rm(list=ls())
#install.packages('quantmod')
library(quantmod)
## Loading required package: xts
## Loading required package: zoo
##
## Attaching package: 'zoo'
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric
## Loading required package: TTR
## Version 0.4-0 included new data defaults. See ?getSymbols.
getSymbols("GOOG", auto.assign = TRUE)
## 'getSymbols' currently uses auto.assign=TRUE by default, but will
## use auto.assign=FALSE in 0.5-0. You will still be able to use
## 'loadSymbols' to automatically load data. getOption("getSymbols.env")
## and getOption("getSymbols.auto.assign") will still be checked for
## alternate defaults.
##
## This message is shown once per session and may be disabled by setting
## options("getSymbols.warning4.0"=FALSE). See ?getSymbols for details.
## [1] "GOOG"
# There are two primary time series data
# xts and zoo
tickers = c("GOOG", "MSFT", "AMZN")
getSymbols(tickers, from = "2010-01-01", auto.assign = TRUE)
## [1] "GOOG" "MSFT" "AMZN"
# download multiple prices to data variable
data = new.env()
getSymbols(tickers, from = "2010-01-01", env = data , auto.assign = TRUE)
## [1] "GOOG" "MSFT" "AMZN"
ls(data)
## [1] "AMZN" "GOOG" "MSFT"
names(data)
## [1] "GOOG" ".getSymbols" "AMZN" "MSFT"
head(data$AMZN)
## AMZN.Open AMZN.High AMZN.Low AMZN.Close AMZN.Volume
## 2010-01-04 136.25 136.61 133.14 133.90 7599900
## 2010-01-05 133.43 135.48 131.81 134.69 8851900
## 2010-01-06 134.60 134.73 131.65 132.25 7178800
## 2010-01-07 132.01 132.32 128.80 130.00 11030200
## 2010-01-08 130.56 133.68 129.03 133.52 9830500
## 2010-01-11 132.62 132.80 129.21 130.31 8779400
## AMZN.Adjusted
## 2010-01-04 133.90
## 2010-01-05 134.69
## 2010-01-06 132.25
## 2010-01-07 130.00
## 2010-01-08 133.52
## 2010-01-11 130.31
str(AMZN)
## An 'xts' object on 2010-01-04/2019-03-26 containing:
## Data: num [1:2322, 1:6] 136 133 135 132 131 ...
## - attr(*, "dimnames")=List of 2
## ..$ : NULL
## ..$ : chr [1:6] "AMZN.Open" "AMZN.High" "AMZN.Low" "AMZN.Close" ...
## Indexed by objects of class: [Date] TZ: UTC
## xts Attributes:
## List of 2
## $ src : chr "yahoo"
## $ updated: POSIXct[1:1], format: "2019-03-27 21:57:31"
class(AMZN)
## [1] "xts" "zoo"
tail(AMZN,3)
## AMZN.Open AMZN.High AMZN.Low AMZN.Close AMZN.Volume
## 2019-03-22 1810.17 1818.98 1763.11 1764.77 6363000
## 2019-03-25 1757.79 1782.68 1747.50 1774.26 5103800
## 2019-03-26 1793.00 1805.77 1773.36 1783.76 4838400
## AMZN.Adjusted
## 2019-03-22 1764.77
## 2019-03-25 1774.26
## 2019-03-26 1783.76
names(AMZN)
## [1] "AMZN.Open" "AMZN.High" "AMZN.Low" "AMZN.Close"
## [5] "AMZN.Volume" "AMZN.Adjusted"
ls(AMZN)
## [1] "AMZN.Adjusted" "AMZN.Close" "AMZN.High" "AMZN.Low"
## [5] "AMZN.Open" "AMZN.Volume"
head(AMZN$AMZN.Close)
## AMZN.Close
## 2010-01-04 133.90
## 2010-01-05 134.69
## 2010-01-06 132.25
## 2010-01-07 130.00
## 2010-01-08 133.52
## 2010-01-11 130.31
AMZN2010_15=AMZN['2010/2015']
#Extract closing price: Cl(),
# Adjusted price: Ad()
AMZN.ad<-Ad(AMZN)
