Procesos estocasticos: Taller 2-3
Felipe Hurtado & Luis Ramos Pastor
22/9/2020
Solución
1.8
Access the data from url http://www.stat.berkeley.edu/users/statlabs/data/babies.data and store the information in an object named BABIES using the function read.table().A description of the variables can be found at http://www.stat.berkeley.edu/users/statlabs/labs.html. These data are a subset from a much larger study dealing with child health and development.
| Nombre de la Variable | Descripción |
|---|---|
| bwt | Fecha de Nacimiento del Recién Nacido [Oz] |
| gestation | Duración del embarazo [Dias] |
| parity | Valores entre 0 y 1 dependiendo si es el primer hijo o no |
| age | Edad de la Madre [Años] |
| height | Altura de la Madre [in] |
| weight | Peso de la Madre [lb] |
| smoke | Estado de Fumadora de la Madre (0= No Ahora - 1=si Ahora) |
a)
The variables bwt, gestation, parity, age, height, weight, and smoke use values of 999, 999, 9, 99, 99, 999, and 9, respectively, to denote “unknown.” \(R\) uses NA to denote a missing or unavailable value. Recode the missing values in BABIES. Hint: use something similar to BABIES\(bwt[BABIES\)bwt == 999] = NA. + Rta/:
BABIES <- read.table('C:/Users/flex/Downloads/babies.data')
names(BABIES) <- sapply(BABIES, "[", 1)
BABIES <- BABIES[-1,]
BABIES$bwt[BABIES$bwt== 999] = NA
BABIES$gestation[BABIES$gestation == 999] = NA
BABIES$parity[BABIES$parity == 9] = NA
BABIES$age[BABIES$age == 99] = NA
BABIES$height[BABIES$height == 99] = NA
BABIES$weight[BABIES$weight == 999] = NA
BABIES$smoke[BABIES$smoke == 9] = NA
summary(BABIES)## bwt gestation parity age
## Length:1236 Length:1236 Length:1236 Length:1236
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
## height weight smoke
## Length:1236 Length:1236 Length:1236
## Class :character Class :character Class :character
## Mode :character Mode :character Mode :characterhead(BABIES,10)## bwt gestation parity age height weight smoke
## 2 120 284 0 27 62 100 0
## 3 113 282 0 33 64 135 0
## 4 128 279 0 28 64 115 1
## 5 123 <NA> 0 36 69 190 0
## 6 108 282 0 23 67 125 1
## 7 136 286 0 25 62 93 0
## 8 138 244 0 33 62 178 0
## 9 132 245 0 23 65 140 0
## 10 120 289 0 25 62 125 0
## 11 143 299 0 30 66 136 1b)
Use the function na.omit() to create a “clean” data set that removes subjects if any observations on the subject are “unknown.” Store the modified data frame in a data frame named CLEAN. + Rta/:
CLEAN=na.omit(BABIES)
summary(CLEAN)## bwt gestation parity age
## Length:1174 Length:1174 Length:1174 Length:1174
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
