AST 230
ALL SLIDE
slide 01 (Introduction to R)
n<-("welcome")
print(n)## [1] "welcome"1+2+3+4+5## [1] 15r <-(10^2)*3
print(r)## [1] 300x <- rnorm(5)
x## [1] -0.2150953 -1.1677641 1.3404319 -0.6383681 0.4801132Vector
x<-c(0,1,1,2,3,5,6,13,21,34,55)
print(x)## [1] 0 1 1 2 3 5 6 13 21 34 55Matrix
testdata <- matrix(c(1,1,1,2,2,3,3,3,10,11,12,13,
14,15,16,17,28,30,25,40,50,47,62,23), ncol=3,
byrow=FALSE)
testdata## [,1] [,2] [,3]
## [1,] 1 10 28
## [2,] 1 11 30
## [3,] 1 12 25
## [4,] 2 13 40
## [5,] 2 14 50
## [6,] 3 15 47
## [7,] 3 16 62
## [8,] 3 17 23age <- c(1, 3, 5, 2, 11, 9, 3, 9, 12, 3)
weight <- c(4.4, 5.3, 7.2, 5.2, 8.5, 7.3, 6.0, 10.4, 10.2, 6.1)
mean(weight)## [1] 7.06sd(weight)## [1] 2.077498cor(age, weight)## [1] 0.9075655plot(age, weight)
help
help.start()## starting httpd help server ... done## If nothing happens, you should open
## 'http://127.0.0.1:21228/doc/html/index.html' yourselfexample(glm)##
## glm> ## Dobson (1990) Page 93: Randomized Controlled Trial :
## glm> counts <- c(18,17,15,20,10,20,25,13,12)
##
## glm> outcome <- gl(3,1,9)
##
## glm> treatment <- gl(3,3)
##
## glm> data.frame(treatment, outcome, counts) # showing data
## treatment outcome counts
## 1 1 1 18
## 2 1 2 17
## 3 1 3 15
## 4 2 1 20
## 5 2 2 10
## 6 2 3 20
## 7 3 1 25
## 8 3 2 13
## 9 3 3 12
##
## glm> glm.D93 <- glm(counts ~ outcome + treatment, family = poisson())
##
## glm> anova(glm.D93)
## Analysis of Deviance Table
##
## Model: poisson, link: log
##
## Response: counts
##
## Terms added sequentially (first to last)
##
##
## Df Deviance Resid. Df Resid. Dev
## NULL 8 10.5814
## outcome 2 5.4523 6 5.1291
## treatment 2 0.0000 4 5.1291
##
## glm> ## No test:
## glm> ##D summary(glm.D93)
## glm> ## End(No test)
## glm> ## Computing AIC [in many ways]:
## glm> (A0 <- AIC(glm.D93))
## [1] 56.76132
##
## glm> (ll <- logLik(glm.D93))
## 'log Lik.' -23.38066 (df=5)
##
## glm> A1 <- -2*c(ll) + 2*attr(ll, "df")
##
## glm> A2 <- glm.D93$family$aic(counts, mu=fitted(glm.D93), wt=1) +
## glm+ 2 * length(coef(glm.D93))
##
## glm> stopifnot(exprs = {
## glm+ all.equal(A0, A1)
## glm+ all.equal(A1, A2)
## glm+ all.equal(A1, glm.D93$aic)
## glm+ })
##
## glm> ## No test:
## glm> ##D ## an example with offsets from Venables & Ripley (2002, p.189)
## glm> ##D utils::data(anorexia, package = "MASS")
## glm> ##D
## glm> ##D anorex.1 <- glm(Postwt ~ Prewt + Treat + offset(Prewt),
## glm> ##D family = gaussian, data = anorexia)
## glm> ##D summary(anorex.1)
## glm> ## End(No test)
## glm>
## glm> # A Gamma example, from McCullagh & Nelder (1989, pp. 300-2)
## glm> clotting <- data.frame(
## glm+ u = c(5,10,15,20,30,40,60,80,100),
## glm+ lot1 = c(118,58,42,35,27,25,21,19,18),
## glm+ lot2 = c(69,35,26,21,18,16,13,12,12))
##
## glm> summary(glm(lot1 ~ log(u), data = clotting, family = Gamma))
##
## Call:
## glm(formula = lot1 ~ log(u), family = Gamma, data = clotting)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.04008 -0.03756 -0.02637 0.02905 0.08641
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.0165544 0.0009275 -17.85 4.28e-07 ***
## log(u) 0.0153431 0.0004150 36.98 2.75e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for Gamma family taken to be 0.002446059)
##
## Null deviance: 3.51283 on 8 degrees of freedom
## Residual deviance: 0.01673 on 7 degrees of freedom
## AIC: 37.99
##
## Number of Fisher Scoring iterations: 3
##
##
## glm> summary(glm(lot2 ~ log(u), data = clotting, family = Gamma))
##
## Call:
## glm(formula = lot2 ~ log(u), family = Gamma, data = clotting)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.05574 -0.02925 0.01030 0.01714 0.06371
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.0239085 0.0013265 -18.02 4.00e-07 ***
## log(u) 0.0235992 0.0005768 40.91 1.36e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for Gamma family taken to be 0.001813354)
##
## Null deviance: 3.118557 on 8 degrees of freedom
## Residual deviance: 0.012672 on 7 degrees of freedom
## AIC: 27.032
##
## Number of Fisher Scoring iterations: 3
##
##
## glm> ## Aliased ("S"ingular) -> 1 NA coefficient
## glm> (fS <- glm(lot2 ~ log(u) + log(u^2), data = clotting, family = Gamma))
##
## Call: glm(formula = lot2 ~ log(u) + log(u^2), family = Gamma, data = clotting)
##
## Coefficients:
## (Intercept) log(u) log(u^2)
## -0.02391 0.02360 NA
##
## Degrees of Freedom: 8 Total (i.e. Null); 7 Residual
## Null Deviance: 3.119
## Residual Deviance: 0.01267 AIC: 27.03
##
## glm> tools::assertError(update(fS, singular.ok=FALSE), verbose=interactive())
##
## glm> ## -> .. "singular fit encountered"
## glm>
## glm> ## Not run:
## glm> ##D ## for an example of the use of a terms object as a formula
## glm> ##D demo(glm.vr)
## glm> ## End(Not run)
## glm>
## glm>example("regression")## Warning in example("regression"): no help found for 'regression'example(lm)##
## lm> require(graphics)
##
## lm> ## Annette Dobson (1990) "An Introduction to Generalized Linear Models".
## lm> ## Page 9: Plant Weight Data.
## lm> ctl <- c(4.17,5.58,5.18,6.11,4.50,4.61,5.17,4.53,5.33,5.14)
##
## lm> trt <- c(4.81,4.17,4.41,3.59,5.87,3.83,6.03,4.89,4.32,4.69)
##
## lm> group <- gl(2, 10, 20, labels = c("Ctl","Trt"))
##
## lm> weight <- c(ctl, trt)
##
## lm> lm.D9 <- lm(weight ~ group)
##
## lm> lm.D90 <- lm(weight ~ group - 1) # omitting intercept
##
## lm> ## No test:
## lm> ##D anova(lm.D9)
## lm> ##D summary(lm.D90)
## lm> ## End(No test)
## lm> opar <- par(mfrow = c(2,2), oma = c(0, 0, 1.1, 0))
##
## lm> plot(lm.D9, las = 1) # Residuals, Fitted, ...
##
## lm> par(opar)
##
## lm> ## Don't show:
## lm> ## model frame :
## lm> stopifnot(identical(lm(weight ~ group, method = "model.frame"),
## lm+ model.frame(lm.D9)))
##
## lm> ## End(Don't show)
## lm> ### less simple examples in "See Also" above
## lm>
## lm>
## lm>data()
data(cars)
cars## speed dist
## 1 4 2
## 2 4 10
## 3 7 4
## 4 7 22
## 5 8 16
## 6 9 10
## 7 10 18
## 8 10 26
## 9 10 34
## 10 11 17
## 11 11 28
## 12 12 14
## 13 12 20
## 14 12 24
## 15 12 28
## 16 13 26
## 17 13 34
## 18 13 34
## 19 13 46
## 20 14 26
## 21 14 36
## 22 14 60
## 23 14 80
## 24 15 20
## 25 15 26
## 26 15 54
## 27 16 32
## 28 16 40
## 29 17 32
## 30 17 40
## 31 17 50
## 32 18 42
## 33 18 56
## 34 18 76
## 35 18 84
## 36 19 36
## 37 19 46
## 38 19 68
## 39 20 32
## 40 20 48
## 41 20 52
## 42 20 56
## 43 20 64
## 44 22 66
## 45 23 54
## 46 24 70
## 47 24 92
## 48 24 93
## 49 24 120
## 50 25 85data(Orange)
Orange## Tree age circumference
## 1 1 118 30
## 2 1 484 58
## 3 1 664 87
## 4 1 1004 115
## 5 1 1231 120
## 6 1 1372 142
## 7 1 1582 145
## 8 2 118 33
## 9 2 484 69
## 10 2 664 111
## 11 2 1004 156
## 12 2 1231 172
## 13 2 1372 203
## 14 2 1582 203
## 15 3 118 30
## 16 3 484 51
## 17 3 664 75
## 18 3 1004 108
## 19 3 1231 115
## 20 3 1372 139
## 21 3 1582 140
## 22 4 118 32
## 23 4 484 62
## 24 4 664 112
## 25 4 1004 167
## 26 4 1231 179
## 27 4 1372 209
## 28 4 1582 214
## 29 5 118 30
## 30 5 484 49
## 31 5 664 81
## 32 5 1004 125
## 33 5 1231 142
## 34 5 1372 174
## 35 5 1582 177help(lm)
RSiteSearch("lm")## A search query has been submitted to https://search.r-project.org
## The results page should open in your browser shortly??regressionsave image
An example of commands used to manage the R workspace
setwd("D:\\2nd Year\\AST 230")
x <- runif(20)
summary(x)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.02316 0.18119 0.33347 0.43033 0.65301 0.93441hist(x)
#savehistory()
save.image()Installing a package
#install.packages("vcd")
help(package="vcd")
library(vcd)## Warning: package 'vcd' was built under R version 4.2.2## Loading required package: gridhelp(Arthritis)
Arthritis## ID Treatment Sex Age Improved
## 1 57 Treated Male 27 Some
## 2 46 Treated Male 29 None
## 3 77 Treated Male 30 None
## 4 17 Treated Male 32 Marked
## 5 36 Treated Male 46 Marked
## 6 23 Treated Male 58 Marked
## 7 75 Treated Male 59 None
## 8 39 Treated Male 59 Marked
## 9 33 Treated Male 63 None
## 10 55 Treated Male 63 None
## 11 30 Treated Male 64 None
## 12 5 Treated Male 64 Some
## 13 63 Treated Male 69 None
## 14 83 Treated Male 70 Marked
## 15 66 Treated Female 23 None
## 16 40 Treated Female 32 None
## 17 6 Treated Female 37 Some
## 18 7 Treated Female 41 None
## 19 72 Treated Female 41 Marked
## 20 37 Treated Female 48 None
## 21 82 Treated Female 48 Marked
## 22 53 Treated Female 55 Marked
## 23 79 Treated Female 55 Marked
## 24 26 Treated Female 56 Marked
## 25 28 Treated Female 57 Marked
## 26 60 Treated Female 57 Marked
## 27 22 Treated Female 57 Marked
## 28 27 Treated Female 58 None
## 29 2 Treated Female 59 Marked
## 30 59 Treated Female 59 Marked
## 31 62 Treated Female 60 Marked
## 32 84 Treated Female 61 Marked
## 33 64 Treated Female 62 Some
## 34 34 Treated Female 62 Marked
## 35 58 Treated Female 66 Marked
## 36 13 Treated Female 67 Marked
## 37 61 Treated Female 68 Some
## 38 65 Treated Female 68 Marked
## 39 11 Treated Female 69 None
## 40 56 Treated Female 69 Some
## 41 43 Treated Female 70 Some
## 42 9 Placebo Male 37 None
## 43 14 Placebo Male 44 None
## 44 73 Placebo Male 50 None
## 45 74 Placebo Male 51 None
## 46 25 Placebo Male 52 None
## 47 18 Placebo Male 53 None
## 48 21 Placebo Male 59 None
## 49 52 Placebo Male 59 None
## 50 45 Placebo Male 62 None
## 51 41 Placebo Male 62 None
## 52 8 Placebo Male 63 Marked
## 53 80 Placebo Female 23 None
## 54 12 Placebo Female 30 None
## 55 29 Placebo Female 30 None
## 56 50 Placebo Female 31 Some
## 57 38 Placebo Female 32 None
## 58 35 Placebo Female 33 Marked
## 59 51 Placebo Female 37 None
## 60 54 Placebo Female 44 None
## 61 76 Placebo Female 45 None
## 62 16 Placebo Female 46 None
## 63 69 Placebo Female 48 None
## 64 31 Placebo Female 49 None
## 65 20 Placebo Female 51 None
## 66 68 Placebo Female 53 None
## 67 81 Placebo Female 54 None
## 68 4 Placebo Female 54 None
## 69 78 Placebo Female 54 Marked
## 70 70 Placebo Female 55 Marked
## 71 49 Placebo Female 57 None
## 72 10 Placebo Female 57 Some
## 73 47 Placebo Female 58 Some
## 74 44 Placebo Female 59 Some
## 75 24 Placebo Female 59 Marked
## 76 48 Placebo Female 61 None
## 77 19 Placebo Female 63 Some
## 78 3 Placebo Female 64 None
## 79 67 Placebo Female 65 Marked
## 80 32 Placebo Female 66 None
## 81 42 Placebo Female 66 None
## 82 15 Placebo Female 66 Some
## 83 71 Placebo Female 68 Some
## 84 1 Placebo Female 74 Markedexample(Arthritis)##
## Arthrt> data("Arthritis")
##
## Arthrt> art <- xtabs(~ Treatment + Improved, data = Arthritis, subset = Sex == "Female")
##
## Arthrt> art
## Improved
## Treatment None Some Marked
## Placebo 19 7 6
## Treated 6 5 16
##
## Arthrt> mosaic(art, gp = shading_Friendly)
##
## Arthrt> mosaic(art, gp = shading_max)
slide 02 (Creating Dataset)
vectors
a<-c(1,2,5,3,6,-2,4)
a[3]## [1] 5a[c(1,3,5)]## [1] 1 5 6a[2:6]## [1] 2 5 3 6 -2b<-c("one","two","three")
c<-c(TRUE,TRUE,TRUE,FALSE,TRUE,FALSE)
b## [1] "one" "two" "three"c## [1] TRUE TRUE TRUE FALSE TRUE FALSEmatrices
mymatrix <- matrix(vector, nrow=number_of_rows,ncol=number_of_columns, byrow=logical_value,dimnames=list(char_vector_rownames, char_vector_colnames))
y<-matrix(1:20,nrow=5,ncol=4)
y## [,1] [,2] [,3] [,4]
## [1,] 1 6 11 16
## [2,] 2 7 12 17
## [3,] 3 8 13 18
## [4,] 4 9 14 19
## [5,] 5 10 15 20cells<-c(1,26,24,68)
rnames<-c("R1","R2")
cnames <- c("C1", "C2")
mymatrix <- matrix(cells, nrow=2, ncol=2, byrow=TRUE, dimnames=list(rnames, cnames))
mymatrix## C1 C2
## R1 1 26
## R2 24 68Array
myarray <- array(vector, dimensions, dimnames)
dim1 <- c("A1", "A2")
dim2 <- c("B1", "B2", "B3")
dim3 <- c("C1", "C2", "C3", "C4")
z <- array(1:48, c(2, 3, 4), dimnames=list(dim1, dim2, dim3))
z## , , C1
##
## B1 B2 B3
## A1 1 3 5
## A2 2 4 6
##
## , , C2
##
## B1 B2 B3
## A1 7 9 11
## A2 8 10 12
##
## , , C3
##
## B1 B2 B3
## A1 13 15 17
## A2 14 16 18
##
## , , C4
##
## B1 B2 B3
## A1 19 21 23
## A2 20 22 24Creating a data frame
patientID <- c(1, 2, 3, 4)
age <- c(25, 34, 28, 52)
diabetes <- c("Type1", "Type2", "Type1", "Type1")
status <- c("Poor", "Improved", "Excellent", "Poor")
patientdata <- data.frame(patientID, age, diabetes, status)
patientdata## patientID age diabetes status
## 1 1 25 Type1 Poor
## 2 2 34 Type2 Improved
## 3 3 28 Type1 Excellent
## 4 4 52 Type1 Poorpatientdata[1:2]## patientID age
## 1 1 25
## 2 2 34
## 3 3 28
## 4 4 52patientdata[c("diabetes", "status")]## diabetes status
## 1 Type1 Poor
## 2 Type2 Improved
## 3 Type1 Excellent
## 4 Type1 Poorpatientdata$age## [1] 25 34 28 52without ATTACH, DETACH
mtcars## mpg cyl disp hp drat wt qsec vs am gear carb
## Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4
## Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4
## Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1
## Hornet 4 Drive 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1
## Hornet Sportabout 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2
## Valiant 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1
## Duster 360 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4
## Merc 240D 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2
## Merc 230 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2
## Merc 280 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4
## Merc 280C 17.8 6 167.6 123 3.92 3.440 18.90 1 0 4 4
## Merc 450SE 16.4 8 275.8 180 3.07 4.070 17.40 0 0 3 3
## Merc 450SL 17.3 8 275.8 180 3.07 3.730 17.60 0 0 3 3
## Merc 450SLC 15.2 8 275.8 180 3.07 3.780 18.00 0 0 3 3
## Cadillac Fleetwood 10.4 8 472.0 205 2.93 5.250 17.98 0 0 3 4
## Lincoln Continental 10.4 8 460.0 215 3.00 5.424 17.82 0 0 3 4
## Chrysler Imperial 14.7 8 440.0 230 3.23 5.345 17.42 0 0 3 4
## Fiat 128 32.4 4 78.7 66 4.08 2.200 19.47 1 1 4 1
## Honda Civic 30.4 4 75.7 52 4.93 1.615 18.52 1 1 4 2
## Toyota Corolla 33.9 4 71.1 65 4.22 1.835 19.90 1 1 4 1
## Toyota Corona 21.5 4 120.1 97 3.70 2.465 20.01 1 0 3 1
## Dodge Challenger 15.5 8 318.0 150 2.76 3.520 16.87 0 0 3 2
## AMC Javelin 15.2 8 304.0 150 3.15 3.435 17.30 0 0 3 2
## Camaro Z28 13.3 8 350.0 245 3.73 3.840 15.41 0 0 3 4
## Pontiac Firebird 19.2 8 400.0 175 3.08 3.845 17.05 0 0 3 2
## Fiat X1-9 27.3 4 79.0 66 4.08 1.935 18.90 1 1 4 1
## Porsche 914-2 26.0 4 120.3 91 4.43 2.140 16.70 0 1 5 2
## Lotus Europa 30.4 4 95.1 113 3.77 1.513 16.90 1 1 5 2
## Ford Pantera L 15.8 8 351.0 264 4.22 3.170 14.50 0 1 5 4
## Ferrari Dino 19.7 6 145.0 175 3.62 2.770 15.50 0 1 5 6
## Maserati Bora 15.0 8 301.0 335 3.54 3.570 14.60 0 1 5 8
## Volvo 142E 21.4 4 121.0 109 4.11 2.780 18.60 1 1 4 2summary(mtcars$mpg)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 10.40 15.43 19.20 20.09 22.80 33.90plot(mtcars$mpg, mtcars$disp)
plot(mtcars$mpg, mtcars$wt)
ATTACH, DETACH
attach(mtcars)
summary(mpg)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 10.40 15.43 19.20 20.09 22.80 33.90plot(mpg, disp)
plot(mpg, wt)
detach(mtcars)more than one object can have the same name
mpg <- c(25, 36, 47) attach(mtcars) plot(mpg, wt) Error in xy.coords(x, y, xlabel, ylabel, log) : ‘x’ and ‘y’ lengths differ > mpg 1 25 36 47
WITH function
An alternative approach is to use the with() function.
with(mtcars, {
summary(mpg,disp,wt)
plot(mpg, disp)
plot(mpg, wt)
})
local environment
with(mtcars, {
stats <- summary(mpg)
stats
})## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 10.40 15.43 19.20 20.09 22.80 33.90stats Error: object ‘stats’ not found
global environment
save the object to the global environment outside ofthe with() call by using <<-
with(mtcars, {
nokeepstats <- summary(mpg)
keepstats <<- summary(mpg)
})
keepstats## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 10.40 15.43 19.20 20.09 22.80 33.90nokeepstats Error: object ‘nokeepstats’ not found
Lists
g <- "My First List"
h <- c(25, 26, 18, 39)
j <- matrix(1:10, nrow=5)
k <- c("one", "two", "three")
mylist <- list(title=g, ages=h, j, k)
mylist## $title
## [1] "My First List"
##
## $ages
## [1] 25 26 18 39
##
## [[3]]
## [,1] [,2]
## [1,] 1 6
## [2,] 2 7
## [3,] 3 8
## [4,] 4 9
## [5,] 5 10
##
## [[4]]
## [1] "one" "two" "three"#individually
mylist[[1]]## [1] "My First List"mylist[[2]]## [1] 25 26 18 39mylist[[3]]## [,1] [,2]
## [1,] 1 6
## [2,] 2 7
## [3,] 3 8
## [4,] 4 9
## [5,] 5 10mylist[[4]]## [1] "one" "two" "three"create a data frame
create a data frame named mydata with three variables: age (numeric) , gender (character) , and weight (numeric)
mydata <- data.frame(age=numeric(0),
gender=character(0), weight=numeric(0))edit data
mydata <- edit(mydata)read text file
mydataframe <- read.table(file,header=logical_value,sep=“delimiter”, row.names=“name”)
income <- read.table("D://2nd Year//AST 230//EXCELL PRACTICE2.txt", header=T)
View(income)read.xlsx(file,n)
library(xlsx) mydataframe <- read.xlsx(“D://2nd Year//AST 230//EXCELL PRACTICE2.xlsx”, 1)
Importing data from SPSS
1st way
#install.packages(“Hmisc”)
library(Hmisc) mydataframe <- spss.get(“mydata.sav”, use.value.labels=TRUE)
2nd way
library( foreign) testdata=read.spss(“C:/Users/ SNA.sav”, use.value.labels=TRUE, to.data.frame=TRUE)
Importing data from Stata
library(foreign) mydataframe <- read.dta(“mydata.dta”)
#after importing data from stata,sas,etc
example
patientID <- c(1, 2, 3, 4)
age <- c(25, 34, 28, 52)
gender<-c(1,1,2,1)
diabetes <- c("Type1", "Type2", "Type1", "Type1")
status <- c("Poor", "Improved", "Excellent", "Poor")
patientdata <- data.frame(patientID, age, gender, diabetes, status)
patientdata## patientID age gender diabetes status
## 1 1 25 1 Type1 Poor
## 2 2 34 1 Type2 Improved
## 3 3 28 2 Type1 Excellent
## 4 4 52 1 Type1 PoorRename coloum title (age)
names(patientdata)[2] <- "Age at hospitalization (in
years)"
patientdata## patientID Age at hospitalization (in\nyears) gender diabetes status
## 1 1 25 1 Type1 Poor
## 2 2 34 1 Type2 Improved
## 3 3 28 2 Type1 Excellent
## 4 4 52 1 Type1 Poorvalue lables(coding)
patientdata## patientID Age at hospitalization (in\nyears) gender diabetes status
## 1 1 25 1 Type1 Poor
## 2 2 34 1 Type2 Improved
## 3 3 28 2 Type1 Excellent
## 4 4 52 1 Type1 Poorpatientdata$gender <- factor(patientdata$gender,
levels = c(1,2),
labels = c("male", "female"))
patientdata## patientID Age at hospitalization (in\nyears) gender diabetes status
## 1 1 25 male Type1 Poor
## 2 2 34 male Type2 Improved
## 3 3 28 female Type1 Excellent
## 4 4 52 male Type1 Poorslide 03 (working with graphs)
Regression line
rm(list = ls())
show(mtcars)## mpg cyl disp hp drat wt qsec vs am gear carb
## Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4
## Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4
## Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1
## Hornet 4 Drive 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1
## Hornet Sportabout 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2
## Valiant 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1
## Duster 360 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4
## Merc 240D 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2
## Merc 230 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2
## Merc 280 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4
## Merc 280C 17.8 6 167.6 123 3.92 3.440 18.90 1 0 4 4
## Merc 450SE 16.4 8 275.8 180 3.07 4.070 17.40 0 0 3 3
## Merc 450SL 17.3 8 275.8 180 3.07 3.730 17.60 0 0 3 3
## Merc 450SLC 15.2 8 275.8 180 3.07 3.780 18.00 0 0 3 3
## Cadillac Fleetwood 10.4 8 472.0 205 2.93 5.250 17.98 0 0 3 4
## Lincoln Continental 10.4 8 460.0 215 3.00 5.424 17.82 0 0 3 4
## Chrysler Imperial 14.7 8 440.0 230 3.23 5.345 17.42 0 0 3 4
## Fiat 128 32.4 4 78.7 66 4.08 2.200 19.47 1 1 4 1
## Honda Civic 30.4 4 75.7 52 4.93 1.615 18.52 1 1 4 2
## Toyota Corolla 33.9 4 71.1 65 4.22 1.835 19.90 1 1 4 1
## Toyota Corona 21.5 4 120.1 97 3.70 2.465 20.01 1 0 3 1
## Dodge Challenger 15.5 8 318.0 150 2.76 3.520 16.87 0 0 3 2
## AMC Javelin 15.2 8 304.0 150 3.15 3.435 17.30 0 0 3 2
## Camaro Z28 13.3 8 350.0 245 3.73 3.840 15.41 0 0 3 4
## Pontiac Firebird 19.2 8 400.0 175 3.08 3.845 17.05 0 0 3 2
## Fiat X1-9 27.3 4 79.0 66 4.08 1.935 18.90 1 1 4 1
## Porsche 914-2 26.0 4 120.3 91 4.43 2.140 16.70 0 1 5 2
## Lotus Europa 30.4 4 95.1 113 3.77 1.513 16.90 1 1 5 2
## Ford Pantera L 15.8 8 351.0 264 4.22 3.170 14.50 0 1 5 4
## Ferrari Dino 19.7 6 145.0 175 3.62 2.770 15.50 0 1 5 6
## Maserati Bora 15.0 8 301.0 335 3.54 3.570 14.60 0 1 5 8
## Volvo 142E 21.4 4 121.0 109 4.11 2.780 18.60 1 1 4 2attach(mtcars)
plot(wt, mpg)
lm(mpg~wt)##
## Call:
## lm(formula = mpg ~ wt)
##
## Coefficients:
## (Intercept) wt
## 37.285 -5.344abline(lm(mpg~wt))
title("Regression of MPG on Weight")
detach(mtcars)save pdf
pdf("mygraph11.pdf")
attach(mtcars)
plot(wt, mpg)
abline(lm(mpg~wt))
title("Regression of MPG on Weight")
detach(mtcars)
dev.off()## png
## 2# Finally, close the file using the dev.off function.Example
dose <- c(20, 30, 40, 45, 60)
drugA <- c(16, 20, 27, 40, 60)
drugB <- c(15, 18, 25, 31, 40)
plot(dose, drugA, type="b")
resulting graph
opar <- par(no.readonly=TRUE)
par(lty=2, pch=17)
plot(dose, drugA, type="b")
par(opar)#For example, all graphs created after the statement par(font.lab=3, cex.lab=1.5, font.main=4, cex.main=2) will have italic axis labels that are 1.5 times the default text size, and bold italic titles that are twice the default text size.
#The code par(pin=c(4,3), mai=c(1,.5, 1, .2)) produces graphs that are 4 inches wide by 3 inches tall, with a 1-inch margin on the bottom and top, a 0.5-inch margin on the left, and a 0.2-inch margin on the right.
using graping parameter
dose <- c(20, 30, 40, 45, 60)
drugA <- c(16, 20, 27, 40, 60)
drugB <- c(15, 18, 25, 31, 40)
opar <- par(no.readonly=TRUE)
#2 inches wide by 3 inches tall(pin)
par(pin=c(2, 3))
#The line width(lwd)
#symbols width (cex)
par(lwd=2, cex=1.5)
#axis annotation(15,20,25...) size (cex.axis)
#axis annotation(15,20,25...) font (font.axis)
par(cex.axis=.75, font.axis=2)
plot(dose, drugA, type="b", pch=19, lty=2, col="red")
#bg>background
plot(dose, drugB, type="b", pch=23, lty=6, col="blue",
bg="green")
par(opar)Comparing graps
dose <- c(20, 30, 40, 45, 60)
drugA <- c(16, 20, 27, 40, 60)
drugB <- c(15, 18, 25, 31, 40)
opar <- par(no.readonly=TRUE)
par(lwd=2, cex=1.5, font.lab=2)
plot(dose, drugA, type="b",
pch=15, lty=1, col="red", ylim=c(0, 60),
main="Drug A vs. Drug B",
xlab="Drug Dosage", ylab="Drug Response")
lines(dose, drugB, type="b",
pch=17, lty=2, col="blue")
abline(h=c(30), lwd=1.5, lty=2, col="gray")
library(Hmisc)## Warning: package 'Hmisc' was built under R version 4.2.2## Loading required package: lattice## Loading required package: survival## Loading required package: Formula## Warning: package 'Formula' was built under R version 4.2.2## Loading required package: ggplot2## Warning: package 'ggplot2' was built under R version 4.2.2##
## Attaching package: 'Hmisc'## The following objects are masked from 'package:base':
##
## format.pval, unitsminor.tick(nx=1, ny=1, tick.ratio=0.5)
legend("topleft", inset=.01, title="Drug Type", c("A","B"),
lty=c(1, 2), pch=c(15, 17), col=c("red", "blue"))
par(opar)slide 04 (Basic Data Management)
Creating new variables
mydata<-data.frame(x1 = c(2, 2, 6, 4),
x2 = c(3, 4, 2, 8))
mydata## x1 x2
## 1 2 3
## 2 2 4
## 3 6 2
## 4 4 81st way
mydata$sumx <- mydata$x1 + mydata$x2
mydata$meanx <- (mydata$x1 + mydata$x2)/2
mydata## x1 x2 sumx meanx
## 1 2 3 5 2.5
## 2 2 4 6 3.0
## 3 6 2 8 4.0
## 4 4 8 12 6.02nd way
attach(mydata)
mydata$sumx <- x1 + x2
mydata$meanx <- (x1 + x2)/2
detach(mydata)
mydata## x1 x2 sumx meanx
## 1 2 3 5 2.5
## 2 2 4 6 3.0
## 3 6 2 8 4.0
## 4 4 8 12 6.03rd way
mydata2<- transform(mydata,
sumx = x1 + x2,
meanx = (x1 + x2)/2)
mydata2## x1 x2 sumx meanx
## 1 2 3 5 2.5
## 2 2 4 6 3.0
## 3 6 2 8 4.0
## 4 4 8 12 6.0Recoding variables
manager <- c(1, 2, 3, 4, 5)
date <- c("10/24/08", "10/28/08", "10/1/08", "10/12/08", "5/1/09")
country <- c("US", "US", "UK", "UK", "UK")
gender <- c("M", "F", "F", "M", "F")
age <- c(32, 45, 25, 39, 99)
q1 <- c(5, 3, 3, 3, 2)
q2 <- c(4, 5, 5, 3, 2)
q3 <- c(5, 2, 5, 4, 1)
q4 <- c(5, 5, 5, NA, 2)
q5 <- c(5, 5, 2, NA, 1)
leadership <<- data.frame(manager, date, country, gender, age,q1, q2,
q3, q4, q5, stringsAsFactors=FALSE)
leadership## manager date country gender age q1 q2 q3 q4 q5
## 1 1 10/24/08 US M 32 5 4 5 5 5
## 2 2 10/28/08 US F 45 3 5 2 5 5
## 3 3 10/1/08 UK F 25 3 5 5 5 2
## 4 4 10/12/08 UK M 39 3 3 4 NA NA
## 5 5 5/1/09 UK F 99 2 2 1 2 11st way
leadership$agecat[leadership$age == 99] <- NA
leadership$agecat[leadership$age > 75] <- "Elder"
leadership$agecat[leadership$age >= 55 & leadership$age <= 75] <- "Middle Aged"
leadership$agecat[leadership$age < 55] <- "Young"
leadership## manager date country gender age q1 q2 q3 q4 q5 agecat
## 1 1 10/24/08 US M 32 5 4 5 5 5 Young
## 2 2 10/28/08 US F 45 3 5 2 5 5 Young
## 3 3 10/1/08 UK F 25 3 5 5 5 2 Young
## 4 4 10/12/08 UK M 39 3 3 4 NA NA Young
## 5 5 5/1/09 UK F 99 2 2 1 2 1 Elder2nd way
leadership <- within(leadership,{
agecat <- NA
agecat[age > 75] <- "Elder"
agecat[age >= 55 & age <= 75] <- "Middle Aged"
agecat[age < 55] <- "Young" })
leadership## manager date country gender age q1 q2 q3 q4 q5 agecat
## 1 1 10/24/08 US M 32 5 4 5 5 5 Young
## 2 2 10/28/08 US F 45 3 5 2 5 5 Young
## 3 3 10/1/08 UK F 25 3 5 5 5 2 Young
## 4 4 10/12/08 UK M 39 3 3 4 NA NA Young
## 5 5 5/1/09 UK F 99 2 2 1 2 1 ElderRenaming variables
#Install.packages("reshape")
library(reshape)## Warning: package 'reshape' was built under R version 4.2.2leadership <- rename(leadership,
c(manager="managerID", date="testDate"))
leadership## managerID testDate country gender age q1 q2 q3 q4 q5 agecat
## 1 1 10/24/08 US M 32 5 4 5 5 5 Young
## 2 2 10/28/08 US F 45 3 5 2 5 5 Young
## 3 3 10/1/08 UK F 25 3 5 5 5 2 Young
## 4 4 10/12/08 UK M 39 3 3 4 NA NA Young
## 5 5 5/1/09 UK F 99 2 2 1 2 1 Elder#leadership$age[leadership$age == 99] <- NAremoves missing values
x <- c(1, 2, NA, 3)
x## [1] 1 2 NA 3y <- x[1] + x[2] + x[3] + x[4]
y## [1] NAz <- sum(x)
z## [1] NAy1=sum(x,na.rm = T)
y1## [1] 6## remove any observation with missing data by using the na.omit() functionType conversions
a <- c(1,2,3)
a## [1] 1 2 3is.numeric(a)## [1] TRUEis.vector(a)## [1] TRUEis.matrix(a)## [1] FALSEis.complex(a)## [1] FALSEis.data.frame(a)## [1] FALSEis.logical(a)## [1] FALSEa <- as.character(a)
a## [1] "1" "2" "3"is.numeric(a)## [1] FALSEis.vector(a)## [1] TRUEis.character(a)## [1] TRUESorting data set
1st way
leadership## managerID testDate country gender age q1 q2 q3 q4 q5 agecat
## 1 1 10/24/08 US M 32 5 4 5 5 5 Young
## 2 2 10/28/08 US F 45 3 5 2 5 5 Young
## 3 3 10/1/08 UK F 25 3 5 5 5 2 Young
## 4 4 10/12/08 UK M 39 3 3 4 NA NA Young
## 5 5 5/1/09 UK F 99 2 2 1 2 1 Eldernewdata <- leadership[order( leadership$age),]
newdata## managerID testDate country gender age q1 q2 q3 q4 q5 agecat
## 3 3 10/1/08 UK F 25 3 5 5 5 2 Young
## 1 1 10/24/08 US M 32 5 4 5 5 5 Young
## 4 4 10/12/08 UK M 39 3 3 4 NA NA Young
## 2 2 10/28/08 US F 45 3 5 2 5 5 Young
## 5 5 5/1/09 UK F 99 2 2 1 2 1 Eldernewdata1 <- leadership[order( gender,age),]
newdata1## managerID testDate country gender age q1 q2 q3 q4 q5 agecat
## 3 3 10/1/08 UK F 25 3 5 5 5 2 Young
## 2 2 10/28/08 US F 45 3 5 2 5 5 Young
## 5 5 5/1/09 UK F 99 2 2 1 2 1 Elder
## 1 1 10/24/08 US M 32 5 4 5 5 5 Young
## 4 4 10/12/08 UK M 39 3 3 4 NA NA Young2nd way using attach
attach(leadership)## The following objects are masked _by_ .GlobalEnv:
##
## age, country, gender, q1, q2, q3, q4, q5newdata <- leadership[order(gender, age),]
newdata## managerID testDate country gender age q1 q2 q3 q4 q5 agecat
## 3 3 10/1/08 UK F 25 3 5 5 5 2 Young
## 2 2 10/28/08 US F 45 3 5 2 5 5 Young
## 5 5 5/1/09 UK F 99 2 2 1 2 1 Elder
## 1 1 10/24/08 US M 32 5 4 5 5 5 Young
## 4 4 10/12/08 UK M 39 3 3 4 NA NA Youngdetach(leadership)attach(leadership)## The following objects are masked _by_ .GlobalEnv:
##
## age, country, gender, q1, q2, q3, q4, q5newdata1 <-leadership[order(gender, -age),]
newdata1## managerID testDate country gender age q1 q2 q3 q4 q5 agecat
## 5 5 5/1/09 UK F 99 2 2 1 2 1 Elder
## 2 2 10/28/08 US F 45 3 5 2 5 5 Young
## 3 3 10/1/08 UK F 25 3 5 5 5 2 Young
## 4 4 10/12/08 UK M 39 3 3 4 NA NA Young
## 1 1 10/24/08 US M 32 5 4 5 5 5 Youngdetach(leadership)Merging datasets
dataframeA<-data.frame(ID=c(30,31,32,33),A=c(1,2,3,4))
dataframeB<-data.frame(ID=c(30,31,32,33),B=c(3,6,9,8))
dataframeA## ID A
## 1 30 1
## 2 31 2
## 3 32 3
## 4 33 4dataframeB## ID B
## 1 30 3
## 2 31 6
## 3 32 9
## 4 33 8Adding columns
total <- merge(dataframeA, dataframeB, by="ID")
total## ID A B
## 1 30 1 3
## 2 31 2 6
## 3 32 3 9
## 4 33 4 8two matrices or data frame >> cbind
#If you’re joining two matrices or data frames horizontally and don’t need to specify a common key, you can use the cbind() function
A<-c(1,2,3,4)
B<-c(3,6,9,8)
total1<- cbind(A, B)
total1## A B
## [1,] 1 3
## [2,] 2 6
## [3,] 3 9
## [4,] 4 8Adding rows >>rbind
dataframeA1<-data.frame(ID=c(30,31,32,33,56),m=c(1,2,3,4,10))
dataframeA1## ID m
## 1 30 1
## 2 31 2
## 3 32 3
## 4 33 4
## 5 56 10dataframeB1<-data.frame(ID=c(35,90,30),m=c(8,6,07))
dataframeB1## ID m
## 1 35 8
## 2 90 6
## 3 30 7total2 <- rbind(dataframeA1,dataframeB1)
total2## ID m
## 1 30 1
## 2 31 2
## 3 32 3
## 4 33 4
## 5 56 10
## 6 35 8
## 7 90 6
## 8 30 7Subsetting datasets
leadership## managerID testDate country gender age q1 q2 q3 q4 q5 agecat
## 1 1 10/24/08 US M 32 5 4 5 5 5 Young
## 2 2 10/28/08 US F 45 3 5 2 5 5 Young
## 3 3 10/1/08 UK F 25 3 5 5 5 2 Young
## 4 4 10/12/08 UK M 39 3 3 4 NA NA Young
## 5 5 5/1/09 UK F 99 2 2 1 2 1 Eldernewdata <- leadership[ ,c(6:10)]
newdata## q1 q2 q3 q4 q5
## 1 5 4 5 5 5
## 2 3 5 2 5 5
## 3 3 5 5 5 2
## 4 3 3 4 NA NA
## 5 2 2 1 2 1Excluding (dropping) variables
#Excluding (dropping) variables/excluding column 8,9
newdata2 <- leadership[c(-8,-9)]
newdata2## managerID testDate country gender age q1 q2 q5 agecat
## 1 1 10/24/08 US M 32 5 4 5 Young
## 2 2 10/28/08 US F 45 3 5 5 Young
## 3 3 10/1/08 UK F 25 3 5 2 Young
## 4 4 10/12/08 UK M 39 3 3 NA Young
## 5 5 5/1/09 UK F 99 2 2 1 ElderSelecting observations
leadership## managerID testDate country gender age q1 q2 q3 q4 q5 agecat
## 1 1 10/24/08 US M 32 5 4 5 5 5 Young
## 2 2 10/28/08 US F 45 3 5 2 5 5 Young
## 3 3 10/1/08 UK F 25 3 5 5 5 2 Young
## 4 4 10/12/08 UK M 39 3 3 4 NA NA Young
## 5 5 5/1/09 UK F 99 2 2 1 2 1 Eldernewdata <- leadership[1:3,]
newdata## managerID testDate country gender age q1 q2 q3 q4 q5 agecat
## 1 1 10/24/08 US M 32 5 4 5 5 5 Young
## 2 2 10/28/08 US F 45 3 5 2 5 5 Young
## 3 3 10/1/08 UK F 25 3 5 5 5 2 Youngnewdata <- leadership[which(leadership$gender=="M" &
leadership$age > 30),]
newdata## managerID testDate country gender age q1 q2 q3 q4 q5 agecat
## 1 1 10/24/08 US M 32 5 4 5 5 5 Young
## 4 4 10/12/08 UK M 39 3 3 4 NA NA Youngalternative
attach(leadership) newdata <- leadership[which(gender==‘M’ & age > 30),] detach(leadership)
The subset() function
leadership## managerID testDate country gender age q1 q2 q3 q4 q5 agecat
## 1 1 10/24/08 US M 32 5 4 5 5 5 Young
## 2 2 10/28/08 US F 45 3 5 2 5 5 Young
## 3 3 10/1/08 UK F 25 3 5 5 5 2 Young
## 4 4 10/12/08 UK M 39 3 3 4 NA NA Young
## 5 5 5/1/09 UK F 99 2 2 1 2 1 Eldernewdata <- subset(leadership, age >= 35 | age < 24,
select=c(q1, q2, q3, q4))
newdata## q1 q2 q3 q4
## 2 3 5 2 5
## 4 3 3 4 NA
## 5 2 2 1 2newdata <- subset(leadership, gender=="M" & age > 25,
select=gender:q4)
newdata## gender age q1 q2 q3 q4
## 1 M 32 5 4 5 5
## 4 M 39 3 3 4 NArandom sample
ex-1 row sample
leadership## managerID testDate country gender age q1 q2 q3 q4 q5 agecat
## 1 1 10/24/08 US M 32 5 4 5 5 5 Young
## 2 2 10/28/08 US F 45 3 5 2 5 5 Young
## 3 3 10/1/08 UK F 25 3 5 5 5 2 Young
## 4 4 10/12/08 UK M 39 3 3 4 NA NA Young
## 5 5 5/1/09 UK F 99 2 2 1 2 1 Eldermysample1 <- leadership[sample(1:nrow(leadership), 3,
replace=FALSE),]
mysample1## managerID testDate country gender age q1 q2 q3 q4 q5 agecat
## 1 1 10/24/08 US M 32 5 4 5 5 5 Young
## 3 3 10/1/08 UK F 25 3 5 5 5 2 Young
## 2 2 10/28/08 US F 45 3 5 2 5 5 Youngex-2 row sample
CO2## Plant Type Treatment conc uptake
## 1 Qn1 Quebec nonchilled 95 16.0
## 2 Qn1 Quebec nonchilled 175 30.4
## 3 Qn1 Quebec nonchilled 250 34.8
## 4 Qn1 Quebec nonchilled 350 37.2
## 5 Qn1 Quebec nonchilled 500 35.3
## 6 Qn1 Quebec nonchilled 675 39.2
## 7 Qn1 Quebec nonchilled 1000 39.7
## 8 Qn2 Quebec nonchilled 95 13.6
## 9 Qn2 Quebec nonchilled 175 27.3
## 10 Qn2 Quebec nonchilled 250 37.1
## 11 Qn2 Quebec nonchilled 350 41.8
## 12 Qn2 Quebec nonchilled 500 40.6
## 13 Qn2 Quebec nonchilled 675 41.4
## 14 Qn2 Quebec nonchilled 1000 44.3
## 15 Qn3 Quebec nonchilled 95 16.2
## 16 Qn3 Quebec nonchilled 175 32.4
## 17 Qn3 Quebec nonchilled 250 40.3
## 18 Qn3 Quebec nonchilled 350 42.1
## 19 Qn3 Quebec nonchilled 500 42.9
## 20 Qn3 Quebec nonchilled 675 43.9
## 21 Qn3 Quebec nonchilled 1000 45.5
## 22 Qc1 Quebec chilled 95 14.2
## 23 Qc1 Quebec chilled 175 24.1
## 24 Qc1 Quebec chilled 250 30.3
## 25 Qc1 Quebec chilled 350 34.6
## 26 Qc1 Quebec chilled 500 32.5
## 27 Qc1 Quebec chilled 675 35.4
## 28 Qc1 Quebec chilled 1000 38.7
## 29 Qc2 Quebec chilled 95 9.3
## 30 Qc2 Quebec chilled 175 27.3
## 31 Qc2 Quebec chilled 250 35.0
## 32 Qc2 Quebec chilled 350 38.8
## 33 Qc2 Quebec chilled 500 38.6
## 34 Qc2 Quebec chilled 675 37.5
## 35 Qc2 Quebec chilled 1000 42.4
## 36 Qc3 Quebec chilled 95 15.1
## 37 Qc3 Quebec chilled 175 21.0
## 38 Qc3 Quebec chilled 250 38.1
## 39 Qc3 Quebec chilled 350 34.0
## 40 Qc3 Quebec chilled 500 38.9
## 41 Qc3 Quebec chilled 675 39.6
## 42 Qc3 Quebec chilled 1000 41.4
## 43 Mn1 Mississippi nonchilled 95 10.6
## 44 Mn1 Mississippi nonchilled 175 19.2
## 45 Mn1 Mississippi nonchilled 250 26.2
## 46 Mn1 Mississippi nonchilled 350 30.0
## 47 Mn1 Mississippi nonchilled 500 30.9
## 48 Mn1 Mississippi nonchilled 675 32.4
## 49 Mn1 Mississippi nonchilled 1000 35.5
## 50 Mn2 Mississippi nonchilled 95 12.0
## 51 Mn2 Mississippi nonchilled 175 22.0
## 52 Mn2 Mississippi nonchilled 250 30.6
## 53 Mn2 Mississippi nonchilled 350 31.8
## 54 Mn2 Mississippi nonchilled 500 32.4
## 55 Mn2 Mississippi nonchilled 675 31.1
## 56 Mn2 Mississippi nonchilled 1000 31.5
## 57 Mn3 Mississippi nonchilled 95 11.3
## 58 Mn3 Mississippi nonchilled 175 19.4
## 59 Mn3 Mississippi nonchilled 250 25.8
## 60 Mn3 Mississippi nonchilled 350 27.9
## 61 Mn3 Mississippi nonchilled 500 28.5
## 62 Mn3 Mississippi nonchilled 675 28.1
## 63 Mn3 Mississippi nonchilled 1000 27.8
## 64 Mc1 Mississippi chilled 95 10.5
## 65 Mc1 Mississippi chilled 175 14.9
## 66 Mc1 Mississippi chilled 250 18.1
## 67 Mc1 Mississippi chilled 350 18.9
## 68 Mc1 Mississippi chilled 500 19.5
## 69 Mc1 Mississippi chilled 675 22.2
## 70 Mc1 Mississippi chilled 1000 21.9
## 71 Mc2 Mississippi chilled 95 7.7
## 72 Mc2 Mississippi chilled 175 11.4
## 73 Mc2 Mississippi chilled 250 12.3
## 74 Mc2 Mississippi chilled 350 13.0
## 75 Mc2 Mississippi chilled 500 12.5
## 76 Mc2 Mississippi chilled 675 13.7
## 77 Mc2 Mississippi chilled 1000 14.4
## 78 Mc3 Mississippi chilled 95 10.6
## 79 Mc3 Mississippi chilled 175 18.0
## 80 Mc3 Mississippi chilled 250 17.9
## 81 Mc3 Mississippi chilled 350 17.9
## 82 Mc3 Mississippi chilled 500 17.9
## 83 Mc3 Mississippi chilled 675 18.9
## 84 Mc3 Mississippi chilled 1000 19.9mysample2 <- CO2[sample(1:nrow(CO2), 10,
replace=FALSE),]
mysample2## Plant Type Treatment conc uptake
## 46 Mn1 Mississippi nonchilled 350 30.0
## 45 Mn1 Mississippi nonchilled 250 26.2
## 22 Qc1 Quebec chilled 95 14.2
## 69 Mc1 Mississippi chilled 675 22.2
## 64 Mc1 Mississippi chilled 95 10.5
## 55 Mn2 Mississippi nonchilled 675 31.1
## 37 Qc3 Quebec chilled 175 21.0
## 17 Qn3 Quebec nonchilled 250 40.3
## 13 Qn2 Quebec nonchilled 675 41.4
## 29 Qc2 Quebec chilled 95 9.3ex-3 coloum sample
mysample3 <- CO2[,sample(1:ncol(CO2), 2,
replace=FALSE)]
mysample3## uptake Type
## 1 16.0 Quebec
## 2 30.4 Quebec
## 3 34.8 Quebec
## 4 37.2 Quebec
## 5 35.3 Quebec
## 6 39.2 Quebec
## 7 39.7 Quebec
## 8 13.6 Quebec
## 9 27.3 Quebec
## 10 37.1 Quebec
## 11 41.8 Quebec
## 12 40.6 Quebec
## 13 41.4 Quebec
## 14 44.3 Quebec
## 15 16.2 Quebec
## 16 32.4 Quebec
## 17 40.3 Quebec
## 18 42.1 Quebec
## 19 42.9 Quebec
## 20 43.9 Quebec
## 21 45.5 Quebec
## 22 14.2 Quebec
## 23 24.1 Quebec
## 24 30.3 Quebec
## 25 34.6 Quebec
## 26 32.5 Quebec
## 27 35.4 Quebec
## 28 38.7 Quebec
## 29 9.3 Quebec
## 30 27.3 Quebec
## 31 35.0 Quebec
## 32 38.8 Quebec
## 33 38.6 Quebec
## 34 37.5 Quebec
## 35 42.4 Quebec
## 36 15.1 Quebec
## 37 21.0 Quebec
## 38 38.1 Quebec
## 39 34.0 Quebec
## 40 38.9 Quebec
## 41 39.6 Quebec
## 42 41.4 Quebec
## 43 10.6 Mississippi
## 44 19.2 Mississippi
## 45 26.2 Mississippi
## 46 30.0 Mississippi
## 47 30.9 Mississippi
## 48 32.4 Mississippi
## 49 35.5 Mississippi
## 50 12.0 Mississippi
## 51 22.0 Mississippi
## 52 30.6 Mississippi
## 53 31.8 Mississippi
## 54 32.4 Mississippi
## 55 31.1 Mississippi
## 56 31.5 Mississippi
## 57 11.3 Mississippi
## 58 19.4 Mississippi
## 59 25.8 Mississippi
## 60 27.9 Mississippi
## 61 28.5 Mississippi
## 62 28.1 Mississippi
## 63 27.8 Mississippi
## 64 10.5 Mississippi
## 65 14.9 Mississippi
## 66 18.1 Mississippi
## 67 18.9 Mississippi
## 68 19.5 Mississippi
## 69 22.2 Mississippi
## 70 21.9 Mississippi
## 71 7.7 Mississippi
## 72 11.4 Mississippi
## 73 12.3 Mississippi
## 74 13.0 Mississippi
## 75 12.5 Mississippi
## 76 13.7 Mississippi
## 77 14.4 Mississippi
## 78 10.6 Mississippi
## 79 18.0 Mississippi
## 80 17.9 Mississippi
## 81 17.9 Mississippi
## 82 17.9 Mississippi
## 83 18.9 Mississippi
## 84 19.9 Mississippislide 05 (Advanced Data Management)
Statistical functions
#z <- mean(x, trim = 0.05, na.rm=TRUE)
ceiling(x = 3.551)## [1] 4floor(x = 3.551)## [1] 3round(3.551,2)## [1] 3.55signif(3.551,2)## [1] 3.6log(3)## [1] 1.098612log10(3)## [1] 0.4771213log(x=3,base = 10)## [1] 0.4771213x=c(1,2,3,3,6,59,09,30,20)
plot(x,sin(x))
x=c(1,2,3,4,5,6,7,8)
mean(x)## [1] 4.5median(x)## [1] 4.5sd(x)## [1] 2.44949var(x)## [1] 6mad(x)## [1] 2.9652quantile(x,c(.3,.84))## 30% 84%
## 3.10 6.88range(x)## [1] 1 8sum(x)## [1] 36diff(x,lag = 1)## [1] 1 1 1 1 1 1 1diff(x,lag = 2)## [1] 2 2 2 2 2 2diff(x,lag = 3)## [1] 3 3 3 3 3min(x)## [1] 1max(x)## [1] 8scale(x,center = TRUE,scale = TRUE)## [,1]
## [1,] -1.4288690
## [2,] -1.0206207
## [3,] -0.6123724
## [4,] -0.2041241
## [5,] 0.2041241
## [6,] 0.6123724
## [7,] 1.0206207
## [8,] 1.4288690
## attr(,"scaled:center")
## [1] 4.5
## attr(,"scaled:scale")
## [1] 2.44949Probability functions
d = density p = distribution function q = quantile function r = random generation (random deviates)
x<-pretty(c(-3,3),30)
x## [1] -3.0 -2.8 -2.6 -2.4 -2.2 -2.0 -1.8 -1.6 -1.4 -1.2 -1.0 -0.8 -0.6 -0.4 -0.2
## [16] 0.0 0.2 0.4 0.6 0.8 1.0 1.2 1.4 1.6 1.8 2.0 2.2 2.4 2.6 2.8
## [31] 3.0y<-dnorm(x)
y## [1] 0.004431848 0.007915452 0.013582969 0.022394530 0.035474593 0.053990967
## [7] 0.078950158 0.110920835 0.149727466 0.194186055 0.241970725 0.289691553
## [13] 0.333224603 0.368270140 0.391042694 0.398942280 0.391042694 0.368270140
## [19] 0.333224603 0.289691553 0.241970725 0.194186055 0.149727466 0.110920835
## [25] 0.078950158 0.053990967 0.035474593 0.022394530 0.013582969 0.007915452
## [31] 0.004431848plot(x,y,type ="l",xlab= "NORMAL DEVIATE",ylab = "DENSITY",yaxs= 'i')
#yaxs The style of axis interval calculation to be used for the
y-axis.
Generating multivariate normal data
#install.packages("MASS")
library(MASS)
options(digits=7)
set.seed(1234)
mean <- c(250.7, 130.5, 5.6)
n <- 3
A <- matrix(runif((n^2),-3,3), ncol=n)
A## [,1] [,2] [,3]
## [1,] -2.3177795 0.7402767 -2.9430255
## [2,] 0.7337964 2.1654923 -1.6046970
## [3,] 0.6556484 0.8418636 0.9965025#generating n by n matrix with values from uniform distribution
sigma<- t(A) %*% A #hypothetical var-cov matrix
sigma## [,1] [,2] [,3]
## [1,] 6.340434 0.425199 6.297119
## [2,] 0.425199 5.946101 -4.814693
## [3,] 6.297119 -4.814693 12.229469mydata <- mvrnorm(400, mean, sigma) #generating 400 values from a
#multivariate normal
mydata <- as.data.frame(mydata)
names(mydata) <- c("y","x1","x2")
dim(mydata)## [1] 400 3head(mydata, n=15)## y x1 x2
## 1 251.0184 130.8935 5.4007886
## 2 251.5151 132.6467 5.4306534
## 3 247.0263 131.7707 0.8881412
## 4 248.9954 132.7586 2.4520034
## 5 250.5811 127.8735 7.7745863
## 6 252.3736 129.7477 8.0861491
## 7 252.4378 130.2279 7.1547260
## 8 254.9901 128.2115 11.2019576
## 9 247.7025 130.1414 2.6478323
## 10 248.0582 133.2701 1.2118612
## 11 254.2280 128.2655 11.3189866
## 12 250.8919 127.6359 7.5363612
## 13 248.1130 127.3608 5.6819667
## 14 249.0960 130.1720 2.7826842
## 15 253.2586 131.2778 7.7792555Pattern Matching and Replacement >>grep
grep("[a-z]", letters) ## [1] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25
## [26] 26# letters will produce a,b,c,...z and will match a-z letters
letters ## [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s"
## [20] "t" "u" "v" "w" "x" "y" "z"#to see what letters appear
grep("[abc]", letters) ## [1] 1 2 3#match the places where any of 'abc' found in the sequence
grep("[ased]", letters)## [1] 1 4 5 19grep("[ased]", letters,fixed=T)## integer(0)grep("[ased]", letters,fixed=F)## [1] 1 4 5 19grep("[ased]", c(letters,"[ased]"),fixed=T)## [1] 27grep("[ased]", c(letters,"[ased]"),fixed=F)## [1] 1 4 5 19 27a <- 6
sqrt(a)## [1] 2.44949b <- c(1.532, 5.754, 3.99)
round(b)## [1] 2 6 4d <- matrix(runif(16), nrow=4)
d## [,1] [,2] [,3] [,4]
## [1,] 0.9189159 0.2512678 0.9555143 0.5007705
## [2,] 0.8519516 0.6550916 0.7320949 0.2580541
## [3,] 0.7600845 0.1710871 0.9830077 0.5201532
## [4,] 0.7223479 0.5576245 0.1508911 0.1581700log(d)## [,1] [,2] [,3] [,4]
## [1,] -0.0845607 -1.3812359 -0.04550559 -0.6916074
## [2,] -0.1602256 -0.4229802 -0.31184510 -1.3545860
## [3,] -0.2743256 -1.7655828 -0.01713829 -0.6536319
## [4,] -0.3252484 -0.5840695 -1.89119695 -1.8440846mean(d)## [1] 0.5716892Applying functions
mydata <- matrix(rnorm(30), nrow=6)
mydata## [,1] [,2] [,3] [,4] [,5]
## [1,] 1.2779592 -0.2144554 -0.2475043 0.4743173 1.3109869
## [2,] 0.1393738 -0.4587626 1.1982527 -1.0086812 0.4528040
## [3,] 1.6063475 0.2104320 0.8935556 0.5232864 2.1354266
## [4,] -0.9469487 0.3622436 -0.0294763 -0.1711696 0.4319354
## [5,] -1.2656885 -0.9867580 -0.5971864 0.4732156 -0.1613210
## [6,] 1.5545595 1.2751202 0.6129529 0.3315565 -0.3175865#Calculate row means
apply(mydata, 1, mean) ## [1] 0.52026074 0.06459732 1.07380963 -0.07068311 -0.50754765 0.69132053#Calculate column means
apply(mydata, 2, mean) ## [1] 0.3942671 0.0313033 0.3050990 0.1037542 0.6420409apply(mydata, 2, mean, trim=0.2)## [1] 0.5062360 -0.0251356 0.3073820 0.2769800 0.5086013Data management problem
options(digits=3)
Student <- c("Asif Rahman", "Angela Dean", "Heera Das",
"Issac Robin", "Shamsul Huda", "Ashraf Uddin",
"Nazrul Islam", "Shamsur Rahman", "Hemonto Mukherjee",
"Salemun Bahar")
Math <- c(502, 600, 412, 358, 495, 512, 410, 625, 573, 522)
Science <- c(95, 99, 80, 82, 75, 85, 80, 95, 89, 86)
English <- c(25, 22, 18, 15, 20, 28, 15, 30, 27, 18)
roster <- data.frame(Student, Math, Science, English,
stringsAsFactors=FALSE)
roster ## Student Math Science English
## 1 Asif Rahman 502 95 25
## 2 Angela Dean 600 99 22
## 3 Heera Das 412 80 18
## 4 Issac Robin 358 82 15
## 5 Shamsul Huda 495 75 20
## 6 Ashraf Uddin 512 85 28
## 7 Nazrul Islam 410 80 15
## 8 Shamsur Rahman 625 95 30
## 9 Hemonto Mukherjee 573 89 27
## 10 Salemun Bahar 522 86 18#Obtain performance scores
z <- scale(roster[,2:4])
z## Math Science English
## [1,] 0.0127 1.078 0.5869
## [2,] 1.1434 1.591 0.0367
## [3,] -1.0257 -0.847 -0.6969
## [4,] -1.6487 -0.590 -1.2471
## [5,] -0.0681 -1.489 -0.3301
## [6,] 0.1281 -0.205 1.1370
## [7,] -1.0488 -0.847 -1.2471
## [8,] 1.4318 1.078 1.5038
## [9,] 0.8319 0.308 0.9536
## [10,] 0.2434 -0.077 -0.6969
## attr(,"scaled:center")
## Math Science English
## 500.9 86.6 21.8
## attr(,"scaled:scale")
## Math Science English
## 86.67 7.79 5.45#calculates row means i.e.one score from each student after combining math,science, English
score <- apply(z, 1, mean)
score## [1] 0.559 0.924 -0.857 -1.162 -0.629 0.353 -1.048 1.338 0.698 -0.177roster <- cbind(roster, score)
roster## Student Math Science English score
## 1 Asif Rahman 502 95 25 0.559
## 2 Angela Dean 600 99 22 0.924
## 3 Heera Das 412 80 18 -0.857
## 4 Issac Robin 358 82 15 -1.162
## 5 Shamsul Huda 495 75 20 -0.629
## 6 Ashraf Uddin 512 85 28 0.353
## 7 Nazrul Islam 410 80 15 -1.048
## 8 Shamsur Rahman 625 95 30 1.338
## 9 Hemonto Mukherjee 573 89 27 0.698
## 10 Salemun Bahar 522 86 18 -0.177#setting quantiles ofscore vector at 80%, 60%, 40%, 20%
y <- quantile(score, c(.8,.6,.4,.2))
y## 80% 60% 40% 20%
## 0.743 0.436 -0.358 -0.895#will give natural quantile at 0%, 25%,50%, 75%, 100% points.
t=quantile(score)
t## 0% 25% 50% 75% 100%
## -1.1620 -0.7997 0.0882 0.6632 1.3379roster$grade[score >= y[1]] <- "A"
roster$grade[score < y[1] & score >= y[2]] <- "B"
roster$grade[score < y[2] & score >= y[3]] <- "C"
roster$grade[score < y[3] & score >= y[4]] <- "D"
roster$grade[score < y[4]] <- "F"
roster## Student Math Science English score grade
## 1 Asif Rahman 502 95 25 0.559 B
## 2 Angela Dean 600 99 22 0.924 A
## 3 Heera Das 412 80 18 -0.857 D
## 4 Issac Robin 358 82 15 -1.162 F
## 5 Shamsul Huda 495 75 20 -0.629 D
## 6 Ashraf Uddin 512 85 28 0.353 C
## 7 Nazrul Islam 410 80 15 -1.048 F
## 8 Shamsur Rahman 625 95 30 1.338 A
## 9 Hemonto Mukherjee 573 89 27 0.698 B
## 10 Salemun Bahar 522 86 18 -0.177 Cname <- strsplit((roster$Student), " ")
name## [[1]]
## [1] "Asif" "Rahman"
##
## [[2]]
## [1] "Angela" "Dean"
##
## [[3]]
## [1] "Heera" "Das"
##
## [[4]]
## [1] "Issac" "Robin"
##
## [[5]]
## [1] "Shamsul" "Huda"
##
## [[6]]
## [1] "Ashraf" "Uddin"
##
## [[7]]
## [1] "Nazrul" "Islam"
##
## [[8]]
## [1] "Shamsur" "Rahman"
##
## [[9]]
## [1] "Hemonto" "Mukherjee"
##
## [[10]]
## [1] "Salemun" "Bahar"#extracting last name
lastname <- sapply(name, "[", 2)
lastname## [1] "Rahman" "Dean" "Das" "Robin" "Huda" "Uddin"
## [7] "Islam" "Rahman" "Mukherjee" "Bahar"firstname <- sapply(name, "[", 1)
firstname ## [1] "Asif" "Angela" "Heera" "Issac" "Shamsul" "Ashraf" "Nazrul"
## [8] "Shamsur" "Hemonto" "Salemun"roster <- cbind(firstname,lastname, roster[,-1])
roster## firstname lastname Math Science English score grade
## 1 Asif Rahman 502 95 25 0.559 B
## 2 Angela Dean 600 99 22 0.924 A
## 3 Heera Das 412 80 18 -0.857 D
## 4 Issac Robin 358 82 15 -1.162 F
## 5 Shamsul Huda 495 75 20 -0.629 D
## 6 Ashraf Uddin 512 85 28 0.353 C
## 7 Nazrul Islam 410 80 15 -1.048 F
## 8 Shamsur Rahman 625 95 30 1.338 A
## 9 Hemonto Mukherjee 573 89 27 0.698 B
## 10 Salemun Bahar 522 86 18 -0.177 COrdering
#orders according to frist name and then by last name
roster <- roster[order(firstname,lastname),]
roster## firstname lastname Math Science English score grade
## 2 Angela Dean 600 99 22 0.924 A
## 6 Ashraf Uddin 512 85 28 0.353 C
## 1 Asif Rahman 502 95 25 0.559 B
## 3 Heera Das 412 80 18 -0.857 D
## 9 Hemonto Mukherjee 573 89 27 0.698 B
## 4 Issac Robin 358 82 15 -1.162 F
## 7 Nazrul Islam 410 80 15 -1.048 F
## 10 Salemun Bahar 522 86 18 -0.177 C
## 5 Shamsul Huda 495 75 20 -0.629 D
## 8 Shamsur Rahman 625 95 30 1.338 A#orders according to last name and then by frist name
roster <- roster[order(lastname,firstname),]
roster## firstname lastname Math Science English score grade
## 8 Shamsur Rahman 625 95 30 1.338 A
## 1 Asif Rahman 502 95 25 0.559 B
## 6 Ashraf Uddin 512 85 28 0.353 C
## 9 Hemonto Mukherjee 573 89 27 0.698 B
## 7 Nazrul Islam 410 80 15 -1.048 F
## 5 Shamsul Huda 495 75 20 -0.629 D
## 2 Angela Dean 600 99 22 0.924 A
## 10 Salemun Bahar 522 86 18 -0.177 C
## 3 Heera Das 412 80 18 -0.857 D
## 4 Issac Robin 358 82 15 -1.162 F##orders according grade…….. roster
roster <-roster[order(roster$grade,firstname,lastname),]
roster## firstname lastname Math Science English score grade
## 8 Shamsur Rahman 625 95 30 1.338 A
## 2 Angela Dean 600 99 22 0.924 A
## 1 Asif Rahman 502 95 25 0.559 B
## 9 Hemonto Mukherjee 573 89 27 0.698 B
## 6 Ashraf Uddin 512 85 28 0.353 C
## 10 Salemun Bahar 522 86 18 -0.177 C
## 5 Shamsul Huda 495 75 20 -0.629 D
## 3 Heera Das 412 80 18 -0.857 D
## 4 Issac Robin 358 82 15 -1.162 F
## 7 Nazrul Islam 410 80 15 -1.048 FRepetition and looping
For
for (i in 1:5)
print("Welcome")## [1] "Welcome"
## [1] "Welcome"
## [1] "Welcome"
## [1] "Welcome"
## [1] "Welcome"while
i <- 10
while (i > 0) {
print("2nd year");
i <- i - 1
}## [1] "2nd year"
## [1] "2nd year"
## [1] "2nd year"
## [1] "2nd year"
## [1] "2nd year"
## [1] "2nd year"
## [1] "2nd year"
## [1] "2nd year"
## [1] "2nd year"
## [1] "2nd year"IFELSE
score<-runif(50, 0,100)
score## [1] 15.14 42.96 36.86 61.42 83.11 8.97 35.30 73.66 6.31 58.19 69.58 73.87
## [13] 31.07 34.07 17.26 95.40 47.65 44.44 1.50 54.82 29.61 45.79 15.10 80.13
## [25] 77.78 22.11 1.98 57.98 1.07 71.72 44.10 10.65 93.54 59.01 29.83 27.63
## [37] 23.30 92.35 57.21 75.96 14.76 4.23 33.95 82.10 91.53 58.62 54.44 28.73
## [49] 65.59 36.11outcome <- ifelse (score > 40.0, "Passed", "Failed")
outcome## [1] "Failed" "Passed" "Failed" "Passed" "Passed" "Failed" "Failed" "Passed"
## [9] "Failed" "Passed" "Passed" "Passed" "Failed" "Failed" "Failed" "Passed"
## [17] "Passed" "Passed" "Failed" "Passed" "Failed" "Passed" "Failed" "Passed"
## [25] "Passed" "Failed" "Failed" "Passed" "Failed" "Passed" "Passed" "Failed"
## [33] "Passed" "Passed" "Failed" "Failed" "Failed" "Passed" "Passed" "Passed"
## [41] "Failed" "Failed" "Failed" "Passed" "Passed" "Passed" "Passed" "Failed"
## [49] "Passed" "Failed"table(outcome)## outcome
## Failed Passed
## 23 27Transpose
cars <- mtcars[1:8,1:5]
cars## mpg cyl disp hp drat
## Mazda RX4 21.0 6 160 110 3.90
## Mazda RX4 Wag 21.0 6 160 110 3.90
## Datsun 710 22.8 4 108 93 3.85
## Hornet 4 Drive 21.4 6 258 110 3.08
## Hornet Sportabout 18.7 8 360 175 3.15
## Valiant 18.1 6 225 105 2.76
## Duster 360 14.3 8 360 245 3.21
## Merc 240D 24.4 4 147 62 3.69t(cars)## Mazda RX4 Mazda RX4 Wag Datsun 710 Hornet 4 Drive Hornet Sportabout
## mpg 21.0 21.0 22.80 21.40 18.70
## cyl 6.0 6.0 4.00 6.00 8.00
## disp 160.0 160.0 108.00 258.00 360.00
## hp 110.0 110.0 93.00 110.00 175.00
## drat 3.9 3.9 3.85 3.08 3.15
## Valiant Duster 360 Merc 240D
## mpg 18.10 14.30 24.40
## cyl 6.00 8.00 4.00
## disp 225.00 360.00 146.70
## hp 105.00 245.00 62.00
## drat 2.76 3.21 3.69Aggregation and restructuring
Aggregate function
#takes upto 4 digits for each variable
options(digits=4)
attach(mtcars)## The following object is masked from package:ggplot2:
##
## mpg#Aggregates mtcars by varaiables cyl, and gear.
aggcars<-aggregate(mtcars,by=list(cyl,gear),FUN=mean, na.rm=TRUE)
aggcars## Group.1 Group.2 mpg cyl disp hp drat wt qsec vs am gear carb
## 1 4 3 21.50 4 120.1 97.0 3.700 2.465 20.01 1.0 0.00 3 1.000
## 2 6 3 19.75 6 241.5 107.5 2.920 3.337 19.83 1.0 0.00 3 1.000
## 3 8 3 15.05 8 357.6 194.2 3.121 4.104 17.14 0.0 0.00 3 3.083
## 4 4 4 26.93 4 102.6 76.0 4.110 2.378 19.61 1.0 0.75 4 1.500
## 5 6 4 19.75 6 163.8 116.5 3.910 3.094 17.67 0.5 0.50 4 4.000
## 6 4 5 28.20 4 107.7 102.0 4.100 1.827 16.80 0.5 1.00 5 2.000
## 7 6 5 19.70 6 145.0 175.0 3.620 2.770 15.50 0.0 1.00 5 6.000
## 8 8 5 15.40 8 326.0 299.5 3.880 3.370 14.55 0.0 1.00 5 6.000Reshaping data (Use of melt() and cast() functions)
#install.packages("reshape")
library(reshape)
options(digits=2)
ID<-rep(1:5, each = 2)
Semester<-rep(1:2,times=5)
Math <- c(502, 560, 412, 358, 590, 595, 410, 423, 573, 522)
Science <- c(95, 99, 80, 82, 75, 85, 80, 95, 89, 86)
English <- c(25, 22, 18, 15, 25, 28, 15, 18, 27, 28)
examdata <- data.frame(ID,Semester, Math, Science, English,row.names = NULL,check.rows = F,check.names = T)
examdata## ID Semester Math Science English
## 1 1 1 502 95 25
## 2 1 2 560 99 22
## 3 2 1 412 80 18
## 4 2 2 358 82 15
## 5 3 1 590 75 25
## 6 3 2 595 85 28
## 7 4 1 410 80 15
## 8 4 2 423 95 18
## 9 5 1 573 89 27
## 10 5 2 522 86 28melt() functions
library(reshape)
# for restructure
md <- melt(examdata, id=c("ID", "Semester"))
md## ID Semester variable value
## 1 1 1 Math 502
## 2 1 2 Math 560
## 3 2 1 Math 412
## 4 2 2 Math 358
## 5 3 1 Math 590
## 6 3 2 Math 595
## 7 4 1 Math 410
## 8 4 2 Math 423
## 9 5 1 Math 573
## 10 5 2 Math 522
## 11 1 1 Science 95
## 12 1 2 Science 99
## 13 2 1 Science 80
## 14 2 2 Science 82
## 15 3 1 Science 75
## 16 3 2 Science 85
## 17 4 1 Science 80
## 18 4 2 Science 95
## 19 5 1 Science 89
## 20 5 2 Science 86
## 21 1 1 English 25
## 22 1 2 English 22
## 23 2 1 English 18
## 24 2 2 English 15
## 25 3 1 English 25
## 26 3 2 English 28
## 27 4 1 English 15
## 28 4 2 English 18
## 29 5 1 English 27
## 30 5 2 English 28cast() functions *** problem
Aggregation
#library(reshape)
#library(reshape2)
#Aggregation
#cast(md, ID~variable, mean)
#cast(md, Semester~variable, mean)
#cast(md, ID~Semester, mean)#cast(data = md,ID~.,mean)
#cast(md, Semester~., mean)#average of 3 module scores in each semester
Without Aggregation
#Reshaping data (Use of melt() and cast() functions)
md <- melt(examdata, id=(c("ID", "Semester")))
md## ID Semester variable value
## 1 1 1 Math 502
## 2 1 2 Math 560
## 3 2 1 Math 412
## 4 2 2 Math 358
## 5 3 1 Math 590
## 6 3 2 Math 595
## 7 4 1 Math 410
## 8 4 2 Math 423
## 9 5 1 Math 573
## 10 5 2 Math 522
## 11 1 1 Science 95
## 12 1 2 Science 99
## 13 2 1 Science 80
## 14 2 2 Science 82
## 15 3 1 Science 75
## 16 3 2 Science 85
## 17 4 1 Science 80
## 18 4 2 Science 95
## 19 5 1 Science 89
## 20 5 2 Science 86
## 21 1 1 English 25
## 22 1 2 English 22
## 23 2 1 English 18
## 24 2 2 English 15
## 25 3 1 English 25
## 26 3 2 English 28
## 27 4 1 English 15
## 28 4 2 English 18
## 29 5 1 English 27
## 30 5 2 English 28#Without Aggregation
cast(md, ID+Semester~variable)## ID Semester Math Science English
## 1 1 1 502 95 25
## 2 1 2 560 99 22
## 3 2 1 412 80 18
## 4 2 2 358 82 15
## 5 3 1 590 75 25
## 6 3 2 595 85 28
## 7 4 1 410 80 15
## 8 4 2 423 95 18
## 9 5 1 573 89 27
## 10 5 2 522 86 28cast(md, ID+variable~Semester)## ID variable 1 2
## 1 1 Math 502 560
## 2 1 Science 95 99
## 3 1 English 25 22
## 4 2 Math 412 358
## 5 2 Science 80 82
## 6 2 English 18 15
## 7 3 Math 590 595
## 8 3 Science 75 85
## 9 3 English 25 28
## 10 4 Math 410 423
## 11 4 Science 80 95
## 12 4 English 15 18
## 13 5 Math 573 522
## 14 5 Science 89 86
## 15 5 English 27 28cast(md, ID~variable+Semester)## ID Math_1 Math_2 Science_1 Science_2 English_1 English_2
## 1 1 502 560 95 99 25 22
## 2 2 412 358 80 82 18 15
## 3 3 590 595 75 85 25 28
## 4 4 410 423 80 95 15 18
## 5 5 573 522 89 86 27 28slide 06 (Functions, Loops, Simulation)
Example 1
h<- function(number) {
for(i in seq_len(number)) {
cat("Hello, can you listen me?\n")
} }
h(5)## Hello, can you listen me?