head(AMZN.ad)
## AMZN.Adjusted
## 2010-01-04 133.90
## 2010-01-05 134.69
## 2010-01-06 132.25
## 2010-01-07 130.00
## 2010-01-08 133.52
## 2010-01-11 130.31
class(AMZN.ad)
## [1] "xts" "zoo"
# write function to gather adjusted prices together
firm3<-merge(Ad(AMZN), Ad(GOOG), Ad(MSFT))
head(firm3)
## AMZN.Adjusted GOOG.Adjusted MSFT.Adjusted
## 2010-01-04 133.90 311.3500 24.61580
## 2010-01-05 134.69 309.9789 24.62375
## 2010-01-06 132.25 302.1647 24.47263
## 2010-01-07 130.00 295.1305 24.21812
## 2010-01-08 133.52 299.0649 24.38515
## 2010-01-11 130.31 298.6128 24.07497
colnames(firm3)<-c("AMZN", "GOOG", "MSFG")
head(firm3)
## AMZN GOOG MSFG
## 2010-01-04 133.90 311.3500 24.61580
## 2010-01-05 134.69 309.9789 24.62375
## 2010-01-06 132.25 302.1647 24.47263
## 2010-01-07 130.00 295.1305 24.21812
## 2010-01-08 133.52 299.0649 24.38515
## 2010-01-11 130.31 298.6128 24.07497
#Import data from .txt file
etf4<-read.table("ETF4_2010_2018_d1_english.txt", header = T, sep = ',')
str(etf4)
## 'data.frame': 6991 obs. of 5 variables:
## $ CO_ID : num 50 56 50 56 50 56 50 56 50 56 ...
## $ CoName: Factor w/ 4 levels "FB SSE180_0 ",..: 4 2 4 2 4 2 4 2 4 2 ...
## $ Date : int 20100104 20100104 20100105 20100105 20100106 20100106 20100107 20100107 20100108 20100108 ...
## $ Close : num 41.9 15.5 41.9 15.4 42.7 ...
## $ Volume: int 20083 281 16453 711 19012 402 14110 1223 11342 354 ...
# convert CO_ID into character;
etf4<-read.table("ETF4_2010_2018_d1_english.txt", header = T, sep = ',',
colClasses = c("CO_ID" = "character"))
str(etf4)
## 'data.frame': 6991 obs. of 5 variables:
## $ CO_ID : chr "0050 " "0056 " "0050 " "0056 " ...
## $ CoName: Factor w/ 4 levels "FB SSE180_0 ",..: 4 2 4 2 4 2 4 2 4 2 ...
## $ Date : int 20100104 20100104 20100105 20100105 20100106 20100106 20100107 20100107 20100108 20100108 ...
## $ Close : num 41.9 15.5 41.9 15.4 42.7 ...
## $ Volume: int 20083 281 16453 711 19012 402 14110 1223 11342 354 ...
head(etf4)
## CO_ID CoName Date Close Volume
## 1 0050 Yuanta Taiwan Top50 20100104 41.91 20083
## 2 0056 PTD 20100104 15.49 281
## 3 0050 Yuanta Taiwan Top50 20100105 41.91 16453
## 4 0056 PTD 20100105 15.42 711
## 5 0050 Yuanta Taiwan Top50 20100106 42.69 19012
## 6 0056 PTD 20100106 15.66 402
write.csv(etf4, "etf4.csv")
installed.packages('readr')
## Package LibPath Version Priority Depends Imports LinkingTo Suggests
## Enhances License License_is_FOSS License_restricts_use OS_type Archs
## MD5sum NeedsCompilation Built
library(readr)
etf4_csv<-read_csv("etf4.csv")
## Warning: Missing column names filled in: 'X1' [1]
## Parsed with column specification:
## cols(
## X1 = col_double(),
## CO_ID = col_character(),
## CoName = col_character(),
## Date = col_double(),
## Close = col_double(),
## Volume = col_double()
## )
etf4_csv
