mini_2_0927

Tidy the data

Delete duplicted rows by unique POI id (column “id”)

yelp_all_pois_filtered <- distinct(yelp_all_pois, id, .keep_all = T) # # Remove duplicate entries based on the "id" column to keep only unique POIs

Flatten nested columns that have multiple variables in one column

Transactions and location address
Categories

yelp_all_pois_flat <- jsonlite::flatten(yelp_all_pois_filtered)

yelp_all_pois_concat <- yelp_all_pois_flat %>% 
  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=", "))) # Convert the 'transactions' and 'location.display_address' into comma-separated strings

concate_list <- function(x){
  titles <- x[["title"]] %>% str_c(collapse = ", ")
  return(titles)
} # # Custom function to concatenate category titles

yelp_all_pois_flat2 <- yelp_all_pois_concat %>%   
  mutate(categories = categories %>% map_chr(concate_list)) # Concatenate 'categories' titles into a single string

Delete rows that have missing data in coordinates variable

yelp_all_pois_flat2 %<>% filter(!is.na(coordinates.latitude)) # Filter out rows where latitude is missing

Delete rows that fall outside of the boundary of the city of Suwanee

yelp_sf <- yelp_all_pois_flat2 %>% 
  mutate(x = .$coordinates.longitude,
         y = .$coordinates.latitude) %>% 
  st_as_sf(coords = c("x", "y"), crs = 4326) # Convert Yelp POIs data into a spatial object (sf) using longitude and latitude coordinates

city <- tigris::places('GA') %>% 
  filter(NAME == 'Suwanee') %>% 
  st_transform(st_crs(yelp_sf)) # Get the boundary of Suwanee city

yelp_within_city <- yelp_sf[city,] # Identify POIs within the Suwanee city boundary
yelp_without_city <- filter(yelp_sf, !id %in% yelp_within_city$id) # Identify POIs outside it

Descriptive Analysis

print(paste0("Before data wrangling: ", nrow(yelp_all_pois)))

## [1] "Before data wrangling: 173"

print(paste0("POIs located within the city: ", nrow(yelp_within_city)))

## [1] "POIs located within the city: 20"

tmap_mode("view")
tm_shape(yelp_within_city) +
  tm_dots(col = "type", style="quantile") +
  tm_shape(city) +
  tm_borders(col = "red", lwd = 3)

summary(yelp_within_city$rating)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   3.200   3.600   3.950   4.035   4.525   5.000

summary(yelp_without_city$rating)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   0.000   2.800   3.400   3.259   4.200   5.000

table(yelp_within_city$price)

## 
##   $  $$ $$$ 
##   4   9   1

table(yelp_without_city$price)

## 
##    $   $$  $$$ $$$$ 
##    2   22    2    2

summary(yelp_within_city$review_count)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    1.00   40.75  135.50  138.50  209.25  393.00

summary(yelp_without_city$review_count)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##     0.0    14.0    62.0   112.7   162.0   661.0

mini_2_0927

Seung Jae Lieu

2024-09-26

Load the yelp dataset used in the previous assignment (mini 1)

Tidy the data

Delete duplicted rows by unique POI id (column “id”)

Flatten nested columns that have multiple variables in one column

Delete rows that have missing data in coordinates variable

Delete rows that fall outside of the boundary of the city of Suwanee

Descriptive Analysis

A Short Story