In [3]:

    

x <- rnorm(50)
y <- x + rnorm(50, mean=0, sd=0.5)


    

In [4]:

    

data <- as.data.frame(cbind(x, y))
summary(data)


    

    
Out[4]:





       x                  y           
 Min.   :-1.90735   Min.   :-2.55561  
 1st Qu.:-0.65233   1st Qu.:-0.82265  
 Median :-0.09495   Median :-0.04525  
 Mean   :-0.05587   Mean   :-0.06356  
 3rd Qu.: 0.64674   3rd Qu.: 0.72672  
 Max.   : 2.10736   Max.   : 1.72585  

In [5]:

    

library(ggplot2)


    

In [6]:

    

ggplot(data, aes(x=x, y=y)) +
  geom_point(size=2) +
  ggtitle("Scatterplot of X and Y") + 
  theme(axis.text=element_text(size=12), 
        axis.title = element_text(size=14),
        plot.title = element_text(size=20, face="bold"))


    

In [1]:

    

library(dplyr)


    

    




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

In [2]:

    

iris


    

    




Warning message:
In `[<-.factor`(`*tmp*`, ri, value = "⋮"): invalid factor level, NA generatedWarning message:
In `[<-.factor`(`*tmp*`, ri, value = "⋮"): invalid factor level, NA generated





    
Out[2]:





Sepal.Length
Sepal.Width
Petal.Length
Petal.Width
Species

	
1
5.1
3.5
1.4
0.2
setosa
	
2
4.9
3
1.4
0.2
setosa
	
3
4.7
3.2
1.3
0.2
setosa
	
4
4.6
3.1
1.5
0.2
setosa
	
5
5
3.6
1.4
0.2
setosa
	
6
5.4
3.9
1.7
0.4
setosa
	
7
4.6
3.4
1.4
0.3
setosa
	
8
5
3.4
1.5
0.2
setosa
	
9
4.4
2.9
1.4
0.2
setosa
	
10
4.9
3.1
1.5
0.1
setosa
	
11
5.4
3.7
1.5
0.2
setosa
	
12
4.8
3.4
1.6
0.2
setosa
	
13
4.8
3
1.4
0.1
setosa
	
14
4.3
3
1.1
0.1
setosa
	
15
5.8
4
1.2
0.2
setosa
	
16
5.7
4.4
1.5
0.4
setosa
	
17
5.4
3.9
1.3
0.4
setosa
	
18
5.1
3.5
1.4
0.3
setosa
	
19
5.7
3.8
1.7
0.3
setosa
	
20
5.1
3.8
1.5
0.3
setosa
	
21
5.4
3.4
1.7
0.2
setosa
	
22
5.1
3.7
1.5
0.4
setosa
	
23
4.6
3.6
1
0.2
setosa
	
24
5.1
3.3
1.7
0.5
setosa
	
25
4.8
3.4
1.9
0.2
setosa
	
26
5
3
1.6
0.2
setosa
	
27
5
3.4
1.6
0.4
setosa
	
28
5.2
3.5
1.5
0.2
setosa
	
29
5.2
3.4
1.4
0.2
setosa
	
30
4.7
3.2
1.6
0.2
setosa
	
31
⋮
⋮
⋮
⋮
NA
	
121
6.9
3.2
5.7
2.3
virginica
	
122
5.6
2.8
4.9
2
virginica
	
123
7.7
2.8
6.7
2
virginica
	
124
6.3
2.7
4.9
1.8
virginica
	
125
6.7
3.3
5.7
2.1
virginica
	
126
7.2
3.2
6
1.8
virginica
	
127
6.2
2.8
4.8
1.8
virginica
	
128
6.1
3
4.9
1.8
virginica
	
129
6.4
2.8
5.6
2.1
virginica
	
130
7.2
3
5.8
1.6
virginica
	
131
7.4
2.8
6.1
1.9
virginica
	
132
7.9
3.8
6.4
2
virginica
	
133
6.4
2.8
5.6
2.2
virginica
	
134
6.3
2.8
5.1
1.5
virginica
	
135
6.1
2.6
5.6
1.4
virginica
	
136
7.7
3
6.1
2.3
virginica
	
137
6.3
3.4
5.6
2.4
virginica
	
138
6.4
3.1
5.5
1.8
virginica
	
139
6
3
4.8
1.8
virginica
	
140
6.9
3.1
5.4
2.1
virginica
	
141
6.7
3.1
5.6
2.4
virginica
	
142
6.9
3.1
5.1
2.3
virginica
	
143
5.8
2.7
5.1
1.9
virginica
	
144
6.8
3.2
5.9
2.3
virginica
	
145
6.7
3.3
5.7
2.5
virginica
	
146
6.7
3
5.2
2.3
virginica
	
147
6.3
2.5
5
1.9
virginica
	
148
6.5
3
5.2
2
virginica
	
149
6.2
3.4
5.4
2.3
virginica
	
150
5.9
3
5.1
1.8
virginica

In [1]:

    

library(ggplot2)


    

In [4]:

    

ggplot(data=iris, aes(x=Sepal.Length, y=Sepal.Width, color=Species)) + geom_point(size=3)


    

In [2]:

    

str(diamonds)


    

    




'data.frame':	53940 obs. of  10 variables:
 $ carat  : num  0.23 0.21 0.23 0.29 0.31 0.24 0.24 0.26 0.22 0.23 ...
 $ cut    : Ord.factor w/ 5 levels "Fair"<"Good"<..: 5 4 2 4 2 3 3 3 1 3 ...
 $ color  : Ord.factor w/ 7 levels "D"<"E"<"F"<"G"<..: 2 2 2 6 7 7 6 5 2 5 ...
 $ clarity: Ord.factor w/ 8 levels "I1"<"SI2"<"SI1"<..: 2 3 5 4 2 6 7 3 4 5 ...
 $ depth  : num  61.5 59.8 56.9 62.4 63.3 62.8 62.3 61.9 65.1 59.4 ...
 $ table  : num  55 61 65 58 58 57 57 55 61 61 ...
 $ price  : int  326 326 327 334 335 336 336 337 337 338 ...
 $ x      : num  3.95 3.89 4.05 4.2 4.34 3.94 3.95 4.07 3.87 4 ...
 $ y      : num  3.98 3.84 4.07 4.23 4.35 3.96 3.98 4.11 3.78 4.05 ...
 $ z      : num  2.43 2.31 2.31 2.63 2.75 2.48 2.47 2.53 2.49 2.39 ...

In [5]:

    

head(diamonds)


    

    
Out[5]:





carat
cut
color
clarity
depth
table
price
x
y
z

	
1
0.23
Ideal
E
SI2
61.5
55
326
3.95
3.98
2.43
	
2
0.21
Premium
E
SI1
59.8
61
326
3.89
3.84
2.31
	
3
0.23
Good
E
VS1
56.9
65
327
4.05
4.07
2.31
	
4
0.29
Premium
I
VS2
62.4
58
334
4.2
4.23
2.63
	
5
0.31
Good
J
SI2
63.3
58
335
4.34
4.35
2.75
	
6
0.24
Very Good
J
VVS2
62.8
57
336
3.94
3.96
2.48

In [6]:

    

ggplot(diamonds, aes(x=carat, y=price, col=clarity)) + geom_point()


    

In [8]:

    

ggplot(diamonds, aes(x=price, fill=cut)) +
  geom_density(alpha = .3, color=NA)


    

In [9]:

    

ggplot(diamonds, aes(x=log10(price), fill=cut)) +
  geom_density(alpha = .3, color=NA)


    

In [ ]: