tidycensus::census_api_key(Sys.getenv("census_api"))## To install your API key for use in future sessions, run this function with `install = TRUE`.The city that I choose is Champaign, Illinois. ## Getting Census Tract Boundary for Champaign, IL
tract <- suppressMessages(
get_acs(geography = "tract",
state = "IL",
county = c("Champaign"),
variables = c(hhincome = 'B19019_001'),
year = 2021,
survey = "acs5",
geometry = TRUE,
output = "wide")
)
champaign <- tigris::places('IL') %>%
filter(NAME == 'Champaign') ## Retrieving data for the year 2022tract_champaign <- tract[champaign,]tract_champaign <- tract_champaign %>%
select(GEOID,
hhincome = hhincomeE)
tract_champaign <- tract_champaign %>%
filter(GEOID != "17019010604") #Removing one tract which is too large
tmap_mode("view")## tmap mode set to interactive viewingtm_shape(tract_champaign) + tm_polygons(col='brown', alpha=0.1) +
tm_shape(champaign) + tm_polygons(col = 'cyan', alpha = 0.4)Function to get tract-wise radius:
get_r <- function(poly, epsg_id){
bb <- st_bbox(poly)
bb_corner <- st_point(c(bb[1], bb[2])) %>% st_sfc(crs = epsg_id)
bb_center_x <- (bb[3]+bb[1])/2
bb_center_y <- (bb[4]+bb[2])/2
bb_center <- st_point(c(bb_center_x, bb_center_y)) %>% st_sfc(crs = epsg_id) %>% st_sf()
r <- st_distance(bb_corner, bb_center)
bb_center$radius <- r*1.1
return(bb_center)
}epsg_id <- 4326
r4all_apply <- tract_champaign %>%
st_geometry() %>%
st_transform(crs = epsg_id) %>%
lapply(., function(x) get_r(x, epsg_id = epsg_id))
r4all_apply <- bind_rows(r4all_apply)ready_4_yelp <- r4all_apply %>%
mutate(x = st_coordinates(.)[,1],
y = st_coordinates(.)[,2])tmap_mode('view')## tmap mode set to interactive viewingready_4_yelp %>%
# Draw a buffer centered at the centroid of Tract polygons.
# Radius of the buffer is the radius we just calculated using loop
st_buffer(., dist = .$radius) %>%
# Display this buffer in red
tm_shape(.) + tm_polygons(alpha = 0.2, col = 'red') +
# Display the original polygon in blue
tm_shape(tract_champaign) + tm_borders(col= 'blue')We can now start with writing a function using business_search in yelpr.
# FUNCTION
get_yelp <- function(tract, category){
# ----------------------------------
# Gets one row of tract information (1,) and category name (str),
# Outputs a list of business data.frame
Sys.sleep(1)
n <- 1
# First request --------------------------------------------------------------
resp <- business_search(api_key = Sys.getenv("yelp_api"),
term = category,
latitude = tract$y,
longitude = tract$x,
offset = (n - 1) * 50, # = 0 when n = 1
radius = round(tract$radius),
limit = 50)
# Calculate how many requests are needed in total
required_n <- ceiling(resp$total/50)
# out is where the results will be appended to.
out <- vector("list", required_n)
# Store the business information to nth slot in out
out[[n]] <- resp$businesses
# Change the name of the elements to the total required_n
# This is to know if there are more than 1000 businesses,
# we know how many.
names(out)[n] <- required_n
# Throw error if more than 1000
if (resp$total >= 1000)
{
# glue formats string by inserting {n} with what's currently stored in object n.
print(glue::glue("{n}th row has >= 1000 businesses."))
# Stop before going into the loop because we need to
# break down Census Tract to something smaller.
return(out)
}
else
{
# add 1 to n
n <- n + 1
# Now we know required_n -----------------------------------------------------
# Starting a loop
while(n <= required_n){
resp <- business_search(api_key = Sys.getenv("yelp_api"),
categories = category,
latitude = tract$y,
longitude = tract$x,
offset = (n - 1) * 50,
radius = round(tract$radius),
limit = 50)
out[[n]] <- resp$businesses
n <- n + 1
} #<< end of while loop
# Merge all elements in the list into a single data frame
out <- out %>% bind_rows()
return(out)
}
}We can loop through all census tracts to find two categories of businesses: gas station and auto repair.
