LAB1
Ignacio Titos Zamora
EJERCICIO 1
Para comprobar los paquetes instalados en el sistema uso
head(installed.packages()[, c("Package", "Version")], n = 10)## Package Version
## base64enc "base64enc" "0.1-6"
## bit "bit" "4.6.0"
## bit64 "bit64" "4.6.0-1"
## bslib "bslib" "0.10.0"
## cachem "cachem" "1.1.0"
## cli "cli" "3.6.5"
## clipr "clipr" "0.8.0"
## cpp11 "cpp11" "0.5.3"
## crayon "crayon" "1.5.3"
## digest "digest" "0.6.39"install.packages(c("MASS", "survival"))## Installing packages into '/home/ignacio/R/x86_64-pc-linux-gnu-library/4.5'
## (as 'lib' is unspecified)Ya teníamos los paquetes descargados en nuestra librería de R.
help(Rcmdr)## No documentation for 'Rcmdr' in specified packages and libraries:
## you could try '??Rcmdr'??RcmdrUsar el ??Rcmdr muestra la interfaz de ayuda de R.
EJERCICIO 2
a)
library("readr")
drug_interaction <- read_table("db_drug_interactions.txt")##
## ── Column specification ────────────────────────────────────────────────────────
## cols(
## Drug = col_character(),
## `1,Drug` = col_character(),
## `2,Interaction` = col_character(),
## Description = col_character()
## )## Warning: 191541 parsing failures.
## row col expected actual file
## 1 -- 4 columns 8 columns 'db_drug_interactions.txt'
## 2 -- 4 columns 10 columns 'db_drug_interactions.txt'
## 3 -- 4 columns 10 columns 'db_drug_interactions.txt'
## 4 -- 4 columns 10 columns 'db_drug_interactions.txt'
## 5 -- 4 columns 8 columns 'db_drug_interactions.txt'
## ... ... ......... .......... ..........................
## See problems(...) for more details.View(drug_interaction)
summary(drug_interaction)## Drug 1,Drug 2,Interaction Description
## Length:191541 Length:191541 Length:191541 Length:191541
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :characterb)
structural_protein <- read_csv("pdb_data_no_dups.csv")## Rows: 141401 Columns: 14
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (6): structureId, classification, experimentalTechnique, macromoleculeTy...
## dbl (8): residueCount, resolution, structureMolecularWeight, crystallization...
##
## 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.summary(structural_protein)## structureId classification experimentalTechnique macromoleculeType
## Length:141401 Length:141401 Length:141401 Length:141401
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## residueCount resolution structureMolecularWeight
