Rents in San Francsisco 2000-2018

# download directly off tidytuesdaygithub repo
rent <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-07-05/rent.csv')

What are the variable types? Do they all correspond to what they really are? Which variables have most missing values?

There are 8 character variables and 9 numeric variables. They all seem to correspond to what they really are. The variable with the most missing values is “descr”.

# YOUR CODE GOES HERE
skimr::skim(rent)

Variable type: character

Variable type: numeric

summary(rent)

##    post_id               date               year         nhood          
##  Length:200796      Min.   :20000902   Min.   :2000   Length:200796     
##  Class :character   1st Qu.:20050227   1st Qu.:2005   Class :character  
##  Mode  :character   Median :20110924   Median :2011   Mode  :character  
##                     Mean   :20095718   Mean   :2010                     
##                     3rd Qu.:20120805   3rd Qu.:2012                     
##                     Max.   :20180717   Max.   :2018                     
##                                                                         
##      city              county              price            beds     
##  Length:200796      Length:200796      Min.   :  220   Min.   : 0    
##  Class :character   Class :character   1st Qu.: 1295   1st Qu.: 1    
##  Mode  :character   Mode  :character   Median : 1800   Median : 2    
##                                        Mean   : 2135   Mean   : 2    
##                                        3rd Qu.: 2505   3rd Qu.: 3    
##                                        Max.   :40000   Max.   :12    
##                                                        NA's   :6608  
##      baths             sqft         room_in_apt      address         
##  Min.   :1        Min.   :    80   Min.   :0.000   Length:200796     
##  1st Qu.:1        1st Qu.:   750   1st Qu.:0.000   Class :character  
##  Median :2        Median :  1000   Median :0.000   Mode  :character  
##  Mean   :2        Mean   :  1202   Mean   :0.001                     
##  3rd Qu.:2        3rd Qu.:  1360   3rd Qu.:0.000                     
##  Max.   :8        Max.   :900000   Max.   :1.000                     
##  NA's   :158121   NA's   :136117                                     
##       lat              lon            title              descr          
##  Min.   :34       Min.   :-123     Length:200796      Length:200796     
##  1st Qu.:37       1st Qu.:-122     Class :character   Class :character  
##  Median :38       Median :-122     Mode  :character   Mode  :character  
##  Mean   :38       Mean   :-122                                          
##  3rd Qu.:38       3rd Qu.:-122                                          
##  Max.   :40       Max.   : -74                                          
##  NA's   :193145   NA's   :196484                                        
##    details         
##  Length:200796     
##  Class :character  
##  Mode  :character  
##                    
##                    
##                    
## 

Make a plot that shows the top 20 cities in terms of % of classifieds between 2000-2018. You need to calculate the number of listings by city, and then convert that number to a %.

# YOUR CODE GOES HERE
rent %>% 
  count(city, sort=TRUE) %>% 
  mutate(prop = n/sum(n)) %>% 
  slice_max(order_by = prop, n=20) %>% 
  mutate(city = fct_reorder(city, prop)) %>% 
  
  ggplot(aes(x=prop, y= city)) +
  geom_col() +
  labs(title = "San Francisco accounts for more than a quarter of all rental classifieds",
       subtitle = "% of Craigslist listings, 2000-2018", 
       caption = "Source: Pennington, Kate (2018). Bay Area Craigslist Rental Housing Posts, 2000-2018", y = "City", x = element_blank()) +
  scale_x_continuous(labels = scales::percent)

Make a plot that shows the evolution of median prices in San Francisco for 0, 1, 2, and 3 bedrooms listings.

# YOUR CODE GOES HERE
rent %>%
  filter(city == "san francisco", beds<=3) %>%
  group_by(year, beds) %>%
  summarise(median_price = median(price)) %>% 

ggplot( mapping=aes(x=year, y=median_price, colour = factor(beds))) +
  geom_line() +
  facet_wrap(~beds, nrow=1)+
  theme(legend.position = "none") +
  labs(title = "San Francisco rents have been steadily increasing",
       subtitle = "0- to 3-bed listings, 2000-2018", 
       caption = "Source: Pennington, Kate (2018). Bay Area Craigslist Rental Housing Posts, 2000-2018", y = element_blank(), x = element_blank())

Finally, make a plot that shows median rental prices for the top 12 cities in the Bay area.

# YOUR CODE GOES HERE
rent %>%
  filter(city %in% c("san francisco", "san jose", "oakland", "santa rosa", "santa cruz", "san mateo", "sunnyvale", "mountain view", "berkeley", "santa clara", "palo alto", "union city"), beds == 1)%>%
  group_by(city,year) %>%
  summarise(median_price = median(price), city)%>%
  
  ggplot(aes(x=year, y=median_price, color=city)) +
  geom_line() +
  facet_wrap(~city, nrow=3)+
  theme(legend.position = "none") +
  labs(title = "Median rental prices for 1 bedroom flats in top 12 cities from Bay Area", x = "Year", y = "Median rental price", caption = "Source: Pennington, Kate (2018). Bay Area Craigslist Rental Housing Posts, 2000-2018")

What can you infer from these plots? Don’t just explain what’s in the graph, but speculate or tell a short story (1-2 paragraphs max).

The general trend that can be seen across the cities in the Bay area is that the rent has decreased in the years following the dot.com bubble (2001-2004), after which it increased rapidly prior to the housing market crash and global financial crisis that started in 2007-2008. After 2010 rents started increasing rapidly again until the economic slowdown that commenced at the end of the decade.