RPrin_Mar20

GGPLOT

library(ggplot2)
## Warning: package 'ggplot2' was built under R version 4.0.4
cars <- mtcars
str(cars)
## 'data.frame':    32 obs. of  11 variables:
##  $ mpg : num  21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
##  $ cyl : num  6 6 4 6 8 6 8 4 4 6 ...
##  $ disp: num  160 160 108 258 360 ...
##  $ hp  : num  110 110 93 110 175 105 245 62 95 123 ...
##  $ drat: num  3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
##  $ wt  : num  2.62 2.88 2.32 3.21 3.44 ...
##  $ qsec: num  16.5 17 18.6 19.4 17 ...
##  $ vs  : num  0 0 1 1 0 1 0 1 1 1 ...
##  $ am  : num  1 1 1 0 0 0 0 0 0 0 ...
##  $ gear: num  4 4 4 3 3 3 3 4 4 4 ...
##  $ carb: num  4 4 1 1 2 1 4 2 2 4 ...
head(cars)
##                    mpg cyl disp  hp drat    wt  qsec vs am gear carb
## Mazda RX4         21.0   6  160 110 3.90 2.620 16.46  0  1    4    4
## Mazda RX4 Wag     21.0   6  160 110 3.90 2.875 17.02  0  1    4    4
## Datsun 710        22.8   4  108  93 3.85 2.320 18.61  1  1    4    1
## Hornet 4 Drive    21.4   6  258 110 3.08 3.215 19.44  1  0    3    1
## Hornet Sportabout 18.7   8  360 175 3.15 3.440 17.02  0  0    3    2
## Valiant           18.1   6  225 105 2.76 3.460 20.22  1  0    3    1
p <- ggplot(data= cars,
aes(x= as.factor(am), y= mpg, col= as.factor(am)))
p

p + geom_boxplot()

p <- ggplot(data= cars,
aes(x= as.factor(am), y= mpg))
p + geom_boxplot()

p <- ggplot(data= cars,
aes(x= as.factor(am), y= drat))
p + geom_boxplot()

p <- ggplot(data= cars,
aes(x= as.factor(am), y= hp))
p + geom_boxplot()

ggplot(data= cars, aes(x= as.factor(am), y= hp)) + geom_boxplot()

ggplot(data= cars, aes(x= as.factor(am), y= mpg)) + geom_boxplot()

ggplot(data=cars, aes(x= as.factor(am), y=mpg)) + geom_boxplot() + geom_point(position = position_jitter(width= 0.1))

ggplot(data=cars, aes(x= as.factor(am), y=mpg)) + geom_boxplot() + geom_point()

ggplot(data=cars, aes(x= as.factor(am), y=mpg)) + geom_boxplot() + geom_point(position = position_jitter(width = 0.3))

ggplot(data=cars, aes(x= as.factor(am), y=mpg)) + geom_boxplot() + geom_point(position = position_jitter(width = 0.5))

ggplot(data=cars, aes(x= as.factor(am), y=mpg)) + geom_boxplot() + geom_point(position = position_jitter(width = 0.2))

ggplot(data=cars, aes(x= as.factor(am), y=mpg)) + geom_boxplot() + geom_point(position = position_jitter(width = 0.15))

ggplot(data=cars, aes(x= as.factor(am), y=mpg)) + geom_point(position = position_jitter(width = 0.15))

ggplot(data=cars, aes(x= as.factor(am), y=mpg)) + geom_point(position = position_jitter(width = 0.1))

p <- ggplot(data=cars, aes(x= as.factor(am), y=mpg))
p + geom_point(position = position_jitter(width = 0.15))

p + geom_point(position = position_jitter(width = 0.15)) + geom_boxplot()

p + geom_boxplot() + geom_point(position = position_jitter(width = 0.15))

