INRIX TMC

getwd()
## [1] "C:/Users/xuw12/OneDrive - Texas State University/Hackathon_Rohit/02_Projects/0-7171/INRIX/Analysis"
setwd("C:/Users/xuw12/OneDrive - Texas State University/Hackathon_Rohit/02_Projects/0-7171/INRIX/Analysis")

##Start
library(readxl)
library(readr)
library(skimr)
library(ggplot2)
library(ggstatsplot)

dat01= read.csv("Routes_TMC_2.csv")
dim(dat01)
## [1] 235716     16
names(dat01)
##  [1] "tmc_code"                 "measurement_tstamp"      
##  [3] "speed"                    "historical_average_speed"
##  [5] "reference_speed"          "travel_time_minutes"     
##  [7] "confidence_score"         "cvalue"                  
##  [9] "Month"                    "Day"                     
## [11] "DOW"                      "Weekday_Weekend"         
## [13] "Hours"                    "PeakHr"                  
## [15] "Period"                   "Site"
skim(dat01)
Data summary
Name dat01
Number of rows 235716
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 13 0
measurement_tstamp 0 1 13 15 0 18132 0
DOW 0 1 6 9 0 7 0
Weekday_Weekend 0 1 7 7 0 2 0
Hours 0 1 11 11 0 24 0
PeakHr 0 1 7 11 0 3 0
Period 0 1 5 12 0 3 0
Site 0 1 6 6 0 4 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 60.33 10.25 2.00 58.31 62.99 65.98 74.19 ▁▁▁▃▇
historical_average_speed 0 1 60.05 8.56 16.00 58.00 63.00 65.00 71.00 ▁▁▁▅▇
reference_speed 0 1 62.41 3.34 57.00 60.00 64.00 65.00 66.00 ▅▃▁▅▇
travel_time_minutes 0 1 0.43 0.38 0.08 0.19 0.30 0.64 10.16 ▇▁▁▁▁
confidence_score 0 1 30.00 0.03 20.00 30.00 30.00 30.00 30.00 ▁▁▁▁▇
cvalue 1 1 99.74 1.44 23.00 100.00 100.00 100.00 100.00 ▁▁▁▁▇
Month 0 1 3.87 0.79 3.00 3.00 4.00 5.00 5.00 ▇▁▇▁▆
Day 0 1 15.64 8.72 1.00 8.00 16.00 23.00 31.00 ▇▇▇▇▆ 
table(dat01$Site)
## 
## Site 3 Site 5 Site 7 Site 8 
##  36264  90660  54396  54396

Analysis by Period

Site 3

Site3= subset(dat01, Site=="Site 3")
dim(Site3)
## [1] 36264    16
skim(Site3)
Data summary
Name Site3
Number of rows 36264
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 2 0
measurement_tstamp 0 1 13 15 0 18132 0
DOW 0 1 6 9 0 7 0
Weekday_Weekend 0 1 7 7 0 2 0
Hours 0 1 11 11 0 24 0
PeakHr 0 1 7 11 0 3 0
Period 0 1 5 12 0 3 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 65.63 4.93 6.67 64.77 66.33 67.74 73.76 ▁▁▁▁▇
historical_average_speed 0 1 65.52 1.58 57.00 65.00 65.00 66.00 71.00 ▁▁▇▇▁
reference_speed 0 1 65.50 0.50 65.00 65.00 65.50 66.00 66.00 ▇▁▁▁▇
travel_time_minutes 0 1 0.41 0.31 0.12 0.13 0.61 0.66 6.49 ▇▁▁▁▁
confidence_score 0 1 30.00 0.00 30.00 30.00 30.00 30.00 30.00 ▁▁▇▁▁
cvalue 0 1 99.90 0.96 80.00 100.00 100.00 100.00 100.00 ▁▁▁▁▇
Month 0 1 3.87 0.79 3.00 3.00 4.00 5.00 5.00 ▇▁▇▁▆
Day 0 1 15.64 8.72 1.00 8.00 16.00 23.00 31.00 ▇▇▇▇▆ 
Site3$`speed`= as.integer(Site3$`speed`)
ggbetweenstats(
  data = Site3,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Site 5

Site5= subset(dat01, Site=="Site 5")
dim(Site5)
## [1] 90660    16
skim(Site5)
Data summary
Name Site5
Number of rows 90660
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 5 0
measurement_tstamp 0 1 13 15 0 18132 0
DOW 0 1 6 9 0 7 0
Weekday_Weekend 0 1 7 7 0 2 0
Hours 0 1 11 11 0 24 0
PeakHr 0 1 7 11 0 3 0
Period 0 1 5 12 0 3 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 61.89 11.38 6.00 62.53 64.77 66.58 74.19 ▁▁▁▁▇
historical_average_speed 0 1 61.53 9.74 16.00 63.00 64.00 66.00 71.00 ▁▁▁▁▇
reference_speed 0 1 64.40 1.02 63.00 64.00 64.00 65.00 66.00 ▃▇▁▃▃
travel_time_minutes 0 1 0.36 0.35 0.16 0.19 0.20 0.35 7.68 ▇▁▁▁▁
confidence_score 0 1 30.00 0.05 20.00 30.00 30.00 30.00 30.00 ▁▁▁▁▇
cvalue 1 1 99.73 1.48 23.00 100.00 100.00 100.00 100.00 ▁▁▁▁▇
Month 0 1 3.87 0.79 3.00 3.00 4.00 5.00 5.00 ▇▁▇▁▆
Day 0 1 15.64 8.72 1.00 8.00 16.00 23.00 31.00 ▇▇▇▇▆ 
Site5$`speed`= as.integer(Site5$`speed`)
ggbetweenstats(
  data = Site5,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Site 7

