Highest traffic in I-10 Phoenix: Near Loop 101. Traffic count in that area tracked by ATR Station 100086. Need to forecast daily traffic volume
rm(list = ls())
library(dygraphs)
library(fpp3)
## ── Attaching packages ────────────────────────────────────────────── fpp3 0.5 ──
## ✔ tibble 3.2.1 ✔ tsibble 1.1.3
## ✔ dplyr 1.1.2 ✔ tsibbledata 0.4.1
## ✔ tidyr 1.3.0 ✔ feasts 0.3.1
## ✔ lubridate 1.9.2 ✔ fable 0.3.3
## ✔ ggplot2 3.4.2 ✔ fabletools 0.3.3
## ── Conflicts ───────────────────────────────────────────────── fpp3_conflicts ──
## ✖ lubridate::date() masks base::date()
## ✖ dplyr::filter() masks stats::filter()
## ✖ tsibble::intersect() masks base::intersect()
## ✖ tsibble::interval() masks lubridate::interval()
## ✖ dplyr::lag() masks stats::lag()
## ✖ tsibble::setdiff() masks base::setdiff()
## ✖ tsibble::union() masks base::union()
# read the data
origin = read.csv("AZ_traffic.csv")
head(origin)
df <- origin |> filter(Station_Id == 100086)
head(df)
df[['datetime']] <- as.POSIXct(df[['datetime']],
format = "%Y-%m-%d %H:%M:%S")
head(df)
unique(df$Travel_Lane)
## [1] 1 2 3 4 5 6
unique(df$Travel_Dir)
## [1] 3 7
df <- df |> select(-c('Travel_Lane', 'Station_Id')) |>
mutate(date=as.Date(datetime))
head(df)
df <- df |> select(-datetime) |>
group_by(Travel_Dir, date) |>
summarise(daily_volume = sum(Hour_Volume)) |>
ungroup()
## `summarise()` has grouped output by 'Travel_Dir'. You can override using the
## `.groups` argument.
head(df)
df <- df |>
as_tsibble(index = date,
key = Travel_Dir)
library(tsbox)
tsbox::ts_xts(df) |>
dygraph() |>
dyRangeSelector(dateWindow = c("2018-01-01", "2019-12-30"))
## Found numeric [id] column(s): 'Travel_Dir'.
## Are you using a wide data frame? To convert, use 'ts_long()'.
## Convert column(s) to character or factor to silence this message.
## [time]: 'date' [value]: 'daily_volume'
We notice some unusually low traffic flow for some data points. After closer inspection, we observe that there are some missing dates in the time-series for which no traffic count is available. This is because ATR tracker was out of order in those days. In some cases, the tracker stopped functioning in the middle of the day. For those dates, we also observe very low traffic flow. That’s we will treat this partial records as missing values.
threshold = 61000
errors <- df |>
filter(daily_volume < threshold)
df <- df |> anti_join(errors)
## Joining with `by = join_by(Travel_Dir, date, daily_volume)`
df <- df |> fill_gaps()
library(tsbox)
tsbox::ts_xts(df) |>
dygraph() |>
dyRangeSelector(dateWindow = c("2018-01-01", "2019-12-30"))
## Found numeric [id] column(s): 'Travel_Dir'.
## Are you using a wide data frame? To convert, use 'ts_long()'.
## Convert column(s) to character or factor to silence this message.
## [time]: 'date' [value]: 'daily_volume'
missing_data <- df |> filter(is.na(daily_volume))
proxy <- origin |> filter(Station_Id == 100087)
proxy$date <- as.Date(proxy$datetime, format = "%Y-%m-%d")
proxy <- proxy |> select(-c('Travel_Lane', 'Station_Id'))
proxy <- proxy |> select(-datetime) |>
group_by(Travel_Dir, date) |>
summarise(daily_volume = sum(Hour_Volume)) |>
ungroup()
## `summarise()` has grouped output by 'Travel_Dir'. You can override using the
## `.groups` argument.
proxy <- proxy |> as_tsibble(index = date, key = Travel_Dir)
df <- df %>%
left_join(proxy, by = c("date", "Travel_Dir"), suffix = c("", "_tsb2")) %>%
mutate(daily_volume = coalesce(daily_volume, daily_volume_tsb2)) %>% # coalesce finds the first non-missing value
select(-daily_volume_tsb2)
head(df)
library(tsbox)
tsbox::ts_xts(df) |>
dygraph() |>
dyRangeSelector(dateWindow = c("2018-01-01", "2019-12-30"))