## Hello, can you listen me?
## Hello, can you listen me?
## Hello, can you listen me?
## Hello, can you listen me?Example 2
sumdice=function(n){
k=sample(1:6, size=n, replace=TRUE)
#return(k)
return(sum(k))
}
sumdice(2)## [1] 10sumdice(3)## [1] 7Example 3
dice=function(n){
k=sample(1:6, size=n, replace=TRUE)
return(k)
#return(k)
}
dice(2)## [1] 2 4dice(3)## [1] 5 3 2Example 4
sumdice1=function(m, n){
k=sample(1:m, size=n, replace=TRUE)
return(k)
#return(sum(k))
}
sumdice1(7,2)## [1] 7 2sumdice1(7,3)## [1] 4 7 1sumdice1(500,30)## [1] 330 416 329 3 121 263 322 106 445 99 104 368 217 52 13 372 362 188 213
## [20] 75 249 262 88 90 253 22 342 327 180 290Example 5
poisson2=function(lambda, x){
p=(exp(-lambda)*(lambda)^x)/factorial(x)
return(p)
}
poisson2(lambda=2, x=3)## [1] 0.18poisson2(lambda=(50/60), x=5)## [1] 0.0015slide 07 (Exploratory Data Analysis)
base plotting system
ex:1
data(airquality)
with(airquality, {
plot(Temp, Ozone)
lines(loess.smooth(Temp, Ozone))
})
ex:2
data(cars)
## Create the plot / draw canvas
with(cars, plot(speed, dist))
## Add annotation
title("Speed vs. Stopping distance")
The Lattice System
#install lattice packages
library(lattice)
state <- data.frame(state.x77, region = state.region)
xyplot(Life.Exp ~ Income | region, data = state, layout =
c(4, 1))
The ggplot2 System
#install.packages("ggplot2")
library(ggplot2)
data(mpg)
qplot(displ, hwy, data = mpg)## Warning: `qplot()` was deprecated in ggplot2 3.4.0.
slide 08 (The Base Plotting System)
Histogram
##The Base Plotting System
library(datasets)
hist(airquality$Ozone)
Boxplot
airquality <- transform(airquality,
Month = factor(Month))
boxplot(Ozone ~ Month, airquality, xlab
= "Month", ylab = "Ozone (ppb)")
slide 09 (The ggplot2 Plotting System)
Ex 1
with(airquality,{
plot(Temp,Ozone)
lines(loess.smooth(Temp,Ozone))
})
Ex 2
#install.packages("ggplot2")
library(ggplot2)
ggplot(airquality,aes(Temp,Ozone))+
geom_point()+
geom_smooth(method = "loess",se = F)## `geom_smooth()` using formula = 'y ~ x'## Warning: Removed 37 rows containing non-finite values (`stat_smooth()`).## Warning: Removed 37 rows containing missing values (`geom_point()`).
Ex 3
library(ggplot2)
str(mpg)## tibble [234 × 11] (S3: tbl_df/tbl/data.frame)
## $ manufacturer: chr [1:234] "audi" "audi" "audi" "audi" ...
## $ model : chr [1:234] "a4" "a4" "a4" "a4" ...
## $ displ : num [1:234] 1.8 1.8 2 2 2.8 2.8 3.1 1.8 1.8 2 ...
## $ year : int [1:234] 1999 1999 2008 2008 1999 1999 2008 1999 1999 2008 ...
## $ cyl : int [1:234] 4 4 4 4 6 6 6 4 4 4 ...
## $ trans : chr [1:234] "auto(l5)" "manual(m5)" "manual(m6)" "auto(av)" ...
## $ drv : chr [1:234] "f" "f" "f" "f" ...
## $ cty : int [1:234] 18 21 20 21 16 18 18 18 16 20 ...
## $ hwy : int [1:234] 29 29 31 30 26 26 27 26 25 28 ...
## $ fl : chr [1:234] "p" "p" "p" "p" ...
## $ class : chr [1:234] "compact" "compact" "compact" "compact" ...qplot(displ,hwy,data =mpg)
qplot(cty,cyl,data=mpg)
qplot(displ,cyl,data=mpg)
qplot(cyl,displ,data=mpg)
qplot(cty,displ,data=mpg)
qplot(displ,hwy,data=mpg,color=drv)
qplot(displ,hwy,data=mpg,color=fl)
qplot(displ,hwy,data=mpg,color=class)
View(mpg)
qplot(displ, hwy, data = mpg, geom = c("point", "smooth"))## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
slide 12 (R packages: Tidyverse)
Aesthetic Mappings
ggplot(data = ) +
#install.packages("tidyverse")
#install.packages(c("nycflights13", "gapminder", "Lahman"))
library(ggplot2)
#to know about mpg data set
ggplot(data = mpg) +
geom_point (mapping = aes(x = displ, y = hwy))
ggplot(data = mpg) +
geom_point(mapping = aes(x = displ, y = hwy, color = class))
ggplot(data = mpg) +
geom_point(mapping = aes(x = displ, y = hwy, size = class))## Warning: Using size for a discrete variable is not advised.
#to get rid of warnings in the previous plot:
ggplot(data = mpg) +
geom_point(mapping =aes(x = displ, y = hwy, size = displ))
#adding color "blue" instead of default color "black"
ggplot(data = mpg) + geom_point(mapping =
aes(x = displ, y = hwy, size =
displ),color="blue")
### Facets
ggplot(data = mpg) +
geom_point(mapping =aes(x = displ, y = hwy)) +
facet_wrap(~class, nrow = 2)
Geometric Objects
# left
ggplot(data = mpg) +
geom_point(mapping = aes(x = displ, y = hwy))
# right
ggplot(data = mpg) +
geom_smooth(mapping = aes(x = displ, y = hwy))## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
ggplot(data = mpg) +
geom_smooth (mapping = aes(x = displ,y = hwy, linetype = drv))## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
ggplot(data = mpg) +
geom_smooth(mapping = aes(x = displ, y = hwy, color=drv))## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
ggplot(data = mpg) +
geom_smooth(mapping = aes(x = displ, y = hwy))## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
ggplot(data = mpg) +
geom_smooth(mapping = aes(x = displ, y = hwy, group = drv))## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
ggplot(data = mpg) +
geom_smooth(mapping = aes(x = displ, y = hwy, color = drv),show.legend = F)## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
Statistical Transformations
ggplot(data = diamonds) +
stat_count(mapping = aes(x = cut))
ggplot(data = diamonds) +
geom_bar(mapping = aes(x = cut, y =..prop.., group = 1))## Warning: The dot-dot notation (`..prop..`) was deprecated in ggplot2 3.4.0.
## ℹ Please use `after_stat(prop)` instead.
ggplot(data = diamonds) +
stat_summary(
mapping = aes(x = cut, y = depth),
fun.ymin = min,
fun.ymax = max,
fun.y = median
)## Warning: The `fun.y` argument of `stat_summary()` is deprecated as of ggplot2 3.3.0.
## ℹ Please use the `fun` argument instead.## Warning: The `fun.ymin` argument of `stat_summary()` is deprecated as of ggplot2 3.3.0.
## ℹ Please use the `fun.min` argument instead.## Warning: The `fun.ymax` argument of `stat_summary()` is deprecated as of ggplot2 3.3.0.
## ℹ Please use the `fun.max` argument instead.
ggplot(data = diamonds) +
stat_summary(
mapping = aes(x = cut, y = price),
fun.ymin = min,
fun.ymax = max,
fun.y = median
)
Position Adjustments
ggplot(data = diamonds) +
geom_bar(mapping = aes(x = cut, color =
cut))
ggplot(data = diamonds) +
geom_bar(mapping = aes(x = cut, fill =
cut))
ggplot(data = diamonds) +
geom_bar(mapping = aes(x = cut, fill =
clarity))
ggplot(data = diamonds,
mapping = aes(x = cut, fill = clarity)
) +
geom_bar(alpha = 1/5, position = "identity")
ggplot( data = diamonds,
mapping = aes(x = cut, color = clarity)
) +
geom_bar(fill = NA, position = "identity")
INCOURSE SOLVE
1st incourse
2019
Q1
set.seed(100)
x<-rnorm(n = 100,mean = 15,sd = 4)
mean(x)## [1] 15var(x)## [1] 17min(x)## [1] 5.9max(x)## [1] 25hist(x)
Q2
set.seed(100)
x<-runif(n=10,min=10,20)2a
c<-matrix(x,2,5,byrow =T)
c## [,1] [,2] [,3] [,4] [,5]
## [1,] 13 13 16 11 15
## [2,] 15 18 14 15 122b
d<-matrix(x,nrow = 5,ncol=2,byrow = F)
d## [,1] [,2]
## [1,] 13 15
## [2,] 13 18
## [3,] 16 14
## [4,] 11 15
## [5,] 15 12Q3
a<-matrix(data = 1:24,nrow = 6,ncol = 4,byrow = T)
rownames(a)<-c("R1","R2","R3","R4","R5","R6")
colnames(a)<-c("C1","C2","C3","C4")
a## C1 C2 C3 C4
## R1 1 2 3 4
## R2 5 6 7 8
## R3 9 10 11 12
## R4 13 14 15 16
## R5 17 18 19 20
## R6 21 22 23 24or
a<-c(1:24)
rnam<-c("R1","R2","R3","R4","R5","R6")
cnam<-c("C1","C2","C3","C4")
x<-matrix(a,nrow=6,ncol=4,byrow = T,dimnames = list(rnam,cnam))
x## C1 C2 C3 C4
## R1 1 2 3 4
## R2 5 6 7 8
## R3 9 10 11 12
## R4 13 14 15 16
## R5 17 18 19 20
## R6 21 22 23 24Q5
age<-c(10,5,3,3,12,8,6,7,7,4,15,7,13,10,12)
weight<-c(30,20,15,11,35,28,16,19,22,20,55,27,46,35,39)
mean(age)## [1] 8.1mean(weight)## [1] 28sd(age)## [1] 3.7sd(weight)## [1] 12cor(age,weight)## [1] 0.95plot(age,weight)
abline(lm(weight~age))
#create scatter plot of x vs. y plot(x, y)
#add line of best fit to scatter plot abline(lm(y ~ x))
Q6
x<-c(1:120)
rnames<-c(1:10)
cnames<-c("a","b","c","d","e","f","g","h","i","j","k","l")
y<-matrix(x,nrow=10,ncol=12,byrow = T,dimnames = list(rnames,cnames))
y## a b c d e f g h i j k l
## 1 1 2 3 4 5 6 7 8 9 10 11 12
## 2 13 14 15 16 17 18 19 20 21 22 23 24
## 3 25 26 27 28 29 30 31 32 33 34 35 36
## 4 37 38 39 40 41 42 43 44 45 46 47 48
## 5 49 50 51 52 53 54 55 56 57 58 59 60
## 6 61 62 63 64 65 66 67 68 69 70 71 72
## 7 73 74 75 76 77 78 79 80 81 82 83 84
## 8 85 86 87 88 89 90 91 92 93 94 95 96
## 9 97 98 99 100 101 102 103 104 105 106 107 108
## 10 109 110 111 112 113 114 115 116 117 118 119 120sm<-y[,c(2,6,8)]
sm## b f h
## 1 2 6 8
## 2 14 18 20
## 3 26 30 32
## 4 38 42 44
## 5 50 54 56
## 6 62 66 68
## 7 74 78 80
## 8 86 90 92
## 9 98 102 104
## 10 110 114 116Q7
dose<-c(10,15,20,30,45,50,60,65,70,80)
drugA<-c(16,18,24,32,40,48,50,65,65,80)
drugB<-c(15,16,20,25,35,42,47,55,56,70)
plot(x = dose,y = drugA, type="b",
pch=15, lty=1, col="red", ylim=c(0, 80),
main="Drug A vs. Drug B",
xlab="Drug Dosage", ylab="Drug Response")
lines(x = dose,y = drugB, type="b",
pch=17, lty=2, col="blue")
abline(h=c(30), lwd=1.5, lty=2, col="gray")
legend("topleft", inset=.05, title="Drug Type", c("A","B"),
lty=c(1, 2), pch=c(15, 17), col=c("red", "blue"))
Q8
rm(list = ls())
library(ggplot2)
attach(mtcars)## The following objects are masked from mtcars (pos = 3):
##
## am, carb, cyl, disp, drat, gear, hp, mpg, qsec, vs, wt## The following object is masked from package:ggplot2:
##
## mpgplot(wt,mpg)
plot(mpg,disp)
hist(mpg)
boxplot(wt)
detach(mtcars)2020
Q.1
1a
sample<-(rpois(n = 500,lambda = 2))
mean(sample)## [1] 2var(sample)## [1] 2min(sample)## [1] 0max(sample)## [1] 71b
hist(sample)
Q.2
sam<-rnorm(n = 16,mean = 5,sd = sqrt(2))
sam## [1] 4.4 2.3 7.7 3.2 4.3 5.3 5.6 3.3 5.4 6.3 5.7 6.2 3.7 4.8 6.6 5.7a
matrix(data = sam,nrow = 2)## [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8]
## [1,] 4.4 7.7 4.3 5.6 5.4 5.7 3.7 6.6
## [2,] 2.3 3.2 5.3 3.3 6.3 6.2 4.8 5.7b
matrix(data = sam,ncol = 2,byrow = FALSE)## [,1] [,2]
## [1,] 4.4 5.4
## [2,] 2.3 6.3
## [3,] 7.7 5.7
## [4,] 3.2 6.2
## [5,] 4.3 3.7
## [6,] 5.3 4.8
## [7,] 5.6 6.6
## [8,] 3.3 5.7Q.3
The attach() function adds the data frame to R search path attach (mtcars)
The detach() function removes the data frame from the search path
detach(mtcars)
The with()function evaliate an expression in R environment
with(data = mtcars,summary(mpg))## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 10 15 19 20 23 34Q.4
id<-c(1:16)
iq<-c(180,150,140,110,122,181,186,170,117,142,115,175,103,90,101,135)
math<-c(85,60,70,71,55,78,90,89,75,65,55,80,46,40,39,60)
data.frame(id,iq,math)## id iq math
## 1 1 180 85
## 2 2 150 60
## 3 3 140 70
## 4 4 110 71
## 5 5 122 55
## 6 6 181 78
## 7 7 186 90
## 8 8 170 89
## 9 9 117 75
## 10 10 142 65
## 11 11 115 55
## 12 12 175 80
## 13 13 103 46
## 14 14 90 40
## 15 15 101 39
## 16 16 135 60#ans
mean(iq)## [1] 139sd(iq)## [1] 32mean(math)## [1] 66sd(math)## [1] 16cor(iq,math)## [1] 0.85cor.test(iq,math)##
## Pearson's product-moment correlation
##
## data: iq and math
## t = 6, df = 14, p-value = 3e-05
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.61 0.95
## sample estimates:
## cor
## 0.85plot(iq,math)
abline(lm(math~iq))
#### Q.5
d=matrix(data = 1:110,nrow = 10)
#for column label
colnames(d )<-c("a","b","c","d","e","f","g","h","i","j","k")
d## a b c d e f g h i j k
## [1,] 1 11 21 31 41 51 61 71 81 91 101
## [2,] 2 12 22 32 42 52 62 72 82 92 102
## [3,] 3 13 23 33 43 53 63 73 83 93 103
## [4,] 4 14 24 34 44 54 64 74 84 94 104
## [5,] 5 15 25 35 45 55 65 75 85 95 105
## [6,] 6 16 26 36 46 56 66 76 86 96 106
## [7,] 7 17 27 37 47 57 67 77 87 97 107
## [8,] 8 18 28 38 48 58 68 78 88 98 108
## [9,] 9 19 29 39 49 59 69 79 89 99 109
## [10,] 10 20 30 40 50 60 70 80 90 100 110#for row label
rownames(d )<-c("a","b","c","d","e","f","g","h","i","j")
d## a b c d e f g h i j k
## a 1 11 21 31 41 51 61 71 81 91 101
## b 2 12 22 32 42 52 62 72 82 92 102
## c 3 13 23 33 43 53 63 73 83 93 103
## d 4 14 24 34 44 54 64 74 84 94 104
## e 5 15 25 35 45 55 65 75 85 95 105
## f 6 16 26 36 46 56 66 76 86 96 106
## g 7 17 27 37 47 57 67 77 87 97 107
## h 8 18 28 38 48 58 68 78 88 98 108
## i 9 19 29 39 49 59 69 79 89 99 109
## j 10 20 30 40 50 60 70 80 90 100 110#for 2nd 4th 8th coloums
d[,c(2,4,8)]## b d h
## a 11 31 71
## b 12 32 72
## c 13 33 73
## d 14 34 74
## e 15 35 75
## f 16 36 76
## g 17 37 77
## h 18 38 78
## i 19 39 79
## j 20 40 80#for 2nd 4th 8th rows
d[c(2,4,8),]## a b c d e f g h i j k
## b 2 12 22 32 42 52 62 72 82 92 102
## d 4 14 24 34 44 54 64 74 84 94 104
## h 8 18 28 38 48 58 68 78 88 98 108alternative
colnames<-c("a","b","c","d","e","f","g","h","i","j","k")
rownames<-c("a","b","c","d","e","f","g","h","i","j")
matrix(data = 1:110,nrow = 10,dimnames = list(rownames,colnames))## a b c d e f g h i j k
## a 1 11 21 31 41 51 61 71 81 91 101
## b 2 12 22 32 42 52 62 72 82 92 102
## c 3 13 23 33 43 53 63 73 83 93 103
## d 4 14 24 34 44 54 64 74 84 94 104
## e 5 15 25 35 45 55 65 75 85 95 105
## f 6 16 26 36 46 56 66 76 86 96 106
## g 7 17 27 37 47 57 67 77 87 97 107
## h 8 18 28 38 48 58 68 78 88 98 108
## i 9 19 29 39 49 59 69 79 89 99 109
## j 10 20 30 40 50 60 70 80 90 100 110Q.6
doses<-c(10,15,20,30,45,50,60,65,70,80,85,90)
doses## [1] 10 15 20 30 45 50 60 65 70 80 85 90drugc<-c(16,18,24,32,40,48,50,65,65,80,82,87)
drugc## [1] 16 18 24 32 40 48 50 65 65 80 82 87drugd<-c(15,16,20,25,35,42,47,55,56,70,75,79)
drugd## [1] 15 16 20 25 35 42 47 55 56 70 75 79#two different way combining data
data.frame(doses,drugc,drugd)## doses drugc drugd
## 1 10 16 15
## 2 15 18 16
## 3 20 24 20
## 4 30 32 25
## 5 45 40 35
## 6 50 48 42
## 7 60 50 47
## 8 65 65 55
## 9 70 65 56
## 10 80 80 70
## 11 85 82 75
## 12 90 87 79cbind(doses,drugc,drugd)## doses drugc drugd
## [1,] 10 16 15
## [2,] 15 18 16
## [3,] 20 24 20
## [4,] 30 32 25
## [5,] 45 40 35
## [6,] 50 48 42
## [7,] 60 50 47
## [8,] 65 65 55
## [9,] 70 65 56
## [10,] 80 80 70
## [11,] 85 82 75
## [12,] 90 87 79##main part
plot(x = doses,y = drugc,type = "b",main = "Drug c vs Drug d",xlab ="Drug Doses", ylab = "Response to Drug",col="red",pch="c")
lines(x = doses,y = drugd,type = "b",col="blue",pch="d")
legend("topleft",title = "Durg types",c("C","D"),fill=c("red",'blue'))
Q.7
attach(mtcars)## The following objects are masked from mtcars (pos = 3):
##
## am, carb, cyl, disp, drat, gear, hp, mpg, qsec, vs, wt## The following object is masked from package:ggplot2:
##
## mpg7a
plot(wt,hp)
7b
plot(mpg,disp)
7c
hist(disp)
7d
boxplot(mpg)
detach(mtcars)2021(same 19)
Q1
set.seed(100)
x<-rnorm(n = 100,mean = 15,sd = 4)
mean(x)## [1] 15var(x)## [1] 17min(x)## [1] 5.9max(x)## [1] 25hist(x)
Q2
set.seed(13)
x<-runif(n=25,min=5,10)2a
c<-matrix(x,nrow=2,byrow =T)## Warning in matrix(x, nrow = 2, byrow = T): data length [25] is not a
## sub-multiple or multiple of the number of rows [2]c## [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10] [,11] [,12] [,13]
## [1,] 8.6 6.2 6.9 5.5 9.8 5.1 7.9 8.8 9.4 5.2 8.3 9.4 9.5
## [2,] 7.8 8.0 6.8 6.8 8.0 9.3 8.4 5.7 7.7 8.4 7.6 5.4 8.62b
d<-matrix(x,ncol=2,byrow = F)## Warning in matrix(x, ncol = 2, byrow = F): data length [25] is not a
## sub-multiple or multiple of the number of rows [13]d## [,1] [,2]
## [1,] 8.6 7.8
## [2,] 6.2 8.0
## [3,] 6.9 6.8
## [4,] 5.5 6.8
## [5,] 9.8 8.0
## [6,] 5.1 9.3
## [7,] 7.9 8.4
## [8,] 8.8 5.7
## [9,] 9.4 7.7
## [10,] 5.2 8.4
## [11,] 8.3 7.6
## [12,] 9.4 5.4
## [13,] 9.5 8.6Q3
a<-matrix(data = 1:24,nrow = 6,ncol = 4,byrow = T)
rownames(a)<-c("R1","R2","R3","R4","R5","R6")
colnames(a)<-c("C1","C2","C3","C4")
a## C1 C2 C3 C4
## R1 1 2 3 4
## R2 5 6 7 8
## R3 9 10 11 12
## R4 13 14 15 16
## R5 17 18 19 20
## R6 21 22 23 24or
a<-c(1:24)
rnam<-c("R1","R2","R3","R4","R5","R6")
cnam<-c("C1","C2","C3","C4")
x<-matrix(a,nrow=6,ncol=4,byrow = T,dimnames = list(rnam,cnam))
x## C1 C2 C3 C4
## R1 1 2 3 4
## R2 5 6 7 8
## R3 9 10 11 12
## R4 13 14 15 16
## R5 17 18 19 20
## R6 21 22 23 24Q5
age<-c(10,5,3,3,12,8,6,7,7,4,15,7,13,10,12)
weight<-c(30,20,15,11,35,28,16,19,22,20,55,27,46,35,39)
mean(age)## [1] 8.1mean(weight)## [1] 28sd(age)## [1] 3.7sd(weight)## [1] 12cor(age,weight)## [1] 0.95plot(age,weight)
abline(lm(weight~age))
#create scatter plot of x vs. y plot(x, y)
#add line of best fit to scatter plot abline(lm(y ~ x))
Q6
x<-c(1:120)
rnames<-c(1:10)
cnames<-c("a","b","c","d","e","f","g","h","i","j","k","l")
y<-matrix(x,nrow=10,ncol=12,byrow = T,dimnames = list(rnames,cnames))
y## a b c d e f g h i j k l
## 1 1 2 3 4 5 6 7 8 9 10 11 12
## 2 13 14 15 16 17 18 19 20 21 22 23 24
## 3 25 26 27 28 29 30 31 32 33 34 35 36
## 4 37 38 39 40 41 42 43 44 45 46 47 48
## 5 49 50 51 52 53 54 55 56 57 58 59 60
## 6 61 62 63 64 65 66 67 68 69 70 71 72
## 7 73 74 75 76 77 78 79 80 81 82 83 84
## 8 85 86 87 88 89 90 91 92 93 94 95 96
## 9 97 98 99 100 101 102 103 104 105 106 107 108
## 10 109 110 111 112 113 114 115 116 117 118 119 120sm<-y[,c(2,6,8)]
sm## b f h
## 1 2 6 8
## 2 14 18 20
## 3 26 30 32
## 4 38 42 44
## 5 50 54 56
## 6 62 66 68
## 7 74 78 80
## 8 86 90 92
## 9 98 102 104
## 10 110 114 116Q7
dose<-c(10,15,20,30,45,50,60,65,70,80)
drugA<-c(16,18,24,32,40,48,50,65,65,80)
drugB<-c(15,16,20,25,35,42,47,55,56,70)
plot(x = dose,y = drugA, type="b",
pch=15, lty=1, col="red", ylim=c(0, 80),
main="Drug A vs. Drug B",
xlab="Drug Dosage", ylab="Drug Response")
lines(x = dose,y = drugB, type="b",
pch=17, lty=2, col="blue")
abline(h=c(30), lwd=1.5, lty=2, col="gray")
legend("topleft", inset=.05, title="Drug Type", c("A","B"),
lty=c(1, 2), pch=c(15, 17), col=c("red", "blue"))
Q8
attach(mtcars)## The following objects are masked from mtcars (pos = 3):
##
## am, carb, cyl, disp, drat, gear, hp, mpg, qsec, vs, wt## The following object is masked from package:ggplot2:
##
## mpgplot(wt,mpg)
plot(mpg,disp)
hist(mpg)
boxplot(wt)
2022
Q1
1a
*how can you trace a working directory in r ?
To trace the current working directory in R, you can use the getwd() function. This function returns the current working directory as a character string.
To use this function, simply type getwd() into the R console and press enter. The output will be the current working directory.
Alternatively, you can also use the dir() function to list the files and directories in the current working directory. This function takes an optional argument that specifies the directory to list, so you can use dir(getwd()) to list the contents of the current working directory.
You can also change the current working directory using the setwd() function. This function takes a character string argument specifying the path to the new working directory. For example, to change the working directory to a folder named “data” located in the current working directory, you could use setwd(“data”).
It’s important to note that when working with file paths in R, you should use forward slashes (/) instead of backslashes () on Windows systems. For example, to specify a file path in the “data” folder located in the current working directory on a Windows system, you would use “./data” instead of “.”.
1b
What is necessity of changing working directory in r?
Changing the working directory in R is important when you are working with files or data that are located in a different directory than the one where R is currently running.
When you are working with files in R, you often need to specify the path to the file. If the file is located in a different directory than the one where R is currently running, you need to provide the full path to the file. Changing the working directory to the directory where the file is located allows you to simply use the file name instead of the full path, which can save time and reduce the chance of errors.
In addition, changing the working directory can make it easier to organize your files and keep your code organized. For example, you might keep your data files in a separate directory from your R scripts. By changing the working directory to the data directory, you can more easily access and work with the data files in your R scripts.
Finally, some R packages, such as shiny, require that the working directory be set correctly in order to work properly. For example, if you are building a shiny app that reads in data from a file, you need to set the working directory to the location of the file in order for the app to work correctly.
Overall, changing the working directory in R can make it easier to work with files, keep your code organized, and ensure that your code works correctly with R packages that require the working directory to be set properly.
Q2
2a
data("rivers")
rivers## [1] 735 320 325 392 524 450 1459 135 465 600 330 336 280 315 870
## [16] 906 202 329 290 1000 600 505 1450 840 1243 890 350 407 286 280
## [31] 525 720 390 250 327 230 265 850 210 630 260 230 360 730 600
## [46] 306 390 420 291 710 340 217 281 352 259 250 470 680 570 350
## [61] 300 560 900 625 332 2348 1171 3710 2315 2533 780 280 410 460 260
## [76] 255 431 350 760 618 338 981 1306 500 696 605 250 411 1054 735
## [91] 233 435 490 310 460 383 375 1270 545 445 1885 380 300 380 377
## [106] 425 276 210 800 420 350 360 538 1100 1205 314 237 610 360 540
## [121] 1038 424 310 300 444 301 268 620 215 652 900 525 246 360 529
## [136] 500 720 270 430 671 1770summary(rivers)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 135 310 425 591 680 37102b
hist(rivers)
boxplot(rivers)
Q3
3a
data(stackloss)
stackloss## Air.Flow Water.Temp Acid.Conc. stack.loss
## 1 80 27 89 42
## 2 80 27 88 37
## 3 75 25 90 37
## 4 62 24 87 28
## 5 62 22 87 18
## 6 62 23 87 18
## 7 62 24 93 19
## 8 62 24 93 20
## 9 58 23 87 15
## 10 58 18 80 14
## 11 58 18 89 14
## 12 58 17 88 13
## 13 58 18 82 11
## 14 58 19 93 12
## 15 50 18 89 8
## 16 50 18 86 7
## 17 50 19 72 8
## 18 50 19 79 8
## 19 50 20 80 9
## 20 56 20 82 15
## 21 70 20 91 15plot(stackloss$Air.Flow,stackloss$stack.loss)
abline(lm(stackloss$stack.loss~stackloss$Air.Flow))
plot(stackloss$Water.Temp,stackloss$stack.loss)
abline(lm(stackloss$stack.loss~stackloss$Water.Temp))
plot(stackloss$Acid.Conc.,stackloss$stack.loss)
abline(lm(stackloss$stack.loss~stackloss$Acid.Conc.))
3b
cor(stackloss$Air.Flow,stackloss$stack.loss)## [1] 0.92cor(stackloss$Water.Temp,stackloss$stack.loss)## [1] 0.88cor(stackloss$Acid.Conc.,stackloss$stack.loss)## [1] 0.43c
lm(data = stackloss,stack.loss~Air.Flow+Water.Temp+Acid.Conc.)##
## Call:
## lm(formula = stack.loss ~ Air.Flow + Water.Temp + Acid.Conc.,
## data = stackloss)
##
## Coefficients:
## (Intercept) Air.Flow Water.Temp Acid.Conc.
## -39.920 0.716 1.295 -0.152Q4
x<-c(1,2,3,4,5,6,7,8,9,10,11,12)
a<-c(73.3, 75.9, 89.2, 88.3, 90.0, 100.0, 85.4, 103.0, 91.2, 65.7, 63.3, 75.4)
b<-c(67.3, 59.5, 74.7, 58.3, 72.0, 48.3, 66.0, 75.6, 61.3, 50.6, 59.7, 61.0)
c<-c(104.0, 142.5, 80.1, 51.0, 70.1, 83.3, 109.8, 126.3, 104.4, 103.6, 132.2, 102.3)
plot(x = x,y = a,main="sunpot",type = "b",col="red" )
lines(x=x,y=b,col="blue")
lines(x=x,y=c)
Q5
data(attitude)
attitude## rating complaints privileges learning raises critical advance
## 1 43 51 30 39 61 92 45
## 2 63 64 51 54 63 73 47
## 3 71 70 68 69 76 86 48
## 4 61 63 45 47 54 84 35
## 5 81 78 56 66 71 83 47
## 6 43 55 49 44 54 49 34
## 7 58 67 42 56 66 68 35
## 8 71 75 50 55 70 66 41
## 9 72 82 72 67 71 83 31
## 10 67 61 45 47 62 80 41
## 11 64 53 53 58 58 67 34
## 12 67 60 47 39 59 74 41
## 13 69 62 57 42 55 63 25
## 14 68 83 83 45 59 77 35
## 15 77 77 54 72 79 77 46
## 16 81 90 50 72 60 54 36
## 17 74 85 64 69 79 79 63
## 18 65 60 65 75 55 80 60
## 19 65 70 46 57 75 85 46
## 20 50 58 68 54 64 78 52
## 21 50 40 33 34 43 64 33
## 22 64 61 52 62 66 80 41
## 23 53 66 52 50 63 80 37
## 24 40 37 42 58 50 57 49
## 25 63 54 42 48 66 75 33
## 26 66 77 66 63 88 76 72
## 27 78 75 58 74 80 78 49
## 28 48 57 44 45 51 83 38
## 29 85 85 71 71 77 74 55
## 30 82 82 39 59 64 78 39#a
plot(attitude$rating ,attitude$complaints )
#b
abline(lm(attitude$complaints~attitude$rating))
5c
attitude$learning## [1] 39 54 69 47 66 44 56 55 67 47 58 39 42 45 72 72 69 75 57 54 34 62 50 58 48
## [26] 63 74 45 71 59w<-cut(x = attitude$learning,breaks = c(30,45,60,75))
w## [1] (30,45] (45,60] (60,75] (45,60] (60,75] (30,45] (45,60] (45,60] (60,75]
## [10] (45,60] (45,60] (30,45] (30,45] (30,45] (60,75] (60,75] (60,75] (60,75]
## [19] (45,60] (45,60] (30,45] (60,75] (45,60] (45,60] (45,60] (60,75] (60,75]
## [28] (30,45] (60,75] (45,60]
## Levels: (30,45] (45,60] (60,75]table(w)## w
## (30,45] (45,60] (60,75]
## 7 12 112nd incourse
2019
Question no. 01
The ls() code lists all of the objects in your workspace.
The rm() code removes objects in your workspace. You can begin your code with the rm() function to clear all of the objects from your workspace to start with a clean environment. This way the workspace is empty and everything you create is clearly visible.
rm(list=ls())
attach(trees)
par(mfrow = c(2,2))
plot(Girth, Height)
plot(Girth, Volume)
hist(Volume)
boxplot(Volume)
detach(trees)Question no. 02
The swiss data set is built in R as a built in resource.