Site7= subset(dat01, Site=="Site 7")
dim(Site7)
## [1] 54396    16
skim(Site7)
Data summary
Name Site7
Number of rows 54396
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 3 0
measurement_tstamp 0 1 13 15 0 18132 0
DOW 0 1 6 9 0 7 0
Weekday_Weekend 0 1 7 7 0 2 0
Hours 0 1 11 11 0 24 0
PeakHr 0 1 7 11 0 3 0
Period 0 1 5 12 0 3 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 59.82 8.08 8.19 58.07 61.29 64.77 73.57 ▁▁▁▅▇
historical_average_speed 0 1 59.92 6.04 29.00 58.00 60.00 64.00 69.00 ▁▁▁▇▆
reference_speed 0 1 62.00 2.83 60.00 60.00 60.00 66.00 66.00 ▇▁▁▁▃
travel_time_minutes 0 1 0.66 0.47 0.19 0.24 0.43 1.24 10.16 ▇▁▁▁▁
confidence_score 0 1 30.00 0.00 30.00 30.00 30.00 30.00 30.00 ▁▁▇▁▁
cvalue 0 1 99.83 1.12 90.00 100.00 100.00 100.00 100.00 ▁▁▁▁▇
Month 0 1 3.87 0.79 3.00 3.00 4.00 5.00 5.00 ▇▁▇▁▆
Day 0 1 15.64 8.72 1.00 8.00 16.00 23.00 31.00 ▇▇▇▇▆ 
Site7$`speed`= as.integer(Site7$`speed`)
ggbetweenstats(
  data = Site7,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Site 8

Site8= subset(dat01, Site=="Site 8")
dim(Site8)
## [1] 54396    16
skim(Site8)
Data summary
Name Site8
Number of rows 54396
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 3 0
measurement_tstamp 0 1 13 15 0 18132 0
DOW 0 1 6 9 0 7 0
Weekday_Weekend 0 1 7 7 0 2 0
Hours 0 1 11 11 0 24 0
PeakHr 0 1 7 11 0 3 0
Period 0 1 5 12 0 3 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 54.70 10.14 2.00 55.0 57.20 59.15 68.4 ▁▁▁▂▇
historical_average_speed 0 1 54.05 7.84 17.00 55.0 57.00 58.00 62.0 ▁▁▁▁▇
reference_speed 0 1 57.43 0.66 57.00 57.0 57.00 58.00 59.0 ▇▁▃▁▁
travel_time_minutes 0 1 0.33 0.27 0.08 0.1 0.32 0.42 9.2 ▇▁▁▁▁
confidence_score 0 1 30.00 0.00 30.00 30.0 30.00 30.00 30.0 ▁▁▇▁▁
cvalue 0 1 99.57 1.86 70.00 100.0 100.00 100.00 100.0 ▁▁▁▁▇
Month 0 1 3.87 0.79 3.00 3.0 4.00 5.00 5.0 ▇▁▇▁▆
Day 0 1 15.64 8.72 1.00 8.0 16.00 23.00 31.0 ▇▇▇▇▆ 
Site8$`speed`= as.integer(Site8$`speed`)
ggbetweenstats(
  data = Site8,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Analysis by Peak Hour

Site 3_OffPeak

Site3= subset(dat01, Site=="Site 3" & PeakHr=="OffPeak")
dim(Site3)
## [1] 27192    16
skim(Site3)
Data summary
Name Site3
Number of rows 27192
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 2 0
measurement_tstamp 0 1 13 15 0 13596 0
DOW 0 1 6 9 0 7 0
Weekday_Weekend 0 1 7 7 0 2 0
Hours 0 1 11 11 0 18 0
PeakHr 0 1 7 7 0 1 0
Period 0 1 5 12 0 3 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 65.99 3.30 7.18 64.95 66.37 67.75 73.76 ▁▁▁▁▇
historical_average_speed 0 1 65.63 1.18 63.00 65.00 65.00 66.00 70.00 ▂▇▇▁▁
reference_speed 0 1 65.50 0.50 65.00 65.00 65.50 66.00 66.00 ▇▁▁▁▇
travel_time_minutes 0 1 0.40 0.27 0.12 0.13 0.61 0.66 3.68 ▇▁▁▁▁
confidence_score 0 1 30.00 0.00 30.00 30.00 30.00 30.00 30.00 ▁▁▇▁▁
cvalue 0 1 99.97 0.55 80.00 100.00 100.00 100.00 100.00 ▁▁▁▁▇
Month 0 1 3.87 0.79 3.00 3.00 4.00 5.00 5.00 ▇▁▇▁▆
Day 0 1 15.64 8.72 1.00 8.00 16.00 23.00 31.00 ▇▇▇▇▆ 
Site3$`speed`= as.integer(Site3$`speed`)
ggbetweenstats(
  data = Site3,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Site 3_MorningPeak