cars
##                      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    2
rownames(cars)
##  [1] "Mazda RX4"           "Mazda RX4 Wag"       "Datsun 710"         
##  [4] "Hornet 4 Drive"      "Hornet Sportabout"   "Valiant"            
##  [7] "Duster 360"          "Merc 240D"           "Merc 230"           
## [10] "Merc 280"            "Merc 280C"           "Merc 450SE"         
## [13] "Merc 450SL"          "Merc 450SLC"         "Cadillac Fleetwood" 
## [16] "Lincoln Continental" "Chrysler Imperial"   "Fiat 128"           
## [19] "Honda Civic"         "Toyota Corolla"      "Toyota Corona"      
## [22] "Dodge Challenger"    "AMC Javelin"         "Camaro Z28"         
## [25] "Pontiac Firebird"    "Fiat X1-9"           "Porsche 914-2"      
## [28] "Lotus Europa"        "Ford Pantera L"      "Ferrari Dino"       
## [31] "Maserati Bora"       "Volvo 142E"
### Bars
cars$name <- rownames(cars)
head(cars)
##                    mpg cyl disp  hp drat    wt  qsec vs am gear carb
## Mazda RX4         21.0   6  160 110 3.90 2.620 16.46  0  1    4    4
## Mazda RX4 Wag     21.0   6  160 110 3.90 2.875 17.02  0  1    4    4
## Datsun 710        22.8   4  108  93 3.85 2.320 18.61  1  1    4    1
## Hornet 4 Drive    21.4   6  258 110 3.08 3.215 19.44  1  0    3    1
## Hornet Sportabout 18.7   8  360 175 3.15 3.440 17.02  0  0    3    2
## Valiant           18.1   6  225 105 2.76 3.460 20.22  1  0    3    1
##                                name
## Mazda RX4                 Mazda RX4
## Mazda RX4 Wag         Mazda RX4 Wag
## Datsun 710               Datsun 710
## Hornet 4 Drive       Hornet 4 Drive
## Hornet Sportabout Hornet Sportabout
## Valiant                     Valiant
str(cars)
## 'data.frame':    32 obs. of  12 variables:
##  $ mpg : num  21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
##  $ cyl : num  6 6 4 6 8 6 8 4 4 6 ...
##  $ disp: num  160 160 108 258 360 ...
##  $ hp  : num  110 110 93 110 175 105 245 62 95 123 ...
##  $ drat: num  3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
##  $ wt  : num  2.62 2.88 2.32 3.21 3.44 ...
##  $ qsec: num  16.5 17 18.6 19.4 17 ...
##  $ vs  : num  0 0 1 1 0 1 0 1 1 1 ...
##  $ am  : num  1 1 1 0 0 0 0 0 0 0 ...
##  $ gear: num  4 4 4 3 3 3 3 4 4 4 ...
##  $ carb: num  4 4 1 1 2 1 4 2 2 4 ...
##  $ name: chr  "Mazda RX4" "Mazda RX4 Wag" "Datsun 710" "Hornet 4 Drive" ...
cars$cyl.F <- as.factor(cars$cyl)
str(cars)
## 'data.frame':    32 obs. of  13 variables:
##  $ mpg  : num  21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
##  $ cyl  : num  6 6 4 6 8 6 8 4 4 6 ...
##  $ disp : num  160 160 108 258 360 ...
##  $ hp   : num  110 110 93 110 175 105 245 62 95 123 ...
##  $ drat : num  3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
##  $ wt   : num  2.62 2.88 2.32 3.21 3.44 ...
##  $ qsec : num  16.5 17 18.6 19.4 17 ...
##  $ vs   : num  0 0 1 1 0 1 0 1 1 1 ...
##  $ am   : num  1 1 1 0 0 0 0 0 0 0 ...
##  $ gear : num  4 4 4 3 3 3 3 4 4 4 ...
##  $ carb : num  4 4 1 1 2 1 4 2 2 4 ...
##  $ name : chr  "Mazda RX4" "Mazda RX4 Wag" "Datsun 710" "Hornet 4 Drive" ...
##  $ cyl.F: Factor w/ 3 levels "4","6","8": 2 2 1 2 3 2 3 1 1 2 ...
p <- ggplot(data=cars,
aes(x= as.factor(am)))
p

p + geom_bar()

p <- ggplot(data= cars,
aes(x=name))
p

p + geom_bar()

