Lab1
2025-03-03
Exercici 1:
library(MASS)
library(survival)Exercici 2:
setwd("C:/Users/pbujosa/OneDrive - San Juan de Dios/Màster Bioinformàtica Bioestadística/S1_Programari per a l'anàlisi de dades/R environment/LAB1")
library(readr)a)
Vaccination_data1 <- read.delim("vaccination-data.txt")
head(Vaccination_data1, n = 5)summary(Vaccination_data1)## COUNTRY ISO3 WHO_REGION DATA_SOURCE
## Length:215 Length:215 Length:215 Length:215
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## DATE_UPDATED TOTAL_VACCINATIONS PERSONS_VACCINATED_1PLUS_DOSE
## Length:215 Min. :4.619e+03 Min. :1.638e+03
## Class :character 1st Qu.:9.034e+05 1st Qu.:4.511e+05
## Mode :character Median :7.372e+06 Median :3.746e+06
## Mean :6.536e+07 Mean :2.687e+07
## 3rd Qu.:2.730e+07 3rd Qu.:1.360e+07
## Max. :3.520e+09 Max. :1.320e+09
## NA's :6 NA's :6
## TOTAL_VACCINATIONS_PER100 PERSONS_VACCINATED_1PLUS_DOSE_PER100
## Min. : 4.0 Min. : 4.00
## 1st Qu.: 82.0 1st Qu.: 45.00
## Median :154.0 Median : 67.00
## Mean :153.9 Mean : 62.77
## 3rd Qu.:221.5 3rd Qu.: 83.00
## Max. :470.0 Max. :100.00
## NA's :8 NA's :8
## PERSONS_LAST_DOSE PERSONS_LAST_DOSE_PER100 FIRST_VACCINE_DATE
## Min. :1.635e+03 Min. : 3.00 Length:215
## 1st Qu.:3.971e+05 1st Qu.: 38.50 Class :character
## Median :3.325e+06 Median : 62.00 Mode :character
## Mean :2.470e+07 Mean : 57.76
## 3rd Qu.:1.110e+07 3rd Qu.: 77.50
## Max. :1.280e+09 Max. :100.00
## NA's :6 NA's :8
## PERSONS_BOOSTER_ADD_DOSE PERSONS_BOOSTER_ADD_DOSE_PER100
## Min. : 314 Min. : 1.00
## 1st Qu.: 76120 1st Qu.:10.00
## Median : 803560 Median :31.00
## Mean : 12856725 Mean :33.12
## 3rd Qu.: 5230598 3rd Qu.:56.00
## Max. :834000000 Max. :83.00
## NA's :20 NA's :31b)
Vaccination_data2 <- read.csv("vaccination-data.csv")
head(Vaccination_data2, n = 2)fivenum(Vaccination_data2$PERSONS_VACCINATED_1PLUS_DOSE_PER100)## [1] 4 45 67 83 100fivenum(Vaccination_data2$PERSONS_LAST_DOSE_PER100)## [1] 3.0 38.5 62.0 77.5 100.0fivenum(Vaccination_data2$PERSONS_BOOSTER_ADD_DOSE_PER100)## [1] 1 10 31 56 83Exercici 3
head(anorexia, n = 3)na_values <- is.na(anorexia)
# Ja que sum conta TRUE com 1 i FALSE com 0 el resultat
# serà el nombre de valors NA a anorexia
sum(na_values)## [1] 0null_values <- is.null(anorexia)
sum(null_values)## [1] 0# Veiem que no hi ha cap valor NA ni NULL a les nostres
# dades
library(dplyr)##
## Attaching package: 'dplyr'## The following object is masked from 'package:MASS':
##
## select## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union# Generem el nou vector amb els valors canviats
anorexia_NewTreatName <- factor(anorexia$Treat, levels = c("CBT",
"Cont", "FT"), labels = c("Cogn Beh Tr", "Contr", "Fam Tr"))
# Intercanviem la primera columna per nou vector generat
anorexia[1] <- anorexia_NewTreatName
anorexia[1, ]anorexia[27, ]anorexia[56, ]Exercici 4:
a)
write.csv(biopsy, file = "C:/Users/pbujosa/OneDrive - San Juan de Dios/Màster Bioinformàtica Bioestadística/S1_Programari per a l'anàlisi de dades/R environment/LAB1/MASS_biopsy.csv")b)
write.csv(Melanoma, file = "C:/Users/pbujosa/OneDrive - San Juan de Dios/Màster Bioinformàtica Bioestadística/S1_Programari per a l'anàlisi de dades/R environment/LAB1/MASS_melanoma.csv")
write.table(Melanoma, "C:/Users/pbujosa/OneDrive - San Juan de Dios/Màster Bioinformàtica Bioestadística/S1_Programari per a l'anàlisi de dades/R environment/LAB1/MASS_melanoma.txt",
sep = "")
library(xlsx)## Warning: package 'xlsx' was built under R version 4.4.3write.xlsx(Melanoma, "C:/Users/pbujosa/OneDrive - San Juan de Dios/Màster Bioinformàtica Bioestadística/S1_Programari per a l'anàlisi de dades/R environment/LAB1/MASS_melanoma.xlsx")Els documents s’han generat:
c)
sum_age <- summary(Melanoma$age)
capture.output(sum_age, file = "Melanoma_age_sum.doc")d)
Age_death_rate <- read.csv("ESP_m_full_idr.csv")
head(Age_death_rate, n = 4)Exercici 5:
a)
max(birthwt$age)## [1] 45L’edat màxima és 45 anys.