Site3= subset(dat01, Site=="Site 3" & PeakHr=="MorningPeak")
dim(Site3)
## [1] 4536   16
skim(Site3)
Data summary
Name Site3
Number of rows 4536
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 2 0
measurement_tstamp 0 1 13 14 0 2268 0
DOW 0 1 6 9 0 7 0
Weekday_Weekend 0 1 7 7 0 2 0
Hours 0 1 11 11 0 3 0
PeakHr 0 1 11 11 0 1 0
Period 0 1 5 12 0 3 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 65.72 5.70 9.92 64.96 66.58 68.00 72.40 ▁▁▁▁▇
historical_average_speed 0 1 64.92 2.77 57.00 63.00 65.00 67.00 71.00 ▁▂▇▆▂
reference_speed 0 1 65.50 0.50 65.00 65.00 65.50 66.00 66.00 ▇▁▁▁▇
travel_time_minutes 0 1 0.41 0.31 0.12 0.13 0.61 0.65 4.43 ▇▁▁▁▁
confidence_score 0 1 30.00 0.00 30.00 30.00 30.00 30.00 30.00 ▁▁▇▁▁
cvalue 0 1 99.84 1.15 90.00 100.00 100.00 100.00 100.00 ▁▁▁▁▇
Month 0 1 3.87 0.79 3.00 3.00 4.00 5.00 5.00 ▇▁▇▁▅
Day 0 1 15.63 8.72 1.00 8.00 16.00 23.00 31.00 ▇▇▇▇▆ 
Site3$`speed`= as.integer(Site3$`speed`)
ggbetweenstats(
  data = Site3,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Site 3_EveningPeak

Site3= subset(dat01, Site=="Site 3" & PeakHr=="EveningPeak")
dim(Site3)
## [1] 4536   16
skim(Site3)
Data summary
Name Site3
Number of rows 4536
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 2 0
measurement_tstamp 0 1 14 15 0 2268 0
DOW 0 1 6 9 0 7 0
Weekday_Weekend 0 1 7 7 0 2 0
Hours 0 1 11 11 0 3 0
PeakHr 0 1 11 11 0 1 0
Period 0 1 5 12 0 3 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 63.38 9.51 6.67 63.79 65.72 67.19 71.77 ▁▁▁▁▇
historical_average_speed 0 1 65.50 1.90 62.00 64.00 65.00 67.00 70.00 ▃▇▅▅▂
reference_speed 0 1 65.50 0.50 65.00 65.00 65.50 66.00 66.00 ▇▁▁▁▇
travel_time_minutes 0 1 0.45 0.46 0.12 0.13 0.62 0.66 6.49 ▇▁▁▁▁
confidence_score 0 1 30.00 0.00 30.00 30.00 30.00 30.00 30.00 ▁▁▇▁▁
cvalue 0 1 99.54 2.02 90.00 100.00 100.00 100.00 100.00 ▁▁▁▁▇
Month 0 1 3.87 0.79 3.00 3.00 4.00 5.00 5.00 ▇▁▇▁▅
Day 0 1 15.63 8.72 1.00 8.00 16.00 23.00 31.00 ▇▇▇▇▆ 
Site3$`speed`= as.integer(Site3$`speed`)
ggbetweenstats(
  data = Site3,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Site 5_OffPeak

Site5= subset(dat01, Site=="Site 5" & PeakHr=="OffPeak")
dim(Site5)
## [1] 67980    16
skim(Site5)
Data summary
Name Site5
Number of rows 67980
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 5 0
measurement_tstamp 0 1 13 15 0 13596 0
DOW 0 1 6 9 0 7 0
Weekday_Weekend 0 1 7 7 0 2 0
Hours 0 1 11 11 0 18 0
PeakHr 0 1 7 7 0 1 0
Period 0 1 5 12 0 3 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 64.40 4.17 13.29 62.96 64.98 66.6 74.19 ▁▁▁▂▇
historical_average_speed 0 1 64.14 2.94 43.00 63.00 64.00 66.0 70.00 ▁▁▁▇▇
reference_speed 0 1 64.40 1.02 63.00 64.00 64.00 65.0 66.00 ▃▇▁▃▃
travel_time_minutes 0 1 0.31 0.20 0.16 0.19 0.20 0.3 1.99 ▇▂▁▁▁
confidence_score 0 1 30.00 0.06 20.00 30.00 30.00 30.0 30.00 ▁▁▁▁▇
cvalue 1 1 99.92 0.82 23.00 100.00 100.00 100.0 100.00 ▁▁▁▁▇
Month 0 1 3.87 0.79 3.00 3.00 4.00 5.0 5.00 ▇▁▇▁▆
Day 0 1 15.64 8.72 1.00 8.00 16.00 23.0 31.00 ▇▇▇▇▆ 
Site5$`speed`= as.integer(Site5$`speed`)
ggbetweenstats(
  data = Site5,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Site 5_MorningPeak

