# for Core packages
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
# for financial analysis
library(tidyquant)
## 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
##
##
## ######################### Warning from 'xts' package ##########################
## # #
## # The dplyr lag() function breaks how base R's lag() function is supposed to #
## # work, which breaks lag(my_xts). Calls to lag(my_xts) that you type or #
## # source() into this session won't work correctly. #
## # #
## # Use stats::lag() to make sure you're not using dplyr::lag(), or you can add #
## # conflictRules('dplyr', exclude = 'lag') to your .Rprofile to stop #
## # dplyr from breaking base R's lag() function. #
## # #
## # Code in packages is not affected. It's protected by R's namespace mechanism #
## # Set `options(xts.warn_dplyr_breaks_lag = FALSE)` to suppress this warning. #
## # #
## ###############################################################################
##
## 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
# for times series
library(timetk)
Goal: Apply Matt Dancho’s tutorial to state unemployment initial claims of New England states.
The following is the replication of Matt Dancho’s tutorial on this page
start_date <- "1989-01-01"
symbols_txt <- c("CTICLAIMS", # Connecticut
"MEICLAIMS", # Maine
"MAICLAIMS", # Massachusetts
"NHICLAIMS", # New Hampshire
"RIICLAIMS", # Rhode Island
"VTICLAIMS") # Vermont
claims_tbl <- tq_get(symbols_txt, get = "economic.data", from = start_date) %>%
mutate(symbol = fct_recode(symbol,
"Connecticut" = "CTICLAIMS",
"Maine" = "MEICLAIMS",
"Massachusetts" = "MAICLAIMS",
"New Hampshire" = "NHICLAIMS",
"Rhode Island" = "RIICLAIMS",
"Vermont" = "VTICLAIMS")) %>%
rename(claims = price)
claims_tbl %>% glimpse()
## Rows: 11,244
## Columns: 3
## $ symbol <fct> Connecticut, Connecticut, Connecticut, Connecticut, Connecticut…
## $ date <date> 1989-01-07, 1989-01-14, 1989-01-21, 1989-01-28, 1989-02-04, 19…
## $ claims <int> 8345, 6503, 3821, 4663, 4162, 4337, 4079, 3556, 3826, 3515, 288…
# Plot the time series
claims_tbl %>%
group_by(symbol) %>%
plot_time_series(
.date_var = date,
.value = claims,
.facet_ncol = 2,
.smooth = TRUE,
.title = "Unemployment Initial Claims in New England States")
# Filter data by a specific time period
filtered_claims_tbl <- claims_tbl %>%
filter_by_time(.date_var = date, .start = "2010-01-01", .end = "2020-12-31")
# Check the filtered data
glimpse(filtered_claims_tbl)
## Rows: 3,444
## Columns: 3
## $ symbol <fct> Connecticut, Connecticut, Connecticut, Connecticut, Connecticut…
## $ date <date> 2010-01-02, 2010-01-09, 2010-01-16, 2010-01-23, 2010-01-30, 20…
## $ claims <int> 9247, 13760, 10518, 6970, 5688, 5707, 4762, 6780, 7614, 5532, 4…
# Create box plots
filtered_claims_tbl %>%
group_by(symbol) %>%
plot_time_series_boxplot(
.date_var = date,
.value = claims,
.period = "1 month", # Aggregate data by month for box plots
.facet_ncol = 2,
.title = "Monthly Distribution of Unemployment Claims (2010-2020)")
# Create a regression plot
claims_tbl %>%
group_by(symbol) %>%
plot_time_series_regression(
.date_var = date,
.formula = claims ~ as.numeric(date),
.facet_ncol = 2, # Arrange plots in 2 columns
.title = "Linear Regression of Unemployment Claims Over Time" )
claims_tbl %>%
group_by(symbol) %>%
plot_acf_diagnostics(
.date_var = date,
.value = claims,
.lags = 24,
.facet_ncol = 2,
.title = "Autocorrelation Diagnostics for Unemployment Claims")
# Plot seasonality diagnostics
claims_tbl %>%
group_by(symbol) %>%
plot_seasonal_diagnostics(
.date_var = date,
.value = claims,
.title = "Seasonality Diagnostics for Unemployment Claims")
filtered_claims_tbl <- claims_tbl %>%
filter(symbol %in% c("Connecticut", "Maine"))
filtered_claims_tbl %>%
group_by(symbol) %>%
plot_stl_diagnostics(
.date_var = date,
.value = claims,
.feature_set = c("observed", "trend", "season", "remainder"), # Select specific components
.title = "STL Diagnostics for Selected States (Specific Features)",
.interactive = FALSE ) +
theme(
axis.text = element_text(size = 7),
axis.ticks = element_line(size = 0.5),
panel.grid = element_line(color = "grey80")
)