## height weight smoke
## Length:1174 Length:1174 Length:1174
## Class :character Class :character Class :character
## Mode :character Mode :character Mode :characterhead(CLEAN,10)## bwt gestation parity age height weight smoke
## 2 120 284 0 27 62 100 0
## 3 113 282 0 33 64 135 0
## 4 128 279 0 28 64 115 1
## 6 108 282 0 23 67 125 1
## 7 136 286 0 25 62 93 0
## 8 138 244 0 33 62 178 0
## 9 132 245 0 23 65 140 0
## 10 120 289 0 25 62 125 0
## 11 143 299 0 30 66 136 1
## 12 140 351 0 27 68 120 0c)
How many missing values are there for gestation, age, height, weight, and smoke, respectively? How many rows of BABIES have no missing values, one missing value, two missing values, and three missing values, respectively? Note: the number of rows in CLEAN should agree with your answer for the number of rows in BABIES that have no missing values. + Rta/:
U1 <- union(which(is.na(BABIES$bwt)),which(is.na(BABIES$gestation)))
U2 <- union(U1,which(is.na(BABIES$parity)))
U3 <- union(U2,which(is.na(BABIES$age)))
U4 <- union(U3,which(is.na(BABIES$height)))
U5 <- union(U4,which(is.na(BABIES$weight)))
U6 <- union(U5,which(is.na(BABIES$smoke)))
Positions <- sort(U6, decreasing = FALSE)
EmptyG <- length(which(is.na(BABIES$gestation)))
EmptyA <- length(which(is.na(BABIES$age)))
EmptyH <- length(which(is.na(BABIES$height)))
EmptyW <- length(which(is.na(BABIES$weight)))
EmptyS <- length(which(is.na(BABIES$smoke)))
print(paste("Missing Values for Gestation: ", EmptyG))## [1] "Missing Values for Gestation: 13"print(paste("Missing Values for Age: ", EmptyA))## [1] "Missing Values for Age: 2"print(paste("Missing Values for Height: ", EmptyH))## [1] "Missing Values for Height: 22"print(paste("Missing Values for Weight: ", EmptyW))## [1] "Missing Values for Weight: 36"print(paste("Missing Values for Smoke Status: ", EmptyS))## [1] "Missing Values for Smoke Status: 10"lna <- length(Positions)
lb <- length(BABIES$bwt)
lc <- length(CLEAN$bwt)
lcc <- lb-lna
print(paste("Erased Data Length (lna = ",lna,")"))## [1] "Erased Data Length (lna = 62 )"print(paste("Total Data Length (lb = ",lb,")"))## [1] "Total Data Length (lb = 1236 )"print(paste("CLEAN Length (lc =",lc,")"))## [1] "CLEAN Length (lc = 1174 )"print(paste("Subtract Between lb & lna (lcc = ",lcc,")"))## [1] "Subtract Between lb & lna (lcc = 1174 )"d)
Use the function complete.cases() to create a “clean” data set that removes subjects if any observations on the subject are “unknown.” Store the modified data frame in a data frame named CLEAN2. Write a line of code that shows all of the values in CLEAN are the same as those in CLEAN2. + Rta/:
CLEAN2 <- complete.cases(BABIES)
CLEAN2_1 <- complete.cases(BABIES)
CLEAN2_1[CLEAN2_1 == "FALSE"] = NA
CLEAN2_2=na.omit(CLEAN2_1)
length(CLEAN2_2)## [1] 1174Positions_1 <- which(is.na(CLEAN2_1))
print("Erased Data Position in CLEAN: ")## [1] "Erased Data Position in CLEAN: "Positions## [1] 4 40 43 86 90 94 99 103 111 114 153 155 159 170 186