Site5= subset(dat01, Site=="Site 5" & PeakHr=="MorningPeak")
dim(Site5)
## [1] 11340    16
skim(Site5)
Data summary
Name Site5
Number of rows 11340
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 5 0
measurement_tstamp 0 1 13 14 0 2268 0
DOW 0 1 6 9 0 7 0
Weekday_Weekend 0 1 7 7 0 2 0
Hours 0 1 11 11 0 3 0
PeakHr 0 1 11 11 0 1 0
Period 0 1 5 12 0 3 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 64.53 3.77 6.00 62.95 64.92 66.59 72.98 ▁▁▁▁▇
historical_average_speed 0 1 63.69 2.22 58.00 62.00 64.00 65.00 70.00 ▂▅▇▅▁
reference_speed 0 1 64.40 1.02 63.00 64.00 64.00 65.00 66.00 ▃▇▁▃▃
travel_time_minutes 0 1 0.32 0.28 0.16 0.19 0.20 0.30 7.68 ▇▁▁▁▁
confidence_score 0 1 30.00 0.00 30.00 30.00 30.00 30.00 30.00 ▁▁▇▁▁
cvalue 0 1 99.96 0.60 90.00 100.00 100.00 100.00 100.00 ▁▁▁▁▇
Month 0 1 3.87 0.79 3.00 3.00 4.00 5.00 5.00 ▇▁▇▁▅
Day 0 1 15.63 8.72 1.00 8.00 16.00 23.00 31.00 ▇▇▇▇▆ 
Site5$`speed`= as.integer(Site5$`speed`)
ggbetweenstats(
  data = Site5,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Site 5_EveningPeak

Site5= subset(dat01, Site=="Site 5" & PeakHr=="EveningPeak")
dim(Site5)
## [1] 11340    16
skim(Site5)
Data summary
Name Site5
Number of rows 11340
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 5 0
measurement_tstamp 0 1 14 15 0 2268 0
DOW 0 1 6 9 0 7 0
Weekday_Weekend 0 1 7 7 0 2 0
Hours 0 1 11 11 0 3 0
PeakHr 0 1 11 11 0 1 0
Period 0 1 5 12 0 3 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 44.22 23.68 6.18 17.07 61.08 65.60 71.79 ▅▂▁▁▇
historical_average_speed 0 1 43.71 18.40 16.00 27.00 40.00 65.00 71.00 ▆▆▃▂▇
reference_speed 0 1 64.40 1.02 63.00 64.00 64.00 65.00 66.00 ▃▇▁▃▃
travel_time_minutes 0 1 0.70 0.73 0.17 0.20 0.59 0.84 7.24 ▇▁▁▁▁
confidence_score 0 1 30.00 0.00 30.00 30.00 30.00 30.00 30.00 ▁▁▇▁▁
cvalue 0 1 98.39 3.32 90.00 100.00 100.00 100.00 100.00 ▁▁▁▁▇
Month 0 1 3.87 0.79 3.00 3.00 4.00 5.00 5.00 ▇▁▇▁▅
Day 0 1 15.63 8.72 1.00 8.00 16.00 23.00 31.00 ▇▇▇▇▆ 
Site5$`speed`= as.integer(Site5$`speed`)
ggbetweenstats(
  data = Site5,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Site 7_OffPeak

Site7= subset(dat01, Site=="Site 7" & PeakHr=="OffPeak")
dim(Site7)
## [1] 40788    16
skim(Site7)
Data summary
Name Site7
Number of rows 40788
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 3 0
measurement_tstamp 0 1 13 15 0 13596 0
DOW 0 1 6 9 0 7 0
Weekday_Weekend 0 1 7 7 0 2 0
Hours 0 1 11 11 0 18 0
PeakHr 0 1 7 7 0 1 0
Period 0 1 5 12 0 3 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 60.91 6.13 8.19 58.54 61.50 64.98 73.57 ▁▁▁▅▇
historical_average_speed 0 1 60.89 4.17 42.00 59.00 60.00 65.00 69.00 ▁▁▃▇▅
reference_speed 0 1 62.00 2.83 60.00 60.00 60.00 66.00 66.00 ▇▁▁▁▃
travel_time_minutes 0 1 0.65 0.47 0.19 0.24 0.43 1.24 10.16 ▇▁▁▁▁
confidence_score 0 1 30.00 0.00 30.00 30.00 30.00 30.00 30.00 ▁▁▇▁▁
cvalue 0 1 99.88 0.95 90.00 100.00 100.00 100.00 100.00 ▁▁▁▁▇
Month 0 1 3.87 0.79 3.00 3.00 4.00 5.00 5.00 ▇▁▇▁▆
Day 0 1 15.64 8.72 1.00 8.00 16.00 23.00 31.00 ▇▇▇▇▆ 
Site7$`speed`= as.integer(Site7$`speed`)
ggbetweenstats(
  data = Site7,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Site 7_MorningPeak