Recode the variable Infant.Mortality into four categories- the values upto first quartile as Good, first quartile until median as Normal, median until third quartile as Weaker and above third quartile as Poor.
a
#rm(list = ls())
#library(tidyverse) # needed for tibble & ggplot
#library(knitr) # needed for kable function
#tibble(swiss) # original data set
swiss## Fertility Agriculture Examination Education Catholic
## Courtelary 80 17.0 15 12 10.0
## Delemont 83 45.1 6 9 84.8
## Franches-Mnt 92 39.7 5 5 93.4
## Moutier 86 36.5 12 7 33.8
## Neuveville 77 43.5 17 15 5.2
## Porrentruy 76 35.3 9 7 90.6
## Broye 84 70.2 16 7 92.8
## Glane 92 67.8 14 8 97.2
## Gruyere 82 53.3 12 7 97.7
## Sarine 83 45.2 16 13 91.4
## Veveyse 87 64.5 14 6 98.6
## Aigle 64 62.0 21 12 8.5
## Aubonne 67 67.5 14 7 2.3
## Avenches 69 60.7 19 12 4.4
## Cossonay 62 69.3 22 5 2.8
## Echallens 68 72.6 18 2 24.2
## Grandson 72 34.0 17 8 3.3
## Lausanne 56 19.4 26 28 12.1
## La Vallee 54 15.2 31 20 2.1
## Lavaux 65 73.0 19 9 2.8
## Morges 66 59.8 22 10 5.2
## Moudon 65 55.1 14 3 4.5
## Nyone 57 50.9 22 12 15.1
## Orbe 57 54.1 20 6 4.2
## Oron 72 71.2 12 1 2.4
## Payerne 74 58.1 14 8 5.2
## Paysd'enhaut 72 63.5 6 3 2.6
## Rolle 60 60.8 16 10 7.7
## Vevey 58 26.8 25 19 18.5
## Yverdon 65 49.5 15 8 6.1
## Conthey 76 85.9 3 2 99.7
## Entremont 69 84.9 7 6 99.7
## Herens 77 89.7 5 2 100.0
## Martigwy 70 78.2 12 6 99.0
## Monthey 79 64.9 7 3 98.2
## St Maurice 65 75.9 9 9 99.1
## Sierre 92 84.6 3 3 99.5
## Sion 79 63.1 13 13 96.8
## Boudry 70 38.4 26 12 5.6
## La Chauxdfnd 66 7.7 29 11 13.8
## Le Locle 73 16.7 22 13 11.2
## Neuchatel 64 17.6 35 32 16.9
## Val de Ruz 78 37.6 15 7 5.0
## ValdeTravers 68 18.7 25 7 8.6
## V. De Geneve 35 1.2 37 53 42.3
## Rive Droite 45 46.6 16 29 50.4
## Rive Gauche 43 27.7 22 29 58.3
## Infant.Mortality
## Courtelary 22
## Delemont 22
## Franches-Mnt 20
## Moutier 20
## Neuveville 21
## Porrentruy 27
## Broye 24
## Glane 25
## Gruyere 21
## Sarine 24
## Veveyse 24
## Aigle 16
## Aubonne 19
## Avenches 23
## Cossonay 19
## Echallens 21
## Grandson 20
## Lausanne 20
## La Vallee 11
## Lavaux 20
## Morges 18
## Moudon 22
## Nyone 17
## Orbe 15
## Oron 21
## Payerne 24
## Paysd'enhaut 18
## Rolle 16
## Vevey 21
## Yverdon 22
## Conthey 15
## Entremont 20
## Herens 18
## Martigwy 19
## Monthey 20
## St Maurice 18
## Sierre 16
## Sion 18
## Boudry 20
## La Chauxdfnd 20
## Le Locle 19
## Neuchatel 23
## Val de Ruz 20
## ValdeTravers 20
## V. De Geneve 18
## Rive Droite 18
## Rive Gauche 19# ans
quantile(swiss$Infant.Mortality)## 0% 25% 50% 75% 100%
## 11 18 20 22 27swiss <- within(data = swiss, expr = {
status <- NA
status[Infant.Mortality <= 18.15] <- "Good"
status[Infant.Mortality > 18.15 & Infant.Mortality <= 20] <- "Normal"
status[Infant.Mortality > 20 & Infant.Mortality <= 21.70] <- "Weaker"
status[Infant.Mortality > 21.70] <- "Poor"
})
swiss## Fertility Agriculture Examination Education Catholic
## Courtelary 80 17.0 15 12 10.0
## Delemont 83 45.1 6 9 84.8
## Franches-Mnt 92 39.7 5 5 93.4
## Moutier 86 36.5 12 7 33.8
## Neuveville 77 43.5 17 15 5.2
## Porrentruy 76 35.3 9 7 90.6
## Broye 84 70.2 16 7 92.8
## Glane 92 67.8 14 8 97.2
## Gruyere 82 53.3 12 7 97.7
## Sarine 83 45.2 16 13 91.4
## Veveyse 87 64.5 14 6 98.6
## Aigle 64 62.0 21 12 8.5
## Aubonne 67 67.5 14 7 2.3
## Avenches 69 60.7 19 12 4.4
## Cossonay 62 69.3 22 5 2.8
## Echallens 68 72.6 18 2 24.2
## Grandson 72 34.0 17 8 3.3
## Lausanne 56 19.4 26 28 12.1
## La Vallee 54 15.2 31 20 2.1
## Lavaux 65 73.0 19 9 2.8
## Morges 66 59.8 22 10 5.2
## Moudon 65 55.1 14 3 4.5
## Nyone 57 50.9 22 12 15.1
## Orbe 57 54.1 20 6 4.2
## Oron 72 71.2 12 1 2.4
## Payerne 74 58.1 14 8 5.2
## Paysd'enhaut 72 63.5 6 3 2.6
## Rolle 60 60.8 16 10 7.7
## Vevey 58 26.8 25 19 18.5
## Yverdon 65 49.5 15 8 6.1
## Conthey 76 85.9 3 2 99.7
## Entremont 69 84.9 7 6 99.7
## Herens 77 89.7 5 2 100.0
## Martigwy 70 78.2 12 6 99.0
## Monthey 79 64.9 7 3 98.2
## St Maurice 65 75.9 9 9 99.1
## Sierre 92 84.6 3 3 99.5
## Sion 79 63.1 13 13 96.8
## Boudry 70 38.4 26 12 5.6
## La Chauxdfnd 66 7.7 29 11 13.8
## Le Locle 73 16.7 22 13 11.2
## Neuchatel 64 17.6 35 32 16.9
## Val de Ruz 78 37.6 15 7 5.0
## ValdeTravers 68 18.7 25 7 8.6
## V. De Geneve 35 1.2 37 53 42.3
## Rive Droite 45 46.6 16 29 50.4
## Rive Gauche 43 27.7 22 29 58.3
## Infant.Mortality status
## Courtelary 22 Poor
## Delemont 22 Poor
## Franches-Mnt 20 Weaker
## Moutier 20 Weaker
## Neuveville 21 Weaker
## Porrentruy 27 Poor
## Broye 24 Poor
## Glane 25 Poor
## Gruyere 21 Weaker
## Sarine 24 Poor
## Veveyse 24 Poor
## Aigle 16 Good
## Aubonne 19 Normal
## Avenches 23 Poor
## Cossonay 19 Normal
## Echallens 21 Weaker
## Grandson 20 Normal
## Lausanne 20 Weaker
## La Vallee 11 Good
## Lavaux 20 Normal
## Morges 18 Good
## Moudon 22 Poor
## Nyone 17 Good
## Orbe 15 Good
## Oron 21 Weaker
## Payerne 24 Poor
## Paysd'enhaut 18 Good
## Rolle 16 Good
## Vevey 21 Weaker
## Yverdon 22 Poor
## Conthey 15 Good
## Entremont 20 Normal
## Herens 18 Normal
## Martigwy 19 Normal
## Monthey 20 Weaker
## St Maurice 18 Good
## Sierre 16 Good
## Sion 18 Good
## Boudry 20 Weaker
## La Chauxdfnd 20 Weaker
## Le Locle 19 Normal
## Neuchatel 23 Poor
## Val de Ruz 20 Normal
## ValdeTravers 20 Normal
## V. De Geneve 18 Good
## Rive Droite 18 Normal
## Rive Gauche 19 Normalb
library(tidyverse) # needed for tibble & ggplot## Warning: package 'tidyverse' was built under R version 4.2.2## Warning: package 'tidyr' was built under R version 4.2.2## Warning: package 'readr' was built under R version 4.2.2## Warning: package 'purrr' was built under R version 4.2.2## Warning: package 'dplyr' was built under R version 4.2.2## Warning: package 'stringr' was built under R version 4.2.2## Warning: package 'forcats' was built under R version 4.2.2## Warning: package 'lubridate' was built under R version 4.2.2## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.0 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ lubridate 1.9.2 ✔ tibble 3.1.8
## ✔ purrr 1.0.1 ✔ tidyr 1.3.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ tidyr::expand() masks reshape::expand()
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ✖ dplyr::rename() masks reshape::rename()
## ✖ dplyr::select() masks MASS::select()
## ✖ dplyr::src() masks Hmisc::src()
## ✖ lubridate::stamp() masks reshape::stamp()
## ✖ dplyr::summarize() masks Hmisc::summarize()
## ℹ Use the ]8;;http://conflicted.r-lib.org/conflicted package]8;; to force all conflicts to become errorsggplot(data = swiss)+
geom_bar(mapping = aes(x = status), fill = "blue")
c
#Draw a random sample of size 10 from the swiss data set and calculate summary statistics for the variables Fertility and Education
set.seed(30)
new_swiss <- swiss[sample(x = nrow(swiss),size = 10),]
# don't forget that comma at the end!!
new_swiss## Fertility Agriculture Examination Education Catholic
## Sarine 83 45 16 13 91.4
## Rive Droite 45 47 16 29 50.4
## Aubonne 67 68 14 7 2.3
## Aigle 64 62 21 12 8.5
## Rive Gauche 43 28 22 29 58.3
## Val de Ruz 78 38 15 7 5.0
## Vevey 58 27 25 19 18.5
## Moutier 86 36 12 7 33.8
## Franches-Mnt 92 40 5 5 93.4
## Entremont 69 85 7 6 99.7
## Infant.Mortality status
## Sarine 24 Poor
## Rive Droite 18 Normal
## Aubonne 19 Normal
## Aigle 16 Good
## Rive Gauche 19 Normal
## Val de Ruz 20 Normal
## Vevey 21 Weaker
## Moutier 20 Weaker
## Franches-Mnt 20 Weaker
## Entremont 20 Normalsummary(new_swiss$Fertility)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 43 60 68 68 82 92summary(new_swiss$Education)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 5.0 7.0 9.5 13.4 17.5 29.0Question no. 03
Distinguish between FOR loop and WHILE loop by giving R executable examples.
For loop executes a statement repetitively till the variable’s value is contained in the sequence.The syntax is for(variable in sequence) statement Example:
for (i in 1:5) print("Hello world!")## [1] "Hello world!"
## [1] "Hello world!"
## [1] "Hello world!"
## [1] "Hello world!"
## [1] "Hello world!"While loop executes a statement repetitively till the condition is true The syntax is while(condition) statement Example:
i <-5
while(i > 0){
print("Hello world!");
i <- i-1
}## [1] "Hello world!"
## [1] "Hello world!"
## [1] "Hello world!"
## [1] "Hello world!"
## [1] "Hello world!"Question no. 04
Aggregates warpbreaks data for breaks by the variables wool and tension. Ignore the warnings and find the mean number of breaks corresponding to wool=A and tension=M
#rm(list = ls())
aggregate(warpbreaks, by = list(wool=warpbreaks$wool,tension=warpbreaks$tension), FUN=mean)## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA## wool tension breaks wool tension
## 1 A L 45 NA NA
## 2 B L 28 NA NA
## 3 A M 24 NA NA
## 4 B M 29 NA NA
## 5 A H 25 NA NA
## 6 B H 19 NA NAaggregate(warpbreaks,by=list(warpbreaks$wool,warpbreaks$tension),mean)## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA## Group.1 Group.2 breaks wool tension
## 1 A L 45 NA NA
## 2 B L 28 NA NA
## 3 A M 24 NA NA
## 4 B M 29 NA NA
## 5 A H 25 NA NA
## 6 B H 19 NA NAlibrary(reshape)
m<-melt(data = warpbreaks,id= c('wool' ,'tension'))
m## wool tension variable value
## 1 A L breaks 26
## 2 A L breaks 30
## 3 A L breaks 54
## 4 A L breaks 25
## 5 A L breaks 70
## 6 A L breaks 52
## 7 A L breaks 51
## 8 A L breaks 26
## 9 A L breaks 67
## 10 A M breaks 18
## 11 A M breaks 21
## 12 A M breaks 29
## 13 A M breaks 17
## 14 A M breaks 12
## 15 A M breaks 18
## 16 A M breaks 35
## 17 A M breaks 30
## 18 A M breaks 36
## 19 A H breaks 36
## 20 A H breaks 21
## 21 A H breaks 24
## 22 A H breaks 18
## 23 A H breaks 10
## 24 A H breaks 43
## 25 A H breaks 28
## 26 A H breaks 15
## 27 A H breaks 26
## 28 B L breaks 27
## 29 B L breaks 14
## 30 B L breaks 29
## 31 B L breaks 19
## 32 B L breaks 29
## 33 B L breaks 31
## 34 B L breaks 41
## 35 B L breaks 20
## 36 B L breaks 44
## 37 B M breaks 42
## 38 B M breaks 26
## 39 B M breaks 19
## 40 B M breaks 16
## 41 B M breaks 39
## 42 B M breaks 28
## 43 B M breaks 21
## 44 B M breaks 39
## 45 B M breaks 29
## 46 B H breaks 20
## 47 B H breaks 21
## 48 B H breaks 24
## 49 B H breaks 17
## 50 B H breaks 13
## 51 B H breaks 15
## 52 B H breaks 15
## 53 B H breaks 16
## 54 B H breaks 28cast(data = m,wool+tension ~ variable,mean)## wool tension breaks
## 1 A L 45
## 2 A M 24
## 3 A H 25
## 4 B L 28
## 5 B M 29
## 6 B H 19Question no. 05
rm(list = ls())
p_weibull <- function(x, a, lambda){
if (! x >= 0){
0
} else {
if (! a > 0){
"a must be greater than zero"
} else {
if (! lambda > 0){
"lambda must be greater than zero"
} else {
1-exp((-1*(lambda*x))**a)
}
}
}
}
p_weibull(5,3,1) # function we created## [1] 1pweibull(5,3,1) # fuction built in 'stats' package## [1] 1p_weibull(1.0,3,2)## [1] 1pweibull(1.0,3,.5)## [1] 1p_weibull(1.5,3,5)## [1] 1pweibull(1.5,3,5^-1)## [1] 1p_weibull(-5,3,1)## [1] 0pweibull(-5,3,1)## [1] 0p_weibull(5,-3,1)## [1] "a must be greater than zero"pweibull(5,-3,1)## Warning in pweibull(5, -3, 1): NaNs produced## [1] NaNp_weibull(5,3,-1)## [1] "lambda must be greater than zero"pweibull(5,3,-1)## Warning in pweibull(5, 3, -1): NaNs produced## [1] NaN2020
Question no. 01
rm(list = ls())
breaks<-c(26, 30, 54, 47, 26, 48, 58, 76, 21, 56, 96, 30, 14, 45, 65, 32, 14, 85, 45)
wool<-c('A','A','A', 'B', 'B', 'B', 'C', 'C', 'C', 'D', 'D', 'D', 'D', 'D', 'D', 'E', 'E', 'E', 'E')
tension<-c('L','L', 'L', 'L', 'L', 'M', 'M', 'M', 'M', 'M', 'M', 'M', 'M', 'N', 'N', 'N','N', 'N', 'N')
data<-data.frame(breaks,wool,tension)
data## breaks wool tension
## 1 26 A L
## 2 30 A L
## 3 54 A L
## 4 47 B L
## 5 26 B L
## 6 48 B M
## 7 58 C M
## 8 76 C M
## 9 21 C M
## 10 56 D M
## 11 96 D M
## 12 30 D M
## 13 14 D M
## 14 45 D N
## 15 65 D N
## 16 32 E N
## 17 14 E N
## 18 85 E N
## 19 45 E N1a
quantile(breaks)## 0% 25% 50% 75% 100%
## 14 28 45 57 96status<-NA
status[breaks<=28]<-"Good"
status[breaks>28 & breaks <=45 ]<-"Normal"
status[breaks>45 & breaks <=57 ]<-"Weaker"
status[breaks>57 ]<-"Poor"
status## [1] "Good" "Normal" "Weaker" "Weaker" "Good" "Weaker" "Poor" "Poor"
## [9] "Good" "Weaker" "Poor" "Normal" "Good" "Normal" "Poor" "Normal"
## [17] "Good" "Poor" "Normal"data$status<-status
data## breaks wool tension status
## 1 26 A L Good
## 2 30 A L Normal
## 3 54 A L Weaker
## 4 47 B L Weaker
## 5 26 B L Good
## 6 48 B M Weaker
## 7 58 C M Poor
## 8 76 C M Poor
## 9 21 C M Good
## 10 56 D M Weaker
## 11 96 D M Poor
## 12 30 D M Normal
## 13 14 D M Good
## 14 45 D N Normal
## 15 65 D N Poor
## 16 32 E N Normal
## 17 14 E N Good
## 18 85 E N Poor
## 19 45 E N Normalalternative
data<- within(data = data,expr = {
quantile(breaks)
status1<-NULL
status1[breaks<=28]<-"Good"
status1[breaks>28 & breaks <=45 ]<-"Normal"
status1[breaks>45 & breaks <=57 ]<-"Weaker"
status1[breaks>57 ]<-"Poor"
status1
})
data## breaks wool tension status status1
## 1 26 A L Good Good
## 2 30 A L Normal Normal
## 3 54 A L Weaker Weaker
## 4 47 B L Weaker Weaker
## 5 26 B L Good Good
## 6 48 B M Weaker Weaker
## 7 58 C M Poor Poor
## 8 76 C M Poor Poor
## 9 21 C M Good Good
## 10 56 D M Weaker Weaker
## 11 96 D M Poor Poor
## 12 30 D M Normal Normal
## 13 14 D M Good Good
## 14 45 D N Normal Normal
## 15 65 D N Poor Poor
## 16 32 E N Normal Normal
## 17 14 E N Good Good
## 18 85 E N Poor Poor
## 19 45 E N Normal Normal1b
library(tidyverse)
ggplot(data = data)+
geom_bar(aes(status))
1c
set.seed(13)
sample<-data[sample(x = nrow(data),size = 5),]
sample## breaks wool tension status status1
## 3 54 A L Weaker Weaker
## 5 26 B L Good Good
## 10 56 D M Weaker Weaker
## 13 14 D M Good Good
## 6 48 B M Weaker Weakersummary(wool)## Length Class Mode
## 19 character charactersummary(tension)## Length Class Mode
## 19 character characterQuestion no. 03
3a
Detect the errors from the following codes & explain why they appear to be errors. (I) qplot(x1, x2, data=(), color=x3) data argument should be assigned to a valid data frame in which object x1, x2, x3 must exist.
- boxplot(nitrogen=Month, airquality, xlab=Month, ylab=Nitrogen) Nitrogen object does not exist in airquality data frame. We should replace it with Ozone. Also the formula is incorrect it should be written with ~ sign. Also x- and y-axis annotations should be characters not object.
3b
Write down the executable R codes to generate 30 random numbers from the following distributions:
#rm(list = ls())
set.seed(30)
# log normal
rlnorm(30)## [1] 0.28 0.71 0.59 3.57 6.20 0.22 1.12 0.47 0.51 1.32 0.36 0.16 0.51 0.94 2.41
## [16] 1.31 0.98 0.59 0.24 0.16 0.85 2.13 0.40 2.23 4.44 0.33 0.59 0.24 0.29 1.26# geometric
rgeom(30, .4)## [1] 2 1 1 4 0 0 0 0 2 0 0 5 2 0 4 0 0 7 1 2 0 1 1 0 0 1 0 2 0 0# gamma
round(rgamma(30, shape = 5), 2)## [1] 8.7 7.2 3.1 4.7 2.5 5.6 3.1 2.6 4.1 8.8 4.3 3.6 5.7 6.6 7.6 6.9 2.5 5.8 4.0
## [20] 6.8 2.7 5.1 4.7 5.1 5.0 2.0 3.5 6.0 3.4 6.4Question no. 04
Interpret the following R codes (a) apply(data5, 2, median, trim=.12)
Calculate trimmed (based on middle 76 percent) column medians of the data object data5
- marks< − rnorm(50, 30, 50)
Create a numeric vector named marks by generating 50 random numbers that follow normal disrtibution with mean 30 and stadanrd deviation 50.
** results< − ifelse(marks>= 50, ”Passed”, ”Failed”)
Create a character vector named results of size 50, which include “Passed” if the marks obtained is 50 or more, and include “Failed” if marks obtained in less than 50.
- boxplot(oxygen∼year, weather, xlab=”year”, ylab=”oxygen”)
Create a boxplot by splitting oxygen (which must be a numeric vector) into year from the data object weather putting oxygen data in the y-axis and year in the x-axis.
Question no. 05
Write a fuction to calculate 1−e−λx where x≥0, λ is the rate parameter
#rm(list = ls())
p_exp <- function(x, lambda){
if (! x >= 0){
0
} else {
1-exp(-1*lambda*x)
}
}
p_exp(1,4) # function we created ## [1] 0.98pexp(1,4) # function built in 'stats' package## [1] 0.98p_exp(-1,4) ## [1] 0pexp(-1,4)## [1] 0d_exp <- function(x, lambda){
if (! x >= 0){
0
} else {
exp(-1*lambda*x)*lambda
}
}
d_exp(1,4) # function we created ## [1] 0.073dexp(x = 1,4) # function built in 'stats' package## [1] 0.073d_exp(-1,4) ## [1] 0dexp(-1,4)## [1] 02021 (same 19)
Q1
Base plotting system, lattice system, and ggplot2 are all R packages that can be used for data visualization. Each has its own advantages and disadvantages, and the choice of which to use may depend on the specific needs of the user.
Base Plotting System: Advantages:
Base plotting system is the default plotting system in R, so it requires no additional packages or installation. It provides a lot of control over the appearance of plots, allowing users to customize almost every aspect of the plot. It has a very shallow learning curve, and is easy to use for simple plots. Disadvantages:
It can be difficult to use for more complex plots. The code required to produce even simple plots can be quite verbose and difficult to read. It produces static plots that cannot be easily updated or modified. Lattice System: Advantages:
The lattice system provides a wide range of statistical graphics with many advanced features, such as multi-panel displays and conditioning plots. It provides a simple syntax for producing complex graphics. It is well-suited for creating plots that show relationships between multiple variables. Disadvantages:
It can be difficult to customize plots to the degree that the base plotting system allows. It can be slower than other plotting systems when creating large numbers of plots. ggplot2: Advantages:
ggplot2 is a powerful and flexible plotting system, capable of creating complex and beautiful visualizations. It has a more intuitive syntax than the base plotting system, making it easier to use for complex plots. It is highly customizable, and allows users to create plots that are tailored to their needs. Disadvantages:
ggplot2 can have a steep learning curve for users unfamiliar with its syntax and structure. It may require additional packages to produce certain types of plots, adding to the complexity of the process. It can be slower than other plotting systems when creating large numbers of plots. In summary, the base plotting system is easy to use and highly customizable, but can be difficult to use for complex plots. The lattice system is well-suited for creating plots with multiple variables, but can be difficult to customize. ggplot2 is highly flexible and customizable, but may require additional packages and can have a steep learning curve. The choice of which to use may depend on the specific needs of the user, and the type of plot they are looking to create.
2022
Q1
1a
library(Hmisc) world95 summary(world95\(babymort) cor(world95\)lifeexpm,world95\(literacy, na.rm= T) abline(lm(world95\)literacy~world95$lifeexpm),)
Q3
3a
library(reshape)
ChickWeight## Grouped Data: weight ~ Time | Chick
## 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 1
## 7 106 12 1 1
## 8 125 14 1 1
## 9 149 16 1 1
## 10 171 18 1 1
## 11 199 20 1 1
## 12 205 21 1 1
## 13 40 0 2 1
## 14 49 2 2 1
## 15 58 4 2 1
## 16 72 6 2 1
## 17 84 8 2 1
## 18 103 10 2 1
## 19 122 12 2 1
## 20 138 14 2 1
## 21 162 16 2 1
## 22 187 18 2 1
## 23 209 20 2 1
## 24 215 21 2 1
## 25 43 0 3 1
## 26 39 2 3 1
## 27 55 4 3 1
## 28 67 6 3 1
## 29 84 8 3 1
## 30 99 10 3 1
## 31 115 12 3 1
## 32 138 14 3 1
## 33 163 16 3 1
## 34 187 18 3 1
## 35 198 20 3 1
## 36 202 21 3 1
## 37 42 0 4 1
## 38 49 2 4 1
## 39 56 4 4 1
## 40 67 6 4 1
## 41 74 8 4 1
## 42 87 10 4 1
## 43 102 12 4 1
## 44 108 14 4 1
## 45 136 16 4 1
## 46 154 18 4 1
## 47 160 20 4 1
## 48 157 21 4 1
## 49 41 0 5 1
## 50 42 2 5 1
## 51 48 4 5 1
## 52 60 6 5 1
## 53 79 8 5 1
## 54 106 10 5 1
## 55 141 12 5 1
## 56 164 14 5 1
## 57 197 16 5 1
## 58 199 18 5 1
## 59 220 20 5 1
## 60 223 21 5 1
## 61 41 0 6 1
## 62 49 2 6 1
## 63 59 4 6 1
## 64 74 6 6 1
## 65 97 8 6 1
## 66 124 10 6 1
## 67 141 12 6 1
## 68 148 14 6 1
## 69 155 16 6 1
## 70 160 18 6 1
## 71 160 20 6 1
## 72 157 21 6 1
## 73 41 0 7 1
## 74 49 2 7 1
## 75 57 4 7 1
## 76 71 6 7 1
## 77 89 8 7 1
## 78 112 10 7 1
## 79 146 12 7 1
## 80 174 14 7 1
## 81 218 16 7 1
## 82 250 18 7 1
## 83 288 20 7 1
## 84 305 21 7 1
## 85 42 0 8 1
## 86 50 2 8 1
## 87 61 4 8 1
## 88 71 6 8 1
## 89 84 8 8 1
## 90 93 10 8 1
## 91 110 12 8 1
## 92 116 14 8 1
## 93 126 16 8 1
## 94 134 18 8 1
## 95 125 20 8 1
## 96 42 0 9 1
## 97 51 2 9 1
## 98 59 4 9 1
## 99 68 6 9 1
## 100 85 8 9 1
## 101 96 10 9 1
## 102 90 12 9 1
## 103 92 14 9 1
## 104 93 16 9 1
## 105 100 18 9 1
## 106 100 20 9 1
## 107 98 21 9 1
## 108 41 0 10 1
## 109 44 2 10 1
## 110 52 4 10 1
## 111 63 6 10 1
## 112 74 8 10 1
## 113 81 10 10 1
## 114 89 12 10 1
## 115 96 14 10 1
## 116 101 16 10 1
## 117 112 18 10 1
## 118 120 20 10 1
## 119 124 21 10 1
## 120 43 0 11 1
## 121 51 2 11 1
## 122 63 4 11 1
## 123 84 6 11 1
## 124 112 8 11 1
## 125 139 10 11 1
## 126 168 12 11 1
## 127 177 14 11 1
## 128 182 16 11 1
## 129 184 18 11 1
## 130 181 20 11 1
## 131 175 21 11 1
## 132 41 0 12 1
## 133 49 2 12 1
## 134 56 4 12 1
## 135 62 6 12 1
## 136 72 8 12 1
## 137 88 10 12 1
## 138 119 12 12 1
## 139 135 14 12 1
## 140 162 16 12 1
## 141 185 18 12 1
## 142 195 20 12 1
## 143 205 21 12 1
## 144 41 0 13 1
## 145 48 2 13 1
## 146 53 4 13 1
## 147 60 6 13 1
## 148 65 8 13 1
## 149 67 10 13 1
## 150 71 12 13 1
## 151 70 14 13 1
## 152 71 16 13 1
## 153 81 18 13 1
## 154 91 20 13 1
## 155 96 21 13 1
## 156 41 0 14 1
## 157 49 2 14 1
## 158 62 4 14 1
## 159 79 6 14 1
## 160 101 8 14 1
## 161 128 10 14 1
## 162 164 12 14 1
## 163 192 14 14 1
## 164 227 16 14 1
## 165 248 18 14 1
## 166 259 20 14 1
## 167 266 21 14 1
## 168 41 0 15 1
## 169 49 2 15 1
## 170 56 4 15 1
## 171 64 6 15 1
## 172 68 8 15 1
## 173 68 10 15 1
## 174 67 12 15 1
## 175 68 14 15 1
## 176 41 0 16 1
## 177 45 2 16 1
## 178 49 4 16 1
## 179 51 6 16 1
## 180 57 8 16 1
## 181 51 10 16 1
## 182 54 12 16 1
## 183 42 0 17 1
## 184 51 2 17 1
## 185 61 4 17 1
## 186 72 6 17 1
## 187 83 8 17 1
## 188 89 10 17 1
## 189 98 12 17 1
## 190 103 14 17 1
## 191 113 16 17 1
## 192 123 18 17 1
## 193 133 20 17 1
## 194 142 21 17 1
## 195 39 0 18 1
## 196 35 2 18 1
## 197 43 0 19 1
## 198 48 2 19 1
## 199 55 4 19 1
## 200 62 6 19 1
## 201 65 8 19 1
## 202 71 10 19 1
## 203 82 12 19 1
## 204 88 14 19 1
## 205 106 16 19 1
## 206 120 18 19 1
## 207 144 20 19 1
## 208 157 21 19 1
## 209 41 0 20 1
## 210 47 2 20 1
## 211 54 4 20 1
## 212 58 6 20 1
## 213 65 8 20 1
## 214 73 10 20 1
## 215 77 12 20 1
## 216 89 14 20 1
## 217 98 16 20 1
## 218 107 18 20 1
## 219 115 20 20 1
## 220 117 21 20 1
## 221 40 0 21 2
## 222 50 2 21 2
## 223 62 4 21 2
## 224 86 6 21 2
## 225 125 8 21 2
## 226 163 10 21 2
## 227 217 12 21 2
## 228 240 14 21 2
## 229 275 16 21 2
## 230 307 18 21 2
## 231 318 20 21 2
## 232 331 21 21 2
## 233 41 0 22 2
## 234 55 2 22 2
## 235 64 4 22 2
## 236 77 6 22 2
## 237 90 8 22 2
## 238 95 10 22 2
## 239 108 12 22 2
## 240 111 14 22 2
## 241 131 16 22 2
## 242 148 18 22 2
## 243 164 20 22 2
## 244 167 21 22 2
## 245 43 0 23 2
## 246 52 2 23 2
## 247 61 4 23 2
## 248 73 6 23 2
## 249 90 8 23 2
## 250 103 10 23 2
## 251 127 12 23 2
## 252 135 14 23 2
## 253 145 16 23 2
## 254 163 18 23 2
## 255 170 20 23 2
## 256 175 21 23 2
## 257 42 0 24 2
## 258 52 2 24 2
## 259 58 4 24 2
## 260 74 6 24 2
## 261 66 8 24 2
## 262 68 10 24 2
## 263 70 12 24 2
## 264 71 14 24 2
## 265 72 16 24 2
## 266 72 18 24 2
## 267 76 20 24 2
## 268 74 21 24 2
## 269 40 0 25 2
## 270 49 2 25 2
## 271 62 4 25 2
## 272 78 6 25 2
## 273 102 8 25 2
## 274 124 10 25 2
## 275 146 12 25 2
## 276 164 14 25 2
## 277 197 16 25 2
## 278 231 18 25 2
## 279 259 20 25 2
## 280 265 21 25 2
## 281 42 0 26 2
## 282 48 2 26 2
## 283 57 4 26 2
## 284 74 6 26 2
## 285 93 8 26 2
## 286 114 10 26 2
## 287 136 12 26 2
## 288 147 14 26 2
## 289 169 16 26 2
## 290 205 18 26 2
## 291 236 20 26 2
## 292 251 21 26 2
## 293 39 0 27 2
## 294 46 2 27 2
## 295 58 4 27 2
## 296 73 6 27 2
## 297 87 8 27 2
## 298 100 10 27 2
## 299 115 12 27 2
## 300 123 14 27 2
## 301 144 16 27 2
## 302 163 18 27 2
## 303 185 20 27 2
## 304 192 21 27 2
## 305 39 0 28 2
## 306 46 2 28 2
## 307 58 4 28 2
## 308 73 6 28 2
## 309 92 8 28 2
## 310 114 10 28 2
## 311 145 12 28 2
## 312 156 14 28 2
## 313 184 16 28 2
## 314 207 18 28 2
## 315 212 20 28 2
## 316 233 21 28 2
## 317 39 0 29 2
## 318 48 2 29 2
## 319 59 4 29 2
## 320 74 6 29 2
## 321 87 8 29 2
## 322 106 10 29 2
## 323 134 12 29 2
## 324 150 14 29 2
## 325 187 16 29 2
## 326 230 18 29 2
## 327 279 20 29 2
## 328 309 21 29 2
## 329 42 0 30 2
## 330 48 2 30 2
## 331 59 4 30 2
## 332 72 6 30 2
## 333 85 8 30 2
## 334 98 10 30 2
## 335 115 12 30 2
## 336 122 14 30 2
## 337 143 16 30 2
## 338 151 18 30 2
## 339 157 20 30 2
## 340 150 21 30 2
## 341 42 0 31 3
## 342 53 2 31 3
## 343 62 4 31 3
## 344 73 6 31 