## frequency = 13 observations per 1 quarter
## trend = 53 observations per 1 year
## frequency = 13 observations per 1 quarter
## trend = 53 observations per 1 year
## Warning: The `size` argument of `element_line()` is deprecated as of ggplot2 3.4.0.
## ℹ Please use the `linewidth` argument instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
# Summarize unemployment claims by year
yearly_claims_tbl <- claims_tbl %>%
group_by(symbol) %>%
summarise_by_time(
.date_var = date,
.by = "year",
claims = mean(claims, na.rm = TRUE)
)
# Plot the yearly summarized data with facets
yearly_claims_tbl %>%
group_by(symbol) %>%
plot_time_series(
.date_var = date,
.value = claims,
.facet_ncol = 2,
.smooth = TRUE,
.title = "Yearly Average Unemployment Claims by State",
.interactive = FALSE
)
filtered_claims_tbl <- claims_tbl %>%
filter_by_time(
.date_var = date,
.start = "2010-01-01",
.end = "2020-12-31"
)
# Plot the filtered data
filtered_claims_tbl %>%
group_by(symbol) %>%
plot_time_series(
.date_var = date,
.value = claims,
.facet_ncol = 2,
.smooth = TRUE,
.title = "Filtered Unemployment Claims (2010-2020)",
.interactive = FALSE
)
monthly_claims_tbl <- claims_tbl %>%
group_by(symbol) %>%
summarise_by_time(
.date_var = date,
.by = "month",
claims = mean(claims, na.rm = TRUE)
)
padded_monthly_claims_tbl <- monthly_claims_tbl %>%
group_by(symbol) %>%
pad_by_time(
.date_var = date,
.by = "month"
)
# Check the padded data
glimpse(padded_monthly_claims_tbl)
## Rows: 2,586
## Columns: 3
## Groups: symbol [6]
## $ symbol <fct> Connecticut, Connecticut, Connecticut, Connecticut, Connecticut…
## $ date <date> 1989-01-01, 1989-02-01, 1989-03-01, 1989-04-01, 1989-05-01, 19…
## $ claims <dbl> 5833.00, 4033.50, 3277.25, 3506.60, 2938.50, 3755.50, 5478.20, …
# Plot the padded data
padded_monthly_claims_tbl %>%
group_by(symbol) %>%
plot_time_series(
.date_var = date,
.value = claims,
.facet_ncol = 2,
.smooth = TRUE,
.title = "Padded Unemployment Claims Data (Monthly Aggregated)",
.interactive = FALSE
)
lm_roll <- slidify(
~ lm(..1 ~ ..2 + ..3),
.period = 90,
.unlist = FALSE,
.align = "right"
)
rolling_claims_tbl <- claims_tbl %>%
group_by(symbol) %>%
mutate(numeric_date = as.numeric(date)) %>%
mutate(
rolling_lm = lm_roll(claims, numeric_date, numeric_date)
) %>%
filter(!is.na(rolling_lm))
glimpse(rolling_claims_tbl)
## Rows: 10,710
## Columns: 5
## Groups: symbol [6]
## $ symbol <fct> Connecticut, Connecticut, Connecticut, Connecticut, Conne…
## $ date <date> 1990-09-22, 1990-09-29, 1990-10-06, 1990-10-13, 1990-10-…
## $ claims <int> 3927, 4471, 4430, 4494, 4894, 4653, 4719, 5347, 4824, 536…
## $ numeric_date <dbl> 7569, 7576, 7583, 7590, 7597, 7604, 7611, 7618, 7625, 763…
## $ rolling_lm <list> [-11224.937411, 2.192839, NA, 4338.48034, 2481.13047, -2…