Site7= subset(dat01, Site=="Site 7" & PeakHr=="MorningPeak")
dim(Site7)
## [1] 6804   16
skim(Site7)
Data summary
Name Site7
Number of rows 6804
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 3 0
measurement_tstamp 0 1 13 14 0 2268 0
DOW 0 1 6 9 0 7 0
Weekday_Weekend 0 1 7 7 0 2 0
Hours 0 1 11 11 0 3 0
PeakHr 0 1 11 11 0 1 0
Period 0 1 5 12 0 3 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 59.31 8.75 9.59 57.15 61.78 64.96 71.39 ▁▁▁▃▇
historical_average_speed 0 1 59.03 6.89 37.00 54.00 61.00 64.00 69.00 ▁▂▃▇▇
reference_speed 0 1 62.00 2.83 60.00 60.00 60.00 66.00 66.00 ▇▁▁▁▃
travel_time_minutes 0 1 0.66 0.45 0.20 0.25 0.43 1.23 2.63 ▇▁▅▁▁
confidence_score 0 1 30.00 0.00 30.00 30.00 30.00 30.00 30.00 ▁▁▇▁▁
cvalue 0 1 99.78 1.18 90.00 100.00 100.00 100.00 100.00 ▁▁▁▁▇
Month 0 1 3.87 0.79 3.00 3.00 4.00 5.00 5.00 ▇▁▇▁▅
Day 0 1 15.63 8.72 1.00 8.00 16.00 23.00 31.00 ▇▇▇▇▆ 
Site7$`speed`= as.integer(Site7$`speed`)
ggbetweenstats(
  data = Site7,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Site 7_EveningPeak

Site7= subset(dat01, Site=="Site 7" & PeakHr=="EveningPeak")
dim(Site7)
## [1] 6804   16
skim(Site7)
Data summary
Name Site7
Number of rows 6804
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 3 0
measurement_tstamp 0 1 14 15 0 2268 0
DOW 0 1 6 9 0 7 0
Weekday_Weekend 0 1 7 7 0 2 0
Hours 0 1 11 11 0 3 0
PeakHr 0 1 11 11 0 1 0
Period 0 1 5 12 0 3 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 53.78 13.30 9.21 43.44 59.41 62.99 70.20 ▁▂▂▂▇
historical_average_speed 0 1 54.98 10.45 29.00 46.00 59.00 62.00 69.00 ▂▃▂▇▇
reference_speed 0 1 62.00 2.83 60.00 60.00 60.00 66.00 66.00 ▇▁▁▁▃
travel_time_minutes 0 1 0.73 0.46 0.21 0.41 0.54 1.26 7.35 ▇▁▁▁▁
confidence_score 0 1 30.00 0.00 30.00 30.00 30.00 30.00 30.00 ▁▁▇▁▁
cvalue 0 1 99.59 1.77 90.00 100.00 100.00 100.00 100.00 ▁▁▁▁▇
Month 0 1 3.87 0.79 3.00 3.00 4.00 5.00 5.00 ▇▁▇▁▅
Day 0 1 15.63 8.72 1.00 8.00 16.00 23.00 31.00 ▇▇▇▇▆ 
Site7$`speed`= as.integer(Site7$`speed`)
ggbetweenstats(
  data = Site7,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Site 8_OffPeak

Site8= subset(dat01, Site=="Site 8" & PeakHr=="OffPeak")
dim(Site8)
## [1] 40788    16
skim(Site8)
Data summary
Name Site8
Number of rows 40788
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 3 0
measurement_tstamp 0 1 13 15 0 13596 0
DOW 0 1 6 9 0 7 0
Weekday_Weekend 0 1 7 7 0 2 0
Hours 0 1 11 11 0 18 0
PeakHr 0 1 7 7 0 1 0
Period 0 1 5 12 0 3 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 56.75 5.82 2.00 55.59 57.40 59.36 68.4 ▁▁▁▂▇
historical_average_speed 0 1 56.22 3.39 38.00 56.00 57.00 58.00 62.0 ▁▁▁▇▅
reference_speed 0 1 57.43 0.66 57.00 57.00 57.00 58.00 59.0 ▇▁▃▁▁
travel_time_minutes 0 1 0.30 0.20 0.08 0.10 0.32 0.42 9.2 ▇▁▁▁▁
confidence_score 0 1 30.00 0.00 30.00 30.00 30.00 30.00 30.0 ▁▁▇▁▁
cvalue 0 1 99.82 1.22 70.00 100.00 100.00 100.00 100.0 ▁▁▁▁▇
Month 0 1 3.87 0.79 3.00 3.00 4.00 5.00 5.0 ▇▁▇▁▆
Day 0 1 15.64 8.72 1.00 8.00 16.00 23.00 31.0 ▇▇▇▇▆ 
Site8$`speed`= as.integer(Site8$`speed`)
ggbetweenstats(
  data = Site8,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Site 8_MorningPeak

Site8= subset(dat01, Site=="Site 8" & PeakHr=="MorningPeak")
dim(Site8)
## [1] 6804   16
skim(Site8)
Data summary
Name Site8
Number of rows 6804
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 3 0
measurement_tstamp 0 1 13 14 0 2268 0
DOW 0 1 6 9 0 7 0
Weekday_Weekend 0 1 7 7 0 2 0
Hours 0 1 11 11 0 3 0
PeakHr 0 1 11 11 0 1 0
Period 0 1 5 12 0 3 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 52.88 11.46 7.26 52.88 56.60 59.12 66.79 ▁▁▁▃▇
historical_average_speed 0 1 51.03 9.15 25.00 46.00 55.00 58.00 61.00 ▁▁▂▃▇
reference_speed 0 1 57.42 0.65 57.00 57.00 57.00 58.00 59.00 ▇▁▃▁▁
travel_time_minutes 0 1 0.34 0.25 0.08 0.11 0.33 0.42 2.51 ▇▁▁▁▁
confidence_score 0 1 30.00 0.00 30.00 30.00 30.00 30.00 30.00 ▁▁▇▁▁
cvalue 0 1 98.94 2.75 90.00 100.00 100.00 100.00 100.00 ▁▁▁▁▇
Month 0 1 3.87 0.79 3.00 3.00 4.00 5.00 5.00 ▇▁▇▁▅
Day 0 1 15.63 8.72 1.00 8.00 16.00 23.00 31.00 ▇▇▇▇▆ 
Site8$`speed`= as.integer(Site8$`speed`)
ggbetweenstats(
  data = Site8,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Site 8_EveningPeak