3
## 345 85 8 31 3
## 346 102 10 31 3
## 347 123 12 31 3
## 348 138 14 31 3
## 349 170 16 31 3
## 350 204 18 31 3
## 351 235 20 31 3
## 352 256 21 31 3
## 353 41 0 32 3
## 354 49 2 32 3
## 355 65 4 32 3
## 356 82 6 32 3
## 357 107 8 32 3
## 358 129 10 32 3
## 359 159 12 32 3
## 360 179 14 32 3
## 361 221 16 32 3
## 362 263 18 32 3
## 363 291 20 32 3
## 364 305 21 32 3
## 365 39 0 33 3
## 366 50 2 33 3
## 367 63 4 33 3
## 368 77 6 33 3
## 369 96 8 33 3
## 370 111 10 33 3
## 371 137 12 33 3
## 372 144 14 33 3
## 373 151 16 33 3
## 374 146 18 33 3
## 375 156 20 33 3
## 376 147 21 33 3
## 377 41 0 34 3
## 378 49 2 34 3
## 379 63 4 34 3
## 380 85 6 34 3
## 381 107 8 34 3
## 382 134 10 34 3
## 383 164 12 34 3
## 384 186 14 34 3
## 385 235 16 34 3
## 386 294 18 34 3
## 387 327 20 34 3
## 388 341 21 34 3
## 389 41 0 35 3
## 390 53 2 35 3
## 391 64 4 35 3
## 392 87 6 35 3
## 393 123 8 35 3
## 394 158 10 35 3
## 395 201 12 35 3
## 396 238 14 35 3
## 397 287 16 35 3
## 398 332 18 35 3
## 399 361 20 35 3
## 400 373 21 35 3
## 401 39 0 36 3
## 402 48 2 36 3
## 403 61 4 36 3
## 404 76 6 36 3
## 405 98 8 36 3
## 406 116 10 36 3
## 407 145 12 36 3
## 408 166 14 36 3
## 409 198 16 36 3
## 410 227 18 36 3
## 411 225 20 36 3
## 412 220 21 36 3
## 413 41 0 37 3
## 414 48 2 37 3
## 415 56 4 37 3
## 416 68 6 37 3
## 417 80 8 37 3
## 418 83 10 37 3
## 419 103 12 37 3
## 420 112 14 37 3
## 421 135 16 37 3
## 422 157 18 37 3
## 423 169 20 37 3
## 424 178 21 37 3
## 425 41 0 38 3
## 426 49 2 38 3
## 427 61 4 38 3
## 428 74 6 38 3
## 429 98 8 38 3
## 430 109 10 38 3
## 431 128 12 38 3
## 432 154 14 38 3
## 433 192 16 38 3
## 434 232 18 38 3
## 435 280 20 38 3
## 436 290 21 38 3
## 437 42 0 39 3
## 438 50 2 39 3
## 439 61 4 39 3
## 440 78 6 39 3
## 441 89 8 39 3
## 442 109 10 39 3
## 443 130 12 39 3
## 444 146 14 39 3
## 445 170 16 39 3
## 446 214 18 39 3
## 447 250 20 39 3
## 448 272 21 39 3
## 449 41 0 40 3
## 450 55 2 40 3
## 451 66 4 40 3
## 452 79 6 40 3
## 453 101 8 40 3
## 454 120 10 40 3
## 455 154 12 40 3
## 456 182 14 40 3
## 457 215 16 40 3
## 458 262 18 40 3
## 459 295 20 40 3
## 460 321 21 40 3
## 461 42 0 41 4
## 462 51 2 41 4
## 463 66 4 41 4
## 464 85 6 41 4
## 465 103 8 41 4
## 466 124 10 41 4
## 467 155 12 41 4
## 468 153 14 41 4
## 469 175 16 41 4
## 470 184 18 41 4
## 471 199 20 41 4
## 472 204 21 41 4
## 473 42 0 42 4
## 474 49 2 42 4
## 475 63 4 42 4
## 476 84 6 42 4
## 477 103 8 42 4
## 478 126 10 42 4
## 479 160 12 42 4
## 480 174 14 42 4
## 481 204 16 42 4
## 482 234 18 42 4
## 483 269 20 42 4
## 484 281 21 42 4
## 485 42 0 43 4
## 486 55 2 43 4
## 487 69 4 43 4
## 488 96 6 43 4
## 489 131 8 43 4
## 490 157 10 43 4
## 491 184 12 43 4
## 492 188 14 43 4
## 493 197 16 43 4
## 494 198 18 43 4
## 495 199 20 43 4
## 496 200 21 43 4
## 497 42 0 44 4
## 498 51 2 44 4
## 499 65 4 44 4
## 500 86 6 44 4
## 501 103 8 44 4
## 502 118 10 44 4
## 503 127 12 44 4
## 504 138 14 44 4
## 505 145 16 44 4
## 506 146 18 44 4
## 507 41 0 45 4
## 508 50 2 45 4
## 509 61 4 45 4
## 510 78 6 45 4
## 511 98 8 45 4
## 512 117 10 45 4
## 513 135 12 45 4
## 514 141 14 45 4
## 515 147 16 45 4
## 516 174 18 45 4
## 517 197 20 45 4
## 518 196 21 45 4
## 519 40 0 46 4
## 520 52 2 46 4
## 521 62 4 46 4
## 522 82 6 46 4
## 523 101 8 46 4
## 524 120 10 46 4
## 525 144 12 46 4
## 526 156 14 46 4
## 527 173 16 46 4
## 528 210 18 46 4
## 529 231 20 46 4
## 530 238 21 46 4
## 531 41 0 47 4
## 532 53 2 47 4
## 533 66 4 47 4
## 534 79 6 47 4
## 535 100 8 47 4
## 536 123 10 47 4
## 537 148 12 47 4
## 538 157 14 47 4
## 539 168 16 47 4
## 540 185 18 47 4
## 541 210 20 47 4
## 542 205 21 47 4
## 543 39 0 48 4
## 544 50 2 48 4
## 545 62 4 48 4
## 546 80 6 48 4
## 547 104 8 48 4
## 548 125 10 48 4
## 549 154 12 48 4
## 550 170 14 48 4
## 551 222 16 48 4
## 552 261 18 48 4
## 553 303 20 48 4
## 554 322 21 48 4
## 555 40 0 49 4
## 556 53 2 49 4
## 557 64 4 49 4
## 558 85 6 49 4
## 559 108 8 49 4
## 560 128 10 49 4
## 561 152 12 49 4
## 562 166 14 49 4
## 563 184 16 49 4
## 564 203 18 49 4
## 565 233 20 49 4
## 566 237 21 49 4
## 567 41 0 50 4
## 568 54 2 50 4
## 569 67 4 50 4
## 570 84 6 50 4
## 571 105 8 50 4
## 572 122 10 50 4
## 573 155 12 50 4
## 574 175 14 50 4
## 575 205 16 50 4
## 576 234 18 50 4
## 577 264 20 50 4
## 578 264 21 50 4x<-melt(data =ChickWeight,id=c("Diet"))
x## Diet variable value
## 1 1 weight 42
## 2 1 weight 51
## 3 1 weight 59
## 4 1 weight 64
## 5 1 weight 76
## 6 1 weight 93
## 7 1 weight 106
## 8 1 weight 125
## 9 1 weight 149
## 10 1 weight 171
## 11 1 weight 199
## 12 1 weight 205
## 13 1 weight 40
## 14 1 weight 49
## 15 1 weight 58
## 16 1 weight 72
## 17 1 weight 84
## 18 1 weight 103
## 19 1 weight 122
## 20 1 weight 138
## 21 1 weight 162
## 22 1 weight 187
## 23 1 weight 209
## 24 1 weight 215
## 25 1 weight 43
## 26 1 weight 39
## 27 1 weight 55
## 28 1 weight 67
## 29 1 weight 84
## 30 1 weight 99
## 31 1 weight 115
## 32 1 weight 138
## 33 1 weight 163
## 34 1 weight 187
## 35 1 weight 198
## 36 1 weight 202
## 37 1 weight 42
## 38 1 weight 49
## 39 1 weight 56
## 40 1 weight 67
## 41 1 weight 74
## 42 1 weight 87
## 43 1 weight 102
## 44 1 weight 108
## 45 1 weight 136
## 46 1 weight 154
## 47 1 weight 160
## 48 1 weight 157
## 49 1 weight 41
## 50 1 weight 42
## 51 1 weight 48
## 52 1 weight 60
## 53 1 weight 79
## 54 1 weight 106
## 55 1 weight 141
## 56 1 weight 164
## 57 1 weight 197
## 58 1 weight 199
## 59 1 weight 220
## 60 1 weight 223
## 61 1 weight 41
## 62 1 weight 49
## 63 1 weight 59
## 64 1 weight 74
## 65 1 weight 97
## 66 1 weight 124
## 67 1 weight 141
## 68 1 weight 148
## 69 1 weight 155
## 70 1 weight 160
## 71 1 weight 160
## 72 1 weight 157
## 73 1 weight 41
## 74 1 weight 49
## 75 1 weight 57
## 76 1 weight 71
## 77 1 weight 89
## 78 1 weight 112
## 79 1 weight 146
## 80 1 weight 174
## 81 1 weight 218
## 82 1 weight 250
## 83 1 weight 288
## 84 1 weight 305
## 85 1 weight 42
## 86 1 weight 50
## 87 1 weight 61
## 88 1 weight 71
## 89 1 weight 84
## 90 1 weight 93
## 91 1 weight 110
## 92 1 weight 116
## 93 1 weight 126
## 94 1 weight 134
## 95 1 weight 125
## 96 1 weight 42
## 97 1 weight 51
## 98 1 weight 59
## 99 1 weight 68
## 100 1 weight 85
## 101 1 weight 96
## 102 1 weight 90
## 103 1 weight 92
## 104 1 weight 93
## 105 1 weight 100
## 106 1 weight 100
## 107 1 weight 98
## 108 1 weight 41
## 109 1 weight 44
## 110 1 weight 52
## 111 1 weight 63
## 112 1 weight 74
## 113 1 weight 81
## 114 1 weight 89
## 115 1 weight 96
## 116 1 weight 101
## 117 1 weight 112
## 118 1 weight 120
## 119 1 weight 124
## 120 1 weight 43
## 121 1 weight 51
## 122 1 weight 63
## 123 1 weight 84
## 124 1 weight 112
## 125 1 weight 139
## 126 1 weight 168
## 127 1 weight 177
## 128 1 weight 182
## 129 1 weight 184
## 130 1 weight 181
## 131 1 weight 175
## 132 1 weight 41
## 133 1 weight 49
## 134 1 weight 56
## 135 1 weight 62
## 136 1 weight 72
## 137 1 weight 88
## 138 1 weight 119
## 139 1 weight 135
## 140 1 weight 162
## 141 1 weight 185
## 142 1 weight 195
## 143 1 weight 205
## 144 1 weight 41
## 145 1 weight 48
## 146 1 weight 53
## 147 1 weight 60
## 148 1 weight 65
## 149 1 weight 67
## 150 1 weight 71
## 151 1 weight 70
## 152 1 weight 71
## 153 1 weight 81
## 154 1 weight 91
## 155 1 weight 96
## 156 1 weight 41
## 157 1 weight 49
## 158 1 weight 62
## 159 1 weight 79
## 160 1 weight 101
## 161 1 weight 128
## 162 1 weight 164
## 163 1 weight 192
## 164 1 weight 227
## 165 1 weight 248
## 166 1 weight 259
## 167 1 weight 266
## 168 1 weight 41
## 169 1 weight 49
## 170 1 weight 56
## 171 1 weight 64
## 172 1 weight 68
## 173 1 weight 68
## 174 1 weight 67
## 175 1 weight 68
## 176 1 weight 41
## 177 1 weight 45
## 178 1 weight 49
## 179 1 weight 51
## 180 1 weight 57
## 181 1 weight 51
## 182 1 weight 54
## 183 1 weight 42
## 184 1 weight 51
## 185 1 weight 61
## 186 1 weight 72
## 187 1 weight 83
## 188 1 weight 89
## 189 1 weight 98
## 190 1 weight 103
## 191 1 weight 113
## 192 1 weight 123
## 193 1 weight 133
## 194 1 weight 142
## 195 1 weight 39
## 196 1 weight 35
## 197 1 weight 43
## 198 1 weight 48
## 199 1 weight 55
## 200 1 weight 62
## 201 1 weight 65
## 202 1 weight 71
## 203 1 weight 82
## 204 1 weight 88
## 205 1 weight 106
## 206 1 weight 120
## 207 1 weight 144
## 208 1 weight 157
## 209 1 weight 41
## 210 1 weight 47
## 211 1 weight 54
## 212 1 weight 58
## 213 1 weight 65
## 214 1 weight 73
## 215 1 weight 77
## 216 1 weight 89
## 217 1 weight 98
## 218 1 weight 107
## 219 1 weight 115
## 220 1 weight 117
## 221 2 weight 40
## 222 2 weight 50
## 223 2 weight 62
## 224 2 weight 86
## 225 2 weight 125
## 226 2 weight 163
## 227 2 weight 217
## 228 2 weight 240
## 229 2 weight 275
## 230 2 weight 307
## 231 2 weight 318
## 232 2 weight 331
## 233 2 weight 41
## 234 2 weight 55
## 235 2 weight 64
## 236 2 weight 77
## 237 2 weight 90
## 238 2 weight 95
## 239 2 weight 108
## 240 2 weight 111
## 241 2 weight 131
## 242 2 weight 148
## 243 2 weight 164
## 244 2 weight 167
## 245 2 weight 43
## 246 2 weight 52
## 247 2 weight 61
## 248 2 weight 73
## 249 2 weight 90
## 250 2 weight 103
## 251 2 weight 127
## 252 2 weight 135
## 253 2 weight 145
## 254 2 weight 163
## 255 2 weight 170
## 256 2 weight 175
## 257 2 weight 42
## 258 2 weight 52
## 259 2 weight 58
## 260 2 weight 74
## 261 2 weight 66
## 262 2 weight 68
## 263 2 weight 70
## 264 2 weight 71
## 265 2 weight 72
## 266 2 weight 72
## 267 2 weight 76
## 268 2 weight 74
## 269 2 weight 40
## 270 2 weight 49
## 271 2 weight 62
## 272 2 weight 78
## 273 2 weight 102
## 274 2 weight 124
## 275 2 weight 146
## 276 2 weight 164
## 277 2 weight 197
## 278 2 weight 231
## 279 2 weight 259
## 280 2 weight 265
## 281 2 weight 42
## 282 2 weight 48
## 283 2 weight 57
## 284 2 weight 74
## 285 2 weight 93
## 286 2 weight 114
## 287 2 weight 136
## 288 2 weight 147
## 289 2 weight 169
## 290 2 weight 205
## 291 2 weight 236
## 292 2 weight 251
## 293 2 weight 39
## 294 2 weight 46
## 295 2 weight 58
## 296 2 weight 73
## 297 2 weight 87
## 298 2 weight 100
## 299 2 weight 115
## 300 2 weight 123
## 301 2 weight 144
## 302 2 weight 163
## 303 2 weight 185
## 304 2 weight 192
## 305 2 weight 39
## 306 2 weight 46
## 307 2 weight 58
## 308 2 weight 73
## 309 2 weight 92
## 310 2 weight 114
## 311 2 weight 145
## 312 2 weight 156
## 313 2 weight 184
## 314 2 weight 207
## 315 2 weight 212
## 316 2 weight 233
## 317 2 weight 39
## 318 2 weight 48
## 319 2 weight 59
## 320 2 weight 74
## 321 2 weight 87
## 322 2 weight 106
## 323 2 weight 134
## 324 2 weight 150
## 325 2 weight 187
## 326 2 weight 230
## 327 2 weight 279
## 328 2 weight 309
## 329 2 weight 42
## 330 2 weight 48
## 331 2 weight 59
## 332 2 weight 72
## 333 2 weight 85
## 334 2 weight 98
## 335 2 weight 115
## 336 2 weight 122
## 337 2 weight 143
## 338 2 weight 151
## 339 2 weight 157
## 340 2 weight 150
## 341 3 weight 42
## 342 3 weight 53
## 343 3 weight 62
## 344 3 weight 73
## 345 3 weight 85
## 346 3 weight 102
## 347 3 weight 123
## 348 3 weight 138
## 349 3 weight 170
## 350 3 weight 204
## 351 3 weight 235
## 352 3 weight 256
## 353 3 weight 41
## 354 3 weight 49
## 355 3 weight 65
## 356 3 weight 82
## 357 3 weight 107
## 358 3 weight 129
## 359 3 weight 159
## 360 3 weight 179
## 361 3 weight 221
## 362 3 weight 263
## 363 3 weight 291
## 364 3 weight 305
## 365 3 weight 39
## 366 3 weight 50
## 367 3 weight 63
## 368 3 weight 77
## 369 3 weight 96
## 370 3 weight 111
## 371 3 weight 137
## 372 3 weight 144
## 373 3 weight 151
## 374 3 weight 146
## 375 3 weight 156
## 376 3 weight 147
## 377 3 weight 41
## 378 3 weight 49
## 379 3 weight 63
## 380 3 weight 85
## 381 3 weight 107
## 382 3 weight 134
## 383 3 weight 164
## 384 3 weight 186
## 385 3 weight 235
## 386 3 weight 294
## 387 3 weight 327
## 388 3 weight 341
## 389 3 weight 41
## 390 3 weight 53
## 391 3 weight 64
## 392 3 weight 87
## 393 3 weight 123
## 394 3 weight 158
## 395 3 weight 201
## 396 3 weight 238
## 397 3 weight 287
## 398 3 weight 332
## 399 3 weight 361
## 400 3 weight 373
## 401 3 weight 39
## 402 3 weight 48
## 403 3 weight 61
## 404 3 weight 76
## 405 3 weight 98
## 406 3 weight 116
## 407 3 weight 145
## 408 3 weight 166
## 409 3 weight 198
## 410 3 weight 227
## 411 3 weight 225
## 412 3 weight 220
## 413 3 weight 41
## 414 3 weight 48
## 415 3 weight 56
## 416 3 weight 68
## 417 3 weight 80
## 418 3 weight 83
## 419 3 weight 103
## 420 3 weight 112
## 421 3 weight 135
## 422 3 weight 157
## 423 3 weight 169
## 424 3 weight 178
## 425 3 weight 41
## 426 3 weight 49
## 427 3 weight 61
## 428 3 weight 74
## 429 3 weight 98
## 430 3 weight 109
## 431 3 weight 128
## 432 3 weight 154
## 433 3 weight 192
## 434 3 weight 232
## 435 3 weight 280
## 436 3 weight 290
## 437 3 weight 42
## 438 3 weight 50
## 439 3 weight 61
## 440 3 weight 78
## 441 3 weight 89
## 442 3 weight 109
## 443 3 weight 130
## 444 3 weight 146
## 445 3 weight 170
## 446 3 weight 214
## 447 3 weight 250
## 448 3 weight 272
## 449 3 weight 41
## 450 3 weight 55
## 451 3 weight 66
## 452 3 weight 79
## 453 3 weight 101
## 454 3 weight 120
## 455 3 weight 154
## 456 3 weight 182
## 457 3 weight 215
## 458 3 weight 262
## 459 3 weight 295
## 460 3 weight 321
## 461 4 weight 42
## 462 4 weight 51
## 463 4 weight 66
## 464 4 weight 85
## 465 4 weight 103
## 466 4 weight 124
## 467 4 weight 155
## 468 4 weight 153
## 469 4 weight 175
## 470 4 weight 184
## 471 4 weight 199
## 472 4 weight 204
## 473 4 weight 42
## 474 4 weight 49
## 475 4 weight 63
## 476 4 weight 84
## 477 4 weight 103
## 478 4 weight 126
## 479 4 weight 160
## 480 4 weight 174
## 481 4 weight 204
## 482 4 weight 234
## 483 4 weight 269
## 484 4 weight 281
## 485 4 weight 42
## 486 4 weight 55
## 487 4 weight 69
## 488 4 weight 96
## 489 4 weight 131
## 490 4 weight 157
## 491 4 weight 184
## 492 4 weight 188
## 493 4 weight 197
## 494 4 weight 198
## 495 4 weight 199
## 496 4 weight 200
## 497 4 weight 42
## 498 4 weight 51
## 499 4 weight 65
## 500 4 weight 86
## 501 4 weight 103
## 502 4 weight 118
## 503 4 weight 127
## 504 4 weight 138
## 505 4 weight 145
## 506 4 weight 146
## 507 4 weight 41
## 508 4 weight 50
## 509 4 weight 61
## 510 4 weight 78
## 511 4 weight 98
## 512 4 weight 117
## 513 4 weight 135
## 514 4 weight 141
## 515 4 weight 147
## 516 4 weight 174
## 517 4 weight 197
## 518 4 weight 196
## 519 4 weight 40
## 520 4 weight 52
## 521 4 weight 62
## 522 4 weight 82
## 523 4 weight 101
## 524 4 weight 120
## 525 4 weight 144
## 526 4 weight 156
## 527 4 weight 173
## 528 4 weight 210
## 529 4 weight 231
## 530 4 weight 238
## 531 4 weight 41
## 532 4 weight 53
## 533 4 weight 66
## 534 4 weight 79
## 535 4 weight 100
## 536 4 weight 123
## 537 4 weight 148
## 538 4 weight 157
## 539 4 weight 168
## 540 4 weight 185
## 541 4 weight 210
## 542 4 weight 205
## 543 4 weight 39
## 544 4 weight 50
## 545 4 weight 62
## 546 4 weight 80
## 547 4 weight 104
## 548 4 weight 125
## 549 4 weight 154
## 550 4 weight 170
## 551 4 weight 222
## 552 4 weight 261
## 553 4 weight 303
## 554 4 weight 322
## 555 4 weight 40
## 556 4 weight 53
## 557 4 weight 64
## 558 4 weight 85
## 559 4 weight 108
## 560 4 weight 128
## 561 4 weight 152
## 562 4 weight 166
## 563 4 weight 184
## 564 4 weight 203
## 565 4 weight 233
## 566 4 weight 237
## 567 4 weight 41
## 568 4 weight 54
## 569 4 weight 67
## 570 4 weight 84
## 571 4 weight 105
## 572 4 weight 122
## 573 4 weight 155
## 574 4 weight 175
## 575 4 weight 205
## 576 4 weight 234
## 577 4 weight 264
## 578 4 weight 264
## 579 1 Time 0
## 580 1 Time 2
## 581 1 Time 4
## 582 1 Time 6
## 583 1 Time 8
## 584 1 Time 10
## 585 1 Time 12
## 586 1 Time 14
## 587 1 Time 16
## 588 1 Time 18
## 589 1 Time 20
## 590 1 Time 21
## 591 1 Time 0
## 592 1 Time 2
## 593 1 Time 4
## 594 1 Time 6
## 595 1 Time 8
## 596 1 Time 10
## 597 1 Time 12
## 598 1 Time 14
## 599 1 Time 16
## 600 1 Time 18
## 601 1 Time 20
## 602 1 Time 21
## 603 1 Time 0
## 604 1 Time 2
## 605 1 Time 4
## 606 1 Time 6
## 607 1 Time 8
## 608 1 Time 10
## 609 1 Time 12
## 610 1 Time 14
## 611 1 Time 16
## 612 1 Time 18
## 613 1 Time 20
## 614 1 Time 21
## 615 1 Time 0
## 616 1 Time 2
## 617 1 Time 4
## 618 1 Time 6
## 619 1 Time 8
## 620 1 Time 10
## 621 1 Time 12
## 622 1 Time 14
## 623 1 Time 16
## 624 1 Time 18
## 625 1 Time 20
## 626 1 Time 21
## 627 1 Time 0
## 628 1 Time 2
## 629 1 Time 4
## 630 1 Time 6
## 631 1 Time 8
## 632 1 Time 10
## 633 1 Time 12
## 634 1 Time 14
## 635 1 Time 16
## 636 1 Time 18
## 637 1 Time 20
## 638 1 Time 21
## 639 1 Time 0
## 640 1 Time 2
## 641 1 Time 4
## 642 1 Time 6
## 643 1 Time 8
## 644 1 Time 10
## 645 1 Time 12
## 646 1 Time 14
## 647 1 Time 16
## 648 1 Time 18
## 649 1 Time 20
## 650 1 Time 21
## 651 1 Time 0
## 652 1 Time 2
## 653 1 Time 4
## 654 1 Time 6
## 655 1 Time 8
## 656 1 Time 10
## 657 1 Time 12
## 658 1 Time 14
## 659 1 Time 16
## 660 1 Time 18
## 661 1 Time 20
## 662 1 Time 21
## 663 1 Time 0
## 664 1 Time 2
## 665 1 Time 4
## 666 1 Time 6
## 667 1 Time 8
## 668 1 Time 10
## 669 1 Time 12
## 670 1 Time 14
## 671 1 Time 16
## 672 1 Time 18
## 673 1 Time 20
## 674 1 Time 0
## 675 1 Time 2
## 676 1 Time 4
## 677 1 Time 6
## 678 1 Time 8
## 679 1 Time 10
## 680 1 Time 12
## 681 1 Time 14
## 682 1 Time 16
## 683 1 Time 18
## 684 1 Time 20
## 685 1 Time 21
## 686 1 Time 0
## 687 1 Time 2
## 688 1 Time 4
## 689 1 Time 6
## 690 1 Time 8
## 691 1 Time 10
## 692 1 Time 12
## 693 1 Time 14
## 694 1 Time 16
## 695 1 Time 18
## 696 1 Time 20
## 697 1 Time 21
## 698 1 Time 0
## 699 1 Time 2
## 700 1 Time 4
## 701 1 Time 6
## 702 1 Time 8
## 703 1 Time 10
## 704 1 Time 12
## 705 1 Time 14
## 706 1 Time 16
## 707 1 Time 18
## 708 1 Time 20
## 709 1 Time 21
## 710 1 Time 0
## 711 1 Time 2
## 712 1 Time 4
## 713 1 Time 6
## 714 1 Time 8
## 715 1 Time 10
## 716 1 Time 12
## 717 1 Time 14
## 718 1 Time 16
## 719 1 Time 18
## 720 1 Time 20
## 721 1 Time 21
## 722 1 Time 0
## 723 1 Time 2
## 724 1 Time 4
## 725 1 Time 6
## 726 1 Time 8
## 727 1 Time 10
## 728 1 Time 12
## 729 1 Time 14
## 730 1 Time 16
## 731 1 Time 18
## 732 1 Time 20
## 733 1 Time 21
## 734 1 Time 0
## 735 1 Time 2
## 736 1 Time 4
## 737 1 Time 6
## 738 1 Time 8
## 739 1 Time 10
## 740 1 Time 12
## 741 1 Time 14
## 742 1 Time 16
## 743 1 Time 18
## 744 1 Time 20
## 745 1 Time 21
## 746 1 Time 0
## 747 1 Time 2
## 748 1 Time 4
## 749 1 Time 6
## 750 1 Time 8
## 751 1 Time 10
## 752 1 Time 12
## 753 1 Time 14
## 754 1 Time 0
## 755 1 Time 2
## 756 1 Time 4
## 757 1 Time 6
## 758 1 Time 8
## 759 1 Time 10
## 760 1 Time 12
## 761 1 Time 0
## 762 1 Time 2
## 763 1 Time 4
## 764 1 Time 6
## 765 1 Time 8
## 766 1 Time 10
## 767 1 Time 12
## 768 1 Time 14
## 769 1 Time 16
## 770 1 Time 18
## 771 1 Time 20
## 772 1 Time 21
## 773 1 Time 0
## 774 1 Time 2
## 775 1 Time 0
## 776 1 Time 2
## 777 1 Time 4
## 778 1 Time 6
## 779 1 Time 8
## 780 1 Time 10
## 781 1 Time 12
## 782 1 Time 14
## 783 1 Time 16
## 784 1 Time 18
## 785 1 Time 20
## 786 1 Time 21
## 787 1 Time 0
## 788 1 Time 2
## 789 1 Time 4
## 790 1 Time 6
## 791 1 Time 8
## 792 1 Time 10
## 793 1 Time 12
## 794 1 Time 14
## 795 1 Time 16
## 796 1 Time 18
## 797 1 Time 20
## 798 1 Time 21
## 799 2 Time 0
## 800 2 Time 2
## 801 2 Time 4
## 802 2 Time 6
## 803 2 Time 8
## 804 2 Time 10
## 805 2 Time 12
## 806 2 Time 14
## 807 2 Time 16
## 808 2 Time 18
## 809 2 Time 20
## 810 2 Time 21
## 811 2 Time 0
## 812 2 Time 2
## 813 2 Time 4
## 814 2 Time 6
## 815 2 Time 8
## 816 2 Time 10
## 817 2 Time 12
## 818 2 Time 14
## 819 2 Time 16
## 820 2 Time 18
## 821 2 Time 20
## 822 2 Time 21
## 823 2 Time 0
## 824 2 Time 2
## 825 2 Time 4
## 826 2 Time 6
## 827 2 Time 8
## 828 2 Time 10
## 829 2 Time 12
## 830 2 Time 14
## 831 2 Time 16
## 832 2 Time 18
## 833 2 Time 20
## 834 2 Time 21
## 835 2 Time 0
## 836 2 Time 2
## 837 2 Time 4
## 838 2 Time 6
## 839 2 Time 8
## 840 2 Time 10
## 841 2 Time 12
## 842 2 Time 14
## 843 2 Time 16
## 844 2 Time 18
## 845 2 Time 20
## 846 2 Time 21
## 847 2 Time 0
## 848 2 Time 2
## 849 2 Time 4
## 850 2 Time 6
## 851 2 Time 8
## 852 2 Time 10
## 853 2 Time 12
## 854 2 Time 14
## 855 2 Time 16
## 856 2 Time 18
## 857 2 Time 20
## 858 2 Time 21
## 859 2 Time 0
## 860 2 Time 2
## 861 2 Time 4
## 862 2 Time 6
## 863 2 Time 8
## 864 2 Time 10
## 865 2 Time 12
## 866 2 Time 14
## 867 2 Time 16
## 868 2 Time 18
## 869 2 Time 20
## 870 2 Time 21
## 871 2 Time 0
## 872 2 Time 2
## 873 2 Time 4
## 874 2 Time 6
## 875 2 Time 8
## 876 2 Time 10
## 877 2 Time 12
## 878 2 Time 14
## 879 2 Time 16
## 880 2 Time 18
## 881 2 Time 20
## 882 2 Time 21
## 883 2 Time 0
## 884 2 Time 2
## 885 2 Time 4
## 886 2 Time 6
## 887 2 Time 8
## 888 2 Time 10
## 889 2 Time 12
## 890 2 Time 14
## 891 2 Time 16
## 892 2 Time 18
## 893 2 Time 20
## 894 2 Time 21
## 895 2 Time 0
## 896 2 Time 2
## 897 2 Time 4
## 898 2 Time 6
## 899 2 Time 8
## 900 2 Time 10
## 901 2 Time 12
## 902 2 Time 14
## 903 2 Time 16
## 904 2 Time 18
## 905 2 Time 20
## 906 2 Time 21
## 907 2 Time 0
## 908 2 Time 2
## 909 2 Time 4
## 910 2 Time 6
## 911 2 Time 8
## 912 2 Time 10
## 913 2 Time 12
## 914 2 Time 14
## 915 2 Time 16
## 916 2 Time 18
## 917 2 Time 20
## 918 2 Time 21
## 919 3 Time 0
## 920 3 Time 2
## 921 3 Time 4
## 922 3 Time 6
## 923 3 Time 8
## 924 3 Time 10
## 925 3 Time 12
## 926 3 Time 14
## 927 3 Time 16
## 928 3 Time 18
## 929 3 Time 20
## 930 3 Time 21
## 931 3 Time 0
## 932 3 Time 2
## 933 3 Time 4
## 934 3 Time 6
## 935 3 Time 8
## 936 3 Time 10
## 937 3 Time 12
## 938 3 Time 14
## 939 3 Time 16
## 940 3 Time 18
## 941 3 Time 20
## 942 3 Time 21
## 943 3 Time 0
## 944 3 Time 2
## 945 3 Time 4
## 946 3 Time 6
## 947 3 Time 8
## 948 3 Time 10
## 949 3 Time 12
## 950 3 Time 14
## 951 3 Time 16
## 952 3 Time 18
## 953 3 Time 20
## 954 3 Time 21
## 955 3 Time 0
## 956 3 Time 2
## 957 3 Time 4
## 958 3 Time 6
## 959 3 Time 8
## 960 3 Time 10
## 961 3 Time 12
## 962 3 Time 14
## 963 3 Time 16
## 964 3 Time 18
## 965 3 Time 20
## 966 3 Time 21
## 967 3 Time 0
## 968 3 Time 2
## 969 3 Time 4
## 970 3 Time 6
## 971 3 Time 8
## 972 3 Time 10
## 973 3 Time 12
## 974 3 Time 14
## 975 3 Time 16
## 976 3 Time 18
## 977 3 Time 20
## 978 3 Time 21
## 979 3 Time 0
## 980 3 Time 2
## 981 3 Time 4
## 982 3 Time 6
## 983 3 Time 8
## 984 3 Time 10
## 985 3 Time 12
## 986 3 Time 14
## 987 3 Time 16
## 988 3 Time 18
## 989 3 Time 20
## 990 3 Time 21
## 991 3 Time 0
## 992 3 Time 2
## 993 3 Time 4
## 994 3 Time 6
## 995 3 Time 8
## 996 3 Time 10
## 997 3 Time 12
## 998 3 Time 14
## 999 3 Time 16
## 1000 3 Time 18
## 1001 3 Time 20
## 1002 3 Time 21
## 1003 3 Time 0
## 1004 3 Time 2
## 1005 3 Time 4
## 1006 3 Time 6
## 1007 3 Time 8
## 1008 3 Time 10
## 1009 3 Time 12
## 1010 3 Time 14
## 1011 3 Time 16
## 1012 3 Time 18
## 1013 3 Time 20
## 1014 3 Time 21
## 1015 3 Time 0
## 1016 3 Time 2
## 1017 3 Time 4
## 1018 3 Time 6
## 1019 3 Time 8
## 1020 3 Time 10
## 1021 3 Time 12
## 1022 3 Time 14
## 1023 3 Time 16
## 1024 3 Time 18
## 1025 3 Time 20
## 1026 3 Time 21
## 1027 3 Time 0
## 1028 3 Time 2
## 1029 3 Time 4
## 1030 3 Time 6
## 1031 3 Time 8
## 1032 3 Time 10
## 1033 3 Time 12
## 1034 3 Time 14
## 1035 3 Time 16
## 1036 3 Time 18
## 1037 3 Time 20
## 1038 3 Time 21
## 1039 4 Time 0
## 1040 4 Time 2
## 1041 4 Time 4
## 1042 4 Time 6
## 1043 4 Time 8
## 1044 4 Time 10
## 1045 4 Time 12
## 1046 4 Time 14
## 1047 4 Time 16
## 1048 4 Time 18
## 1049 4 Time 20
## 1050 4 Time 21
## 1051 4 Time 0
## 1052 4 Time 2
## 1053 4 Time 4
## 1054 4 Time 6
## 1055 4 Time 8
## 1056 4 Time 10
## 1057 4 Time 12
## 1058 4 Time 14
## 1059 4 Time 16
## 1060 4 Time 18
## 1061 4 Time 20
## 1062 4 Time 21
## 1063 4 Time 0
## 1064 4 Time 2
## 1065 4 Time 4
## 1066 4 Time 6
## 1067 4 Time 8
## 1068 4 Time 10
## 1069 4 Time 12
## 1070 4 Time 14
## 1071 4 Time 16
## 1072 4 Time 18
## 1073 4 Time 20
## 1074 4 Time 21
## 1075 4 Time 0
## 1076 4 Time 2
## 1077 4 Time 4
## 1078 4 Time 6
## 1079 4 Time 8
## 1080 4 Time 10
## 1081 4 Time 12
## 1082 4 Time 14
## 1083 4 Time 16
## 1084 4 Time 18
## 1085 4 Time 0
## 1086 4 Time 2
## 1087 4 Time 4
## 1088 4 Time 6
## 1089 4 Time 8
## 1090 4 Time 10
## 1091 4 Time 12
## 1092 4 Time 14
## 1093 4 Time 16
## 1094 4 Time 18
## 1095 4 Time 20
## 1096 4 Time 21
## 1097 4 Time 0
## 1098 4 Time 2
## 1099 4 Time 4
## 1100 4 Time 6
## 1101 4 Time 8
## 1102 4 Time 10
## 1103 4 Time 12
## 1104 4 Time 14
## 1105 4 Time 16
## 1106 4 Time 18
## 1107 4 Time 20
## 1108 4 Time 21
## 1109 4 Time 0
## 1110 4 Time 2
## 1111 4 Time 4
## 1112 4 Time 6
## 1113 4 Time 8
## 1114 4 Time 10
## 1115 4 Time 12
## 1116 4 Time 14
## 1117 4 Time 16
## 1118 4 Time 18
## 1119 4 Time 20
## 1120 4 Time 21
## 1121 4 Time 0
## 1122 4 Time 2
## 1123 4 Time 4
## 1124 4 Time 6
## 1125 4 Time 8
## 1126 4 Time 10
## 1127 4 Time 12
## 1128 4 Time 14
## 1129 