library(dplyr)
##
## 다음의 패키지를 부착합니다: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(ggplot2)
data("midwest")
glimpse(midwest)
## Rows: 437
## Columns: 28
## $ PID <int> 561, 562, 563, 564, 565, 566, 567, 568, 569, 570,…
## $ county <chr> "ADAMS", "ALEXANDER", "BOND", "BOONE", "BROWN", "…
## $ state <chr> "IL", "IL", "IL", "IL", "IL", "IL", "IL", "IL", "…
## $ area <dbl> 0.052, 0.014, 0.022, 0.017, 0.018, 0.050, 0.017, …
## $ poptotal <int> 66090, 10626, 14991, 30806, 5836, 35688, 5322, 16…
## $ popdensity <dbl> 1270.9615, 759.0000, 681.4091, 1812.1176, 324.222…
## $ popwhite <int> 63917, 7054, 14477, 29344, 5264, 35157, 5298, 165…
## $ popblack <int> 1702, 3496, 429, 127, 547, 50, 1, 111, 16, 16559,…
## $ popamerindian <int> 98, 19, 35, 46, 14, 65, 8, 30, 8, 331, 51, 26, 17…
## $ popasian <int> 249, 48, 16, 150, 5, 195, 15, 61, 23, 8033, 89, 3…
## $ popother <int> 124, 9, 34, 1139, 6, 221, 0, 84, 6, 1596, 20, 7, …
## $ percwhite <dbl> 96.71206, 66.38434, 96.57128, 95.25417, 90.19877,…
## $ percblack <dbl> 2.57527614, 32.90043290, 2.86171703, 0.41225735, …
## $ percamerindan <dbl> 0.14828264, 0.17880670, 0.23347342, 0.14932156, 0…
## $ percasian <dbl> 0.37675897, 0.45172219, 0.10673071, 0.48691813, 0…
## $ percother <dbl> 0.18762294, 0.08469791, 0.22680275, 3.69733169, 0…
## $ popadults <int> 43298, 6724, 9669, 19272, 3979, 23444, 3583, 1132…
## $ perchsd <dbl> 75.10740, 59.72635, 69.33499, 75.47219, 68.86152,…
## $ percollege <dbl> 19.63139, 11.24331, 17.03382, 17.27895, 14.47600,…
## $ percprof <dbl> 4.355859, 2.870315, 4.488572, 4.197800, 3.367680,…
## $ poppovertyknown <int> 63628, 10529, 14235, 30337, 4815, 35107, 5241, 16…
## $ percpovertyknown <dbl> 96.27478, 99.08714, 94.95697, 98.47757, 82.50514,…
## $ percbelowpoverty <dbl> 13.151443, 32.244278, 12.068844, 7.209019, 13.520…
## $ percchildbelowpovert <dbl> 18.011717, 45.826514, 14.036061, 11.179536, 13.02…
## $ percadultpoverty <dbl> 11.009776, 27.385647, 10.852090, 5.536013, 11.143…
## $ percelderlypoverty <dbl> 12.443812, 25.228976, 12.697410, 6.217047, 19.200…
## $ inmetro <int> 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 1, 0…
## $ category <chr> "AAR", "LHR", "AAR", "ALU", "AAR", "AAR", "LAR", …
#Unweighted
ggplot(midwest, aes(percwhite, percbelowpoverty)) +
geom_point()
# Weight by population
ggplot(midwest, aes(percwhite, percbelowpoverty)) +
geom_point(aes(size = poptotal / 1e6))
#1 e6 = 1*10^6
ggplot(midwest, aes(percwhite, percbelowpoverty)) +
geom_point(aes(size = poptotal / 1e6)) +
scale_size_area("Population|n(millions)", breaks = c(0.5, 1, 2, 4))
#Unweighted
ggplot(midwest, aes(percwhite, percbelowpoverty)) +
geom_point() +
geom_smooth(method=lm, size = 1)
## `geom_smooth()` using formula 'y ~ x'
# Weight by population
ggplot(midwest, aes(percwhite, percbelowpoverty)) +
geom_point(aes(size = poptotal / 1e6)) +
geom_smooth(aes(weight = poptotal), method = lm, size = 1)
## `geom_smooth()` using formula 'y ~ x'
#3.10 Diamonds Data
data("diamonds")
glimpse(diamonds)
## Rows: 53,940
## Columns: 10
## $ carat <dbl> 0.23, 0.21, 0.23, 0.29, 0.31, 0.24, 0.24, 0.26, 0.22, 0.23, 0.…
## $ cut <ord> Ideal, Premium, Good, Premium, Good, Very Good, Very Good, Ver…
## $ color <ord> E, E, E, I, J, J, I, H, E, H, J, J, F, J, E, E, I, J, J, J, I,…
## $ clarity <ord> SI2, SI1, VS1, VS2, SI2, VVS2, VVS1, SI1, VS2, VS1, SI1, VS1, …
## $ depth <dbl> 61.5, 59.8, 56.9, 62.4, 63.3, 62.8, 62.3, 61.9, 65.1, 59.4, 64…
## $ table <dbl> 55, 61, 65, 58, 58, 57, 57, 55, 61, 61, 55, 56, 61, 54, 62, 58…
## $ price <int> 326, 326, 327, 334, 335, 336, 336, 337, 337, 338, 339, 340, 34…
## $ x <dbl> 3.95, 3.89, 4.05, 4.20, 4.34, 3.94, 3.95, 4.07, 3.87, 4.00, 4.…
## $ y <dbl> 3.98, 3.84, 4.07, 4.23, 4.35, 3.96, 3.98, 4.11, 3.78, 4.05, 4.…
## $ z <dbl> 2.43, 2.31, 2.31, 2.63, 2.75, 2.48, 2.47, 2.53, 2.49, 2.39, 2.…
ggplot(diamonds, aes(depth)) +
geom_histogram()
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
ggplot(diamonds, aes(depth)) +
geom_histogram(binwidth = 0.1) +
xlim(55, 70)
## Warning: Removed 45 rows containing non-finite values (stat_bin).
## Warning: Removed 2 rows containing missing values (geom_bar).
#depth는 수치형 데이터, cut은 범주형 데이터
ggplot(diamonds, aes(depth, fill = cut, colour = cut)) +
geom_density(alpha = 0.2, na.rm=TRUE) +
xlim(58, 68)
ggplot(diamonds, aes(cut, depth)) +
geom_boxplot()
# 3.13 Statistical summaries
ggplot(diamonds, aes(color)) +
geom_bar()
ggplot(diamonds, aes(color, price)) +
geom_bar(stat="summary_bin", fun.y =mean)
## Warning: Ignoring unknown parameters: fun.y
## No summary function supplied, defaulting to `mean_se()`
## No summary function supplied, defaulting to `mean_se()`
## No summary function supplied, defaulting to `mean_se()`
## No summary function supplied, defaulting to `mean_se()`
## No summary function supplied, defaulting to `mean_se()`
## No summary function supplied, defaulting to `mean_se()`
## No summary function supplied, defaulting to `mean_se()`
#4.2 78p Building a Scatterplot
ggplot(mpg, aes(displ, hwy, colour = factor(cyl))) +
geom_line()
ggplot(mpg, aes(displ, hwy, colour = factor(cyl))) +
geom_line()+
geom_smooth(method="lm")
## `geom_smooth()` using formula 'y ~ x'
dplot <- ggplot(diamonds, aes(color, fill=cut)) +
xlab(NULL) + ylab(NULL) + theme(legend.position = "none")
dplot+ geom_bar()
dplot + geom_bar(position = "fill")
dplot + geom_bar(position = "dodge")
