Intro To Urban Analytics Mini Three
Siddhartha Baghel
2022-09-02
R Markdown
This is an R Markdown document for Mini 3!
client_secret <- "heiQtuO2RnUpIIOYNIBNwQI_prhD0_we8HyhuISPJTY14XXQ-n3B0McQUxofxO6oWMBU1rH4Z6tbsJ3P1IQsdA8D_zKSX7oFCrM1Yv4fpFGqq8-9wNAFmKbL3gchY3Yx"
#client_secret <- "d_8lzfKBfcZ1zp7QNd6DcLBDfQmnyio93Ab5DYjblRoh_75EL08VRMHFgW-0qm5zuChGQmPi7Ivm78TkIFXpe_2Cx20t4wNPNASZQlWPRUn-vOCaqeahzhScYi8qY3Yx"
Sys.getenv("CENSUS_API_KEY")## [1] "dd63c5ddc43a230bd9d8e634b9d9d1fc26703e3b"#state_pop <- get_decennial(geography = "state", variables = "P001001")
#head(state_pop)
tract <- suppressMessages(
get_acs(geography = ("tract"), # or "block group", "county", "state" etc.
state = ("GA"),
county = c("Fulton", "Dekalb"),
variables = c(hhincome = 'B19019_001',
race.tot = "B02001_001",
race.white = "B02001_002",
race.black = 'B02001_003',
trans.total = "B08006_001",
trans.car = "B08006_002",
trans.drovealone = "B08006_003",
trans.carpooled = "B08006_004", # Notice that I was not interested in 005-007 (2 person/ 4 person carpool etc.)
trans.pubtrans = "B08006_008", # Did not want to download any details about the type of public transport (009-0013)
trans.bicycle = "B08006_014",
trans.walk = "B08006_015",
trans.WfH = "B08006_017",
med_housexp = "B25104_001",
med_realestate_taxes = "B25103_001"
),
year = 2019,
survey = "acs5", # American Community Survey 5-year estimate
geometry = TRUE, # returns sf objects
output = "wide") # wide vs. long
)##
|
| | 0%
|
|= | 1%
|
|= | 2%
|
|== | 3%
|
|==== | 6%
|
|===== | 7%
|
|====== | 9%
|
|======= | 11%
|
|========= | 13%
|
|========== | 14%
|
|============ | 16%
|
|============ | 18%
|
|============== | 20%
|
|=============== | 21%
|
|================= | 24%
|
|================= | 25%
|
|=================== | 27%
|
|==================== | 29%
|
|====================== | 31%
|
|======================= | 32%
|
|======================== | 34%
|
|========================= | 36%
|
|=========================== | 38%
|
|============================ | 39%
|
|============================= | 42%
|
|============================== | 43%
|
|================================ | 45%
|
|================================= | 47%
|
|================================== | 49%
|
|=================================== | 50%
|
|===================================== | 52%
|
|====================================== | 54%
|
|======================================= | 56%
|
|======================================== | 57%
|
|========================================== | 60%
|
|=========================================== | 61%
|
|============================================ | 63%
|
|============================================= | 64%
|
|=============================================== | 67%
|
|================================================ | 68%
|
|================================================= | 70%
|
|================================================== | 72%
|
|==================================================== | 74%
|
|===================================================== | 75%
|
|====================================================== | 77%
|
|======================================================= | 79%
|
|========================================================= | 81%
|
|========================================================== | 82%
|
|=========================================================== | 85%
|
|============================================================ | 86%
|
|============================================================== | 88%
|
|=============================================================== | 90%
|
|================================================================ | 92%
|
|================================================================= | 93%
|
|=================================================================== | 95%
|
|==================================================================== | 97%
|
|===================================================================== | 99%
|
|======================================================================| 100%message(sprintf("nrow: %s, ncol: %s", nrow(tract), ncol(tract)))## nrow: 349, ncol: 31#print(tract)
tract <- tract %>%
select(GEOID,
county = NAME,
hhincome = hhincomeE, # New name = old name
race.tot = race.totE,
race.white = race.whiteE,
race.black = race.blackE,
trans.total = trans.totalE,
trans.car = trans.carE,
trans.drovealone = trans.drovealoneE,
trans.carpooled = trans.carpooledE,
trans.pubtrans = trans.pubtransE,
trans.bicycle = trans.bicycleE,
trans.walk = trans.walkE,
trans.WfH = trans.WfHE,
Med_HHExp = med_housexpE,
med_RETaxes = med_realestate_taxesE)
#DISPLAY NEW FOR FULTON
tmap_mode("view")## tmap mode set to interactive viewing## tmap mode set to interactive viewing
RE_Taxes <- tm_shape(tract) + tm_polygons("med_RETaxes")
HH_exp <- tm_shape(tract) + tm_polygons("Med_HHExp")
tmap_arrange(RE_Taxes, HH_exp)#END DISPLAY FOR FULTON
#print(tract)
#print tract after
tmap_mode("view")## tmap mode set to interactive viewingtm_shape(tract) + tm_borders()Draw Tracts
# Function: Get tract-wise radius
get_r <- function(poly, epsg_id){
#---------------------
# Takes: a single POLYGON or LINESTRTING
# Outputs: distance between the centroid of the boundingbox and a corner of the bounding box
#---------------------
# Get bounding box of a given polygon
bb <- st_bbox(poly)
# Get lat & long coordinates of any one corner of the bounding box.
bb_corner <- st_point(c(bb[1], bb[2])) %>% st_sfc(crs = epsg_id)
# Get centroid of the bb
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()
# Get the distance between bb_p and c
r <- st_distance(bb_corner, bb_center)
# Multiply 1.1 to make the circle a bit larger than the Census Tract.
# See the Yelp explanation of their radius parameter to see why we do this.
bb_center$radius <- r*1.2
return(bb_center)
}
## Using a loop -----------------------------------------------------------------
# Creating an empty vector of NA.
# Results will fill this vector
epsg_id <- 4326 # Edit (9/8/2022): 4326 measures distance in meter. Before the edit, I used 26967.
r4all_loop <- vector("list", nrow(tract))
# Starting a for-loop
for (i in 1:nrow(tract)){
r4all_loop[[i]] <- tract %>%
st_transform(crs = epsg_id) %>%
st_geometry() %>%
.[[i]] %>%
get_r(epsg_id = epsg_id)
}
r4all_loop <- bind_rows(r4all_loop)
# Using a functional -----------------------------------------------------------
# We use a functional (sapply) to apply this custom function to each Census Tract.
r4all_apply <- tract %>%
st_geometry() %>%
st_transform(crs = epsg_id) %>%
lapply(., function(x) get_r(x, epsg_id = epsg_id))
r4all_apply <- bind_rows(r4all_apply)
# Are these two identical?
identical(r4all_apply, r4all_loop)## [1] TRUEready_4_yelp <- r4all_apply %>%
mutate(x = st_coordinates(.)[,1],
y = st_coordinates(.)[,2])
tmap_mode('view')## tmap mode set to interactive viewing# Select the first 10 rows
ready_4_yelp[1:10,] %>%
# Draw a buffer centered at the centroid of Tract polygons.
# Radius of the buffer is the radius we just calculated using loop
st_buffer(., dist = .$radius) %>%
# Display this buffer in red
tm_shape(.) + tm_polygons(alpha = 0.5, col = 'red') +
# Display the original polygon in blue
tm_shape(tract[1:10,]) + tm_borders(col= 'blue')which_tract <- 1
test <- business_search(api_key = client_secret, # like we did for census, store your api key
categories = 'bikerentals', # return only restaurant businesses
latitude = ready_4_yelp$y[which_tract],
longitude = ready_4_yelp$x[which_tract],
offset = 0, # 1st page, 1st obs
radius = round(ready_4_yelp$radius[which_tract]), # radius requires integer value
limit = 50) # how many business per page## No encoding supplied: defaulting to UTF-8.test1 <- business_search(api_key = client_secret, # like we did for census, store your api key
categories = 'restaurants', # return only restaurant businesses
latitude = ready_4_yelp$y[which_tract],
longitude = ready_4_yelp$x[which_tract],
offset = 0, # 1st page, 1st obs
radius = round(ready_4_yelp$radius[which_tract]), # radius requires integer value
limit = 50) # how many business per page## No encoding supplied: defaulting to UTF-8.lapply(test, head)## $businesses
## list()
##
## $total
## [1] 0
##
## $region
## $region$center
## $region$center$longitude
## [1] -84.38286
##
## $region$center$latitude
## [1] 33.78421names(test)## [1] "businesses" "total" "region"paste0("is it a data.frame?: ", is.data.frame(test$businesses), ", ",
" how many rows?: ", nrow(test$businesses), ", ",
" how many columns?: ", ncol(test$businesses))## [1] "is it a data.frame?: FALSE, how many rows?: , how many columns?: "# FUNCTION
get_yelp <- function(tract, category){
# ----------------------------------
# Gets one row of tract information (1,) and category name (str),
# Outputs a list of business data.frame
n <- 1
# First request --------------------------------------------------------------
resp <- business_search(api_key = client_secret,
categories = 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 = client_secret,
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)
}
}
yelp_first_tract <- get_yelp(ready_4_yelp[1,], "bikerentals") %>%
as_tibble()## No encoding supplied: defaulting to UTF-8.## Warning: Outer names are only allowed for unnamed scalar atomic inputsyelp_first_tract %>% print## # A tibble: 0 × 0# Prepare a collector
yelp_all_list <- vector("list", nrow(ready_4_yelp))
# Looping through all Census Tracts
for (row in 1:nrow(ready_4_yelp)){
yelp_all_list[[row]] <- suppressMessages(get_yelp(ready_4_yelp[row,], "bikerentals"))
if (row %% 50 == 0){
print(paste0("Current row: ", row))
}
Sys.sleep(.5)}## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs## [1] "Current row: 50"## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs## [1] "Current row: 100"## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs## [1] "Current row: 150"## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs## [1] "Current row: 200"## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs## [1] "Current row: 250"## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs## [1] "Current row: 300"## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs
## Warning: Outer names are only allowed for unnamed scalar atomic inputs#Start Test For Second Category
#yelp_first_tract1 <- get_yelp(ready_4_yelp[1,], "indpak") %>%
# as_tibble()
#yelp_first_tract1 %>% print
# Prepare a collector
#yelp_all_list1 <- 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,], "indpak"))
# if (row %% 50 == 0){
# print(paste0("Current row: ", row))
# }
# Sys.sleep(.5)
#}
#yelp_all_list <- c(yelp_all_list1,yelp_all_list)
#End Test For Second Category
# Collapsing the list into a data.frame
yelp_all <- yelp_all_list %>% bind_rows() %>% as_tibble()
# print
yelp_all %>% print(width=1000)## # A tibble: 208 × 16
## id alias
## <chr> <chr>
## 1 FK7-M9BGyCgpEmVifcPfoA aztec-cycles-stone-mountain
## 2 FK7-M9BGyCgpEmVifcPfoA aztec-cycles-stone-mountain
## 3 JkkHRgYj0mvdgbMXFm436w civil-bikes-atlanta
## 4 FK7-M9BGyCgpEmVifcPfoA aztec-cycles-stone-mountain
## 5 UmftRC3h0h_owHEm5ZLp7Q jump-atlanta-2
## 6 FK7-M9BGyCgpEmVifcPfoA aztec-cycles-stone-mountain
## 7 JkkHRgYj0mvdgbMXFm436w civil-bikes-atlanta
## 8 kJJiJqGbiO_QXmdhol3hIQ british-and-american-bikes-atlanta
## 9 FK7-M9BGyCgpEmVifcPfoA aztec-cycles-stone-mountain
## 10 ot4UyUsRAlTFudTlCVRMrQ pedego-electric-bikes-alpharetta-alpharetta
## name
## <chr>
## 1 Aztec Cycles
## 2 Aztec Cycles
## 3 Civil Bikes
## 4 Aztec Cycles
## 5 JUMP
## 6 Aztec Cycles
## 7 Civil Bikes
## 8 British and American Bikes
## 9 Aztec Cycles
## 10 Pedego Electric Bikes Alpharetta
## image_url
## <chr>
## 1 https://s3-media3.fl.yelpcdn.com/bphoto/re-aoEuun-QS1SE7dQCySQ/o.jpg
## 2 https://s3-media3.fl.yelpcdn.com/bphoto/re-aoEuun-QS1SE7dQCySQ/o.jpg
## 3 https://s3-media4.fl.yelpcdn.com/bphoto/JqTLT-chrqtbyuoB-52gdw/o.jpg
## 4 https://s3-media3.fl.yelpcdn.com/bphoto/re-aoEuun-QS1SE7dQCySQ/o.jpg
## 5 https://s3-media2.fl.yelpcdn.com/bphoto/D87H00XdLWZJS-LvQkTalA/o.jpg
## 6 https://s3-media3.fl.yelpcdn.com/bphoto/re-aoEuun-QS1SE7dQCySQ/o.jpg
## 7 https://s3-media4.fl.yelpcdn.com/bphoto/JqTLT-chrqtbyuoB-52gdw/o.jpg
## 8 https://s3-media2.fl.yelpcdn.com/bphoto/9I0G3Ge2yKFg6184t1XYEQ/o.jpg
## 9 https://s3-media3.fl.yelpcdn.com/bphoto/re-aoEuun-QS1SE7dQCySQ/o.jpg
## 10 https://s3-media2.fl.yelpcdn.com/bphoto/gPNidtknlSWKu3Bh4iOJ3Q/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/aztec-cycles-stone-mountain?adjust_creative=2LH0tJl…
## 2 https://www.yelp.com/biz/aztec-cycles-stone-mountain?adjust_creative=2LH0tJl…
## 3 https://www.yelp.com/biz/civil-bikes-atlanta?adjust_creative=2LH0tJl-lVjcpTq…
## 4 https://www.yelp.com/biz/aztec-cycles-stone-mountain?adjust_creative=2LH0tJl…
## 5 https://www.yelp.com/biz/jump-atlanta-2?adjust_creative=2LH0tJl-lVjcpTqQqmZP…
## 6 https://www.yelp.com/biz/aztec-cycles-stone-mountain?adjust_creative=2LH0tJl…
## 7 https://www.yelp.com/biz/civil-bikes-atlanta?adjust_creative=2LH0tJl-lVjcpTq…
## 8 https://www.yelp.com/biz/british-and-american-bikes-atlanta?adjust_creative=…
## 9 https://www.yelp.com/biz/aztec-cycles-stone-mountain?adjust_creative=2LH0tJl…
## 10 https://www.yelp.com/biz/pedego-electric-bikes-alpharetta-alpharetta?adjust_…
## review_count categories rating coordinates$latitude $longitude transactions
## <int> <list> <dbl> <dbl> <dbl> <list>
## 1 54 <df [3 × 2]> 5 33.8 -84.2 <list [0]>
## 2 54 <df [3 × 2]> 5 33.8 -84.2 <list [0]>
## 3 9 <df [2 × 2]> 4.5 33.7 -84.4 <list [0]>
## 4 54 <df [3 × 2]> 5 33.8 -84.2 <list [0]>
## 5 1 <df [2 × 2]> 1 33.7 -84.4 <list [0]>
## 6 54 <df [3 × 2]> 5 33.8 -84.2 <list [0]>
## 7 9 <df [2 × 2]> 4.5 33.7 -84.4 <list [0]>
## 8 2 <df [2 × 2]> 5 33.9 -84.3 <list [0]>
## 9 54 <df [3 × 2]> 5 33.8 -84.2 <list [0]>
## 10 7 <df [3 × 2]> 5 34.0 -84.3 <list [0]>
## price location$address1 $address2 $address3 $city
## <chr> <chr> <chr> <chr> <chr>
## 1 $$ "901 Main St" "" "" Stone Mountain
## 2 $$ "901 Main St" "" "" Stone Mountain
## 3 <NA> "" <NA> "" Atlanta
## 4 $$ "901 Main St" "" "" Stone Mountain
## 5 <NA> "" "" <NA> Atlanta
## 6 $$ "901 Main St" "" "" Stone Mountain
## 7 <NA> "" <NA> "" Atlanta
## 8 <NA> "4264 F Winters Chapel Rd" "" "" Atlanta
## 9 $$ "901 Main St" "" "" Stone Mountain
## 10 <NA> "6480 N Point Pkwy" "Ste 1100b" <NA> Alpharetta
## $zip_code $country $state $display_address phone display_phone
## <chr> <chr> <chr> <list> <chr> <chr>
## 1 30083 US GA <chr [2]> +16786369043 (678) 636-9043
## 2 30083 US GA <chr [2]> +16786369043 (678) 636-9043
## 3 30312 US GA <chr [1]> +14043238754 (404) 323-8754
## 4 30083 US GA <chr [2]> +16786369043 (678) 636-9043
## 5 30301 US GA <chr [1]> +18333006106 (833) 300-6106
## 6 30083 US GA <chr [2]> +16786369043 (678) 636-9043
## 7 30312 US GA <chr [1]> +14043238754 (404) 323-8754
## 8 30360 US GA <chr [2]> +17704518868 (770) 451-8868
## 9 30083 US GA <chr [2]> +16786369043 (678) 636-9043
## 10 30022 US GA <chr [3]> +14042810264 (404) 281-0264
## distance
## <dbl>
## 1 22818.
## 2 29547.
## 3 366.
## 4 20724.
## 5 1238.
## 6 20887.
## 7 527.
## 8 1715.
## 9 1921.
## 10 2501.
## # … with 198 more rows
## # ℹ Use `print(n = ...)` to see 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)
# Map
tm_shape(yelp_sf) +
tm_dots(col = "review_count", style="quantile")yelp_unique <- yelp_all %>%
distinct(id, .keep_all=T)
glue::glue("Before dropping NA, there were {nrow(yelp_all)} rows. After dropping them, there are {nrow(yelp_unique)} rows") %>%
print()## Before dropping NA, there were 208 rows. After dropping them, there are 16 rows#This makes sense as the Map only shows 8 points!!!
concate_list <- function(x){
# x is a data frame with columns "alias" and "title" from Yelp$categories
# returns a character vector containing category concatenated titles
titles <- x[["title"]] %>% str_c(collapse = ", ")
return(titles)
}
# Custom function that takes the data frame in "categories" column in Yelp data
# and returns a character vector
# Issue 3 ------------------------------
yelp_flat <- yelp_unique %>%
# 1. Flattening columns with data frame
jsonlite::flatten() %>%
# 2. Handling list-columns
mutate(transactions = transactions %>%
map_chr(., function(x) str_c(x, collapse=", ")),
location.display_address = location.display_address %>%
map_chr(., function(x) str_c(x, collapse=", ")),
categories = categories %>% map_chr(concate_list)) # concate_list is the custom function
yelp_flat %>%
map_dbl(., function(x) sum(is.na(x)))## id alias name
## 0 0 0
## image_url is_closed url
## 0 0 0
## review_count categories rating
## 0 0 0
## transactions price phone
## 0 9 0
## display_phone distance coordinates.latitude
## 0 0 0
## coordinates.longitude location.address1 location.address2
## 0 1 5
## location.address3 location.city location.zip_code
## 7 0 0
## location.country location.state location.display_address
## 0 0 0identical(is.na(yelp_flat$coordinates.latitude),
is.na(yelp_flat$coordinates.longitude))## [1] TRUEyelp_dropna1 <- yelp_flat %>%
drop_na(coordinates.longitude)
# Dropping NAs in price
yelp_dropna2 <- yelp_dropna1 %>%
drop_na(price)
census <- tract
yelp_sf <- yelp_dropna2 %>%
st_as_sf(coords=c("coordinates.longitude", "coordinates.latitude"), crs = 4326)
# sf subsets
print(st_crs(yelp_sf))## Coordinate Reference System:
## User input: EPSG:4326
## wkt:
## GEOGCRS["WGS 84",
## DATUM["World Geodetic System 1984",
## ELLIPSOID["WGS 84",6378137,298.257223563,
## LENGTHUNIT["metre",1]]],
## PRIMEM["Greenwich",0,
## ANGLEUNIT["degree",0.0174532925199433]],
## CS[ellipsoidal,2],
## AXIS["geodetic latitude (Lat)",north,
## ORDER[1],
## ANGLEUNIT["degree",0.0174532925199433]],
## AXIS["geodetic longitude (Lon)",east,
## ORDER[2],
## ANGLEUNIT["degree",0.0174532925199433]],
## USAGE[
## SCOPE["Horizontal component of 3D system."],
## AREA["World."],
## BBOX[-90,-180,90,180]],
## ID["EPSG",4326]]print(st_crs(tract))## Coordinate Reference System:
## User input: NAD83
## wkt:
## GEOGCRS["NAD83",
## DATUM["North American Datum 1983",
## ELLIPSOID["GRS 1980",6378137,298.257222101,
## LENGTHUNIT["metre",1]]],
## PRIMEM["Greenwich",0,
## ANGLEUNIT["degree",0.0174532925199433]],
## CS[ellipsoidal,2],
## AXIS["latitude",north,
## ORDER[1],
## ANGLEUNIT["degree",0.0174532925199433]],
## AXIS["longitude",east,
## ORDER[2],
## ANGLEUNIT["degree",0.0174532925199433]],
## ID["EPSG",4269]]crs_to_use <- st_crs(yelp_sf) # store crs information from the van_boundary dataset
crs_epsg <- crs_to_use$epsg # store the epsg code from the van_boundary dataset
tract <- st_transform(tract,crs=crs_epsg)
yelp_in <- yelp_sf[tract %>% st_union(), ,op = st_intersects]
glue::glue("nrow before: {nrow(yelp_all)} -> nrow after: {nrow(yelp_in)} \n
ncol before: {ncol(yelp_all)} -> ncol after: {ncol(yelp_in)} \n") %>%
print()## nrow before: 208 -> nrow after: 6
##
## ncol before: 16 -> ncol after: 23print(colnames(yelp_in))## [1] "id" "alias"
## [3] "name" "image_url"
## [5] "is_closed" "url"
## [7] "review_count" "categories"
## [9] "rating" "transactions"
## [11] "price" "phone"
## [13] "display_phone" "distance"
## [15] "location.address1" "location.address2"
## [17] "location.address3" "location.city"
## [19] "location.zip_code" "location.country"
## [21] "location.state" "location.display_address"
## [23] "geometry"tmap_mode("view")## tmap mode set to interactive viewingtm_shape(yelp_in) + tm_dots(col = "price")head(tract)## Simple feature collection with 6 features and 16 fields
## Geometry type: MULTIPOLYGON
## Dimension: XY
## Bounding box: xmin: -84.41692 ymin: 33.72043 xmax: -84.33426 ymax: 33.97001
## Geodetic CRS: WGS 84
## GEOID county hhincome race.tot
## 1 13121001100 Census Tract 11, Fulton County, Georgia 109426 5193
## 2 13121009603 Census Tract 96.03, Fulton County, Georgia 83243 4830
## 3 13121005800 Census Tract 58, Fulton County, Georgia 42679 1479
## 4 13121010117 Census Tract 101.17, Fulton County, Georgia 60731 4319
## 5 13121009502 Census Tract 95.02, Fulton County, Georgia 86053 3867
## 6 13089021213 Census Tract 212.13, DeKalb County, Georgia 154063 3526
## race.white race.black trans.total trans.car trans.drovealone trans.carpooled
## 1 4060 299 3972 2482 2350 132
## 2 3561 749 3293 2786 2742 44
## 3 300 1057 736 398 341 57
## 4 1701 2007 2941 2346 2217 129
## 5 2627 796 2087 1774 1593 181
## 6 3196 67 1365 1098 981 117
## trans.pubtrans trans.bicycle trans.walk trans.WfH Med_HHExp med_RETaxes
## 1 276 71 632 455 3432 3699
## 2 63 0 22 303 3071 4869
## 3 271 12 43 12 576 493
## 4 178 24 15 282 1962 1330
## 5 17 0 62 161 2254 1993
## 6 36 0 0 213 1205 5987
## geometry
## 1 MULTIPOLYGON (((-84.38782 3...
## 2 MULTIPOLYGON (((-84.38738 3...
## 3 MULTIPOLYGON (((-84.41692 3...
## 4 MULTIPOLYGON (((-84.36575 3...
## 5 MULTIPOLYGON (((-84.39472 3...
## 6 MULTIPOLYGON (((-84.34783 3...head(yelp_in)## Simple feature collection with 6 features and 22 fields
## Geometry type: POINT
## Dimension: XY
## Bounding box: xmin: -84.36515 ymin: 33.75833 xmax: -84.16982 ymax: 34.05956
## Geodetic CRS: WGS 84
## id alias name
## 1 FK7-M9BGyCgpEmVifcPfoA aztec-cycles-stone-mountain Aztec Cycles
## 2 LsNS77QoD4wauKgGeCfxPQ dads-emissions-decatur-4 Dad's Emissions
## 3 b3nacMG8PR77GNCaI4RBKA atlanta-bicycle-barn-atlanta Atlanta Bicycle Barn
## 4 BozJwfoXvoDEUj-sgr7WDg podium-multisport-atlanta Podium Multisport
## 5 OJVvH1CUZacuHjSLkhSKOg roswell-bicycles-roswell Roswell Bicycles
## 6 cRTM5f8ATvVr9lrKcOnWgg the-sport-factory-roswell The Sport Factory
## image_url
## 1 https://s3-media3.fl.yelpcdn.com/bphoto/re-aoEuun-QS1SE7dQCySQ/o.jpg
## 2 https://s3-media3.fl.yelpcdn.com/bphoto/_W7WHceEBLyPI86R2-3-Vw/o.jpg
## 3 https://s3-media3.fl.yelpcdn.com/bphoto/Ik2pMce41_MRcg3svjTbSQ/o.jpg
## 4 https://s3-media1.fl.yelpcdn.com/bphoto/T78pUkBulcQ5osv4mVGTiQ/o.jpg
## 5 https://s3-media2.fl.yelpcdn.com/bphoto/1YUjKn4QEkVQG_eIH7wiXQ/o.jpg
## 6 https://s3-media2.fl.yelpcdn.com/bphoto/KbtggaK_z06YtHcweq5beg/o.jpg
## is_closed
## 1 FALSE
## 2 FALSE
## 3 FALSE
## 4 FALSE
## 5 FALSE
## 6 FALSE
## url
## 1 https://www.yelp.com/biz/aztec-cycles-stone-mountain?adjust_creative=2LH0tJl-lVjcpTqQqmZPWQ&utm_campaign=yelp_api_v3&utm_medium=api_v3_business_search&utm_source=2LH0tJl-lVjcpTqQqmZPWQ
## 2 https://www.yelp.com/biz/dads-emissions-decatur-4?adjust_creative=2LH0tJl-lVjcpTqQqmZPWQ&utm_campaign=yelp_api_v3&utm_medium=api_v3_business_search&utm_source=2LH0tJl-lVjcpTqQqmZPWQ
## 3 https://www.yelp.com/biz/atlanta-bicycle-barn-atlanta?adjust_creative=2LH0tJl-lVjcpTqQqmZPWQ&utm_campaign=yelp_api_v3&utm_medium=api_v3_business_search&utm_source=2LH0tJl-lVjcpTqQqmZPWQ
## 4 https://www.yelp.com/biz/podium-multisport-atlanta?adjust_creative=2LH0tJl-lVjcpTqQqmZPWQ&utm_campaign=yelp_api_v3&utm_medium=api_v3_business_search&utm_source=2LH0tJl-lVjcpTqQqmZPWQ
## 5 https://www.yelp.com/biz/roswell-bicycles-roswell?adjust_creative=2LH0tJl-lVjcpTqQqmZPWQ&utm_campaign=yelp_api_v3&utm_medium=api_v3_business_search&utm_source=2LH0tJl-lVjcpTqQqmZPWQ
## 6 https://www.yelp.com/biz/the-sport-factory-roswell?adjust_creative=2LH0tJl-lVjcpTqQqmZPWQ&utm_campaign=yelp_api_v3&utm_medium=api_v3_business_search&utm_source=2LH0tJl-lVjcpTqQqmZPWQ
## review_count categories rating transactions
## 1 54 Bikes, Bike Repair/Maintenance, Bike Rentals 5.0
## 2 64 Smog Check Stations, Bikes, Bike Rentals 4.5
## 3 124 Bike Rentals, Bike Repair/Maintenance, Bikes 4.5
## 4 19 Bikes, Bike Rentals 4.5
## 5 70 Bikes, Bike Rentals 4.0
## 6 1 Bike Repair/Maintenance, Bikes, Bike Rentals 1.0
## price phone display_phone distance location.address1
## 1 $$ +16786369043 (678) 636-9043 22817.680 901 Main St
## 2 $ +14042946644 (404) 294-6644 1427.664 1707 Church St
## 3 $$ +17708732413 (770) 873-2413 1191.788 151 Sampson St NE
## 4 $$$ +14048923400 (404) 892-3400 2221.750 1167 Zonolite Pl NE
## 5 $$$ +17706424057 (770) 642-4057 2841.926 670 Houze Way
## 6 $$$$ +16783889835 (678) 388-9835 2253.020 720 Hembree Pl
## location.address2 location.address3 location.city location.zip_code
## 1 Stone Mountain 30083
## 2 <NA> <NA> Decatur 30030
## 3 Atlanta 30312
## 4 Ste A2 Atlanta 30306
## 5 Roswell 30076
## 6 <NA> Roswell 30076
## location.country location.state
## 1 US GA
## 2 US GA
## 3 US GA
## 4 US GA
## 5 US GA
## 6 US GA
## location.display_address geometry
## 1 901 Main St, Stone Mountain, GA 30083 POINT (-84.16982 33.80586)
## 2 1707 Church St, Decatur, GA 30030 POINT (-84.28105 33.79757)
## 3 151 Sampson St NE, Atlanta, GA 30312 POINT (-84.36515 33.75833)
## 4 1167 Zonolite Pl NE, Ste A2, Atlanta, GA 30306 POINT (-84.34143 33.8051)
## 5 670 Houze Way, Roswell, GA 30076 POINT (-84.34202 34.04687)
## 6 720 Hembree Pl, Roswell, GA 30076 POINT (-84.31985 34.05956)bikeRental_in_tract <- st_join(tract, yelp_in, join = st_intersects)
skim(bikeRental_in_tract)## Warning: Couldn't find skimmers for class: sfc_MULTIPOLYGON, sfc; No user-
## defined `sfl` provided. Falling back to `character`.| Name | bikeRental_in_tract |
| Number of rows | 349 |
| Number of columns | 39 |
| _______________________ | |
| Column type frequency: | |
| character | 21 |
| logical | 1 |
| numeric | 17 |
| ________________________ | |
| Group variables | None |
Variable type: character
| skim_variable | n_missing | complete_rate | min | max | empty | n_unique | whitespace |
|---|---|---|---|---|---|---|---|
| GEOID | 0 | 1.00 | 11 | 11 | 0 | 349 | 0 |
| county | 0 | 1.00 | 38 | 43 | 0 | 349 | 0 |
| id | 343 | 0.02 | 22 | 22 | 0 | 6 | 0 |
| alias | 343 | 0.02 | 24 | 28 | 0 | 6 | 0 |
| name | 343 | 0.02 | 12 | 20 | 0 | 6 | 0 |
| image_url | 343 | 0.02 | 68 | 68 | 0 | 6 | 0 |
| url | 343 | 0.02 | 181 | 185 | 0 | 6 | 0 |
| categories | 343 | 0.02 | 19 | 44 | 0 | 5 | 0 |
| transactions | 343 | 0.02 | 0 | 0 | 6 | 1 | 0 |
| price | 343 | 0.02 | 1 | 4 | 0 | 4 | 0 |
| phone | 343 | 0.02 | 12 | 12 | 0 | 6 | 0 |
| display_phone | 343 | 0.02 | 14 | 14 | 0 | 6 | 0 |
| location.address1 | 343 | 0.02 | 11 | 19 | 0 | 6 | 0 |
| location.address2 | 344 | 0.01 | 0 | 6 | 4 | 2 | 0 |
| location.address3 | 345 | 0.01 | 0 | 0 | 4 | 1 | 0 |
| location.city | 343 | 0.02 | 7 | 14 | 0 | 4 | 0 |
| location.zip_code | 343 | 0.02 | 5 | 5 | 0 | 5 | 0 |
| location.country | 343 | 0.02 | 2 | 2 | 0 | 1 | 0 |
| location.state | 343 | 0.02 | 2 | 2 | 0 | 1 | 0 |
| location.display_address | 343 | 0.02 | 32 | 46 | 0 | 6 | 0 |
| geometry | 0 | 1.00 | 174 | 3684 | 0 | 349 | 0 |
Variable type: logical
| skim_variable | n_missing | complete_rate | mean | count |
|---|---|---|---|---|
| is_closed | 343 | 0.02 | 0 | FAL: 6 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| hhincome | 4 | 0.99 | 73209.99 | 41838.74 | 12485.00 | 42517.00 | 63269.00 | 92404.00 | 236149.00 | ▇▆▂▁▁ |
| race.tot | 0 | 1.00 | 5116.11 | 2794.29 | 0.00 | 3242.00 | 4599.00 | 6224.00 | 21010.00 | ▆▇▁▁▁ |
| race.white | 0 | 1.00 | 2061.66 | 1960.52 | 0.00 | 286.00 | 1618.00 | 3378.00 | 12764.00 | ▇▅▁▁▁ |
| race.black | 0 | 1.00 | 2469.18 | 2750.80 | 0.00 | 658.00 | 1433.00 | 3215.00 | 19263.00 | ▇▂▁▁▁ |
| trans.total | 0 | 1.00 | 2579.90 | 1461.48 | 0.00 | 1515.00 | 2426.00 | 3358.00 | 9813.00 | ▆▇▂▁▁ |
| trans.car | 0 | 1.00 | 2062.77 | 1295.37 | 0.00 | 1105.00 | 1945.00 | 2726.00 | 8545.00 | ▇▇▂▁▁ |
| trans.drovealone | 0 | 1.00 | 1846.89 | 1192.38 | 0.00 | 1005.00 | 1660.00 | 2454.00 | 8070.00 | ▇▇▁▁▁ |
| trans.carpooled | 0 | 1.00 | 215.88 | 199.04 | 0.00 | 83.00 | 155.00 | 289.00 | 1304.00 | ▇▂▁▁▁ |
| trans.pubtrans | 0 | 1.00 | 192.57 | 177.80 | 0.00 | 69.00 | 148.00 | 262.00 | 1158.00 | ▇▃▁▁▁ |
| trans.bicycle | 0 | 1.00 | 12.11 | 29.40 | 0.00 | 0.00 | 0.00 | 11.00 | 225.00 | ▇▁▁▁▁ |
| trans.walk | 0 | 1.00 | 58.21 | 114.16 | 0.00 | 0.00 | 23.00 | 61.00 | 889.00 | ▇▁▁▁▁ |
| trans.WfH | 0 | 1.00 | 209.55 | 180.30 | 0.00 | 79.00 | 169.00 | 280.00 | 1218.00 | ▇▃▁▁▁ |
| Med_HHExp | 0 | 1.00 | 1985.71 | 1061.13 | 0.00 | 1246.00 | 1837.00 | 2572.00 | 6723.00 | ▅▇▃▁▁ |
| med_RETaxes | 19 | 0.95 | 2940.77 | 2190.89 | 199.00 | 1253.50 | 2326.00 | 4192.25 | 10001.00 | ▇▅▃▁▁ |
| review_count | 343 | 0.02 | 55.33 | 43.08 | 1.00 | 27.75 | 59.00 | 68.50 | 124.00 | ▅▁▇▁▂ |
| rating | 343 | 0.02 | 3.92 | 1.46 | 1.00 | 4.12 | 4.50 | 4.50 | 5.00 | ▂▁▁▂▇ |
| distance | 343 | 0.02 | 5458.97 | 8525.16 | 1191.79 | 1626.19 | 2237.39 | 2694.70 | 22817.68 | ▇▁▁▁▂ |
bikeRental_count_tract <- count(as_tibble(bikeRental_in_tract), GEOID) %>%
print()## # A tibble: 349 × 2
## GEOID n
## <chr> <int>
## 1 13089020100 1
## 2 13089020200 1
## 3 13089020300 1
## 4 13089020400 1
## 5 13089020500 1
## 6 13089020600 1
## 7 13089020700 1
## 8 13089020801 1
## 9 13089020802 1
## 10 13089020900 1
## # … with 339 more rows
## # ℹ Use `print(n = ...)` to see more rows# Join tract geometry with the number of Bike Rental businesses in tract
test <- st_join(tract, yelp_in %>% mutate(count = 1))
out <- test %>%
group_by(GEOID) %>%
summarise(count = sum(count, na.rm = T))
# Lets' check to see if the polygons and the point data on match
tm_shape(out) + tm_polygons(col = "count") + tm_shape(yelp_in) + tm_dots()FD_tract_Geom_bikeRental <- tract %>%
left_join(out %>% st_set_geometry(NULL), by = "GEOID")
skim(FD_tract_Geom_bikeRental)## Warning: Couldn't find skimmers for class: sfc_MULTIPOLYGON, sfc; No user-
## defined `sfl` provided. Falling back to `character`.| Name | FD_tract_Geom_bikeRental |
| Number of rows | 349 |
| Number of columns | 18 |
| _______________________ | |
| Column type frequency: | |
| character | 3 |
| numeric | 15 |
| ________________________ | |
| Group variables | None |
Variable type: character
| skim_variable | n_missing | complete_rate | min | max | empty | n_unique | whitespace |
|---|---|---|---|---|---|---|---|
| GEOID | 0 | 1 | 11 | 11 | 0 | 349 | 0 |
| county | 0 | 1 | 38 | 43 | 0 | 349 | 0 |
| geometry | 0 | 1 | 174 | 3684 | 0 | 349 | 0 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| hhincome | 4 | 0.99 | 73209.99 | 41838.74 | 12485 | 42517.0 | 63269 | 92404.00 | 236149 | ▇▆▂▁▁ |
| race.tot | 0 | 1.00 | 5116.11 | 2794.29 | 0 | 3242.0 | 4599 | 6224.00 | 21010 | ▆▇▁▁▁ |
| race.white | 0 | 1.00 | 2061.66 | 1960.52 | 0 | 286.0 | 1618 | 3378.00 | 12764 | ▇▅▁▁▁ |
| race.black | 0 | 1.00 | 2469.18 | 2750.80 | 0 | 658.0 | 1433 | 3215.00 | 19263 | ▇▂▁▁▁ |
| trans.total | 0 | 1.00 | 2579.90 | 1461.48 | 0 | 1515.0 | 2426 | 3358.00 | 9813 | ▆▇▂▁▁ |
| trans.car | 0 | 1.00 | 2062.77 | 1295.37 | 0 | 1105.0 | 1945 | 2726.00 | 8545 | ▇▇▂▁▁ |
| trans.drovealone | 0 | 1.00 | 1846.89 | 1192.38 | 0 | 1005.0 | 1660 | 2454.00 | 8070 | ▇▇▁▁▁ |
| trans.carpooled | 0 | 1.00 | 215.88 | 199.04 | 0 | 83.0 | 155 | 289.00 | 1304 | ▇▂▁▁▁ |
| trans.pubtrans | 0 | 1.00 | 192.57 | 177.80 | 0 | 69.0 | 148 | 262.00 | 1158 | ▇▃▁▁▁ |
| trans.bicycle | 0 | 1.00 | 12.11 | 29.40 | 0 | 0.0 | 0 | 11.00 | 225 | ▇▁▁▁▁ |
| trans.walk | 0 | 1.00 | 58.21 | 114.16 | 0 | 0.0 | 23 | 61.00 | 889 | ▇▁▁▁▁ |
| trans.WfH | 0 | 1.00 | 209.55 | 180.30 | 0 | 79.0 | 169 | 280.00 | 1218 | ▇▃▁▁▁ |
| Med_HHExp | 0 | 1.00 | 1985.71 | 1061.13 | 0 | 1246.0 | 1837 | 2572.00 | 6723 | ▅▇▃▁▁ |
| med_RETaxes | 19 | 0.95 | 2940.77 | 2190.89 | 199 | 1253.5 | 2326 | 4192.25 | 10001 | ▇▅▃▁▁ |
| count | 0 | 1.00 | 0.02 | 0.13 | 0 | 0.0 | 0 | 0.00 | 1 | ▇▁▁▁▁ |
tm_shape(FD_tract_Geom_bikeRental) + tm_polygons(col="count") +tm_shape(yelp_in) +tm_dots()print(skim(FD_tract_Geom_bikeRental))## Warning: Couldn't find skimmers for class: sfc_MULTIPOLYGON, sfc; No user-
## defined `sfl` provided. Falling back to `character`.## ── Data Summary ────────────────────────
## Values
## Name FD_tract_Geom_bikeRental
## Number of rows 349
## Number of columns 18
## _______________________
## Column type frequency:
## character 3
## numeric 15
## ________________________
## Group variables None
##
## ── Variable type: character ────────────────────────────────────────────────────
## skim_variable n_missing complete_rate min max empty n_unique whitespace
## 1 GEOID 0 1 11 11 0 349 0
## 2 county 0 1 38 43 0 349 0
## 3 geometry 0 1 174 3684 0 349 0
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable n_missing complete_rate mean sd p0 p25
