#PUNTO 2.1
x = c(1,3,5,7,9)
y = c(2,4,6,7,11,12)
c = x+1
cat("PUNTO c es:", c, "\n")
## PUNTO c es: 2 4 6 8 10
d = y*2
cat("PUNTO d es:", d, "\n")
## PUNTO d es: 4 8 12 14 22 24
e = length(x)
cat("PUNTO e:", e, "\n")
## PUNTO e: 5
e_2 = length(y)
cat("punto e 2 es:", e_2, "\n")
## punto e 2 es: 6
f = x + y
## Warning in x + y: longitud de objeto mayor no es múltiplo de la longitud de uno
## menor
cat("PUNTO f:", f, "\n")
## PUNTO f: 3 7 11 14 20 13
g = sum(x>5) # cuales son > 5
cat("PUNTO g:", g, "\n")
## PUNTO g: 2
g_2 = sum(x[x>5]) # SUMA LOS > 5
cat("PUNTO g 2:", g_2, "\n")
## PUNTO g 2: 16
h = sum(x>5 | x< 3)
cat("PUNTO h:", h, "\n")
## PUNTO h: 3
i = y[2]
cat("PUNTO i:", i, "\n")
## PUNTO i: 4
j = y[-2]
cat("PUNTO j:", j, "\n")
## PUNTO j: 2 6 7 11 12
k = y[x]
cat("PUNTO k:", k, "\n")
## PUNTO k: 2 6 11 NA NA
cat("PUNTO l: AUSENCIA DE LOS VALORES", "\n")
## PUNTO l: AUSENCIA DE LOS VALORES
m = y[y>=8]
cat("PUNTO m:", m, "\n")
## PUNTO m: 11 12
#PUNTO 2.2
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
dife_2 = diff(kms)
difee =round(dife_2, 1)
print(difee)
## [1] 682.2 535.8 25.7 857.6 498.8 270.3 679.0 -786.8 70.8
# Punto d, resumir datos
resumen = summary(difee)
print(resumen)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -786.8 70.8 498.8 314.8 679.0 857.6
# PUNTO 2.3
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 cada 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, cantidades MAX y MIN pagadas
c_1 = max(pagos)
cat("El pago máximo es:",c_1, "euros\n")
## El pago máximo es: 49 euros
c_2 = min(pagos)
cat("El pago mínimo es:",c_2, "euros\n")
## El pago mínimo 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 más de 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 del gasto total
x = sum(pagos[pagos > 40])
print(x)
## [1] 242
y = sum(pagos)
print(y)
## [1] 478
operacion = ((x*100)/y)
porcentaje = round(operacion,1)
cat("Los pagos superiores a 40 euros:",porcentaje, "%\n")
## Los pagos superiores a 40 euros: 50.6 %
# Punto 2.4
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)
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%"
# Punto b, resúmen numéricos
# 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 99.00
# Desviación estándar
desviacion_estandar = sd(datos)
desviacion_estandar = round(desviacion_estandar,2)
cat("La DE es:",desviacion_estandar, "\n")
## La DE es: 35.7
# Varianza
varianza = 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 99.0
# Punto 2.5
# Punto a, generación de valores
a_numeros = rnorm(100)
