rm(list = ls())
new=NULL
id_list=c('CII','DIG','HPG',"HT1",'HSG',"GAS","GVR",'TPB','TCB',
'MSN')
for (j in id_list){
for (i in 1:9){
query_params <- list(currentPage=i,id = j)
parameter_response <- GET("https://www.cophieu68.vn/historyprice.php", query = query_params)
stock_share =read_html(parameter_response)
new1=html_nodes(stock_share, xpath="//table[@class='stock']") %>%
html_table(header = TRUE,fill=TRUE) %>% as.data.frame()
new1=new1[,2:13]
new1$symbol=j
new=rbind(new,new1)
}}
stock=new
colnames(stock)=c("date","Last_closed_price","absolute_price_change",
"Percentage_price_change", "Closed_price",
"Trading_Volume","Open_price","Highest_price",
"Lowest_price","Exchange_volume", "Foregin_buy_volume", "Foreign_sell_volume","symbol")
stock$date=as.Date(stock$date, format="%d-%m-%Y")
for (i in 2:12){stock[,i]=as.numeric(gsub(',', '', stock[,i]))}
stock$Trading_Volume=as.numeric(gsub(',', '', stock$Trading_Volume))
stock$Percentage_price_change=stock$absolute_price_change/stock$Last_closed_price
prices=stock %>% filter(!is.na(date))
# prices = prices %>%
# select(date, Closed_price) %>%
# mutate_at(vars(-date), as.numeric) %>%
# mutate(date = ymd(parse_date_time(date, "%Y-%m-%d"))) %>%
# arrange(date)
Log Return Data Preparation
prices_daily_log_returns <- prices %>%
group_by(symbol) %>%
tq_transmute(select = Closed_price,
mutate_fun = periodReturn,
period = "daily",
type = "log",
col_rename = "daily.returns")
prices_daily_log_returns %>% ggplot(aes(x=date, y=daily.returns, col=symbol))+geom_line()+facet_wrap(symbol~.)
# Discard row with price tag
#
# raw_data <- raw_data[-1,]%>%
# select(.,-c(X,X.1,X.2,X.3))
#
# raw_data <- raw_data[-c(1248,1249),]
# raw_data <- raw_data %>% mutate_at(vars(-Date), as.numeric) %>%
# mutate(Date = ymd(parse_date_time(Date, "%d/%m/%Y"))) %>%
# arrange(Date)
#
#
# # Extract each symbol for future usage if necessary
# symbols <- colnames(raw_data[,-1])
#
# # Create return dataframe
# data_wide_return <- sapply(raw_data[2:ncol(raw_data)], function(x) diff(log(x), lag =1))
#
# data_wide_return <- cbind.data.frame(raw_data['Date'][-1,], data_wide_return)
#
# colnames(data_wide_return)[1] = "Date"
prices_daily_log_returns %>% filter(date > "2018-06-04" , date < "2021-11-03") %>% pivot_wider(names_from = symbol, values_from = daily.returns) -> data_wide_return
# Remove date column:
data_wide_return %>% select(-date) -> return_wide_train
# Calculate stock mean:
mean_ret <- colMeans(return_wide_train)
# Covariance matrix:
cov_mat <- cov(return_wide_train)
# Number of observations:
T_rows <- nrow(return_wide_train)
# Number of stock symbols:
N <- ncol(return_wide_train)
# Risk-free rate
Rf <- 5.11/100
# Defining the Sharpe ratio function
sharpe_func <- function(w1,w2,w3,w4,w5,w6,w7,w8,w9,w10){
