TALLER 2
Manuel Rengifo
2024-04-18
EJERCICIO 1
x = c(1,3,5,7,9)
y = c(2,4,6,7,11,12)
c = x+1
cat("El resultado, item c es:", c, "\n")## El resultado, item c es: 2 4 6 8 10d = y*2
cat("El resultado, item d es:", d, "\n")## El resultado, item d es: 4 8 12 14 22 24e = length(x)
cat("El resultado, item e_1 es:", e, "\n")## El resultado, item e_1 es: 5e_2 = length(y)
cat("El resultado, item e_2 es:", e_2, "\n")## El resultado, item e_2 es: 6f = x + y## Warning in x + y: longer object length is not a multiple of shorter object
## lengthcat("El resultado, item f es:", f, "\n")## El resultado, item f es: 3 7 11 14 20 13g = sum(x>5) # cuales son > 5
cat("El resultado, item g es:", g, "\n")## El resultado, item g es: 2g_2 = sum(x[x>5]) # suma los > 5
cat("El resultado, item g_2 es:", g_2, "\n")## El resultado, item g_2 es: 16h = sum(x>5 | x< 3)
cat("El resultado, item h es:", h, "\n")## El resultado, item h es: 3i = y[2]
cat("El resultado, item i es:", i, "\n")## El resultado, item i es: 4j = y[-2]
cat("El resultado, item j es:", j, "\n")## El resultado, item j es: 2 6 7 11 12cat("El resultado, item l es: ausencia de valores", "\n") ## El resultado, item l es: ausencia de valoresm = y[y>=8]
cat("El resultado, item m es:", m, "\n")## El resultado, item m es: 11 12EJERCICIO 2
# Punto a, vector millas
millas = c(65241, 65665, 65998, 66014, 66547, 66857, 67025, 67447, 66958, 67002)
# Punto b, km a millas
kms = 1.609*millas
kms_1 = round(kms, 1)
print(kms_1)## [1] 104972.8 105655.0 106190.8 106216.5 107074.1 107572.9 107843.2 108522.2
## [9] 107735.4 107806.2# Punto c, función diff
dife = diff(millas)
print(dife)## [1] 424 333 16 533 310 168 422 -489 44# Punto d, resumir datos
resumen = summary(dife)
print(resumen)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -489.0 44.0 310.0 195.7 422.0 533.0EJERCICIO 3
pagos=c(47,32,40,36,49,31,49,30,49,35,48,32)
meses= c("enero","febrero","marzo","abril","mayo","junio","julio","agosto","septiembre","octubre","noviembre","diciembre")
# Punto a, factura del último año
costo = sum(pagos)
cat("El costo de la factura es:",costo, "euros\n")## El costo de la factura es: 478 euros# Punto b, pago promedio/mes
b = mean(pagos)
b = round(b,2)
cat("El pago promedio por mes es:",b, "euros\n")## El pago promedio por mes es: 39.83 euros# Punto c, MAX y MIN
c_1 = max(pagos)
cat("El pago máximo es:",c_1, "euros\n")## El pago máximo es: 49 eurosc_2 = min(pagos)
cat("El pago mÃnimo es:",c_2, "euros\n")## El pago mÃnimo es: 30 euros# Punto d, pagos vs meses
meses_pagos= cbind(meses,pagos)
meses_pagos## meses pagos
## [1,] "enero" "47"
## [2,] "febrero" "32"
## [3,] "marzo" "40"
## [4,] "abril" "36"
## [5,] "mayo" "49"
## [6,] "junio" "31"
## [7,] "julio" "49"
## [8,] "agosto" "30"
## [9,] "septiembre" "49"
## [10,] "octubre" "35"
## [11,] "noviembre" "48"
## [12,] "diciembre" "32"# Punto e, pagos > 40
e = sum(pagos > 40)
cat("La persona hizo:",e, "pagos superiores a 40 euros\n")## La persona hizo: 5 pagos superiores a 40 euros# Punto f, porcentaje
x = sum(pagos[pagos > 40])
print(x)## [1] 242y = sum(pagos)
print(y)## [1] 478operacion = ((x*100)/y)
porcentaje = round(operacion,1)
cat("Los pagos superiores a 40 euros:",porcentaje, "%\n")## Los pagos superiores a 40 euros: 50.6 %EJERCICIO 4
datos = c(61, 88, 73, 49, 41, 72, 99, 07, 12, 13, 87, 91, 05, 17, 97)
# Punto a, diagrama porcentual
etiquetas = paste0(round(100 * datos/sum(datos), 2), "%")
pie(datos, labels = etiquetas)
# Otra alternativa
diagrama = cbind(datos,etiquetas)
diagrama## datos etiquetas