## Found numeric [id] column(s): 'Travel_Dir'.
## Are you using a wide data frame? To convert, use 'ts_long()'.
## Convert column(s) to character or factor to silence this message.
## [time]: 'date' [value]: 'daily_volume'
df |> has_gaps()
Data also missing in proxy
na_count <- sum(is.na(df$daily_volume))
print(na_count)
## [1] 6
df |> filter(is.na(daily_volume))
library(imputeTS)
## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo
# Impute missing values using linear interpolation
df <- df %>%
group_by(Travel_Dir) %>%
mutate(daily_volume = na_interpolation(daily_volume, option = "linear"))
na_count <- sum(is.na(df$daily_volume))
print(na_count)
## [1] 0
df |>
autoplot(daily_volume)
## `mutate_if()` ignored the following grouping variables:
## • Column `Travel_Dir`
df |>
gg_season(daily_volume, period = "year", pal = c("#3333FF", "#FF3333")) +
theme(legend.position = "left") +
labs(y="Daily traffic count", title="Traffic volume by year") +
facet_wrap(vars(Travel_Dir))
The annual pattern shows a uniform distribution of traffic flow
throughout the year expect in March and April (due to tourism season) as
well as in November and December (due to vacation period)
df |>
gg_season(daily_volume, period = "week") +
theme(legend.position = "none") +
labs(y="Daily traffic count", x="Day of the week", title="Traffic Volume per week")
We notice weakly seasonality. Traffic count on weekend is a
significantly lower than weekdays.
df |>
gg_season(daily_volume, period = "month") +
theme(legend.position = "none") +
labs(y="Daily traffic count", x="Week of the month", title="Traffic Volume per month")
No monthly seasonality can be observed
df |>
gg_subseries(daily_volume, period = 'week')
Same weakly pattern as seasonal plot. Less traffic on weekends. Using
multiple plots, we confirm the presence of weekly seasonality
df |> filter(Travel_Dir == '3') |>
ACF(daily_volume, lag_max = 33) |> autoplot()
The autocorrelation plot also suggests the presence of weekly
seasonality
dcmp <- df |> filter(Travel_Dir == '3') |>
model(STL(daily_volume ~ trend(window=120) + season("week", window='periodic'), robust=TRUE)) #trend(window = 90) + season('week', window=30)))
components(dcmp)|> autoplot()
components(dcmp) |>
as_tsibble() |>
autoplot(daily_volume, colour="gray") +
geom_line(aes(y=trend), colour = "#D55E00") +
labs(
y = "Traffic Volume"
)
From the decomposition plot, it is evident that the trend and weekly
seasonality is a small part of the data. There are too much noise left
in the remainder. We need some explanatory factors to explain this
source of noise.
df |>
features(daily_volume, feat_stl)
# Extract day of the week, day of the month, month, and year
df <- df %>%
mutate(day_of_week = wday(date, label=TRUE), # Day of the week (e.g., Mon, Tue)
week_of_month = week(date) - week(floor_date(date, "month")) + 1,
month = month(date, label=TRUE)) # Month (e.g., Jan, Feb)
head(df)
df$week_of_month = factor(df$week_of_month, ordered = TRUE)
head(df)
We can also consider holidays like July 4th (independence day), Thanksgiving (November 23rd), etc. So, we need to add an indicator column for holidays as well.
