forked from zeuses23/RProject
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathrproject.R
150 lines (117 loc) · 4.74 KB
/
rproject.R
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
setwd("C:/Users/PC/Documents/Projects/College Assignments/RProject")
rdata=read.csv("dataset.csv")
rdata1=as.data.frame(rdata)
View(rdata1)
class(rdata1)
library(zoo)
library(tidyr)
library(dplyr)
#for (i in seq(1,5744))+
# if(rdata1$Air.Quality[i] == "--")
# rdata1$Air.Quality[i]<-TRUE
#for (i in seq(1,5744))
#if(rdata1$O3.Quality[i] == "--")
# rdata1$O3.Quality[i]<-"NA"
#for (i in seq(1,5744))
#if(rdata1$NO2.Quality[i] == "--")
# rdata1$NO2.Quality[i]<-TRUE
#for (i in seq(1,5744))
# if(rdata1$PM10.Quality[i] == "--")
# rdata1$PM10.Quality[i]<-"NA"
# Repacing all the blank values with NA
rdata1$NO2.Quality[rdata1$NO2.Quality=="--"]<-NA
rdata1$O3.Quality[rdata1$O3.Quality=="--"]<-NA
rdata1$PM10.Quality[rdata1$PM10.Quality=="--"]<-NA
rdata1$Air.Quality[rdata1$Air.Quality=="--"]<-NA
print("hi")
# Replacing all the NA values with the previous value
dfair<-as.data.frame(rdata1[,2])
rdata1[,2]<-dfair%>%do(na.locf(.))
dfoxy<-as.data.frame(rdata1[,c(5,6)])
rdata1[,c(5,6)]<-dfoxy%>%do(na.locf(.))
dfoxy1<-as.data.frame(rdata1[,7])
rdata1[,7]<-dfoxy1%>%do(na.locf(.))
dfnitro<-as.data.frame(rdata1[8,9])
rdata1[,c(8,9)]<-dfoxy%>%do(na.locf(.))
dfnitro1<-as.data.frame(rdata1[,10])
rdata1[,10]<-dfnitro1%>%do(na.locf(.))
dfpm<-as.data.frame(rdata1[,c(11,12)])
rdata1[,c(11,12)]<-dfoxy%>%do(na.locf(.))
dfpm1<-as.data.frame(rdata1[,13])
rdata1[,13]<-dfpm1%>%do(na.locf(.))
rdata1$Latitude<-as.numeric(rdata1$Latitude)
print("hi")
# correcting the outliers in latitude column
for (i in seq(1,5744)){
if(rdata1$Latitude[i] > 42)
rdata1$Latitude[i]=rdata1$Latitude[i]/10000
}
# normalizing the PM10.Value column
mx = max(rdata1$PM10.Value, na.rm=TRUE)
print(mx)
mn = min(rdata1$PM10.Value, na.rm=TRUE)
print(mn)
for (i in seq(1,5744)){
rdata1$PM10.Value[i]=round((rdata1$PM10.Value[i]-mn)/(mx-mn),digits=3)
}
#Visualisations
a = data.frame()
b = data.frame()
c = data.frame()
d = data.frame()
e = data.frame()
f = data.frame()
g = data.frame()
h = data.frame()
for(i in seq(1,5744,8)){
a = rbind(a,c(rdata1$Station[i],rdata1$Latitude[i],rdata1$Longitude[i],rdata1$NO2.Value[i],rdata1$O3.Value[i],rdata1$PM10.Value[i],rdata1$Date.Time[i],rdata1$Air.Quality))
}
print("1")
for(i in seq(2,5744,8)){
b = rbind(b,c(rdata1$Station[i],rdata1$Latitude[i],rdata1$Longitude[i],rdata1$NO2.Value[i],rdata1$O3.Value[i],rdata1$PM10.Value[i],rdata1$Date.Time[i],rdata1$Air.Quality))
}
print("2")
for(i in seq(3,5744,8)){
c = rbind(c,c(rdata1$Station[i],rdata1$Latitude[i],rdata1$Longitude[i],rdata1$NO2.Value[i],rdata1$O3.Value[i],rdata1$PM10.Value[i],rdata1$Date.Time[i],rdata1$Air.Quality))
}
print("3")
for(i in seq(4,5744,8)){
d = rbind(d,c(rdata1$Station[i],rdata1$Latitude[i],rdata1$Longitude[i],rdata1$NO2.Value[i],rdata1$O3.Value[i],rdata1$PM10.Value[i],rdata1$Date.Time[i],rdata1$Air.Quality))
}
print("4")
for(i in seq(5,5744,8)){
e = rbind(e,c(rdata1$Station[i],rdata1$Latitude[i],rdata1$Longitude[i],rdata1$NO2.Value[i],rdata1$O3.Value[i],rdata1$PM10.Value[i],rdata1$Date.Time[i],rdata1$Air.Quality))
}
print("5")
for(i in seq(6,5744,8)){
f = rbind(f,c(rdata1$Station[i],rdata1$Latitude[i],rdata1$Longitude[i],rdata1$NO2.Value[i],rdata1$O3.Value[i],rdata1$PM10.Value[i],rdata1$Date.Time[i],rdata1$Air.Quality))
}
print("6")
for(i in seq(7,5744,8)){
g = rbind(g,c(rdata1$Station[i],rdata1$Latitude[i],rdata1$Longitude[i],rdata1$NO2.Value[i],rdata1$O3.Value[i],rdata1$PM10.Value[i],rdata1$Date.Time[i],rdata1$Air.Quality))
}
print("7")
for(i in seq(8,5744,8)){
h = rbind(h,c(rdata1$Station[i],rdata1$Latitude[i],rdata1$Longitude[i],rdata1$NO2.Value[i],rdata1$O3.Value[i],rdata1$PM10.Value[i],rdata1$Date.Time[i],rdata1$Air.Quality))
}
print("8")
colnames(a)=c("Station","Lat","Long","NO2","O3","PM10","Time","AQ")
colnames(b)=c("Station","Lat","Long","NO2","O3","PM10","Time","AQ")
colnames(c)=c("Station","Lat","Long","NO2","O3","PM10","Time","AQ")
colnames(d)=c("Station","Lat","Long","NO2","O3","PM10","Time","AQ")
colnames(e)=c("Station","Lat","Long","NO2","O3","PM10","Time","AQ")
colnames(f)=c("Station","Lat","Long","NO2","O3","PM10","Time","AQ")
colnames(g)=c("Station","Lat","Long","NO2","O3","PM10","Time","AQ")
colnames(h)=c("Station","Lat","Long","NO2","O3","PM10","Time","AQ")
final = data.frame()
final = rbind(a,b,c,d,e,f,g,h)
library(plotly)
sp2 <- plot_ly(final, x = ~Lat, y = ~Time, z = ~Long, color = ~NO2, size=1, colorscale = c('#BF382A', '#0G4B8E'),showscale=TRUE) %>%
add_markers() %>%
layout(scene = list(xaxis = list(title = 'Latitude'),
yaxis = list(title = 'Time'),
zaxis = list(title = 'Longitude')))
print(sp2)
#print(pie(table(rdata1$Air.Quality), names(table(rdata1$Air.Quality)),main="Air Quality breakdown"))
print(plot_ly(rdata1,x = ~Air.Quality , type = "bar",colors = c('#BF382A', '#0G4B8E')))
View(rdata1)