## # A tibble: 6,991 x 6
## X1 CO_ID CoName Date Close Volume
## <dbl> <chr> <chr> <dbl> <dbl> <dbl>
## 1 1 0050 Yuanta Taiwan Top50 20100104 41.9 20083
## 2 2 0056 PTD 20100104 15.5 281
## 3 3 0050 Yuanta Taiwan Top50 20100105 41.9 16453
## 4 4 0056 PTD 20100105 15.4 711
## 5 5 0050 Yuanta Taiwan Top50 20100106 42.7 19012
## 6 6 0056 PTD 20100106 15.7 402
## 7 7 0050 Yuanta Taiwan Top50 20100107 42.6 14110
## 8 8 0056 PTD 20100107 15.5 1223
## 9 9 0050 Yuanta Taiwan Top50 20100108 42.8 11342
## 10 10 0056 PTD 20100108 15.7 354
## # ... with 6,981 more rows
#--------------------------
# clean data
etf4.c<-etf4_csv[, c(-1,-3,-6)]
etf4.c
## # A tibble: 6,991 x 3
## CO_ID Date Close
## <chr> <dbl> <dbl>
## 1 0050 20100104 41.9
## 2 0056 20100104 15.5
## 3 0050 20100105 41.9
## 4 0056 20100105 15.4
## 5 0050 20100106 42.7
## 6 0056 20100106 15.7
## 7 0050 20100107 42.6
## 8 0056 20100107 15.5
## 9 0050 20100108 42.8
## 10 0056 20100108 15.7
## # ... with 6,981 more rows
colnames(etf4.c)<-c("id", "date", "price")
etf4.c
## # A tibble: 6,991 x 3
## id date price
## <chr> <dbl> <dbl>
## 1 0050 20100104 41.9
## 2 0056 20100104 15.5
## 3 0050 20100105 41.9
## 4 0056 20100105 15.4
## 5 0050 20100106 42.7
## 6 0056 20100106 15.7
## 7 0050 20100107 42.6
## 8 0056 20100107 15.5
## 9 0050 20100108 42.8
## 10 0056 20100108 15.7
## # ... with 6,981 more rows
#install.packages("magrittr")
library(magrittr)
#install.packages("dplyr")
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:xts':
##
## first, last
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
etf4.c<-etf4_csv%>%select(c(2,4,5))%>%rename("id" = "CO_ID", "date"= "Date", "price" = "Close")
etf4.c
## # A tibble: 6,991 x 3
## id date price
## <chr> <dbl> <dbl>
## 1 0050 20100104 41.9
## 2 0056 20100104 15.5
## 3 0050 20100105 41.9
## 4 0056 20100105 15.4
## 5 0050 20100106 42.7
## 6 0056 20100106 15.7
## 7 0050 20100107 42.6
## 8 0056 20100107 15.5
## 9 0050 20100108 42.8
## 10 0056 20100108 15.7
## # ... with 6,981 more rows
#install.packages("reshape2")
library(reshape2)
etf4.reorder = dcast(etf4.c, date~id)
## Using price as value column: use value.var to override.
dim(etf4.reorder)
## [1] 2223 5
head(etf4.reorder)
## date 0050 0056 006205 00646
## 1 20100104 41.91 15.49 NA NA
## 2 20100105 41.91 15.42 NA NA
## 3 20100106 42.69 15.66 NA NA
## 4 20100107 42.58 15.52 NA NA
## 5 20100108 42.84 15.69 NA NA
## 6 20100111 42.95 15.85 NA NA
str(etf4.reorder)
## 'data.frame': 2223 obs. of 5 variables:
## $ date : num 20100104 20100105 20100106 20100107 20100108 ...
## $ 0050 : num 41.9 41.9 42.7 42.6 42.8 ...
## $ 0056 : num 15.5 15.4 15.7 15.5 15.7 ...
## $ 006205: num NA NA NA NA NA NA NA NA NA NA ...
## $ 00646 : num NA NA NA NA NA NA NA NA NA NA ...
# convert into date format using as.Date()
etf4.reorder$date<-as.Date(as.character(etf4.reorder$date), "%Y%m%d")
head(etf4.reorder)
## date 0050 0056 006205 00646
## 1 2010-01-04 41.91 15.49 NA NA
## 2 2010-01-05 41.91 15.42 NA NA
## 3 2010-01-06 42.69 15.66 NA NA
## 4 2010-01-07 42.58 15.52 NA NA
## 5 2010-01-08 42.84 15.69 NA NA
## 6 2010-01-11 42.95 15.85 NA NA
str(etf4.reorder)
