Apply 10
# 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)## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo
## ── Attaching core tidyquant packages ──────────────────────── tidyquant 1.0.9 ──
## ✔ PerformanceAnalytics 2.0.4 ✔ TTR 0.24.4
## ✔ quantmod 0.4.26 ✔ xts 0.14.0── 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)##
## Attaching package: 'timetk'
##
## The following object is masked from 'package:tidyquant':
##
## FANGGoal: 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 = claims)claims_tbl %>% count(symbol)## # A tibble: 6 × 2
## symbol n
## <fct> <int>
## 1 Connecticut 1893
## 2 Massachusetts 1893
## 3 Maine 1893
## 4 New Hampshire 1893
## 5 Rhode Island 1893
## 6 Vermont 1893claims_tbl %>%
group_by(symbol) %>%
plot_time_series(.date_var = date,
.value = claims,
.facet_ncol = 2,
.facet_scales = "free",
.interactive = FALSE)
Static ggplot2 Visulization and Customization
claims_tbl %>%
plot_time_series(date, claims,
.color_var = month(date, label = TRUE),
.interactive = FALSE,
#customize
.title = "Unemployment Claims Data",
.x_lab = "Year",
.y_lab = "unemployment Claims Filed",
.color_lab = "Month")
Box plots
claims_tbl %>% count(symbol)## # A tibble: 6 × 2
## symbol n
## <fct> <int>
## 1 Connecticut 1893
## 2 Massachusetts 1893
## 3 Maine 1893
## 4 New Hampshire 1893
## 5 Rhode Island 1893
## 6 Vermont 1893claims_tbl %>%
filter_by_time(.date_var = date, .end_date = "2009") %>%
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,
.formula = log(claims) ~ as.numeric(date) + month(date, label = TRUE),
.facet_ncol = 2,
.interactive = FALSE,
.show_summary = FALSE)
Plotting Seasonality and Correlation
Correlation Plots
claims_tbl %>%
group_by(symbol) %>%
plot_acf_diagnostics(date, claims, .lags = "1 month")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 1893
## 2 Massachusetts 1893
## 3 Maine 1893
## 4 New Hampshire 1893
## 5 Rhode Island 1893
## 6 Vermont 1893claims_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
claims_tbl %>%
group_by(symbol) %>%
summarize_by_time(.date_var = date, volume = sum(claims), .by = "year") %>%
plot_time_series(date, volume, .facet_ncol = 2, .interactive = FALSE)
claims_tbl %>%
group_by(symbol) %>%
summarise_by_time(.date_var = date, adjusted = mean(claims), .by = "year") %>%
plot_time_series(date, adjusted, .facet_ncol = 2, .interactive = FALSE)
Filter By Time
claims_tbl %>%
group_by(symbol) %>%
filter_by_time(.date_var = date,
.start_date = "1989",
.end_date = "2009") %>%
plot_time_series(date, claims, .facet_ncol = 2)Padding Data
claims_tbl %>%
group_by(symbol) %>%
pad_by_time(date, .by = "day", .fill_na_direction = "down")## # A tibble: 79,470 × 3
## # Groups: symbol [6]
## symbol date claims
## <fct> <date> <int>
## 1 Connecticut 1989-01-07 8345
## 2 Connecticut 1989-01-08 8345
## 3 Connecticut 1989-01-09 8345
## 4 Connecticut 1989-01-10 8345
## 5 Connecticut 1989-01-11 8345
## 6 Connecticut 1989-01-12 8345
## 7 Connecticut 1989-01-13 8345
## 8 Connecticut 1989-01-14 6503
## 9 Connecticut 1989-01-15 6503
## 10 Connecticut 1989-01-16 6503
## # ℹ 79,460 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.lm_roll <- slidify(~ lm(..1 ~ ..2), .period = 90,
.unlist = FALSE, .align = "right")
claims_tbl %>%
select(symbol, date, claims) %>%
group_by(symbol) %>%
mutate(numeric_date = as.numeric(date)) %>%
mutate(rolling_lm = lm_roll(claims, numeric_date)) %>%
filter(!is.na(rolling_lm))## # 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