Plotly

We’re going to make some plotly plots.

Load packages and data

library(tidyverse)
library(p8105.datasets)
library(plotly)
library(httr)
library(jsonlite)

Hw3

get_all_inspections = function(url) {
  
  all_inspections = vector("list", length = 0)
  
  loop_index = 1
  chunk_size = 50000
  DO_NEXT = TRUE
  
  while (DO_NEXT) {
    message("Getting data, page ", loop_index)
    
    all_inspections[[loop_index]] = 
      GET(url,
          query = list(`$order` = "zipcode",
                       `$limit` = chunk_size,
                       `$offset` = as.integer((loop_index - 1) * chunk_size)
                       )
          ) %>%
      content("text") %>%
      fromJSON() %>%
      as_tibble()
    
    DO_NEXT = dim(all_inspections[[loop_index]])[1] == chunk_size
    loop_index = loop_index + 1
  }
  
  all_inspections
  
}

url = "https://data.cityofnewyork.us/resource/43nn-pn8j.json"

nyc_inspections = 
  get_all_inspections(url) %>%
  bind_rows() 

## Getting data, page 1

## Getting data, page 2

## Getting data, page 3

## Getting data, page 4

## Getting data, page 5

nyc = nyc_inspections %>% 
  select(score,boro,camis, grade, latitude, longitude,street, cuisine_description) %>% 
  filter(score %in% 20:100) %>% 
  drop_na(grade)

#Scatter plot: Score of resteraurants in Manhattan

nyc %>% 
  filter(boro == "Manhattan") %>% 
  plot_ly(x= ~latitude, y=~longitude, color = ~score, type = "scatter", mode ="markers", alpha = .5, text = ~score)

## Warning: Ignoring 14 observations

## 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

## 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

#box plot: Different locations restaurants score

nyc %>% 
  mutate(street = fct_reorder(boro, score)) %>% 
  plot_ly(x=~boro, y= ~score, color = ~street, type= "box", colors= "viridis")

## Warning in mean.default(sort(x, partial = half + 0L:1L)[half + 0L:1L]): argument
## is not numeric or logical: returning NA

nyc %>% 
  count(cuisine_description) %>% 
  mutate(cuisine_description = fct_reorder(cuisine_description, n)) %>% 
  plot_ly(x=~cuisine_description, y=~n, type="bar")

Let’s get some data

data("nyc_airbnb")

nyc_airbnb = 
  nyc_airbnb %>% 
  mutate(rating = review_scores_location / 2) %>% 
  select(borough = neighbourhood_group, neighbourhood, price, room_type, lat, long, rating) %>% 
filter(borough == "Manhattan",
       room_type == "Entire home/apt",
       price %in% 100:500) %>% 
  drop_na(rating)

Let’s make a scatterplot!!

nyc_airbnb %>% 
  mutate(text_label = str_c("Price:", price)) %>% 
  plot_ly(x= ~lat, y=~long, color = ~price, type = "scatter", mode ="markers", alpha = .5, text = ~text_label)

can we make boxplots?? Sure can!

nyc_airbnb %>% 
  mutate(neighbourhood = fct_reorder(neighbourhood, price)) %>% 
  plot_ly(y= ~price, color = ~neighbourhood, type= "box", colors= "viridis")

Can we make a bar plot?

nyc_airbnb %>% 
  count(neighbourhood) %>% 
  mutate(neighbourhood = fct_reorder(neighbourhood, n)) %>% 
  plot_ly(x=~neighbourhood, y=~n, type="bar")

##ggplotly..

ggp_scatterplot=
nyc_airbnb %>% 
  ggplot(aes(x=lat,y =long, color =price))+geom_point()

ggplotly(ggp_scatterplot)

Create a dashboard…