Instacart Orders

knitr::opts_chunk$set(echo = TRUE)
library(tidyverse)
library(p8105.datasets)
library(plotly)

Clean & Filter the data

I filtered the instacart data to only focous on snack department

data("instacart")
ins_df = instacart %>%
  filter(department == "snacks")

Scatter Plot

ins_df %>% 
  group_by(product_name) %>%
  mutate(reordered_sum = sum(reordered),
         n_obs = n()) %>%
  mutate(text_label = str_c("Product Name: ", product_name, "\n Number of Reorder Purchases: ", n_obs)) %>% 
  plot_ly(
    x = ~n_obs, y = ~reordered_sum, color = ~aisle, text = ~text_label,
    alpha = .5, type = "scatter", mode = "markers", colors = "viridis", showlegend = FALSE) %>%
  layout(
    xaxis = list(title = "Number of Purchases"),
    yaxis = list(title = "Number of Reorder Purchases"),
    title = "Number of Purchases vs. Number of Reorder Purchases"
  ) %>% 
  layout(legend = list(x = 0.05, y = 0.9))

Box Plot

ins_df %>%
  group_by(aisle) %>%
  plot_ly(x = ~aisle,
          y = ~days_since_prior_order,
          color = ~aisle,
          type = "box", colors = "viridis", showlegend = FALSE) %>%
    layout(
    xaxis = list(title = "Aisel"),
    yaxis = list(title = "Days since the last order"),
    title = "Boxplot of Days since the last order of each aisle"
  )

Bar Plot

ins_df %>% 
    count(aisle) %>% 
    mutate(
        aisle = factor(aisle),
        aisle = fct_reorder(aisle, n)
    ) %>% 
   plot_ly(
    x = ~aisle, y = ~n, color = ~aisle, 
    type = "bar", colors = "viridis", showlegend = FALSE) %>%
  layout(
    xaxis = list(title = "Aisle"),
    yaxis = list(title = "Count"),
    title = "Count of Items in the Snack Department"
  )