Apply Data 10
John Tomlinson
2024-04-18
# for Core packages
library(tidyverse)## Warning: package 'ggplot2' was built under R version 4.3.3## ── 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 3.5.0 ✔ 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)## Warning: package 'tidyquant' was built under R version 4.3.3## Loading required package: PerformanceAnalytics## Warning: package 'PerformanceAnalytics' was built under R version 4.3.3## 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## Warning: package 'quantmod' was built under R version 4.3.3## Loading required package: TTR## Warning: package 'TTR' was built under R version 4.3.3## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo# for times series
library(timetk)## Warning: package 'timetk' was built under R version 4.3.3Goal: 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)Plotting time series
claims_tbl## # A tibble: 11,058 × 3
## symbol date claims
## <fct> <date> <int>
## 1 Connecticut 1989-01-07 8345
## 2 Connecticut 1989-01-14 6503
## 3 Connecticut 1989-01-21 3821
## 4 Connecticut 1989-01-28 4663
## 5 Connecticut 1989-02-04 4162
## 6 Connecticut 1989-02-11 4337
## 7 Connecticut 1989-02-18 4079
## 8 Connecticut 1989-02-25 3556
## 9 Connecticut 1989-03-04 3826
## 10 Connecticut 1989-03-11 3515
## # ℹ 11,048 more rowsclaims_tbl %>%
plot_time_series(.date_var = date, .value = claims)Box plots
claims_tbl %>% count(symbol)## # A tibble: 6 × 2
## symbol n
## <fct> <int>
## 1 Connecticut 1843
## 2 Massachusetts 1843
## 3 Maine 1843
## 4 New Hampshire 1843
## 5 Rhode Island 1843
## 6 Vermont 1843claims_tbl %>%
filter_by_time(.date_var = date, .end_date = "2024") %>%
group_by(symbol) %>%
plot_time_series_boxplot(
.date_var = date,
.value = claims,
.period = "1 year",
.facet_ncol = 2)Regression plots
claims_tbl %>%
group_by(symbol) %>%
plot_time_series_regression(
.date_var = date,
.facet_ncol = 2,
.formula = log(claims) ~ as.numeric(date) + month(date, label = TRUE),
.show_summary = FALSE)Plotting Seasonality and Correlation
Correlation Plots
claims_tbl %>%
group_by(symbol) %>%
plot_acf_diagnostics(date, claims, .lags = "7 days")Seasonality
claims_tbl %>%
plot_seasonal_diagnostics(date, claims)claims_tbl %>% count(claims)## # A tibble: 5,332 × 2
## claims n
## <int> <int>
## 1 152 1
## 2 154 1
## 3 184 2
## 4 189 1
## 5 200 1
## 6 201 1
## 7 203 1
## 8 205 1
## 9 206 1
## 10 211 2
## # ℹ 5,322 more rowsclaims_tbl %>%
group_by(symbol) %>%
plot_seasonal_diagnostics(date, claims)STL Diagnostics
claims_tbl %>%
group_by(symbol) %>%
plot_stl_diagnostics(
date, claims,
.feature_set = c("observed", "season", "trend", "remainder"))## frequency = 13 observations per 1 quarter## trend = 53 observations per 1 year## frequency = 13 observations per 1 quarter## trend = 53 observations per 1 year## frequency = 13 observations per 1 quarter## trend = 53 observations per 1 year## frequency = 13 observations per 1 quarter## trend = 53 observations per 1 year## frequency = 13 observations per 1 quarter## trend = 53 observations per 1 year## frequency = 13 observations per 1 quarter## trend = 53 observations per 1 yearTime Series Data Wrangling
Summarize by Time
daily data
claims_tbl %>%
group_by(symbol) %>%
plot_time_series(date, claims, .facet_ncol = 2, .interactive = FALSE)
summarize it by quarter
claims_tbl %>%
group_by(symbol) %>%
summarise_by_time(.date_var = date, .by = "month", claims = mean(claims)) %>%
plot_time_series(date, claims, .facet_ncol = 2, .interactive = FALSE)
Filter By Time
claims_tbl %>%
group_by(symbol) %>%
filter_by_time(.date_var = date,
.start_date = "2013-09",
.end_date = "2013") %>%
plot_time_series(date, claims, .facet_ncol = 2)Padding Data
claims_tbl %>%
group_by(symbol) %>%
pad_by_time(date, .by = "day", .pad_value = 0)## # A tibble: 77,370 × 3
## # Groups: symbol [6]
## symbol date claims
## <fct> <date> <int>
## 1 Connecticut 1989-01-07 8345
## 2 Connecticut 1989-01-08 0
## 3 Connecticut 1989-01-09 0
## 4 Connecticut 1989-01-10 0
## 5 Connecticut 1989-01-11 0
## 6 Connecticut 1989-01-12 0
## 7 Connecticut 1989-01-13 0
## 8 Connecticut 1989-01-14 6503
## 9 Connecticut 1989-01-15 0
## 10 Connecticut 1989-01-16 0
## # ℹ 77,360 more rowsSliding (Rolling) Calculations
claims_tbl %>%
head(10) %>%
mutate(rolling_avg_2 = slidify_vec(claims, mean,
.period = 2,
.align = "right",
.partial = TRUE))## # A tibble: 10 × 4
## symbol date claims rolling_avg_2
## <fct> <date> <int> <dbl>
## 1 Connecticut 1989-01-07 8345 8345
## 2 Connecticut 1989-01-14 6503 7424
## 3 Connecticut 1989-01-21 3821 5162
## 4 Connecticut 1989-01-28 4663 4242
## 5 Connecticut 1989-02-04 4162 4412.
## 6 Connecticut 1989-02-11 4337 4250.
## 7 Connecticut 1989-02-18 4079 4208
## 8 Connecticut 1989-02-25 3556 3818.
## 9 Connecticut 1989-03-04 3826 3691
## 10 Connecticut 1989-03-11 3515 3670.# Rolling regressions are easy to implement using ' .unlist = FALSE'
lm_roll <- slidify(~ lm(..1 ~ ..2), .period = 90,
.unlist = FALSE, .align = "right")
claims_tbl %>%
select(symbol, date, claims) %>%
group_by(symbol) %>%
mutate(date = as.numeric(date)) %>%
# Apply rolling regression
mutate(rolling_lm = lm_roll(claims, date)) %>%
filter(!is.na(rolling_lm))## # A tibble: 10,524 × 4
## # Groups: symbol [6]
## symbol date claims rolling_lm
## <fct> <dbl> <int> <list>
## 1 Connecticut 7569 3927 <lm>
## 2 Connecticut 7576 4471 <lm>
## 3 Connecticut 7583 4430 <lm>
## 4 Connecticut 7590 4494 <lm>
## 5 Connecticut 7597 4894 <lm>
## 6 Connecticut 7604 4653 <lm>
## 7 Connecticut 7611 4719 <lm>
## 8 Connecticut 7618 5347 <lm>
## 9 Connecticut 7625 4824 <lm>
## 10 Connecticut 7632 5367 <lm>
## # ℹ 10,514 more rows