# Define commonly observed holidays in the USA
holidays <- c("2017-01-01", "2017-01-16", "2017-02-20", "2017-05-29", "2017-07-04", "2017-09-04", "2017-10-09", "2017-11-11", "2017-11-23", "2017-11-24", "2017-12-24", "2017-12-25", "2017-12-31",
"2018-01-01", "2018-01-15", "2018-02-19", "2018-05-28", "2018-07-04", "2018-09-03", "2018-10-08", "2018-11-11", "2018-11-22", "2018-11-23", "2018-12-24", "2018-12-25", "2018-12-31",
"2019-01-01", "2019-01-21", "2019-02-18", "2019-05-27", "2019-07-04", "2019-09-02", "2019-10-14", "2019-11-11", "2019-11-28", "2019-11-29", "2019-12-24", "2019-12-25", "2019-12-31")
# Function to check if a date is a holiday in the USA
is_us_holiday <- function(date) {
return(as.numeric(as.character(date) %in% holidays))
}
# Create 'is_holiday' column and set default value to FALSE
df$is_holiday <- 0
# Iterate through rows and set the 'is_holiday' indicator based on the date
for (i in 1:nrow(df)) {
date <- df$date[i]
year <- year(date)
df$is_holiday[i] <- is_us_holiday(paste(year, format(date, "-%m-%d"), sep = ""))
}
head(df)
is_long_weekend <- function(date, holidays) {
weekdays <- wday(date)
is_holiday <- date %in% as.Date(holidays)
is_friday_or_monday <- weekdays %in% c(2, 6) # Monday or Friday
ifelse(is_holiday & is_friday_or_monday, 1, 0)
}
df$is_long_weekend <- is_long_weekend(df$date, holidays)
head(df)
# Define a function to check if a date is within Thanksgiving week
is_thanksgiving_week <- function(date) {
# Calculate Thanksgiving date (fourth Thursday in November)
first_november <- as.Date(paste0(year(date), "-11-01"))
offset <- 22 + (11 - as.numeric(format(first_november, "%w"))) %% 7
thanksgiving_date <- as.Date(paste0(year(date), "-11-", offset))
# Check if the date is within the week of Thanksgiving
return(ifelse(date >= thanksgiving_date - days(3) & date <= thanksgiving_date + days(3), 1, 0))
}
# Define a function to check if a date is within Christmas week
is_christmas_week <- function(date) {
# Assuming Christmas week is the week of December 25th
return(ifelse(week(date) == week(as.Date(paste0(year(date), "-12-25"))), 1, 0))
}
# Define a function to check if a date is within the New Year season
is_new_year_season <- function(date) {
# Assuming New Year season is from December 28th to January 3rd
january_condition <- date >= (as.Date(paste0(year(date), "-12-28")) - years(1)) & date <= as.Date(paste0(year(date), "-01-03"))
december_condition <- date >= as.Date(paste0(year(date), "-12-28")) & date <= (as.Date(paste0(year(date), "-01-03")) + years(1))
return(ifelse(january_condition || december_condition, 1, 0))
}
# Add indicator columns for Thanksgiving week, Christmas week, and New Year season
df <- df |>
mutate(
is_thanksgiving_week = sapply(date, is_thanksgiving_week),
is_christmas_week = sapply(date, is_christmas_week),
is_new_year_season = sapply(date, is_new_year_season)
)
df$is_long_weekend_lag2 <- lag(df$is_long_weekend, 2, default = -1)
df$is_long_weekend_lag1 <- lag(df$is_long_weekend, 1, default = -1)
df$is_long_weekend_lead2 <- lead(df$is_long_weekend, 2, default = -1)
df$is_long_weekend_lead1 <- lead(df$is_long_weekend, 1, default = -1)
df$is_holiday_lag1 <- lag(df$is_holiday, 1, default = -1)
df$is_holiday_lead1 <- lead(df$is_holiday, 1, default = -1)
df$daily_volume_lag1 <- lag(df$daily_volume, 1, default = -1)
df$daily_volume_lag2 <- lag(df$daily_volume, 2, default = -1)
df$daily_volume_lag3 <- lag(df$daily_volume, 3, default = -1)
df$daily_volume_lag4 <- lag(df$daily_volume, 4, default = -1)
df$daily_volume_lag5 <- lag(df$daily_volume, 5, default = -1)
df$daily_volume_lag6 <- lag(df$daily_volume, 6, default = -1)
df$daily_volume_lag7 <- lag(df$daily_volume, 7, default = -1)
head(df)
save(df, file="processed_data")
load("processed_data")
We want to forecast the hourly traffic for next two weeks. So, we create a test dataset with only last two weeks of data.
# Identify the cutoff point for the training data (all data except the last two weeks)
training_cutoff <- max(df$date) - 30
# Create training and test datasets
train <- df %>% filter(date < training_cutoff)
test <- df %>% filter(date >= training_cutoff)
head(test)
baseline_fit <- train |> filter(Travel_Dir == '3') |>
model(Mean = MEAN(daily_volume),
`Naïve` = NAIVE(daily_volume),
`Seasonal_naïve_week` = SNAIVE(daily_volume ~ lag('week')),
Drift = NAIVE(daily_volume ~ drift())
)
# Generate forecasts for 14 quarters
baseline_fc <- baseline_fit |> forecast(h = 31)
# Plot forecasts against actual values
baseline_fc |>
autoplot(train |> filter(Travel_Dir == '3') |> tail(30*6), level = NULL) +
autolayer(
filter_index(test |> filter(Travel_Dir == '3'), "2019-12-02" ~ "2019-12-31"),
colour = "black"
) +
labs(
y = "Traffic Count",
title = "Forecasts for daily traffic volume"
) +
guides(colour = guide_legend(title = "Forecast"))
## `mutate_if()` ignored the following grouping variables:
## Plot variable not specified, automatically selected `.vars = daily_volume`
## • Column `Travel_Dir`
accuracy( baseline_fc, df|> filter(Travel_Dir == '3')) |> select(.model, MAPE, RMSE, RMSSE)
So, the ‘mean’ model performs best.