## 'data.frame': 2223 obs. of 5 variables:
## $ date : Date, format: "2010-01-04" "2010-01-05" ...
## $ 0050 : num 41.9 41.9 42.7 42.6 42.8 ...
## $ 0056 : num 15.5 15.4 15.7 15.5 15.7 ...
## $ 006205: num NA NA NA NA NA NA NA NA NA NA ...
## $ 00646 : num NA NA NA NA NA NA NA NA NA NA ...
# convert character into numeric
# convert to xts
#install.packages("xts")
library(xts)
etf4.xts<-xts(etf4.reorder[,-1], order.by = etf4.reorder$date)
head(etf4.xts)
## 0050 0056 006205 00646
## 2010-01-04 41.91 15.49 NA NA
## 2010-01-05 41.91 15.42 NA NA
## 2010-01-06 42.69 15.66 NA NA
## 2010-01-07 42.58 15.52 NA NA
## 2010-01-08 42.84 15.69 NA NA
## 2010-01-11 42.95 15.85 NA NA
tail(etf4.xts)
## 0050 0056 006205 00646
## 2018-12-22 72.60 24.17 25.10 23.15
## 2018-12-24 72.45 24.18 25.30 22.74
## 2018-12-25 71.53 23.97 24.96 22.47
## 2018-12-26 71.34 23.72 25.03 22.19
## 2018-12-27 72.79 23.91 25.17 23.06
## 2018-12-28 73.23 23.94 25.23 23.23
str(etf4.xts)
## An 'xts' object on 2010-01-04/2018-12-28 containing:
## Data: num [1:2223, 1:4] 41.9 41.9 42.7 42.6 42.8 ...
## - attr(*, "dimnames")=List of 2
## ..$ : NULL
## ..$ : chr [1:4] "0050" "0056" "006205" "00646"
## Indexed by objects of class: [Date] TZ: UTC
## xts Attributes:
## NULL
#----------------------------------------------
# Handling missingness in your data
#----------------------------------------------
# Last obs. carried forward
#etf4.xts$`0050`['2018-12-27']<-NA
#tail(etf4.xts)
etf4.xts<-na.locf(etf4.xts)
tail(etf4.xts)
## 0050 0056 006205 00646
## 2018-12-22 72.60 24.17 25.10 23.15
## 2018-12-24 72.45 24.18 25.30 22.74
## 2018-12-25 71.53 23.97 24.96 22.47
## 2018-12-26 71.34 23.72 25.03 22.19
## 2018-12-27 72.79 23.91 25.17 23.06
## 2018-12-28 73.23 23.94 25.23 23.23
# Next obs. carried backward
etf4.xts.fill<-na.locf(etf4.xts, fromLast = TRUE)
head(etf4.xts.fill)
## 0050 0056 006205 00646
## 2010-01-04 41.91 15.49 20.45 19.61
## 2010-01-05 41.91 15.42 20.45 19.61
## 2010-01-06 42.69 15.66 20.45 19.61
## 2010-01-07 42.58 15.52 20.45 19.61
## 2010-01-08 42.84 15.69 20.45 19.61
## 2010-01-11 42.95 15.85 20.45 19.61
#-------------------------------------------------
# delete NA values
etf4.xts<-na.omit(etf4.xts)
head(etf4.xts)
## 0050 0056 006205 00646
## 2015-12-14 53.29 18.25 31.06 19.61
## 2015-12-15 53.33 18.38 31.59 19.63
## 2015-12-16 54.14 18.56 31.60 19.89
## 2015-12-17 54.77 18.81 32.23 20.05
## 2015-12-18 54.50 18.95 32.18 19.85
## 2015-12-21 54.41 19.02 33.00 19.64
# or complete cases
#install.packages("tidyr")
library(tidyr)
##
## Attaching package: 'tidyr'
## The following object is masked from 'package:reshape2':
##
## smiths
## The following object is masked from 'package:magrittr':
##
## extract
etf4.xts1<-etf4.xts[complete.cases(etf4.xts),]
head(etf4.xts1)
## 0050 0056 006205 00646
## 2015-12-14 53.29 18.25 31.06 19.61
## 2015-12-15 53.33 18.38 31.59 19.63
## 2015-12-16 54.14 18.56 31.60 19.89
## 2015-12-17 54.77 18.81 32.23 20.05
## 2015-12-18 54.50 18.95 32.18 19.85
## 2015-12-21 54.41 19.02 33.00 19.64
#-----------------------------------------------------------
# export data
#----------------------------------------------------------
write.csv(etf4.xts, file = "myetf4.csv")
