I am making a plot to show the relationship between house size and prices. The thing is, I need the 5% of the most recently built houses to have a different color and symbol on the plot. Here is my code (new_baltimore is the dataframe):
y <- new_baltimore$AGE
quantile(y, 0.05) #the result is 4
k <- subset(new_baltimore, y<=4)
kk <- k$SQFT
col = ifelse(any new_baltimore$SQFT %in% kk, "red", "green")
pch = ifelse(any new_baltimore$SQFT %in% kk, 25, 20)
plot(new_baltimore$SQFT, PRICE, col=col, pch=pch)
R gives me the errors
Error: unexpected symbol in "col = ifelse(any new_baltimore"
Error: unexpected symbol in "pch = ifelse(any new_baltimore"
Any help?
edit: This is the reproducible data:
baltimore_struct <-
structure(
list(
new_baltimore.SQFT = c(
11.25,
28.92,
30.62,
26.12,
22.04,
39.42,
21.88,
25.6,
44.12,
19.88,
12.08,
10.99,
12.8,
29.79,
14.3,
13.72,
11.84,
18.06,
10.72,
8.96,
14.38,
36.75,
20,
22.82,
24.86,
19.2,
11.58,
26,
14.4,
11.62,
23.08,
23.76,
15.6,
10,
22.8,
16.76,
22.1,
14.28,
15.36,
16,
23.04,
24.94,
11.82,
12.88,
11.2,
18.12,
38.25,
17.68,
19.02,
32.8,
15.16,
21.975,
12.6,
23.52,
17.52,
47.61,
20.55,
35.52,
8.4,
13.68,
14.48,
12.8,
12.8,
18,
15.4,
10.08,
8.96,
8.96,
20,
12.88,
12,
18.16,
14.28,
26,
12.02,
20.8,
11.78,
8.68,
17.6,
11.4,
44.55,
46.32,
10.24,
9.6,
31.2,
26.4,
13.6,
27.48,
17.86,
18.04,
14.84,
10.46,
14.56,
6.96,
9.5,
11.86,
12.88,
12.32,
6.72,
10.08,
15.6,
6.72,
11.52,
11.76,
10.24,
11.52,
9.28,
6.72,
15.6,
15.5,
9.84,
15.6,
13.76,
10.24,
5.76,
10.08,
11.52,
12.15,
9.77,
15,
14.4,
14.5,
22.54,
10.24,
7.8,
8.4,
10.92,
42.9,
9,
10.5,
10.08,
12.6,
8.96,
8.58,
7.56,
10.8,
13.44,
10.24,
14.44,
12.24,
13.2,
9.6,
15.22,
24.16,
10.24,
10.24,
9.88,
23.2,
17.68,
24.3,
35.94,
21.6,
11.02,
21,
23.92,
14.4,
28,
11.44,
21.94,
10.24,
16.86,
9.92,
13.44,
12,
14.76,
8.96,
11.52,
8.64,
8.12,
11.12,
11.28,
10.36,
11.52,
17.1,
17.52,
10.73,
11.2,
12.8,
12,
41.07,
12.8,
22.36,
10.56,
13.44,
11.02,
17.98,
18.88,
11.76,
9.36,
11.52,
27.3,
23.04,
17.68,
13.36,
11.6,
11.52,
9.98,
12.96,
11.13,
19.6,
11.52,
12.16,
0,
10.64
),
PRICE2 = c(
47,
113,
165,
104.3,
62.5,
70,
127.5,
64.5,
145,
63.5,
58.9,
65,
48,
3.5,
12.8,
17.5,
36,
41.9,
53.5,
24.5,
24.5,
55.5,
60,
51,
46,
46,
44,
54.9,
42.5,
44,
44.9,
37.9,
