library(datasets)
library(dplyr)
## Warning: package 'dplyr' was built under R version 3.3.2
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
glimpse(mtcars)
## Observations: 32
## Variables: 11
## $ mpg <dbl> 21.0, 21.0, 22.8, 21.4, 18.7, 18.1, 14.3, 24.4, 22.8, 19....
## $ cyl <dbl> 6, 6, 4, 6, 8, 6, 8, 4, 4, 6, 6, 8, 8, 8, 8, 8, 8, 4, 4, ...
## $ disp <dbl> 160.0, 160.0, 108.0, 258.0, 360.0, 225.0, 360.0, 146.7, 1...
## $ hp <dbl> 110, 110, 93, 110, 175, 105, 245, 62, 95, 123, 123, 180, ...
## $ drat <dbl> 3.90, 3.90, 3.85, 3.08, 3.15, 2.76, 3.21, 3.69, 3.92, 3.9...
## $ wt <dbl> 2.620, 2.875, 2.320, 3.215, 3.440, 3.460, 3.570, 3.190, 3...
## $ qsec <dbl> 16.46, 17.02, 18.61, 19.44, 17.02, 20.22, 15.84, 20.00, 2...
## $ vs <dbl> 0, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, ...
## $ am <dbl> 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, ...
## $ gear <dbl> 4, 4, 4, 3, 3, 3, 3, 4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 4, 4, ...
## $ carb <dbl> 4, 4, 1, 1, 2, 1, 4, 2, 2, 4, 4, 3, 3, 3, 4, 4, 4, 1, 2, ...
help(mtcars)
?mtcars
data(mtcars)
head(mtcars)
## 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
tail(mtcars)
## mpg cyl disp hp drat wt qsec vs am gear carb
## Porsche 914-2 26.0 4 120.3 91 4.43 2.140 16.7 0 1 5 2
## Lotus Europa 30.4 4 95.1 113 3.77 1.513 16.9 1 1 5 2
## Ford Pantera L 15.8 8 351.0 264 4.22 3.170 14.5 0 1 5 4
## Ferrari Dino 19.7 6 145.0 175 3.62 2.770 15.5 0 1 5 6
## Maserati Bora 15.0 8 301.0 335 3.54 3.570 14.6 0 1 5 8
## Volvo 142E 21.4 4 121.0 109 4.11 2.780 18.6 1 1 4 2
str(mtcars)
## '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 ...
summary(mtcars)
## mpg cyl disp hp
## Min. :10.40 Min. :4.000 Min. : 71.1 Min. : 52.0
## 1st Qu.:15.43 1st Qu.:4.000 1st Qu.:120.8 1st Qu.: 96.5
## Median :19.20 Median :6.000 Median :196.3 Median :123.0
## Mean :20.09 Mean :6.188 Mean :230.7 Mean :146.7
## 3rd Qu.:22.80 3rd Qu.:8.000 3rd Qu.:326.0 3rd Qu.:180.0
## Max. :33.90 Max. :8.000 Max. :472.0 Max. :335.0
## drat wt qsec vs
## Min. :2.760 Min. :1.513 Min. :14.50 Min. :0.0000
## 1st Qu.:3.080 1st Qu.:2.581 1st Qu.:16.89 1st Qu.:0.0000
## Median :3.695 Median :3.325 Median :17.71 Median :0.0000
## Mean :3.597 Mean :3.217 Mean :17.85 Mean :0.4375
## 3rd Qu.:3.920 3rd Qu.:3.610 3rd Qu.:18.90 3rd Qu.:1.0000
## Max. :4.930 Max. :5.424 Max. :22.90 Max. :1.0000
## am gear carb
## Min. :0.0000 Min. :3.000 Min. :1.000
## 1st Qu.:0.0000 1st Qu.:3.000 1st Qu.:2.000
## Median :0.0000 Median :4.000 Median :2.000
## Mean :0.4062 Mean :3.688 Mean :2.812
## 3rd Qu.:1.0000 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :1.0000 Max. :5.000 Max. :8.000
mtcars$mpg
## [1] 21.0 21.0 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 17.8 16.4 17.3 15.2
## [15] 10.4 10.4 14.7 32.4 30.4 33.9 21.5 15.5 15.2 13.3 19.2 27.3 26.0 30.4
## [29] 15.8 19.7 15.0 21.4
stem(mtcars$mpg)
