—title: “HW #1” author: “Zachary Gooch” date: “09/07/22” output: html_document —
Load packages and data
library(fpp3)
library(dplyr)
library(ggplot2)
library(tidyr)
library(tsibble)
library(ggfortify)
library(tidyverse)
library(moments)
library(USgas)
library(readxl)
# install and load any package necessaryQuestions
Exercise 1
tute1 <- readxl::read_excel("C:\\Users\\Zacha\\Downloads\\tute1.xlsx")
tute2 <- tute1 %>%
mutate(Quarter=yearquarter(Quarter)) %>% as_tsibble(index=Quarter)
head(tute2)## # A tsibble: 6 x 4 [1Q]
## Quarter Sales AdBudget GDP
## <qtr> <dbl> <dbl> <dbl>
## 1 1981 Q1 1020. 659. 252.
## 2 1981 Q2 889. 589 291.
## 3 1981 Q3 795 512. 291.
## 4 1981 Q4 1004. 614. 292.
## 5 1982 Q1 1058. 647. 279.
## 6 1982 Q2 944. 602 254SalesP <- ggplot(tute2, aes(x=Quarter, y=Sales)) + geom_line()
AdBudgetP <- ggplot(tute2, aes(x=Quarter, y= AdBudget)) + geom_line()
GDPP <- ggplot(tute2, aes(x=quarter, y = GDP)) + geom_line()
BigPlot = tute2 %>%
pivot_longer(cols=c("Sales","AdBudget","GDP"),
names_to = "Measures",
values_to = "Money")
ggplot(data = BigPlot)+ geom_point(mapping=aes(x=Quarter, y= Money )) + facet_grid(~Measures)
Exercise 2
USA <- us_total %>%
as_tsibble(
index= year,
key= state)
Northeast <- USA %>%
filter(state == "Maine"| state == "Vermont"| state=="New Hampshire"| state == "Massachusetts"| state == "Connecticut"| state == "Rhode Island")
ggplot(data = Northeast) + geom_line(mapping=aes(x=year, y=y, color = state))
Exercise 3
tourism1<- readxl::read_excel("C:\\Users\\Zacha\\Downloads\\tourism.xlsx")
Toursible <- tourism1 %>%
mutate(Quarter = yearquarter (Quarter)) %>%
as_tsibble(index=Quarter,
key= c(Region, State, Purpose))
Toursible %>% group_by(Region, Purpose) %>%
summarise(mean=mean(Trips))%>%ungroup()%>%filter(mean==max(mean))## # A tsibble: 1 x 4 [1Q]
## # Key: Region, Purpose [1]
## Region Purpose Quarter mean
## <chr> <chr> <qtr> <dbl>
## 1 Melbourne Visiting 2017 Q4 985.ttyl <- Toursible %>%
group_by(State)%>%
summarise(Trips =sum(Trips))%>%
ungroup()
ttyl## # A tsibble: 640 x 3 [1Q]