# Prepare 2 collectors
yelp_all_list1 <- vector("list", nrow(ready_4_yelp))
yelp_all_list2 <- vector("list", nrow(ready_4_yelp))
# Looping through all Census Tracts
for (row in 1:nrow(ready_4_yelp)){
yelp_all_list1[[row]] <- suppressMessages(get_yelp(ready_4_yelp[row,], "gas stations"))
print(paste0("Current row: ", row))
}## [1] "Current row: 1"
## [1] "Current row: 2"
## [1] "Current row: 3"
## [1] "Current row: 4"
## [1] "Current row: 5"
## [1] "Current row: 6"
## [1] "Current row: 7"
## [1] "Current row: 8"
## [1] "Current row: 9"
## [1] "Current row: 10"
## [1] "Current row: 11"
## [1] "Current row: 12"
## [1] "Current row: 13"
## [1] "Current row: 14"
## [1] "Current row: 15"
## [1] "Current row: 16"
## [1] "Current row: 17"
## [1] "Current row: 18"
## [1] "Current row: 19"
## [1] "Current row: 20"
## [1] "Current row: 21"
## [1] "Current row: 22"
## [1] "Current row: 23"
## [1] "Current row: 24"
## [1] "Current row: 25"
## [1] "Current row: 26"for (row in 1:nrow(ready_4_yelp)){
yelp_all_list2[[row]] <- suppressMessages(get_yelp(ready_4_yelp[row,], "auto repair"))
print(paste0("Current row: ", row))
}## [1] "Current row: 1"
## [1] "Current row: 2"
## [1] "Current row: 3"
## [1] "Current row: 4"
## [1] "Current row: 5"
## [1] "Current row: 6"
## [1] "Current row: 7"
## [1] "Current row: 8"
## [1] "Current row: 9"
## [1] "Current row: 10"
## [1] "Current row: 11"
## [1] "Current row: 12"
## [1] "Current row: 13"
## [1] "Current row: 14"
## [1] "Current row: 15"
## [1] "Current row: 16"
## [1] "Current row: 17"
## [1] "Current row: 18"
## [1] "Current row: 19"
## [1] "Current row: 20"
## [1] "Current row: 21"
## [1] "Current row: 22"
## [1] "Current row: 23"
## [1] "Current row: 24"
## [1] "Current row: 25"
## [1] "Current row: 26"# Add a row indicating whether it is gas station or auto repair
yelp_all_list1 <- yelp_all_list1 %>% bind_rows() %>% as_tibble() %>% mutate(type = "gas station")
yelp_all_list2 <- yelp_all_list2 %>% bind_rows() %>% as_tibble() %>% mutate(type = "auto repair")
# Collapsing the list into a data.frame
yelp_all <- yelp_all_list1 %>% bind_rows(yelp_all_list2) %>% as_tibble()
# print
yelp_all %>% print(width=1000)## # A tibble: 653 × 19
## id alias
## <chr> <chr>
## 1 F7JWSELLVvDLBVBTVCmu0g circle-k-champaign
## 2 dY5bImdQbT_6V7_kPrn1HQ circle-k-champaign-10
## 3 vyCTd76g2aGqWvY1229ofw cvs-pharmacy-champaign-3
## 4 GKQWjnloUthLFGsSsrpZUw reynolds-towing-service-urbana-2
## 5 lAoWkjChB2BkvPJXWD3AFA road-ready-truck-and-tire-champaign
## 6 EO6ZQJwWdzTbcL3WMrWs0w mobil-champaign-3
## 7 4sKzg4-WSkucvHsjre4wcw costco-champaign
## 8 7JtxfWCmrKFnozNGK8Gj7A shell-champaign
## 9 CI85fp3NLH0GGoUXBk3Gzw circle-k-champaign-7
## 10 lVbQzYza0POviyTCBEnVjg mach-1-champaign-2
## name
## <chr>
## 1 Circle K
## 2 Circle K
## 3 CVS Pharmacy
## 4 Reynolds Towing Service
## 5 Road Ready Truck & Tire
## 6 Mobil
## 7 Costco
## 8 Shell
## 9 Circle K
## 10 Mach 1
## image_url
## <chr>
## 1 "https://s3-media4.fl.yelpcdn.com/bphoto/lODk-3lvG9jUxOiSQeSibQ/o.jpg"
## 2 "https://s3-media3.fl.yelpcdn.com/bphoto/RyxizO-1U5-1c0kg87T-pg/o.jpg"
## 3 "https://s3-media1.fl.yelpcdn.com/bphoto/7vRKcO6fIxSxaq7WKvroUw/o.jpg"
## 4 "https://s3-media3.fl.yelpcdn.com/bphoto/-6MytL-R4CMb1EJC7F_H6g/o.jpg"
## 5 ""
## 6 ""
## 7 "https://s3-media2.fl.yelpcdn.com/bphoto/7bee76lvKxAW6fJVMbUdDw/o.jpg"
## 8 ""
## 9 ""
## 10 "https://s3-media3.fl.yelpcdn.com/bphoto/EzzMPtxdTfbdIKZ4MpTU0g/o.jpg"
## is_closed
## <lgl>
## 1 FALSE
## 2 FALSE
## 3 FALSE
## 4 FALSE
## 5 FALSE
## 6 FALSE
## 7 FALSE
## 8 FALSE
## 9 FALSE
## 10 FALSE
## url
## <chr>
## 1 