b)
min(birthwt$age)## [1] 14L’edat mínima és 14 anys.
c)
max_edat <- max(birthwt$age)
min_edat <- min(birthwt$age)
max_edat - min_edat## [1] 31El rang d’edat és 31 anys.
d)
birthwt$smoke[birthwt$bwt == min(birthwt$bwt)]## [1] 1Sí, la mare del nounat amb menor pes era fumadora.
e)
birthwt$bwt[birthwt$age == max(birthwt$age)]## [1] 4990El nounat de la mare de més edat va pesar 4990 grams.
f)
Pesos_menys2visites <- birthwt$bwt[birthwt$ftv < 2]
head(Pesos_menys2visites)## [1] 2523 2557 2600 2622 2637 2637Exercici 6:
matrix_anorexia <- matrix(c(anorexia$Prewt, anorexia$Postwt),
ncol = 2)
head(matrix_anorexia, n = 3)## [,1] [,2]
## [1,] 80.7 80.2
## [2,] 89.4 80.1
## [3,] 91.8 86.4Exercici 7:
Identificador <- c("I1", "I2", "I3", "I4", "I5", "I6", "I7",
"I8", "I9", "I10", "I11", "I12", "I13", "I14", "I15", "I16",
"I17", "I18", "I19", "I20", "I21", "I22", "I23", "I24", "I25")
Edat <- c(23, 24, 21, 22, 23, 25, 26, 24, 21, 22, 23, 25, 26,
24, 22, 21, 25, 26, 24, 21, 25, 27, 26, 22, 29)
Sexe <- c(1, 2, 1, 1, 1, 2, 2, 2, 1, 2, 1, 2, 2, 2, 1, 1, 1,
2, 2, 2, 1, 2, 1, 1, 2) #1 per a dones i 2 per a homes
Pes <- c(76.5, 81.2, 79.3, 59.5, 67.3, 78.6, 67.9, 100.2, 97.8,
56.4, 65.4, 67.5, 87.4, 99.7, 87.6, 93.4, 65.4, 73.7, 85.1,
61.2, 54.8, 103.4, 65.8, 71.7, 85)
Alt <- c(165, 154, 178, 165, 164, 175, 182, 165, 178, 165, 158,
183, 184, 164, 189, 167, 182, 179, 165, 158, 183, 184, 189,
166, 175) #altura en cm
Fuma <- c("SÍ", "NO", "SÍ", "SÍ", "NO", "NO", "NO", "SÍ",
"SÍ", "SÍ", "NO", "NO", "SÍ", "SÍ", "SÍ", "SÍ", "NO",
"NO", "SÍ", "SÍ", "SÍ", "NO", "SÍ", "NO", "SÍ")
Tract_Pulmo <- data.frame(Identificador, Edat, Sexe, Pes, Alt,
Fuma)
head(Tract_Pulmo)a)
subset(Tract_Pulmo, Edat > 22)b)
Tract_Pulmo[3, 4]## [1] 79.3c)
Tract_Pulmo_menors27 <- subset(Tract_Pulmo, Edat < 27, select = -c(Alt))
head(Tract_Pulmo_menors27)Exercici 8:
a)
data(ChickWeight)b)
plot(ChickWeight$weight, main = "Weight", col = "blue")
c)
boxplot(ChickWeight$Time, horizontal = TRUE, col = "orange2",
main = "Time")
Exercici 9:
data(anorexia)
dif_weight <- c(anorexia$Prewt - anorexia$Postwt)
Treat <- c(anorexia$Treat)
anorexia_treat_df <- data.frame(Treat, dif_weight)
head(anorexia_treat_df, n = 3)# Per selecionar les persones que han guanyat pes hem de
# seleccionar que la diferència entre el pes inicial i el
# pes final sigui menor que zero
anorexia_treat_C_df <- subset(anorexia_treat_df, Treat == "Cont" &
dif_weight < 0)
head(anorexia_treat_C_df, n = 3)