## [16] 194 205 219 231 243 255 256 312 338 353 361 364 400 429 433
## [31] 440 444 478 479 482 509 526 601 642 649 651 654 666 672 699
## [46] 707 740 754 763 848 875 880 883 921 964 972 1014 1045 1178 1191
## [61] 1193 1216print("Erased Data Position in CLEAN2")## [1] "Erased Data Position in CLEAN2"Positions_1## [1] 4 40 43 86 90 94 99 103 111 114 153 155 159 170 186
## [16] 194 205 219 231 243 255 256 312 338 353 361 364 400 429 433
## [31] 440 444 478 479 482 509 526 601 642 649 651 654 666 672 699
## [46] 707 740 754 763 848 875 880 883 921 964 972 1014 1045 1178 1191
## [61] 1193 1216print("Subtract Between Vectors")## [1] "Subtract Between Vectors"Positions_1 - Positions## [1] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## [39] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0e)
Sort the values in CLEAN by bwt, gestation, and age. Store the sorted values in a data frame named BGA and show the last six rows. + Rta/:
BWT <- sort(CLEAN$bwt, decreasing = FALSE)
GES <- sort(CLEAN$gestation, decreasing = FALSE)
AGE <- sort(CLEAN$age, decreasing = FALSE)
BGA <- cbind(BWT, GES, AGE)
tail(BGA,6)## BWT GES AGE
## [1169,] "99" "329" "43"
## [1170,] "99" "330" "43"
## [1171,] "99" "330" "43"
## [1172,] "99" "338" "43"
## [1173,] "99" "351" "44"
## [1174,] "99" "353" "45"f)
Store the data frame CLEAN in your working directory as a _*.csv_ file. + Rta/:
write.csv(CLEAN, file = "C:/Users/flex/Downloads/clean.csv")g)
What percent of the women in CLEAN are pregnant with their first child (parity = 0) and do not smoke? + Rta/:
PERCENT <- CLEAN[-which(CLEAN$parity == 1),]
PERCENT <- PERCENT[-which(PERCENT$smoke == 1),]
PERCENT <- length(PERCENT$bwt)
TOTAL <- length(CLEAN$parity)
RESULT <- (PERCENT/TOTAL)*100
print(paste(RESULT,"%"))## [1] "44.7189097103918 %"1.10
Use the data frame VIT2005 in the PASWR2 package, which contains data on the 218 used apartments sold in Vitoria (Spain) in 2005 to answer the following questions. A description of the variables can be obtained from the help file for this data frame.
library(PASWR2)## Loading required package: lattice## Loading required package: ggplot2library(lattice)
library(ggplot2)
library(optimbase)## Loading required package: Matrixlibrary(epiDisplay)## Loading required package: foreign## Loading required package: survival## Loading required package: MASS## Loading required package: nnet##
## Attaching package: 'epiDisplay'## The following object is masked from 'package:ggplot2':
##
## alpha## The following object is masked from 'package:lattice':
##
## dotplotdata(VIT2005)a)
Create a table of the number of apartments according to the number of garages. + Rta/:
G0 <- VIT2005[-which(VIT2005$garage > 0),]
G1 <- VIT2005[-which(VIT2005$garage != 1),]
G2 <- VIT2005[-which(VIT2005$garage != 2),]
E0 <- VIT2005[which(VIT2005$elevator == 0),]
E1 <- VIT2005[which(VIT2005$elevator == 1),]
APTOS <- c(length(G0[,1]), length(G1[,1]), length(G2[,1]))
names(APTOS) <- c("No Garage","1 Garage","2 Garages")
APTOS## No Garage 1 Garage 2 Garages