## Min. : 0.0 Min. : 0.480 Min. : 314
## 1st Qu.: 226.0 1st Qu.: 1.800 1st Qu.: 26129
## Median : 414.0 Median : 2.100 Median : 47478
## Mean : 825.4 Mean : 2.264 Mean : 112079
## 3rd Qu.: 820.0 3rd Qu.: 2.500 3rd Qu.: 94085
## Max. :313236.0 Max. :70.000 Max. :97730536
## NA's :12812
## crystallizationMethod crystallizationTempK densityMatthews densityPercentSol
## Length:141401 Min. : 4 Min. : 0.00 Min. : 0.00
## Class :character 1st Qu.:290 1st Qu.: 2.21 1st Qu.:44.37
## Mode :character Median :293 Median : 2.49 Median :50.50
## Mean :291 Mean : 2.67 Mean :51.35
## 3rd Qu.:295 3rd Qu.: 2.91 3rd Qu.:57.71
## Max. :398 Max. :99.00 Max. :92.00
## NA's :44362 NA's :16677 NA's :16652
## pdbxDetails phValue publicationYear
## Length:141401 Min. : 0.000 Min. : 201
## Class :character 1st Qu.: 6.000 1st Qu.:2005
## Mode :character Median : 7.000 Median :2010
## Mean : 6.789 Mean :2009
## 3rd Qu.: 7.500 3rd Qu.:2014
## Max. :724.000 Max. :2018
## NA's :36291 NA's :23799fivenum(structural_protein$residueCount)## [1] 0 226 414 820 313236fivenum(structural_protein$structureMolecularWeight)## [1] 314.38 26128.56 47477.79 94084.84 97730536.00EJERCICIO 3
library("MASS")
data("anorexia")
head(anorexia)## Treat Prewt Postwt
## 1 Cont 80.7 80.2
## 2 Cont 89.4 80.1
## 3 Cont 91.8 86.4
## 4 Cont 74.0 86.3
## 5 Cont 78.1 76.1
## 6 Cont 88.3 78.1summary(anorexia)## Treat Prewt Postwt
## CBT :29 Min. :70.00 Min. : 71.30
## Cont:26 1st Qu.:79.60 1st Qu.: 79.33
## FT :17 Median :82.30 Median : 84.05
## Mean :82.41 Mean : 85.17
## 3rd Qu.:86.00 3rd Qu.: 91.55
## Max. :94.90 Max. :103.60# Valores perdidos
table(is.na(anorexia))##
## FALSE
## 216# valores nulos
table(is.null(anorexia))##
## FALSE
## 1anorexia_changed <- factor(anorexia$Treat,
levels=c("CBT", "Cont", "FT"),
labels=c("Cogn Beh Tr", "Contr", "Fam Tr"))
anorexia_changed## [1] Contr Contr Contr Contr Contr Contr
## [7] Contr Contr Contr Contr Contr Contr
## [13] Contr Contr Contr Contr Contr Contr
## [19] Contr Contr Contr Contr Contr Contr
## [25] Contr Contr Cogn Beh Tr Cogn Beh Tr Cogn Beh Tr Cogn Beh Tr
## [31] Cogn Beh Tr Cogn Beh Tr Cogn Beh Tr Cogn Beh Tr Cogn Beh Tr Cogn Beh Tr
## [37] Cogn Beh Tr Cogn Beh Tr Cogn Beh Tr Cogn Beh Tr Cogn Beh Tr Cogn Beh Tr
## [43] Cogn Beh Tr Cogn Beh Tr Cogn Beh Tr Cogn Beh Tr Cogn Beh Tr Cogn Beh Tr
## [49] Cogn Beh Tr Cogn Beh Tr Cogn Beh Tr Cogn Beh Tr Cogn Beh Tr Cogn Beh Tr
## [55] Cogn Beh Tr Fam Tr Fam Tr Fam Tr Fam Tr Fam Tr
## [61] Fam Tr Fam Tr Fam Tr Fam Tr Fam Tr Fam Tr
## [67] Fam Tr Fam Tr Fam Tr Fam Tr Fam Tr Fam Tr
## Levels: Cogn Beh Tr Contr Fam TrEJERCICIO 4
a)