baseline_fit |> select(Mean) |> gg_tsresiduals()
# Linear Regression
dummy_vars <- model.matrix(~ week_of_month + day_of_week + month - 1, data = train)
train_reg <- cbind(train, dummy_vars) |> select(-week_of_month, -day_of_week, -month)
head(train_reg)
train_sample <- train_reg |> filter(Travel_Dir == 3)
head(train_sample)
library(leaps)
back <- regsubsets(daily_volume ~ . -daily_volume -Travel_Dir -week_of_month6 -date, data = train_sample, nvmax=40, method="backward")
coefficient.regfitBack <- coef(back, 1:40)
train.mat <- model.matrix(daily_volume ~ . -daily_volume -Travel_Dir -week_of_month6 -date, data = train_sample)
trainErrorBackward = rep(NA, 40)
for (i in 1:40) {
coefficient = coef(back, id=i)
prediction = train.mat[,names(coefficient)]%*%coefficient
trainErrorBackward[i] = mean((train_sample$daily_volume - prediction)^2)
}
cat("Training errors:\n")
## Training errors:
trainErrorBackward
## [1] 71439419 56291482 45677999 39346921 34814558 31950003 31107585 29646426
## [9] 28164852 27126011 26474808 26070776 25653386 25433415 25292765 25110961
## [17] 24988427 24877207 24771849 24687848 24617812 24551992 24515415 24482608
## [25] 24427736 24385780 24351557 24324469 24296180 24271966 24257785 24243022
## [33] 24238082 24235126 24233397 24233339 24233302 24233275 24233251 24233244
nTrain = nrow(train_sample)
linreg.bic = nTrain*log(trainErrorBackward) + log(nTrain)*c(seq(2,41,1))
linreg.bic
## [1] 12635.98 12476.19 12336.91 12239.32 12160.44 12107.06 12094.95 12067.92
## [9] 12038.68 12019.00 12008.59 12004.40 11999.68 12000.22 12002.90 12004.41
## [17] 12007.55 12010.98 12014.57 12018.74 12023.31 12027.99 12033.50 12039.11
## [25] 12044.09 12049.44 12055.01 12060.78 12066.52 12072.37 12078.51 12084.63
## [33] 12091.04 12097.50 12104.00 12110.55 12117.09 12123.64 12130.19 12136.74
bestlinreg.bic = which.min(linreg.bic)
bestlinreg.bic
## [1] 13
bestcoeff.bic = coef(back,id=bestlinreg.bic)
cat("The selected variables according to BIC criteria:\n")
## The selected variables according to BIC criteria:
names(bestcoeff.bic)
## [1] "(Intercept)" "is_holiday" "is_long_weekend"
## [4] "is_long_weekend_lead2" "daily_volume_lag1" "day_of_week.L"
## [7] "day_of_week.Q" "day_of_week.C" "`day_of_week^4`"
## [10] "`day_of_week^5`" "`day_of_week^6`" "month.C"
## [13] "`month^4`" "`month^7`"
linreg.aic <- nTrain*log(trainErrorBackward) + 2*c(seq(2,41,1))
linreg.aic
## [1] 12626.88 12462.55 12318.71 12216.57 12133.15 12075.22 12058.57 12026.99
## [9] 11993.20 11968.97 11954.01 11945.28 11936.01 11932.00 11930.13 11927.09
## [17] 11925.68 11924.56 11923.60 11923.23 11923.25 11923.38 11924.34 11925.40
## [25] 11925.84 11926.64 11927.66 11928.88 11930.07 11931.37 11932.97 11934.54
## [33] 11936.40 11938.31 11940.26 11942.26 11944.26 11946.26 11948.26 11950.26
bestlinreg.aic = which.min(linreg.aic)
bestlinreg.aic