## [1,] "61" "7.51%"
## [2,] "88" "10.84%"
## [3,] "73" "8.99%"
## [4,] "49" "6.03%"
## [5,] "41" "5.05%"
## [6,] "72" "8.87%"
## [7,] "99" "12.19%"
## [8,] "7" "0.86%"
## [9,] "12" "1.48%"
## [10,] "13" "1.6%"
## [11,] "87" "10.71%"
## [12,] "91" "11.21%"
## [13,] "5" "0.62%"
## [14,] "17" "2.09%"
## [15,] "97" "11.95%"# Resumen numérico básico
resumen_basico = summary(datos)
print(resumen_basico)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 5.00 15.00 61.00 54.13 87.50 99.00desviacion_estandar = sd(datos)
desviacion_estandar = round(desviacion_estandar,2)
cat("La DE es:",desviacion_estandar, "\n")## La DE es: 35.7varianza = var(datos)
varianza = round(varianza, 2)
cat("La varianza es:",varianza, "\n")## La varianza es: 1274.27# Punto c, diferencia entre summary / fivenum
fivenum(datos)## [1] 5.0 15.0 61.0 87.5 99.0EJERCICIO 5
# Punto a, generación de valores
a_numeros = rnorm(100)
a_numeros## [1] -0.50194582 1.58253883 -0.20339634 2.25233414 0.07481705 -2.89934785
## [7] -0.07005551 -0.15825320 0.34654954 0.99818136 0.13155775 1.45748935
## [13] 0.15783635 -0.44091242 -0.30679301 0.74023037 -0.47353061 -0.88208234
## [19] 0.29294086 -0.39589162 -0.42787837 -0.80549966 -0.48776794 -1.69710066
## [25] 1.27646390 1.41559026 1.07308920 0.90919261 -0.92619150 -2.19448947
## [31] 1.79742072 0.07613918 -0.26497894 -0.23394075 0.48599167 -0.40548400
## [37] -0.31202827 -0.63082755 -0.15890007 -0.66719808 -0.98932300 0.79351603
## [43] 0.94788325 0.53216006 -1.01575078 1.83412927 1.45279144 0.51088708
## [49] -1.70500685 -0.08179927 -1.56398218 0.33834702 0.22094900 1.38316386
## [55] 0.57979928 0.32991390 -1.22660184 1.32317434 -0.28458718 1.36831468
## [61] 0.87837037 1.00887077 -1.25242576 0.79854519 0.17510311 0.79103288
## [67] 0.12525747 -0.50858509 1.11875023 0.35896367 0.21990102 2.26796778
## [73] 0.36966213 -0.18415137 -0.43460133 -0.45563806 -1.04589472 -0.11894527
## [79] 1.73880962 1.23788143 -0.12735233 -1.54128837 -2.22271435 -0.72505286
## [85] -0.37152996 -0.78628485 2.20469010 0.21819063 0.97399374 -0.41782080
## [91] -0.24691110 1.07188699 0.80809535 -0.57214548 1.83879341 0.08000992
## [97] -1.11429498 -0.44010386 0.99553068 1.11388417# Punto b, histograma
hist(a_numeros, main="Valores con rnorm")
# Punto c, resumen de los datos
summary(a_numeros)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -2.89935 -0.46011 0.07807 0.12100 0.91887 2.26797EJERCICIO 6
# Ejercico 2.6 datos aleatorios / rbinom
aleatorio = rbinom(30,5,0.9)
aleatorio## [1] 5 5 5 5 5 4 5 5 5 4 4 5 5 5 5 5 5 4 5 5 4 5 5 4 4 4 3 5 4 5# Punto a, represnatación de datos
barplot(rbinom(30,5,0.9))
B
summary(aleatorio)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3.000 4.000 5.000 4.633 5.000 5.000EJERCICIO 7
fallos = c(0, 1, 0, NA, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 3, 0, 0, 0, 0, 0, 2, 0, 1)
# Punto a, diagrama de cajas / barras
boxplot(fallos) # El diagrama de cajas no es la mejor representación para este caso
barplot(fallos, xlab = "Intentos", ylab = "Fallos", main = "Satélite en Orbita")
PUNTO B
fallos_satelite = fallos[!is.na(fallos)]
round(mean(fallos_satelite),2)## [1] 0.45EJERCICIO 8
Estudiante = c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10)
P1 = c(3, 3, 3, 4, 3, 4, 3, 4, 4, 3)
P2 = c (5, 5, 2, 2, 5, 2, 2, 5, 5, 2)
P3 = c(1, 3, 1, 3, 3, 3, 1, 3, 1, 1)
# Punto b, tabulación
tabla = c(P1,P2,P3)
matriz = matrix(tabla,3,10,byrow = TRUE)
rownames(matriz)= c("P1","P2","P3")
colnames(matriz)=paste("Est",1:10)
matriz## Est 1 Est 2 Est 3 Est 4 Est 5 Est 6 Est 7 Est 8 Est 9 Est 10
## P1 3 3 3 4 3 4 3 4 4 3
## P2 5 5 2 2 5 2 2 5 5 2
## P3 1 3 1 3 3 3 1 3 1 1matriz[2,]## Est 1 Est 2 Est 3 Est 4 Est 5 Est 6 Est 7 Est 8 Est 9 Est 10
## 5 5 2 2 5 2 2 5 5 2matriz[3,]## Est 1 Est 2 Est 3 Est 4 Est 5 Est 6 Est 7 Est 8 Est 9 Est 10
## 1 3 1 3 3 3 1 3 1 1Datos_2 = c(P2,P3)
Datos_3 = matrix(Datos_2,2,10,byrow = TRUE)
