Dataset

library(tidyverse)
## Loading tidyverse: ggplot2
## Loading tidyverse: tibble
## Loading tidyverse: tidyr
## Loading tidyverse: readr
## Loading tidyverse: purrr
## Loading tidyverse: dplyr
## Conflicts with tidy packages ----------------------------------------------
## filter(): dplyr, stats
## lag():    dplyr, stats
library(janitor)
library(stringr)
library(forcats)
library(viridis)
## Loading required package: viridisLite
library(plotly)
## 
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## The following object is masked from 'package:stats':
## 
##     filter
## The following object is masked from 'package:graphics':
## 
##     layout

Clean data.

airbnb = read_csv("./data/nyc_airbnb.zip") %>% 
  clean_names() %>% 
  rename(boro = neighbourhood_group) %>% 
  mutate(rating = review_scores_location / 2) %>% 
  filter(boro == "Manhattan",
         room_type == "Entire home/apt",
         price > 100 & price < 400)
## Parsed with column specification:
## cols(
##   id = col_integer(),
##   review_scores_location = col_integer(),
##   name = col_character(),
##   host_id = col_integer(),
##   host_name = col_character(),
##   neighbourhood_group = col_character(),
##   neighbourhood = col_character(),
##   latitude = col_double(),
##   longitude = col_double(),
##   room_type = col_character(),
##   price = col_integer(),
##   minimum_nights = col_integer(),
##   number_of_reviews = col_integer(),
##   last_review = col_date(format = ""),
##   reviews_per_month = col_double(),
##   calculated_host_listings_count = col_integer(),
##   availability_365 = col_integer()
## )

Plotly Scatterplot

airbnb %>% 
  mutate(hover_text = str_c("Price: $", price, '\nRating: ', rating)) %>% 
  plot_ly(x = ~longitude, y = ~latitude, color = ~price,
          text = ~hover_text,
          type = "scatter", mode = "marker", alpha = 0.5)
## A marker object has been specified, but markers is not in the mode
## Adding markers to the mode...

Plotly boxplot

airbnb %>% 
  mutate(neighbourhood = fct_reorder(neighbourhood, price)) %>% 
  plot_ly(x = ~neighbourhood, y = ~price, color = ~neighbourhood,
          colors = "Set2",
          type = "box")

Plotly bar chart

airbnb %>% 
  count(neighbourhood) %>% 
  mutate(neighbourhood = fct_reorder(neighbourhood, n)) %>% 
  plot_ly(x = ~neighbourhood, y = ~n, color = ~neighbourhood, 
          type = "bar")
## Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colors

ggplotly

scatter_ggplot = 
  airbnb %>%
  ggplot(aes(x = longitude, y = latitude, color = price)) +
  geom_point(alpha = 0.25) +
  scale_color_viridis() +
  coord_cartesian() +
  theme_classic()

ggplotly(scatter_ggplot)
## We recommend that you use the dev version of ggplot2 with `ggplotly()`
## Install it with: `devtools::install_github('hadley/ggplot2')`