M3 Act1
Santiago Guerra Leija
2023-08-29
####Programas y Set up ###Desacargar Base
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.2 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.3 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(dplyr)
library(ggplot2)
library(readxl)
df_bank <- read_csv("C:\\Users\\sguerra\\Downloads\\bank.csv")## Rows: 4521 Columns: 17
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (10): job, marital, education, default, housing, loan, contact, month, p...
## dbl (7): age, balance, day, duration, campaign, pdays, previous
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.View (df_bank)
str (df_bank) #structure, nos dice que tipo de variables tenemos## spc_tbl_ [4,521 × 17] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
## $ age : num [1:4521] 30 33 35 30 59 35 36 39 41 43 ...
## $ job : chr [1:4521] "unemployed" "services" "management" "management" ...
## $ marital : chr [1:4521] "married" "married" "single" "married" ...
## $ education: chr [1:4521] "primary" "secondary" "tertiary" "tertiary" ...
## $ default : chr [1:4521] "no" "no" "no" "no" ...
## $ balance : num [1:4521] 1787 4789 1350 1476 0 ...
## $ housing : chr [1:4521] "no" "yes" "yes" "yes" ...
## $ loan : chr [1:4521] "no" "yes" "no" "yes" ...
## $ contact : chr [1:4521] "cellular" "cellular" "cellular" "unknown" ...
## $ day : num [1:4521] 19 11 16 3 5 23 14 6 14 17 ...
## $ month : chr [1:4521] "oct" "may" "apr" "jun" ...
## $ duration : num [1:4521] 79 220 185 199 226 141 341 151 57 313 ...
## $ campaign : num [1:4521] 1 1 1 4 1 2 1 2 2 1 ...
## $ pdays : num [1:4521] -1 339 330 -1 -1 176 330 -1 -1 147 ...
## $ previous : num [1:4521] 0 4 1 0 0 3 2 0 0 2 ...
## $ poutcome : chr [1:4521] "unknown" "failure" "failure" "unknown" ...
## $ y : chr [1:4521] "no" "no" "no" "no" ...
## - attr(*, "spec")=
## .. cols(
## .. age = col_double(),
## .. job = col_character(),
## .. marital = col_character(),
## .. education = col_character(),
## .. default = col_character(),
## .. balance = col_double(),
## .. housing = col_character(),
## .. loan = col_character(),
## .. contact = col_character(),
## .. day = col_double(),
## .. month = col_character(),
## .. duration = col_double(),
## .. campaign = col_double(),
## .. pdays = col_double(),
## .. previous = col_double(),
## .. poutcome = col_character(),
## .. y = col_character()
## .. )
## - attr(*, "problems")=<externalptr>summary(df_bank)## age job marital education
## Min. :19.00 Length:4521 Length:4521 Length:4521
## 1st Qu.:33.00 Class :character Class :character Class :character
## Median :39.00 Mode :character Mode :character Mode :character
## Mean :41.17
## 3rd Qu.:49.00
## Max. :87.00
## default balance housing loan
## Length:4521 Min. :-3313 Length:4521 Length:4521
## Class :character 1st Qu.: 69 Class :character Class :character
## Mode :character Median : 444 Mode :character Mode :character
## Mean : 1423
## 3rd Qu.: 1480
## Max. :71188
## contact day month duration
## Length:4521 Min. : 1.00 Length:4521 Min. : 4
## Class :character 1st Qu.: 9.00 Class :character 1st Qu.: 104
## Mode :character Median :16.00 Mode :character Median : 185
## Mean :15.92 Mean : 264
## 3rd Qu.:21.00 3rd Qu.: 329
## Max. :31.00 Max. :3025
## campaign pdays previous poutcome
## Min. : 1.000 Min. : -1.00 Min. : 0.0000 Length:4521
## 1st Qu.: 1.000 1st Qu.: -1.00 1st Qu.: 0.0000 Class :character
## Median : 2.000 Median : -1.00 Median : 0.0000 Mode :character
## Mean : 2.794 Mean : 39.77 Mean : 0.5426
## 3rd Qu.: 3.000 3rd Qu.: -1.00 3rd Qu.: 0.0000
## Max. :50.000 Max. :871.00 Max. :25.0000
## y
## Length:4521
## Class :character
## Mode :character
##
##
## glimpse(df_bank)## Rows: 4,521
## Columns: 17
## $ age <dbl> 30, 33, 35, 30, 59, 35, 36, 39, 41, 43, 39, 43, 36, 20, 31, …
## $ job <chr> "unemployed", "services", "management", "management", "blue-…
## $ marital <chr> "married", "married", "single", "married", "married", "singl…
## $ education <chr> "primary", "secondary", "tertiary", "tertiary", "secondary",…
## $ default <chr> "no", "no", "no", "no", "no", "no", "no", "no", "no", "no", …
## $ balance <dbl> 1787, 4789, 1350, 1476, 0, 747, 307, 147, 221, -88, 9374, 26…
## $ housing <chr> "no", "yes", "yes", "yes", "yes", "no", "yes", "yes", "yes",…
## $ loan <chr> "no", "yes", "no", "yes", "no", "no", "no", "no", "no", "yes…
## $ contact <chr> "cellular", "cellular", "cellular", "unknown", "unknown", "c…
## $ day <dbl> 19, 11, 16, 3, 5, 23, 14, 6, 14, 17, 20, 17, 13, 30, 29, 29,…
## $ month <chr> "oct", "may", "apr", "jun", "may", "feb", "may", "may", "may…
## $ duration <dbl> 79, 220, 185, 199, 226, 141, 341, 151, 57, 313, 273, 113, 32…
## $ campaign <dbl> 1, 1, 1, 4, 1, 2, 1, 2, 2, 1, 1, 2, 2, 1, 1, 2, 5, 1, 1, 1, …
## $ pdays <dbl> -1, 339, 330, -1, -1, 176, 330, -1, -1, 147, -1, -1, -1, -1,…
## $ previous <dbl> 0, 4, 1, 0, 0, 3, 2, 0, 0, 2, 0, 0, 0, 0, 1, 0, 0, 2, 0, 1, …
## $ poutcome <chr> "unknown", "failure", "failure", "unknown", "unknown", "fail…
## $ y <chr> "no", "no", "no", "no", "no", "no", "no", "no", "no", "no", …str(df_bank)## spc_tbl_ [4,521 × 17] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