## 1 hhincome 4 0.989 73210. 41839. 12485 42517
## 2 race.tot 0 1 5116. 2794. 0 3242
## 3 race.white 0 1 2062. 1961. 0 286
## 4 race.black 0 1 2469. 2751. 0 658
## 5 trans.total 0 1 2580. 1461. 0 1515
## 6 trans.car 0 1 2063. 1295. 0 1105
## 7 trans.drovealone 0 1 1847. 1192. 0 1005
## 8 trans.carpooled 0 1 216. 199. 0 83
## 9 trans.pubtrans 0 1 193. 178. 0 69
## 10 trans.bicycle 0 1 12.1 29.4 0 0
## 11 trans.walk 0 1 58.2 114. 0 0
## 12 trans.WfH 0 1 210. 180. 0 79
## 13 Med_HHExp 0 1 1986. 1061. 0 1246
## 14 med_RETaxes 19 0.946 2941. 2191. 199 1254.
## 15 count 0 1 0.0172 0.130 0 0
## p50 p75 p100 hist
## 1 63269 92404 236149 ▇▆▂▁▁
## 2 4599 6224 21010 ▆▇▁▁▁
## 3 1618 3378 12764 ▇▅▁▁▁
## 4 1433 3215 19263 ▇▂▁▁▁
## 5 2426 3358 9813 ▆▇▂▁▁
## 6 1945 2726 8545 ▇▇▂▁▁
## 7 1660 2454 8070 ▇▇▁▁▁
## 8 155 289 1304 ▇▂▁▁▁
## 9 148 262 1158 ▇▃▁▁▁
## 10 0 11 225 ▇▁▁▁▁
## 11 23 61 889 ▇▁▁▁▁
## 12 169 280 1218 ▇▃▁▁▁
## 13 1837 2572 6723 ▅▇▃▁▁
## 14 2326 4192. 10001 ▇▅▃▁▁
## 15 0 0 1 ▇▁▁▁▁## $character
##
## ── Variable type: character ────────────────────────────────────────────────────
## skim_variable n_missing complete_rate min max empty n_unique whitespace
## 1 GEOID 0 1 11 11 0 349 0
## 2 county 0 1 38 43 0 349 0
## 3 geometry 0 1 174 3684 0 349 0
##
## $numeric
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_…¹ n_mis…² compl…³ mean sd p0 p25 p50 p75 p100 hist
## 1 hhinco… 4 0.989 7.32e+4 4.18e+4 12485 42517 63269 92404 236149 ▇▆▂…
## 2 race.t… 0 1 5.12e+3 2.79e+3 0 3242 4599 6224 21010 ▆▇▁…
## 3 race.w… 0 1 2.06e+3 1.96e+3 0 286 1618 3378 12764 ▇▅▁…
## 4 race.b… 0 1 2.47e+3 2.75e+3 0 658 1433 3215 19263 ▇▂▁…
## 5 trans.… 0 1 2.58e+3 1.46e+3 0 1515 2426 3358 9813 ▆▇▂…
## 6 trans.… 0 1 2.06e+3 1.30e+3 0 1105 1945 2726 8545 ▇▇▂…
## 7 trans.… 0 1 1.85e+3 1.19e+3 0 1005 1660 2454 8070 ▇▇▁…
## 8 trans.… 0 1 2.16e+2 1.99e+2 0 83 155 289 1304 ▇▂▁…
## 9 trans.… 0 1 1.93e+2 1.78e+2 0 69 148 262 1158 ▇▃▁…
## 10 trans.… 0 1 1.21e+1 2.94e+1 0 0 0 11 225 ▇▁▁…
## 11 trans.… 0 1 5.82e+1 1.14e+2 0 0 23 61 889 ▇▁▁…
## 12 trans.… 0 1 2.10e+2 1.80e+2 0 79 169 280 1218 ▇▃▁…
## 13 Med_HH… 0 1 1.99e+3 1.06e+3 0 1246 1837 2572 6723 ▅▇▃…
## 14 med_RE… 19 0.946 2.94e+3 2.19e+3 199 1254. 2326 4192. 10001 ▇▅▃…
## 15 count 0 1 1.72e-2 1.30e-1 0 0 0 0 1 ▇▁▁…
## # … with abbreviated variable names ¹skim_variable, ²n_missing, ³complete_rate# Dropping the missing values
bikeRental_census_dropnaHH2 <- FD_tract_Geom_bikeRental[!is.na(FD_tract_Geom_bikeRental$hhincome),]
# Just to check whether the NAs have been dropped from hhincome
print(skim(bikeRental_census_dropnaHH2))## Warning: Couldn't find skimmers for class: sfc_MULTIPOLYGON, sfc; No user-
## defined `sfl` provided. Falling back to `character`.## ── Data Summary ────────────────────────
## Values
## Name bikeRental_census_dropnaH...
## Number of rows 345
## Number of columns 18
## _______________________
## Column type frequency:
## character 3
## numeric 15
## ________________________
## Group variables None
##
## ── Variable type: character ────────────────────────────────────────────────────
## skim_variable n_missing complete_rate min max empty n_unique whitespace
## 1 GEOID 0 1 11 11 0 345 0
## 2 county 0 1 38 43 0 345 0
## 3 geometry 0 1 174 3684 0 345 0
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_variable n_missing complete_rate mean sd p0 p25
## 1 hhincome 0 1 73210. 41839. 12485 42517
## 2 race.tot 0 1 5162. 2774. 196 3344
## 3 race.white 0 1 2083. 1961. 0 300
## 4 race.black 0 1 2488. 2759. 19 671
## 5 trans.total 0 1 2610. 1443. 54 1560
## 6 trans.car 0 1 2087. 1284. 54 1128
## 7 trans.drovealone 0 1 1868. 1182. 54 1017
## 8 trans.carpooled 0 1 218. 199. 0 86
## 9 trans.pubtrans 0 1 195. 178. 0 71
## 10 trans.bicycle 0 1 12.2 29.5 0 0
## 11 trans.walk 0 1 58.9 115. 0 1
## 12 trans.WfH 0 1 212. 180. 0 82
## 13 Med_HHExp 0 1 2009. 1045. 164 1261
## 14 med_RETaxes 15 0.957 2941. 2191. 199 1254.
## 15 count 0 1 0.0174 0.131 0 0
## p50 p75 p100 hist
## 1 63269 92404 236149 ▇▆▂▁▁
## 2 4693 6236 21010 ▇▇▁▁▁
## 3 1652 3383 12764 ▇▅▁▁▁
## 4 1456 3215 19263 ▇▂▁▁▁
## 5 2436 3366 9813 ▆▇▂▁▁
## 6 1958 2731 8545 ▇▇▂▁▁
## 7 1669 2467 8070 ▇▇▁▁▁
## 8 160 289 1304 ▇▂▁▁▁
## 9 149 263 1158 ▇▃▁▁▁
## 10 0 11 225 ▇▁▁▁▁
## 11 23 61 889 ▇▁▁▁▁
## 12 171 282 1218 ▇▃▁▁▁
## 13 1847 2577 6723 ▆▇▃▁▁
## 14 2326 4192. 10001 ▇▅▃▁▁
## 15 0 0 1 ▇▁▁▁▁## $character
##
## ── Variable type: character ────────────────────────────────────────────────────
## skim_variable n_missing complete_rate min max empty n_unique whitespace
## 1 GEOID 0 1 11 11 0 345 0
## 2 county 0 1 38 43 0 345 0
## 3 geometry 0 1 174 3684 0 345 0
##
## $numeric
##
## ── Variable type: numeric ──────────────────────────────────────────────────────
## skim_…¹ n_mis…² compl…³ mean sd p0 p25 p50 p75 p100 hist
## 1 hhinco… 0 1 7.32e+4 4.18e+4 12485 42517 63269 92404 236149 ▇▆▂…
## 2 race.t… 0 1 5.16e+3 2.77e+3 196 3344 4693 6236 21010 ▇▇▁…
## 3 race.w… 0 1 2.08e+3 1.96e+3 0 300 1652 3383 12764 ▇▅▁…
## 4 race.b… 0 1 2.49e+3 2.76e+3 19 671 1456 3215 19263 ▇▂▁…
## 5 trans.