# date index disappears!!!
# you have to use write.zoo to save .xts file
write.zoo(etf4.xts, sep = ',', file = "myetf4.csv.1")
# you can save big file using saveRDS()
saveRDS(etf4.xts, file = "etf4.xts.rds")
etf4.xts2 <- readRDS("etf4.xts.rds")
head(etf4.xts2)
## 0050 0056 006205 00646
## 2015-12-14 53.29 18.25 31.06 19.61
## 2015-12-15 53.33 18.38 31.59 19.63
## 2015-12-16 54.14 18.56 31.60 19.89
## 2015-12-17 54.77 18.81 32.23 20.05
## 2015-12-18 54.50 18.95 32.18 19.85
## 2015-12-21 54.41 19.02 33.00 19.64
##
etf4.zoo <- read.zoo("myetf4.csv.1", header = TRUE, index.column =1,
sep = ",", format = "%Y-%m-%d")
head(etf4.zoo)
## X0050 X0056 X006205 X00646
## 2015-12-14 53.29 18.25 31.06 19.61
## 2015-12-15 53.33 18.38 31.59 19.63
## 2015-12-16 54.14 18.56 31.60 19.89
## 2015-12-17 54.77 18.81 32.23 20.05
## 2015-12-18 54.50 18.95 32.18 19.85
## 2015-12-21 54.41 19.02 33.00 19.64
class(etf4.zoo)
## [1] "zoo"
etf4.xts3<-as.xts(etf4.zoo)
head(etf4.xts3)
## X0050 X0056 X006205 X00646
## 2015-12-14 53.29 18.25 31.06 19.61
## 2015-12-15 53.33 18.38 31.59 19.63
## 2015-12-16 54.14 18.56 31.60 19.89
## 2015-12-17 54.77 18.81 32.23 20.05
## 2015-12-18 54.50 18.95 32.18 19.85
## 2015-12-21 54.41 19.02 33.00 19.64
#=============================================
# Querying for data
#=============================================
etf4_2016<-etf4.xts['2016']
etf4_2016_01_06 <- etf4.xts["20160101/20160630"]
head(etf4_2016_01_06)
## 0050 0056 006205 00646
## 2016-01-04 53.42 18.54 30.48 19.79
## 2016-01-05 52.97 18.50 29.81 19.74
## 2016-01-06 52.44 18.21 30.14 19.62
## 2016-01-07 51.45 18.38 28.08 19.43
## 2016-01-08 51.54 18.15 29.32 19.32
## 2016-01-11 50.73 17.80 28.13 19.01
#-----------------------------------------
# write function to compute returns
library(magrittr)
simple_returns01<-function(x) {
coredata(x[-1,])/coredata(x[-length(x),]) - 1 %>%
na.omit()
}
head(simple_returns01(AMZN.ad))
## AMZN.Adjusted
## [1,] 0.005899985
## [2,] -0.018115688
## [3,] -0.017013233
## [4,] 0.027076954
## [5,] -0.024041386
## [6,] -0.022715064
# or to keep the index of dates
simple_returns02<-function(x) {
na.omit(x/lag(x) - 1)
}
head(simple_returns02(AMZN.ad))
## AMZN.Adjusted
## 2010-01-05 0.005899985
## 2010-01-06 -0.018115688
## 2010-01-07 -0.017013233
## 2010-01-08 0.027076954
## 2010-01-11 -0.024041386
## 2010-01-12 -0.022715064
#
#install.packages("PerformanceAnalytics")
library(PerformanceAnalytics)
##
## Attaching package: 'PerformanceAnalytics'
## The following object is masked from 'package:graphics':
##
## legend
head(na.omit(Return.calculate(firm3)))
## AMZN GOOG MSFG
## 2010-01-05 0.005899985 -0.004403707 0.0003231258
## 2010-01-06 -0.018115688 -0.025208746 -0.0061373255
## 2010-01-07 -0.017013233 -0.023279489 -0.0103996583
## 2010-01-08 0.027076954 0.013331111 0.0068965292
## 2010-01-11 -0.024041386 -0.001511568 -0.0127199982
## 2010-01-12 -0.022715064 -0.017684003 -0.0066073198
firm3.mon<-firm3 %>% to.monthly(indexAt = "lastof", OHLC=FALSE) %>%
Return.calculate()
head(firm3.mon)