## $ age : num [1:4521] 30 33 35 30 59 35 36 39 41 43 ...
## $ job : chr [1:4521] "unemployed" "services" "management" "management" ...
## $ marital : chr [1:4521] "married" "married" "single" "married" ...
## $ education: chr [1:4521] "primary" "secondary" "tertiary" "tertiary" ...
## $ default : chr [1:4521] "no" "no" "no" "no" ...
## $ balance : num [1:4521] 1787 4789 1350 1476 0 ...
## $ housing : chr [1:4521] "no" "yes" "yes" "yes" ...
## $ loan : chr [1:4521] "no" "yes" "no" "yes" ...
## $ contact : chr [1:4521] "cellular" "cellular" "cellular" "unknown" ...
## $ day : num [1:4521] 19 11 16 3 5 23 14 6 14 17 ...
## $ month : chr [1:4521] "oct" "may" "apr" "jun" ...
## $ duration : num [1:4521] 79 220 185 199 226 141 341 151 57 313 ...
## $ campaign : num [1:4521] 1 1 1 4 1 2 1 2 2 1 ...
## $ pdays : num [1:4521] -1 339 330 -1 -1 176 330 -1 -1 147 ...
## $ previous : num [1:4521] 0 4 1 0 0 3 2 0 0 2 ...
## $ poutcome : chr [1:4521] "unknown" "failure" "failure" "unknown" ...
## $ y : chr [1:4521] "no" "no" "no" "no" ...
## - attr(*, "spec")=
## .. cols(
## .. age = col_double(),
## .. job = col_character(),
## .. marital = col_character(),
## .. education = col_character(),
## .. default = col_character(),
## .. balance = col_double(),
## .. housing = col_character(),
## .. loan = col_character(),
## .. contact = col_character(),
## .. day = col_double(),
## .. month = col_character(),
## .. duration = col_double(),
## .. campaign = col_double(),
## .. pdays = col_double(),
## .. previous = col_double(),
## .. poutcome = col_character(),
## .. y = col_character()
## .. )
## - attr(*, "problems")=<externalptr>summary(df_bank)## age job marital education
## Min. :19.00 Length:4521 Length:4521 Length:4521
## 1st Qu.:33.00 Class :character Class :character Class :character
## Median :39.00 Mode :character Mode :character Mode :character
## Mean :41.17
## 3rd Qu.:49.00
## Max. :87.00
## default balance housing loan
## Length:4521 Min. :-3313 Length:4521 Length:4521
## Class :character 1st Qu.: 69 Class :character Class :character
## Mode :character Median : 444 Mode :character Mode :character
## Mean : 1423
## 3rd Qu.: 1480
## Max. :71188
## contact day month duration
## Length:4521 Min. : 1.00 Length:4521 Min. : 4
## Class :character 1st Qu.: 9.00 Class :character 1st Qu.: 104
## Mode :character Median :16.00 Mode :character Median : 185
## Mean :15.92 Mean : 264
## 3rd Qu.:21.00 3rd Qu.: 329
## Max. :31.00 Max. :3025
## campaign pdays previous poutcome
## Min. : 1.000 Min. : -1.00 Min. : 0.0000 Length:4521
## 1st Qu.: 1.000 1st Qu.: -1.00 1st Qu.: 0.0000 Class :character
## Median : 2.000 Median : -1.00 Median : 0.0000 Mode :character
## Mean : 2.794 Mean : 39.77 Mean : 0.5426
## 3rd Qu.: 3.000 3rd Qu.: -1.00 3rd Qu.: 0.0000
## Max. :50.000 Max. :871.00 Max. :25.0000
## y
## Length:4521
## Class :character
## Mode :character
##
##
## ###Histograma de Edad
hist(x = df_bank$age)
hist(x = df_bank$age, main = "HISTOGRAMA DE EDAD", col = "cadetblue", xlab = "Edad", ylab = "Frecuencia")
hist(x = df_bank$age, breaks = 3, main = "HISTOGRAMA DE EDAD", col = "cadetblue", xlab = "Edad", ylab = "Frecuencia")
###Grafica de educación
plot(factor(df_bank$education), main = "Gráfica Educación", col = c("blue","green","yellow","grey"), xlab = "Nivel de Educación", ylab = "Frecuencia")
plot(x = df_bank$age, y = df_bank$balance)
plot(x = df_bank$age, y= df_bank$balance, col = factor(df_bank$education %>% c("royalblue", "pink", "purple", "grey")))
plot(x=df_bank$age, y=df_bank$balance, col =factor(df_bank$loan))