## 167 49 2b)
Find the mean of total price according to the number of garages. * Rta/:
NoGaragePrice <- mean(G0$totalprice)
OneGaragePrice <- mean(G1$totalprice)
TwoGaragesPrice <- mean(G2$totalprice)
print(paste("Mean Price With No Garages",NoGaragePrice))## [1] "Mean Price With No Garages 260537.438502994"print(paste("Mean Price With One Garages",OneGaragePrice))## [1] "Mean Price With One Garages 345987.755102041"print(paste("Mean Price With Two Garages",TwoGaragesPrice))## [1] "Mean Price With Two Garages 369250"c)
Create a frequency table of apartments using the categories: number of garages and number of elevators. * Rta/:
AG0 <- length(G0[,1])
AG1 <- length(G1[,1])
AG2 <- length(G2[,1])
TOTALA <- AG0 + AG1 + AG2
RG0 <- AG0/TOTALA
RG1 <- AG1/TOTALA
RG2 <- AG2/TOTALA
TOTALR <- RG0 + RG1 + RG2
AF <- c(AG0, AG1, AG2, TOTALA)
AAF <- c(AG0, AG1 + AG0, AG2 + AG1 + AG0, TOTALA)
RF <- c(RG0, RG1, RG2, TOTALR)
ARF <- c(RG0, RG1 + RG0, RG2 + RG1 + RG0, TOTALR)
FT <- matrix(c(AF , AAF , RF , ARF) ,nrow = 4, ncol = 4)
colnames(FT) <- c("Abs. Freq.","Accum. Abs. Freq.","Rel. Freq", "Accum. Rel. Freq")
rownames(FT) <- c(0,1,2,"Total")
First <- tab1(VIT2005$garage, sort.group = "decreasing", cum.percent = TRUE)
FT## Abs. Freq. Accum. Abs. Freq. Rel. Freq Accum. Rel. Freq
## 0 167 167 0.766055046 0.7660550
## 1 49 216 0.224770642 0.9908257
## 2 2 218 0.009174312 1.0000000
## Total 218 218 1.000000000 1.0000000First## VIT2005$garage :
## Frequency Percent Cum. percent
## 0 167 76.6 76.6
## 1 49 22.5 99.1
## 2 2 0.9 100.0
## Total 218 100.0 100.0#########################################################################################
AE0 <- length(E0[,1])
AE1 <- length(E1[,1])
ETOTALA <- AE0 + AE1
RE0 <- AE0/ETOTALA
RE1 <- AE1/ETOTALA
ETOTALR <- RE0 + RE1
AFE <- c(AE0, AE1, ETOTALA)
AAFE <- c(AE0, AE1 + AE0, ETOTALA)
RFE <- c(RE0, RE1, ETOTALR)
ARFE <- c(RE0, RE1 + RE0, ETOTALR)
FTE <- matrix(c(AFE , AAFE , RFE , ARFE) ,nrow = 3, ncol = 4)
colnames(FTE) <- c("Abs. Freq.","Accum. Abs. Freq.","Rel. Freq", "Accum. Rel. Freq")
rownames(FTE) <- c(0,1,"Total")
Second <- tab1(VIT2005$elevator, sort.group = "decreasing", cum.percent = TRUE)
FTE## Abs. Freq. Accum. Abs. Freq. Rel. Freq Accum. Rel. Freq
## 0 44 44 0.2018349 0.2018349
## 1 174 218 0.7981651 1.0000000
## Total 218 218 1.0000000 1.0000000Second## VIT2005$elevator :
## Frequency Percent Cum. percent
## 1 174 79.8 79.8
## 0 44 20.2 100.0
## Total 218 100.0 100.0d)
Find the mean flat price (total price) for each of the cells of the table created in part (c). * Rta/:
NoGaragePrice## [1] 260537.4OneGaragePrice## [1] 345987.8TwoGaragesPrice## [1] 369250NoElevatorPrice <- mean(E0$totalprice)
OneElevatorPrice <- mean(E1$totalprice)
NoElevatorPrice #Precio de apto sin elevador## [1] 210492.1OneElevatorPrice #Precio de apto con un elevador## [1] 298505.7e)