## AMZN GOOG MSFG
## 2010-01-31 NA NA NA
## 2010-02-28 -0.055896673 -0.005925163 0.02214583
## 2010-03-31 0.146706095 0.076537582 0.02162538
## 2010-04-30 0.009795993 -0.073035690 0.04267668
## 2010-05-31 -0.084901579 -0.076222178 -0.15139444
## 2010-06-30 -0.129124798 -0.083767454 -0.10813944
# Main problem: the return series are shown in calendar dates,
# not in trading dates
# Therefore, we use package PMwR instead!
#install.packages("PMwR")
library(PMwR)
head(returns(firm3))
## AMZN GOOG MSFG
## 2010-01-05 0.005899985 -0.004403707 0.0003231258
## 2010-01-06 -0.018115688 -0.025208746 -0.0061373255
## 2010-01-07 -0.017013233 -0.023279489 -0.0103996583
## 2010-01-08 0.027076954 0.013331111 0.0068965292
## 2010-01-11 -0.024041386 -0.001511568 -0.0127199982
## 2010-01-12 -0.022715064 -0.017684003 -0.0066073198
firm3.mon1<-returns(firm3, period = "month")
#options(digits = 5)
head(firm3.mon1)
## [1] -0.063405455 -0.055896673 0.146706095 0.009795993 -0.084901579
## [6] -0.129124798
firm3.mon1
## AMZN GOOG MSFG
## 2010-01-29 -6.3 -15.4 -8.9
## 2010-02-26 -5.6 -0.6 2.2
## 2010-03-31 14.7 7.7 2.2
## 2010-04-30 1.0 -7.3 4.3
## 2010-05-28 -8.5 -7.6 -15.1
## 2010-06-30 -12.9 -8.4 -10.8
## 2010-07-30 7.9 9.0 12.2
## 2010-08-31 5.9 -7.2 -8.6
## 2010-09-30 25.8 16.8 4.3
## 2010-10-29 5.2 16.7 8.9
## 2010-11-30 6.2 -9.4 -4.7
## 2010-12-31 2.6 6.9 10.5
## 2011-01-31 -5.8 1.1 -0.6
## 2011-02-28 2.2 2.2 -3.6
## 2011-03-31 3.9 -4.3 -4.5
## 2011-04-29 8.7 -7.3 2.1
## 2011-05-31 0.4 -2.8 -2.9
## 2011-06-30 4.0 -4.3 4.0
## 2011-07-29 8.8 19.2 5.4
## 2011-08-31 -3.3 -10.4 -2.3
## 2011-09-30 0.5 -4.8 -6.4
## 2011-10-31 -1.3 15.1 7.0
## 2011-11-30 -9.9 1.1 -3.2
## 2011-12-30 -10.0 7.8 1.5
## 2012-01-31 12.3 -10.2 13.8
## 2012-02-29 -7.6 6.6 8.2
## 2012-03-30 12.7 3.7 1.6
## 2012-04-30 14.5 -5.7 -0.7
## 2012-05-31 -8.2 -4.0 -8.2
## 2012-06-29 7.3 -0.1 4.8
## 2012-07-31 2.2 9.1 -3.7
## 2012-08-31 6.4 8.2 5.3
## 2012-09-28 2.4 10.1 -3.4
## 2012-10-31 -8.4 -9.8 -4.1
## 2012-11-30 8.2 2.7 -6.0
## 2012-12-31 -0.5 1.3 0.3
## 2013-01-31 5.8 6.8 2.8
## 2013-02-28 -0.5 6.0 2.1
## 2013-03-28 0.8 -0.9 2.9
## 2013-04-30 -4.8 3.8 15.7
## 2013-05-31 6.1 5.7 6.2
## 2013-06-28 3.2 1.1 -1.0
## 2013-07-31 8.5 0.8 -7.8
## 2013-08-30 -6.7 -4.6 5.6
## 2013-09-30 11.3 3.4 -0.4
## 2013-10-31 16.4 17.7 6.4
## 2013-11-29 8.1 2.8 8.5
## 2013-12-31 1.3 5.8 -1.9
## 2014-01-31 -10.1 5.4 1.1
## 2014-02-28 1.0 2.9 2.0
## 2014-03-31 -7.1 -8.3 7.0
## 2014-04-30 -9.6 -5.4 -1.4
## 2014-05-30 2.8 6.3 2.1
## 2014-06-30 3.9 2.7 1.9
## 2014-07-31 -3.6 -0.6 3.5
## 2014-08-29 8.3 0.0 5.9
## 2014-09-30 -4.9 1.0 2.0
## 2014-10-31 -5.3 -3.2 1.3
## 2014-11-28 10.9 -3.1 2.5
## 2014-12-31 -8.4 -2.8 -2.8
## 2015-01-30 14.2 1.5 -13.0
## 2015-02-27 7.2 4.5 9.3
## 2015-03-31 -2.1 -1.9 -7.3
## 2015-04-30 13.4 -1.4 19.6
## 2015-05-29 1.8 -1.0 -3.0
## 2015-06-30 1.1 -2.2 -5.8
## 2015-07-31 23.5 