## # Key: State [8]
## State Quarter Trips
## <chr> <qtr> <dbl>
## 1 ACT 1998 Q1 551.
## 2 ACT 1998 Q2 416.
## 3 ACT 1998 Q3 436.
## 4 ACT 1998 Q4 450.
## 5 ACT 1999 Q1 379.
## 6 ACT 1999 Q2 558.
## 7 ACT 1999 Q3 449.
## 8 ACT 1999 Q4 595.
## 9 ACT 2000 Q1 600.
## 10 ACT 2000 Q2 557.
## # ... with 630 more rows
## # i Use `print(n = ...)` to see more rowsExercise 4
head(aus_arrivals)## # A tsibble: 6 x 3 [1Q]
## # Key: Origin [1]
## Quarter Origin Arrivals
## <qtr> <chr> <int>
## 1 1981 Q1 Japan 14763
## 2 1981 Q2 Japan 9321
## 3 1981 Q3 Japan 10166
## 4 1981 Q4 Japan 19509
## 5 1982 Q1 Japan 17117
## 6 1982 Q2 Japan 10617autoplot(aus_arrivals) ## Plot variable not specified, automatically selected `.vars = Arrivals`
gg_season(aus_arrivals)## Plot variable not specified, automatically selected `y = Arrivals`
gg_subseries(aus_arrivals) ## Plot variable not specified, automatically selected `y = Arrivals`
#Japan after experiencing steady growth for some time began to plateau and decrease; no other country appears to decrease like Japan. New Zealand experienced a sharp increase around 2005. The US has a very steady consistant growth albeit minor. Exercise 5
set.seed(262)
myseries <- aus_retail %>%
filter(`Series ID` == sample(aus_retail$`Series ID`,1))
myseries## # A tsibble: 441 x 5 [1M]
## # Key: State, Industry [1]
## State Industry Serie~1 Month Turno~2
## <chr> <chr> <chr> <mth> <dbl>
## 1 Western Australia Cafes, restaurants and catering s~ A33499~ 1982 Apr 8
## 2 Western Australia Cafes, restaurants and catering s~ A33499~ 1982 May 8
## 3 Western Australia Cafes, restaurants and catering s~ A33499~ 1982 Jun 7.3
## 4 Western Australia Cafes, restaurants and catering s~ A33499~ 1982 Jul 7.8
## 5 Western Australia Cafes, restaurants and catering s~ A33499~ 1982 Aug 7.6
## 6 Western Australia Cafes, restaurants and catering s~ A33499~ 1982 Sep 8.2
## 7 Western Australia Cafes, restaurants and catering s~ A33499~ 1982 Oct 9.3
## 8 Western Australia Cafes, restaurants and catering s~ A33499~ 1982 Nov 9.6
## 9 Western Australia Cafes, restaurants and catering s~ A33499~ 1982 Dec 13.4
## 10 Western Australia Cafes, restaurants and catering s~ A33499~ 1983 Jan 8
## # ... with 431 more rows, and abbreviated variable names 1: `Series ID`,
## # 2: Turnover
## # i Use `print(n = ...)` to see more rowsautoplot(myseries) ## Plot variable not specified, automatically selected `.vars = Turnover`
gg_season(myseries)## Plot variable not specified, automatically selected `y = Turnover`
gg_subseries(myseries)## Plot variable not specified, automatically selected `y = Turnover`
gg_lag(myseries)## Plot variable not specified, automatically selected `y = Turnover`
myseries %>%
ACF(Turnover) %>% autoplot()
#There's definitely a positive trend in the data it's always increasing in the different graph types. The seasonality is very apparent in the autoplot function. It peaks upwards and then goes back down quickly consistently through the graph. The graphs appear to follow a general business cycle with a consistant series of rises and falls. Exercise 6
gafa_stock## # A tsibble: 5,032 x 8 [!]
## # Key: Symbol [4]
## Symbol Date Open High Low Close Adj_Close Volume
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 AAPL 2014-01-02 79.4 79.6 78.9 79.0 67.0 58671200
