-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathBuild Map.R
241 lines (212 loc) · 11.1 KB
/
Build Map.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
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
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
#1 Pull Shapefiles
#Author: Scott Onestak
library(tidycensus)
library(tigris)
library(sf)
library(ggplot2)
library(tidyverse)
library(stringr)
library(xml2)
library(tidyr)
library(httr)
library(rvest)
library(readxl)
#Pull divisions that aren't Pittsburgh
divisions = county_subdivisions(state = "PA",county=3,year=2022) %>%
filter(NAME != "Pittsburgh") %>%
mutate(Pittsburgh = 0) %>%
select(NAMELSAD,Pittsburgh,geometry) %>%
rename(NAME=NAMELSAD) %>%
st_transform(.,crs = 4326)
#Pull in Pittsburgh neighborhoods and append
Pittsburgh = st_sf(st_read("Data/Pittsburgh Neighborhoods/Neighborhoods_.shp")) %>%
rename(NAME=hood) %>%
mutate(Pittsburgh = 1) %>%
select(NAME,Pittsburgh,geometry) %>%
st_transform(.,crs = 4326)
#stack the shapefiles
areas = rbind(divisions,Pittsburgh)
areas2 = areas %>% st_drop_geometry() %>% mutate(JOIN_NAME = ifelse(Pittsburgh==0,toupper(NAME),"CITY OF PITTSBURGH"))
write.csv(areas2,"Data/Tax Rates/tax_rates.csv",row.names=F)
#Scrape Property Tax Rates
muni_tax = as.data.frame(read_html("https://apps.alleghenycounty.us/website/millmuni.asp") %>%
html_table(fill=TRUE) %>% .[2]) %>%
rename('Land_Municipal_Tax' = 'Land.1',
'JOIN_NAME'='Municipality',
'Municipality'='Millage')
allegheny_tax_rt = as.numeric(unlist(muni_tax %>% filter(JOIN_NAME == "Allegheny County") %>% select(Municipality)))
for(i in seq(from=1,to=dim(muni_tax)[1],by=1)){
if(str_detect(muni_tax[i,"JOIN_NAME"],"1")){
muni_tax[i,"JOIN_NAME"] = toupper(trimws(str_replace_all(muni_tax[i,"JOIN_NAME"],"1","")))
} else if(str_detect(muni_tax[i,"JOIN_NAME"],"2")){
muni_tax[i,"JOIN_NAME"] = toupper(trimws(str_replace_all(muni_tax[i,"JOIN_NAME"],"2","")))
} else if(str_detect(muni_tax[i,"JOIN_NAME"],"3")){
muni_tax[i,"JOIN_NAME"] = toupper(trimws(str_replace_all(muni_tax[i,"JOIN_NAME"],"3","")))
} else if(str_detect(muni_tax[i,"JOIN_NAME"],"4")){
muni_tax[i,"JOIN_NAME"] = toupper(trimws(str_replace_all(muni_tax[i,"JOIN_NAME"],"4","")))
} else if(str_detect(muni_tax[i,"JOIN_NAME"],"5")){
muni_tax[i,"JOIN_NAME"] = toupper(trimws(str_replace_all(muni_tax[i,"JOIN_NAME"],"5","")))
} else if(str_detect(muni_tax[i,"JOIN_NAME"],"6")){
muni_tax[i,"JOIN_NAME"] = toupper(trimws(str_replace_all(muni_tax[i,"JOIN_NAME"],"6","")))
} else if(str_detect(muni_tax[i,"JOIN_NAME"],"7")){
muni_tax[i,"JOIN_NAME"] = toupper(trimws(str_replace_all(muni_tax[i,"JOIN_NAME"],"7","")))
} else if(str_detect(muni_tax[i,"JOIN_NAME"],"8")){
muni_tax[i,"JOIN_NAME"] = toupper(trimws(str_replace_all(muni_tax[i,"JOIN_NAME"],"8","")))
} else if(str_detect(muni_tax[i,"JOIN_NAME"],"9")){
muni_tax[i,"JOIN_NAME"] = toupper(trimws(str_replace_all(muni_tax[i,"JOIN_NAME"],"9","")))
} else if(str_detect(muni_tax[i,"JOIN_NAME"],"0")){
muni_tax[i,"JOIN_NAME"] = toupper(trimws(str_replace_all(muni_tax[i,"JOIN_NAME"],"0","")))
} else {
muni_tax[i,"JOIN_NAME"] = toupper(trimws(muni_tax[i,"JOIN_NAME"]))
}
#Some manual overrides
if(muni_tax[i,"JOIN_NAME"]=="CITY OF DUQUESNE"){
muni_tax[i,"JOIN_NAME"]="DUQUESNE CITY"
} else if(muni_tax[i,"JOIN_NAME"]=="BETHEL PARK"){