p + geom_bar() + guides(x= guide_axis(angle= 80))

p + geom_bar() + guides(x= guide_axis(angle= 90))

p + geom_bar() + guides(x= guide_axis(angle= 70))

p + geom_bar() + guides(x= guide_axis(angle= 90))

p + geom_bar() + guides(x= guide_axis(angle= 90))

p + geom_bar() + guides(x= guide_axis(angle= 0))

ggplot(data=cars, aes(x=cyl.F)) + geom_bar() + guides(x= guide_axis(angle= 90))

ggplot(data=cars, aes(x=cyl.F)) + geom_bar() + guides(x= guide_axis(angle= 0))

p <- ggplot(data= cars,
aes(x=cyl.F, y= hp, col= as.factor(am)))
p

p + geom_point()

p + geom_point() + geom_boxplot()

p + geom_point(position = position_jitter(width = 0.1)) + geom_boxplot()

p + geom_boxplot() + geom_point(position = position_jitter(width = 0.1))

p <- ggplot(data= cars,
aes(x=wt, y= drat, col= as.factor(am)))
p + geom_point()

p <- ggplot(data= cars,
aes(x=wt, y= drat, col= cyl.F) )
p + geom_point()

p <- ggplot(data= cars,
aes(x=wt, y= drat) )
p + geom_point()

p + geom_point() + geom_smooth()
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

p + geom_point() + geom_smooth(method= "lm")
## `geom_smooth()` using formula 'y ~ x'

p <- ggplot(data= cars,
aes(x=wt, y= drat, col= as.factor(am)) )
p + geom_point()

p + geom_point() + geom_smooth(method= "lm")
## `geom_smooth()` using formula 'y ~ x'

p <- ggplot(data= cars,
aes(x=wt, y= drat, col= cyl.F )
)
p + geom_point() + geom_smooth(method= "lm")
## `geom_smooth()` using formula 'y ~ x'

p <- ggplot(data= cars,
aes(x=wt, y= drat, col= as.factor(am) ))
p + geom_point() + geom_smooth(method= "lm")
## `geom_smooth()` using formula 'y ~ x'