What command will select only the apartments having at least one garage? * Rta/:
G_12 <- VIT2005[which(VIT2005$garage > 0),]
G_12## totalprice area zone category age floor rooms out conservation toilets
## 2 409000 100.65 Z31 3B 5 7 5 E50 1A 2
## 13 560000 155.90 Z21 2B 7 4 6 E100 1A 2
## 20 360500 108.74 Z43 3A 14 3 5 E75 1A 2
## 22 380000 103.00 Z37 3B 15 3 6 E50 1A 1
## 24 372000 115.59 Z44 3B 17 4 6 E100 1A 2
## 27 330000 94.53 Z56 2B 7 3 4 E100 1A 2
## 33 333000 91.89 Z41 3B 14 5 5 E100 1A 2
## 34 403000 118.86 Z41 3A 25 5 6 E100 1A 2
## 37 330500 110.71 Z61 3A 18 5 5 E100 1A 2
## 39 373000 103.72 Z37 3A 29 3 5 E50 1A 2
## 48 426200 141.48 Z42 3A 13 5 5 E100 1A 2
## 50 326000 86.86 Z41 3B 15 4 5 E100 1A 2
## 54 308000 104.27 Z52 3A 7 2 5 E50 1A 2
## 55 345000 114.78 Z31 3B 16 4 5 E50 1A 2
## 56 390000 90.92 Z41 2A 10 3 5 E100 1A 2
## 58 343000 115.59 Z44 3B 16 5 6 E100 1A 2
## 64 329000 92.94 Z56 3A 7 3 5 E100 1A 2
## 67 291500 69.18 Z56 2B 9 7 4 E100 1A 1
## 69 331600 96.59 Z52 3A 8 2 5 E100 1A 2
## 73 294000 111.37 Z53 3B 19 10 5 E100 2B 2
## 75 347500 93.71 Z56 3A 8 4 5 E100 1A 2
## 78 286000 124.45 Z52 3A 24 5 7 E50 1A 2
## 79 325000 105.58 Z56 3A 4 2 5 E100 1A 2
## 83 379500 109.20 Z42 3A 13 5 5 E100 1A 2
## 90 327500 106.15 Z56 2A 5 4 5 E50 1A 2
## 97 392500 118.68 Z41 3A 15 2 5 E100 1A 2
## 99 262000 88.44 Z47 3B 18 5 5 E100 1A 2
## 103 398000 92.21 Z41 3A 10 2 5 E100 1A 2
## 104 258000 81.00 Z52 3B 15 8 5 E100 1A 1
## 107 340000 103.51 Z41 3A 12 5 5 E100 1A 2
## 109 273000 74.79 Z45 3B 10 4 4 E50 1A 1
## 114 370000 115.34 Z56 2A 6 4 5 E50 1A 2
## 130 378000 104.07 Z42 3A 19 3 5 E100 1A 2
## 131 347000 106.60 Z36 3A 14 7 6 E100 1A 2
## 132 240000 71.05 Z62 3A 14 3 4 E100 1A 1
## 133 457000 142.18 Z42 3A 14 4 6 E100 2A 2
## 135 348000 112.47 Z43 3A 26 2 5 E50 1A 2
## 136 391000 90.92 Z41 2B 10 5 5 E100 1A 2
## 138 398000 87.44 Z41 3A 11 2 5 E100 1A 2
## 140 257500 80.34 Z45 3B 23 6 5 E50 2B 2
## 141 341000 95.84 Z43 3B 27 3 5 E100 1A 2
## 152 396000 114.91 Z42 3A 11 7 5 E50 1A 2
## 154 303500 91.93 Z61 2B 13 4 5 E50 1A 2
## 155 354600 100.64 Z36 2B 22 6 5 E100 1A 2
## 186 433500 113.51 Z41 2B 8 4 5 E100 1A 2
## 190 366000 106.60 Z36 3B 19 2 6 E100 1A 2
## 192 320000 98.28 Z61 3B 22 5 5 E100 1A 2
## 199 261500 96.33 Z47 4A 17 5 4 E100 1A 2
## 207 285000 97.16 Z41 3A 13 2 5 E100 1A 2
## 215 340000 95.61 Z56 2B 8 6 5 E50 1A 2
## 216 280000 83.22 Z34 3B 29 7 5 E50 2B 1
## garage elevator streetcategory heating storage
## 2 1 1 S5 4A 1
## 13 1 1 S4 3B 1
## 20 1 1 S3 4A 1
## 22 1 1 S3 3A 1
## 24 1 1 S4 3A 1
## 27 1 1 S3 3A 1
## 33 1 1 S4 4A 1
## 34 1 1 S4 4A 1
## 37 1 1 S3 4A 1
## 39 1 1 S2 4A 1
## 48 1 1 S5 3A 1
## 50 1 1 S2 3A 1
## 54 1 1 S3 3A 1
## 55 1 1 S5 3A 1
## 56 1 1 S4 3B 1
## 58 1 1 S4 3A 1
## 64 1 1 S2 3A 1
## 67 1 1 S3 3A 1
## 69 1 1 S3 3A 2
## 73 1 1 S4 3A 1
## 75 2 1 S3 3A 1
## 78 