## [1] 20
bestcoeff.aic = coef(back,id=bestlinreg.aic)
cat("The selected variables according to AIC criteria:\n")
## The selected variables according to AIC criteria:
names(bestcoeff.aic)
## [1] "(Intercept)" "is_holiday" "is_long_weekend"
## [4] "is_thanksgiving_week" "is_new_year_season" "is_long_weekend_lag2"
## [7] "is_long_weekend_lag1" "is_long_weekend_lead2" "daily_volume_lag1"
## [10] "daily_volume_lag6" "week_of_month1" "day_of_week.L"
## [13] "day_of_week.Q" "day_of_week.C" "`day_of_week^4`"
## [16] "`day_of_week^5`" "`day_of_week^6`" "month.C"
## [19] "`month^4`" "`month^7`" "`month^8`"
tsregFormula.bic <- as.formula(paste("daily_volume ~ trend() + ", paste0(names(bestcoeff.bic)[-1], collapse = " + ")))
tsregFormula.bic
## daily_volume ~ trend() + is_holiday + is_long_weekend + is_long_weekend_lead2 +
## daily_volume_lag1 + day_of_week.L + day_of_week.Q + day_of_week.C +
## `day_of_week^4` + `day_of_week^5` + `day_of_week^6` + month.C +
## `month^4` + `month^7`
fit_linreg.bic <- train_reg |>
model(tslm = TSLM(tsregFormula.bic))
fit_linreg.bic |> filter(Travel_Dir == 3) |> report()
## Series: daily_volume
## Model: TSLM
##
## Residuals:
## Min 1Q Median 3Q Max
## -28607.7 -1285.5 347.1 1967.6 24664.2
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 8.490e+04 2.580e+03 32.906 < 2e-16 ***
## trend() 8.877e+00 9.709e-01 9.143 < 2e-16 ***
## is_holiday -2.516e+04 1.853e+03 -13.575 < 2e-16 ***
## is_long_weekend 1.342e+04 2.288e+03 5.866 6.96e-09 ***
## is_long_weekend_lead2 4.800e+03 1.331e+03 3.605 0.000335 ***
## daily_volume_lag1 1.020e-01 2.729e-02 3.738 0.000201 ***
## day_of_week.L 5.912e+03 6.616e+02 8.936 < 2e-16 ***
## day_of_week.Q -1.852e+04 5.025e+02 -36.860 < 2e-16 ***
## day_of_week.C 4.475e+03 5.081e+02 8.808 < 2e-16 ***
## `day_of_week^4` -1.219e+04 5.730e+02 -21.269 < 2e-16 ***
## `day_of_week^5` 3.110e+03 5.462e+02 5.694 1.84e-08 ***
## `day_of_week^6` -2.478e+03 5.044e+02 -4.912 1.13e-06 ***
## month.C 3.633e+03 6.830e+02 5.319 1.42e-07 ***
## `month^4` -5.601e+03 6.767e+02 -8.276 6.66e-16 ***
## `month^7` -2.925e+03 6.289e+02 -4.651 3.97e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 4833 on 683 degrees of freedom
## Multiple R-squared: 0.8059, Adjusted R-squared: 0.802
## F-statistic: 202.6 on 14 and 683 DF, p-value: < 2.22e-16
fit_linreg.bic |> filter(Travel_Dir == 3) |> augment() |>
ggplot(aes(x = date)) +
geom_line(aes(y = daily_volume, colour = "Data")) +
geom_line(aes(y = .fitted, colour = "Fitted")) +
labs(y = NULL,
title = "Fitted traffic volume"
) +
scale_colour_manual(values=c(Data="black",Fitted="#D55E00")) +
guides(colour = guide_legend(title = NULL))
fit_linreg.bic |> filter(Travel_Dir == 3) |> gg_tsresiduals()
fit_linreg.bic |> augment() |>
features(.innov, ljung_box, lag = 14)
As p-value is less than 0.05, we conclude that the residuals are significantly distinguishable from the white noise.