Site8= subset(dat01, Site=="Site 8" & PeakHr=="EveningPeak")
dim(Site8)
## [1] 6804   16
skim(Site8)
Data summary
Name Site8
Number of rows 6804
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 3 0
measurement_tstamp 0 1 14 15 0 2268 0
DOW 0 1 6 9 0 7 0
Weekday_Weekend 0 1 7 7 0 2 0
Hours 0 1 11 11 0 3 0
PeakHr 0 1 11 11 0 1 0
Period 0 1 5 12 0 3 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 44.23 18.68 6.00 21.26 55.41 57.80 64.27 ▂▁▁▁▇
historical_average_speed 0 1 44.07 14.22 17.00 30.00 51.00 57.00 60.00 ▂▃▁▂▇
reference_speed 0 1 57.43 0.66 57.00 57.00 57.00 58.00 59.00 ▇▁▃▁▁
travel_time_minutes 0 1 0.52 0.48 0.09 0.19 0.38 0.48 3.43 ▇▁▁▁▁
confidence_score 0 1 30.00 0.00 30.00 30.00 30.00 30.00 30.00 ▁▁▇▁▁
cvalue 0 1 98.65 3.06 90.00 100.00 100.00 100.00 100.00 ▁▁▁▁▇
Month 0 1 3.87 0.79 3.00 3.00 4.00 5.00 5.00 ▇▁▇▁▅
Day 0 1 15.63 8.72 1.00 8.00 16.00 23.00 31.00 ▇▇▇▇▆ 
Site8$`speed`= as.integer(Site8$`speed`)
ggbetweenstats(
  data = Site8,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Analysis by Weekday/Weekend

Site 3_Weekday

Site3= subset(dat01, Site=="Site 3" & Weekday_Weekend=="Weekday")
dim(Site3)
## [1] 25920    16
skim(Site3)
Data summary
Name Site3
Number of rows 25920
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 2 0
measurement_tstamp 0 1 13 15 0 12960 0
DOW 0 1 6 9 0 5 0
Weekday_Weekend 0 1 7 7 0 1 0
Hours 0 1 11 11 0 24 0
PeakHr 0 1 7 11 0 3 0
Period 0 1 5 12 0 3 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 65.22 5.59 6.67 64.52 66.05 67.40 73.76 ▁▁▁▁▇
historical_average_speed 0 1 65.00 1.29 57.00 65.00 65.00 66.00 68.00 ▁▁▁▇▅
reference_speed 0 1 65.50 0.50 65.00 65.00 65.50 66.00 66.00 ▇▁▁▁▇
travel_time_minutes 0 1 0.41 0.32 0.12 0.13 0.61 0.66 6.49 ▇▁▁▁▁
confidence_score 0 1 30.00 0.00 30.00 30.00 30.00 30.00 30.00 ▁▁▇▁▁
cvalue 0 1 99.86 1.12 80.00 100.00 100.00 100.00 100.00 ▁▁▁▁▇
Month 0 1 3.91 0.78 3.00 3.00 4.00 5.00 5.00 ▇▁▇▁▆
Day 0 1 15.60 8.68 1.00 8.00 16.00 23.00 31.00 ▇▇▇▇▆ 
Site3$`speed`= as.integer(Site3$`speed`)
ggbetweenstats(
  data = Site3,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Site 3_Weekend

Site3= subset(dat01, Site=="Site 3" & Weekday_Weekend=="Weekend")
dim(Site3)
## [1] 10344    16
skim(Site3)
Data summary
Name Site3
Number of rows 10344
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 2 0
measurement_tstamp 0 1 13 15 0 5172 0
DOW 0 1 6 8 0 2 0
Weekday_Weekend 0 1 7 7 0 1 0
Hours 0 1 11 11 0 24 0
PeakHr 0 1 7 11 0 3 0
Period 0 1 5 6 0 2 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 66.66 2.31 42.11 65.47 66.96 68.17 72.59 ▁▁▁▆▇
historical_average_speed 0 1 66.84 1.47 64.00 66.00 67.00 68.00 71.00 ▅▆▇▃▁
reference_speed 0 1 65.50 0.50 65.00 65.00 65.50 66.00 66.00 ▇▁▁▁▇
travel_time_minutes 0 1 0.39 0.26 0.12 0.13 0.41 0.65 1.04 ▇▁▇▁▁
confidence_score 0 1 30.00 0.00 30.00 30.00 30.00 30.00 30.00 ▁▁▇▁▁
cvalue 0 1 99.99 0.28 90.00 100.00 100.00 100.00 100.00 ▁▁▁▁▇
Month 0 1 3.78 0.79 3.00 3.00 4.00 4.00 5.00 ▇▁▆▁▅
Day 0 1 15.74 8.84 3.00 8.00 16.00 23.00 30.00 ▇▅▅▅▆ 
Site3$`speed`= as.integer(Site3$`speed`)
ggbetweenstats(
  data = Site3,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Site 5_Weekday