1 1 S2 3A 0
## 79 1 1 S3 3A 0
## 83 1 1 S4 3A 1
## 90 1 1 S3 3B 1
## 97 1 1 S4 3A 1
## 99 1 1 S2 3A 1
## 103 1 1 S4 4A 1
## 104 1 1 S2 4A 1
## 107 1 1 S2 3A 1
## 109 1 1 S3 4A 1
## 114 1 1 S3 3B 1
## 130 1 1 S4 3A 1
## 131 1 1 S2 3A 1
## 132 1 1 S3 3A 0
## 133 1 1 S4 3A 1
## 135 1 1 S4 3B 1
## 136 2 1 S4 3A 0
## 138 1 1 S4 4A 1
## 140 1 1 S4 3A 1
## 141 1 1 S4 4A 1
## 152 1 1 S5 3A 1
## 154 1 1 S3 3A 1
## 155 1 1 S2 3A 1
## 186 1 1 S4 3B 1
## 190 1 1 S2 3A 1
## 192 1 1 S3 3A 1
## 199 1 1 S3 4A 1
## 207 1 1 S2 3A 1
## 215 1 1 S3 3A 1
## 216 1 1 S3 4A 1f)
Define a new file called data.c with the apartments that have category = “3B” and have an elevator. * Rta/:
C_3B <- VIT2005[which(VIT2005$category == "3B"),]
data.c <- c(C_3B, E1)1.11
Use the data frame EPIDURALF to answer the following questions:
library(PASWR2)
data("EPIDURALF")
EL <- length(EPIDURALF$doctor)a)
How many patients have been treated with the Hamstring Stretch? * Rta/:
HS <- EPIDURALF[-which(EPIDURALF$treatment != "Hamstring Stretch"),]
HSL <- length(HS$treatment)
HSL## [1] 171b)
What percent of the patients treated with Hamstring Stretch were classified as each of Easy, Difficult, and Impossible? * Rta/:
HSE <- HS[-which(HS$ease != "Easy"),]
HSD <- HS[-which(HS$ease != "Difficult"),]
HSI <- HS[-which(HS$ease != "Impossible"),]
HSEL <- length(HSE$ease)
HSDL <- length(HSD$ease)
HSIL <- length(HSI$ease)
print(paste("Percent of Patients Classified as Easy in HS treatement: ",PE <- (HSEL/HSL)*100," %"))## [1] "Percent of Patients Classified as Easy in HS treatement: 58.4795321637427 %"print(paste("Percent of Patients Classified as Difficult in HS treatement: ",PD <- (HSDL/HSL)*100," %"))## [1] "Percent of Patients Classified as Difficult in HS treatement: 36.8421052631579 %"print(paste("Percent of Patients Classified as Difficult in HS treatement: ",PI <- (HSIL/HSL)*100," %"))## [1] "Percent of Patients Classified as Difficult in HS treatement: 4.67836257309941 %"#PE + PD + PI
PE_1 <- (HSEL/EL)*100
PD_1 <- (HSDL/EL)*100
PI_1 <- (HSIL/EL)*100
P_1 <- c(PE_1, PD_1, PI_1)
names(P_1) <- c("% Easy","% Difficult","% Impossible")
P_1## % Easy % Difficult % Impossible
## 29.239766 18.421053 2.339181c)
What percent of the patients classified as Easy to palpate were assigned to the Traditional Sitting position? * Rta/:
EE <- EPIDURALF[-which(EPIDURALF$ease != "Easy"),]
TSE_1 <- EE[-which(EE$treatment != "Traditional Sitting"),]
EEL <- length(EE$ease)
TSEL <- length(TSE_1$treatment)
P_2<-(TSEL/EEL)*100
print(paste(P_2," %"))## [1] "51.6908212560386 %"d)
What is the mean weight for each cell in a contingency table created with the variables Ease and Treatment? + Rta/:
TS <- EPIDURALF[-which(EPIDURALF$treatment != "Traditional Sitting"),]
TSE <- TS[-which(TS$ease != "Easy"),]
TSD <- TS[-which(TS$ease != "Difficult"),]
TSI <- TS[-which(TS$ease != "Impossible"),]