fit_linreg.bic |> filter(Travel_Dir == 3) |> augment() |>
ggplot(aes(x = .fitted, y = .resid)) +
geom_point() + labs(x = "Fitted", y = "Residuals")
dummy_vars <- model.matrix(~ week_of_month + day_of_week + month - 1, data = test)
test_reg <- cbind(test, dummy_vars) |> select(-week_of_month, -day_of_week, -month)
linreg.bic.fc <- fit_linreg.bic |> forecast(new_data = test_reg)
accuracy(linreg.bic.fc, df) |> select(.model, MAPE, RMSSE)
tsregFormula.aic <- as.formula(paste("daily_volume ~ trend() + ", paste0(names(bestcoeff.aic)[-1], collapse = " + ")))
tsregFormula.aic
## daily_volume ~ trend() + is_holiday + is_long_weekend + is_thanksgiving_week +
## is_new_year_season + is_long_weekend_lag2 + is_long_weekend_lag1 +
## is_long_weekend_lead2 + daily_volume_lag1 + daily_volume_lag6 +
## week_of_month1 + day_of_week.L + day_of_week.Q + day_of_week.C +
## `day_of_week^4` + `day_of_week^5` + `day_of_week^6` + month.C +
## `month^4` + `month^7` + `month^8`
fit_linreg.aic <- train_reg |>
model(tslm = TSLM(tsregFormula.aic))
fit_linreg.aic |> filter(Travel_Dir == 7) |> report()
## Series: daily_volume
## Model: TSLM
##
## Residuals:
## Min 1Q Median 3Q Max
## -34758 -1466 275 2117 14590
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.626e+04 4.319e+03 13.025 < 2e-16 ***
## trend() 6.424e+00 1.093e+00 5.878 6.52e-09 ***
## is_holiday -1.789e+04 2.085e+03 -8.578 < 2e-16 ***
## is_long_weekend 1.179e+04 2.512e+03 4.692 3.28e-06 ***
## is_thanksgiving_week 2.423e+03 1.579e+03 1.535 0.125323
## is_new_year_season -1.343e+03 1.820e+03 -0.738 0.460833
## is_long_weekend_lag2 -3.268e+03 1.501e+03 -2.177 0.029839 *
## is_long_weekend_lag1 -8.419e+02 1.484e+03 -0.567 0.570722
## is_long_weekend_lead2 4.720e+03 1.465e+03 3.222 0.001334 **
## daily_volume_lag1 2.160e-01 3.515e-02 6.146 1.36e-09 ***
## daily_volume_lag6 1.643e-01 3.310e-02 4.965 8.72e-07 ***
## week_of_month1 -9.516e+02 6.085e+02 -1.564 0.118302
## day_of_week.L 1.252e+04 7.640e+02 16.383 < 2e-16 ***
## day_of_week.Q -1.076e+04 8.437e+02 -12.755 < 2e-16 ***
## day_of_week.C -1.813e+02 6.410e+02 -0.283 0.777361
## `day_of_week^4` -6.203e+03 6.069e+02 -10.222 < 2e-16 ***
## `day_of_week^5` -1.522e+03 5.584e+02 -2.726 0.006569 **
## `day_of_week^6` -1.837e+03 5.515e+02 -3.331 0.000914 ***
## month.C 2.825e+03 7.584e+02 3.725 0.000211 ***
## `month^4` -4.285e+03 7.789e+02 -5.501 5.37e-08 ***
## `month^7` -1.291e+03 6.892e+02 -1.874 0.061373 .
## `month^8` 3.891e+02 6.697e+02 0.581 0.561420
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 5176 on 676 degrees of freedom
## Multiple R-squared: 0.753, Adjusted R-squared: 0.7454
## F-statistic: 98.15 on 21 and 676 DF, p-value: < 2.22e-16
fit_linreg.aic |> filter(Travel_Dir == 3) |> augment() |>
ggplot(aes(x = date)) +
geom_line(aes(y = daily_volume, colour = "Data")) +
geom_line(aes(y = .fitted, colour = "Fitted")) +
labs(y = NULL,
title = "Fitted traffic volume"
) +
scale_colour_manual(values=c(Data="black",Fitted="#D55E00")) +
guides(colour = guide_legend(title = NULL))
fit_linreg.aic |> filter(Travel_Dir == 3) |> gg_tsresiduals()
fit_linreg.aic |> augment() |>
features(.innov, ljung_box, lag = 14)
As p-value is less than 0.05 for Travel_Dir 7, we conclude that the residuals for that series are significantly distinguishable from the white noise.
fit_linreg.aic |> filter(Travel_Dir == 3) |> augment() |>
ggplot(aes(x = .fitted, y = .resid)) +
geom_point() + labs(x = "Fitted", y = "Residuals")
linreg.aic.fc <- fit_linreg.aic |> forecast(new_data = test_reg)
accuracy(linreg.aic.fc, df) |> select(.model, MAPE, RMSSE)
fit_dcmp <- train_reg |>
model(stlf = decomposition_model(
STL(daily_volume ~ trend(window=120) + season("week", window=60), robust=TRUE),
TSLM(season_adjust ~ trend() + is_holiday + is_long_weekend + is_thanksgiving_week +
is_new_year_season + is_long_weekend_lag2 + is_long_weekend_lag1 +
is_long_weekend_lead2 + lag(season_adjust, 1) + lag(season_adjust, 6) +
week_of_month1 + month.C + `month^4` + `month^7`+`month^8`)
))
fit_dcmp |> filter(Travel_Dir == 7) |> gg_tsresiduals()