33,
43.9,
49.6,
52,
37.5,
50,
35.9,
42.9,
107,
112,
44.9,
55,
102,
35.5,
62.9,
39,
110,
8,
62,
85.9,
57,
110,
67.7,
89.5,
70,
74,
13,
48,
24,
53.5,
34.5,
53,
87.5,
33.5,
24,
9.6,
30,
41,
30,
38.9,
20.7,
49.9,
18.6,
39,
34,
16,
18.9,
15.2,
41.5,
53,
22,
24.9,
6.7,
32.5,
30,
59,
29.5,
26,
16.5,
39,
48.9,
33.5,
46,
54,
57.9,
37.9,
32,
31,
34,
29,
32.5,
51.9,
31,
41.8,
48,
28,
35,
46.5,
51.9,
35.4,
16,
35,
35,
36.5,
35.9,
45,
40,
35,
38,
37,
23,
25.5,
39.5,
21.5,
9,
67.5,
13.4,
12.5,
28.5,
23,
33.5,
9,
11,
30.9,
31.65,
33,
33.4,
47,
40,
46,
45.5,
57,
29.9,
30,
34,
51,
64.5,
57.5,
85.5,
61,
38,
56.5,
60.4,
51.5,
54,
69,
56,
27.9,
37.5,
32.9,
22,
29.9,
39.9,
32.6,
38.5,
21.5,
25.9,
27.5,
22.9,
31.5,
8.5,
5.5,
33,
57,
47,
43.5,
43.9,
68.5,
44.25,
61,
40,
44.5,
57,
35,
35.1,
64.5,
40,
42.6,
50,
58,
58,
55,
43,
54,
39,
45,
42,
38.9,
43.215,
26.5,
30,
29.5
)
),
row.names = c(
1L,
2L,
3L,
4L,
5L,
6L,
7L,
8L,
9L,
10L,
11L,
12L,
13L,
14L,
15L,
16L,
17L,
18L,
19L,
20L,
21L,
22L,
23L,
24L,
25L,
26L,
27L,
28L,
29L,
30L,
31L,
32L,
33L,
34L,
35L,
36L,
37L,
38L,
39L,
40L,
41L,
42L,
43L,
44L,
45L,
46L,
47L,
48L,
49L,
50L,
51L,
53L,
54L,
55L,
56L,
57L,
58L,
59L,
60L,
61L,
62L,
63L,
64L,
65L,
66L,
67L,
68L,
69L,
70L,
71L,
72L,
73L,
74L,
75L,
76L,
77L,
78L,
79L,
80L,
81L,
82L,
83L,
84L,
85L,
86L,
87L,
88L,
89L,
90L,
91L,
92L,
93L,
94L,
95L,
96L,
97L,
98L,
99L,
100L,
101L,
102L,
103L,
104L,
105L,
106L,
107L,
108L,
109L,
110L,
111L,
112L,
113L,
114L,
115L,
116L,
117L,
118L,
119L,
120L,
121L,
122L,
123L,
124L,
125L,
126L,
127L,
128L,
129L,
130L,
131L,
132L,
133L,
134L,
135L,
136L,
137L,
138L,
139L,
140L,
141L,
142L,
143L,
144L,
145L,
146L,
147L,
148L,
149L,
150L,
151L,
152L,
153L,
154L,
155L,
156L,
157L,
158L,
159L,
160L,
161L,
162L,
163L,
164L,
165L,
166L,
167L,
168L,
169L,
170L,
171L,
172L,
173L,
174L,
175L,
176L,
177L,
178L,
179L,
180L,
181L,
182L,
183L,
184L,
185L,
186L,
187L,
188L,
189L,
190L,
191L,
192L,
193L,
194L,
195L,
196L,
197L,
198L,
199L,
200L,
201L,
202L,
203L,
204L,
205L
),
class = "data.frame"
)
edit2: I found the error, I just had to remove the any in the ifelse commands. So the correct code looks like this
col = ifelse(new_baltimore$SQFT %in% kk, "red", "green")
pch = ifelse(new_baltimore$SQFT %in% kk, 25, 20)
