Apply 11
# for Core packages
library(tidyverse)## Warning: package 'purrr' was built under R version 4.3.3## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.1
## ✔ purrr 1.0.4
## ── 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)Plotting time series
claims_tbl## # A tibble: 11,358 × 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 11,348 more rowsclaims_tbl %>%
plot_time_series(.date_var = date, .value = log(claims))claims_tbl %>%
group_by(symbol) %>%
plot_time_series(
.date_var = date,
.value = log(claims),
.facet_ncol = 2,
.facet_scales = "free",
.interactive = FALSE)
claims_tbl %>%
plot_time_series(date, log(claims),
.color_var = month(date, label = TRUE),
# Returns static ggplot
.interactive = FALSE,
# Customize
.title = "Jobless Claims",
.x_lab = "Date (10-year intervals)",
.y_lab = "Number log-adjusted",
.color_lab = "month") 
Box plots
claims_tbl## # A tibble: 11,358 × 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 11,348 more rowsclaims_tbl %>%
filter_by_time(.date_var = date, .end_date = "2024") %>%
group_by(symbol) %>%
plot_time_series_boxplot(
.date_var = date,
.value = log(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 plots
claims_tbl %>%
group_by(symbol) %>%
plot_acf_diagnostics(
date, log(claims), .lags = "5 years")Seasonality
claims_tbl %>%
plot_seasonal_diagnostics(date, log(claims))claims_tbl %>%
group_by(symbol) %>%
plot_seasonal_diagnostics(date, log(claims))STL Diagnostics
claims_tbl %>%
group_by(symbol) %>%
plot_stl_diagnostics(
date, log(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
claims_tbl %>%
group_by(symbol) %>%
plot_time_series(date, log(claims), .facet_ncol = 2, .interactive = FALSE)
Filter By Time
claims_tbl %>%
group_by(symbol) %>%
filter_by_time(.date_var = date,
.start_date = "2023-01",
.end_date = "2023") %>%
plot_time_series(date, log(claims), .facet_ncol = 2)Padding Data
claims_tbl %>%
group_by(symbol) %>%
pad_by_time(date, .by = "week", .pad_value = 0)## # A tibble: 11,358 × 3
## # Groups: symbol [6]
## 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 11,348 more rowsSliding (Rolling) Calculations
lm_roll <- slidify(~ lm(..1 ~ ..2 + ..3), .period = 90,
.unlist = FALSE, .align = "right")
claims_tbl %>%
select(symbol, date, claims) %>%
group_by(symbol) %>%
mutate(numeric_date = as.numeric(date)) %>%
# Apply rolling regression
mutate(rolling_lm = lm_roll(symbol, claims, numeric_date)) %>%
filter(!is.na(rolling_lm))## Warning: There were 22716 warnings in `mutate()`.
## The first warning was:
## ℹ In argument: `rolling_lm = lm_roll(symbol, claims, numeric_date)`.
## ℹ In group 1: `symbol = Connecticut`.
## Caused by warning in `model.response()`:
## ! using type = "numeric" with a factor response will be ignored
## ℹ Run `dplyr::last_dplyr_warnings()` to see the 22715 remaining warnings.## # A tibble: 10,824 × 5
## # Groups: symbol [6]
## symbol date claims numeric_date rolling_lm
## <fct> <date> <int> <dbl> <list>
## 1 Connecticut 1990-09-22 3927 7569 <lm>
## 2 Connecticut 1990-09-29 4471 7576 <lm>
## 3 Connecticut 1990-10-06 4430 7583 <lm>
## 4 Connecticut 1990-10-13 4494 7590 <lm>
## 5 Connecticut 1990-10-20 4894 7597 <lm>
## 6 Connecticut 1990-10-27 4653 7604 <lm>
## 7 Connecticut 1990-11-03 4719 7611 <lm>
## 8 Connecticut 1990-11-10 5347 7618 <lm>
## 9 Connecticut 1990-11-17 4824 7625 <lm>
## 10 Connecticut 1990-11-24 5367 7632 <lm>
## # ℹ 10,814 more rows