Code Along 10
Tindra Bergstrand
2024-11-11
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(ggplot2)
library(lubridate)##
## Attaching package: 'lubridate'## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, unionlibrary(timetk)
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 zoolibrary(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ purrr 1.0.2 ✔ tibble 3.2.1
## ✔ readr 2.1.5 ✔ tidyr 1.3.1## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ xts::first() masks dplyr::first()
## ✖ dplyr::lag() masks stats::lag()
## ✖ xts::last() masks dplyr::last()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorsPlotting time series
taylor_30_min## # A tibble: 4,032 × 2
## date value
## <dttm> <dbl>
## 1 2000-06-05 00:00:00 22262
## 2 2000-06-05 00:30:00 21756
## 3 2000-06-05 01:00:00 22247
## 4 2000-06-05 01:30:00 22759
## 5 2000-06-05 02:00:00 22549
## 6 2000-06-05 02:30:00 22313
## 7 2000-06-05 03:00:00 22128
## 8 2000-06-05 03:30:00 21860
## 9 2000-06-05 04:00:00 21751
## 10 2000-06-05 04:30:00 21336
## # ℹ 4,022 more rowstaylor_30_min %>%
plot_time_series(.date_var = date, .value = value)m4_daily %>% count(id)## # A tibble: 4 × 2
## id n
## <fct> <int>
## 1 D10 674
## 2 D160 4197
## 3 D410 676
## 4 D500 4196m4_daily %>%
group_by(id) %>%
plot_time_series(
.date_var = date,
.value = value,
.facet_ncol = 2,
.facet_scales = "free",
.interactive = FALSE)
Visualizing transformations and sub-groups
m4_hourly %>% count(id)## # A tibble: 4 × 2
## id n
## <fct> <int>
## 1 H10 700
## 2 H50 700
## 3 H150 700
## 4 H410 960m4_hourly %>%
group_by(id) %>%
plot_time_series(.date_var = date,
.value = log(value),
.facet_ncol = 2,
.facet_scales = "free",
.color_var = week(date))Static ggplot2 visualization & customization
taylor_30_min %>%
plot_time_series(date, value,
.color_var = month(date, label = TRUE),
# Return static ggplot
.interactive = FALSE,
# Customize
.title = "Taylor's MegaWatt Data",
.x_lab = "Date (30-min intervals)",
.y_lab = "Energy Demand (MW)",
.color_lab = "Month")
Box plots
m4_monthly %>% count(id)## # A tibble: 4 × 2
## id n
## <fct> <int>
## 1 M1 469
## 2 M2 469
## 3 M750 306
## 4 M1000 330m4_monthly %>%
filter_by_time(.date_var = date, .end_date = "1977") %>%
group_by(id) %>%
plot_time_series_boxplot(.date_var = date,
.value = value,
.period = "1 year",
.facet_ncol = 2)## Warning: There were 10 warnings in `dplyr::mutate()`.
## The first warning was:
## ℹ In argument: `.value_smooth = auto_smooth(...)`.
## ℹ In group 1: `id = M1`.
## Caused by warning in `simpleLoess()`:
## ! span too small. fewer data values than degrees of freedom.
## ℹ Run `dplyr::last_dplyr_warnings()` to see the 9 remaining warnings.Regression plots
m4_monthly %>%
group_by(id) %>%
plot_time_series_regression(
.date_var = date,
.facet_ncol = 2,
.formula = log(value) ~ as.numeric(date) + month(date, label = TRUE),
.show_summary = FALSE)Plotting Seasonality and Correlation
Correlation Plot
m4_hourly %>%
group_by(id) %>%
plot_acf_diagnostics(date, value,
.lags = "7 days") # 7 days of lagswalmart_sales_weekly %>%
group_by(id) %>%
plot_acf_diagnostics(Date, Weekly_Sales,
.ccf_vars = c(Temperature, Fuel_Price),
.lags = "3 months") # 3 months of weekly lagsSeasonality
taylor_30_min %>%
plot_seasonal_diagnostics(date, value)m4_hourly %>% count(id)## # A tibble: 4 × 2
## id n
## <fct> <int>
## 1 H10 700
## 2 H50 700
## 3 H150 700
## 4 H410 960m4_hourly %>%
group_by(id) %>%
plot_seasonal_diagnostics(date, value)STL Diagnostics
m4_hourly %>%
group_by(id) %>%
plot_stl_diagnostics(
date, value,
.feature_set = c("observed", "season", "trend", "remainder"))## frequency = 24 observations per 1 day## trend = 336 observations per 14 days## frequency = 24 observations per 1 day## trend = 336 observations per 14 days## frequency = 24 observations per 1 day## trend = 336 observations per 14 days## frequency = 24 observations per 1 day## trend = 336 observations per 14 daysTime series data wrangling
Summarize by time
Daily data
FANG %>%
group_by(symbol) %>%
plot_time_series(date, volume, .facet_ncol = 2, .interactive = FALSE)
Summarize it by quarter
FANG %>%
group_by(symbol) %>%
summarise_by_time(.date_var = date, volume = sum(volume), .by = "quarter") %>%
plot_time_series(date, volume, .facet_ncol = 2, .interactive = FALSE)
FANG %>%
group_by(symbol) %>%
summarise_by_time(.date_var = date, adjusted = mean(adjusted), .by = "month") %>%
plot_time_series(date, adjusted, .facet_ncol = 2, .interactive = FALSE)
Filter by time
FANG %>%
group_by(symbol) %>%
filter_by_time(.date_var = date,
.start_date = "2013-09",
.end_date = "2013") %>%
plot_time_series(date, adjusted, .facet_ncol = 2)Padding data
FANG %>%
group_by(symbol) %>%
pad_by_time(date, .by = "day", .pad_value = 0)## # A tibble: 5,836 × 8
## # Groups: symbol [4]
## symbol date open high low close volume adjusted
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 AMZN 2013-01-02 256. 258. 253. 257. 3271000 257.
