library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──
## ✓ ggplot2 3.3.5 ✓ purrr 0.3.4
## ✓ tibble 3.1.6 ✓ dplyr 1.0.7
## ✓ tidyr 1.1.4 ✓ stringr 1.4.0
## ✓ readr 2.1.0 ✓ forcats 0.5.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
library(ggplot2)
library(rvest)
##
## Attaching package: 'rvest'
## The following object is masked from 'package:readr':
##
## guess_encoding
library(janitor)
##
## Attaching package: 'janitor'
## The following objects are masked from 'package:stats':
##
## chisq.test, fisher.test
library(tidyquant)
## Loading required package: lubridate
##
## Attaching package: 'lubridate'
## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, union
## Loading required package: PerformanceAnalytics
## Loading required package: xts
## Loading required package: zoo
##
## Attaching package: 'zoo'
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric
##
## Attaching package: 'xts'
## The following objects are masked from 'package:dplyr':
##
## first, last
##
## Attaching package: 'PerformanceAnalytics'
## The following object is masked from 'package:graphics':
##
## legend
## Loading required package: quantmod
## Loading required package: TTR
## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo
## ══ Need to Learn tidyquant? ════════════════════════════════════════════════════
## Business Science offers a 1-hour course - Learning Lab #9: Performance Analysis & Portfolio Optimization with tidyquant!
## </> Learn more at: https://university.business-science.io/p/learning-labs-pro </>
library(lubridate)
today <- Sys.Date()
date = today %m+% months(-3)
print(date)
## [1] "2021-10-08"
#get stock information
tickers_df <- tq_index("SP500")
## Getting holdings for SP500
tickers_df2 = tq_get(tickers_df, from = date) #"date" - variable about the last 3 month
## Warning: x = 'BRK.B', get = 'stock.prices': Error in getSymbols.yahoo(Symbols = "BRK.B", env = <environment>, verbose = FALSE, : Unable to import "BRK.B".
## argument "conn" is missing, with no default
## Removing BRK.B.
## Warning: x = 'BF.B', get = 'stock.prices': Error in getSymbols.yahoo(Symbols = "BF.B", env = <environment>, verbose = FALSE, : Unable to import "BF.B".
## argument "conn" is missing, with no default
## Removing BF.B.
tickers_df2 %>%
head()
## # A tibble: 6 × 15
## symbol company identifier sedol weight sector shares_held local_currency
## <chr> <chr> <chr> <chr> <dbl> <chr> <dbl> <chr>
## 1 AAPL Apple Inc. 03783310 2046251 0.0674 Inform… 175321170 USD
## 2 AAPL Apple Inc. 03783310 2046251 0.0674 Inform… 175321170 USD
## 3 AAPL Apple Inc. 03783310 2046251 0.0674 Inform… 175321170 USD
## 4 AAPL Apple Inc. 03783310 2046251 0.0674 Inform… 175321170 USD
## 5 AAPL Apple Inc. 03783310 2046251 0.0674 Inform… 175321170 USD
## 6 AAPL Apple Inc. 03783310 2046251 0.0674 Inform… 175321170 USD
## # … with 7 more variables: date <date>, open <dbl>, high <dbl>, low <dbl>,
## # close <dbl>, volume <dbl>, adjusted <dbl>
#get daily return become own table
daily_sector = tickers_df2 %>% group_by(company, sector, symbol) %>%
tq_transmute(select = adjusted,
mutate_fun = periodReturn,
period = "daily") %>%
ungroup()
#create average return table
#volatility ~~ standard deviation of returns
avg_return =daily_sector %>%
group_by(company, sector) %>%
summarise(avg_return = round(mean(daily.returns), 4),Volatility = sd(daily.returns)) %>%
arrange(desc(avg_return), desc(Volatility))
## `summarise()` has grouped output by 'company'. You can override using the `.groups` argument.
avg_return %>% head()
## # A tibble: 6 × 4
## # Groups: company [6]
## company sector avg_return Volatility
## <chr> <chr> <dbl> <dbl>
## 1 Ford Motor Company Consumer Discretionary 0.0081 0.0309
## 2 Teradyne Inc. Information Technology 0.0061 0.0246
## 3 Qualcomm Inc Information Technology 0.0059 0.0263
## 4 Dollar Tree Inc. Consumer Discretionary 0.0059 0.0255
## 5 Arista Networks Inc. Information Technology 0.0057 0.0328
## 6 HP Inc. Information Technology 0.0055 0.0221
#create average return table with symbol
avg_return3 =daily_sector %>%
group_by(symbol, company, sector) %>%
summarise(avg_return3 = round(mean(daily.returns), 4),Volatility = sd(daily.returns)) %>%
arrange(desc(avg_return3), desc(Volatility))
## `summarise()` has grouped output by 'symbol', 'company'. You can override using the `.groups` argument.
avg_return3 %>% head()
## # A tibble: 6 × 5
## # Groups: symbol, company [6]
## symbol company sector avg_return3 Volatility
## <chr> <chr> <chr> <dbl> <dbl>
## 1 F Ford Motor Company Consumer Discretionary 0.0081 0.0309
## 2 TER Teradyne Inc. Information Technology 0.0061 0.0246
## 3 QCOM Qualcomm Inc Information Technology 0.0059 0.0263
## 4 DLTR Dollar Tree Inc. Consumer Discretionary 0.0059 0.0255
## 5 ANET Arista Networks Inc. Information Technology 0.0057 0.0328
## 6 HPQ HP Inc. Information Technology 0.0055 0.0221
#question 1
avg_return %>% head(20) %>% ggplot(aes(reorder(company, -avg_return), avg_return, fill = avg_return))+
geom_col()+
coord_flip()+
labs(title = "Securities With Highest Average Returns In SP500 Over Past 3 Month", x = "Security", y = "Average Return")+
theme_classic()+
theme(legend.position="none")
#question 2
avg_return3 = avg_return3 %>%
mutate(Indicator = case_when(symbol %in% c('MRNA', 'ENPH','TSLA') ~ "3 Highest volatility companies",
TRUE ~ "The Rest of the SP500"))
plot = avg_return3 %>% ggplot(aes(avg_return3, Volatility, color = Indicator))+
geom_text(aes(label = symbol), size = 3)+
labs(title = "Average Return vs Volatility Over Last 3 Months In SP500", x = "Average Return", subtitle = "Data Source: Yahoo Finance")+
theme_minimal()
plot