… 0 1 2.61e+3 1.44e+3 54 1560 2436 3366 9813 ▆▇▂…
## 6 trans.… 0 1 2.09e+3 1.28e+3 54 1128 1958 2731 8545 ▇▇▂…
## 7 trans.… 0 1 1.87e+3 1.18e+3 54 1017 1669 2467 8070 ▇▇▁…
## 8 trans.… 0 1 2.18e+2 1.99e+2 0 86 160 289 1304 ▇▂▁…
## 9 trans.… 0 1 1.95e+2 1.78e+2 0 71 149 263 1158 ▇▃▁…
## 10 trans.… 0 1 1.22e+1 2.95e+1 0 0 0 11 225 ▇▁▁…
## 11 trans.… 0 1 5.89e+1 1.15e+2 0 1 23 61 889 ▇▁▁…
## 12 trans.… 0 1 2.12e+2 1.80e+2 0 82 171 282 1218 ▇▃▁…
## 13 Med_HH… 0 1 2.01e+3 1.05e+3 164 1261 1847 2577 6723 ▆▇▃…
## 14 med_RE… 15 0.957 2.94e+3 2.19e+3 199 1254. 2326 4192. 10001 ▇▅▃…
## 15 count 0 1 1.74e-2 1.31e-1 0 0 0 0 1 ▇▁▁…
## # … with abbreviated variable names ¹skim_variable, ²n_missing, ³complete_ratey_census_dropnaHHTX <- bikeRental_census_dropnaHH2[!is.na(bikeRental_census_dropnaHH2$med_RETaxes),]
skim(y_census_dropnaHHTX)## Warning: Couldn't find skimmers for class: sfc_MULTIPOLYGON, sfc; No user-
## defined `sfl` provided. Falling back to `character`.| Name | y_census_dropnaHHTX |
| Number of rows | 330 |
| Number of columns | 18 |
| _______________________ | |
| Column type frequency: | |
| character | 3 |
| numeric | 15 |
| ________________________ | |
| Group variables | None |
Variable type: character
| skim_variable | n_missing | complete_rate | min | max | empty | n_unique | whitespace |
|---|---|---|---|---|---|---|---|
| GEOID | 0 | 1 | 11 | 11 | 0 | 330 | 0 |
| county | 0 | 1 | 38 | 43 | 0 | 330 | 0 |
| geometry | 0 | 1 | 174 | 3684 | 0 | 330 | 0 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| hhincome | 0 | 1 | 75223.13 | 41645.99 | 12485 | 44023.25 | 66595.0 | 94728.00 | 236149 | ▇▇▂▂▁ |
| race.tot | 0 | 1 | 5276.50 | 2757.89 | 1254 | 3391.75 | 4886.0 | 6370.75 | 21010 | ▇▆▁▁▁ |
| race.white | 0 | 1 | 2154.37 | 1968.38 | 0 | 312.25 | 1739.5 | 3524.25 | 12764 | ▇▅▁▁▁ |
| race.black | 0 | 1 | 2521.78 | 2806.73 | 19 | 661.25 | 1444.5 | 3361.25 | 19263 | ▇▂▁▁▁ |
| trans.total | 0 | 1 | 2681.46 | 1429.68 | 421 | 1647.25 | 2476.5 | 3405.75 | 9813 | ▇▇▂▁▁ |
| trans.car | 0 | 1 | 2152.82 | 1270.68 | 246 | 1231.75 | 2017.0 | 2784.25 | 8545 | ▇▇▁▁▁ |
| trans.drovealone | 0 | 1 | 1930.55 | 1169.36 | 108 | 1067.25 | 1753.5 | 2534.50 | 8070 | ▇▇▁▁▁ |
| trans.carpooled | 0 | 1 | 222.26 | 199.16 | 0 | 88.50 | 161.5 | 294.75 | 1304 | ▇▂▁▁▁ |
| trans.pubtrans | 0 | 1 | 195.22 | 177.66 | 0 | 71.00 | 150.0 | 262.75 | 1158 | ▇▃▁▁▁ |
| trans.bicycle | 0 | 1 | 12.34 | 29.84 | 0 | 0.00 | 0.0 | 12.00 | 225 | ▇▁▁▁▁ |
| trans.walk | 0 | 1 | 56.37 | 106.29 | 0 | 1.00 | 23.5 | 61.00 | 889 | ▇▁▁▁▁ |
| trans.WfH | 0 | 1 | 218.59 | 180.20 | 0 | 89.25 | 177.0 | 286.50 | 1218 | ▇▃▁▁▁ |
| Med_HHExp | 0 | 1 | 2064.01 | 1030.49 | 347 | 1319.50 | 1922.5 | 2608.75 | 6723 | ▇▇▂▁▁ |
| med_RETaxes | 0 | 1 | 2940.77 | 2190.89 | 199 | 1253.50 | 2326.0 | 4192.25 | 10001 | ▇▅▃▁▁ |
| count | 0 | 1 | 0.02 | 0.13 | 0 | 0.00 | 0.0 | 0.00 | 1 | ▇▁▁▁▁ |
class(y_census_dropnaHHTX)## [1] "sf" "data.frame"ggplot(y_census_dropnaHHTX, aes(x=hhincome, y=count)) +
geom_point() +
ylab("Number of Bike Rental Businesses and Household Median Income in Tract")
y_census_dropnaHHTX$Bikerentals <- ifelse(y_census_dropnaHHTX$count>0, 1, 0)
boxplot(hhincome~Bikerentals, data=y_census_dropnaHHTX, main="Boxplot of Bike Rental Businesses by Income", xlab="Whether Bike Rental Businesses are present", ylab="Household median income")
boxplot(med_RETaxes~Bikerentals, data=y_census_dropnaHHTX, main="Boxplot of Bike Rental Businesses by Real Estate Taxes", xlab="Whether Bike Rental Businesses are present", ylab="Real Estate Taxes in tract")
#ggplot(y_census_dropnaHHTX, aes(x=count, y=trans.bicycle)) +
#geom_point() +
#ylab("Number of Bike Commuters")
boxplot(trans.bicycle~Bikerentals, data=y_census_dropnaHHTX, main="Boxplot of Bike Rental Businesses by Bike Commuters", xlab="Bike Rental Businesses are present", ylab="Bike Commuters")
y_census_dropnaHHTX$pop_density <- 1000*y_census_dropnaHHTX$race.tot/st_area(y_census_dropnaHHTX$geometry)
y_census_dropnaHHTX$bike_commuter_proportion <- 100*y_census_dropnaHHTX$trans.bicycle/y_census_dropnaHHTX$trans.total
boxplot(pop_density~Bikerentals, data=y_census_dropnaHHTX, main="Boxplot of Bike Rentals by population density of a tract", xlab="Presence Bike Rental Businesses", ylab="Population Density")
boxplot(bike_commuter_proportion~Bikerentals, data=y_census_dropnaHHTX, main="Boxplot of Bike Rentals by percentage of Bike Commuters", xlab="Presence of Bike Rental Businesses", ylab="percentage of people using bicycle to commute")
tmap_mode("view")## tmap mode set to interactive viewingt_pop_den <- tm_shape(y_census_dropnaHHTX) + tm_polygons(col ="pop_density") +tm_shape(yelp_in) +tm_dots()
t_bike_commute <- tm_shape(y_census_dropnaHHTX) + tm_polygons(col="bike_commuter_proportion") +tm_shape(yelp_in) +tm_dots()
tmap_arrange(t_pop_den, t_bike_commute)