data("biopsy")
# Exportar el CSV
write.csv(biopsy, file="biopsy.csv")b)
data("Melanoma")
write.table(Melanoma, file="melanoma.txt")
#library(xlsx)
#write.excel(Melanoma, file="melanoma.xslx")c)
capture.output(summary(Melanoma$age), file="melanome_age.doc")EJERCICIO 5
data("birthwt")a)
max(birthwt$age)## [1] 45b)
min(birthwt$age)## [1] 14c)
sprintf("[%d, %d]", min(birthwt$age), max(birthwt$age))## [1] "[14, 45]"range(birthwt$age)## [1] 14 45rank<-max(birthwt$age)-min(birthwt$age) #solución del pdf
rank## [1] 31d)
head(birthwt)## low age lwt race smoke ptl ht ui ftv bwt
## 85 0 19 182 2 0 0 0 1 0 2523
## 86 0 33 155 3 0 0 0 0 3 2551
## 87 0 20 105 1 1 0 0 0 1 2557
## 88 0 21 108 1 1 0 0 1 2 2594
## 89 0 18 107 1 1 0 0 1 0 2600
## 91 0 21 124 3 0 0 0 0 0 2622summary(birthwt)## low age lwt race
## Min. :0.0000 Min. :14.00 Min. : 80.0 Min. :1.000
## 1st Qu.:0.0000 1st Qu.:19.00 1st Qu.:110.0 1st Qu.:1.000
## Median :0.0000 Median :23.00 Median :121.0 Median :1.000
## Mean :0.3122 Mean :23.24 Mean :129.8 Mean :1.847
## 3rd Qu.:1.0000 3rd Qu.:26.00 3rd Qu.:140.0 3rd Qu.:3.000
## Max. :1.0000 Max. :45.00 Max. :250.0 Max. :3.000
## smoke ptl ht ui
## Min. :0.0000 Min. :0.0000 Min. :0.00000 Min. :0.0000
## 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.00000 1st Qu.:0.0000
## Median :0.0000 Median :0.0000 Median :0.00000 Median :0.0000
## Mean :0.3915 Mean :0.1958 Mean :0.06349 Mean :0.1481
## 3rd Qu.:1.0000 3rd Qu.:0.0000 3rd Qu.:0.00000 3rd Qu.:0.0000
## Max. :1.0000 Max. :3.0000 Max. :1.00000 Max. :1.0000
## ftv bwt
## Min. :0.0000 Min. : 709
## 1st Qu.:0.0000 1st Qu.:2414
## Median :0.0000 Median :2977
## Mean :0.7937 Mean :2945
## 3rd Qu.:1.0000 3rd Qu.:3487
## Max. :6.0000 Max. :4990birthwt$smoke[birthwt$bwt == min(birthwt$bwt)]## [1] 1e)
birthwt$bwt[birthwt$age == max(birthwt$age)]## [1] 4990f)
birthwt$bwt[birthwt$ftv < 2]## [1] 2523 2557 2600 2622 2637 2637 2663 2665 2722 2733 2751 2769 2769 2778 2807
## [16] 2821 2836 2863 2877 2906 2920 2920 2920 2948 2948 2977 2977 2922 3033 3062
## [31] 3062 3062 3062 3090 3090 3100 3104 3132 3175 3175 3203 3203 3203 3225 3225
## [46] 3232 3234 3260 3274 3317 3317 3331 3374 3374 3402 3416 3444 3459 3460 3473
## [61] 3544 3487 3544 3572 3572 3586 3600 3614 3614 3629 3637 3643 3651 3651 3651
## [76] 3651 3699 3728 3756 3770 3770 3770 3790 3799 3827 3884 3912 3940 3941 3941
## [91] 3969 3997 3997 4054 4054 4111 4174 4238 4593 4990 709 1135 1330 1474 1588
## [106] 1588 1701 1729 1790 1818 1885 1893 1899 1928 1936 1970 2055 2055 2084 2084
## [121] 2100 2125 2187 2187 2211 2225 2240 2240 2282 2296 2296 2325 2353 2353 2367
## [136] 2381 2381 2381 2410 2410 2410 2424 2442 2466 2466 2495 2495EJERCICIO 6
data("anorexia")