Site5= subset(dat01, Site=="Site 5" & Weekday_Weekend=="Weekday")
dim(Site5)
## [1] 64800    16
skim(Site5)
Data summary
Name Site5
Number of rows 64800
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 5 0
measurement_tstamp 0 1 13 15 0 12960 0
DOW 0 1 6 9 0 5 0
Weekday_Weekend 0 1 7 7 0 1 0
Hours 0 1 11 11 0 24 0
PeakHr 0 1 7 11 0 3 0
Period 0 1 5 12 0 3 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 60.46 13.09 6.00 61.95 64.20 66.19 73.00 ▁▁▁▁▇
historical_average_speed 0 1 59.78 10.99 16.00 62.00 64.00 65.00 70.00 ▁▁▁▁▇
reference_speed 0 1 64.40 1.02 63.00 64.00 64.00 65.00 66.00 ▃▇▁▃▃
travel_time_minutes 0 1 0.38 0.39 0.16 0.19 0.21 0.64 7.68 ▇▁▁▁▁
confidence_score 0 1 30.00 0.05 20.00 30.00 30.00 30.00 30.00 ▁▁▁▁▇
cvalue 1 1 99.64 1.72 23.00 100.00 100.00 100.00 100.00 ▁▁▁▁▇
Month 0 1 3.91 0.78 3.00 3.00 4.00 5.00 5.00 ▇▁▇▁▆
Day 0 1 15.60 8.68 1.00 8.00 16.00 23.00 31.00 ▇▇▇▇▆ 
Site5$`speed`= as.integer(Site5$`speed`)
ggbetweenstats(
  data = Site5,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Site 5_Weekend

Site5= subset(dat01, Site=="Site 5" & Weekday_Weekend=="Weekend")
dim(Site5)
## [1] 25860    16
skim(Site5)
Data summary
Name Site5
Number of rows 25860
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 5 0
measurement_tstamp 0 1 13 15 0 5172 0
DOW 0 1 6 8 0 2 0
Weekday_Weekend 0 1 7 7 0 1 0
Hours 0 1 11 11 0 24 0
PeakHr 0 1 7 11 0 3 0
Period 0 1 5 6 0 2 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 65.47 2.68 38.19 63.96 65.6 67.33 74.19 ▁▁▁▇▃
historical_average_speed 0 1 65.92 1.82 61.00 65.00 66.0 67.00 71.00 ▂▇▇▂▂
reference_speed 0 1 64.40 1.02 63.00 64.00 64.0 65.00 66.00 ▃▇▁▃▃
travel_time_minutes 0 1 0.31 0.19 0.16 0.18 0.2 0.30 0.87 ▇▁▁▂▁
confidence_score 0 1 30.00 0.05 22.00 30.00 30.0 30.00 30.00 ▁▁▁▁▇
cvalue 0 1 99.98 0.41 85.00 100.00 100.0 100.00 100.00 ▁▁▁▁▇
Month 0 1 3.78 0.79 3.00 3.00 4.0 4.00 5.00 ▇▁▆▁▅
Day 0 1 15.74 8.84 3.00 8.00 16.0 23.00 30.00 ▇▅▅▅▆ 
Site5$`speed`= as.integer(Site5$`speed`)
ggbetweenstats(
  data = Site5,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Site 7_Weekday

Site7= subset(dat01, Site=="Site 7" & Weekday_Weekend=="Weekday")
dim(Site7)
## [1] 38880    16
skim(Site7)
Data summary
Name Site7
Number of rows 38880
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 3 0
measurement_tstamp 0 1 13 15 0 12960 0
DOW 0 1 6 9 0 5 0
Weekday_Weekend 0 1 7 7 0 1 0
Hours 0 1 11 11 0 24 0
PeakHr 0 1 7 11 0 3 0
Period 0 1 5 12 0 3 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 59.12 8.87 8.19 57.58 61.00 64.58 73.57 ▁▁▁▆▇
historical_average_speed 0 1 58.99 6.62 29.00 57.00 60.00 64.00 68.00 ▁▁▁▇▆
reference_speed 0 1 62.00 2.83 60.00 60.00 60.00 66.00 66.00 ▇▁▁▁▃
travel_time_minutes 0 1 0.67 0.47 0.19 0.24 0.44 1.24 10.16 ▇▁▁▁▁
confidence_score 0 1 30.00 0.00 30.00 30.00 30.00 30.00 30.00 ▁▁▇▁▁
cvalue 0 1 99.81 1.18 90.00 100.00 100.00 100.00 100.00 ▁▁▁▁▇
Month 0 1 3.91 0.78 3.00 3.00 4.00 5.00 5.00 ▇▁▇▁▆
Day 0 1 15.60 8.68 1.00 8.00 16.00 23.00 31.00 ▇▇▇▇▆ 
Site7$`speed`= as.integer(Site7$`speed`)
ggbetweenstats(
  data = Site7,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Site 7_Weekend