TSEL <- length(TSE$ease)
TSDL <- length(TSD$ease)
TSIL <- length(TSI$ease)
TOTAL_TS <- TSEL + TSDL + TSIL
TOTAL_HS <- HSEL + HSDL + HSIL
TOTAL_E <- TSEL + HSEL
TOTAL_D <- TSDL + HSDL
TOTAL_I <- TSIL + HSIL
TOTAL <- TOTAL_E + TOTAL_D + TOTAL_I
CT <- matrix(c(TSEL, HSEL, TOTAL_E, TSDL, HSDL, TOTAL_D, TSIL, HSIL, TOTAL_E, TOTAL_TS, TOTAL_HS, TOTAL) ,nrow = 3, ncol = 4)
colnames(CT) <- c("Easy","Difficult","Impossible", "Total")
rownames(CT) <- c("Traditional","Hamstring","Total")
CT## Easy Difficult Impossible Total
## Traditional 107 51 13 171
## Hamstring 100 63 8 171
## Total 207 114 207 342M1_1 <- mean(TSE$kg)
M1_2 <- mean(TSD$kg)
M1_3 <- mean(TSI$kg)
M1_4 <- mean(TS$kg)
M2_1 <- mean(HSE$kg)
M2_2 <- mean(HSD$kg)
M2_3 <- mean(HSI$kg)
M2_4 <- mean(HS$kg)
print(paste("Mean Weights from each column of row 1: ",M1_1," kg, ",M1_2," kg, ",M1_3," kg, ",M1_4," kg"))## [1] "Mean Weights from each column of row 1: 79.4018691588785 kg, 94.2745098039216 kg, 113.615384615385 kg, 86.4385964912281 kg"print(paste("Mean Weights from each column of row 2: ",M2_1," kg, ",M2_2," kg, ",M2_3," kg, ",M2_4," kg"))## [1] "Mean Weights from each column of row 2: 78.67 kg, 92.6666666666667 kg, 127.875 kg, 86.1286549707602 kg"e)
What percent of the patients have a body mass index (\(BMI= kg/(cm/100^2\))) less than 25 and are classified as Easy to palpate? * Rta/:
BMI <- EE$kg/(EE$cm/100)^2
CLASS <- EE[which(BMI < 25),]
CL <- length(CLASS$doctor)
print(paste((CL/EL)*100," %"))## [1] "9.06432748538012 %"1.12
The millions of tourists visiting Spain in 2003, 2004, and 2005 according their nationalities are given in the following table:
a)
Store the values in this table in a matrix with the name tourists.
library(PASWR2)- Rta/:
colum_1 <- c("German", "French", "British", "American", "Rest of the world")
Fila_1<-c("2003","2004","2005")
datos<-c(9.303,9.536,9.918,7.959,7.736,8.875,15.224,15.629,16.090,0.905,0.894,0.883,17.463,18.635,20.148)
tourists <- matrix(data=datos,nrow=5,byrow=TRUE)
tourists #tourists.## [,1] [,2] [,3]
## [1,] 9.303 9.536 9.918
## [2,] 7.959 7.736 8.875
## [3,] 15.224 15.629 16.090
## [4,] 0.905 0.894 0.883
## [5,] 17.463 18.635 20.148dimnames(tourists)<-list(colum_1,Fila_1)
tourists## 2003 2004 2005
## German 9.303 9.536 9.918
## French 7.959 7.736 8.875
## British 15.224 15.629 16.090
## American 0.905 0.894 0.883
## Rest of the world 17.463 18.635 20.148is.matrix(tourists)## [1] TRUEb)
Calculate the totals of the rows. + Rta/:
apply(X=tourists, MARGIN=1,FUN=sum)#Suma de las filas: Total de turistas por Nacionalidad (Por millon)## German French British American
## 28.757 24.570 46.943 2.682
## Rest of the world
## 56.246c)
Calculate the totals of the columns. + Rta/:
apply(X=tourists, MARGIN=2,FUN=sum)#Suma de las columnas: Total de turistas por año (Por millon)## 2003 2004 2005
## 50.854 52.430 55.914