muni_tax[i,"JOIN_NAME"]="BETHEL PARK MUNICIPALITY"
} else if(muni_tax[i,"JOIN_NAME"]=="CITY OF CLAIRTON"){
muni_tax[i,"JOIN_NAME"]="CLAIRTON CITY"
} else if(muni_tax[i,"JOIN_NAME"]=="PENNSBURY VILLAGE"){
muni_tax[i,"JOIN_NAME"]="PENNSBURY VILLAGE BOROUGH"
} else if(muni_tax[i,"JOIN_NAME"]=="CITY OF MCKEESPORT"){
muni_tax[i,"JOIN_NAME"]="MCKEESPORT CITY"
} else if(muni_tax[i,"JOIN_NAME"]=="MOUNT LEBANON"){
muni_tax[i,"JOIN_NAME"]="MOUNT LEBANON TOWNSHIP"
}
if(muni_tax[i,"Land_Municipal_Tax"] == "N/A") {
muni_tax[i,"Land_Municipal_Tax"] = ""
}
}
muni_tax$Land_Municipal_Tax = as.numeric(muni_tax$Land_Municipal_Tax)
#pull school tax rates
school_tax = as.data.frame(read_html("https://apps.alleghenycounty.us/website/millsd.asp") %>%
html_table(fill=TRUE) %>% .[2]) %>%
rename('Land_School_Tax' = 'Land..U.0095.',
'JOIN_NAME'='Municipality',
'School'='Millage',
'School District'='School.District') %>%
mutate(JOIN_NAME = toupper(JOIN_NAME))
for(i in seq(from=1,to=dim(school_tax)[1],by=1)){
#Some manual overrides
if(str_detect(school_tax[i,"School District"],"\u0095")){
school_tax[i,"School District"] = trimws(str_replace_all(school_tax[i,"School District"],"\u0095",""))
} else if(str_detect(school_tax[i,"School District"],"º")){
school_tax[i,"School District"] = trimws(str_replace_all(school_tax[i,"School District"],"º",""))
} else {
school_tax[i,"School District"] = trimws(school_tax[i,"School District"])
}
}
school_tax_final = NA
school_tax_started = FALSE
for(i in seq(from=1,to=dim(school_tax)[1],by=1)){
temp = unlist(str_split(school_tax[i,"JOIN_NAME"],","))
for(j in seq(from=1,to=length(temp),by=1)){
if(school_tax_started==FALSE){
school_tax_final = as.data.frame(t(c(trimws(temp[j]),
school_tax[i,"School District"],
school_tax[i,"School"],
school_tax[i,"Land_School_Tax"])))
school_tax_started = TRUE
} else {
school_tax_final = rbind(school_tax_final,
as.data.frame(t(c(trimws(temp[j]),
school_tax[i,"School District"],
school_tax[i,"School"],
school_tax[i,"Land_School_Tax"]))))
}
}
}
colnames(school_tax_final) = c("JOIN_NAME","School District","School","Land_School_Tax")
school_tax_final$School = as.numeric(school_tax_final$School)
school_tax_final$Land_School_Tax = as.numeric(school_tax_final$Land_School_Tax)
for(i in seq(from=1,to=dim(school_tax_final)[1],by=1)){
if(school_tax_final[i,"JOIN_NAME"]=="CITY OF DUQUESNE"){
school_tax_final[i,"JOIN_NAME"]="DUQUESNE CITY"
} else if(school_tax_final[i,"JOIN_NAME"]=="BETHEL PARK"){
school_tax_final[i,"JOIN_NAME"]="BETHEL PARK MUNICIPALITY"
} else if(school_tax_final[i,"JOIN_NAME"]=="CITY OF CLAIRTON"){
school_tax_final[i,"JOIN_NAME"]="CLAIRTON CITY"
} else if(school_tax_final[i,"JOIN_NAME"]=="PENNSBURY VILLAGE"){
school_tax_final[i,"JOIN_NAME"]="PENNSBURY VILLAGE BOROUGH"
} else if(school_tax_final[i,"JOIN_NAME"]=="CITY OF MCKEESPORT"){
school_tax_final[i,"JOIN_NAME"]="MCKEESPORT CITY"
} else if(school_tax_final[i,"JOIN_NAME"]=="MOUNT LEBANON"){
school_tax_final[i,"JOIN_NAME"]="MOUNT LEBANON TOWNSHIP"
}
}
#Read in income tax rates
income_tax = read_excel("Data/Tax Rates/Income_Tax_Rates.xlsx") %>%
rename("Income_Tax" = "Total Resident Income Tax (percent)",
"JOIN_NAME" = "Municipality") %>%
select(c("JOIN_NAME","Income_Tax")) %>%
unique()
#Fix for Baldwin-Whitehall SD...which has part inside Pittsburgh City Limits but has its own tax rates