https://www.yelp.com/biz/circle-k-champaign?adjust_creative=4ZMcoYhbkuS8Q062…
## 2 https://www.yelp.com/biz/circle-k-champaign-10?adjust_creative=4ZMcoYhbkuS8Q…
## 3 https://www.yelp.com/biz/cvs-pharmacy-champaign-3?adjust_creative=4ZMcoYhbku…
## 4 https://www.yelp.com/biz/reynolds-towing-service-urbana-2?adjust_creative=4Z…
## 5 https://www.yelp.com/biz/road-ready-truck-and-tire-champaign?adjust_creative…
## 6 https://www.yelp.com/biz/mobil-champaign-3?adjust_creative=4ZMcoYhbkuS8Q062L…
## 7 https://www.yelp.com/biz/costco-champaign?adjust_creative=4ZMcoYhbkuS8Q062Le…
## 8 https://www.yelp.com/biz/shell-champaign?adjust_creative=4ZMcoYhbkuS8Q062Le5…
## 9 https://www.yelp.com/biz/circle-k-champaign-7?adjust_creative=4ZMcoYhbkuS8Q0…
## 10 https://www.yelp.com/biz/mach-1-champaign-2?adjust_creative=4ZMcoYhbkuS8Q062…
## review_count categories rating coordinates$latitude $longitude transactions
## <int> <list> <dbl> <dbl> <dbl> <list>
## 1 2 <df [2 × 2]> 2.5 40.1 -88.2 <chr [0]>
## 2 2 <df [2 × 2]> 1 40.1 -88.2 <chr [0]>
## 3 22 <df [3 × 2]> 2 40.1 -88.2 <chr [1]>
## 4 23 <df [1 × 2]> 3 40.1 -88.2 <chr [0]>
## 5 2 <df [3 × 2]> 3 40.2 -88.2 <chr [0]>
## 6 1 <df [1 × 2]> 1 40.1 -88.2 <list [0]>
## 7 19 <df [3 × 2]> 4 40.1 -88.2 <list [0]>
## 8 1 <df [2 × 2]> 1 40.1 -88.3 <list [0]>
## 9 1 <df [2 × 2]> 1 40.1 -88.3 <list [0]>
## 10 3 <df [2 × 2]> 2.3 40.1 -88.3 <list [0]>
## price location$address1 $address2 $address3 $city $zip_code $country
## <chr> <chr> <chr> <chr> <chr> <chr> <chr>
## 1 $ 1301 S Neil St <NA> <NA> Champaign 61820 US
## 2 <NA> 59 E Green St "" <NA> Champaign 61820 US
## 3 $$ 107 West Green St "" "" Champaign 61820 US
## 4 <NA> 1417 W Kenyon Rd "" "" Urbana 61801 US
## 5 <NA> 51 E Leverett Rd "" "" Champaign 61822 US
## 6 <NA> 1503 N Neil St "" <NA> Champaign 61820 US
## 7 $$ 2002 N Neil St "" <NA> Champaign 61820 US
## 8 <NA> 1406 N Prospect Ave "" <NA> Champaign 61820 US
## 9 <NA> 1511 N Prospect Ave "" <NA> Champaign 61820 US
## 10 $ 902 W Bloomington Rd "" "" Champaign 61821 US
## $state $display_address phone display_phone distance business_hours
## <chr> <list> <chr> <chr> <dbl> <list>
## 1 IL <chr [2]> +12173985868 (217) 398-5868 639. <df [1 × 3]>
## 2 IL <chr [2]> +12173448722 (217) 344-8722 1085. <df [1 × 3]>
## 3 IL <chr [2]> +12173558123 (217) 355-8123 706. <df [1 × 3]>
## 4 IL <chr [2]> +12173370913 (217) 337-0913 3630. <df [1 × 3]>
## 5 IL <chr [2]> +12176432800 (217) 643-2800 8243. <df [1 × 3]>
## 6 IL <chr [2]> +12173551872 (217) 355-1872 310. <df [1 × 3]>
## 7 IL <chr [2]> +12176006546 (217) 600-6546 1353. <df [1 × 3]>
## 8 IL <chr [2]> +12173984930 (217) 398-4930 1095. <df [1 × 3]>
## 9 IL <chr [2]> +12173555271 (217) 355-5271 1205. <df [1 × 3]>
## 10 IL <chr [2]> +12175008220 (217) 500-8220 1271. <df [1 × 3]>
## attributes$business_temp_closed $waitlist_reservation $menu_url $open24_hours
## <lgl> <lgl> <chr> <lgl>
## 1 NA NA <NA> NA
## 2 NA NA <NA> NA
## 3 NA NA <NA> NA
## 4 NA NA <NA> NA
## 5 NA NA <NA> NA
## 6 NA NA <NA> NA
## 7 NA NA <NA> NA
## 8 NA NA <NA> NA
## 9 NA NA <NA> NA
## 10 NA NA <NA> NA
## type
## <chr>
## 1 gas station
## 2 gas station
## 3 gas station
## 4 gas station
## 5 gas station
## 6 gas station
## 7 gas station
## 8 gas station
## 9 gas station
## 10 gas station
## # ℹ 643 more rows# Extract coordinates
yelp_sf <- yelp_all %>%
mutate(x = .$coordinates$longitude,
y = .$coordinates$latitude) %>%
filter(!is.na(x) & !is.na(y)) %>%
st_as_sf(coords = c("x", "y"), crs = 4326)Some results are not in our desired region. We can filter out the results that are in Champaign only.