head(anorexia)## Treat Prewt Postwt
## 1 Cont 80.7 80.2
## 2 Cont 89.4 80.1
## 3 Cont 91.8 86.4
## 4 Cont 74.0 86.3
## 5 Cont 78.1 76.1
## 6 Cont 88.3 78.1matrix_anorexia <- matrix(c(anorexia$Prewt, anorexia$Postwt), ncol=2)
head(matrix_anorexia)## [,1] [,2]
## [1,] 80.7 80.2
## [2,] 89.4 80.1
## [3,] 91.8 86.4
## [4,] 74.0 86.3
## [5,] 78.1 76.1
## [6,] 88.3 78.1EJERCICIO 7
Identificador <-
c("I1","I2","I3","I4","I5","I6","I7","I8","I9","I10","I11","I12","I13","I14",
"I15","I16","I17","I18","I19","I20","I21","I22","I23","I24","I25")
Edad <-
c(23,24,21,22,23,25,26,24,21,22,23,25,26,24,22,21,25,26,24,21,25,27,26,22,29)
Sexo <-c(1,2,1,1,1,2,2,2,1,2,1,2,2,2,1,1,1,2,2,2,1,2,1,1,2) #1 para mujeres y 2 para hombres
Peso <-
c(76.5,81.2,79.3,59.5,67.3,78.6,67.9,100.2,97.8,56.4,65.4,67.5,87.4,99.7,87.6
,93.4,65.4,73.7,85.1,61.2,54.8,103.4,65.8,71.7,85.0)
Alt <-
c(165,154,178,165,164,175,182,165,178,165,158,183,184,164,189,167,182,179,165
,158,183,184,189,166,175) #altura en cm
Fuma <-
c("SÍ","NO","SÍ","SÍ","NO","NO","NO","SÍ","SÍ","SÍ","NO","NO","SÍ","SÍ","SÍ",
"SÍ","NO","NO","SÍ","SÍ","SÍ","NO","SÍ","NO","SÍ")
Trat_Pulmon <- data.frame(Identificador,Edad,Sexo,Peso,Alt,Fuma)
Trat_Pulmon## Identificador Edad Sexo Peso Alt Fuma
## 1 I1 23 1 76.5 165 SÍ
## 2 I2 24 2 81.2 154 NO
## 3 I3 21 1 79.3 178 SÍ
## 4 I4 22 1 59.5 165 SÍ
## 5 I5 23 1 67.3 164 NO
## 6 I6 25 2 78.6 175 NO
## 7 I7 26 2 67.9 182 NO
## 8 I8 24 2 100.2 165 SÍ
## 9 I9 21 1 97.8 178 SÍ
## 10 I10 22 2 56.4 165 SÍ
## 11 I11 23 1 65.4 158 NO
## 12 I12 25 2 67.5 183 NO
## 13 I13 26 2 87.4 184 SÍ
## 14 I14 24 2 99.7 164 SÍ
## 15 I15 22 1 87.6 189 SÍ
## 16 I16 21 1 93.4 167 SÍ
## 17 I17 25 1 65.4 182 NO
## 18 I18 26 2 73.7 179 NO
## 19 I19 24 2 85.1 165 SÍ
## 20 I20 21 2 61.2 158 SÍ
## 21 I21 25 1 54.8 183 SÍ
## 22 I22 27 2 103.4 184 NO
## 23 I23 26 1 65.8 189 SÍ
## 24 I24 22 1 71.7 166 NO
## 25 I25 29 2 85.0 175 SÍa)
Trat_Pulmon[Trat_Pulmon$Edad > 22,]## Identificador Edad Sexo Peso Alt Fuma