legend ## function (x, y = NULL, legend, fill = NULL, col = par("col"),
## border = "black", lty, lwd, pch, angle = 45, density = NULL,
## bty = "o", bg = par("bg"), box.lwd = par("lwd"), box.lty = par("lty"),
## box.col = par("fg"), pt.bg = NA, cex = 1, pt.cex = cex, pt.lwd = lwd,
## xjust = 0, yjust = 1, x.intersp = 1, y.intersp = 1, adj = c(0,
## 0.5), text.width = NULL, text.col = par("col"), text.font = NULL,
## merge = do.lines && has.pch, trace = FALSE, plot = TRUE,
## ncol = 1, horiz = FALSE, title = NULL, inset = 0, xpd, title.col = text.col[1],
## title.adj = 0.5, title.cex = cex[1], title.font = text.font[1],
## seg.len = 2)
## {
## if (missing(legend) && !missing(y) && (is.character(y) ||
## is.expression(y))) {
## legend <- y
## y <- NULL
## }
## mfill <- !missing(fill) || !missing(density)
## if (!missing(xpd)) {
## op <- par("xpd")
## on.exit(par(xpd = op))
## par(xpd = xpd)
## }
## text.font <- if (is.null(text.font))
## par("font")
## else text.font
## title <- as.graphicsAnnot(title)
## if (length(title) > 1)
## stop("invalid 'title'")
## legend <- as.graphicsAnnot(legend)
## if (any(sapply(legend, is.language)))
## legend <- as.expression(legend)
## n.leg <- length(legend)
## if (n.leg == 0)
## stop("'legend' is of length 0")
## auto <- if (is.character(x))
## match.arg(x, c("bottomright", "bottom", "bottomleft",
## "left", "topleft", "top", "topright", "right", "center"))
## else NA
## if (is.na(auto)) {
## xy <- xy.coords(x, y, setLab = FALSE)
## x <- xy$x
## y <- xy$y
## nx <- length(x)
## if (nx < 1 || nx > 2)
## stop("invalid coordinate lengths")
## }
## else nx <- 0
## reverse.xaxis <- par("xaxp")[1] > par("xaxp")[2]
## reverse.yaxis <- par("yaxp")[1] > par("yaxp")[2]
## xlog <- par("xlog")
## ylog <- par("ylog")
## cex <- rep(cex, length.out = n.leg)
## x.intersp <- rep(x.intersp, length.out = n.leg)
## seg.len <- rep(seg.len, length.out = n.leg)
## rect2 <- function(left, top, dx, dy, density = NULL, angle,
## ...) {
## r <- left + dx
## if (xlog) {
## left <- 10^left
## r <- 10^r
## }
## b <- top - dy
## if (ylog) {
## top <- 10^top
## b <- 10^b
## }
## rect(left, top, r, b, angle = angle, density = density,
## ...)
## }
## segments2 <- function(x1, y1, dx, dy, ...) {
## x2 <- x1 + dx
## if (xlog) {
## x1 <- 10^x1
## x2 <- 10^x2
## }
## y2 <- y1 + dy
## if (ylog) {
## y1 <- 10^y1
## y2 <- 10^y2
## }
## segments(x1, y1, x2, y2, ...)
## }
## points2 <- function(x, y, ...) {
## if (xlog)
## x <- 10^x
## if (ylog)
## y <- 10^y
## points(x, y, ...)
## }
## text2 <- function(x, y, ...) {
## if (xlog)
## x <- 10^x
## if (ylog)
## y <- 10^y
## text(x, y, ...)
## }
## colwise <- function(x, n, ncol, n.legpercol, fun, reverse = FALSE) {
## xmat <- matrix(c(rep(x, length.out = n), rep(0L, n.legpercol *
## ncol - n)), ncol = ncol)
## res <- apply(xmat, 2, fun)
## res[res == 0L] <- max(res)
## if (reverse)
## -res
## else res
## }
## rowwise <- function(x, n, ncol, n.legpercol, fun, reverse = FALSE) {
## xmat <- matrix(c(rep(x, length.out = n), rep(0L, n.legpercol *
## ncol - n)), ncol = ncol)
## res <- apply(xmat, 1, fun)
## if (reverse)
## -res
## else res
## }
## if (trace) {
## catn <- function(...) do.call(cat, c(lapply(list(...),
## formatC), "\n"))
## fv <- function(...) paste(vapply(lapply(list(...), formatC),
## paste, collapse = ",", ""), collapse = ", ")
## }
## n.legpercol <- if (horiz) {
## if (ncol != 1)
## warning(gettextf("horizontal specification overrides: Number of columns := %d",
## n.leg), domain = NA)
## ncol <- n.leg
## 1
## }
## else ceiling(n.leg/ncol)
## Cex <- cex * par("cex")
## if (is.null(text.width))
## text.width <- max(abs(mapply(strwidth, legend, cex = cex,
## font = text.font, MoreArgs = list(units = "user"))))
## else if ((length(text.width) > 1L && any(is.na(text.width))) ||
## (all(!is.na(text.width)) && (!is.numeric(text.width) ||
## any(text.width < 0))))
## stop("'text.width' must be numeric, >= 0, or a scalar NA")
## if (auto.text.width <- all(is.na(text.width))) {
## text.width <- abs(mapply(strwidth, legend, cex = cex,
## font = text.font, MoreArgs = list(units = "user")))
## ncol <- ceiling(n.leg/n.legpercol)
## }
## xyc <- xyinch(par("cin"), warn.log = FALSE)
## xc <- Cex * xyc[1L]
## yc <- Cex * xyc[2L]
## if (any(xc < 0))
## text.width <- -text.width
## xchar <- xc
## xextra <- 0
## y.intersp <- rep(y.intersp, length.out = n.legpercol)
## yextra <- rowwise(yc, n = n.leg, ncol = ncol, n.legpercol = n.legpercol,
## fun = function(x) max(abs(x)), reverse = reverse.yaxis) *
## (y.intersp - 1)
## ymax <- sign(yc[1]) * max(abs(yc)) * max(1, mapply(strheight,
## legend, cex = cex, font = text.font, MoreArgs = list(units = "user"))/yc)
## ychar <- yextra + ymax
## ymaxtitle <- title.cex * par("cex") * xyc[2L] * max(1, strheight(title,
## cex = title.cex, font = title.font, units = "user")/(title.cex *
## par("cex") * xyc[2L]))
## ychartitle <- yextra[1] + ymaxtitle
## if (trace)
## catn(" xchar=", fv(xchar), "; (yextra, ychar)=", fv(yextra,
## ychar))
## if (mfill) {
## xbox <- xc * 0.8
## ybox <- yc * 0.5
## dx.fill <- max(xbox)
## }
## do.lines <- (!missing(lty) && (is.character(lty) || any(lty >
## 0))) || !missing(lwd)
## has.pch <- !missing(pch) && length(pch) > 0
## if (do.lines) {
## x.off <- if (merge)
## -0.7
## else 0
## }
## else if (merge)
## warning("'merge = TRUE' has no effect when no line segments are drawn")
## if (has.pch) {
## if (is.character(pch) && !is.na(pch[1L]) && nchar(pch[1L],
## type = "c") > 1) {
## if (length(pch) > 1)
## warning("not using pch[2..] since pch[1L] has multiple chars")
## np <- nchar(pch[1L], type = "c")
## pch <- substr(rep.int(pch[1L], np), 1L:np, 1L:np)
## }
## if (!is.character(pch))
## pch <- as.integer(pch)
## }
## if (is.na(auto)) {
## if (xlog)
## x <- log10(x)
## if (ylog)
## y <- log10(y)
## }
## if (nx == 2) {
## x <- sort(x)
## y <- sort(y)
## left <- x[1L]
## top <- y[2L]
## w <- diff(x)
## h <- diff(y)
## w0 <- w/ncol
## x <- mean(x)
## y <- mean(y)
## if (missing(xjust))
## xjust <- 0.5
## if (missing(yjust))
## yjust <- 0.5
## }
## else {
## yc <- rowwise(yc, n.leg, ncol, n.legpercol, fun = function(x) max(abs(x)),
## reverse = reverse.yaxis)
## h <- sum(ychar) + yc[length(yc)] + (!is.null(title)) *
## ychartitle
## xch1 <- colwise(xchar, n.leg, ncol, n.legpercol, fun = function(x) max(abs(x)),
## reverse = reverse.xaxis)
## x.interspCol <- colwise(x.intersp, n.leg, ncol, n.legpercol,
## fun = max)
## seg.lenCol <- colwise(seg.len, n.leg, ncol, n.legpercol,
## fun = max)
## text.width <- colwise(text.width, n = if (auto.text.width)
## n.leg
## else ncol, ncol, n.legpercol = if (auto.text.width)
## n.legpercol
## else 1, fun = function(x) max(abs(x)), reverse = reverse.xaxis)
## w0 <- text.width + (x.interspCol + 1) * xch1
## if (mfill)
## w0 <- w0 + dx.fill
## if (do.lines)
## w0 <- w0 + (seg.lenCol + x.off) * xch1
## w <- sum(w0) + 0.5 * xch1[ncol]
## if (!is.null(title) && (abs(tw <- strwidth(title, units = "user",
## cex = title.cex, font = title.font) + 0.5 * title.cex *
## par("cex") * xyc[1L])) > abs(w)) {
## xextra <- (tw - w)/2
## w <- tw
## }
## if (is.na(auto)) {
## left <- x - xjust * w
## top <- y + (1 - yjust) * h
## }
## else {
## usr <- par("usr")
## inset <- rep_len(inset, 2)
## insetx <- inset[1L] * (usr[2L] - usr[1L])
## left <- switch(auto, bottomright = , topright = ,
## right = usr[2L] - w - insetx, bottomleft = ,
## left = , topleft = usr[1L] + insetx, bottom = ,
## top = , center = (usr[1L] + usr[2L] - w)/2)
## insety <- inset[2L] * (usr[4L] - usr[3L])
## top <- switch(auto, bottomright = , bottom = , bottomleft = usr[3L] +
## h + insety, topleft = , top = , topright = usr[4L] -
## insety, left = , right = , center = (usr[3L] +
## usr[4L] + h)/2)
## }
## }
## if (plot && bty != "n") {
## if (trace)
## catn(" rect2(", left, ",", top, ", w=", w, ", h=",
## h, ", ...)", sep = "")
## rect2(left, top, dx = w, dy = h, col = bg, density = NULL,
## lwd = box.lwd, lty = box.lty, border = box.col)
## }
## xt <- left + xc + xextra + rep(c(0, cumsum(w0))[1L:ncol],
## each = n.legpercol, length.out = n.leg)
## topspace <- 0.5 * ymax + (!is.null(title)) * ychartitle
## yt <- top - topspace - cumsum((c(0, ychar)/2 + c(ychar, 0)/2)[1L:n.legpercol])
## yt <- rep(yt, length.out = n.leg)
## if (mfill) {
## if (plot) {
## if (!is.null(fill))
## fill <- rep_len(fill, n.leg)
## rect2(left = xt, top = yt + ybox/2, dx = xbox, dy = ybox,
## col = fill, density = density, angle = angle,
## border = border)
## }
## xt <- xt + dx.fill
## }
## if (plot && (has.pch || do.lines))
## col <- rep_len(col, n.leg)
## if (missing(lwd) || is.null(lwd))
## lwd <- par("lwd")
## if (do.lines) {
## if (missing(lty) || is.null(lty))
## lty <- 1
## lty <- rep_len(lty, n.leg)
## lwd <- rep_len(lwd, n.leg)
## ok.l <- !is.na(lty) & (is.character(lty) | lty > 0) &
## !is.na(lwd)
## if (trace)
## catn(" segments2(", xt[ok.l] + x.off * xchar[ok.l],
## ",", yt[ok.l], ", dx=", (seg.len * xchar)[ok.l],
## ", dy=0, ...)")