weight <- c(w1,w2,w3,w4,w5,w6,w7,w8,w9,w10)
# Sharpe ratio numerator (Difference between return of portfolio and return of the market)
numerator <- numeric()
for (i in 1:N) {
numerator[i] <- weight[i]*mean_ret[i]
}
# Sharpe ratio denominator
denominator<- numeric()
for (i in 1:N) {
denominator1 <- numeric()
for (j in 1:N) {
denominator1[j] <- weight[i]*weight[j]*cov_mat[i,j]
}
denominator[i] <-sum(denominator1)
}
sharpe_func<- (sum(numerator) - Rf)/sum(denominator)
sharpe_func <- sharpe_func - 1e9 * (round(sum(weight),10)-1)^2
result <- list(Score = sharpe_func, Pred = 0)
return(result)
}
# Place for replicate coding input
# x = 5:30
#
# paste0("w", x, "= runif(20,0,1)", collapse = ",")
library(rBayesianOptimization)
# Defining search boundary
search_bound <- list(w1= c(0,0.5),w2= c(0,0.5),w3= c(0,1),w4= c(0,1),w5= c(0,0.5),w6= c(0,0.5),w7= c(0,0.5),w8= c(0,1),w9= c(0,1),w10= c(0,1))
# Defining the initial weight
set.seed(29)
search_grid <- data.frame(w1 = runif(20,0,0.5),
w2 = runif(20,0,0.5),
w3 = runif(20,0,1),
w4 = runif(20,0,1),
w5= runif(20,0,0.5),w6= runif(20,0,1),w7= runif(20,0,0.5),w8= runif(20,0,1),w9= runif(20,0,1),w10= runif(20,0,1))
bayes_finance_ucb <- BayesianOptimization(FUN = sharpe_func, bounds = search_bound,
init_grid_dt = search_grid, init_points = 0,
n_iter = 10, acq = "ei")
## elapsed = 0.02 Round = 1 w1 = 0.04984052 w2 = 0.3329466 w3 = 0.6111826 w4 = 0.4156561 w5 = 0.3312624 w6 = 0.1508912 w7 = 0.198907 w8 = 0.8652624 w9 = 0.1592352 w10 = 0.4184502 Value = -6419302564.2893
## elapsed = 0.00 Round = 2 w1 = 0.1204511 w2 = 0.3091565 w3 = 0.002232353 w4 = 0.1553593 w5 = 0.01037559 w6 = 0.2003316 w7 = 0.0793302 w8 = 0.05953728 w9 = 0.8781436 w10 = 0.7184413 Value = -2351189330.3493
## elapsed = 0.00 Round = 3 w1 = 0.0516069 w2 = 0.4864382 w3 = 0.9860362 w4 = 0.5596409 w5 = 0.4153229 w6 = 0.2821699 w7 = 0.424858 w8 = 0.140359 w9 = 0.1264804 w10 = 0.5893252 Value = -9377298733.1494
## elapsed = 0.00 Round = 4 w1 = 0.1627919 w2 = 0.4911547 w3 = 0.6829247 w4 = 0.3582216 w5 = 0.1795848 w6 = 0.1353195 w7 = 0.4777378 w8 = 0.6203624 w9 = 0.8325267 w10 = 0.7825712 Value = -13862183214.0860
## elapsed = 0.00 Round = 5 w1 = 0.2924944 w2 = 0.3108449 w3 = 0.07372197 w4 = 0.5145345 w5 = 0.1693941 w6 = 0.885249 w7 = 0.1130167 w8 = 0.7341157 w9 = 0.8221141 w10 = 0.1641373 Value = -9484076778.5601
## elapsed = 0.00 Round = 6 w1 = 0.04654339 w2 = 0.1756746 w3 = 0.8676589 w4 = 0.7653593 w5 = 0.235783 w6 = 0.9293707 w7 = 0.005117598 w8 = 0.5512438 w9 = 0.3087414 w10 = 0.6289377 Value = -12351221645.5199
## elapsed = 0.00 Round = 7 w1 = 0.4140838 w2 = 0.2437006 w3 = 0.9599468 w4 = 0.5132438 w5 = 0.4804521 w6 = 0.3827009 w7 = 0.2728062 w8 = 0.04626104 w9 = 0.4052774 w10 = 0.396292 Value = -9701758685.6108