## 1 I1 23 1 76.5 165 SÍ
## 2 I2 24 2 81.2 154 NO
## 5 I5 23 1 67.3 164 NO
## 6 I6 25 2 78.6 175 NO
## 7 I7 26 2 67.9 182 NO
## 8 I8 24 2 100.2 165 SÍ
## 11 I11 23 1 65.4 158 NO
## 12 I12 25 2 67.5 183 NO
## 13 I13 26 2 87.4 184 SÍ
## 14 I14 24 2 99.7 164 SÍ
## 17 I17 25 1 65.4 182 NO
## 18 I18 26 2 73.7 179 NO
## 19 I19 24 2 85.1 165 SÍ
## 21 I21 25 1 54.8 183 SÍ
## 22 I22 27 2 103.4 184 NO
## 23 I23 26 1 65.8 189 SÍ
## 25 I25 29 2 85.0 175 SÍresultado <- subset(Trat_Pulmon, Edad > 2)
resultado## Identificador Edad Sexo Peso Alt Fuma
## 1 I1 23 1 76.5 165 SÍ
## 2 I2 24 2 81.2 154 NO
## 3 I3 21 1 79.3 178 SÍ
## 4 I4 22 1 59.5 165 SÍ
## 5 I5 23 1 67.3 164 NO
## 6 I6 25 2 78.6 175 NO
## 7 I7 26 2 67.9 182 NO
## 8 I8 24 2 100.2 165 SÍ
## 9 I9 21 1 97.8 178 SÍ
## 10 I10 22 2 56.4 165 SÍ
## 11 I11 23 1 65.4 158 NO
## 12 I12 25 2 67.5 183 NO
## 13 I13 26 2 87.4 184 SÍ
## 14 I14 24 2 99.7 164 SÍ
## 15 I15 22 1 87.6 189 SÍ
## 16 I16 21 1 93.4 167 SÍ
## 17 I17 25 1 65.4 182 NO
## 18 I18 26 2 73.7 179 NO
## 19 I19 24 2 85.1 165 SÍ
## 20 I20 21 2 61.2 158 SÍ
## 21 I21 25 1 54.8 183 SÍ
## 22 I22 27 2 103.4 184 NO
## 23 I23 26 1 65.8 189 SÍ
## 24 I24 22 1 71.7 166 NO
## 25 I25 29 2 85.0 175 SÍb)
Trat_Pulmon[3,4]## [1] 79.3resultado <- subset(Trat_Pulmon, Edad < 27, select = -Alt)
resultado## Identificador Edad Sexo Peso Fuma
## 1 I1 23 1 76.5 SÍ
## 2 I2 24 2 81.2 NO
## 3 I3 21 1 79.3 SÍ
## 4 I4 22 1 59.5 SÍ
## 5 I5 23 1 67.3 NO
## 6 I6 25 2 78.6 NO
## 7 I7 26 2 67.9 NO
## 8 I8 24 2 100.2 SÍ
## 9 I9 21 1 97.8 SÍ
## 10 I10 22 2 56.4 SÍ
## 11 I11 23 1 65.4 NO
## 12 I12 25 2 67.5 NO
## 13 I13 26 2 87.4 SÍ
## 14 I14 24 2 99.7 SÍ
## 15 I15 22 1 87.6 SÍ
## 16 I16 21 1 93.4 SÍ
## 17 I17 25 1 65.4 NO
## 18 I18 26 2 73.7 NO
## 19 I19 24 2 85.1 SÍ
## 20 I20 21 2 61.2 SÍ
## 21 I21 25 1 54.8 SÍ
## 23 I23 26 1 65.8 SÍ
## 24 I24 22 1 71.7 NOEJERCICIO 8
a)
data("ChickWeight")
head(ChickWeight)## weight Time Chick Diet
## 1 42 0 1 1
## 2 51 2 1 1
## 3 59 4 1 1
## 4 64 6 1 1
## 5 76 8 1 1
## 6 93 10 1 1b)
plot(ChickWeight$weight, main="Peso de los pollitos")
### c)
boxplot(ChickWeight$Time, main="Time")
summary(ChickWeight$Time)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 4.00 10.00 10.72 16.00 21.00EJERCICIO 9
data(anorexia)
anorexia_treat_df <- data.frame(Treat=anorexia$Treat, Diferencia=c(anorexia$Postwt-anorexia$Prewt))
head(anorexia_treat_df)## Treat Diferencia
## 1 Cont -0.5
## 2 Cont -9.3
## 3 Cont -5.4
## 4 Cont 12.3
## 5 Cont -2.0
## 6 Cont -10.2anorexia_treat_C_df <- subset(anorexia_treat_df, Treat=="Cont" & Diferencia > 0)
head(anorexia_treat_C_df)## Treat Diferencia
## 4 Cont 12.3
## 8 Cont 11.6
## 10 Cont 6.2
## 13 Cont 8.3
## 14 Cont 3.3
## 15 Cont 11.3