Import data
# excel file
nfl <- read_excel("../00_data/MyData.xlsx")
data
## function (..., list = character(), package = NULL, lib.loc = NULL,
## verbose = getOption("verbose"), envir = .GlobalEnv, overwrite = TRUE)
## {
## fileExt <- function(x) {
## db <- grepl("\\.[^.]+\\.(gz|bz2|xz)$", x)
## ans <- sub(".*\\.", "", x)
## ans[db] <- sub(".*\\.([^.]+\\.)(gz|bz2|xz)$", "\\1\\2",
## x[db])
## ans
## }
## my_read_table <- function(...) {
## lcc <- Sys.getlocale("LC_COLLATE")
## on.exit(Sys.setlocale("LC_COLLATE", lcc))
## Sys.setlocale("LC_COLLATE", "C")
## read.table(...)
## }
## stopifnot(is.character(list))
## names <- c(as.character(substitute(list(...))[-1L]), list)
## if (!is.null(package)) {
## if (!is.character(package))
## stop("'package' must be a character vector or NULL")
## }
## paths <- find.package(package, lib.loc, verbose = verbose)
## if (is.null(lib.loc))
## paths <- c(path.package(package, TRUE), if (!length(package)) getwd(),
## paths)
## paths <- unique(normalizePath(paths[file.exists(paths)]))
## paths <- paths[dir.exists(file.path(paths, "data"))]
## dataExts <- tools:::.make_file_exts("data")
## if (length(names) == 0L) {
## db <- matrix(character(), nrow = 0L, ncol = 4L)
## for (path in paths) {
## entries <- NULL
## packageName <- if (file_test("-f", file.path(path,
## "DESCRIPTION")))
## basename(path)
## else "."
## if (file_test("-f", INDEX <- file.path(path, "Meta",
## "data.rds"))) {
## entries <- readRDS(INDEX)
## }
## else {
## dataDir <- file.path(path, "data")
## entries <- tools::list_files_with_type(dataDir,
## "data")
## if (length(entries)) {
## entries <- unique(tools::file_path_sans_ext(basename(entries)))
## entries <- cbind(entries, "")
## }
## }
## if (NROW(entries)) {
## if (is.matrix(entries) && ncol(entries) == 2L)
## db <- rbind(db, cbind(packageName, dirname(path),
## entries))
## else warning(gettextf("data index for package %s is invalid and will be ignored",
## sQuote(packageName)), domain = NA, call. = FALSE)
## }
## }
## colnames(db) <- c("Package", "LibPath", "Item", "Title")
## footer <- if (missing(package))
## paste0("Use ", sQuote(paste("data(package =", ".packages(all.available = TRUE))")),
## "\n", "to list the data sets in all *available* packages.")
## else NULL
## y <- list(title = "Data sets", header = NULL, results = db,
## footer = footer)
## class(y) <- "packageIQR"
## return(y)
## }
## paths <- file.path(paths, "data")
## for (name in names) {
## found <- FALSE
## for (p in paths) {
## tmp_env <- if (overwrite)
## envir
## else new.env()
## if (file_test("-f", file.path(p, "Rdata.rds"))) {
## rds <- readRDS(file.path(p, "Rdata.rds"))
## if (name %in% names(rds)) {
## found <- TRUE
## if (verbose)
## message(sprintf("name=%s:\t found in Rdata.rds",
## name), domain = NA)
## objs <- rds[[name]]
## lazyLoad(file.path(p, "Rdata"), envir = tmp_env,
## filter = function(x) x %in% objs)
## break
## }
## else if (verbose)
## message(sprintf("name=%s:\t NOT found in names() of Rdata.rds, i.e.,\n\t%s\n",
## name, paste(names(rds), collapse = ",")),
## domain = NA)
## }
## files <- list.files(p, full.names = TRUE)
## files <- files[grep(name, files, fixed = TRUE)]
## if (length(files) > 1L) {
## o <- match(fileExt(files), dataExts, nomatch = 100L)
## paths0 <- dirname(files)
## paths0 <- factor(paths0, levels = unique(paths0))
## files <- files[order(paths0, o)]
## }
## if (length(files)) {
## for (file in files) {
## if (verbose)
## message("name=", name, ":\t file= ...", .Platform$file.sep,
## basename(file), "::\t", appendLF = FALSE,
## domain = NA)
## ext <- fileExt(file)
## if (basename(file) != paste0(name, ".", ext))
## found <- FALSE
## else {
## found <- TRUE
## switch(ext, R = , r = {
## library("utils")
## sys.source(file, chdir = TRUE, envir = tmp_env)
## }, RData = , rdata = , rda = load(file, envir = tmp_env),
## TXT = , txt = , tab = , tab.gz = , tab.bz2 = ,
## tab.xz = , txt.gz = , txt.bz2 = , txt.xz = assign(name,
## my_read_table(file, header = TRUE, as.is = FALSE),
## envir = tmp_env), CSV = , csv = , csv.gz = ,
## csv.bz2 = , csv.xz = assign(name, my_read_table(file,
## header = TRUE, sep = ";", as.is = FALSE),
## envir = tmp_env), found <- FALSE)
## }
## if (found)
## break
## }
## if (verbose)
## message(if (!found)
## "*NOT* ", "found", domain = NA)
## }
## if (found)
## break
## }
## if (!found) {
## warning(gettextf("data set %s not found", sQuote(name)),
## domain = NA)
## }
## else if (!overwrite) {
## for (o in ls(envir = tmp_env, all.names = TRUE)) {
## if (exists(o, envir = envir, inherits = FALSE))
## warning(gettextf("an object named %s already exists and will not be overwritten",
## sQuote(o)))
## else assign(o, get(o, envir = tmp_env, inherits = FALSE),
## envir = envir)
## }
## rm(tmp_env)
## }
## }
## invisible(names)
## }
## <bytecode: 0x000001d285e08430>
## <environment: namespace:utils>
Apply the following dplyr verbs to your data
Filter rows
filter(nfl, year == 2019)
## # A tibble: 544 × 8
## team team_name year total home away week weekly_attendance
## <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Arizona Cardinals 2019 1000509 490586 509923 1 60687
## 2 Arizona Cardinals 2019 1000509 490586 509923 2 70126
## 3 Arizona Cardinals 2019 1000509 490586 509923 3 60104
## 4 Arizona Cardinals 2019 1000509 490586 509923 4 60500
## 5 Arizona Cardinals 2019 1000509 490586 509923 5 46012
## 6 Arizona Cardinals 2019 1000509 490586 509923 6 60140
## 7 Arizona Cardinals 2019 1000509 490586 509923 7 73577
## 8 Arizona Cardinals 2019 1000509 490586 509923 8 73064
## 9 Arizona Cardinals 2019 1000509 490586 509923 9 60986
## 10 Arizona Cardinals 2019 1000509 490586 509923 10 40038
## # ℹ 534 more rows
Arrange rows
arrange(nfl, weekly_attendance)
## # A tibble: 10,846 × 8
## team team_name year total home away week weekly_attendance
## <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Dallas Cowboys 2009 1307231 718055 589176 17 100621
## 2 Philadelphia Eagles 2009 1144895 553152 591743 17 100621
## 3 Arizona Cardinals 2005 920848 401035 519813 4 103467
## 4 San Francisco 49ers 2005 1113073 523426 589647 4 103467
## 5 Dallas Cowboys 2009 1307231 718055 589176 2 105121
## 6 New York Giants 2009 1223927 629615 594312 2 105121
## 7 Arizona Cardinals 2003 804401 288499 515902 2 23127
## 8 Seattle Seahawks 2003 1005938 512150 493788 2 23127
## 9 Arizona Cardinals 2003 804401 288499 515902 15 23217
## 10 Carolina Panthers 2003 1078988 582566 496422 15 23217
## # ℹ 10,836 more rows
Select columns
select(nfl, team_name, year, week, weekly_attendance)
## # A tibble: 10,846 × 4
## team_name year week weekly_attendance
## <chr> <dbl> <dbl> <chr>
## 1 Cardinals 2000 1 77434
## 2 Cardinals 2000 2 66009
## 3 Cardinals 2000 3 NA
## 4 Cardinals 2000 4 71801
## 5 Cardinals 2000 5 66985
## 6 Cardinals 2000 6 44296
## 7 Cardinals 2000 7 38293
## 8 Cardinals 2000 8 62981
## 9 Cardinals 2000 9 35286
## 10 Cardinals 2000 10 52244
## # ℹ 10,836 more rows
Add columns
# Select Team name, year, week, weekly attendance
nfl %>%
group_by(team_name) %>%
mutate(attendance_cumsum = cumsum(weekly_attendance))
## # A tibble: 10,846 × 9
## # Groups: team_name [32]
## team team_name year total home away week weekly_attendance
## <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 Arizona Cardinals 2000 893926 387475 506451 1 77434
## 2 Arizona Cardinals 2000 893926 387475 506451 2 66009
## 3 Arizona Cardinals 2000 893926 387475 506451 3 NA
## 4 Arizona Cardinals 2000 893926 387475 506451 4 71801
## 5 Arizona Cardinals 2000 893926 387475 506451 5 66985
## 6 Arizona Cardinals 2000 893926 387475 506451 6 44296
## 7 Arizona Cardinals 2000 893926 387475 506451 7 38293
## 8 Arizona Cardinals 2000 893926 387475 506451 8 62981
## 9 Arizona Cardinals 2000 893926 387475 506451 9 35286
## 10 Arizona Cardinals 2000 893926 387475 506451 10 52244
## # ℹ 10,836 more rows
## # ℹ 1 more variable: attendance_cumsum <dbl>
Summarize by groups
nfl <- nfl %>%
mutate(weekly_attendance = as.numeric(weekly_attendance))
nfl %>%
group_by(team_name) %>%
summarise(
week = n(),
avg_weekly_attendance = mean(weekly_attendance, na.rm = TRUE),
total_weekly_attendance = sum(weekly_attendance, na.rm = TRUE)) %>%
ggplot(aes(x = avg_weekly_attendance, y = total_weekly_attendance)) +
geom_point(aes(size = week), alpha = 0.3)