20.2 5.8
## 2015-08-31 -4.3 -1.2 -6.2
## 2015-09-30 -0.2 -1.6 1.7
## 2015-10-30 22.3 16.8 18.9
## 2015-11-30 6.2 4.5 3.9
## 2015-12-31 1.7 2.2 2.1
## 2016-01-29 -13.2 -2.1 -0.7
## 2016-02-29 -5.9 -6.1 -7.0
## 2016-03-31 7.4 6.8 8.5
## 2016-04-29 11.1 -7.0 -9.7
## 2016-05-31 9.6 6.2 7.0
## 2016-06-30 -1.0 -5.9 -3.5
## 2016-07-29 6.0 11.1 10.8
## 2016-08-31 1.4 -0.2 2.0
## 2016-09-30 8.9 1.3 0.2
## 2016-10-31 -5.7 0.9 4.0
## 2016-11-30 -5.0 -3.4 1.2
## 2016-12-30 -0.1 1.8 3.1
## 2017-01-31 9.8 3.2 4.0
## 2017-02-28 2.6 3.3 -0.4
## 2017-03-31 4.9 0.8 2.9
## 2017-04-28 4.3 9.2 3.9
## 2017-05-31 7.5 6.5 2.6
## 2017-06-30 -2.7 -5.8 -1.3
## 2017-07-31 2.0 2.4 5.5
## 2017-08-31 -0.7 0.9 3.4
## 2017-09-29 -2.0 2.1 -0.4
## 2017-10-31 15.0 6.0 11.7
## 2017-11-30 6.5 0.5 1.7
## 2017-12-29 -0.6 2.4 1.6
## 2018-01-31 24.1 11.8 11.1
## 2018-02-28 4.2 -5.6 -0.8
## 2018-03-29 -4.3 -6.6 -2.7
## 2018-04-30 8.2 -1.4 2.5
## 2018-05-31 4.1 6.7 6.1
## 2018-06-29 4.3 2.8 -0.2
## 2018-07-31 4.6 9.1 7.6
## 2018-08-31 13.2 0.1 6.3
## 2018-09-28 -0.5 -2.0 1.8
## 2018-10-31 -20.2 -9.8 -6.6
## 2018-11-30 5.8 1.6 4.3
## 2018-12-31 -11.1 -5.4 -8.4
## 2019-01-31 14.4 7.8 2.8
## 2019-02-28 -4.6 0.3 7.7
## 2019-03-26 8.8 5.8 5.2
firm3.day<-returns(firm3)
head(firm3.day)
## AMZN GOOG MSFG
## 2010-01-05 0.005899985 -0.004403707 0.0003231258
## 2010-01-06 -0.018115688 -0.025208746 -0.0061373255
## 2010-01-07 -0.017013233 -0.023279489 -0.0103996583
## 2010-01-08 0.027076954 0.013331111 0.0068965292
## 2010-01-11 -0.024041386 -0.001511568 -0.0127199982
## 2010-01-12 -0.022715064 -0.017684003 -0.0066073198
head(merge(firm3, firm3.day))
## AMZN GOOG MSFG AMZN.1 GOOG.1
## 2010-01-04 133.90 311.3500 24.61580 NA NA
## 2010-01-05 134.69 309.9789 24.62375 0.005899985 -0.004403707
## 2010-01-06 132.25 302.1647 24.47263 -0.018115688 -0.025208746
## 2010-01-07 130.00 295.1305 24.21812 -0.017013233 -0.023279489
## 2010-01-08 133.52 299.0649 24.38515 0.027076954 0.013331111
## 2010-01-11 130.31 298.6128 24.07497 -0.024041386 -0.001511568
## MSFG.1
## 2010-01-04 NA
## 2010-01-05 0.0003231258
## 2010-01-06 -0.0061373255
## 2010-01-07 -0.0103996583
## 2010-01-08 0.0068965292
## 2010-01-11 -0.0127199982
head(100* cumprod(1+firm3.day))
## AMZN GOOG MSFG
## 2010-01-05 100.59000 99.55963 100.03231
## 2010-01-06 98.76774 97.04986 99.41838
## 2010-01-07 97.08738 94.79058 98.38446
## 2010-01-08 99.71621 96.05425 99.06298
## 2010-01-11 97.31890 95.90906 97.80289
## 2010-01-12 95.10829 94.21300 97.15668
firm3.p.ret<-firm3.day %>% merge(firm3)
head(firm3.p.ret)
## AMZN.. GOOG.. MSFG.. AMZN.firm3 GOOG.firm3
## 2010-01-04 NA NA NA 133.90 311.3500
## 2010-01-05 0.005899985 -0.004403707 0.0003231258 134.69 309.9789
## 2010-01-06 -0.018115688 -0.025208746 -0.0061373255 132.25 302.1647
## 2010-01-07 -0.017013233 -0.023279489 -0.0103996583 130.00 295.1305
## 2010-01-08 0.027076954 0.013331111 0.0068965292 133.52 299.0649
## 2010-01-11 -0.024041386 -0.001511568 -0.0127199982 130.31 298.6128
## MSFG.firm3
## 2010-01-04 24.61580
## 2010-01-05 24.62375
## 2010-01-06 24.47263
## 2010-01-07 24.21812
## 2010-01-08 24.38515
## 2010-01-11 24.07497
#
#============================================================