## 2 AAPL 2014-01-03 79.0 79.1 77.2 77.3 65.5 98116900
## 3 AAPL 2014-01-06 76.8 78.1 76.2 77.7 65.9 103152700
## 4 AAPL 2014-01-07 77.8 78.0 76.8 77.1 65.4 79302300
## 5 AAPL 2014-01-08 77.0 77.9 77.0 77.6 65.8 64632400
## 6 AAPL 2014-01-09 78.1 78.1 76.5 76.6 65.0 69787200
## 7 AAPL 2014-01-10 77.1 77.3 75.9 76.1 64.5 76244000
## 8 AAPL 2014-01-13 75.7 77.5 75.7 76.5 64.9 94623200
## 9 AAPL 2014-01-14 76.9 78.1 76.8 78.1 66.1 83140400
## 10 AAPL 2014-01-15 79.1 80.0 78.8 79.6 67.5 97909700
## # ... with 5,022 more rows
## # i Use `print(n = ...)` to see more rowsautoplot(gafa_stock)## Plot variable not specified, automatically selected `.vars = Open`
#calculate mean and standard deviation
fbstock <- gafa_stock %>%
filter(Symbol=="FB")%>%
select(Symbol,Close)
mean(fbstock$Close)## [1] 120.4625#120.4625
sd(fbstock$Close)## [1] 41.32364#41.32364
install.packages('moments')## Warning: package 'moments' is in use and will not be installedlibrary("moments")
fbvector<- pull(fbstock,Close)
firstdiff<- diff(fbvector)
head(firstdiff)## [1] -0.149998 2.640000 0.719997 0.310002 -1.009999 0.719998FBMean<- mean(firstdiff)
#0.06076372
FBMedian <- median(firstdiff)
#.1
FBsd <- sd(firstdiff)
#2.414555
FBskew <- skewness(firstdiff)
#-3.973192
FBkurt <- kurtosis(firstdiff)
#74.02921
#By Hand Stuff
FBMeanbh <- sum(fbvector, na.rm = TRUE) / length(fbvector)
FBsdbh <- sqrt(sum((fbvector-mean(fbvector))^2/(length(fbvector)-1)))
FBkurbh <- ((sum((fbvector-mean(fbvector))^4))/length(fbvector))/(sum((fbvector-mean(fbvector))^2)/length(fbvector))^2
FBskewbh <- (3*(FBMeanbh-FBMedian))/FBsdbhExercise #7
PELE <- readxl::read_excel("C:\\Users\\Zacha\\Downloads\\PTON.xlsx")
Pele <- PELE %>% select(-(Open:Close)) %>%
select(-(Volume))
Peloton <- PELE %>%
mutate(Date= as_date(Date)) %>%
as_tsibble(index="Date", key= "Adj Close")
Pelaline <- Peloton %>%
filter(Date >= as.Date("2022-06-01") & Date <= as.Date("2022-06-30"))%>%
ggplot(aes(x=Date, y= `Adj Close`)) + geom_line()
Pelaline
#Mean and Variance per month
PelaJan <- Peloton %>%
filter(Date >= as.Date("2022-01-01") & Date <= as.Date("2022-01-31"))
PelaFeb <- Peloton %>%
filter(Date >= as.Date("2022-02-01") & Date <= as.Date("2022-02-28"))
PelaMarch <- Peloton %>%
filter(Date >= as.Date("2022-03-01") & Date <= as.Date("2022-03-31"))
PelaApril <- Peloton %>%
filter(Date >= as.Date("2022-04-01") & Date <= as.Date("2022-04-30"))
PelaMay <- Peloton %>%
filter(Date >= as.Date("2022-05-01") & Date <= as.Date("2022-05-31"))
PelaJune <- Peloton %>%
filter(Date >= as.Date("2022-06-01") & Date <= as.Date("2022-06-30"))
PelaJuly <- Peloton %>%
filter(Date >= as.Date("2022-07-01") & Date <= as.Date("2022-07-31"))
PelaAugust <- Peloton %>%
filter(Date >= as.Date("2022-08-01") & Date <= as.Date("2022-08-31"))
PelaSeptember <- Peloton %>%
filter(Date >= as.Date("2022-09-01") & Date <= as.Date("2022-09-02"))
JanVec <- pull(PelaJan, "Adj Close")
JanMean <- mean(JanVec)
FebVec <- pull(PelaFeb, "Adj Close")
FebMea <- mean(FebVec)
MarchVec <- pull(PelaMarch, "Adj Close")
MarchMean <- mean(MarchVec)
AprilVec <- pull(PelaApril, "Adj Close")
AprilMean <- mean(AprilVec)
MayVec <- pull(PelaMay, "Adj Close")
MayMean <- mean(MayVec)
JuneVec <- pull(PelaJune, "Adj Close")
JuneMean <- mean(JuneVec)
JulyVec <- pull(PelaJuly, "Adj Close")
JulyMean <- mean(JulyVec)
AugustVec <- pull(PelaAugust, "Adj Close")
AugustMean <- mean(AugustVec)
SeptemberVec <- pull(PelaSeptember, "Adj Close")
SeptemberMean <- mean(SeptemberVec)
JanVar <- var(JanVec)
FebVar <- var(FebVec)
MarchVar <- var(MarchVec)
AprilVar <- var(AprilVec)
MayVar <- var(MayVec)
JuneVar <- var(JuneVec)
JulyVar <- var(JulyVec)
AugustVar <- var(AugustVec)
SeptemberVar <-var(SeptemberVec)