tract_champaign_transformed <- st_transform(tract_champaign, 4326)
within_matrix <- st_within(yelp_sf, tract_champaign_transformed, sparse = FALSE)
within_vector <- apply(within_matrix, 1, any)
yelp_sf1 <- yelp_sf %>% filter(within_vector)
yelp_sf1## Simple feature collection with 495 features and 19 fields
## Geometry type: POINT
## Dimension: XY
## Bounding box: xmin: -88.31897 ymin: 40.05884 xmax: -88.20487 ymax: 40.15636
## Geodetic CRS: WGS 84
## # A tibble: 495 × 20
## id alias name image_url is_closed url review_count categories rating
## * <chr> <chr> <chr> <chr> <lgl> <chr> <int> <list> <dbl>
## 1 F7JWSEL… circ… Circ… "https:/… FALSE http… 2 <df> 2.5
## 2 dY5bImd… circ… Circ… "https:/… FALSE http… 2 <df> 1
## 3 vyCTd76… cvs-… CVS … "https:/… FALSE http… 22 <df> 2
## 4 GKQWjnl… reyn… Reyn… "https:/… FALSE http… 23 <df> 3
## 5 EO6ZQJw… mobi… Mobil "" FALSE http… 1 <df> 1
## 6 4sKzg4-… cost… Cost… "https:/… FALSE http… 19 <df> 4
## 7 7JtxfWC… shel… Shell "" FALSE http… 1 <df> 1
## 8 CI85fp3… circ… Circ… "" FALSE http… 1 <df> 1
## 9 lVbQzYz… mach… Mach… "https:/… FALSE http… 3 <df> 2.3
## 10 Zyq6S_M… circ… Circ… "https:/… FALSE http… 3 <df> 2.3
## # ℹ 485 more rows
## # ℹ 11 more variables: coordinates <df[,2]>, transactions <list>, price <chr>,
## # location <df[,8]>, phone <chr>, display_phone <chr>, distance <dbl>,
## # business_hours <list>, attributes <df[,4]>, type <chr>,
## # geometry <POINT [°]>There are a total of 496 businesses in Champaign for gas stations and auto repair.
nrow(yelp_sf1)## [1] 495There are 355 auto repair shops and 141 gas stations in Champaign area.
yelp_sf1 %>% count(type)## Simple feature collection with 2 features and 2 fields
## Geometry type: MULTIPOINT
## Dimension: XY
## Bounding box: xmin: -88.31897 ymin: 40.05884 xmax: -88.20487 ymax: 40.15636
## Geodetic CRS: WGS 84
## # A tibble: 2 × 3
## type n geometry
## * <chr> <int> <MULTIPOINT [°]>
## 1 auto repair 354 ((-88.31897 40.11364), (-88.31738 40.11496), (-88.31222 40.…
## 2 gas station 141 ((-88.31525 40.11371), (-88.28559 40.11257), (-88.28643 40.…Mapping out all gas stations and auto repairs in Champaign:
# Map
tm_shape(yelp_sf1) +
tm_dots(col = "type",
style="quantile",
shapes.labels="name",
popup.vars=c("Name"="name", "Reviews"="review_count", "Rating"="rating")
)Upon visual inspection, we can see that the gas stations and auto repair shops all have a clustering pattern along major highways, notably the north-south Neil Street and the east-west Springfield Avenue. There is also a significant cluster on the northern suburbs around the Interstate 74 and Towncenter Mall region.