my-final-project

Quarto

Quarto enables you to weave together content and executable code into a finished document. To learn more about Quarto see https://quarto.org.

Running Code

When you click the Render button a document will be generated that includes both content and the output of embedded code. You can embed code like this:

#FINAL PROJECT

# Gather the following economics activity series for the state of Connecticut:

# Real Trade Weighted Value of the dollar for Connecticut

# Total Nonfarm Employees in Connecticut (CTNA)

# Average Hourly Earnings, All Employees, Total Private, Connecticut

# (SMU09000000500000003)

# Average Weekly Hours of All Employees, Total Private Connecticut

#(SMU09000000500000002)

# Assemble them into an equally weighted “Performance Index” for Connecticut;

# BEFORE you create the index make sure you standardize (or normalize) the series.

# Conduct a 12 month forecast using triple exponential smoothing.

# Provide succinct commentary on the economic environment expected for CT.

# Assemble your work in a Quarto document.

# Submit the Quarto document html to the bucket labeled “Final Project”

# by April 30 COB.

#========================== #

# QED ============

setwd("~/Business Forcasting")

options(digits = 3, scipen = 99999, stringsAsFactors = FALSE)

remove(list = ls())
graphics.off()

#load libraries

suppressWarnings({

  suppressPackageStartupMessages({

    library(tidyverse)

    library(pdfetch)

    library(lubridate)  

    library(ggplot2)

    library(forecast)

    

    library(tsbox)

    library(tsibble)

    #library(timetk)

    library(TSstudio)

    

    library(rio)

    library(pdfetch)

    

    library(tidyr)

    library(stringr)

    library(dygraphs)

    library(quantmod)

    

    library(broom)

  })

})

#You can add options to executable code like this

Rtrade <- getSymbols("RTWVDCT684NMFRBDAL",src="FRED",auto.assign=FALSE)
ts_info(Rtrade)

 The Rtrade series is a xts object with 1 variable and 426 observations
 Frequency: monthly 
 Start time: 1988-01-01 
 End time: 2023-06-01

Nfemp <- getSymbols("CTNA",src="FRED",auto.assign=FALSE)
ts_info(Nfemp)

 The Nfemp series is a xts object with 1 variable and 411 observations
 Frequency: monthly 
 Start time: 1990-01-01 
 End time: 2024-03-01

Earn <- getSymbols("SMU09000000500000003",src="FRED",auto.assign=FALSE)
ts_info(Earn)

 The Earn series is a xts object with 1 variable and 207 observations
 Frequency: monthly 
 Start time: 2007-01-01 
 End time: 2024-03-01

Time <- getSymbols("SMU09000000500000002",src="FRED",auto.assign=FALSE)
ts_info(Time)

 The Time series is a xts object with 1 variable and 207 observations
 Frequency: monthly 
 Start time: 2007-01-01 
 End time: 2024-03-01

# Assemble them into an equally weighted “Performance Index” for Connecticut;

Rtrade.ts = ts(Rtrade, start = c(1988,1), frequency = 12)
      Rtrade.ts = window(Rtrade.ts, start = c(2007,1), end =c(2023,6), frequency = 12)
      
      
Nfemp.ts = ts(Nfemp, start = c(1990,1), frequency = 12)
      Nfemp.ts = window(Nfemp.ts, start = c(2007,1), end =c(2023,6), frequency = 12)
 
           
Earn.ts = ts(Earn, start = c(2007,1), frequency = 12)
    Earn.ts = window(Earn.ts, start = c(2007,1), end =c(2023,6), frequency = 12)
Time.ts = ts(Time, start = c(2007,1), frequency = 12)
     Time.ts = window(Time.ts, start = c(2007,1), end =c(2023,6), frequency = 12)

ts_info(Rtrade.ts)

 The Rtrade.ts series is a ts object with 1 variable and 198 observations
 Frequency: 12 
 Start time: 2007 1 
 End time: 2023 6

ts_info(Nfemp.ts)

 The Nfemp.ts series is a ts object with 1 variable and 198 observations
 Frequency: 12 
 Start time: 2007 1 
 End time: 2023 6

ts_info(Earn.ts)

 The Earn.ts series is a ts object with 1 variable and 198 observations
 Frequency: 12 
 Start time: 2007 1 
 End time: 2023 6

ts_info(Time.ts)

 The Time.ts series is a ts object with 1 variable and 198 observations
 Frequency: 12 
 Start time: 2007 1 
 End time: 2023 6

cbind(Rtrade.ts, Nfemp.ts,Earn.ts, Time.ts) |> tidy() |>
  group_by(series) |>
  dplyr::mutate(normindex = value*100/first(value),
                standvalues = value/max(value)) |>
  ggplot(aes(x = index, y = normindex, col =series)) + geom_line()

#standardize the variable

cbind(Rtrade.ts, Nfemp.ts,Earn.ts, Time.ts) |> tidy() |>
  group_by(series) |>
  dplyr::mutate(normindex = value*100/first(value),
                standvalues = value/max(value)) |>
 ggplot(aes(x = index, y = standvalues, col =series)) + geom_line()

#standardize the variable

mydat = cbind.data.frame(Rtrade.ts/max(Rtrade.ts),
                         Nfemp.ts/max(Nfemp.ts),
                         Earn.ts/max(Earn.ts),
                         Time.ts/max(Time.ts)
                         )
mydat = mydat |> dplyr::mutate(CTIndex = rowSums(mydat))
head(mydat,3)

  RTWVDCT684NMFRBDAL  CTNA SMU09000000500000003 SMU09000000500000002 CTIndex
1              0.780 0.987                0.718                0.980    3.47
2              0.778 0.986                0.729                0.968    3.46
3              0.777 0.986                0.722                0.977    3.46

mydat.ts = ts(mydat$CTIndex, start = c(2007,1), frequency = 12)

mydat.ts |> tidy() |> 
  ggplot(aes(x = index, y = value)) + geom_line()

#Forecast

mymodel = HoltWinters(mydat.ts)
myfc = forecast(mymodel, h = 12)
autoplot(myfc)

autoplot(mydat.ts) + autolayer(myfc$mean) + 
  xlim(2022, 2026) + ylim(3.7,4.0)

Scale for x is already present.
Adding another scale for x, which will replace the existing scale.