] MCnebula2: create_features_annotationmcn1 <- cross_filter_stardust(mcn1, 2, 1)## [INFO] MCnebula2: cross_filter_stardust## ## cross_filter_stardust: quantity## ## cross_filter_stardust: score## ## cross_filter_stardust: identicalmcn1 <- create_nebula_index(mcn1)## [INFO] MCnebula2: create_nebula_indexmcn1 <- compute_spectral_similarity(mcn1)## [INFO] MCnebula2: compute_spectral_similarity## ## compute_spectral_similarity: compareSpectramcn1 <- create_parent_nebula(mcn1, 0.01)## [INFO] MCnebula2: create_parent_nebulamcn1 <- create_child_nebulae(mcn1, 0.01)## [INFO] MCnebula2: create_child_nebulaemcn1 <- create_parent_layout(mcn1)## [INFO] MCnebula2: create_parent_layoutmcn1 <- create_child_layouts(mcn1)## [INFO] MCnebula2: create_child_layoutsmcn1 <- activate_nebulae(mcn1)## [INFO] MCnebula2: activate_nebulae## optional Child-Nebulae
visualize(mcn1)## [INFO] MCnebula2: visualize## Specify item as following to visualize:## # A tibble: 18 × 3
## seq hierarchy class.name
## <int> <dbl> <chr>
## 1 1 5 Amino acids and derivatives
## 2 2 4 Amino acids, peptides, and analogues
## 3 3 2 Benzenoids
## 4 4 4 Carbonyl compounds
## 5 5 5 Carboxylic acid amides
## 6 6 4 Carboxylic acid derivatives
## 7 7 3 Carboxylic acids and derivatives
## 8 8 3 Heteroaromatic compounds
## 9 9 4 Indoles
## 10 10 5 Ketones
## 11 11 3 Lactams
## 12 12 3 Macrolactams
## 13 13 2 Organic acids and derivatives
## 14 14 3 Organic oxides
## 15 15 5 Peptides
## 16 16 2 Phenylpropanoids and polyketides
## 17 17 3 Pyrroles
## 18 18 4 Substituted pyrrolesvisualize(mcn1, "parent")## [INFO] MCnebula2: visualize
visualize(mcn1, 1)## [INFO] MCnebula2: visualize
visualize_all(mcn1)## [INFO] MCnebula2: visualize_all## ## BEGIN: current.viewport:
## viewport[ROOT]## ## info: current.viewport:
## viewport[GRID.VP.3436]## ## info: current.viewport:
## viewport[legend_hierarchy]## ## info: current.viewport:
## viewport[sub_panel]## ## info: current.viewport:
## viewport[ROOT]## ## visualize: legend:
## extract legend from `ggset(child_nebulae(x))[[1]]` (nebula names:).
## In default, legend scales have been unified for all child-nebulae.## ## END: current.viewport:
## viewport[GRID.VP.3437]