### plots con base de datos de 'cancer'
#1. y= remission ~  x=White blood cells
###  white blood cells ~ Remission ??
library(googlesheets4)
ss = "https://docs.google.com/spreadsheets/d/1KjHM67cVFQ9iMXwJpNvkDuJqEc1Sw5u8CCCZUl5RV1E/edit?usp=sharing"
hoja="cancer"
rango = "A2:AA8527"
cancer <- read_sheet(ss,
sheet= hoja,
range= rango,
col_names = TRUE,
col_types = NULL,
na= "NA")
## Suitable tokens found in the cache, associated with these emails:
##   * fvillatorop@miumg.edu.gt
##   * msc.fvilla@digi.usac.edu.gt
## The first will be used.
## Using an auto-discovered, cached token.
## To suppress this message, modify your code or options to clearly consent to the use of a cached token.
## See gargle's "Non-interactive auth" vignette for more details:
## https://gargle.r-lib.org/articles/non-interactive-auth.html
## The googlesheets4 package is using a cached token for fvillatorop@miumg.edu.gt.
## Reading from "Remission"
## Range "'cancer'!A2:AA8527"
str(cancer)
## tibble [8,525 x 27] (S3: tbl_df/tbl/data.frame)
##  $ remission   : num [1:8525] 0 0 0 0 0 0 0 0 0 0 ...
##  $ ntumors     : num [1:8525] 0 0 0 0 0 0 0 0 2 0 ...
##  $ tumorsize   : num [1:8525] 68 64.7 51.6 86.4 53.4 ...
##  $ co2         : num [1:8525] 1.53 1.68 1.53 1.45 1.57 ...
##  $ pain        : num [1:8525] 4 2 6 3 3 4 3 3 4 5 ...
##  $ wound       : num [1:8525] 4 3 3 3 4 5 4 3 4 4 ...
##  $ mobility    : num [1:8525] 2 2 2 2 2 2 2 3 3 3 ...
##  $ nmorphine   : num [1:8525] 0 0 0 0 0 0 0 0 0 0 ...
##  $ lungcapacity: num [1:8525] 0.801 0.326 0.565 0.848 0.886 ...
##  $ Age         : num [1:8525] 65 53.9 53.3 41.4 46.8 ...
##  $ Married     : num [1:8525] 0 0 1 0 0 1 1 0 1 0 ...
##  $ FamilyHx    : chr [1:8525] "no" "no" "no" "no" ...
##  $ SmokingHx   : chr [1:8525] "a.former" "a.former" "never" "a.former" ...
##  $ Sex         : chr [1:8525] "male" "female" "female" "male" ...
##  $ CancerStage : chr [1:8525] "II" "II" "II" "I" ...
##  $ LengthofStay: num [1:8525] 6 6 5 5 6 5 4 5 6 7 ...
##  $ WBC         : num [1:8525] 6088 6700 6043 7163 6443 ...
##  $ RBC         : num [1:8525] 4.87 4.68 5.01 5.27 4.98 ...
##  $ BMI         : num [1:8525] 24.1 29.4 29.5 21.6 29.8 ...
##  $ IL6         : num [1:8525] 3.7 2.63 13.9 3.01 3.89 ...
##  $ CRP         : num [1:8525] 8.086 0.803 4.034 2.126 1.349 ...
##  $ DID         : num [1:8525] 1 1 1 1 1 1 1 1 1 1 ...
##  $ Experience  : num [1:8525] 25 25 25 25 25 25 25 25 25 25 ...
##  $ School      : chr [1:8525] "average" "average" "average" "average" ...
##  $ Lawsuits    : num [1:8525] 3 3 3 3 3 3 3 3 3 3 ...
##  $ HID         : num [1:8525] 1 1 1 1 1 1 1 1 1 1 ...
##  $ Medicaid    : num [1:8525] 0.606 0.606 0.606 0.606 0.606 ...
p <- ggplot(data=cancer,
aes(x=as.factor(remission),
y=WBC,
col=as.factor(remission)))
p

p + geom_boxplot()

p + geom_point(position = position_jitter(width = 0.3))

p + geom_point(position = position_jitter(width = 0.6))

p + geom_point(position = position_jitter(width = 0.4))

p + geom_violin() + geom_point(position = position_jitter(width = 0.4))

p + geom_point(position = position_jitter(width = 0.4))+ geom_violin()

p + geom_point(position = position_jitter(width = 0.4))

p + geom_point(position = position_jitter(width = 0.4)) + geom_violin()

p + geom_point(position = position_jitter(width = 0.3)) + geom_violin()

p <- ggplot(data=cancer,
aes(x= as.factor(CancerStage),
y= WBC,
col=as.factor(remission)))
p

p + geom_point(position = position_jitter(width = 0.3)) + geom_violin()

p + geom_point(position = position_jitter(width = 0.1)) + geom_violin()

p <- ggplot(data=cancer,
aes(x= as.factor(CancerStage),
y= WBC))
p + geom_point(position = position_jitter(width = 0.1)) + geom_violin()

p + geom_point(position = position_jitter(width = 0.1)) + geom_boxplot()

p + geom_point(position = position_jitter(width = 0.1)) + geom_violin()

p <- ggplot(data=cancer,
aes( x= BMI,
y= WBC))
p + geom_point()

p + geom_point() + geom_smooth()
## `geom_smooth()` using method = 'gam' and formula 'y ~ s(x, bs = "cs")'

p <- ggplot(data=cancer,
aes( x= BMI,
y= remission))
p + geom_point()

p <- ggplot(data=cancer,
aes( x= as.factor(remission),
y= BMI))
p + geom_boxplot()

p <- ggplot(data=cancer,
aes( x= as.factor(remission),
y= BMI))
p + geom_boxplot()

p + geom_boxplot() + geom_point(position = position_jitter(width= 0.2))

p  + geom_point(position = position_jitter(width= 0.2))

p  + geom_point(position = position_jitter(width= 0.2)) + geom_violin()