4 Time 16
## 1130 4 Time 18
## 1131 4 Time 20
## 1132 4 Time 21
## 1133 4 Time 0
## 1134 4 Time 2
## 1135 4 Time 4
## 1136 4 Time 6
## 1137 4 Time 8
## 1138 4 Time 10
## 1139 4 Time 12
## 1140 4 Time 14
## 1141 4 Time 16
## 1142 4 Time 18
## 1143 4 Time 20
## 1144 4 Time 21
## 1145 4 Time 0
## 1146 4 Time 2
## 1147 4 Time 4
## 1148 4 Time 6
## 1149 4 Time 8
## 1150 4 Time 10
## 1151 4 Time 12
## 1152 4 Time 14
## 1153 4 Time 16
## 1154 4 Time 18
## 1155 4 Time 20
## 1156 4 Time 21
## 1157 1 Chick 1
## 1158 1 Chick 1
## 1159 1 Chick 1
## 1160 1 Chick 1
## 1161 1 Chick 1
## 1162 1 Chick 1
## 1163 1 Chick 1
## 1164 1 Chick 1
## 1165 1 Chick 1
## 1166 1 Chick 1
## 1167 1 Chick 1
## 1168 1 Chick 1
## 1169 1 Chick 2
## 1170 1 Chick 2
## 1171 1 Chick 2
## 1172 1 Chick 2
## 1173 1 Chick 2
## 1174 1 Chick 2
## 1175 1 Chick 2
## 1176 1 Chick 2
## 1177 1 Chick 2
## 1178 1 Chick 2
## 1179 1 Chick 2
## 1180 1 Chick 2
## 1181 1 Chick 3
## 1182 1 Chick 3
## 1183 1 Chick 3
## 1184 1 Chick 3
## 1185 1 Chick 3
## 1186 1 Chick 3
## 1187 1 Chick 3
## 1188 1 Chick 3
## 1189 1 Chick 3
## 1190 1 Chick 3
## 1191 1 Chick 3
## 1192 1 Chick 3
## 1193 1 Chick 4
## 1194 1 Chick 4
## 1195 1 Chick 4
## 1196 1 Chick 4
## 1197 1 Chick 4
## 1198 1 Chick 4
## 1199 1 Chick 4
## 1200 1 Chick 4
## 1201 1 Chick 4
## 1202 1 Chick 4
## 1203 1 Chick 4
## 1204 1 Chick 4
## 1205 1 Chick 5
## 1206 1 Chick 5
## 1207 1 Chick 5
## 1208 1 Chick 5
## 1209 1 Chick 5
## 1210 1 Chick 5
## 1211 1 Chick 5
## 1212 1 Chick 5
## 1213 1 Chick 5
## 1214 1 Chick 5
## 1215 1 Chick 5
## 1216 1 Chick 5
## 1217 1 Chick 6
## 1218 1 Chick 6
## 1219 1 Chick 6
## 1220 1 Chick 6
## 1221 1 Chick 6
## 1222 1 Chick 6
## 1223 1 Chick 6
## 1224 1 Chick 6
## 1225 1 Chick 6
## 1226 1 Chick 6
## 1227 1 Chick 6
## 1228 1 Chick 6
## 1229 1 Chick 7
## 1230 1 Chick 7
## 1231 1 Chick 7
## 1232 1 Chick 7
## 1233 1 Chick 7
## 1234 1 Chick 7
## 1235 1 Chick 7
## 1236 1 Chick 7
## 1237 1 Chick 7
## 1238 1 Chick 7
## 1239 1 Chick 7
## 1240 1 Chick 7
## 1241 1 Chick 8
## 1242 1 Chick 8
## 1243 1 Chick 8
## 1244 1 Chick 8
## 1245 1 Chick 8
## 1246 1 Chick 8
## 1247 1 Chick 8
## 1248 1 Chick 8
## 1249 1 Chick 8
## 1250 1 Chick 8
## 1251 1 Chick 8
## 1252 1 Chick 9
## 1253 1 Chick 9
## 1254 1 Chick 9
## 1255 1 Chick 9
## 1256 1 Chick 9
## 1257 1 Chick 9
## 1258 1 Chick 9
## 1259 1 Chick 9
## 1260 1 Chick 9
## 1261 1 Chick 9
## 1262 1 Chick 9
## 1263 1 Chick 9
## 1264 1 Chick 10
## 1265 1 Chick 10
## 1266 1 Chick 10
## 1267 1 Chick 10
## 1268 1 Chick 10
## 1269 1 Chick 10
## 1270 1 Chick 10
## 1271 1 Chick 10
## 1272 1 Chick 10
## 1273 1 Chick 10
## 1274 1 Chick 10
## 1275 1 Chick 10
## 1276 1 Chick 11
## 1277 1 Chick 11
## 1278 1 Chick 11
## 1279 1 Chick 11
## 1280 1 Chick 11
## 1281 1 Chick 11
## 1282 1 Chick 11
## 1283 1 Chick 11
## 1284 1 Chick 11
## 1285 1 Chick 11
## 1286 1 Chick 11
## 1287 1 Chick 11
## 1288 1 Chick 12
## 1289 1 Chick 12
## 1290 1 Chick 12
## 1291 1 Chick 12
## 1292 1 Chick 12
## 1293 1 Chick 12
## 1294 1 Chick 12
## 1295 1 Chick 12
## 1296 1 Chick 12
## 1297 1 Chick 12
## 1298 1 Chick 12
## 1299 1 Chick 12
## 1300 1 Chick 13
## 1301 1 Chick 13
## 1302 1 Chick 13
## 1303 1 Chick 13
## 1304 1 Chick 13
## 1305 1 Chick 13
## 1306 1 Chick 13
## 1307 1 Chick 13
## 1308 1 Chick 13
## 1309 1 Chick 13
## 1310 1 Chick 13
## 1311 1 Chick 13
## 1312 1 Chick 14
## 1313 1 Chick 14
## 1314 1 Chick 14
## 1315 1 Chick 14
## 1316 1 Chick 14
## 1317 1 Chick 14
## 1318 1 Chick 14
## 1319 1 Chick 14
## 1320 1 Chick 14
## 1321 1 Chick 14
## 1322 1 Chick 14
## 1323 1 Chick 14
## 1324 1 Chick 15
## 1325 1 Chick 15
## 1326 1 Chick 15
## 1327 1 Chick 15
## 1328 1 Chick 15
## 1329 1 Chick 15
## 1330 1 Chick 15
## 1331 1 Chick 15
## 1332 1 Chick 16
## 1333 1 Chick 16
## 1334 1 Chick 16
## 1335 1 Chick 16
## 1336 1 Chick 16
## 1337 1 Chick 16
## 1338 1 Chick 16
## 1339 1 Chick 17
## 1340 1 Chick 17
## 1341 1 Chick 17
## 1342 1 Chick 17
## 1343 1 Chick 17
## 1344 1 Chick 17
## 1345 1 Chick 17
## 1346 1 Chick 17
## 1347 1 Chick 17
## 1348 1 Chick 17
## 1349 1 Chick 17
## 1350 1 Chick 17
## 1351 1 Chick 18
## 1352 1 Chick 18
## 1353 1 Chick 19
## 1354 1 Chick 19
## 1355 1 Chick 19
## 1356 1 Chick 19
## 1357 1 Chick 19
## 1358 1 Chick 19
## 1359 1 Chick 19
## 1360 1 Chick 19
## 1361 1 Chick 19
## 1362 1 Chick 19
## 1363 1 Chick 19
## 1364 1 Chick 19
## 1365 1 Chick 20
## 1366 1 Chick 20
## 1367 1 Chick 20
## 1368 1 Chick 20
## 1369 1 Chick 20
## 1370 1 Chick 20
## 1371 1 Chick 20
## 1372 1 Chick 20
## 1373 1 Chick 20
## 1374 1 Chick 20
## 1375 1 Chick 20
## 1376 1 Chick 20
## 1377 2 Chick 21
## 1378 2 Chick 21
## 1379 2 Chick 21
## 1380 2 Chick 21
## 1381 2 Chick 21
## 1382 2 Chick 21
## 1383 2 Chick 21
## 1384 2 Chick 21
## 1385 2 Chick 21
## 1386 2 Chick 21
## 1387 2 Chick 21
## 1388 2 Chick 21
## 1389 2 Chick 22
## 1390 2 Chick 22
## 1391 2 Chick 22
## 1392 2 Chick 22
## 1393 2 Chick 22
## 1394 2 Chick 22
## 1395 2 Chick 22
## 1396 2 Chick 22
## 1397 2 Chick 22
## 1398 2 Chick 22
## 1399 2 Chick 22
## 1400 2 Chick 22
## 1401 2 Chick 23
## 1402 2 Chick 23
## 1403 2 Chick 23
## 1404 2 Chick 23
## 1405 2 Chick 23
## 1406 2 Chick 23
## 1407 2 Chick 23
## 1408 2 Chick 23
## 1409 2 Chick 23
## 1410 2 Chick 23
## 1411 2 Chick 23
## 1412 2 Chick 23
## 1413 2 Chick 24
## 1414 2 Chick 24
## 1415 2 Chick 24
## 1416 2 Chick 24
## 1417 2 Chick 24
## 1418 2 Chick 24
## 1419 2 Chick 24
## 1420 2 Chick 24
## 1421 2 Chick 24
## 1422 2 Chick 24
## 1423 2 Chick 24
## 1424 2 Chick 24
## 1425 2 Chick 25
## 1426 2 Chick 25
## 1427 2 Chick 25
## 1428 2 Chick 25
## 1429 2 Chick 25
## 1430 2 Chick 25
## 1431 2 Chick 25
## 1432 2 Chick 25
## 1433 2 Chick 25
## 1434 2 Chick 25
## 1435 2 Chick 25
## 1436 2 Chick 25
## 1437 2 Chick 26
## 1438 2 Chick 26
## 1439 2 Chick 26
## 1440 2 Chick 26
## 1441 2 Chick 26
## 1442 2 Chick 26
## 1443 2 Chick 26
## 1444 2 Chick 26
## 1445 2 Chick 26
## 1446 2 Chick 26
## 1447 2 Chick 26
## 1448 2 Chick 26
## 1449 2 Chick 27
## 1450 2 Chick 27
## 1451 2 Chick 27
## 1452 2 Chick 27
## 1453 2 Chick 27
## 1454 2 Chick 27
## 1455 2 Chick 27
## 1456 2 Chick 27
## 1457 2 Chick 27
## 1458 2 Chick 27
## 1459 2 Chick 27
## 1460 2 Chick 27
## 1461 2 Chick 28
## 1462 2 Chick 28
## 1463 2 Chick 28
## 1464 2 Chick 28
## 1465 2 Chick 28
## 1466 2 Chick 28
## 1467 2 Chick 28
## 1468 2 Chick 28
## 1469 2 Chick 28
## 1470 2 Chick 28
## 1471 2 Chick 28
## 1472 2 Chick 28
## 1473 2 Chick 29
## 1474 2 Chick 29
## 1475 2 Chick 29
## 1476 2 Chick 29
## 1477 2 Chick 29
## 1478 2 Chick 29
## 1479 2 Chick 29
## 1480 2 Chick 29
## 1481 2 Chick 29
## 1482 2 Chick 29
## 1483 2 Chick 29
## 1484 2 Chick 29
## 1485 2 Chick 30
## 1486 2 Chick 30
## 1487 2 Chick 30
## 1488 2 Chick 30
## 1489 2 Chick 30
## 1490 2 Chick 30
## 1491 2 Chick 30
## 1492 2 Chick 30
## 1493 2 Chick 30
## 1494 2 Chick 30
## 1495 2 Chick 30
## 1496 2 Chick 30
## 1497 3 Chick 31
## 1498 3 Chick 31
## 1499 3 Chick 31
## 1500 3 Chick 31
## 1501 3 Chick 31
## 1502 3 Chick 31
## 1503 3 Chick 31
## 1504 3 Chick 31
## 1505 3 Chick 31
## 1506 3 Chick 31
## 1507 3 Chick 31
## 1508 3 Chick 31
## 1509 3 Chick 32
## 1510 3 Chick 32
## 1511 3 Chick 32
## 1512 3 Chick 32
## 1513 3 Chick 32
## 1514 3 Chick 32
## 1515 3 Chick 32
## 1516 3 Chick 32
## 1517 3 Chick 32
## 1518 3 Chick 32
## 1519 3 Chick 32
## 1520 3 Chick 32
## 1521 3 Chick 33
## 1522 3 Chick 33
## 1523 3 Chick 33
## 1524 3 Chick 33
## 1525 3 Chick 33
## 1526 3 Chick 33
## 1527 3 Chick 33
## 1528 3 Chick 33
## 1529 3 Chick 33
## 1530 3 Chick 33
## 1531 3 Chick 33
## 1532 3 Chick 33
## 1533 3 Chick 34
## 1534 3 Chick 34
## 1535 3 Chick 34
## 1536 3 Chick 34
## 1537 3 Chick 34
## 1538 3 Chick 34
## 1539 3 Chick 34
## 1540 3 Chick 34
## 1541 3 Chick 34
## 1542 3 Chick 34
## 1543 3 Chick 34
## 1544 3 Chick 34
## 1545 3 Chick 35
## 1546 3 Chick 35
## 1547 3 Chick 35
## 1548 3 Chick 35
## 1549 3 Chick 35
## 1550 3 Chick 35
## 1551 3 Chick 35
## 1552 3 Chick 35
## 1553 3 Chick 35
## 1554 3 Chick 35
## 1555 3 Chick 35
## 1556 3 Chick 35
## 1557 3 Chick 36
## 1558 3 Chick 36
## 1559 3 Chick 36
## 1560 3 Chick 36
## 1561 3 Chick 36
## 1562 3 Chick 36
## 1563 3 Chick 36
## 1564 3 Chick 36
## 1565 3 Chick 36
## 1566 3 Chick 36
## 1567 3 Chick 36
## 1568 3 Chick 36
## 1569 3 Chick 37
## 1570 3 Chick 37
## 1571 3 Chick 37
## 1572 3 Chick 37
## 1573 3 Chick 37
## 1574 3 Chick 37
## 1575 3 Chick 37
## 1576 3 Chick 37
## 1577 3 Chick 37
## 1578 3 Chick 37
## 1579 3 Chick 37
## 1580 3 Chick 37
## 1581 3 Chick 38
## 1582 3 Chick 38
## 1583 3 Chick 38
## 1584 3 Chick 38
## 1585 3 Chick 38
## 1586 3 Chick 38
## 1587 3 Chick 38
## 1588 3 Chick 38
## 1589 3 Chick 38
## 1590 3 Chick 38
## 1591 3 Chick 38
## 1592 3 Chick 38
## 1593 3 Chick 39
## 1594 3 Chick 39
## 1595 3 Chick 39
## 1596 3 Chick 39
## 1597 3 Chick 39
## 1598 3 Chick 39
## 1599 3 Chick 39
## 1600 3 Chick 39
## 1601 3 Chick 39
## 1602 3 Chick 39
## 1603 3 Chick 39
## 1604 3 Chick 39
## 1605 3 Chick 40
## 1606 3 Chick 40
## 1607 3 Chick 40
## 1608 3 Chick 40
## 1609 3 Chick 40
## 1610 3 Chick 40
## 1611 3 Chick 40
## 1612 3 Chick 40
## 1613 3 Chick 40
## 1614 3 Chick 40
## 1615 3 Chick 40
## 1616 3 Chick 40
## 1617 4 Chick 41
## 1618 4 Chick 41
## 1619 4 Chick 41
## 1620 4 Chick 41
## 1621 4 Chick 41
## 1622 4 Chick 41
## 1623 4 Chick 41
## 1624 4 Chick 41
## 1625 4 Chick 41
## 1626 4 Chick 41
## 1627 4 Chick 41
## 1628 4 Chick 41
## 1629 4 Chick 42
## 1630 4 Chick 42
## 1631 4 Chick 42
## 1632 4 Chick 42
## 1633 4 Chick 42
## 1634 4 Chick 42
## 1635 4 Chick 42
## 1636 4 Chick 42
## 1637 4 Chick 42
## 1638 4 Chick 42
## 1639 4 Chick 42
## 1640 4 Chick 42
## 1641 4 Chick 43
## 1642 4 Chick 43
## 1643 4 Chick 43
## 1644 4 Chick 43
## 1645 4 Chick 43
## 1646 4 Chick 43
## 1647 4 Chick 43
## 1648 4 Chick 43
## 1649 4 Chick 43
## 1650 4 Chick 43
## 1651 4 Chick 43
## 1652 4 Chick 43
## 1653 4 Chick 44
## 1654 4 Chick 44
## 1655 4 Chick 44
## 1656 4 Chick 44
## 1657 4 Chick 44
## 1658 4 Chick 44
## 1659 4 Chick 44
## 1660 4 Chick 44
## 1661 4 Chick 44
## 1662 4 Chick 44
## 1663 4 Chick 45
## 1664 4 Chick 45
## 1665 4 Chick 45
## 1666 4 Chick 45
## 1667 4 Chick 45
## 1668 4 Chick 45
## 1669 4 Chick 45
## 1670 4 Chick 45
## 1671 4 Chick 45
## 1672 4 Chick 45
## 1673 4 Chick 45
## 1674 4 Chick 45
## 1675 4 Chick 46
## 1676 4 Chick 46
## 1677 4 Chick 46
## 1678 4 Chick 46
## 1679 4 Chick 46
## 1680 4 Chick 46
## 1681 4 Chick 46
## 1682 4 Chick 46
## 1683 4 Chick 46
## 1684 4 Chick 46
## 1685 4 Chick 46
## 1686 4 Chick 46
## 1687 4 Chick 47
## 1688 4 Chick 47
## 1689 4 Chick 47
## 1690 4 Chick 47
## 1691 4 Chick 47
## 1692 4 Chick 47
## 1693 4 Chick 47
## 1694 4 Chick 47
## 1695 4 Chick 47
## 1696 4 Chick 47
## 1697 4 Chick 47
## 1698 4 Chick 47
## 1699 4 Chick 48
## 1700 4 Chick 48
## 1701 4 Chick 48
## 1702 4 Chick 48
## 1703 4 Chick 48
## 1704 4 Chick 48
## 1705 4 Chick 48
## 1706 4 Chick 48
## 1707 4 Chick 48
## 1708 4 Chick 48
## 1709 4 Chick 48
## 1710 4 Chick 48
## 1711 4 Chick 49
## 1712 4 Chick 49
## 1713 4 Chick 49
## 1714 4 Chick 49
## 1715 4 Chick 49
## 1716 4 Chick 49
## 1717 4 Chick 49
## 1718 4 Chick 49
## 1719 4 Chick 49
## 1720 4 Chick 49
## 1721 4 Chick 49
## 1722 4 Chick 49
## 1723 4 Chick 50
## 1724 4 Chick 50
## 1725 4 Chick 50
## 1726 4 Chick 50
## 1727 4 Chick 50
## 1728 4 Chick 50
## 1729 4 Chick 50
## 1730 4 Chick 50
## 1731 4 Chick 50
## 1732 4 Chick 50
## 1733 4 Chick 50
## 1734 4 Chick 50#cast(data = x,Diet~variable,mean)
cast(x, Diet~variable, mean)## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
## returning NA## Diet weight Time Chick
## 1 1 NA NA NA
## 2 2 NA NA NA
## 3 3 NA NA NA
## 4 4 NA NA NAalternative 1 (eassiest)
# Load the ChickWeight dataset
data(ChickWeight)
# Load the reshape2 package
library(reshape2)## Warning: package 'reshape2' was built under R version 4.2.2##
## Attaching package: 'reshape2'## The following object is masked from 'package:tidyr':
##
## smiths## The following objects are masked from 'package:reshape':
##
## colsplit, melt, recast# Cast the data to calculate the mean weight for each diet type
avg_weight <- cast(ChickWeight, Diet ~ ., mean, value = "weight")
# Print the average weight for each diet type
print(avg_weight)## Diet (all)
## 1 1 103
## 2 2 123
## 3 3 143
## 4 4 135alternative 2
# Load the ChickWeight dataset
data(ChickWeight)
# Group the data by diet type and calculate the mean weight for each group
avg_weight <- aggregate(weight ~ Diet, data = ChickWeight, mean)
# Print the average weight for each diet type
print(avg_weight)## Diet weight
## 1 1 103
## 2 2 123
## 3 3 143
## 4 4 1353b
cast(data = ChickWeight,Time~.,value = "weight")## Aggregation requires fun.aggregate: length used as default## Time (all)
## 1 0 50
## 2 2 50
## 3 4 49
## 4 6 49
## 5 8 49
## 6 10 49
## 7 12 49
## 8 14 48
## 9 16 47
## 10 18 47
## 11 20 46
## 12 21 453c
boxplot(weight~ Diet,ChickWeight)
Q4
cdf<-function(x){
m<-function(x){exp(-x)}
return(integrate(f = m,lower = 0,upper = x))
#return(exp(-x))
}
cdf(6)## 1 with absolute error < 1.1e-14Final Exam
2019
1
1(a) Minimum
rm(list=ls())
dataState = as.data.frame(state.x77)
index = apply(dataState, 2, which.min)
index## Population Income Illiteracy Life Exp Murder HS Grad Frost
## 2 24 15 40 34 40 11
## Area
## 39minimum = row.names(dataState)[index]
minimum## [1] "Alaska" "Mississippi" "Iowa" "South Carolina"
## [5] "North Dakota" "South Carolina" "Hawaii" "Rhode Island"1(b) Maximum
x<-apply(X = state.x77,MARGIN = 2,FUN = which.max)
x## Population Income Illiteracy Life Exp Murder HS Grad Frost
## 5 2 18 11 1 44 28
## Area
## 2row.names(state.x77)[x]## [1] "California" "Alaska" "Louisiana" "Hawaii" "Alabama"
## [6] "Utah" "Nevada" "Alaska"1c(easy)
x<-state.x77[sample(x = nrow(state.x77),size = 10,replace = F),]
x## Population Income Illiteracy Life Exp Murder HS Grad Frost
## Texas 12237 4188 2.2 71 12.2 47 35
## California 21198 5114 1.1 72 10.3 63 20
## Virginia 4981 4701 1.4 70 9.5 48 85
## New Hampshire 812 4281 0.7 71 3.3 58 174
## Mississippi 2341 3098 2.4 68 12.5 41 50
## Kentucky 3387 3712 1.6 70 10.6 38 95
## North Carolina 5441 3875 1.8 69 11.1 38 80
## New York 18076 4903 1.4 71 10.9 53 82
## Ohio 10735 4561 0.8 71 7.4 53 124
## Oklahoma 2715 3983 1.1 71 6.4 52 82
## Area
## Texas 262134
## California 156361
## Virginia 39780
## New Hampshire 9027
## Mississippi 47296
## Kentucky 39650
## North Carolina 48798
## New York 47831
## Ohio 40975
## Oklahoma 68782summary(x)## Population Income Illiteracy Life Exp Murder
## Min. : 812 Min. :3098 Min. :0.70 Min. :68 Min. : 3.3
## 1st Qu.: 2883 1st Qu.:3902 1st Qu.:1.10 1st Qu.:70 1st Qu.: 7.9
## Median : 5211 Median :4234 Median :1.40 Median :71 Median :10.4
## Mean : 8192 Mean :4242 Mean :1.45 Mean :70 Mean : 9.4
## 3rd Qu.:11862 3rd Qu.:4666 3rd Qu.:1.75 3rd Qu.:71 3rd Qu.:11.1
## Max. :21198 Max. :5114 Max. :2.40 Max. :72 Max. :12.5
## HS Grad Frost Area
## Min. :38 Min. : 20 Min. : 9027
## 1st Qu.:43 1st Qu.: 58 1st Qu.: 40079
## Median :50 Median : 82 Median : 47564
## Mean :49 Mean : 83 Mean : 76063
## 3rd Qu.:53 3rd Qu.: 92 3rd Qu.: 63786
## Max. :63 Max. :174 Max. :262134alternative
rand_num = ceiling(runif(10, 1, length(dataState$Population)))
sampState = dataState[rand_num,]
summary(sampState)## Population Income Illiteracy Life Exp Murder
## Min. : 365 Min. :3983 Min. :0.50 Min. :69 Min. : 3.1
## 1st Qu.: 1162 1st Qu.:4476 1st Qu.:0.80 1st Qu.:70 1st Qu.: 6.6
## Median : 2908 Median :4802 Median :1.10 Median :71 Median : 8.7
## Mean : 5936 Mean :4878 Mean :1.13 Mean :71 Mean : 8.1
## 3rd Qu.: 5230 3rd Qu.:5140 3rd Qu.:1.40 3rd Qu.:71 3rd Qu.:10.8
## Max. :21198 Max. :6315 Max. :1.80 Max. :72 Max. :11.5
## HS Grad Frost Area
## Min. :48 Min. : 15 Min. : 4862
## 1st Qu.:53 1st Qu.: 82 1st Qu.: 37018
## Median :57 Median :104 Median : 58306
## Mean :57 Mean :106 Mean :115248
## 3rd Qu.:61 3rd Qu.:149 3rd Qu.:112535
## Max. :67 Max. :188 Max. :566432dataState ## Population Income Illiteracy Life Exp Murder HS Grad Frost
## Alabama 3615 3624 2.1 69 15.1 41 20
## Alaska 365 6315 1.5 69 11.3 67 152
## Arizona 2212 4530 1.8 71 7.8 58 15
## Arkansas 2110 3378 1.9 71 10.1 40 65
## California 21198 5114 1.1 72 10.3 63 20
## Colorado 2541 4884 0.7 72 6.8 64 166
## Connecticut 3100 5348 1.1 72 3.1 56 139
## Delaware 579 4809 0.9 70 6.2 55 103
## Florida 8277 4815 1.3 71 10.7 53 11
## Georgia 4931 4091 2.0 69 13.9 41 60
## Hawaii 868 4963 1.9 74 6.2 62 0
## Idaho 813 4119 0.6 72 5.3 60 126
## Illinois 11197 5107 0.9 70 10.3 53 127
## Indiana 5313 4458 0.7 71 7.1 53 122
## Iowa 2861 4628 0.5 73 2.3 59 140
## Kansas 2280 4669 0.6 73 4.5 60 114
## Kentucky 3387 3712 1.6 70 10.6 38 95
## Louisiana 3806 3545 2.8 69 13.2 42 12
## Maine 1058 3694 0.7 70 2.7 55 161
## Maryland 4122 5299 0.9 70 8.5 52 101
## Massachusetts 5814 4755 1.1 72 3.3 58 103
## Michigan 9111 4751 0.9 71 11.1 53 125
## Minnesota 3921 4675 0.6 73 2.3 58 160
## Mississippi 2341 3098 2.4 68 12.5 41 50
## Missouri 4767 4254 0.8 71 9.3 49 108
## Montana 746 4347 0.6 71 5.0 59 155
## Nebraska 1544 4508 0.6 73 2.9 59 139
## Nevada 590 5149 0.5 69 11.5 65 188
## New Hampshire 812 4281 0.7 71 3.3 58 174
## New Jersey 7333 5237 1.1 71 5.2 52 115
## New Mexico 1144 3601 2.2 70 9.7 55 120
## New York 18076 4903 1.4 71 10.9 53 82
## North Carolina 5441 3875 1.8 69 11.1 38 80
## North Dakota 637 5087 0.8 73 1.4 50 186
## Ohio 10735 4561 0.8 71 7.4 53 124
## Oklahoma 2715 3983 1.1 71 6.4 52 82
## Oregon 2284 4660 0.6 72 4.2 60 44
## Pennsylvania 11860 4449 1.0 70 6.1 50 126
## Rhode Island 931 4558 1.3 72 2.4 46 127
## South Carolina 2816 3635 2.3 68 11.6 38 65
## South Dakota 681 4167 0.5 72 1.7 53 172
## Tennessee 4173 3821 1.7 70 11.0 42 70
## Texas 12237 4188 2.2 71 12.2 47 35
## Utah 1203 4022 0.6 73 4.5 67 137
## Vermont 472 3907 0.6 72 5.5 57 168
## Virginia 4981 4701 1.4 70 9.5 48 85
## Washington 3559 4864 0.6 72 4.3 64 32
## West Virginia 1799 3617 1.4 69 6.7 42 100
## Wisconsin 4589 4468 0.7 72 3.0 54 149
## Wyoming 376 4566 0.6 70 6.9 63 173
## Area
## Alabama 50708
## Alaska 566432
## Arizona 113417
## Arkansas 51945
## California 156361
## Colorado 103766
## Connecticut 4862
## Delaware 1982
## Florida 54090
## Georgia 58073
## Hawaii 6425
## Idaho 82677
## Illinois 55748
## Indiana 36097
## Iowa 55941
## Kansas 81787
## Kentucky 39650
## Louisiana 44930
## Maine 30920
## Maryland 9891
## Massachusetts 7826
## Michigan 56817
## Minnesota 79289
## Mississippi 47296
## Missouri 68995
## Montana 145587
## Nebraska 76483
## Nevada 109889
## New Hampshire 9027
## New Jersey 7521
## New Mexico 121412
## New York 47831
## North Carolina 48798
## North Dakota 69273
## Ohio 40975
## Oklahoma 68782
## Oregon 96184
## Pennsylvania 44966
## Rhode Island 1049
## South Carolina 30225
## South Dakota 75955
## Tennessee 41328
## Texas 262134
## Utah 82096
## Vermont 9267
## Virginia 39780
## Washington 66570
## West Virginia 24070
## Wisconsin 54464
## Wyoming 97203cor(dataState$Murder,dataState$Illiteracy )## [1] 0.71d
quantile(x = dataState$Area,.33)## 33%
## 41940quantile(x = dataState$Area,.66)## 66%
## 69090dataState$category[dataState$Area<41940.34 ]<-"small"
dataState$category[dataState$Area>= 41940.34 & dataState$Area<69089.52 ]<-"mediam"
dataState$category[dataState$Area>=69089.52 ]<-"big"
table(dataState$category)##
## big mediam small
## 17 16 172
par(mfrow=c(2,2))
plot(trees$Volume,trees$Height)
plot(trees$Girth,trees$Volume)
hist(trees$Height)
boxplot(trees$Volume)
3
3a
rm(list = ls())
quantile(swiss$Infant.Mortality)## 0% 25% 50% 75% 100%
## 11 18 20 22 27swiss$categories[swiss$Infant.Mortality<=18.15]<-"Good"
swiss$categories[swiss$Infant.Mortalit>18.15 &
swiss$Infant.Mortality<=20]<-"Normal"
swiss$categories[swiss$Infant.Mortality>20 &
swiss$Infant.Mortality<=21.70]<-"Weaker"
swiss$categories[swiss$Infant.Mortality>21.70 ]<-"Poor"
swiss## Fertility Agriculture Examination Education Catholic
## Courtelary 80 17.0 15 12 10.0
## Delemont 83 45.1 6 9 84.8
## Franches-Mnt 92 39.7 5 5 93.4
## Moutier 86 36.5 12 7 33.8
## Neuveville 77 43.5 17 15 5.2
## Porrentruy 76 35.3 9 7 90.6
## Broye 84 70.2 16 7 92.8
## Glane 92 67.8 14 8 97.2
## Gruyere 82 53.3 12 7 97.7
## Sarine 83 45.2 16 13 91.4
## Veveyse 87 64.5 14 6 98.6
## Aigle 64 62.0 21 12 8.5
## Aubonne 67 67.5 14 7 2.3
## Avenches 69 60.7 19 12 4.4
## Cossonay 62 69.3 22 5 2.8
## Echallens 68 72.6 18 2 24.2
## Grandson 72 34.0 17 8 3.3
## Lausanne 56 19.4 26 28 12.1
## La Vallee 54 15.2 31 20 2.1
## Lavaux 65 73.0 19 9 2.8
## Morges 66 59.8 22 10 5.2
## Moudon 65 55.1 14 3 4.5
## Nyone 57 50.9 22 12 15.1
## Orbe 57 54.1 20 6 4.2
## Oron 72 71.2 12 1 2.4
## Payerne 74 58.1 14 8 5.2
## Paysd'enhaut 72 63.5 6 3 2.6
## Rolle 60 60.8 16 10 7.7
## Vevey 58 26.8 25 19 18.5
## Yverdon 65 49.5 15 8 6.1
## Conthey 76 85.9 3 2 99.7
## Entremont 69 84.9 7 6 99.7
## Herens 77 89.7 5 2 100.0
## Martigwy 70 78.2 12 6 99.0
## Monthey 79 64.9 7 3 98.2
## St Maurice 65 75.9 9 9 99.1
## Sierre 92 84.6 3 3 99.5
## Sion 79 63.1 13 13 96.8
## Boudry 70 38.4 26 12 5.6
## La Chauxdfnd 66 7.7 29 11 13.8
## Le Locle 73 16.7 22 13 11.2
## Neuchatel 64 17.6 35 32 16.9
## Val de Ruz 78 37.6 15 7 5.0
## ValdeTravers 68 18.7 25 7 8.6
## V. De Geneve 35 1.2 37 53 42.3
## Rive Droite 45 46.6 16 29 50.4
## Rive Gauche 43 27.7 22 29 58.3
## Infant.Mortality categories
## Courtelary 22 Poor
## Delemont 22 Poor
## Franches-Mnt 20 Weaker
## Moutier 20 Weaker
## Neuveville 21 Weaker
## Porrentruy 27 Poor
## Broye 24 Poor
## Glane 25 Poor
## Gruyere 21 Weaker
## Sarine 24 Poor
## Veveyse 24 Poor
## Aigle 16 Good
## Aubonne 19 Normal
## Avenches 23 Poor
## Cossonay 19 Normal
## Echallens 21 Weaker
## Grandson 20 Normal
## Lausanne 20 Weaker
## La Vallee 11 Good
## Lavaux 20 Normal
## Morges 18 Good
## Moudon 22 Poor
## Nyone 17 Good
## Orbe 15 Good
## Oron 21 Weaker
## Payerne 24 Poor
## Paysd'enhaut 18 Good
## Rolle 16 Good
## Vevey 21 Weaker
## Yverdon 22 Poor
## Conthey 15 Good
## Entremont 20 Normal
## Herens 18 Normal
## Martigwy 19 Normal
## Monthey 20 Weaker
## St Maurice 18 Good
## Sierre 16 Good
## Sion 18 Good
## Boudry 20 Weaker
## La Chauxdfnd 20 Weaker
## Le Locle 19 Normal
## Neuchatel 23 Poor
## Val de Ruz 20 Normal
## ValdeTravers 20 Normal
## V. De Geneve 18 Good
## Rive Droite 18 Normal
## Rive Gauche 19 Normaltable(swiss$categories)##
## Good Normal Poor Weaker
## 12 12 12 113b
library(ggplot2)
ggplot(data = swiss)+
geom_bar(mapping = aes(categories))
## alternative
barplot(table(swiss$categories))
3c
is.data.frame(swiss)## [1] TRUEswiss[sample(x = nrow(swiss),size = 15,replace = F),]## Fertility Agriculture Examination Education Catholic
## St Maurice 65 76 9 9 99.1
## Rive Droite 45 47 16 29 50.4
## Sarine 83 45 16 13 91.4
## Neuchatel 64 18 35 32 16.9
## Yverdon 65 50 15 8 6.1
## Aigle 64 62 21 12 8.5
## Paysd'enhaut 72 64 6 3 2.6
## Conthey 76 86 3 2 99.7
## Val de Ruz 78 38 15 7 5.0
## Aubonne 67 68 14 7 2.3
## Lavaux 65 73 19 9 2.8
## Martigwy 70 78 12 6 99.0
## Veveyse 87 64 14 6 98.6
## Rive Gauche 43 28 22 29 58.3
## Herens 77 90 5 2 100.0
## Infant.Mortality categories
## St Maurice 18 Good
## Rive Droite 18 Normal
## Sarine 24 Poor
## Neuchatel 23 Poor
## Yverdon 22 Poor
## Aigle 16 Good
## Paysd'enhaut 18 Good
## Conthey 15 Good
## Val de Ruz 20 Normal
## Aubonne 19 Normal
## Lavaux 20 Normal
## Martigwy 19 Normal
## Veveyse 24 Poor
## Rive Gauche 19 Normal
## Herens 18 Normalsummary(swiss)## Fertility Agriculture Examination Education Catholic
## Min. :35 Min. : 1 Min. : 3 Min. : 1 Min. : 2
## 1st Qu.:65 1st Qu.:36 1st Qu.:12 1st Qu.: 6 1st Qu.: 5
## Median :70 Median :54 Median :16 Median : 8 Median : 15
## Mean :70 Mean :51 Mean :16 Mean :11 Mean : 41
## 3rd Qu.:78 3rd Qu.:68 3rd Qu.:22 3rd Qu.:12 3rd Qu.: 93
## Max. :92 Max. :90 Max. :37 Max. :53 Max. :100
## Infant.Mortality categories
## Min. :10.8 Length:47
## 1st Qu.:18.1 Class :character
## Median :20.0 Mode :character
## Mean :19.9
## 3rd Qu.:21.7
## Max. :26.6summary(swiss$Agriculture)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1 36 54 51 68 90summary(swiss$Education)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1 6 8 11 12 534
#library(reshape)
#aggregate(x = mtcars,by = list(cyl) ,FUN = "mean")
#aggregate(x = mtcars,by = list(gear) ,FUN = "median")alternative
#cast(data = mtcars,cyl~.,mean)
#cast(data = mtcars,gear~.,mean)5
aggregate(x = warpbreaks$breaks,by = list(warpbreaks$wool ,warpbreaks$tension),FUN = "mean")## Group.1 Group.2 x
## 1 A L 45
## 2 B L 28
## 3 A M 24
## 4 B M 29
## 5 A H 25
## 6 B H 196
library(dplyr)
library(MASS)7
7a
x<-c(1:1:100)
sum(x)## [1] 50508
pdf<-function(a,x){
return(a*exp(-a*x))
}
cdf<-function(a,x){
return(1-exp(-a*x))
}
x<-c(1:20)
par(mfrow=c(2,2))
plot(x = x,y = pdf(1,x))
plot(x = x,y = cdf(1,x))
plot(pdf(2,x))
plot(cdf(2,x))
2020
Q1
1a
#What is meant by wrangling? Illustrate with example.
