North Carolina Rural Interstate

Subasish Das and Chaolun Ma

2018-11-12

North Carolina Conflated Data (Rural Interstate)

library(data.table)
library(dplyr)
library(wavelets)
library(tidyr)
library(naniar)
library(stringr)
library(ggplot2)
library(DT)
library(lubridate)
library(ggpubr)



setwd("/scratch/user/cma16/Task4_Deliverable2/NCprocess4/AllCrash/FacilityBased/")
load("NC_Rural_Principle_Arterial_Interstate_1_TMC_TT_SI_reduce_withCrash.rData")
mytype = 'RI'
setwd(paste0("/scratch/user/cma16/Task4_Deliverable2/NCprocess4/AllCrash/FacilityBased/",mytype))

df_RI <- b02a
dim(df_RI)
## [1] 2261664      30
### Calculating Speed
df_RI$spd_av = 3600*df_RI$TMC_length/df_RI$Travel_TIME_ALL_VEHICLES/5280
df_RI$spd_pv = 3600*df_RI$TMC_length/df_RI$Travel_TIME_PASSENGER_VEHICLES/5280
df_RI$spd_ft = 3600*df_RI$TMC_length/df_RI$Travel_TIME_FREIGHT_TRUCKS/5280


### Month, Day
df_RI$date <- as.character(df_RI$DATE)
df_RI$date <- str_pad(df_RI$DATE, 8, pad = "0")
df_RI$Month <- substr(df_RI$date, start = 1, stop = 2)
df_RI$Day   <- substr(df_RI$date, start = 3, stop = 4)
df_RI$Year  <- substr(df_RI$date, start = 5, stop = 8)

head(df_RI,2)
##           TimeStamp       TMC    DATE EPOCH15 Travel_TIME_ALL_VEHICLES
## 1: 125N04870_0101_0 125N04870 1012015       0                       NA
## 2: 125N04870_0101_1 125N04870 1012015       1                       72
##    Travel_TIME_PASSENGER_VEHICLES Travel_TIME_FREIGHT_TRUCKS TMC_length
## 1:                             NA                         NA   7851.174
## 2:                             72                         NA   7851.174
##    ave_aadt ave_wtdsgspd ave_medwid ave_peaklane ave_row ave_sur_wid
## 1: 115852.4           NA    10.5365           NA     160          36
## 2: 115852.4           NA    10.5365           NA     160          36
##    ave_no_lanes ave_spd_limt ave_rodwycls ave_rshldwid FC TER ACC MED
## 1:            2           45            8      5.61569  1   2   F  St
## 2:            2           45            8      5.61569  1   2   F  St
##    Total K A B C  O DAYMTH Crash   spd_av   spd_pv spd_ft     date Month
## 1:    34 0 2 0 8 24   0101     0       NA       NA     NA 01012015    01
## 2:    34 0 2 0 8 24   0101     0 74.34824 74.34824     NA 01012015    01
##    Day Year
## 1:  01 2015
## 2:  01 2015
#####
df1= df_RI[,c("spd_av","spd_pv","spd_ft")]
df2= df_RI[,c("date","spd_av","spd_pv","spd_ft")]
df3= df_RI[,c("Month","spd_av","spd_pv","spd_ft")]
df4= df_RI[,c("Day","spd_av","spd_pv","spd_ft")]
df5= df_RI[,c("Year","spd_av","spd_pv","spd_ft")]


######################################################
ConvEpoc2HM <- function(x) {
  # for a given epoc number, get its hour:min
  yy <- x*15
  y.hr <- yy %/% 60
  y.min <- yy %% 60
  x <- paste(str_pad(y.hr, 2, side = 'left', pad='0'), 
                     str_pad(y.min, 2, side = 'left', pad='0'), 
                     '00', sep = ':')
}

df_RI$Hour1 <- ConvEpoc2HM(df_RI$EPOCH15)
DATE4 <- paste(strptime(df_RI$date, format = "%m%d%Y", tz =""), df_RI$Hour1, sep = ' ')
df_RI$PCT_TIME <- as.POSIXct(DATE4, tz ="", format = "%Y-%m-%d %H:%M:%OS")
df_RI$Hour <- strftime(df_RI$PCT_TIME, format="%H")
df_RI$DOW <- wday(df_RI$PCT_TIME, label = TRUE)


df6= df_RI[,c("Hour","spd_av","spd_pv","spd_ft")]
df7= df_RI[,c("DOW","spd_av","spd_pv","spd_ft")]

################################################################





#### Operating Speed by Month
long <- melt(df3, id.vars = c("Month"))
ggviolin(long, "Month", "value", fill = "Month",
   add = "boxplot", add.params = list(fill = "white"))+coord_flip()+facet_grid(. ~ "variable")+
geom_hline(yintercept=50, linetype="dashed", 
                color = "red", size=1)+labs(title="Operating Speed by Month", x="Month",y="Speed (mph)")+ theme(legend.position="none")
## Warning: Removed 4773236 rows containing non-finite values (stat_ydensity).
## Warning: Removed 4773236 rows containing non-finite values (stat_boxplot).