##
## The decimal point is at the |
##
## 10 | 44
## 12 | 3
## 14 | 3702258
## 16 | 438
## 18 | 17227
## 20 | 00445
## 22 | 88
## 24 | 4
## 26 | 03
## 28 |
## 30 | 44
## 32 | 49
fivenum(mtcars$mpg)
## [1] 10.40 15.35 19.20 22.80 33.90
quantile(mtcars$mpg)
## 0% 25% 50% 75% 100%
## 10.400 15.425 19.200 22.800 33.900
help(esoph)
?esoph
summary(mtcars)
## mpg cyl disp hp
## Min. :10.40 Min. :4.000 Min. : 71.1 Min. : 52.0
## 1st Qu.:15.43 1st Qu.:4.000 1st Qu.:120.8 1st Qu.: 96.5
## Median :19.20 Median :6.000 Median :196.3 Median :123.0
## Mean :20.09 Mean :6.188 Mean :230.7 Mean :146.7
## 3rd Qu.:22.80 3rd Qu.:8.000 3rd Qu.:326.0 3rd Qu.:180.0
## Max. :33.90 Max. :8.000 Max. :472.0 Max. :335.0
## drat wt qsec vs
## Min. :2.760 Min. :1.513 Min. :14.50 Min. :0.0000
## 1st Qu.:3.080 1st Qu.:2.581 1st Qu.:16.89 1st Qu.:0.0000
## Median :3.695 Median :3.325 Median :17.71 Median :0.0000
## Mean :3.597 Mean :3.217 Mean :17.85 Mean :0.4375
## 3rd Qu.:3.920 3rd Qu.:3.610 3rd Qu.:18.90 3rd Qu.:1.0000
## Max. :4.930 Max. :5.424 Max. :22.90 Max. :1.0000
## am gear carb
## Min. :0.0000 Min. :3.000 Min. :1.000
## 1st Qu.:0.0000 1st Qu.:3.000 1st Qu.:2.000
## Median :0.0000 Median :4.000 Median :2.000
## Mean :0.4062 Mean :3.688 Mean :2.812
## 3rd Qu.:1.0000 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :1.0000 Max. :5.000 Max. :8.000
str(mtcars)
## '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 ...
summary(mtcars$mpg)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 10.40 15.42 19.20 20.09 22.80 33.90
summary(mtcars$cyl)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 4.000 4.000 6.000 6.188 8.000 8.000
summary(mtcars$disp)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 71.1 120.8 196.3 230.7 326.0 472.0
summary(mtcars$mpg,mtcars$cyl,mtcars$disp)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 10.40 15.42 19.20 20.09 22.80 33.90
###esoph table
help(esoph)
esoph_df <-tbl_df(esoph)
e.freq <- table(esoph$agegp, esoph$alcgp, esoph$tobgp)
e.freq
## , , = 0-9g/day
##
##
## 0-39g/day 40-79 80-119 120+
## 25-34 1 1 1 1
## 35-44 1 1 1 1
## 45-54 1 1 1 1
## 55-64 1 1 1 1
## 65-74 1 1 1 1
## 75+ 1 1 1 1
##
## , , = 10-19
##
##
## 0-39g/day 40-79 80-119 120+
## 25-34 1 1 1 1
## 35-44 1 1 1 1
## 45-54 1 1 1 1
## 55-64 1 1 1 1
## 65-74 1 1 1 1
## 75+ 1 1 1 1
##
## , , = 20-29
##
##
## 0-39g/day 40-79 80-119 120+
## 25-34 1 1 0 1
## 35-44 1 1 1 1
## 45-54 1 1 1 1
## 55-64 1 1 1 1
## 65-74 1 1 1 1
## 75+ 0 1 0 0
##
## , , = 30+
##
##
## 0-39g/day 40-79 80-119 120+
## 25-34 1 1 1 1
## 35-44 1 1 1 0
## 45-54 1 1 1 1
## 55-64 1 1 1 1
## 65-74 1 0 1 1
## 75+ 1 1 0 0
e.relfreq <- e.freq / nrow(esoph)
e.relfreq
