Bonus Assignment

raw_df <- read_xlsx("C:/Users/ETR04585/Desktop/BDA/Courses/1st Semester/Data Analytics Essentials with R/Assingment 2_dplr_ggplot/EVDS_istanbul_property_data.xlsx", n_max = 130)

Let’s preview the data

glimpse(raw_df)

## Rows: 129
## Columns: 9
## $ Tarih                   <chr> "2010-01", "2010-02", "2010-03", "2010-04",...
## $ `TP AKONUTSAT1 T40`     <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,...
## $ `TP AKONUTSAT2 T40`     <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,...
## $ `TP AKONUTSAT3 T40`     <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,...
## $ `TP AKONUTSAT4 T40`     <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,...
## $ `TP DISKONSAT ISTANBUL` <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,...
## $ `TP HEDONIKYKFE IST`    <dbl> 35.9, 36.6, 37.4, 38.0, 38.0, 37.6, 37.3, 3...
## $ `TP HKFE02`             <dbl> 36.0, 36.2, 36.5, 36.9, 37.1, 37.0, 37.2, 3...
## $ `TP TCBF02 ISTANBUL`    <dbl> 1414.9, 1420.1, 1427.9, 1442.7, 1449.0, 144...

raw_df$Tarih<-paste0(raw_df$Tarih,as.character("-01"))

raw_df$Tarih<-as.Date(raw_df$Tarih, format="%Y-%m-%d")

I changed the names of columns with more understandable names.

adj_df <- rename(raw_df, "totalsales" = "TP AKONUTSAT1 T40",
                 "mortgaged" = "TP AKONUTSAT2 T40",
                 "first" = "TP AKONUTSAT3 T40",
                 "second" = "TP AKONUTSAT4 T40",
                 "foreigner" = "TP DISKONSAT ISTANBUL",
                 "pi_new" = "TP HEDONIKYKFE IST",
                 "pi_old" = "TP HKFE02",
                 "tl_m2" = "TP TCBF02 ISTANBUL",
                 "years" = "Tarih")

glimpse(adj_df)

## Rows: 129
## Columns: 9
## $ years      <date> 2010-01-01, 2010-02-01, 2010-03-01, 2010-04-01, 2010-05...
## $ totalsales <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, ...
## $ mortgaged  <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, ...
## $ first      <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, ...
## $ second     <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, ...
## $ foreigner  <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, ...
## $ pi_new     <dbl> 35.9, 36.6, 37.4, 38.0, 38.0, 37.6, 37.3, 38.1, 38.8, 39...
## $ pi_old     <dbl> 36.0, 36.2, 36.5, 36.9, 37.1, 37.0, 37.2, 37.3, 37.7, 38...
## $ tl_m2      <dbl> 1414.9, 1420.1, 1427.9, 1442.7, 1449.0, 1445.4, 1452.6, ...

adj_df %>%
  filter(year(years) > 2012)

## # A tibble: 93 x 9
##    years      totalsales mortgaged first second foreigner pi_new pi_old tl_m2
##    <date>          <dbl>     <dbl> <dbl>  <dbl>     <dbl>  <dbl>  <dbl> <dbl>
##  1 2013-01-01      18235      8423  8298   9937       138   49.5   47.8 2064.
##  2 2013-02-01      18971      8836  8277  10694       120   50.4   48.8 2114.
##  3 2013-03-01      21570     10164  9542  12028       198   51.1   49.9 2158.
##  4 2013-04-01      20791      9726  8751  12040       209   51.6   50.9 2186.
##  5 2013-05-01      22030     10805  9371  12659       188   52.2   51.6 2218.
##  6 2013-06-01      19357      9762  8160  11197       155   53     52.4 2263.
##  7 2013-07-01      20668     10071  9034  11634       192   53.8   52.9 2300.
##  8 2013-08-01      14930      6834  6960   7970       170   54.8   53.5 2320.
##  9 2013-09-01      18514      8153  8128  10386       156   55.6   54.3 2346 
## 10 2013-10-01      14866      6268  6737   8129       181   56.3   55   2394.
## # ... with 83 more rows

Mortgaged Sales

adj_df %>%
  filter(year(years) > 2013) %>%
  ggplot(aes(years, mortgaged)) + geom_line() + labs(x="Years", y="Mortgaged Sale", title = "Mortgaged Sale Respected by Years")

According to the graph above, home sales with mortgaged made a peak in 2020. The reason for this could be the low-interest loan campaign of the state. As of September 2020 as the campaign’s end date, the number of sales with mortgaged has decreased fast.

Total Sales Change Compared to The Previous Year

adj_df %>%
  filter(year(years) > 2013) %>%
  mutate(difference = totalsales - lag(totalsales)) %>%
  ggplot(aes(years, difference)) + geom_line() + labs(x="Years", y="Total Sales Change", title = "Total Sales Change Compared to The Previous Year")

## Warning: Removed 1 row(s) containing missing values (geom_path).

The biggest fluctuations are seen after 2018, and the reason can be interpreted as the instability of the economy.

Bonus Assignment

Ozan Barış Baykan

04/11/2020

Mortgaged Sales

Total Sales Change Compared to The Previous Year