Site7= subset(dat01, Site=="Site 7" & Weekday_Weekend=="Weekend")
dim(Site7)
## [1] 15516    16
skim(Site7)
Data summary
Name Site7
Number of rows 15516
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 3 0
measurement_tstamp 0 1 13 15 0 5172 0
DOW 0 1 6 8 0 2 0
Weekday_Weekend 0 1 7 7 0 1 0
Hours 0 1 11 11 0 24 0
PeakHr 0 1 7 11 0 3 0
Period 0 1 5 6 0 2 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 61.59 5.26 18.67 59.14 61.78 65.17 71.40 ▁▁▁▆▇
historical_average_speed 0 1 62.25 3.24 55.00 60.00 61.00 66.00 69.00 ▁▇▃▃▂
reference_speed 0 1 62.00 2.83 60.00 60.00 60.00 66.00 66.00 ▇▁▁▁▃
travel_time_minutes 0 1 0.64 0.45 0.20 0.23 0.42 1.23 2.85 ▇▂▂▁▁
confidence_score 0 1 30.00 0.00 30.00 30.00 30.00 30.00 30.00 ▁▁▇▁▁
cvalue 0 1 99.89 0.95 90.00 100.00 100.00 100.00 100.00 ▁▁▁▁▇
Month 0 1 3.78 0.79 3.00 3.00 4.00 4.00 5.00 ▇▁▆▁▅
Day 0 1 15.74 8.84 3.00 8.00 16.00 23.00 30.00 ▇▅▅▅▆ 
Site7$`speed`= as.integer(Site7$`speed`)
ggbetweenstats(
  data = Site7,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Site 8_Weekday

Site8= subset(dat01, Site=="Site 8" & Weekday_Weekend=="Weekday")
dim(Site8)
## [1] 38880    16
skim(Site8)
Data summary
Name Site8
Number of rows 38880
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 3 0
measurement_tstamp 0 1 13 15 0 12960 0
DOW 0 1 6 9 0 5 0
Weekday_Weekend 0 1 7 7 0 1 0
Hours 0 1 11 11 0 24 0
PeakHr 0 1 7 11 0 3 0
Period 0 1 5 12 0 3 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 53.65 11.50 2.00 54.39 56.99 58.99 68.4 ▁▁▁▂▇
historical_average_speed 0 1 52.56 8.82 17.00 51.00 57.00 57.00 62.0 ▁▁▁▂▇
reference_speed 0 1 57.43 0.67 57.00 57.00 57.00 58.00 59.0 ▇▁▃▁▁
travel_time_minutes 0 1 0.35 0.30 0.08 0.10 0.32 0.43 9.2 ▇▁▁▁▁
confidence_score 0 1 30.00 0.00 30.00 30.00 30.00 30.00 30.0 ▁▁▇▁▁
cvalue 0 1 99.43 2.10 70.00 100.00 100.00 100.00 100.0 ▁▁▁▁▇
Month 0 1 3.91 0.78 3.00 3.00 4.00 5.00 5.0 ▇▁▇▁▆
Day 0 1 15.60 8.68 1.00 8.00 16.00 23.00 31.0 ▇▇▇▇▆ 
Site8$`speed`= as.integer(Site8$`speed`)
ggbetweenstats(
  data = Site8,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)

Site 8_Weekend

Site8= subset(dat01, Site=="Site 8" & Weekday_Weekend=="Weekend")
dim(Site8)
## [1] 15516    16
skim(Site8)
Data summary
Name Site8
Number of rows 15516
Number of columns 16
_______________________
Column type frequency:
character 8
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
tmc_code 0 1 9 9 0 3 0
measurement_tstamp 0 1 13 15 0 5172 0
DOW 0 1 6 8 0 2 0
Weekday_Weekend 0 1 7 7 0 1 0
Hours 0 1 11 11 0 24 0
PeakHr 0 1 7 11 0 3 0
Period 0 1 5 6 0 2 0
Site 0 1 6 6 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
speed 0 1 57.35 4.34 13.29 56.16 57.73 59.37 68.20 ▁▁▁▆▇
historical_average_speed 0 1 57.78 1.05 56.00 57.00 58.00 58.00 61.00 ▇▆▃▁▁
reference_speed 0 1 57.41 0.62 57.00 57.00 57.00 58.00 59.00 ▇▁▃▁▁
travel_time_minutes 0 1 0.29 0.15 0.08 0.10 0.32 0.42 1.68 ▇▃▁▁▁
confidence_score 0 1 30.00 0.00 30.00 30.00 30.00 30.00 30.00 ▁▁▇▁▁
cvalue 0 1 99.90 0.94 90.00 100.00 100.00 100.00 100.00 ▁▁▁▁▇
Month 0 1 3.78 0.79 3.00 3.00 4.00 4.00 5.00 ▇▁▆▁▅
Day 0 1 15.74 8.84 3.00 8.00 16.00 23.00 30.00 ▇▅▅▅▆ 
Site8$`speed`= as.integer(Site8$`speed`)
ggbetweenstats(
  data = Site8,
  x = Period,
  y = speed,
  type = "parametric",
  pairwise.comparisons = FALSE,   # hides pairwise comparisons
  pairwise.display = "none",      # just to reinforce
  p.adjust.method = "none",       # disables p-value correction display
  results.subtitle = FALSE,       # hides subtitle with test results
  messages = FALSE                # suppress output messages in console
)+theme_bw(base_size=16)