## Warning: Removed 7 rows containing missing values (`geom_line()`).
## Warning: Removed 7 rows containing missing values (`geom_point()`).
## Warning: Removed 7 rows containing non-finite values (`stat_bin()`).
fit_dcmp |> augment() |>
features(.innov, ljung_box, lag = 14)
fit_dcmp |> filter(Travel_Dir == 3) |> augment() |>
ggplot(aes(x = .fitted, y = .innov)) +
geom_point() + labs(x = "Fitted", y = "Residuals")
## Warning: Removed 7 rows containing missing values (`geom_point()`).
fit_dcmp |> filter(Travel_Dir == 3) |> augment() |> filter(.resid > 20000)
dcmp_test_dir3 <- test_reg |> filter(Travel_Dir == '3') |>
model(STL(daily_volume ~ trend(window=120) + season("week", window=60), robust=TRUE)) #trend(window = 90) + season('week', window=30)))
dcmp_test_dir7 <- test_reg |> filter(Travel_Dir == '7') |>
model(STL(daily_volume ~ trend(window=120) + season("week", window=60), robust=TRUE))
test_dcmp_dir3 <- test_reg |> filter(Travel_Dir == 3) |>
mutate(season_adjust = components(dcmp_test_dir3) |> pull(season_adjust))
test_dcmp_dir7 <- test_reg |> filter(Travel_Dir == 7) |>
mutate(season_adjust = components(dcmp_test_dir7) |> pull(season_adjust))
test_dcmp <- bind_rows(test_dcmp_dir3, test_dcmp_dir7)
dcmp_fc <- fit_dcmp |> forecast(new_data = test_dcmp)
accuracy(dcmp_fc, df) |> select(.model, MAPE, RMSSE)
train |>
features(daily_volume, unitroot_kpss)
So, the data is not stationary
train |>
features(daily_volume, unitroot_nsdiffs)
one seasonal difference is necessary
train |> mutate(daily_volume = difference(daily_volume, 7)) |>
features(daily_volume, unitroot_ndiffs)
No first difference is necessary
train |> filter(Travel_Dir == 3) |>
gg_tsdisplay(difference(daily_volume, 7),
plot_type='partial', lag=100) +
labs(title="Seasonally differenced", y="")
## Warning: Removed 7 rows containing missing values (`geom_line()`).
## Warning: Removed 7 rows containing missing values (`geom_point()`).
D = 1, d = 0, Q = 0, P = 6, p = 39, q = 0
fit <- train |>
model(
auto = ARIMA(daily_volume, stepwise = FALSE, approx = FALSE)
)
fit
glance(fit) |> arrange(AICc) |> select(Travel_Dir:BIC)
fit |> filter(Travel_Dir == 3) |> select(auto) |> gg_tsresiduals(lag=36)
augment(fit) |>
filter(.model == "auto") |>
features(.innov, ljung_box, lag=24, dof=4)
arima_fc <- fit |> forecast(new_data = test)
accuracy(arima_fc, df) |> select(.model, MAPE, RMSSE)
head(train_reg)
tsregFormula.aic
## daily_volume ~ trend() + is_holiday + is_long_weekend + is_thanksgiving_week +
## is_new_year_season + is_long_weekend_lag2 + is_long_weekend_lag1 +
## is_long_weekend_lead2 + daily_volume_lag1 + daily_volume_lag6 +
## week_of_month1 + day_of_week.L + day_of_week.Q + day_of_week.C +
## `day_of_week^4` + `day_of_week^5` + `day_of_week^6` + month.C +
## `month^4` + `month^7` + `month^8`
fit_dynreg <- train_reg |>
model(ARIMA(daily_volume ~ trend() + is_holiday + is_long_weekend + is_thanksgiving_week +
is_new_year_season + is_long_weekend_lag2 + is_long_weekend_lag1 +
is_long_weekend_lead2 + daily_volume_lag1 + daily_volume_lag6 +
week_of_month1 + day_of_week.L + day_of_week.Q + day_of_week.C +
`day_of_week^4` + `day_of_week^5` + `day_of_week^6` + month.C +
`month^4` + `month^7` + `month^8` + pdq(3,0,0) + PDQ(1,0,2)))
coefficients(fit_dynreg |> filter(Travel_Dir==7))
bind_rows(
`Regression residuals` =