# Plot in R
#-------------------------------------------------------------
# plot zoo object
plot(firm3.day)
# plot xts object
firm3.day %>% as.xts %>%
plot
axis(1, index(firm3.day), format(index(firm3.day), "%Y/%m"))
#
firm3.day.xts <-as.xts(firm3.day)
plot.xts(firm3.day.xts, auto.legend = TRUE)
#axis(side=1, at=yahoo2$date[ at ], labels=format(yahoo2$date[at], '%b-%y'))
#plot.xts(etf4_mon_ret, auto.legend = TRUE)
#-----------------------------------------------------------
#install.packages("tidyverse")
library(tidyverse)
## -- Attaching packages --------------------------------------------------------------------------------- tidyverse 1.2.1 --
## v ggplot2 3.1.0 v purrr 0.3.2
## v tibble 2.1.1 v stringr 1.4.0
## v ggplot2 3.1.0 v forcats 0.4.0
## -- Conflicts ------------------------------------------------------------------------------------ tidyverse_conflicts() --
## x tidyr::extract() masks magrittr::extract()
## x dplyr::filter() masks stats::filter()
## x dplyr::first() masks xts::first()
## x dplyr::lag() masks stats::lag()
## x dplyr::last() masks xts::last()
## x purrr::set_names() masks magrittr::set_names()
library(ggplot2)
# convert xts into data frame which can be used by ggplot
#etf4_returns.df<-fortify(etf4_returns_xts)
firm3_ret.df<-fortify(firm3.day, melt=TRUE)
head(firm3_ret.df)
## Index Series Value
## 1 2010-01-05 AMZN 0.005899985
## 2 2010-01-06 AMZN -0.018115688
## 3 2010-01-07 AMZN -0.017013233
## 4 2010-01-08 AMZN 0.027076954
## 5 2010-01-11 AMZN -0.024041386
## 6 2010-01-12 AMZN -0.022715064
#
p<-ggplot(firm3_ret.df, aes(x = Index, y = Value))+
geom_line(aes(color = Series), size = 0.5)
p
p + scale_x_date(date_labels = "%Y/%m")
# histogram distribution
q<-firm3_ret.df %>%
ggplot(aes(x =Value, fill = Series)) +
geom_histogram(alpha = 0.45, binwidth = .005) +
ggtitle("Daily Returns")
q
q + facet_wrap(~Series)+ theme_update(plot.title = element_text(hjust = 0.5))
# line distribution
firm3_ret.df %>%
ggplot(aes(x = Value, colour = Series)) +
geom_density(alpha = 1) +
ggtitle("Daily Returns Density from 2010") +
xlab("daily returns") +
ylab("distribution") +
theme_update(plot.title = element_text(hjust = 0.5))
# Combine line and histogram together
firm3_ret.df %>%
ggplot(aes(x = Value)) +
geom_density(aes(color = Series), alpha = 1) +
geom_histogram(aes(fill = Series), alpha = 0.45, binwidth = .01) +
guides(fill = FALSE) +
facet_wrap(~Series) +
ggtitle("Daily Returns from 2010") +
xlab("daily returns") +
ylab("distribution") +
theme_update(plot.title = element_text(hjust = 0.5))
