# Load packages
# Core
library(tidyverse)
library(tidyquant)
Functions
When should you write a function?
# For reproducible work
set.seed (1234)
# Create a data frame
df <- tibble:: tibble(
a = rnorm(10),
b = rnorm(10),
c = rnorm(10),
d=rnorm(10)
)
# Rescale each column
df$a <- (df$a - min(df$a, na.rm = TRUE)) /
(max(df$a, na.rm = TRUE) - min(df$a, na.rm = TRUE))
df$b <- (df$b - min(df$b, na.rm = TRUE)) /
(max(df$b, na.rm = TRUE) - min(df$b, na.rm = TRUE))
df$c <- (df$c - min(df$c, na.rm = TRUE)) /
(max(df$c, na.rm = TRUE) - min(df$c, na.rm = TRUE))
df$d <- (df$d - min(df$d, na.rm = TRUE)) /
(max(df$d, na.rm = TRUE) - min(df$d, na.rm = TRUE))
df
## # A tibble: 10 × 4
## a b c d
## <dbl> <dbl> <dbl> <dbl>
## 1 0.332 0.153 0.782 1
## 2 0.765 0 0.473 0.519
## 3 1 0.0651 0.498 0.448
## 4 0 0.311 0.943 0.511
## 5 0.809 0.573 0.373 0.168
## 6 0.831 0.260 0 0.308
## 7 0.516 0.143 1 0
## 8 0.524 0.0255 0.210 0.256
## 9 0.519 0.0472 0.708 0.575
## 10 0.424 1 0.253 0.522
rescale <- function(x) {
# body
x <- (x - min(x, na.rm = TRUE)) /
(max(x, na.rm = TRUE) - min(x, na.rm = TRUE))
# return value
return(x)
}
df$a <- rescale (df$a)
df$b <-rescale (df$b)
df$c <- rescale (df$c)
df$d <- rescale (df$d)
Functions are for humans and computers
Conditional execution
detect_sign <- function (x) {
if (x > 0) {
message ("value is positive")
print(x)
} else if (x == 0) {
warning( "Value is not positive, but it can be accepted")
print(x)
} else{
stop( "Value is negative, but the function must stop")
print(x)
}
}
3 %>% detect_sign()
## [1] 3
0 %>% detect_sign()
## [1] 0
# -1 %>% detect_sign()
Function arguments
?mean
x<- c(1:10, 100, NA)
x
## [1] 1 2 3 4 5 6 7 8 9 10 100 NA
x %>% mean()
## [1] NA
x %>% mean (na.rm = TRUE)
## [1] 14.09091
x %>% mean(na.rm = TRUE, trim = 0.1)
## [1] 6
mean_remove_na <- function(x, na.rm = TRUE, ...) {
avg <- mean(x, na.rm = na.rm, ...)
return(avg)
}
x %>% mean_remove_na()
## [1] 14.09091
x %>% mean_remove_na(na.rm = FALSE)
## [1] NA
x %>% mean_remove_na(trim = 0.1)
## [1] 6
Return values
1 Import stock prices
symbols <- c("SPY", "EFA", "IJS", "EEM","AGG")
prices <- tq_get(x = symbols,
get = "stock.prices",
from = "2012-12-31",
to = "2017-12-31")
2 Convert prices to returns (monthly)
asset_returns_tbl <- prices %>%
group_by(symbol) %>%
tq_transmute(select = adjusted,
mutate_fun = periodReturn,
period = "monthly",
type = "log") %>%
slice(-1) %>%
ungroup() %>%
set_names(c("asset", "date", "returns"))
3 Assign weight
# symbols
symbols <- asset_returns_tbl %>% distinct(asset) %>% pull()
symbols
## [1] "AGG" "EEM" "EFA" "IJS" "SPY"
# weights
weights <- c(0.25, 0.25, 0.2, 0.2, 0.1)
weights
## [1] 0.25 0.25 0.20 0.20 0.10
w_tbl <- tibble(symbols, weights)
w_tbl
## # A tibble: 5 × 2
## symbols weights
## <chr> <dbl>
## 1 AGG 0.25
## 2 EEM 0.25
## 3 EFA 0.2
## 4 IJS 0.2
## 5 SPY 0.1
4 Build a portfolio
# ?tq_portfolio
portfolio_returns_tbl <- asset_returns_tbl %>%
tq_portfolio(assets_col = asset,
returns_col = returns,
weights = w_tbl,
rebalance_on = "months")
portfolio_returns_tbl
## # A tibble: 60 × 2
## date portfolio.returns
## <date> <dbl>
## 1 2013-01-31 0.0204
## 2 2013-02-28 -0.00239
## 3 2013-03-28 0.0121
## 4 2013-04-30 0.0174
## 5 2013-05-31 -0.0128
## 6 2013-06-28 -0.0247
## 7 2013-07-31 0.0321
## 8 2013-08-30 -0.0224
## 9 2013-09-30 0.0511
## 10 2013-10-31 0.0301
## # ℹ 50 more rows
5.1 Get market returns
market_returns_tbl <-tq_get(x = "SPY",
get = "stock.prices",
from = "2012-12-31",
to = "2017-12-31") %>%
# Convert prices to returns
tq_transmute(select = adjusted,
mutate_fun = periodReturn,
period = "monthly",
type = "log",
col_rename ="returns") %>%
slice(-1)
5.2 Join returns
portfolio_market_returns_tbl<-left_join(market_returns_tbl, portfolio_returns_tbl, by = "date") %>%
set_names("date", "market_returns", "portfolio_returns")
5.3 CAPM Beta
portfolio_market_returns_tbl %>%
tq_performance(Ra = portfolio_returns,
Rb = market_returns,
performance_fun = CAPM.beta)
## # A tibble: 1 × 1
## CAPM.beta.1
## <dbl>
## 1 0.738
6 Plot
Scatterplot of returns with regression line
portfolio_market_returns_tbl %>%
ggplot(aes(x=market_returns,
y = portfolio_returns)) +
geom_point(color = "cornflowerblue") +
geom_smooth(method = "lm", se = FALSE, size = 1.5, color = tidyquant:: palette_light()[3]) +
labs(y="Portfolio Returns",
x = "Market Returns")
Line plot of fitted vs actual returns
actual_fitted_long_tbl <-portfolio_market_returns_tbl %>%
#Linear Regression Model
lm(portfolio_returns ~ market_returns, data = .) %>%
# Get
broom::augment() %>%
# Add date
mutate(date = portfolio_market_returns_tbl$date) %>%
select(date, portfolio_returns, .fitted) %>%
#Transform data to long
pivot_longer(cols = c(portfolio_returns, .fitted),
names_to = "type", values_to = "returns")
actual_fitted_long_tbl %>%
ggplot(aes(x=date, y =returns, color = type)) +
geom_line()