## , , = 0-9g/day
##
##
## 0-39g/day 40-79 80-119 120+
## 25-34 0.01136364 0.01136364 0.01136364 0.01136364
## 35-44 0.01136364 0.01136364 0.01136364 0.01136364
## 45-54 0.01136364 0.01136364 0.01136364 0.01136364
## 55-64 0.01136364 0.01136364 0.01136364 0.01136364
## 65-74 0.01136364 0.01136364 0.01136364 0.01136364
## 75+ 0.01136364 0.01136364 0.01136364 0.01136364
##
## , , = 10-19
##
##
## 0-39g/day 40-79 80-119 120+
## 25-34 0.01136364 0.01136364 0.01136364 0.01136364
## 35-44 0.01136364 0.01136364 0.01136364 0.01136364
## 45-54 0.01136364 0.01136364 0.01136364 0.01136364
## 55-64 0.01136364 0.01136364 0.01136364 0.01136364
## 65-74 0.01136364 0.01136364 0.01136364 0.01136364
## 75+ 0.01136364 0.01136364 0.01136364 0.01136364
##
## , , = 20-29
##
##
## 0-39g/day 40-79 80-119 120+
## 25-34 0.01136364 0.01136364 0.00000000 0.01136364
## 35-44 0.01136364 0.01136364 0.01136364 0.01136364
## 45-54 0.01136364 0.01136364 0.01136364 0.01136364
## 55-64 0.01136364 0.01136364 0.01136364 0.01136364
## 65-74 0.01136364 0.01136364 0.01136364 0.01136364
## 75+ 0.00000000 0.01136364 0.00000000 0.00000000
##
## , , = 30+
##
##
## 0-39g/day 40-79 80-119 120+
## 25-34 0.01136364 0.01136364 0.01136364 0.01136364
## 35-44 0.01136364 0.01136364 0.01136364 0.00000000
## 45-54 0.01136364 0.01136364 0.01136364 0.01136364
## 55-64 0.01136364 0.01136364 0.01136364 0.01136364
## 65-74 0.01136364 0.00000000 0.01136364 0.01136364
## 75+ 0.01136364 0.01136364 0.00000000 0.00000000
round.e.relfreq <- round (e.relfreq, digits = 2)
round.e.relfreq
## , , = 0-9g/day
##
##
## 0-39g/day 40-79 80-119 120+
## 25-34 0.01 0.01 0.01 0.01
## 35-44 0.01 0.01 0.01 0.01
## 45-54 0.01 0.01 0.01 0.01
## 55-64 0.01 0.01 0.01 0.01
## 65-74 0.01 0.01 0.01 0.01
## 75+ 0.01 0.01 0.01 0.01
##
## , , = 10-19
##
##
## 0-39g/day 40-79 80-119 120+
## 25-34 0.01 0.01 0.01 0.01
## 35-44 0.01 0.01 0.01 0.01
## 45-54 0.01 0.01 0.01 0.01
## 55-64 0.01 0.01 0.01 0.01
## 65-74 0.01 0.01 0.01 0.01
## 75+ 0.01 0.01 0.01 0.01
##
## , , = 20-29
##
##
## 0-39g/day 40-79 80-119 120+
## 25-34 0.01 0.01 0.00 0.01
## 35-44 0.01 0.01 0.01 0.01
## 45-54 0.01 0.01 0.01 0.01
## 55-64 0.01 0.01 0.01 0.01
## 65-74 0.01 0.01 0.01 0.01
## 75+ 0.00 0.01 0.00 0.00
##
## , , = 30+
##
##
## 0-39g/day 40-79 80-119 120+
## 25-34 0.01 0.01 0.01 0.01
## 35-44 0.01 0.01 0.01 0.00
## 45-54 0.01 0.01 0.01 0.01
## 55-64 0.01 0.01 0.01 0.01
## 65-74 0.01 0.00 0.01 0.01
## 75+ 0.01 0.01 0.00 0.00
acrosstab1 <- table(esoph$agegp, esoph$alcg)
acrosstab1
##
## 0-39g/day 40-79 80-119 120+
## 25-34 4 4 3 4
## 35-44 4 4 4 3
## 45-54 4 4 4 4
## 55-64 4 4 4 4
## 65-74 4 3 4 4
## 75+ 3 4 2 2
ftable(acrosstab1)
## 0-39g/day 40-79 80-119 120+
##
## 25-34 4 4 3 4
## 35-44 4 4 4 3
## 45-54 4 4 4 4
## 55-64 4 4 4 4
## 65-74 4 3 4 4
## 75+ 3 4 2 2
anotheronextab1 <- xtabs(~esoph$agegp + esoph$alcg)
anotheronextab1
## esoph$alcg
## esoph$agegp 0-39g/day 40-79 80-119 120+
## 25-34 4 4 3 4
## 35-44 4 4 4 3
## 45-54 4 4 4 4
## 55-64 4 4 4 4
## 65-74 4 3 4 4
## 75+ 3 4 2 2
ftable(anotheronextab1)
