-
Notifications
You must be signed in to change notification settings - Fork 0
/
House_prices.Rmd
208 lines (149 loc) · 6.31 KB
/
House_prices.Rmd
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
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
---
title: "Analyzing the effect of a Highway on House Prices"
author: "Ignacio Pezo Salazar"
output: github_document
html_document:
df_print: paged
keep_md: true
---
```{r setup, include=FALSE}
knitr::opts_chunk$set( message=F, warning=F, fig.width = 10, fig.height = 10 )
library(maptools)
library(sp)
library(maps) #has mapscale
library(rgeos)
library(raster)
library(rgdal)
library(geojsonio)
setwd("C:/Users/icps/Box Sync/Data Science/Maps-in-R")
```
###PART I
(1-3) Loading shapefiles and extracting interstates and clipping it to the map polygon size.
```{r, echo=FALSE, eval=FALSE}
#Downloading Shapfiles - this is commented because it was already done
#dir.create( "shapefiles" )
#setwd( "./shapefiles" )
#download.file("ftp://ftp2.census.gov/geo/tiger/TIGER2010/TRACT/2010/tl_2010_36067_tract10.zip", "onondaga census tracts.zip" )
#unzip( "onondaga census tracts.zip" )
#file.remove( "onondaga census tracts.zip" )
#download.file("ftp://ftp2.census.gov/geo/tiger/TIGER2015/PRISECROADS/tl_2015_36_prisecroads.zip", "primary_and_secondary_roads.zip" )
#unzip( "primary_and_secondary_roads.zip" )
#file.remove( "primary_and_secondary_roads.zip" )
```
```{r}
#loading shapefile from file
shapes <- readShapePoly( fn="./shapefiles/tl_2010_36067_tract10", proj4string=CRS("+proj=longlat +datum=WGS84") )
shapes@data <- data.frame(Tract = shapes@data$NAME10)
shapes <- shapes[as.numeric(as.character(shapes$Tract)) < 64, ] #Cutting all tracks that are not in syracuse. lower than 64 gets this.
#getting roads
roads <- readShapeLines( fn="./shapefiles/tl_2015_36_prisecroads", proj4string=CRS("+proj=longlat +datum=WGS84") )
#getting interstate in a separate object
interstate <- roads[ roads$RTTYP == "I" , ]
#plotting map and interstate
par(mar=c(0,0,2,0))
plot(shapes, border="gray50")
plot(interstate, col="red3", lwd=1, add=T)
#clipping roads to the shape file
interstate <- gIntersection(shapes, interstate)
#this is an alternative function:
#roads.cropped <- intersect(interstate, shapes)
plot(shapes, border="gray50")
plot(interstate, col="red3", lwd=1, add=T)
```
(4) Create a buffer of approximately a quarter mile (eyeball this) from the interstate
```{r}
buffer <- gBuffer(interstate, width = .005)
plot(shapes, border="gray50")
plot(buffer, border="brown", col = adjustcolor("brown", alpha.f = .2),lwd=1, add=T)
plot(interstate, col="red3", lwd=1, add=T)
#uploading the dataset of houses that was geocoded previously
load("dat_coo.rda") #as a rda file.
# Convert the coordinates that are in lon (x) lat(y) order to spatial points, identifying the coordinates, data, and coordinate system
coo <- dat[ ,c( "lon", "lat") ] #extracting the coordinates
#making binding coordinates (coo) and data (dat) as a spatial object. Notice that dat maintains the lat lon variables as data
dat <- SpatialPointsDataFrame(coo, dat, proj4string=CRS("+proj=longlat +datum=WGS84"))
#plotting
plot(shapes, border="gray50")
plot(buffer, border="brown", col = adjustcolor("brown", alpha.f = .2),lwd=1, add=T)
plot(interstate, col="red3", lwd=1, add=T)
plot(dat, pch = 20, cex=.8, add=T)
```
(5) Add a new categorical variable to the houses dataset that indicates whether it falls within the buffer zone or not.
```{r}
#Over function to determine what points are within the buffer
x <- over( dat, buffer ) #outputs a dummy variable
dat@data$hgwy <- x
#plotting
par(mar=c(0,0,2,0))
plot(shapes, border="gray50")
plot(buffer, border="brown", col = adjustcolor("brown", alpha.f = .2),lwd=1, add=T)
plot(interstate, col="red3", lwd=1, add=T)
plot(dat, pch = 20, cex=.8, add=T)
plot(dat[!is.na(dat$hgwy),], pch = 20, col = "red", cex=1, add=T)
```
###PART II
Using the Syracuse parcel file for this part.
(1) Create a buffer a quarter mile from industrial zones (LandUse). Create a plot to highlight your buffer zone.
```{r}
url <- "https://raw.githubusercontent.com/lecy/geojson/master/syr_parcels.geojson"
shapes <- geojson_read( url, method="local", what="sp" )
#subsetting industrialzones
industrial <- shapes[ shapes$LandUse == "Industrial", ]
#Creating buffer next to industrial zones
buffer <- gBuffer( industrial,
width = 0.003621,
capStyle = "FLAT",
quadsegs = 1,
byid = FALSE
)
#plotting
par(mar=c(0,0,2,0))
plot(shapes, col="gray80", border = FALSE)
plot(buffer, border="brown", col = adjustcolor("brown", alpha.f = .2),lwd=1, add=T)
plot(industrial, col= "red3", border = FALSE, add=T)
```
(2) Identify houses within the buffer zone and create a categorical variable in the dataset indicating proximity to industrial zones.
```{r}
#need to make CRS in both buffer and dat =. there are two ways
proj4string(dat)
proj4string(buffer)
buffer <- spTransform( buffer, CRS( "+proj=longlat +datum=WGS84" ) )
#now they are equal
proj4string(dat)
proj4string(buffer)
#Over function to determine what points are within the buffer
x <- over( dat, buffer ) #outputs a dummy variable
dat@data$indst <- x
#plotting the houses
par(mar=c(0,0,2,0))
plot(shapes, col="gray80", border = FALSE)
plot(buffer, border="brown", col = adjustcolor("brown", alpha.f = .2),lwd=1, add=T)
plot(industrial, col= "red3", border = FALSE, add=T)
plot(dat, pch = 20, cex=.8, add=T)
plot(dat[!is.na(dat$indst),], pch = 20, col = "red", cex=1, add=T)
```
(3-4) Create a buffer zone an eighth of a mile from schools and identifying houses within the buffer zone and create a categorical variable in the dataset indicating proximity to schools.
```{r}
#subsetting industrialzones
schools <- shapes[ shapes$LandUse == "Schools", ]
#Creating buffer next to industrial zones
buffer <- gBuffer( schools,
width = 0.0018105,
capStyle = "FLAT",
quadsegs = 1,
byid = FALSE
)
#plotting
par(mar=c(0,0,2,0))
plot(shapes, col="gray80", border = FALSE)
plot(buffer, border="brown", col = adjustcolor("brown", alpha.f = .2),lwd=1, add=T)
plot(schools, col= "red3", border = FALSE, add=T)
#making buffer share same CRS
buffer <- spTransform( buffer, CRS( "+proj=longlat +datum=WGS84" ) )
#Over function to determine what points are within the buffer
x <- over( dat, buffer ) #outputs a dummy variable
dat@data$school <- x
#plotting the houses
plot(dat, pch = 20, cex=.8, add=T)
plot(dat[!is.na(dat$school),], pch = 20, col = "red", cex=1, add=T)
```