## if (plot)
## segments2(xt[ok.l] + x.off * xchar[ok.l], yt[ok.l],
## dx = (seg.len * xchar)[ok.l], dy = 0, lty = lty[ok.l],
## lwd = lwd[ok.l], col = col[ok.l])
## xt <- xt + (seg.len + x.off) * xchar
## }
## if (has.pch) {
## pch <- rep_len(pch, n.leg)
## pt.bg <- rep_len(pt.bg, n.leg)
## pt.cex <- rep_len(pt.cex, n.leg)
## pt.lwd <- rep_len(pt.lwd, n.leg)
## ok <- !is.na(pch)
## if (!is.character(pch)) {
## ok <- ok & (pch >= 0 | pch <= -32)
## }
## else {
## ok <- ok & nzchar(pch)
## }
## x1 <- (if (merge && do.lines)
## xt - (seg.len/2) * xchar
## else xt)[ok]
## y1 <- yt[ok]
## if (trace)
## catn(" points2(", x1, ",", y1, ", pch=", pch[ok],
## ", ...)")
## if (plot)
## points2(x1, y1, pch = pch[ok], col = col[ok], cex = pt.cex[ok],
## bg = pt.bg[ok], lwd = pt.lwd[ok])
## }
## xt <- xt + x.intersp * xc
## if (plot) {
## if (!is.null(title))
## text2(left + w * title.adj, top - ymaxtitle, labels = title,
## adj = c(title.adj, 0), cex = title.cex, col = title.col,
## font = title.font)
## text2(xt, yt, labels = legend, adj = adj, cex = cex,
## col = text.col, font = text.font)
## }
## invisible(list(rect = list(w = w, h = h, left = left, top = top),
## text = list(x = xt, y = yt)))
## }
## <bytecode: 0x00000130a20058f8>
## <environment: namespace:graphics>###Diagrama de caja
plot (x = factor(df_bank$education), y = df_bank$age, main ="Edad por nivel educativo")
plot (x = factor(df_bank$education), y = df_bank$age, main ="Edad por nivel educativo",
xlab = "Nivel educativo", ylab = "Edad", col = c("blue", "pink","yellow","grey" ))
boxplot(x = df_bank$age, col = "pink")
###Gráfico de mosaico
plot(x = factor (df_bank$marital), y = factor(df_bank$education))
###Función barplot
Tabla de contigencia
table(df_bank$education)##
## primary secondary tertiary unknown
## 678 2306 1350 187tab_bank <- table(df_bank$loan, df_bank$education)
tab_bank##
## primary secondary tertiary unknown
## no 584 1890 1176 180
## yes 94 416 174 7barplot (tab_bank)
#Maregnes de la tabla
prop.table (tab_bank, margin = 1)##
## primary secondary tertiary unknown
## no 0.15248042 0.49347258 0.30704961 0.04699739
## yes 0.13603473 0.60202605 0.25180897 0.01013025prop.table (tab_bank,margin = 2)##
## primary secondary tertiary unknown
## no 0.86135693 0.81960104 0.87111111 0.96256684
## yes 0.13864307 0.18039896 0.12888889 0.03743316tab <- table(df_bank$housing, df_bank$job)###Agregar Leyenda y colores
barplot(tab)
legend(x="topright", legend=c("No", "Yes"), fill = c("Black","Grey"), title = "Housing")
prop.table(tab, margin = 2)##
## admin. blue-collar entrepreneur housemaid management retired
## no 0.36820084 0.26532770 0.44047619 0.65178571 0.48090815 0.78260870
## yes 0.63179916 0.73467230 0.55952381 0.34821429 0.51909185 0.21739130
##
## self-employed services student technician unemployed unknown
## no 0.51912568 0.31654676 0.76190476 0.44791667 0.54687500 0.97368421
## yes 0.48087432 0.68345324 0.23809524 0.55208333 0.45312500 0.02631579#Proporciones
Prestamo personal de acuerdo a la educación
tab2 <- table(df_bank$loan, df_bank$education)
tab2##
## primary secondary tertiary unknown
## no 584 1890 1176 180
## yes 94 416 174 7barplot(tab2)
legend(x="topright", legend=c("No", "Yes"), fill = c("Black","Grey"), title = "Loan")
prop.table(tab2, margin = 2)##
## primary secondary tertiary unknown
## no 0.86135693 0.81960104 0.87111111 0.96256684
## yes 0.13864307 0.18039896 0.12888889 0.03743316