a_numeros
## [1] -1.53562831 -0.72808734 -0.83630638 1.10217201 -0.89171502 -0.17314050
## [7] -0.01880038 -0.27863133 -0.81336800 -0.46920840 0.60249956 -0.27889781
## [13] -0.19336908 -2.64531526 -1.52910686 -0.33895036 -0.93471241 0.99820364
## [19] 0.31547879 0.12705172 0.03970533 0.32132587 0.28210336 0.40555068
## [25] 0.93738718 -0.26722136 0.22376937 0.41114951 -1.58320710 1.54840572
## [31] -0.94261609 0.12066932 -1.05919941 -0.94536329 -0.97398974 0.70192095
## [37] -1.17711593 -0.50420127 -1.24990214 2.70275389 -1.69881120 -1.56478887
## [43] 0.09331801 -0.44710839 1.01849193 -2.44589384 -1.23246379 -0.36770916
## [49] 1.72994887 0.30549219 0.43277281 -2.07585113 -0.58570176 -0.99083119
## [55] 1.19107157 0.37063700 0.33019776 1.32847928 -0.78681335 0.16000317
## [61] -0.17283787 -0.30209835 -1.90106157 0.10160283 1.71732730 -0.04371728
## [67] -0.38552688 -0.26311871 -0.31952810 -0.97306959 -0.99497541 1.48099144
## [73] 1.81502593 -1.77526472 1.03323103 -1.18164760 -0.81589038 0.42871671
## [79] -0.98851637 -0.21389595 -0.28414139 0.76538173 1.11132708 -1.66821015
## [85] -1.30418781 -0.43524798 1.74023041 -0.57964191 0.27250000 0.17522011
## [91] 0.32831662 -0.88022234 -1.37553719 0.11632717 0.33144861 -0.09818807
## [97] -0.85642346 0.53982648 -1.45827923 0.43476155
# 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.
## -2.6453 -0.9433 -0.2652 -0.2164 0.3412 2.7028
# Punto 2.6
aleatorio = rbinom(30,5,0.9)
aleatorio
## [1] 4 4 4 3 4 5 5 5 4 5 4 5 4 5 5 5 5 4 5 4 5 4 4 5 5 4 5 5 5 5
barplot(rbinom(30,5,0.9))
# Punto b, resumen
summary(aleatorio)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3.000 4.000 5.000 4.533 5.000 5.000
# Ejercico 2.7
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
boxplot(fallos)
barplot(fallos, xlab = "Intentos", ylab = "Fallos", main = "Satélite en Orbita")
# Punto b, número medio de errores
fallos_satelite = fallos[!is.na(fallos)]
round(mean(fallos_satelite),2)
## [1] 0.45
# Punto 2.8
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 1
# Punto c, tablas contingencia
matriz[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 2
matriz[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 1
# Punto d, diagrama de barras apilada
Datos_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 1
barplot(Datos_3,beside=F,xlab = "Estudiantes")
# Punto e, diagrama barras con tres preguntas
barplot(matriz,beside = T,xlab = "Estudiantes")
# Punto 2.9
vec_1 = rnorm(50)
vec_1
## [1] 0.370922998 1.400283504 0.557087135 -0.022341035 -2.022295766
## [6] 0.580628444 -0.254432645 0.633926326 1.663867799 2.062984356
## [11] 0.024707069 -0.874023592 0.178852090 -0.460739070 0.704070353
## [16] -0.243398284 -0.341777819 -1.136765810 0.154779590 1.551026641
## [21] -0.563079473 -0.309974418 0.702371531 1.022101897 -0.011381826
## [26] -1.113201173 -0.597670659 -0.549116997 0.035807861 -0.076690688
## [31] -0.513740513 -0.978063268 0.542244911 0.223095995 0.573860342
## [36] -0.982826626 -0.868244541 -0.221020296 0.437183816 0.404271028
## [41] 0.546294839 -0.176474668 -1.090163149 1.907602836 0.004624812
## [46] -1.229136103 0.814941458 1.319638248 -1.264365347 1.279363938
vec_2 = rnorm(50)
vec_2
## [1] -0.99058313 -1.06416270 -0.71507408 -0.24130337 -0.31540739 -0.76841790
## [7] -0.62460504 0.93529438 -0.34420567 0.25830595 0.02834827 0.36160544
## [13] -1.06514380 0.80007962 -0.43535160 1.71083494 -1.00142043 0.62327586
## [19] 0.84216017 -0.69113362 0.49461456 0.76469041 0.27277888 1.14399110
## [25] -0.07046076 -0.17519649 0.03492587 1.68374283 2.67581933 -0.53459113
## [31] 0.53774593 0.85345438 1.33556464 1.08470652 -0.66686792 0.12786009
## [37] -2.25102591 0.12257673 1.19015025 -0.41465277 -0.97298330 -0.77574511
## [43] -0.44075370 0.53454154 1.42112074 -0.37700391 0.09454285 0.21280212
## [49] -1.97599679 -0.82548003
# Punto a, Shapiro-Wilk test // evaluar si los datos en tu vector siguen una distribución normal
shapiro.test(vec_1)
##
## Shapiro-Wilk normality test
##
## data: vec_1
## W = 0.98647, p-value = 0.8325
shapiro.test(vec_2)
##
## Shapiro-Wilk normality test
##
## data: vec_2
## W = 0.98524, p-value = 0.782
# Punto b, t-student test
TEST = t.test(vec_1,vec_2)
TEST
##
## Welch Two Sample t-test
##
## data: vec_1 and vec_2
## t = 0.14953, df = 97.636, p-value = 0.8814
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.3405936 0.3960996
## sample estimates:
## mean of x mean of y
## 0.07591232 0.04815934
# Punto 2.10
vec_3 = rnorm(50)
vec_3
## [1] 0.132580029 0.162590286 0.024316873 -1.599379048 -3.208182500
## [6] 0.747210891 -0.681128144 0.400246259 -0.411536933 -0.418715997
## [11] -1.222777186 -0.124307896 -1.203449831 1.140853273 -0.042985840
## [16] -1.221006410 0.015928408 -2.750010017 0.560474687 -0.695927494
## [21] 1.718304472 -0.301713930 -2.104369483 1.301066011 -0.026884722
## [26] 0.770413133 -1.193029594 -0.114945715 -0.650305475 -0.844522248
## [31] 1.043202394 0.701937180 0.404741814 -0.122181910 0.996056595
## [36] 1.439672711 0.237416793 -1.163466493 1.083972597 0.059361312
## [41] 0.985557363 -0.566093494 0.506060243 0.001976533 0.917969656
## [46] -1.016696402 -0.140315178 -0.483234441 0.204126669 0.538256733
vec_4 = rbinom(50,3,0.9)
vec_4
## [1] 3 3 3 3 2 3 3 2 3 3 3 3 3 3 3 2 3 3 3 3 3 3 3 3 2 3 3 3 3 2 3 2 2 3 3 3 2 3
## [39] 3 2 3 3 2 3 2 3 2 1 3 3
shapiro.test(vec_3)
##
## Shapiro-Wilk normality test
##
## data: vec_3
## W = 0.95843, p-value = 0.07639
shapiro.test(vec_4)
##
## Shapiro-Wilk normality test
##
## data: vec_4
## W = 0.57908, p-value = 9.646e-11
# Punto d
TEST = t.test(vec_3,vec_4)
TEST
##
## Welch Two Sample t-test
##
## data: vec_3 and vec_4
## t = -17.653, df = 70.782, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -3.165531 -2.522984
## sample estimates:
## mean of x mean of y
## -0.1242575 2.7200000