income_tax = income_tax %>%
filter(JOIN_NAME != "PITTSBURGH CITY" | (JOIN_NAME == "PITTSBURGH CITY" & Income_Tax >= 3))
income_tax$Income_Tax =income_tax$Income_Tax/100
for(i in seq(from=1,to=dim(income_tax)[1],by=1)){
if(str_detect(income_tax[i,"JOIN_NAME"]," TWP")){
income_tax[i,"JOIN_NAME"] = trimws(str_replace_all(income_tax[i,"JOIN_NAME"]," TWP"," TOWNSHIP"))
} else if(str_detect(income_tax[i,"JOIN_NAME"]," BORO")){
income_tax[i,"JOIN_NAME"] = trimws(str_replace_all(income_tax[i,"JOIN_NAME"]," BORO"," BOROUGH"))
}
#Manual changes
if(income_tax[i,"JOIN_NAME"]=="UPPER ST CLAIR TOWNSHIP"){
income_tax[i,"JOIN_NAME"] = "UPPER ST. CLAIR TOWNSHIP"
} else if(income_tax[i,"JOIN_NAME"]=="MONROEVILLE BOROUGH"){
income_tax[i,"JOIN_NAME"] = "MONROEVILLE MUNICIPALITY"
} else if(income_tax[i,"JOIN_NAME"]=="BETHEL PARK BOROUGH"){
income_tax[i,"JOIN_NAME"] = "BETHEL PARK MUNICIPALITY"
} else if(income_tax[i,"JOIN_NAME"]=="MT LEBANON TOWNSHIP"){
income_tax[i,"JOIN_NAME"] = "MOUNT LEBANON TOWNSHIP"
} else if(income_tax[i,"JOIN_NAME"]=="OHARA TOWNSHIP"){
income_tax[i,"JOIN_NAME"] = "O'HARA TOWNSHIP"
} else if(income_tax[i,"JOIN_NAME"]=="PITTSBURGH CITY"){
income_tax[i,"JOIN_NAME"] = "CITY OF PITTSBURGH"
}
}
#Join it all together
taxes = areas2 %>% mutate(County = allegheny_tax_rt) %>%
left_join(.,muni_tax %>% select(c("JOIN_NAME","Municipality","Land_Municipal_Tax")),by=c("JOIN_NAME")) %>%
left_join(.,school_tax_final %>% select(c("JOIN_NAME","School District","School","Land_School_Tax")),by=c("JOIN_NAME")) %>%
left_join(.,income_tax,by=c("JOIN_NAME")) %>%
mutate(County = ifelse(is.na(County),NA,County/1000),
Municipality = ifelse(is.na(Municipality),NA,Municipality/1000),
Land_Municipal_Tax = ifelse(is.na(Land_Municipal_Tax),NA,Land_Municipal_Tax/1000),
School = ifelse(is.na(School),NA,School/1000),
Land_School_Tax = ifelse(is.na(Land_School_Tax),NA,Land_School_Tax/1000),
Library = ifelse(JOIN_NAME == "CITY OF PITTSBURGH",0.00025,NA),
Park = ifelse(JOIN_NAME == "CITY OF PITTSBURGH",0.00050,NA)) %>%
rowwise() %>%
mutate(Total_Property_Tax = sum(County,Municipality,School,Library,Park,na.rm = T))
taxes_clean = taxes %>%
rename("Land (Municipality Tax)" = "Land_Municipal_Tax",
"Land (School Tax)" = "Land_School_Tax",
"Total Property Tax"="Total_Property_Tax",
"Income Tax"="Income_Tax") %>%
select(-c("JOIN_NAME","Pittsburgh"))
#Join back to the shapefile
areas = areas %>% left_join(.,taxes_clean,by="NAME")
#write out file
st_write(areas,"Data/Allegheny County Neighborhoods/Allegheny_County_Neighborhoods.shp")
#Build cases for total tax paid
scenarios = NA
scenarios_found = FALSE
for(i in seq(from=50000,to=300000,by=5000)){
for(j in seq(from=100000,to=500000,by=5000)){
if(scenarios_found==FALSE){
scenarios = as.data.frame(t(c(i,j)))
scenarios_found = TRUE
} else {
scenarios = rbind(scenarios,as.data.frame(t(c(i,j))))
}
}
}
colnames(scenarios) = c("Income","Property_Price")
scenarios = taxes %>% full_join(.,scenarios, by = character()) %>%
mutate(CLR = 1.83) %>%
mutate(Total_Tax = Income_Tax*Income + ((Property_Price*(1/CLR))-18000)*County +(Property_Price*(1/CLR))*(Total_Property_Tax-County)) %>%
select(c("NAME","Income","Property_Price","Total_Tax")) %>%
rename("Property Purchase Price"="Property_Price",
"Total Local Tax"="Total_Tax")
write.csv(scenarios,"Data/tax_estimates.csv",row.names = F)