## esoph$alcg 0-39g/day 40-79 80-119 120+
## esoph$agegp
## 25-34 4 4 3 4
## 35-44 4 4 4 3
## 45-54 4 4 4 4
## 55-64 4 4 4 4
## 65-74 4 3 4 4
## 75+ 3 4 2 2
acrosstab2 <- table(esoph$alcgp, esoph$tobgp)
acrosstab2
##
## 0-9g/day 10-19 20-29 30+
## 0-39g/day 6 6 5 6
## 40-79 6 6 6 5
## 80-119 6 6 4 5
## 120+ 6 6 5 4
ftable(acrosstab2)
## 0-9g/day 10-19 20-29 30+
##
## 0-39g/day 6 6 5 6
## 40-79 6 6 6 5
## 80-119 6 6 4 5
## 120+ 6 6 5 4
anotheronextab2 <- xtabs(~esoph$alcgp + esoph$tobgp)
anotheronextab2
## esoph$tobgp
## esoph$alcgp 0-9g/day 10-19 20-29 30+
## 0-39g/day 6 6 5 6
## 40-79 6 6 6 5
## 80-119 6 6 4 5
## 120+ 6 6 5 4
ftable(anotheronextab2)
## esoph$tobgp 0-9g/day 10-19 20-29 30+
## esoph$alcgp
## 0-39g/day 6 6 5 6
## 40-79 6 6 6 5
## 80-119 6 6 4 5
## 120+ 6 6 5 4
library(ggplot2)
## Warning: package 'ggplot2' was built under R version 3.3.2
?diamonds
summary(diamonds)
## carat cut color clarity
## Min. :0.2000 Fair : 1610 D: 6775 SI1 :13065
## 1st Qu.:0.4000 Good : 4906 E: 9797 VS2 :12258
## Median :0.7000 Very Good:12082 F: 9542 SI2 : 9194
## Mean :0.7979 Premium :13791 G:11292 VS1 : 8171
## 3rd Qu.:1.0400 Ideal :21551 H: 8304 VVS2 : 5066
## Max. :5.0100 I: 5422 VVS1 : 3655
## J: 2808 (Other): 2531
## depth table price x
## Min. :43.00 Min. :43.00 Min. : 326 Min. : 0.000
## 1st Qu.:61.00 1st Qu.:56.00 1st Qu.: 950 1st Qu.: 4.710
## Median :61.80 Median :57.00 Median : 2401 Median : 5.700
## Mean :61.75 Mean :57.46 Mean : 3933 Mean : 5.731
## 3rd Qu.:62.50 3rd Qu.:59.00 3rd Qu.: 5324 3rd Qu.: 6.540
## Max. :79.00 Max. :95.00 Max. :18823 Max. :10.740
##
## y z
## Min. : 0.000 Min. : 0.000
## 1st Qu.: 4.720 1st Qu.: 2.910
## Median : 5.710 Median : 3.530
## Mean : 5.735 Mean : 3.539
## 3rd Qu.: 6.540 3rd Qu.: 4.040
## Max. :58.900 Max. :31.800
##
d.price <-diamonds$price
range(d.price )
## [1] 326 18823
d.price_break <- seq (310, 19000, by=1600)
d.price_break
## [1] 310 1910 3510 5110 6710 8310 9910 11510 13110 14710 16310
## [12] 17910
d.price.cut <- cut(d.price, d.price_break, right=FALSE)
d.price.freq <-table(d.price.cut)
d.price.freq
## d.price.cut
## [310,1.91e+03) [1.91e+03,3.51e+03) [3.51e+03,5.11e+03)
## 23499 9034 7123
## [5.11e+03,6.71e+03) [6.71e+03,8.31e+03) [8.31e+03,9.91e+03)
## 4436 2647 1902
## [9.91e+03,1.15e+04) [1.15e+04,1.31e+04) [1.31e+04,1.47e+04)
## 1469 1136 913
## [1.47e+04,1.63e+04) [1.63e+04,1.79e+04)
## 772 669
cbind(d.price.freq)
## d.price.freq
## [310,1.91e+03) 23499
## [1.91e+03,3.51e+03) 9034
## [3.51e+03,5.11e+03) 7123
## [5.11e+03,6.71e+03) 4436
## [6.71e+03,8.31e+03) 2647
## [8.31e+03,9.91e+03) 1902
## [9.91e+03,1.15e+04) 1469
## [1.15e+04,1.31e+04) 1136
## [1.31e+04,1.47e+04) 913
## [1.47e+04,1.63e+04) 772
## [1.63e+04,1.79e+04) 669
hist(diamonds$price)
hist(diamonds$carat)
hist(diamonds$depth)
hist(diamonds$table)
range(diamonds$carat)
## [1] 0.20 5.01
range(diamonds$depth)
## [1] 43 79
range(diamonds$table)
## [1] 43 95