New House Sales vs Old House Sales vs Mortgage House Sales
data_ratios= data %>% mutate(new_sales_ratio=new_building_sales/total_sales,
old_sales_ratio= old_building_sales/total_sales,
mortgage_sales_ratio= total_sales_mortgage/total_sales,
foreign_sales_ratio=foreign_sales/total_sales) %>%
select(date_ist,total_sales, total_sales, new_sales_ratio, old_sales_ratio, mortgage_sales_ratio,
foreign_sales_ratio, new_building_price_index, price_index, `house_unit_price_Tl/m2`)
data_ratios
## # A tibble: 93 x 9
## date_ist total_sales new_sales_ratio old_sales_ratio mortgage_sales_~
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 2013-01 18235 0.455 0.545 0.462
## 2 2013-02 18971 0.436 0.564 0.466
## 3 2013-03 21570 0.442 0.558 0.471
## 4 2013-04 20791 0.421 0.579 0.468
## 5 2013-05 22030 0.425 0.575 0.490
## 6 2013-06 19357 0.422 0.578 0.504
## 7 2013-07 20668 0.437 0.563 0.487
## 8 2013-08 14930 0.466 0.534 0.458
## 9 2013-09 18514 0.439 0.561 0.440
## 10 2013-10 14866 0.453 0.547 0.422
## # ... with 83 more rows, and 4 more variables: foreign_sales_ratio <dbl>,
## # new_building_price_index <dbl>, price_index <dbl>,
## # `house_unit_price_Tl/m2` <dbl>
plot_df2 <- data_ratios %>% select(date_ist,total_sales,new_sales_ratio,old_sales_ratio,mortgage_sales_ratio,foreign_sales_ratio)
plot_df2
## # A tibble: 93 x 6
## date_ist total_sales new_sales_ratio old_sales_ratio mortgage_sales_~
## <chr> <dbl> <dbl> <dbl> <dbl>
## 1 2013-01 18235 0.455 0.545 0.462
## 2 2013-02 18971 0.436 0.564 0.466
## 3 2013-03 21570 0.442 0.558 0.471
## 4 2013-04 20791 0.421 0.579 0.468
## 5 2013-05 22030 0.425 0.575 0.490
## 6 2013-06 19357 0.422 0.578 0.504
## 7 2013-07 20668 0.437 0.563 0.487
## 8 2013-08 14930 0.466 0.534 0.458
## 9 2013-09 18514 0.439 0.561 0.440
## 10 2013-10 14866 0.453 0.547 0.422
## # ... with 83 more rows, and 1 more variable: foreign_sales_ratio <dbl>
plot_df3 = plot_df2 %>% select(date_ist, new_sales_ratio, old_sales_ratio, mortgage_sales_ratio)
ggplot(plot_df2, aes(x=date_ist, y=new_sales_ratio,group=1)) + geom_line()+ geom_point(color="blue") + labs(x = "Months", y = "Sales Ratio of New Houses")
plot_df3 %>% pivot_longer(.,-date_ist) %>% ggplot(.,aes(x=date_ist,y=value, group=1,color=name)) + geom_line() + labs(x = "Months", y = "Sales Ratios")
ggplot()+
geom_line(data=plot_df2,aes(x=date_ist, y=new_sales_ratio,group=1, colour="darkblue"),size=1 )+
geom_line(data=plot_df2,aes(x=date_ist, y=old_sales_ratio,group=1, colour="red"),size=1) +
geom_line(data=plot_df2,aes(x=date_ist, y=mortgage_sales_ratio,group=1, colour="green"), size=1)+
scale_color_discrete(name = "House Categories", labels = c("new house sales ratio", "old house sales ratio","mortgage house sales ratio")) + labs(x = "date", y = "Sales Ratios")
Average Monthly Sales for Years
data_yearly= data %>%filter(date_ist<"2020-09") %>% group_by(year = substr(date_ist,1,4)) %>%
summarise(avg_mean_sales = mean(total_sales), avg_new_bldg_pi=mean(new_building_price_index), avg_price_index=mean(price_index))
## `summarise()` ungrouping output (override with `.groups` argument)
data_yearly
## # A tibble: 8 x 4
## year avg_mean_sales avg_new_bldg_pi avg_price_index
## <chr> <dbl> <dbl> <dbl>
## 1 2013 19566. 53.6 52.5
## 2 2014 18788. 63.6 63.2
## 3 2015 19981. 78.6 79.0
## 4 2016 19369 91.6 92.4
## 5 2017 19865. 100. 100.
## 6 2018 19505. 102. 102.
## 7 2019 19806. 102. 101.
## 8 2020 22004. 122. 116.
ggplot(data_yearly, aes(x=year, y=avg_mean_sales,group=1)) + geom_line()+ geom_point(color="red") + labs(x = "Years", y = "Monthly Number of Sales")
