# 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     1.0.4     
## ── 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)
## Warning: package 'tidyquant' was built under R version 4.4.3
## Registered S3 method overwritten by 'quantmod':
##   method            from
##   as.zoo.data.frame zoo
## Warning: package 'xts' was built under R version 4.4.3
## Warning: package 'zoo' was built under R version 4.4.3
## Warning: package 'quantmod' was built under R version 4.4.3
## Warning: package 'PerformanceAnalytics' was built under R version 4.4.3
## ── Attaching core tidyquant packages ─────────────────────── tidyquant 1.0.11 ──
## ✔ PerformanceAnalytics 2.0.8      ✔ TTR                  0.24.4
## ✔ quantmod             0.4.27     ✔ xts                  0.14.1
## ── Conflicts ────────────────────────────────────────── tidyquant_conflicts() ──
## ✖ zoo::as.Date()                 masks base::as.Date()
## ✖ zoo::as.Date.numeric()         masks base::as.Date.numeric()
## ✖ dplyr::filter()                masks stats::filter()
## ✖ xts::first()                   masks dplyr::first()
## ✖ dplyr::lag()                   masks stats::lag()
## ✖ xts::last()                    masks dplyr::last()
## ✖ PerformanceAnalytics::legend() masks graphics::legend()
## ✖ quantmod::summary()            masks base::summary()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
# for times series
library(timetk)
## Warning: package 'timetk' was built under R version 4.4.3
## 
## Attaching package: 'timetk'
## 
## The following object is masked from 'package:tidyquant':
## 
##     FANG

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: 11,370 × 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 11,360 more rows
claims_tbl %>%
    plot_time_series(.date_var = date, .value = claims)
claims_tbl
## # A tibble: 11,370 × 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 11,360 more rows
claims_tbl %>%
    group_by(symbol) %>%
    plot_time_series(
        .date_var = date,
        .value = claims,
        .facet_ncol = 2,
        .facet_scales = "free",
        .interactive = FALSE)

Box plots

claims_tbl
## # A tibble: 11,370 × 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 11,360 more rows
claims_tbl %>%
    filter_by_time(.date_var = date, .end_date = "1991-08-17
") %>%
    group_by(symbol) %>%
    plot_time_series_boxplot(
        .date_var = date,
        .value = claims,
        .period      = "1 year",
        .facet_ncol  = 2)
## Warning: There were 30 warnings in `dplyr::mutate()`.
## The first warning was:
## ℹ In argument: `.value_smooth = auto_smooth(...)`.
## ℹ In group 1: `symbol = Connecticut`.
## Caused by warning in `simpleLoess()`:
## ! span too small.   fewer data values than degrees of freedom.
## ℹ Run `dplyr::last_dplyr_warnings()` to see the 29 remaining warnings.

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")
claims_tbl %>%
    group_by(symbol) %>%
    plot_acf_diagnostics(
        date, claims,
        .ccf_vars = c(date, claims),
        .lags = "3 months")

Seasonality

claims_tbl %>%
    plot_seasonal_diagnostics(date, claims)
claims_tbl %>% count(symbol)
## # A tibble: 6 × 2
##   symbol            n
##   <fct>         <int>
## 1 Connecticut    1895
## 2 Massachusetts  1895
## 3 Maine          1895
## 4 New Hampshire  1895
## 5 Rhode Island   1895
## 6 Vermont        1895
claims_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 year

Time Series Data Wrangling

Summarize by Time

claims_tbl %>%
    group_by(symbol) %>%
    summarise_by_time(.date_var = date, claims = sum(claims), .by = "quarter") %>%
    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 = "1989-01-07
",
                   .end_date = "1995-03-18
") %>%
    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: 79,554 × 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 79,544 more rows

Sliding (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.
# Make the rolling function
roll_avg_30 <- slidify(.f = mean, .period = 30, .align = "center", .partial = TRUE)

# Apply the rolling function and plot
claims_tbl %>%
  select(symbol, date, claims) %>%
  group_by(symbol) %>%
  # Apply Sliding Function
  mutate(rolling_avg_30 = roll_avg_30(claims)) %>%
  tidyr::pivot_longer(
    cols = c(claims, rolling_avg_30),
    names_to = "name",
    values_to = "value"
  ) %>%
  plot_time_series(
    .date_var = date,
    .value = value,           # <- This is now the correct value column
    .color_var = name,        # <- This maps "claims" vs "rolling_avg_30"
    .facet_ncol = 2,
    .smooth = FALSE, 
    .interactive = FALSE
  )