as_tibble(residuals(fit_dynreg |> filter(Travel_Dir==3), type = "regression")),
`ARIMA residuals` =
as_tibble(residuals(fit_dynreg |> filter(Travel_Dir==3), type = "innovation")),
.id = "type"
) |>
mutate(
type = factor(type, levels=c(
"Regression residuals", "ARIMA residuals"))
) |>
ggplot(aes(x = date, y = .resid)) +
geom_line() +
facet_grid(vars(type))
fit_dynreg |> filter(Travel_Dir==3) |> gg_tsresiduals()
augment(fit_dynreg) |>
features(.innov, ljung_box, lag = 14)
dynreg_fc <- fit_dynreg |> forecast(new_data = test_reg)
accuracy(dynreg_fc, df) |> select(.model, MAPE, RMSSE)
fit_arima_dcmp <- train_reg |>
model(stlf = decomposition_model(
STL(daily_volume ~ trend(window=120) + season("week", window=60), robust=TRUE),
ARIMA(season_adjust ~ trend() + is_holiday + is_long_weekend + is_thanksgiving_week +
is_new_year_season + is_long_weekend_lag2 + is_long_weekend_lag1 +
is_long_weekend_lead2 + lag(season_adjust, 1) + lag(season_adjust, 2) + lag(season_adjust, 3) +
month.C + `month^4` + `month^7` + `month^8` + `month^9`, stepwise = FALSE, approximation = FALSE)
))
fit_arima_dcmp |> filter(Travel_Dir == 3) |> gg_tsresiduals()
## Warning: Removed 7 rows containing missing values (`geom_line()`).
## Warning: Removed 7 rows containing missing values (`geom_point()`).
## Warning: Removed 7 rows containing non-finite values (`stat_bin()`).
fit_arima_dcmp |> filter(Travel_Dir == 3) |> report()
## Series: daily_volume
## Model: STL decomposition model
## Combination: season_adjust + season_week
##
## ========================================
##
## Series: season_adjust
## Model: LM w/ ARIMA(0,0,0)(1,0,1)[7] errors
##
## Coefficients:
## sar1 sma1 trend() is_holiday is_long_weekend
## 0.8815 -0.8412 7.7987 -26919.639 15006.137
## s.e. 0.1221 0.1398 1.2321 1857.119 2185.928
## is_thanksgiving_week is_new_year_season is_long_weekend_lag2
## 2539.881 35.4794 44.2939
## s.e. 1397.337 1822.2034 1337.9996
## is_long_weekend_lag1 is_long_weekend_lead2 lag(season_adjust, 1)
## 4689.844 4490.225 0.1899
## s.e. 1328.271 1241.775 0.0332
## lag(season_adjust, 2) lag(season_adjust, 3) month.C `month^4`
## 0.0265 -0.0079 3277.3572 -4606.580
## s.e. 0.0341 0.0325 735.3434 750.049
## `month^7` `month^8` `month^9` intercept
## -2481.7941 1297.5434 -852.2998 74773.139
## s.e. 628.4171 602.5244 593.6297 4885.812
##
## sigma^2 estimated as 21622101: log likelihood=-6847.16
## AIC=13734.32 AICc=13735.56 BIC=13825.29
##
## Series: season_week
## Model: SNAIVE
##
## sigma^2: 534.5482
augment(fit_arima_dcmp) |>
features(.innov, ljung_box, lag = 14)
dcmp_arima_fc <- fit_arima_dcmp |> forecast(new_data = test_dcmp)
accuracy(dcmp_arima_fc, df) |> select(.model, MAPE, RMSSE)
fit_arima_dcmp |> filter(Travel_Dir == 3) |> augment() |>
ggplot(aes(x = .fitted, y = .innov)) +
geom_point() + labs(x = "Fitted", y = "Residuals")
## Warning: Removed 7 rows containing missing values (`geom_point()`).
forecast(fit_arima_dcmp, new_data = test_dcmp) |>
filter(Travel_Dir == 3) |>
autoplot(tail(train |> filter(Travel_Dir == 3), 90)) +
autolayer(
test |> filter(Travel_Dir == 3),
colour = "black"
) +
labs(title = "Traffic Volume Forecast",
y="Traffic count")
## `mutate_if()` ignored the following grouping variables:
## Plot variable not specified, automatically selected `.vars = daily_volume`
## • Column `Travel_Dir`