## elapsed = 0.00 Round = 8 w1 = 0.4331525 w2 = 0.4496016 w3 = 0.7208769 w4 = 0.6422553 w5 = 0.3821826 w6 = 0.7945976 w7 = 0.2243422 w8 = 0.9881893 w9 = 0.6558969 w10 = 0.8591197 Value = -26524712085.9509
## elapsed = 0.00 Round = 9 w1 = 0.05999622 w2 = 0.3407801 w3 = 0.5997722 w4 = 0.4208255 w5 = 0.03845926 w6 = 0.5476572 w7 = 0.03492753 w8 = 0.2753723 w9 = 0.08356558 w10 = 0.8498428 Value = -5067895807.8965
## elapsed = 0.00 Round = 10 w1 = 0.1165734 w2 = 0.08033245 w3 = 0.6492987 w4 = 0.2934759 w5 = 0.2339024 w6 = 0.1455085 w7 = 0.3942132 w8 = 0.4299034 w9 = 0.1360977 w10 = 0.64035 Value = -4492940151.0987
## elapsed = 0.00 Round = 11 w1 = 0.4912949 w2 = 0.1830575 w3 = 0.4626285 w4 = 0.1177303 w5 = 0.3422389 w6 = 0.5254235 w7 = 0.4546273 w8 = 0.01006644 w9 = 0.3475411 w10 = 0.7914048 Value = -7431148543.6026
## elapsed = 0.00 Round = 12 w1 = 0.1965482 w2 = 0.06592472 w3 = 0.7139501 w4 = 0.892861 w5 = 0.2125736 w6 = 0.37759 w7 = 0.4457036 w8 = 0.1197284 w9 = 0.4222592 w10 = 0.6565981 Value = -9633182230.5617
## elapsed = 0.00 Round = 13 w1 = 0.1505191 w2 = 0.03732479 w3 = 0.2014642 w4 = 0.2470552 w5 = 0.264667 w6 = 0.3697815 w7 = 0.1900549 w8 = 0.1177646 w9 = 0.5620651 w10 = 0.951605 Value = -4377724973.3363
## elapsed = 0.00 Round = 14 w1 = 0.3157334 w2 = 0.3610581 w3 = 0.621876 w4 = 0.07783208 w5 = 0.2021581 w6 = 0.964011 w7 = 0.2376033 w8 = 0.185089 w9 = 0.889262 w10 = 0.04787636 Value = -8424501834.9537
## elapsed = 0.00 Round = 15 w1 = 0.08808544 w2 = 0.2461224 w3 = 0.5012273 w4 = 0.02612822 w5 = 0.1309003 w6 = 0.09747287 w7 = 0.2338389 w8 = 0.1404766 w9 = 0.6059731 w10 = 0.9389886 Value = -4036940142.9839
## elapsed = 0.00 Round = 16 w1 = 0.413705 w2 = 0.04976043 w3 = 0.4914928 w4 = 0.2887795 w5 = 0.08058905 w6 = 0.2680898 w7 = 0.06733307 w8 = 0.3849319 w9 = 0.1917522 w10 = 0.8272932 Value = -4258969178.5048
## elapsed = 0.00 Round = 17 w1 = 0.3312638 w2 = 0.4608563 w3 = 0.5167407 w4 = 0.8971432 w5 = 0.2424163 w6 = 0.7004453 w7 = 0.02640971 w8 = 0.2664996 w9 = 0.7812782 w10 = 0.1021141 Value = -11056736418.3749
## elapsed = 0.00 Round = 18 w1 = 0.18106 w2 = 0.157966 w3 = 0.8234472 w4 = 0.05974056 w5 = 0.3067763 w6 = 0.8400222 w7 = 0.2505397 w8 = 0.5682885 w9 = 0.7567963 w10 = 0.04945041 Value = -8964557769.6340
## elapsed = 0.00 Round = 19 w1 = 0.4333727 w2 = 0.1638351 w3 = 0.5613287 w4 = 0.007461678 w5 = 0.3816424 w6 = 0.5831163 w7 = 0.1469588 w8 = 0.01129588 w9 = 0.4386172 w10 = 0.4383498 Value = -4691462833.6173
## elapsed = 0.00 Round = 20 w1 = 0.1813132 w2 = 0.03351547 w3 = 0.1473852 w4 = 0.2175045 w5 = 0.1893821 w6 = 0.5741353 w7 = 0.1201772 w8 = 0.6580939 w9 = 0.4580795 w10 = 0.8342627 Value = -5826666939.5675
## elapsed = 0.02 Round = 21 w1 = 0.3206193 w2 = 0.5000 w3 = 2.220446e-16 w4 = 2.220446e-16 w5 = 2.220446e-16 w6 = 2.220446e-16 w7 = 2.220446e-16 w8 = 2.220446e-16 w9 = 2.220446e-16 w10 = 2.220446e-16 Value = -32177637.3572
## elapsed = 0.00 Round = 22 w1 = 2.220446e-16 w2 = 2.220446e-16 w3 = 2.220446e-16 w4 = 2.220446e-16 w5 = 0.5000 w6 = 2.220446e-16 w7 = 2.220446e-16 w8 = 2.220446e-16 w9 = 2.220446e-16 w10 = 2.220446e-16 Value = -250000242.4519
## elapsed = 0.00 Round = 23 w1 = 2.220446e-16 w2 = 2.220446e-16 w3 = 2.220446e-16 w4 = 2.220446e-16 w5 = 2.220446e-16 w6 = 2.220446e-16 w7 = 2.220446e-16 w8 = 0.6530171 w9 = 2.220446e-16 w10 = 0.1425383 Value = -41797810.3427
## elapsed = 0.00 Round = 24 w1 = 2.220446e-16 w2 = 2.220446e-16 w3 = 1.0000 w4 = 1.0000 w5 = 2.220446e-16 w6 = 2.220446e-16 w7 = 0.5000 w8 = 2.220446e-16 w9 = 2.220446e-16 w10 = 1.0000 Value = -6.25e+09
## elapsed = 0.00 Round = 25 w1 = 0.4998943 w2 = 0.5000 w3 = 2.220446e-16 w4 = 2.220446e-16 w5 = 2.220446e-16 w6 = 2.220446e-16 w7 = 2.220446e-16 w8 = 0.0002114512 w9 = 1.0000 w10 = 0.0002114512 Value = -1000634500.3461
## elapsed = 0.00 Round = 26 w1 = 0.5000 w2 = 0.5000 w3 = 1.0000 w4 = 2.220446e-16 w5 = 2.220446e-16 w6 = 2.220446e-16 w7 = 0.5000 w8 = 2.220446e-16 w9 = 2.220446e-16 w10 = 0.01161607 Value = -2284983171.1011
## elapsed = 0.00 Round = 27 w1 = 0.2598206 w2 = 0.006403978 w3 = 1.0000 w4 = 0.1690654 w5 = 0.4757668 w6 = 2.220446e-16 w7 = 0.4210082 w8 = 0.09002675 w9 = 1.0000 w10 = 0.6111853 Value = -9200769803.5739
## elapsed = 0.00 Round = 28 w1 = 2.220446e-16 w2 = 2.220446e-16 w3 = 2.220446e-16 w4 = 2.220446e-16 w5 = 2.220446e-16 w6 = 0.5000 w7 = 2.220446e-16 w8 = 2.220446e-16 w9 = 2.220446e-16 w10 = 2.220446e-16 Value = -250000458.0758
## elapsed = 0.00 Round = 29 w1 = 0.4999998 w2 = 0.5000 w3 = 2.220446e-16 w4 = 0.01411956 w5 = 0.4929404 w6 = 4.71866e-08 w7 = 0.461341 w8 = 0.9999995 w9 = 2.220446e-16 w10 = 1.0000 Value = -8811400648.5044
## elapsed = 0.00 Round = 30 w1 = 0.1638408 w2 = 0.5000 w3 = 2.220446e-16 w4 = 2.220446e-16 w5 = 5.703455e-10 w6 = 5.245444e-10 w7 = 2.220446e-16 w8 = 0.01920682 w9 = 0.987083 w10 = 1.0000 Value = -2789336320.9519
##
## Best Parameters Found:
## Round = 21 w1 = 0.3206193 w2 = 0.5000 w3 = 2.220446e-16 w4 = 2.220446e-16 w5 = 2.220446e-16 w6 = 2.220446e-16 w7 = 2.220446e-16 w8 = 2.220446e-16 w9 = 2.220446e-16 w10 = 2.220446e-16 Value = -32177637.3572
markowitz_portfolio <- function(...) {
top_mat <- cbind(2*cov_mat, rep(1, N))
bot_vec <- c(rep(1, N), 0)
Am_mat <- rbind(top_mat, bot_vec)
b_vec <- c(rep(0, N), 1)
zm_mat <- solve(Am_mat) %*% b_vec
X_min_var_markowitz <- zm_mat[1:N, 1]
return(X_min_var_markowitz)
}
markowitz_portfolio()
## CII DIG HPG HT1 HSG GAS
## 0.24920592 0.04889129 0.12661811 0.13792272 -0.06046167 0.07255599
## GVR TPB TCB MSN
## 0.01241077 0.16556898 0.04531483 0.20197308