Data wrangling, also known as data munging, is the process of cleaning, transforming, and preparing data for analysis. It involves working with data that may be incomplete, inconsistent, or in a format that is not suitable for analysis. The goal of data wrangling is to transform the data into a format that is usable and appropriate for analysis, so that insights and value can be extracted from it.
The data wrangling process typically includes tasks such as:
Handling missing or incomplete data by imputing, deleting, or estimating missing values.
Removing duplicates or irrelevant data
Correcting formatting errors
Normalizing data by converting it into a consistent format
Combining data from multiple sources into a single dataset
Aggregating and summarizing data Overall, data wrangling is an essential step in the data analysis process, as it ensures that the data is accurate, complete, and usable for analysis.
alternative
I can give you an example to help illustrate what is meant by data wrangling.
Let’s say you have a dataset containing information about a group of people, including their names, ages, and the city they live in. However, the dataset is messy and contains a lot of errors and inconsistencies. Here’s an example of how you might use data wrangling techniques to clean up the data:
Removing duplicate records: You notice that the dataset contains multiple records for some individuals. For example, there are two records for a person named “John Smith”, with slightly different ages and addresses. To clean up the data, you decide to remove the duplicate records so that each person only appears once in the dataset.
Fixing formatting errors: You notice that some of the city names are not consistently formatted. For example, some records list the city as “New York City”, while others list it as “NYC” or “New York”. To make the data consistent, you decide to standardize all city names to the full name “New York City”.
Handling missing values: You notice that some records are missing information, such as an age or a city. To handle these missing values, you decide to either fill in the missing values with reasonable estimates (e.g. the average age of people in the dataset), or to remove the records entirely if they contain too many missing values.
These are just a few examples of the types of tasks that might be involved in data wrangling. The goal of data wrangling is to clean and transform the data so that it is ready for analysis, which can involve statistical modeling, machine learning, or other data science techniques.
1(b)
The ‘tidyverse’ is a collection of packages for data manipulation, exploration, and visualization in R. The core packages in the ‘tidyverse’ include:
- ggplot2: for creating high-quality visualizations
- dplyr: for data manipulation and transformation
- tidyr: for cleaning and tidying data
- readr: for reading in data in various formats
- purrr: for functional programming and iterating over data
- tibble: for creating and working with data frames
- stringr: for working with strings and text data
- forcats: for working with categorical data
These packages all follow a consistent set of design principles and syntax, making it easy to learn and use them together. The ‘tidyverse’ philosophy emphasizes the use of tidy data principles, which means that data should be structured in a consistent way to facilitate analysis and visualization.
1(c)
1.c.(i)
Question :
library(ggplot2) ggplot(data = diamonds,mapping = aes(x = cut,fill = “clarity” ))+ geom_bar(alpha = 1/5,position = “clarity”)
The code you provided uses the ggplot2 package in R to create a bar plot of the “cut” variable from the “diamonds” dataset. The plot uses the “fill” aesthetic to color the bars based on the “clarity” variable.
Here’s a breakdown of the code:
library(ggplot2) loads the ggplot2 package.
ggplot(data = diamonds, mapping = aes(x = cut, fill = “clarity”)) initializes a ggplot object, specifying that the data is the “diamonds” dataset and the x-axis variable is “cut”. The “fill” aesthetic is also set to “clarity”, which will be used to color the bars.
geom_bar(alpha = 1/5, position = “clarity”) specifies that the plot should be a bar plot (geom_bar) with an alpha of 1/5 (for transparency) and the bars should be positioned based on the “clarity” variable.
The output of this code would be a bar plot with bars representing the frequency of each “cut” category, colored based on the “clarity” variable. However, there is an error in the code as the “fill” aesthetic should be mapped to the clarity variable and not a string (“clarity”).
Here’s the corrected code:
ggplot(data = diamonds, mapping = aes(x = cut, fill = clarity)) +
geom_bar(alpha = 1/5, position = "stack")
#alternative
rm(list = ls())
library(tidyverse)
ggplot(data = diamonds, mapping = aes(x = cut, fill = clarity)) +
geom_bar(alpha = 1/5, position = 'identity')
This should produce a bar plot with bars representing the frequency of
each “cut” category, colored based on the “clarity” variable, and
stacked on top of each other.
1.c.(ii)
Question :
library(ggplot2) ggplot(data = diamonds,mapping = aes(x = cut,fill = “clarity” ))+ geom_bar(fill = NA ,position = “identity”)
The code you provided uses the ggplot2 package in R to create a bar plot of the “cut” variable from the “diamonds” dataset. The plot uses the “fill” aesthetic to color the bars based on a constant string (“clarity”).
Here’s a breakdown of the code:
library(ggplot2) loads the ggplot2 package.
ggplot(data = diamonds, mapping = aes(x = cut, fill = “clarity”)) initializes a ggplot object, specifying that the data is the “diamonds” dataset and the x-axis variable is “cut”. The “fill” aesthetic is also set to a constant string (“clarity”), which will be used to color the bars.
geom_bar(fill = NA ,position = “identity”) specifies that the plot should be a bar plot (geom_bar) with no fill color (fill = NA) and the bars should be positioned with no stacking (position = “identity”).
The output of this code would be a bar plot with bars representing the frequency of each “cut” category, but with no fill color. The constant string used for the “fill” aesthetic doesn’t affect the plot since the fill = NA argument overrides it. The bars are also positioned side by side (position = “identity”), which is the default for a bar plot.
Overall, this code is not very useful for visualizing the data in the “diamonds” dataset since it doesn’t show any meaningful relationship between the variables.
library(ggplot2)
ggplot(data = diamonds, mapping = aes(x = cut, fill = "clarity")) +
geom_bar( position = "identity")
1.b.(iii)
Question :
ggplot(data= diamonds)+ stat_summary(mapping = aes(x = cut,y = price),fun.ymin = min,fun.ymax = max,fun.y = median)
This code creates a plot of the “diamonds” dataset using ggplot2 in R. The stat_summary() function is used to add summary statistics to the plot. In particular, the fun.ymin, fun.ymax, and fun.y arguments are set to min, max, and median, respectively, which means that the plot will show the minimum, maximum, and median values of the “price” variable for each level of the “cut” variable.
The mapping argument specifies the aesthetics for the plot, with x set to “cut” and y set to “price”. The resulting plot will have “cut” on the x-axis and “price” on the y-axis, with boxes that show the median, minimum, and maximum values for each level of “cut”.
Note that the exact appearance of the plot will depend on additional specifications such as the theme, axis labels, and plot title.
2
2(a)
reg<-function(x,y){
beta1<-sum((x-mean(x))*(y-mean(y)))/sum((x-mean(x))^2)
beta0<-mean(y)-beta1*mean(x)
return(c(b0=beta0,b1= beta1))
}
x = c(1,4,8,9,12,16,17,19,27)
y = c(23,59,50,25,29,45,24,75,23)
reg(x,y)## b0 b1
## 39.85 -0.05#by default function
lm(y~x)##
## Call:
## lm(formula = y ~ x)
##
## Coefficients:
## (Intercept) x
## 39.85 -0.052(b)
correl<-function(x,y){
a<-sum((x-mean(x))*(y-mean(y)))/sqrt(sum((x-mean(x))^2)*sum((y-mean(y))^2))
return( a)
}
x = c(1,4,8,9,12,16,17,19,27)
y = c(23,59,50,25,29,45,24,75,23)
correl(x,y)## [1] -0.021#by default function
cor(x,y)## [1] -0.0213
3(i)
The melt() function is a part of the reshape2 package in R, and it is used to reshape data from a wide format to a long format. The long format is often more useful for analysis and visualization purposes.
The basic idea of melt() is to take columns of a data frame and “melt” them down into rows, while preserving other columns that are used as identifiers. Here’s an example:
library(reshape2)
# Create a sample data frame
df <- data.frame(id = 1:3, x1 = c(2, 4, 6), x2 = c(3, 5, 7))
# Melt the data frame
melted_df <- melt(df, id.vars = "id")
# Print the original and melted data frames
print(df)## id x1 x2
## 1 1 2 3
## 2 2 4 5
## 3 3 6 7print(melted_df)## id variable value
## 1 1 x1 2
## 2 2 x1 4
## 3 3 x1 6
## 4 1 x2 3
## 5 2 x2 5
## 6 3 x2 73(ii)
The cast() function in R is used to reshape data from long format to wide format. It is the opposite of the melt() function. This function is part of the reshape2 package in R.
The basic idea of cast() is to take a data frame that has a single row for each observation, but multiple columns for different variables, and convert it to a data frame with a single row for each value of a particular variable. Here’s an example:
library(reshape)
# Create a sample data frame
df <- data.frame(
id = rep(1:3, each = 2),
variable = c("x1", "x2", "x1", "x2", "x1", "x2"),
value = c(2, 3, 4, 5, 6, 7)
)
# Cast the data frame
casted_df <- cast(df, id ~ variable, value = "value")
# Print the original and casted data frames
print(df)## id variable value
## 1 1 x1 2
## 2 1 x2 3
## 3 2 x1 4
## 4 2 x2 5
## 5 3 x1 6
## 6 3 x2 7print(casted_df)## id x1 x2
## 1 1 2 3
## 2 2 4 5
## 3 3 6 73(iii)
The grep function is used to search for a specified pattern in a vector or a text file and returns the indices or the values that match the pattern. It is useful for extracting specific information from text data.
Syntax: grep(pattern, x, …)
Where pattern is the regular expression to search for, x is the vector or text file to search in, and … are optional arguments such as ignore.case and value.
Example:
Suppose we have a vector of strings representing the names of fruits:
fruits <- c("apple", "banana", "orange", "kiwi", "pear", "mango")
grep("a", fruits)## [1] 1 2 3 5 6We can use grep to search for all the fruits that contain the letter “a” in their name:
Here, grep returns the indices of the elements in the fruits vector that contain the letter “a” in their name.
We can also use grep to extract the fruits that contain the letter “a” in their name:
grep("a", fruits, value = TRUE)## [1] "apple" "banana" "orange" "pear" "mango"Here, grep returns the values of the elements in the fruits vector that contain the letter “a” in their name.
Note that grep is case-sensitive by default, but this can be changed using the ignore.case argument.
3(iv)
The qnorm function is used to calculate the quantiles of a normal distribution given a probability value. It is the inverse of the cumulative distribution function pnorm.
Syntax: qnorm(p, mean = 0, sd = 1, lower.tail = TRUE, log.p = FALSE)
Where p is the probability value, mean and sd are the mean and standard deviation of the normal distribution, lower.tail is a logical value indicating whether to calculate the probability for the lower or upper tail of the distribution, and log.p is a logical value indicating whether p is given in log scale or not.
Example:
Suppose we want to find the quantile of a standard normal distribution for a given probability value 0.95:
qnorm(0.95)## [1] 1.6#We can also find the quantile of a normal distribution with a given mean and standard deviation for a probability value of 0.9:
qnorm(0.9, mean = 50, sd = 10)## [1] 633(v)
ggplot is a powerful data visualization package in the R programming language. It is used to create beautiful and informative graphics, and provides a wide range of customization options.
The basic syntax for creating a ggplot object is as follows:
ggplot(data = ) +
Here’s an example of how to use ggplot to create a scatter plot:
library(ggplot2)
# create a dataset
data <- data.frame(x = rnorm(100), y = rnorm(100))
# create a ggplot object
p <- ggplot(data = data) +
geom_point(mapping = aes(x = x, y = y))
# display the plot
p
In this example, we first create a dataset with 100 random points in two dimensions. We then create a ggplot object with data = data and geom_point() as the geometric object. We use the mapping argument to specify that the x and y variables in the dataset should be mapped to the x-axis and y-axis of the plot, respectively. Finally, we display the plot using the p object.
This produces a scatter plot with the x-axis and y-axis labeled and scaled appropriately, and with each point represented as a dot. We can customize the plot further by adding additional geometric objects, changing the color or size of the points, adding titles or legends, etc. The flexibility and power of ggplot makes it a very useful tool for exploring and visualizing data.
4
4(a)
library(tidyverse)
AirPassengers## Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
## 1949 112 118 132 129 121 135 148 148 136 119 104 118
## 1950 115 126 141 135 125 149 170 170 158 133 114 140
## 1951 145 150 178 163 172 178 199 199 184 162 146 166
## 1952 171 180 193 181 183 218 230 242 209 191 172 194
## 1953 196 196 236 235 229 243 264 272 237 211 180 201
## 1954 204 188 235 227 234 264 302 293 259 229 203 229
## 1955 242 233 267 269 270 315 364 347 312 274 237 278
## 1956 284 277 317 313 318 374 413 405 355 306 271 306
## 1957 315 301 356 348 355 422 465 467 404 347 305 336
## 1958 340 318 362 348 363 435 491 505 404 359 310 337
## 1959 360 342 406 396 420 472 548 559 463 407 362 405
## 1960 417 391 419 461 472 535 622 606 508 461 390 432data<-as.data.frame(AirPassengers)
month.abb## [1] "Jan" "Feb" "Mar" "Apr" "May" "Jun" "Jul" "Aug" "Sep" "Oct" "Nov" "Dec"data$year<-rep(c(1949:1960),each=12)
data$month<-rep(month.abb)
data## x year month
## 1 112 1949 Jan
## 2 118 1949 Feb
## 3 132 1949 Mar
## 4 129 1949 Apr
## 5 121 1949 May
## 6 135 1949 Jun
## 7 148 1949 Jul
## 8 148 1949 Aug
## 9 136 1949 Sep
## 10 119 1949 Oct
## 11 104 1949 Nov
## 12 118 1949 Dec
## 13 115 1950 Jan
## 14 126 1950 Feb
## 15 141 1950 Mar
## 16 135 1950 Apr
## 17 125 1950 May
## 18 149 1950 Jun
## 19 170 1950 Jul
## 20 170 1950 Aug
## 21 158 1950 Sep
## 22 133 1950 Oct
## 23 114 1950 Nov
## 24 140 1950 Dec
## 25 145 1951 Jan
## 26 150 1951 Feb
## 27 178 1951 Mar
## 28 163 1951 Apr
## 29 172 1951 May
## 30 178 1951 Jun
## 31 199 1951 Jul
## 32 199 1951 Aug
## 33 184 1951 Sep
## 34 162 1951 Oct
## 35 146 1951 Nov
## 36 166 1951 Dec
## 37 171 1952 Jan
## 38 180 1952 Feb
## 39 193 1952 Mar
## 40 181 1952 Apr
## 41 183 1952 May
## 42 218 1952 Jun
## 43 230 1952 Jul
## 44 242 1952 Aug
## 45 209 1952 Sep
## 46 191 1952 Oct
## 47 172 1952 Nov
## 48 194 1952 Dec
## 49 196 1953 Jan
## 50 196 1953 Feb
## 51 236 1953 Mar
## 52 235 1953 Apr
## 53 229 1953 May
## 54 243 1953 Jun
## 55 264 1953 Jul
## 56 272 1953 Aug
## 57 237 1953 Sep
## 58 211 1953 Oct
## 59 180 1953 Nov
## 60 201 1953 Dec
## 61 204 1954 Jan
## 62 188 1954 Feb
## 63 235 1954 Mar
## 64 227 1954 Apr
## 65 234 1954 May
## 66 264 1954 Jun
## 67 302 1954 Jul
## 68 293 1954 Aug
## 69 259 1954 Sep
## 70 229 1954 Oct
## 71 203 1954 Nov
## 72 229 1954 Dec
## 73 242 1955 Jan
## 74 233 1955 Feb
## 75 267 1955 Mar
## 76 269 1955 Apr
## 77 270 1955 May
## 78 315 1955 Jun
## 79 364 1955 Jul
## 80 347 1955 Aug
## 81 312 1955 Sep
## 82 274 1955 Oct
## 83 237 1955 Nov
## 84 278 1955 Dec
## 85 284 1956 Jan
## 86 277 1956 Feb
## 87 317 1956 Mar
## 88 313 1956 Apr
## 89 318 1956 May
## 90 374 1956 Jun
## 91 413 1956 Jul
## 92 405 1956 Aug
## 93 355 1956 Sep
## 94 306 1956 Oct
## 95 271 1956 Nov
## 96 306 1956 Dec
## 97 315 1957 Jan
## 98 301 1957 Feb
## 99 356 1957 Mar
## 100 348 1957 Apr
## 101 355 1957 May
## 102 422 1957 Jun
## 103 465 1957 Jul
## 104 467 1957 Aug
## 105 404 1957 Sep
## 106 347 1957 Oct
## 107 305 1957 Nov
## 108 336 1957 Dec
## 109 340 1958 Jan
## 110 318 1958 Feb
## 111 362 1958 Mar
## 112 348 1958 Apr
## 113 363 1958 May
## 114 435 1958 Jun
## 115 491 1958 Jul
## 116 505 1958 Aug
## 117 404 1958 Sep
## 118 359 1958 Oct
## 119 310 1958 Nov
## 120 337 1958 Dec
## 121 360 1959 Jan
## 122 342 1959 Feb
## 123 406 1959 Mar
## 124 396 1959 Apr
## 125 420 1959 May
## 126 472 1959 Jun
## 127 548 1959 Jul
## 128 559 1959 Aug
## 129 463 1959 Sep
## 130 407 1959 Oct
## 131 362 1959 Nov
## 132 405 1959 Dec
## 133 417 1960 Jan
## 134 391 1960 Feb
## 135 419 1960 Mar
## 136 461 1960 Apr
## 137 472 1960 May
## 138 535 1960 Jun
## 139 622 1960 Jul
## 140 606 1960 Aug
## 141 508 1960 Sep
## 142 461 1960 Oct
## 143 390 1960 Nov
## 144 432 1960 Decmax(data$x)## [1] 622alternative
data("AirPassengers")
date_raw = time(AirPassengers)[which.max(AirPassengers)]
max_year = floor(date_raw)
max_year## [1] 1960month_raw = date_raw - max_year
month_raw## [1] 0.5month_index = 12*month_raw
month_index## [1] 6max_month = month.abb[month_index+1]
AirPassengers## Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
## 1949 112 118 132 129 121 135 148 148 136 119 104 118
## 1950 115 126 141 135 125 149 170 170 158 133 114 140
## 1951 145 150 178 163 172 178 199 199 184 162 146 166
## 1952 171 180 193 181 183 218 230 242 209 191 172 194
## 1953 196 196 236 235 229 243 264 272 237 211 180 201
## 1954 204 188 235 227 234 264 302 293 259 229 203 229
## 1955 242 233 267 269 270 315 364 347 312 274 237 278
## 1956 284 277 317 313 318 374 413 405 355 306 271 306
## 1957 315 301 356 348 355 422 465 467 404 347 305 336
## 1958 340 318 362 348 363 435 491 505 404 359 310 337
## 1959 360 342 406 396 420 472 548 559 463 407 362 405
## 1960 417 391 419 461 472 535 622 606 508 461 390 432paste("Maximum passenger", max(AirPassengers), "in", max_month, max_year)## [1] "Maximum passenger 622 in Jul 1960"4b
plot(AirPassengers)
4c
library(ggplot2)
x<-factor(cycle(AirPassengers))
x## [1] 1 2 3 4 5 6 7 8 9 10 11 12 1 2 3 4 5 6 7 8 9 10 11 12 1
## [26] 2 3 4 5 6 7 8 9 10 11 12 1 2 3 4 5 6 7 8 9 10 11 12 1 2
## [51] 3 4 5 6 7 8 9 10 11 12 1 2 3 4 5 6 7 8 9 10 11 12 1 2 3
## [76] 4 5 6 7 8 9 10 11 12 1 2 3 4 5 6 7 8 9 10 11 12 1 2 3 4
## [101] 5 6 7 8 9 10 11 12 1 2 3 4 5 6 7 8 9 10 11 12 1 2 3 4 5
## [126] 6 7 8 9 10 11 12 1 2 3 4 5 6 7 8 9 10 11 12
## Levels: 1 2 3 4 5 6 7 8 9 10 11 12ggplot()+
geom_boxplot(mapping = aes(x = x,y = AirPassengers ))## Don't know how to automatically pick scale for object of type <ts>. Defaulting
## to continuous.
alternative
library(tidyverse)
data<-as.data.frame(AirPassengers)
month.abb## [1] "Jan" "Feb" "Mar" "Apr" "May" "Jun" "Jul" "Aug" "Sep" "Oct" "Nov" "Dec"data$year<-rep(c(1949:1960),each=12)
data$month<-rep(month.abb)
data## x year month
## 1 112 1949 Jan
## 2 118 1949 Feb
## 3 132 1949 Mar
## 4 129 1949 Apr
## 5 121 1949 May
## 6 135 1949 Jun
## 7 148 1949 Jul
## 8 148 1949 Aug
## 9 136 1949 Sep
## 10 119 1949 Oct
## 11 104 1949 Nov
## 12 118 1949 Dec
## 13 115 1950 Jan
## 14 126 1950 Feb
## 15 141 1950 Mar
## 16 135 1950 Apr
## 17 125 1950 May
## 18 149 1950 Jun
## 19 170 1950 Jul
## 20 170 1950 Aug
## 21 158 1950 Sep
## 22 133 1950 Oct
## 23 114 1950 Nov
## 24 140 1950 Dec
## 25 145 1951 Jan
## 26 150 1951 Feb
## 27 178 1951 Mar
## 28 163 1951 Apr
## 29 172 1951 May
## 30 178 1951 Jun
## 31 199 1951 Jul
## 32 199 1951 Aug
## 33 184 1951 Sep
## 34 162 1951 Oct
## 35 146 1951 Nov
## 36 166 1951 Dec
## 37 171 1952 Jan
## 38 180 1952 Feb
## 39 193 1952 Mar
## 40 181 1952 Apr
## 41 183 1952 May
## 42 218 1952 Jun
## 43 230 1952 Jul
## 44 242 1952 Aug
## 45 209 1952 Sep
## 46 191 1952 Oct
## 47 172 1952 Nov
## 48 194 1952 Dec
## 49 196 1953 Jan
## 50 196 1953 Feb
## 51 236 1953 Mar
## 52 235 1953 Apr
## 53 229 1953 May
## 54 243 1953 Jun
## 55 264 1953 Jul
## 56 272 1953 Aug
## 57 237 1953 Sep
## 58 211 1953 Oct
## 59 180 1953 Nov
## 60 201 1953 Dec
## 61 204 1954 Jan
## 62 188 1954 Feb
## 63 235 1954 Mar
## 64 227 1954 Apr
## 65 234 1954 May
## 66 264 1954 Jun
## 67 302 1954 Jul
## 68 293 1954 Aug
## 69 259 1954 Sep
## 70 229 1954 Oct
## 71 203 1954 Nov
## 72 229 1954 Dec
## 73 242 1955 Jan
## 74 233 1955 Feb
## 75 267 1955 Mar
## 76 269 1955 Apr
## 77 270 1955 May
## 78 315 1955 Jun
## 79 364 1955 Jul
## 80 347 1955 Aug
## 81 312 1955 Sep
## 82 274 1955 Oct
## 83 237 1955 Nov
## 84 278 1955 Dec
## 85 284 1956 Jan
## 86 277 1956 Feb
## 87 317 1956 Mar
## 88 313 1956 Apr
## 89 318 1956 May
## 90 374 1956 Jun
## 91 413 1956 Jul
## 92 405 1956 Aug
## 93 355 1956 Sep
## 94 306 1956 Oct
## 95 271 1956 Nov
## 96 306 1956 Dec
## 97 315 1957 Jan
## 98 301 1957 Feb
## 99 356 1957 Mar
## 100 348 1957 Apr
## 101 355 1957 May
## 102 422 1957 Jun
## 103 465 1957 Jul
## 104 467 1957 Aug
## 105 404 1957 Sep
## 106 347 1957 Oct
## 107 305 1957 Nov
## 108 336 1957 Dec
## 109 340 1958 Jan
## 110 318 1958 Feb
## 111 362 1958 Mar
## 112 348 1958 Apr
## 113 363 1958 May
## 114 435 1958 Jun
## 115 491 1958 Jul
## 116 505 1958 Aug
## 117 404 1958 Sep
## 118 359 1958 Oct
## 119 310 1958 Nov
## 120 337 1958 Dec
## 121 360 1959 Jan
## 122 342 1959 Feb
## 123 406 1959 Mar
## 124 396 1959 Apr
## 125 420 1959 May
## 126 472 1959 Jun
## 127 548 1959 Jul
## 128 559 1959 Aug
## 129 463 1959 Sep
## 130 407 1959 Oct
## 131 362 1959 Nov
## 132 405 1959 Dec
## 133 417 1960 Jan
## 134 391 1960 Feb
## 135 419 1960 Mar
## 136 461 1960 Apr
## 137 472 1960 May
## 138 535 1960 Jun
## 139 622 1960 Jul
## 140 606 1960 Aug
## 141 508 1960 Sep
## 142 461 1960 Oct
## 143 390 1960 Nov
## 144 432 1960 Dec## main part
ggplot()+
geom_boxplot(mapping = aes(x = data$month,y = AirPassengers))## Don't know how to automatically pick scale for object of type <ts>. Defaulting
## to continuous.
5
5a
rm(list=ls())
x<-read.csv(file = "D:/2nd Year/AST 230/avgpm25.csv")
summary(x$pm25)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3.4 8.5 10.0 9.8 11.4 18.4boxplot(x$pm25)
hist(x$pm25)
2021
Q2
2a
rm(list=ls())
data<- read.csv("D:/2nd Year/AST 230/Final excel/data1.csv")
summary(data)## ID age gender height weight
## Min. :1 Min. :27 Length:5 Min. :1.58 Min. :60
## 1st Qu.:2 1st Qu.:29 Class :character 1st Qu.:1.63 1st Qu.:63
## Median :3 Median :35 Mode :character Median :1.64 Median :64
## Mean :3 Mean :44 Mean :1.67 Mean :66
## 3rd Qu.:4 3rd Qu.:56 3rd Qu.:1.71 3rd Qu.:66
## Max. :5 Max. :74 Max. :1.78 Max. :782b
library(haven)## Warning: package 'haven' was built under R version 4.2.2library(foreign)
breaks<-read.csv("D:/2nd Year/AST 230/Final excel/breaks.csv")
breaks## breaks wool tension
## 1 26 A L
## 2 30 A L
## 3 54 A L
## 4 47 B L
## 5 26 B L
## 6 48 B M
## 7 58 C M
## 8 76 C M
## 9 21 C M
## 10 56 D M
## 11 96 D M
## 12 30 D M
## 13 14 D M
## 14 45 D N
## 15 65 D N
## 16 32 E N
## 17 14 E N
## 18 85 E N
## 19 45 E Nbpwide <- read_dta("D:/2nd Year/AST 230/Final excel/bpwide.dta")
bpwide## # A tibble: 120 × 5