#### Operating Speed by Month [All Vehicles]
long <- melt(df3[,c(1,2)], id.vars = c("Month"))
ggviolin(long, "Month", "value", fill = "Month",
         add = "boxplot", add.params = list(fill = "white"))+coord_flip()+
  geom_hline(yintercept=45, linetype="dashed", 
             color = "red", size=1)+labs(title="Operating Speed (All vehicles) by Month", x="Month",y="Speed (mph)")+ theme(legend.position="none")
## Warning: Removed 1406080 rows containing non-finite values (stat_ydensity).
## Warning: Removed 1406080 rows containing non-finite values (stat_boxplot).

#### Operating Speed by Month [Passenger Cars]
long <- melt(df3[,c(1,3)], id.vars = c("Month"))
ggviolin(long, "Month", "value", fill = "Month",
         add = "boxplot", add.params = list(fill = "white"))+coord_flip()+
  geom_hline(yintercept=43, linetype="dashed", 
             color = "red", size=1)+labs(title="Operating Speed (Passenger Cars) by Month", x="Month",y="Speed (mph)")+ theme(legend.position="none")
## Warning: Removed 1501236 rows containing non-finite values (stat_ydensity).
## Warning: Removed 1501236 rows containing non-finite values (stat_boxplot).

#### Operating Speed by Month [Fright Trucks]
long <- melt(df3[,c(1,4)], id.vars = c("Month"))
ggviolin(long, "Month", "value", fill = "Month",
         add = "boxplot", add.params = list(fill = "white"))+coord_flip()+
  geom_hline(yintercept=60, linetype="dashed", 
             color = "red", size=1)+labs(title="Operating Speed (Freight Trucks) by Month", x="Month",y="Speed (mph)")+ theme(legend.position="none")
## Warning: Removed 1865920 rows containing non-finite values (stat_ydensity).
## Warning: Removed 1865920 rows containing non-finite values (stat_boxplot).

gg_miss_upset(df1)

gg_miss_var(df3, facet = Month, show_pct = TRUE)

gg_miss_var(df4, facet = Day, show_pct = TRUE)

gg_miss_var(df5, facet = Year, show_pct = TRUE)

gg_miss_var(df2, facet = date, show_pct = TRUE)

### Missingness by Date
df2a <- df2 %>%
  group_by(date) %>%
  miss_var_summary()
datatable(
  df2a, extensions = 'Buttons', options = list(
    dom = 'Bfrtip',
    buttons = c('csv', 'excel', 'print')
  )
)
### Missingness by Month
df3a <- df3 %>%
  group_by(Month) %>%
  miss_var_summary()
datatable(
  df3a, extensions = 'Buttons', options = list(
    dom = 'Bfrtip',
    buttons = c('csv', 'excel', 'print')
  )
)
### Missingness by Day
df4a <- df4 %>%
  group_by(Day) %>%
  miss_var_summary()
datatable(
  df4a, extensions = 'Buttons', options = list(
    dom = 'Bfrtip',
    buttons = c('csv', 'excel', 'print')
  )
)
### Missingness by Year
df5a <- df5 %>%
  group_by(Year) %>%
  miss_var_summary()
datatable(
  df5a, extensions = 'Buttons', options = list(
    dom = 'Bfrtip',
    buttons = c('csv', 'excel', 'print')
  )
)
### TMC Level
tmc1 <- df_RI[,c('TMC')] %>%
  group_by(TMC) %>%
  summarize(Count=n())
datatable(
  tmc1, extensions = 'Buttons', options = list(
    dom = 'Bfrtip',
    buttons = c('csv', 'excel', 'print')
  )
)
#### Operating Speed by Hour
long <- melt(df6, id.vars = c("Hour"))
long$Hour <- as.factor(long$Hour)
ggviolin(long, "Hour", "value", fill = "Hour",
   add = "boxplot", add.params = list(fill = "white"))+coord_flip()+
geom_hline(yintercept=50, linetype="dashed", 
                color = "red", size=1)+labs(title="Operating Speed by Hour", x="Hour",y="Speed (mph)")+ theme(legend.position="none")
## Warning: Removed 4773236 rows containing non-finite values (stat_ydensity).
## Warning: Removed 4773236 rows containing non-finite values (stat_boxplot).

#### Operating Speed by DOW
long <- melt(df7, id.vars = c("DOW"))
ggviolin(long, "DOW", "value", fill = "DOW",
   add = "boxplot", add.params = list(fill = "white"))+coord_flip()+
geom_hline(yintercept=50, linetype="dashed", 
                color = "red", size=1)+labs(title="Operating Speed by DOW", x="Day of Week",y="Speed (mph)")+ theme(legend.position="none")
## Warning: Removed 4773236 rows containing non-finite values (stat_ydensity).

## Warning: Removed 4773236 rows containing non-finite values (stat_boxplot).

gg_miss_var(df6, facet = Hour, show_pct = TRUE)

### Missingness by Hour
df6a <- df6 %>%
  group_by(Hour) %>%
  miss_var_summary()
datatable(
  df6a, extensions = 'Buttons', options = list(
    dom = 'Bfrtip',
    buttons = c('csv', 'excel', 'print')
  )
)
### Missingness by DOW
df7a <- df7 %>%
  group_by(DOW) %>%
  miss_var_summary()
datatable(
  df7a, extensions = 'Buttons', options = list(
    dom = 'Bfrtip',
    buttons = c('csv', 'excel', 'print')
  )
)