## 2 AMZN 2013-01-03 257. 261. 256. 258. 2750900 258.
## 3 AMZN 2013-01-04 258. 260. 257. 259. 1874200 259.
## 4 AMZN 2013-01-05 0 0 0 0 0 0
## 5 AMZN 2013-01-06 0 0 0 0 0 0
## 6 AMZN 2013-01-07 263. 270. 263. 268. 4910000 268.
## 7 AMZN 2013-01-08 267. 269. 264. 266. 3010700 266.
## 8 AMZN 2013-01-09 268. 270. 265. 266. 2265600 266.
## 9 AMZN 2013-01-10 269. 269. 262. 265. 2863400 265.
## 10 AMZN 2013-01-11 265. 268. 264. 268. 2413300 268.
## # ℹ 5,826 more rowsSliding (rolling) calculations
FANG %>%
head(10) %>%
mutate(rolling_avg_2 = slidify_vec(adjusted, mean,
.period = 2,
.align = "right",
.partial = TRUE))## # A tibble: 10 × 9
## symbol date open high low close volume adjusted rolling_avg_2
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 FB 2013-01-02 27.4 28.2 27.4 28 69846400 28 28
## 2 FB 2013-01-03 27.9 28.5 27.6 27.8 63140600 27.8 27.9
## 3 FB 2013-01-04 28.0 28.9 27.8 28.8 72715400 28.8 28.3
## 4 FB 2013-01-07 28.7 29.8 28.6 29.4 83781800 29.4 29.1
## 5 FB 2013-01-08 29.5 29.6 28.9 29.1 45871300 29.1 29.2
## 6 FB 2013-01-09 29.7 30.6 29.5 30.6 104787700 30.6 29.8
## 7 FB 2013-01-10 30.6 31.5 30.3 31.3 95316400 31.3 30.9
## 8 FB 2013-01-11 31.3 32.0 31.1 31.7 89598000 31.7 31.5
## 9 FB 2013-01-14 32.1 32.2 30.6 31.0 98892800 31.0 31.3
## 10 FB 2013-01-15 30.6 31.7 29.9 30.1 173242600 30.1 30.5# Make the rolling function
roll_avg_30 <- slidify(.f = mean, .period = 30, .align = "center", .partial = TRUE)
# Apply the rolling function
FANG %>%
select(symbol, date, adjusted) %>%
group_by(symbol) %>%
# Apply Sliding Function
mutate(rolling_avg_30 = roll_avg_30(adjusted)) %>%
tidyr::pivot_longer(cols = c(adjusted, rolling_avg_30)) %>%
plot_time_series(date, value, .color_var = name,
.facet_ncol = 2, .smooth = FALSE,
.interactive = FALSE)
# Rolling regressions are easy to implement using `.unlist = FALSE`
lm_roll <- slidify(~ lm(..1 ~ ..2 + ..3), .period = 90,
.unlist = FALSE, .align = "right")
FANG %>%
select(symbol, date, adjusted, volume) %>%
group_by(symbol) %>%
mutate(numeric_date = as.numeric(date)) %>%
# Apply rolling regression
mutate(rolling_lm = lm_roll(adjusted, volume, numeric_date)) %>%
filter(!is.na(rolling_lm))## # A tibble: 3,676 × 6
## # Groups: symbol [4]
## symbol date adjusted volume numeric_date rolling_lm
## <chr> <date> <dbl> <dbl> <dbl> <list>
## 1 FB 2013-05-10 26.7 30847100 15835 <lm>
## 2 FB 2013-05-13 26.8 29068800 15838 <lm>
## 3 FB 2013-05-14 27.1 24930300 15839 <lm>
## 4 FB 2013-05-15 26.6 30299800 15840 <lm>
## 5 FB 2013-05-16 26.1 35499100 15841 <lm>
## 6 FB 2013-05-17 26.2 29462700 15842 <lm>
## 7 FB 2013-05-20 25.8 42402900 15845 <lm>
## 8 FB 2013-05-21 25.7 26261300 15846 <lm>
## 9 FB 2013-05-22 25.2 45314500 15847 <lm>
## 10 FB 2013-05-23 25.1 37663100 15848 <lm>
## # ℹ 3,666 more rows