## patient sex agegrp bp_before bp_after
## <dbl> <dbl+lbl> <dbl+lbl> <dbl> <dbl>
## 1 1 0 [Male] 1 [30-45] 143 153
## 2 2 0 [Male] 1 [30-45] 163 170
## 3 3 0 [Male] 1 [30-45] 153 168
## 4 4 0 [Male] 1 [30-45] 153 142
## 5 5 0 [Male] 1 [30-45] 146 141
## 6 6 0 [Male] 1 [30-45] 150 147
## 7 7 0 [Male] 1 [30-45] 148 133
## 8 8 0 [Male] 1 [30-45] 153 141
## 9 9 0 [Male] 1 [30-45] 153 131
## 10 10 0 [Male] 1 [30-45] 158 125
## # … with 110 more rowsworld95 <- read.spss("D:/2nd Year/AST 230/Final excel/world95.sav", to.data.frame = T)## re-encoding from CP1252## Warning in read.spss("D:/2nd Year/AST 230/Final excel/world95.sav",
## to.data.frame = T): Undeclared level(s) Animist, Buddhist, Catholic, Hindu,
## Jewish, Muslim, Orthodox, Protstnt, Taoist, Tribal added in variable: religion## Warning in read.spss("D:/2nd Year/AST 230/Final excel/world95.sav",
## to.data.frame = T): Undeclared level(s) 4 added in variable: climateworld95## country populatn density urban religion lifeexpf lifeexpm literacy
## 1 Afghanistan 20500 25.0 18 Muslim 44 45 29
## 2 Argentina 33900 12.0 86 Catholic 75 68 95
## 3 Armenia 3700 126.0 68 Orthodox 75 68 98
## 4 Australia 17800 2.3 85 Protstnt 80 74 100
## 5 Austria 8000 94.0 58 Catholic 79 73 99
## 6 Azerbaijan 7400 86.0 54 Muslim 75 67 98
## 7 Bahrain 600 828.0 83 Muslim 74 71 77
## 8 Bangladesh 125000 800.0 16 Muslim 53 53 35
## 9 Barbados 256 605.0 45 Protstnt 78 73 99
## 10 Belarus 10300 50.0 65 Orthodox 76 66 99
## 11 Belgium 10100 329.0 96 Catholic 79 73 99
## 12 Bolivia 7900 6.9 51 Catholic 64 59 78
## 13 Bosnia 4600 87.0 36 Muslim 78 72 86
## 14 Botswana 1359 2.4 25 Tribal 66 60 72
## 15 Brazil 156600 18.0 75 Catholic 67 57 81
## 16 Bulgaria 8900 79.0 68 Orthodox 75 69 93
## 17 Burkina Faso 10000 36.0 15 Animist 50 47 18
## 18 Burundi 6000 216.0 5 Catholic 50 46 50
## 19 Cambodia 10000 55.0 12 Buddhist 52 50 35
## 20 Cameroon 13100 27.0 40 Animist 58 55 54
## 21 Canada 29100 2.8 77 Catholic 81 74 97
## 22 Cent. Afri.R 3300 5.0 47 Protstnt 44 41 27
## 23 Chile 14000 18.0 85 Catholic 78 71 93
## 24 China 1205200 124.0 26 Taoist 69 67 78
## 25 Colombia 35600 31.0 70 Catholic 75 69 87
## 26 Costa Rica 3300 64.0 47 Catholic 79 76 93
## 27 Croatia 4900 85.0 51 Catholic 77 70 97
## 28 Cuba 11100 99.0 74 Catholic 78 74 94
## 29 Czech Rep. 10400 132.0 NA Catholic 77 69 NA
## 30 Denmark 5200 120.0 85 Protstnt 79 73 99
## 31 Domincan R. 7800 159.0 60 Catholic 70 66 83
## 32 Ecuador 10700 39.0 56 Catholic 73 67 88
## 33 Egypt 60000 57.0 44 Muslim 63 60 48
## 34 El Salvador 5800 246.0 44 Catholic 69 64 73
## 35 Estonia 1600 36.0 72 Protstnt 76 67 99
## 36 Ethiopia 55200 47.0 12 Muslim 54 51 24
## 37 Finland 5100 39.0 60 Protstnt 80 72 100
## 38 France 58000 105.0 73 Catholic 82 74 99
## 39 Gabon 1300 4.2 46 Catholic 58 52 61
## 40 Gambia 959 86.0 23 Muslim 52 48 27
## 41 Georgia 5500 81.0 56 Orthodox 76 69 99
## 42 Germany 81200 227.0 85 Protstnt 79 73 99
## 43 Greece 10400 80.0 63 Orthodox 80 75 93
## 44 Guatemala 10300 97.0 39 Catholic 67 62 55
## 45 Haiti 6500 231.0 29 Catholic 47 43 53
## 46 Honduras 5600 46.0 44 Catholic 70 65 73
## 47 Hong Kong 5800 5494.0 94 Buddhist 80 75 77
## 48 Hungary 10500 111.0 64 Catholic 76 67 99
## 49 Iceland 263 2.5 91 Protstnt 81 76 100
## 50 India 911600 283.0 26 Hindu 59 58 52
## 51 Indonesia 199700 102.0 29 Muslim 65 61 77
## 52 Iran 65600 39.0 57 Muslim 67 65 54
## 53 Iraq 19900 44.0 72 Muslim 68 65 60
## 54 Ireland 3600 51.0 57 Catholic 78 73 98
## 55 Israel 5400 238.0 92 Jewish 80 76 92
## 56 Italy 58100 188.0 69 Catholic 81 74 97
## 57 Japan 125500 330.0 77 Buddhist 82 76 99
## 58 Jordan 3961 42.0 68 Muslim 74 70 80
## 59 Kenya 28200 49.0 24 Catholic 55 51 69
## 60 Kuwait 1800 97.0 96 Muslim 78 73 73
## 61 Latvia 2700 40.0 71 Protstnt 75 64 99
## 62 Lebanon 3620 343.0 84 Muslim 71 67 80
## 63 Liberia 2900 29.0 45 Animist 57 54 40
## 64 Libya 5500 2.8 82 Muslim 65 62 64
## 65 Lithuania 3800 58.0 69 Catholic 77 68 99
## 66 Malaysia 19500 58.0 43 Muslim 72 66 78
## 67 Mexico 91800 46.0 73 Catholic 77 69 87
## 68 Morocco 28600 63.0 46 Muslim 70 66 50
## 69 N. Korea 23100 189.0 60 Buddhist 73 67 99
## 70 Netherlands 15400 366.0 89 Catholic 81 75 99
## 71 New Zealand 3524 13.0 84 Protstnt 80 73 99
## 72 Nicaragua 4100 33.0 60 Catholic 67 61 57
## 73 Nigeria 98100 102.0 35 Muslim 57 54 51
## 74 Norway 4300 11.0 75 Protstnt 81 74 99
## 75 Oman 1900 7.8 11 Muslim 70 66 NA
## 76 Pakistan 128100 143.0 32 Muslim 58 57 35
## 77 Panama 2600 34.0 53 Catholic 78 71 88
## 78 Paraguay 5200 11.0 48 Catholic 75 72 90
## 79 Peru 23650 18.0 70 Catholic 67 63 85
## 80 Philippines 69800 221.0 43 Catholic 68 63 90
## 81 Poland 38600 123.0 62 Catholic 77 69 99
## 82 Portugal 10500 108.0 34 Catholic 78 71 85
## 83 Romania 23400 96.0 54 Orthodox 75 69 96
## 84 Russia 149200 8.8 74 Orthodox 74 64 99
## 85 Rwanda 8400 311.0 6 Catholic 46 43 50
## 86 S. Korea 45000 447.0 72 Protstnt 74 68 96
## 87 Saudi Arabia 18000 7.7 77 Muslim 70 66 62
## 88 Senegal 8700 43.0 40 Muslim 58 55 38
## 89 Singapore 2900 4456.0 100 Taoist 79 73 88
## 90 Somalia 6667 10.0 24 Muslim 55 54 24
## 91 South Africa 43900 35.0 49 <NA> 68 62 76
## 92 Spain 39200 77.0 78 Catholic 81 74 95
## 93 Sweden 8800 19.0 84 Protstnt 81 75 99
## 94 Switzerland 7000 170.0 62 Catholic 82 75 99
## 95 Syria 14900 74.0 50 Muslim 68 65 64
## 96 Taiwan 20944 582.0 71 Buddhist 78 72 91
## 97 Tanzania 29800 29.0 21 Animist 45 41 46
## 98 Thailand 59400 115.0 22 Buddhist 72 65 93
## 99 Turkey 62200 79.0 61 Muslim 73 69 81
## 100 U.Arab Em. 2800 32.0 81 Muslim 74 70 68
## 101 Uganda 19800 76.0 11 Catholic 43 41 48
## 102 UK 58400 237.0 89 Protstnt 80 74 99
## 103 Ukraine 51800 87.0 67 Orthodox 75 65 97
## 104 Uruguay 3200 18.0 89 Catholic 77 71 96
## 105 USA 260800 26.0 75 Protstnt 79 73 97
## 106 Uzbekistan 22600 50.0 41 Muslim 72 65 97
## 107 Venezuela 20600 22.0 91 Catholic 76 70 88
## 108 Vietnam 73100 218.0 20 Buddhist 68 63 88
## 109 Zambia 9100 11.0 42 Protstnt 45 44 73
## pop_incr babymort gdp_cap region calories aids birth_rt death_rt
## 1 2.80 168.0 205 Pacific/Asia NA 0 53 22.0
## 2 1.30 25.6 3408 Latn America 3113 3904 20 9.0
## 3 1.40 27.0 5000 Middle East NA 2 23 6.0
## 4 1.38 7.3 16848 OECD 3216 4727 15 8.0
## 5 0.20 6.7 18396 OECD 3495 1150 12 11.0
## 6 1.40 35.0 3000 Middle East NA NA 23 7.0
## 7 2.40 25.0 7875 Middle East NA 13 29 4.0
## 8 2.40 106.0 202 Pacific/Asia 2021 1 35 11.0
## 9 0.21 20.3 6950 Latn America NA 418 16 8.4
## 10 0.32 19.0 6500 East Europe NA 10 13 11.0
## 11 0.20 7.2 17912 OECD NA 1603 12 11.0
## 12 2.70 75.0 730 Latn America 1916 87 34 9.0
## 13 0.70 12.7 3098 East Europe NA NA 14 6.4
## 14 2.70 39.3 2677 Africa 2375 1415 32 8.0
## 15 1.28 66.0 2354 Latn America 2751 49312 21 9.0
## 16 -0.20 12.0 3831 East Europe NA 24 13 12.0
## 17 2.81 118.0 357 Africa 2288 4193 47 18.0
## 18 2.26 105.0 208 Africa 1932 7225 44 21.0
## 19 2.90 112.0 260 Pacific/Asia 2166 0 45 16.0
## 20 2.90 77.0 993 Africa 2217 3072 41 12.0
## 21 0.70 6.8 19904 OECD 3482 9511 14 8.0
## 22 2.40 137.0 457 Africa 2036 3730 44 21.0
## 23 1.70 14.6 2591 Latn America 2581 831 23 6.0
## 24 1.10 52.0 377 Pacific/Asia 2639 38 21 7.0
## 25 2.00 28.0 1538 Latn America 2598 4583 24 6.0
## 26 2.30 11.0 2031 Latn America 2808 587 26 4.0
## 27 -0.10 8.7 5487 East Europe NA 56 11 11.0
## 28 0.95 10.2 1382 Latn America NA 245 17 7.0
## 29 0.21 9.3 7311 East Europe 3632 48 13 11.1
## 30 0.10 6.6 18277 OECD 3628 1411 12 12.0
## 31 1.80 51.5 1034 Latn America 2359 2353 25 6.0
## 32 2.01 39.0 1085 Latn America 2531 381 26 6.0
## 33 1.95 76.4 748 Middle East 3336 91 29 9.0
## 34 2.04 41.0 1078 Latn America 2317 530 33 7.0
## 35 0.52 19.0 6000 East Europe NA 3 14 12.0
## 36 3.10 110.0 122 Africa 1667 12958 45 14.0
## 37 0.30 5.3 15877 OECD 3253 158 13 10.0
## 38 0.47 6.7 18944 OECD 3465 30003 13 9.3
## 39 1.46 94.0 4283 Africa 2383 472 28 14.0
## 40 3.10 124.0 351 Africa NA 277 46 16.0
## 41 0.80 23.0 4500 East Europe NA 2 16 9.0
## 42 0.36 6.5 17539 OECD 3443 11179 11 11.0
## 43 0.84 8.2 8060 OECD 3825 916 10 10.0
## 44 2.58 57.0 1342 Latn America 2235 499 35 8.0
## 45 1.63 109.0 383 Latn America 2013 4987 40 19.0
## 46 2.73 45.0 1030 Latn America 2247 3473 35 6.0
## 47 -0.09 5.8 14641 Pacific/Asia NA 99 13 6.0
## 48 -0.30 12.5 5249 East Europe 3644 149 12 13.0
## 49 1.10 4.0 17241 OECD NA 31 16 7.0
## 50 1.90 79.0 275 Pacific/Asia 2229 713 29 10.0
## 51 1.60 68.0 681 Pacific/Asia 2750 49 24 9.0
## 52 3.46 60.0 1500 Middle East 3181 92 42 8.0
## 53 3.70 67.0 1955 Middle East 2887 26 44 7.0
## 54 0.30 7.4 12170 OECD 3778 392 14 9.0
## 55 2.22 8.6 13066 Middle East NA 279 21 7.0
## 56 0.21 7.6 17500 OECD 3504 21770 11 10.0
## 57 0.30 4.4 19860 Pacific/Asia 2956 713 11 7.0
## 58 3.30 34.0 1157 Middle East 2634 31 39 5.0
## 59 3.07 74.0 323 Africa 2163 30126 42 11.0
## 60 5.24 12.5 6818 Middle East 3195 10 28 2.0
## 61 0.50 21.5 7400 East Europe NA 8 14 12.0
## 62 2.00 39.5 1429 Middle East NA 72 27 7.0
## 63 3.30 113.0 409 Africa 2382 191 43 12.0
## 64 3.70 63.0 5910 Middle East 3324 10 45 8.0
## 65 0.30 17.0 6710 East Europe NA 5 15 10.0
## 66 2.30 25.6 2995 Pacific/Asia 2774 107 29 5.0
## 67 1.90 35.0 3604 Latn America 3052 18353 28 5.0
## 68 2.12 50.0 1062 Africa NA 196 29 6.0
## 69 1.83 27.7 1000 Pacific/Asia NA 0 24 5.5
## 70 0.58 6.3 17245 OECD 3151 3055 13 9.0
## 71 0.57 8.9 14381 OECD 3362 431 16 8.0
## 72 2.68 52.5 447 Latn America 2265 66 35 7.0
## 73 3.10 75.0 282 Africa 2312 1148 44 12.0
## 74 0.40 6.3 17755 OECD 3326 375 13 10.0
## 75 3.46 36.7 7467 Middle East NA 33 40 5.0
## 76 2.80 101.0 406 Pacific/Asia NA 41 42 10.0
## 77 1.94 16.5 2397 Latn America 2539 644 25 5.0
## 78 2.70 25.2 1500 Latn America 2757 77 33 4.5
## 79 2.00 54.0 1107 Latn America 2186 1068 26 7.0
## 80 1.92 51.0 867 Pacific/Asia 2375 136 27 7.0
## 81 0.30 13.8 4429 East Europe NA 201 14 10.0
## 82 0.36 9.2 9000 OECD NA 1811 12 10.0
## 83 0.06 20.3 2702 East Europe 3155 2736 14 10.0
## 84 0.20 27.0 6680 East Europe NA 136 13 11.0
## 85 2.80 117.0 292 Africa 1971 10706 49 21.0
## 86 1.00 21.7 6627 Pacific/Asia NA 19 16 6.0
## 87 3.20 52.0 6651 Middle East 2874 61 38 6.0
## 88 3.10 76.0 744 Africa 2369 911 43 12.0
## 89 1.20 5.7 14990 Pacific/Asia 3198 75 16 6.0
## 90 3.20 126.0 2126 Africa 1906 13 46 13.0
## 91 2.60 47.1 3128 Africa NA 3210 34 8.0
## 92 0.25 6.9 13047 OECD 3572 24202 11 9.0
## 93 0.52 5.7 16900 OECD 2960 1001 14 11.0
## 94 0.70 6.2 22384 OECD 3562 3662 12 9.0
## 95 3.70 43.0 2436 Middle East NA 26 44 6.0
## 96 0.92 5.1 7055 Pacific/Asia NA NA 16 NA
## 97 2.50 110.0 263 Africa 2206 38719 46 19.0
## 98 1.40 37.0 1800 Pacific/Asia 2316 5654 19 6.0
## 99 2.02 49.0 3721 Middle East 3236 130 26 6.0
## 100 4.80 22.0 14193 Middle East NA 8 28 3.0
## 101 2.42 112.0 325 Africa 2153 43875 49 24.0
## 102 0.20 7.2 15974 OECD 3149 9025 13 11.0
## 103 0.05 20.7 2340 East Europe NA 27 12 13.0
## 104 0.80 17.0 3131 Latn America 2653 469 17 10.0
## 105 0.99 8.1 23474 OECD 3671 411907 15 9.0
## 106 2.13 53.0 1350 Middle East NA 2 30 7.0
## 107 2.16 28.0 2829 Latn America 2582 3511 26 5.0
## 108 1.78 46.0 230 Pacific/Asia 2233 107 27 8.0
## 109 2.80 85.0 573 Africa 2077 29734 46 18.0
## aids_rt log_gdp lg_aidsr b_to_d fertilty log_pop cropgrow lit_male lit_fema
## 1 0.0e+00 2.3 0.00 2.41 6.9 4.3 12 44 14
## 2 1.2e+01 3.5 1.63 2.22 2.8 4.5 9 96 95
## 3 5.4e-02 3.7 0.56 3.83 3.2 3.6 17 100 100
## 4 2.7e+01 4.2 1.93 1.88 1.9 4.3 6 100 100
## 5 1.4e+01 4.3 1.70 1.09 1.5 3.9 17 NA NA
## 6 NA 3.5 NA 3.29 2.8 3.9 18 100 100
## 7 2.2e+00 3.9 1.17 7.25 4.0 2.8 2 55 55
## 8 8.6e-04 2.3 0.24 3.18 4.7 5.1 67 47 22
## 9 1.4e+02 3.8 2.68 1.90 1.8 2.4 77 99 99
## 10 9.7e-02 3.8 0.63 1.18 1.9 4.0 29 100 100
## 11 1.6e+01 4.3 1.74 1.09 1.7 4.0 24 NA NA
## 12 1.1e+00 2.9 1.02 3.78 4.2 3.9 3 85 71
## 13 NA 3.5 NA 2.19 NA 3.7 20 NA NA
## 14 1.0e+02 3.4 2.52 4.00 5.1 3.1 2 32 16
## 15 3.1e+01 3.4 1.99 2.33 2.7 5.2 7 82 80
## 16 2.7e-01 3.6 0.77 1.08 1.8 3.9 34 NA NA
## 17 4.2e+01 2.6 2.11 2.61 6.9 4.0 10 28 9
## 18 1.2e+02 2.3 2.61 2.10 6.8 3.8 43 61 40
## 19 0.0e+00 2.4 0.00 2.81 5.8 4.0 16 48 22
## 20 2.3e+01 3.0 1.88 3.42 5.7 4.1 13 66 45
## 21 3.3e+01 4.3 2.01 1.75 1.8 4.5 5 NA NA
## 22 1.1e+02 2.7 2.57 2.10 5.4 3.5 3 33 15
## 23 5.9e+00 3.4 1.43 3.83 2.5 4.1 7 94 93
## 24 3.2e-03 2.6 0.32 3.00 1.8 6.1 10 87 68
## 25 1.3e+01 3.2 1.67 4.00 2.5 4.6 4 88 86
## 26 1.8e+01 3.3 1.78 6.50 3.1 3.5 6 93 93
## 27 1.1e+00 3.7 1.03 1.00 1.6 3.7 32 NA NA
## 28 2.2e+00 3.1 1.17 2.43 1.9 4.0 23 95 93
## 29 4.6e-01 3.9 0.86 1.17 1.8 4.0 NA NA NA
## 30 2.7e+01 4.3 1.94 1.00 1.7 3.7 61 NA NA
## 31 3.0e+01 3.0 1.98 4.17 2.8 3.9 23 85 82
## 32 3.4e+00 3.0 1.28 4.33 3.1 4.0 6 90 86
## 33 1.5e-01 2.9 0.69 3.22 3.8 4.8 3 63 34
## 34 9.6e+00 3.0 1.57 4.71 3.8 3.8 27 76 70
## 35 1.9e-01 3.8 0.72 1.17 2.0 3.2 22 100 100
## 36 2.3e+01 2.1 1.88 3.21 6.8 4.7 12 32 16
## 37 3.1e+00 4.2 1.25 1.30 1.8 3.7 8 NA NA
## 38 5.2e+01 4.3 2.20 1.40 1.8 4.8 32 NA NA
## 39 3.6e+01 3.6 2.05 2.00 4.0 3.1 1 74 48
## 40 2.5e+01 2.5 1.91 2.88 6.3 3.0 16 39 16
## 41 3.6e-02 3.7 0.52 1.78 2.2 3.7 NA 100 100
## 42 1.4e+01 4.2 1.69 1.00 1.5 4.9 34 NA NA
## 43 8.8e+00 3.9 1.55 1.00 1.5 4.0 23 98 89
## 44 4.8e+00 3.1 1.37 4.38 4.8 4.0 12 63 47
## 45 7.1e+01 2.6 2.35 2.11 5.9 3.8 20 59 47
## 46 6.2e+01 3.0 2.28 5.83 4.9 3.7 14 76 71
## 47 1.7e+00 4.2 1.11 2.17 1.4 3.8 7 90 64
## 48 1.4e+00 3.7 1.07 0.92 1.8 4.0 51 99 98
## 49 1.0e+01 4.2 1.60 2.29 2.1 2.4 1 NA NA
## 50 7.8e-02 2.4 0.60 2.90 4.5 6.0 55 64 39
## 51 2.5e-02 2.8 0.48 2.67 2.8 5.3 8 84 68
## 52 1.5e-01 3.2 0.68 5.25 6.3 4.8 8 64 43
## 53 1.3e-01 3.3 0.67 6.29 6.7 4.3 12 70 49
## 54 1.1e+01 4.1 1.61 1.56 2.0 3.6 14 NA NA
## 55 5.2e+00 4.1 1.39 3.00 2.8 3.7 17 95 89
## 56 3.8e+01 4.2 2.07 1.10 1.3 4.8 32 98 96
## 57 5.7e-01 4.3 0.89 1.57 1.6 5.1 13 NA NA
## 58 7.0e-01 3.1 0.93 7.80 5.6 3.6 4 89 70
## 59 1.1e+02 2.5 2.57 3.82 5.9 4.5 3 80 58
## 60 5.6e-01 3.8 0.89 14.00 4.0 3.3 0 77 67
## 61 3.0e-01 3.9 0.78 1.17 2.0 3.4 27 100 100
## 62 2.5e+00 3.2 1.20 3.86 3.4 3.6 21 88 73
## 63 6.6e+00 2.6 1.46 3.58 6.8 3.5 1 50 29
## 64 1.8e-01 3.8 0.71 5.62 6.4 3.7 2 75 50
## 65 1.3e-01 3.8 0.67 1.50 2.0 3.6 49 99 98
## 66 5.5e-01 3.5 0.89 5.80 3.5 4.3 3 86 70
## 67 2.0e+01 3.6 1.82 5.60 3.2 5.0 12 90 85
## 68 6.9e-01 3.0 0.93 4.83 3.8 4.5 18 61 38
## 69 0.0e+00 3.0 0.00 4.36 2.4 4.4 18 99 99
## 70 2.0e+01 4.2 1.82 1.44 1.6 4.2 26 NA NA
## 71 1.2e+01 4.2 1.65 2.00 2.0 3.5 2 NA NA
## 72 1.5e+00 2.7 1.09 5.00 4.3 3.6 9 57 57
## 73 9.6e-01 2.5 0.99 3.67 6.4 5.0 31 62 40
## 74 8.7e+00 4.2 1.54 1.30 2.0 3.6 3 NA NA
## 75 1.7e+00 3.9 1.12 8.00 6.5 3.3 2 NA NA
## 76 3.2e-02 2.6 0.50 4.20 6.4 5.1 26 47 21
## 77 2.5e+01 3.4 1.90 5.00 2.9 3.4 6 88 88
## 78 1.6e+00 3.2 1.10 7.33 4.3 3.7 20 92 88
## 79 4.7e+00 3.0 1.36 3.71 3.1 4.4 3 92 79
## 80 2.0e-01 2.9 0.72 3.86 3.4 4.8 26 90 90
## 81 5.2e-01 3.6 0.88 1.40 1.9 4.6 46 99 98
## 82 1.8e+01 4.0 1.79 1.20 1.5 4.0 32 89 82
## 83 1.2e+01 3.4 1.64 1.40 1.8 4.4 43 NA NA
## 84 9.1e-02 3.8 0.62 1.18 1.8 5.2 8 100 100
## 85 1.4e+02 2.5 2.68 2.33 8.2 3.9 29 64 37
## 86 4.3e-02 3.8 0.53 2.67 1.6 4.7 21 99 99
## 87 3.4e-01 3.8 0.81 6.33 6.7 4.3 1 73 48
## 88 1.1e+01 2.9 1.62 3.58 6.1 3.9 27 52 25
## 89 2.6e+00 4.2 1.21 2.67 1.9 3.5 4 93 84
## 90 1.3e-01 3.3 0.67 3.54 7.2 3.8 2 36 14
## 91 7.8e+00 3.5 1.51 4.25 4.4 4.6 10 NA NA
## 92 6.2e+01 4.1 2.28 1.22 1.4 4.6 31 97 93
## 93 1.1e+01 4.2 1.63 1.27 2.1 3.9 7 NA NA
## 94 5.2e+01 4.3 2.21 1.33 1.6 3.8 10 NA NA
## 95 1.9e-01 3.4 0.71 7.33 6.6 4.2 28 78 51
## 96 NA 3.8 NA NA NA 4.3 NA NA NA
## 97 1.3e+02 2.4 2.65 2.42 6.2 4.5 5 62 31
## 98 9.5e+00 3.3 1.57 3.17 2.1 4.8 34 96 90
## 99 2.1e-01 3.6 0.73 4.33 3.2 4.8 30 90 71
## 100 4.7e-01 4.2 0.86 9.33 4.5 3.4 0 70 63
## 101 2.2e+02 2.5 2.95 2.04 6.8 4.3 23 62 35
## 102 1.5e+01 4.2 1.73 1.18 1.8 4.8 29 NA NA
## 103 5.2e-02 3.4 0.55 0.92 1.8 4.7 56 100 100
## 104 1.5e+01 3.5 1.71 1.70 2.4 3.5 8 97 96
## 105 1.6e+02 4.4 2.75 1.67 2.1 5.4 20 97 97
## 106 9.0e-03 3.1 0.39 4.29 3.7 4.4 10 100 100
## 107 1.6e+01 3.5 1.75 5.20 3.0 4.3 3 90 87
## 108 1.5e-01 2.4 0.68 3.38 3.3 4.9 22 93 83
## 109 3.3e+02 2.8 3.18 2.56 6.7 4.0 7 81 65
## climate
## 1 arid
## 2 temperate
## 3 <NA>
## 4 arid
## 5 temperate
## 6 arid
## 7 arid
## 8 tropical
## 9 tropical
## 10 temperate
## 11 temperate
## 12 4
## 13 temperate
## 14 4
## 15 tropical
## 16 temperate
## 17 tropical
## 18 temperate
## 19 tropical
## 20 4
## 21 arctic / temp
## 22 tropical
## 23 temperate
## 24 temperate
## 25 tropical
## 26 tropical
## 27 mediterranean
## 28 tropical
## 29 temperate
## 30 temperate
## 31 tropical
## 32 tropical
## 33 desert
## 34 tropical
## 35 maritime
## 36 tropical
## 37 arctic / temp
## 38 temperate
## 39 tropical
## 40 tropical
## 41 mediterranean
## 42 temperate
## 43 temperate
## 44 tropical
## 45 tropical
## 46 4
## 47 tropical
## 48 temperate
## 49 temperate
## 50 mediterranean
## 51 tropical
## 52 arid / desert
## 53 desert
## 54 temperate
## 55 temperate
## 56 mediterranean
## 57 mediterranean
## 58 arid / desert
## 59 4
## 60 arid / desert
## 61 maritime
## 62 mediterranean
## 63 tropical
## 64 mediterranean
## 65 maritime
## 66 tropical
## 67 arid
## 68 mediterranean
## 69 temperate
## 70 temperate
## 71 temperate
## 72 tropical
## 73 tropical
## 74 temperate
## 75 desert
## 76 temperate
## 77 tropical
## 78 mediterranean
## 79 arid
## 80 tropical
## 81 temperate
## 82 maritime
## 83 temperate
## 84 arctic / temp
## 85 temperate
## 86 temperate
## 87 desert
## 88 tropical
## 89 tropical
## 90 desert
## 91 arid / desert
## 92 temperate
## 93 arctic / temp
## 94 temperate
## 95 desert
## 96 <NA>
## 97 mediterranean
## 98 tropical
## 99 temperate
## 100 desert
## 101 tropical
## 102 temperate
## 103 temperate
## 104 temperate
## 105 temperate
## 106 arid / desert
## 107 tropical
## 108 tropical
## 109 tropical2b.i
summary(breaks$breaks)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 14 28 45 46 57 962b.ii
cor(bpwide$bp_before,bpwide$bp_after)## [1] 0.16lm(bpwide$bp_before~bpwide$bp_after)##
## Call:
## lm(formula = bpwide$bp_before ~ bpwide$bp_after)
##
## Coefficients:
## (Intercept) bpwide$bp_after
## 137.102 0.128alternative
# Fit a linear regression model of bp_before in terms of bp_after
model <- lm(bp_before ~ bp_after, data = bpwide)
# Print the model summary
summary(model)##
## Call:
## lm(formula = bp_before ~ bp_after, data = bpwide)
##
## Residuals:
## Min 1Q Median 3Q Max
## -18.50 -9.13 -1.49 7.62 30.00
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 137.102 11.099 12.35 <2e-16 ***
## bp_after 0.128 0.073 1.75 0.083 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 11 on 118 degrees of freedom
## Multiple R-squared: 0.0253, Adjusted R-squared: 0.0171
## F-statistic: 3.07 on 1 and 118 DF, p-value: 0.08262b.iii
max(world95$density)## [1] 5494min(world95$density)## [1] 2.3world95$country[world95$density==5494]## [1] "Hong Kong "world95$country[world95$density==2.3]## [1] "Australia "3
3a
swiss## Fertility Agriculture Examination Education Catholic
## Courtelary 80 17.0 15 12 10.0
## Delemont 83 45.1 6 9 84.8
## Franches-Mnt 92 39.7 5 5 93.4
## Moutier 86 36.5 12 7 33.8
## Neuveville 77 43.5 17 15 5.2
## Porrentruy 76 35.3 9 7 90.6
## Broye 84 70.2 16 7 92.8
## Glane 92 67.8 14 8 97.2
## Gruyere 82 53.3 12 7 97.7
## Sarine 83 45.2 16 13 91.4
## Veveyse 87 64.5 14 6 98.6
## Aigle 64 62.0 21 12 8.5
## Aubonne 67 67.5 14 7 2.3
## Avenches 69 60.7 19 12 4.4
## Cossonay 62 69.3 22 5 2.8
## Echallens 68 72.6 18 2 24.2
## Grandson 72 34.0 17 8 3.3
## Lausanne 56 19.4 26 28 12.1
## La Vallee 54 15.2 31 20 2.1
## Lavaux 65 73.0 19 9 2.8
## Morges 66 59.8 22 10 5.2
## Moudon 65 55.1 14 3 4.5
## Nyone 57 50.9 22 12 15.1
## Orbe 57 54.1 20 6 4.2
## Oron 72 71.2 12 1 2.4
## Payerne 74 58.1 14 8 5.2
## Paysd'enhaut 72 63.5 6 3 2.6
## Rolle 60 60.8 16 10 7.7
## Vevey 58 26.8 25 19 18.5
## Yverdon 65 49.5 15 8 6.1
## Conthey 76 85.9 3 2 99.7
## Entremont 69 84.9 7 6 99.7
## Herens 77 89.7 5 2 100.0
## Martigwy 70 78.2 12 6 99.0
## Monthey 79 64.9 7 3 98.2
## St Maurice 65 75.9 9 9 99.1
## Sierre 92 84.6 3 3 99.5
## Sion 79 63.1 13 13 96.8
## Boudry 70 38.4 26 12 5.6
## La Chauxdfnd 66 7.7 29 11 13.8
## Le Locle 73 16.7 22 13 11.2
## Neuchatel 64 17.6 35 32 16.9
## Val de Ruz 78 37.6 15 7 5.0
## ValdeTravers 68 18.7 25 7 8.6
## V. De Geneve 35 1.2 37 53 42.3
## Rive Droite 45 46.6 16 29 50.4
## Rive Gauche 43 27.7 22 29 58.3
## Infant.Mortality
## Courtelary 22
## Delemont 22
## Franches-Mnt 20
## Moutier 20
## Neuveville 21
## Porrentruy 27
## Broye 24
## Glane 25
## Gruyere 21
## Sarine 24
## Veveyse 24
## Aigle 16
## Aubonne 19
## Avenches 23
## Cossonay 19
## Echallens 21
## Grandson 20
## Lausanne 20
## La Vallee 11
## Lavaux 20
## Morges 18
## Moudon 22
## Nyone 17
## Orbe 15
## Oron 21
## Payerne 24
## Paysd'enhaut 18
## Rolle 16
## Vevey 21
## Yverdon 22
## Conthey 15
## Entremont 20
## Herens 18
## Martigwy 19
## Monthey 20
## St Maurice 18
## Sierre 16
## Sion 18
## Boudry 20
## La Chauxdfnd 20
## Le Locle 19
## Neuchatel 23
## Val de Ruz 20
## ValdeTravers 20
## V. De Geneve 18
## Rive Droite 18
## Rive Gauche 19boxplot(swiss$Education)
boxplot(swiss$Infant.Mortality)
3b
set.seed(235)
samp<-swiss[sample(x = ncol(swiss),size = 5,replace = F),]
samp## Fertility Agriculture Examination Education Catholic
## Porrentruy 76 35 9 7 90.6
## Neuveville 77 44 17 15 5.2
## Courtelary 80 17 15 12 10.0
## Delemont 83 45 6 9 84.8
## Franches-Mnt 92 40 5 5 93.4
## Infant.Mortality
## Porrentruy 27
## Neuveville 21
## Courtelary 22
## Delemont 22
## Franches-Mnt 203c
sub1<-swiss[swiss$Education>=20 &swiss$Agriculture<40,]
sub1## Fertility Agriculture Examination Education Catholic
## Lausanne 56 19.4 26 28 12.1
## La Vallee 54 15.2 31 20 2.1
## Neuchatel 64 17.6 35 32 16.9
## V. De Geneve 35 1.2 37 53 42.3
## Rive Gauche 43 27.7 22 29 58.3
## Infant.Mortality
## Lausanne 20
## La Vallee 11
## Neuchatel 23
## V. De Geneve 18
## Rive Gauche 193d
4
4a
4b
pdf<-function(x,p){
return((1-p)^(x-1)*p)
}
x<-c(3,5,7)
pdf(x,0.4)## [1] 0.144 0.052 0.019cdf<-function(x,p){
return(1-(1-p)^x)
}
cdf(5,.4)## [1] 0.925
5a
# Load airquality dataset
data(airquality)
# Create boxplots for Temp against Month
boxplot(Temp ~ Month, data = airquality,
xlab = "Month", ylab = "Temperature",
main = "Temperature vs Month Boxplot")
alternative
airquality## Ozone Solar.R Wind Temp Month Day
## 1 41 190 7.4 67 5 1
## 2 36 118 8.0 72 5 2
## 3 12 149 12.6 74 5 3
## 4 18 313 11.5 62 5 4
## 5 NA NA 14.3 56 5 5
## 6 28 NA 14.9 66 5 6
## 7 23 299 8.6 65 5 7
## 8 19 99 13.8 59 5 8
## 9 8 19 20.1 61 5 9
## 10 NA 194 8.6 69 5 10
## 11 7 NA 6.9 74 5 11
## 12 16 256 9.7 69 5 12
## 13 11 290 9.2 66 5 13
## 14 14 274 10.9 68 5 14
## 15 18 65 13.2 58 5 15
## 16 14 334 11.5 64 5 16
## 17 34 307 12.0 66 5 17
## 18 6 78 18.4 57 5 18
## 19 30 322 11.5 68 5 19
## 20 11 44 9.7 62 5 20
## 21 1 8 9.7 59 5 21
## 22 11 320 16.6 73 5 22
## 23 4 25 9.7 61 5 23
## 24 32 92 12.0 61 5 24
## 25 NA 66 16.6 57 5 25
## 26 NA 266 14.9 58 5 26
## 27 NA NA 8.0 57 5 27
## 28 23 13 12.0 67 5 28
## 29 45 252 14.9 81 5 29
## 30 115 223 5.7 79 5 30
## 31 37 279 7.4 76 5 31
## 32 NA 286 8.6 78 6 1
## 33 NA 287 9.7 74 6 2
## 34 NA 242 16.1 67 6 3
## 35 NA 186 9.2 84 6 4
## 36 NA 220 8.6 85 6 5
## 37 NA 264 14.3 79 6 6
## 38 29 127 9.7 82 6 7
## 39 NA 273 6.9 87 6 8
## 40 71 291 13.8 90 6 9
## 41 39 323 11.5 87 6 10
## 42 NA 259 10.9 93 6 11
## 43 NA 250 9.2 92 6 12
## 44 23 148 8.0 82 6 13
## 45 NA 332 13.8 80 6 14
## 46 NA 322 11.5 79 6 15
## 47 21 191 14.9 77 6 16
## 48 37 284 20.7 72 6 17
## 49 20 37 9.2 65 6 18
## 50 12 120 11.5 73 6 19
## 51 13 137 10.3 76 6 20
## 52 NA 150 6.3 77 6 21
## 53 NA 59 1.7 76 6 22
## 54 NA 91 4.6 76 6 23
## 55 NA 250 6.3 76 6 24
## 56 NA 135 8.0 75 6 25
## 57 NA 127 8.0 78 6 26
## 58 NA 47 10.3 73 6 27
## 59 NA 98 11.5 80 6 28
## 60 NA 31 14.9 77 6 29
## 61 NA 138 8.0 83 6 30
## 62 135 269 4.1 84 7 1
## 63 49 248 9.2 85 7 2
## 64 32 236 9.2 81 7 3
## 65 NA 101 10.9 84 7 4
## 66 64 175 4.6 83 7 5
## 67 40 314 10.9 83 7 6
## 68 77 276 5.1 88 7 7
## 69 97 267 6.3 92 7 8
## 70 97 272 5.7 92 7 9
## 71 85 175 7.4 89 7 10
## 72 NA 139 8.6 82 7 11
## 73 10 264 14.3 73 7 12
## 74 27 175 14.9 81 7 13
## 75 NA 291 14.9 91 7 14
## 76 7 48 14.3 80 7 15
## 77 48 260 6.9 81 7 16
## 78 35 274 10.3 82 7 17
## 79 61 285 6.3 84 7 18
## 80 79 187 5.1 87 7 19
## 81 63 220 11.5 85 7 20
## 82 16 7 6.9 74 7 21
## 83 NA 258 9.7 81 7 22
## 84 NA 295 11.5 82 7 23
## 85 80 294 8.6 86 7 24
## 86 108 223 8.0 85 7 25
## 87 20 81 8.6 82 7 26
## 88 52 82 12.0 86 7 27
## 89 82 213 7.4 88 7 28
## 90 50 275 7.4 86 7 29
## 91 64 253 7.4 83 7 30
## 92 59 254 9.2 81 7 31
## 93 39 83 6.9 81 8 1
## 94 9 24 13.8 81 8 2
## 95 16 77 7.4 82 8 3
## 96 78 NA 6.9 86 8 4
## 97 35 NA 7.4 85 8 5
## 98 66 NA 4.6 87 8 6
## 99 122 255 4.0 89 8 7
## 100 89 229 10.3 90 8 8
## 101 110 207 8.0 90 8 9
## 102 NA 222 8.6 92 8 10
## 103 NA 137 11.5 86 8 11
## 104 44 192 11.5 86 8 12
## 105 28 273 11.5 82 8 13
## 106 65 157 9.7 80 8 14
## 107 NA 64 11.5 79 8 15
## 108 22 71 10.3 77 8 16
## 109 59 51 6.3 79 8 17
## 110 23 115 7.4 76 8 18
## 111 31 244 10.9 78 8 19
## 112 44 190 10.3 78 8 20
## 113 21 259 15.5 77 8 21
## 114 9 36 14.3 72 8 22
## 115 NA 255 12.6 75 8 23
## 116 45 212 9.7 79 8 24
## 117 168 238 3.4 81 8 25
## 118 73 215 8.0 86 8 26
## 119 NA 153 5.7 88 8 27
## 120 76 203 9.7 97 8 28
## 121 118 225 2.3 94 8 29
## 122 84 237 6.3 96 8 30
## 123 85 188 6.3 94 8 31
## 124 96 167 6.9 91 9 1
## 125 78 197 5.1 92 9 2
## 126 73 183 2.8 93 9 3
## 127 91 189 4.6 93 9 4
## 128 47 95 7.4 87 9 5
## 129 32 92 15.5 84 9 6
## 130 20 252 10.9 80 9 7
## 131 23 220 10.3 78 9 8
## 132 21 230 10.9 75 9 9
## 133 24 259 9.7 73 9 10
## 134 44 236 14.9 81 9 11
## 135 21 259 15.5 76 9 12
## 136 28 238 6.3 77 9 13
## 137 9 24 10.9 71 9 14
## 138 13 112 11.5 71 9 15
## 139 46 237 6.9 78 9 16
## 140 18 224 13.8 67 9 17
## 141 13 27 10.3 76 9 18
## 142 24 238 10.3 68 9 19
## 143 16 201 8.0 82 9 20
## 144 13 238 12.6 64 9 21
## 145 23 14 9.2 71 9 22
## 146 36 139 10.3 81 9 23
## 147 7 49 10.3 69 9 24
## 148 14 20 16.6 63 9 25
## 149 30 193 6.9 70 9 26
## 150 NA 145 13.2 77 9 27
## 151 14 191 14.3 75 9 28
## 152 18 131 8.0 76 9 29
## 153 20 223 11.5 68 9 30library(ggplot2)
ggplot()+
geom_boxplot(mapping = aes(x = factor(Month),y = Temp),data = airquality,)
5b
1st way
morley## Expt Run Speed
## 001 1 1 850
## 002 1 2 740
## 003 1 3 900
## 004 1 4 1070
## 005 1 5 930
## 006 1 6 850
## 007 1 7 950
## 008 1 8 980
## 009 1 9 980
## 010 1 10 880
## 011 1 11 1000
## 012 1 12 980
## 013 1 13 930
## 014 1 14 650
## 015 1 15 760
## 016 1 16 810
## 017 1 17 1000
## 018 1 18 1000
## 019 1 19 960
## 020 1 20 960
## 021 2 1 960
## 022 2 2 940
## 023 2 3 960
## 024 2 4 940
## 025 2 5 880
## 026 2 6 800
## 027 2 7 850
## 028 2 8 880
## 029 2 9 900
## 030 2 10 840
## 031 2 11 830
## 032 2 12 790
## 033 2 13 810
## 034 2 14 880
## 035 2 15 880
## 036 2 16 830
## 037 2 17 800
## 038 2 18 790
## 039 2 19 760
## 040 2 20 800
## 041 3 1 880
## 042 3 2 880
## 043 3 3 880
## 044 3 4 860
## 045 3 5 720
## 046 3 6 720
## 047 3 7 620
## 048 3 8 860
## 049 3 9 970
## 050 3 10 950
## 051 3 11 880
## 052 3 12 910
## 053 3 13 850
## 054 3 14 870
## 055 3 15 840
## 056 3 16 840
## 057 3 17 850
## 058 3 18 840
## 059 3 19 840
## 060 3 20 840
## 061 4 1 890
## 062 4 2 810
## 063 4 3 810
## 064 4 4 820
## 065 4 5 800
## 066 4 6 770
## 067 4 7 760
## 068 4 8 740
## 069 4 9 750
## 070 4 10 760
## 071 4 11 910
## 072 4 12 920
## 073 4 13 890
## 074 4 14 860
## 075 4 15 880
## 076 4 16 720
## 077 4 17 840
## 078 4 18 850
## 079 4 19 850
## 080 4 20 780
## 081 5 1 890
## 082 5 2 840
## 083 5 3 780
## 084 5 4 810
## 085 5 5 760
## 086 5 6 810
## 087 5 7 790
## 088 5 8 810
## 089 5 9 820
## 090 5 10 850
## 091 5 11 870
## 092 5 12 870
## 093 5 13 810
## 094 5 14 740
## 095 5 15 810
## 096 5 16 940
## 097 5 17 950
## 098 5 18 800
## 099 5 19 810
## 100 5 20 870library(tidyverse)
ggplot()+
geom_point(mapping = aes(x = factor(Run),y = factor(Speed),color= factor(Expt) ),data = morley)
2nd way(eassy)
ggplot(data = morley,mapping = aes(Run, Speed))+
geom_point()
3rd way
# Scatter plot of Speed against Run
ggplot(morley, aes(Run, Speed)) +
geom_point() +
labs(x = "Run", y = "Speed (km/sec)") +
ggtitle("Speed vs Run")
1st way (eassy)
ggplot(data = morley,mapping = aes(Run, Speed))+
geom_point()+
geom_smooth()## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
2nd way
# Scatter plot of Speed against Run with trend line
ggplot(morley, aes(Run, Speed)) +
geom_point() +
geom_smooth( se = FALSE, color = "red") +
labs(x = "Run", y = "Speed (km/sec)") +
ggtitle("Speed vs Run")## `geom_smooth()` using method = 'loess' and formula = 'y ~ x'
# Box plot of Speed against Expt
ggplot(morley, aes(factor(Expt), Speed)) +
geom_boxplot() +
labs(x = "Experiment", y = "Speed (km/sec)") +
ggtitle("Speed vs Experiment")