El presente informe permite conocer la realidad de los restaurant fast food en el año 2018.

Problema 1

# librerias
library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.0 --
## v ggplot2 3.3.3     v purrr   0.3.4
## v tibble  3.0.6     v dplyr   1.0.4
## v tidyr   1.1.2     v stringr 1.4.0
## v readr   1.4.0     v forcats 0.5.1
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()
library(skimr)
library(ggrepel)
## Warning: package 'ggrepel' was built under R version 4.0.4
library(visdat)
## Warning: package 'visdat' was built under R version 4.0.5
library(hrbrthemes)
## Warning: package 'hrbrthemes' was built under R version 4.0.4
## NOTE: Either Arial Narrow or Roboto Condensed fonts are required to use these themes.
##       Please use hrbrthemes::import_roboto_condensed() to install Roboto Condensed and
##       if Arial Narrow is not on your system, please see https://bit.ly/arialnarrow
library(viridis)
## Warning: package 'viridis' was built under R version 4.0.4
## Loading required package: viridisLite
library(forcats)
library(ggExtra)
## Warning: package 'ggExtra' was built under R version 4.0.4
# cargar data
ff_sales <- read_csv("data_fastfood_sales.csv") # data de ventas
## 
## -- Column specification --------------------------------------------------------
## cols(
##   restaurant = col_character(),
##   average_sales = col_double(),
##   us_sales = col_double(),
##   num_company_stores = col_double(),
##   num_franchised_stores = col_double(),
##   unit_count = col_double()
## )
ff_calories <- read_csv("data_fastfood_calories.csv") # data de contenido nutricional
## 
## -- Column specification --------------------------------------------------------
## cols(
##   restaurant = col_character(),
##   item = col_character(),
##   calories = col_double(),
##   cal_fat = col_double(),
##   total_fat = col_double(),
##   sat_fat = col_double(),
##   trans_fat = col_double(),
##   cholesterol = col_double(),
##   sodium = col_double(),
##   total_carb = col_double(),
##   fiber = col_double(),
##   sugar = col_double(),
##   protein = col_double(),
##   vit_a = col_double(),
##   vit_c = col_double(),
##   calcium = col_double()
## )
ff_sales <- as_tibble(ff_sales) ;ff_calories <- as_tibble(ff_calories) ;

ff_sales_plot <-  ff_sales %>% mutate(prop_stores_fran = num_franchised_stores / unit_count ) 

# PROBLEMA 1  -----


ggplot(ff_sales_plot, aes(x = us_sales,
                          y = unit_count,
                          color = prop_stores_fran)) +
  geom_point() +
  labs(x = "U.S sales in millions (log10 scale)",
       y = "Total number of stores (log10 scale)") +
  scale_x_continuous(trans = "log10") +
  scale_y_continuous(trans = "log10") +
  scale_color_continuous("Proportion of stores\n\ franchised") + 
  geom_text_repel(aes(label = restaurant), colour="black") + 
  theme_bw() +
  theme(axis.title = element_text(face = "bold"), text = element_text(face = "bold"))

Problema 2

ff_sales_plot$restaurant <- as.factor(ff_sales_plot$restaurant)  # convirtiendo a factor

ff_sales_plot %>%  
  mutate(restaurant = fct_reorder(restaurant, average_sales, .desc = F)) %>% # ordenando la var factor con average_sales
   # graficando 
    ggplot(aes(x=  restaurant, y = average_sales )) + 
  geom_bar(stat = "identity") + 
  scale_y_continuous(labels = scales::label_dollar()) +
  geom_text_repel(aes(label = paste("$", round(average_sales,0)))
                  , hjust = 1) +
  coord_flip() +
  labs(x = "Restaurant", y = "Average sales per unit store (in thousands)") + 
  theme_classic() +
  theme(axis.title = element_text(face = "bold"))

Problema 3

ggplot(ff_calories, aes(x = calories, y = sodium, label = item)) +
  geom_point(size = 1)+
  labs(x = "Calories", y = "Sodium(mg)") + 
  facet_wrap(~restaurant) +
  geom_hline(yintercept = 2300, color = "black", size = 0.5) +
  geom_text_repel(data = ff_calories %>% filter(sodium > 2300),
                  nudge_y = 1000,
                  hjust = -0.5,
                  direction = "y") +
  theme_bw() + 
  theme(axis.title = element_text(face = "bold"))

Problema 4

  # paso 1: transformo todo a minusculas para detectar la palabra "salad"
ff_calories_plot <-  ff_calories %>% 
  mutate(item = tolower(item)) %>% 
  mutate(is_salad = str_detect(item, "salad")) 

  # paso 2: convierto a facto "restaurant" para poder ordenarlo luego
ff_calories_plot$is_salad <- as_factor(ff_calories_plot$is_salad)
ff_calories_plot$restaurant <- as_factor(ff_calories_plot$restaurant)
  
  # paso 3: construyo una tabla resumen que agrupa por restaurant la mediana de calorias y hago un inner con la data global
    # aunque la variable restaurant ya es factor y esta ordenado de forma decreciente con respecto a su mediana
 ff_calories_plot2 <-  ff_calories_plot %>%
  group_by(restaurant) %>% 
  summarize(median_calories = median(calories)) %>% 
  mutate(restaurant2 = fct_reorder(restaurant, median_calories, .desc = F)) %>% 
   inner_join(ff_calories_plot, by = c("restaurant2"="restaurant"))

 ff_calories_plot2 <-   as.data.frame(ff_calories_plot2)
 
  # paso 4: construyo el grĂ¡fico

 ff_calories_plot2 %>% mutate(is_salad = if_else(is_salad == "FALSE","Not a salad","Salad")) %>% 
 
  ggplot( aes(x = calories, y = restaurant2)) +
  geom_boxplot(outlier.colour = "white") +
    geom_jitter(aes(color = is_salad) ,size = 2, alpha = 5) + 
    
  scale_x_continuous(trans = "log10") + 
  labs(x= "Calories (log10 scale)", y = "Restaurant") +
  scale_color_discrete ("Is the entree a salad?")+
  scale_fill_viridis(discrete = T, alpha = 0.6) +
    theme_bw() +
   theme(axis.title = element_text(face = "bold"), text = element_text(face = "bold"))

Problema 5

ff_calories_p5 <-   ff_calories %>% 
   filter(restaurant != "Taco Bell") %>% 
   group_by(restaurant) %>% 
   summarize(median_sugar = median(sugar)) %>% 
  inner_join(ff_sales_plot, by = c("restaurant")) %>% 
   mutate(restaurant = fct_reorder(restaurant, us_sales, .desc = F)) 
 
 # graficando
 ggplot(ff_calories_p5, aes(x = restaurant, y = us_sales)) +
   geom_bar(stat = "identity", aes(fill = median_sugar)) +
   
   labs(x = "Restaurant", y = "U.S. sales (in millions)") + 
   scale_color_continuous ("Median sugar (grams) \n\ in fast food entrees ")+
   theme_classic() + 
   theme(axis.title = element_text(face = "bold"), text = element_text(face = "bold"))