Datos_3## [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
## [1,] 5 5 2 2 5 2 2 5 5 2
## [2,] 1 3 1 3 3 3 1 3 1 1barplot(Datos_3,beside=F,xlab = "Estudiantes")
E
barplot(matriz,beside = T,xlab = "Estudiantes")
vec_1 = rnorm(50)
vec_1## [1] -0.39749787 0.33854194 0.05255373 0.83366078 -1.76587985 0.31617347
## [7] -0.72623350 0.68856046 0.45921013 -0.55097947 0.68783564 -0.65901554
## [13] -0.61063154 0.96533967 0.64681194 -1.30640066 -0.01541070 0.87165911
## [19] -0.57377747 -1.01137754 -1.00223027 -1.05284375 1.86911886 2.39830059
## [25] 1.49710121 0.60513850 -1.13002847 -0.77352376 1.81760104 0.20805162
## [31] -1.22854783 0.55650517 0.45770266 -0.50380562 -0.43399872 0.14953685
## [37] -0.29438508 -0.33308660 0.62489957 1.27180310 0.71043304 0.77389919
## [43] 0.02186379 -0.94895859 -0.05083581 -0.60750088 -0.66639776 0.97581231
## [49] -0.92600940 -0.77371170vec_2 = rnorm(50)
vec_2## [1] -0.55596052 -0.77688045 0.64277939 -0.08585518 -0.16778248 -0.08777215
## [7] 0.11444397 0.99188890 0.95528593 1.11965097 1.64687396 0.59691056
## [13] 0.17893326 1.45270246 0.78464150 -0.46973507 0.68078803 -1.27042476
## [19] -0.26015659 1.20210322 -0.13536962 -0.57137512 1.99391316 -0.35882979
## [25] -0.68944696 0.87018214 -0.43248707 0.41243617 0.56995197 -0.51907797
## [31] -0.60815745 0.54002508 -1.30624510 2.72594684 -0.02914562 0.64286598
## [37] -0.21720630 -0.28842053 -0.44517204 -0.14070422 0.37267182 0.31948052
## [43] 0.95733785 0.59035692 -1.12366304 -0.70810616 0.79049291 0.13201731
## [49] -0.54939407 -1.27814707A
shapiro.test(vec_1)##
## Shapiro-Wilk normality test
##
## data: vec_1
## W = 0.97219, p-value = 0.2835shapiro.test(vec_2)##
## Shapiro-Wilk normality test
##
## data: vec_2
## W = 0.97009, p-value = 0.2334shapiro.test(vec_1)##
## Shapiro-Wilk normality test
##
## data: vec_1
## W = 0.97219, p-value = 0.2835shapiro.test(vec_2)##
## Shapiro-Wilk normality test
##
## data: vec_2
## W = 0.97009, p-value = 0.2334TEST = t.test(vec_1,vec_2)
TEST##
## Welch Two Sample t-test
##
## data: vec_1 and vec_2
## t = -0.76152, df = 97.528, p-value = 0.4482
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.4871198 0.2169550
## sample estimates:
## mean of x mean of y
## 0.02910092 0.16418331vec_3 = rnorm(50)
vec_3## [1] -1.647436463 -0.469357141 -0.116768612 -0.011059263 0.165334274
## [6] 0.006155818 0.087242810 1.091692772 0.000513168 -1.510360550
## [11] -1.277880294 -0.918016285 -0.896756466 -0.347331397 -1.410564084
## [16] -0.092280020 -1.084051994 -0.500996426 -0.358369527 -1.661976461
## [21] 1.818310327 -2.691263844 -0.962015538 -0.710500121 1.711527899
## [26] -0.125616600 0.599804778 -0.229769197 -0.566556085 0.480152787
## [31] 0.432963657 -0.122397583 -2.474644318 -0.292851639 -1.006189174
## [36] 0.730589988 0.267623315 1.423009520 0.496750586 -0.713871752
## [41] -0.773302743 -1.096299544 -2.589534747 0.895710857 1.419504325
## [46] 1.002839003 -1.105004491 -0.371993389 0.249945782 0.096210022vec_4 = rbinom(50,3,0.9)
vec_4## [1] 2 2 3 3 2 3 2 3 3 3 3 2 3 3 3 3 3 2 3 3 3 3 3 2 2 3 3 3 3 3 3 3 3 3 2 3 3 2
## [39] 3 3 2 3 3 3 3 3 3 3 3 3shapiro.test(vec_3)##
## Shapiro-Wilk normality test
##
## data: vec_3
## W = 0.98383, p-value = 0.7205shapiro.test(vec_4)##
## Shapiro-Wilk normality test
##
## data: vec_4
## W = 0.51132, p-value = 1.153e-11TEST = t.test(vec_3,vec_4)
TEST##
## Welch Two Sample t-test
##
## data: vec_3 and vec_4
## t = -19.602, df = 64.731, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -3.397342 -2.769024
## sample estimates:
## mean of x mean of y
## -0.3031827 2.7800000