library(ggplot2)
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, union
setwd("/Users/subasishdas1/Desktop/Data_Works/dec3_2017")
topc <- read.csv("Top Countermeasures.csv")
names(topc)
## [1] "Ori_Code" "Ori_Name" "Count" "Prop_Name"
head(topc[c(1,3)],15)
## Ori_Code Count
## 1 TECH_V2V_FL 244
## 2 TECH_I2V_FL 187
## 3 NOEFL 152
## 4 SPEED_FL 74
## 5 DUI_FL 55
## 6 SIGHT_DIST_FL 37
## 7 IDEAL_SIGNAL_FL 24
## 8 NEW_SIG_FL 24
## 9 RETROREFLECT_FL 23
## 10 RLVW_FL 21
## 11 SIG_PHASE_FL 21
## 12 CSW_FL 17
## 13 WARN_INT_DRV__MERGE_FL 16
## 14 NO_LEFT_SIGN_FL 11
## 15 INT_REDO_FL 10
data1 <- read.csv("MCSS_Imp_Variable_Cat_NwCntms1.csv")
data1$EF007 <- cut(data1$EF007, breaks=c(-1,1, 2,Inf),
labels=c("One Lane","Two Lane","Multi Lane"))
data1$CF006 <- cut(data1$CF006, breaks=c(-1,0, 1,Inf),
labels=c("Only MC", "One OV","Two or more OV"))
############################################## Countermeasure 1: TECH_V2V_FL
TECH_V2V_FL <- subset(data1, TECH_V2V_FL==1)
TECH_V2V_FL1 <- TECH_V2V_FL[c(2:19)]
names(TECH_V2V_FL1)
## [1] "CF003" "EF007" "CF006" "FF004" "CF011" "CF013" "EF005"
## [8] "CF010" "EF002" "EF003" "EF004" "EF006" "EF014" "EF015"
## [15] "EF017" "EF018" "EF022" "EF027a"
library(arules)
## Loading required package: Matrix
##
## Attaching package: 'arules'
## The following object is masked from 'package:dplyr':
##
## recode
## The following objects are masked from 'package:base':
##
## abbreviate, write
trans <- as(TECH_V2V_FL1, "transactions")
summary(trans)
## transactions as itemMatrix in sparse format with
## 244 rows (elements/itemsets/transactions) and
## 134 columns (items) and a density of 0.1341754
##
## most frequent items:
## CF006=One OV
## 207
## CF003=collision with other motor vehicle
## 192
## EF015=straight
## 179
## EF002=at-grade intersection area
## 177
## EF018=no traffic control
## 169
## (Other)
## 3463
##
## element (itemset/transaction) length distribution:
## sizes
## 17 18
## 5 239
##
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 17.00 18.00 18.00 17.98 18.00 18.00
##
## includes extended item information - examples:
## labels variables
## 1 CF003=collision with fixed object CF003
## 2 CF003=collision with non-fixed object CF003
## 3 CF003=collision with other motor vehicle CF003
## levels
## 1 collision with fixed object
## 2 collision with non-fixed object
## 3 collision with other motor vehicle
##
## includes extended transaction information - examples:
## transactionID
## 1 6
## 2 8
## 3 9
m <- data.frame(itemFrequency(trans, type = "relative"))
library(data.table)
##
## Attaching package: 'data.table'
## The following objects are masked from 'package:dplyr':
##
## between, first, last
m1 <- setDT(m, keep.rownames = TRUE)[]
colnames(m1)[1] <- "Attribute"
colnames(m1)[2] <- "Perc"
head(m1, 2)
## Attribute Perc
## 1: CF003=collision with fixed object 0.19262295
## 2: CF003=collision with non-fixed object 0.01229508
library(tidyr)
##
## Attaching package: 'tidyr'
## The following object is masked from 'package:Matrix':
##
## expand
m2 <-arrange(m1,desc(Perc))
m3 <- head(m2, 10)
m3$Perc1 <- round(m3$Perc*100,2)
ggplot(m3, aes(x = reorder(Attribute, -Perc1), y = Perc1), fill="#798E87") +
geom_bar(stat = "identity")+theme_bw(base_size = 16)+coord_flip()+labs(x="Attribute", y="Percentage")+geom_text(aes(label=Perc1), vjust=1, color="white", size=3.5)
### http://ethen8181.github.io/machine-learning/association_rule/R/apriori.html
rules <- apriori(
trans,
parameter = list( support = 0.25, confidence = 0.75, minlen = 2, maxlen = 3))
## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.75 0.1 1 none FALSE TRUE 5 0.25 2
## maxlen target ext
## 3 rules FALSE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 61
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[123 item(s), 244 transaction(s)] done [0.00s].
## sorting and recoding items ... [24 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3
## Warning in apriori(trans, parameter = list(support = 0.25, confidence =
## 0.75, : Mining stopped (maxlen reached). Only patterns up to a length of 3
## returned!
## done [0.00s].
## writing ... [284 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].
rules_dt <- data.table(lhs = labels(lhs(rules)),
rhs = labels(rhs(rules)),
quality(rules))[order(-lift),]
library(dplyr)
mm <- rules_dt %>% mutate_if(is.numeric, funs(round(., 3)))
DT::datatable(mm)
##################################################################
############################################ Countermeasure 2: TECH_I2V_FL
TECH_V2V_FL <- subset(data1, TECH_I2V_FL==1)
TECH_V2V_FL1 <- TECH_V2V_FL[c(2:19)]
names(TECH_V2V_FL1)
## [1] "CF003" "EF007" "CF006" "FF004" "CF011" "CF013" "EF005"
## [8] "CF010" "EF002" "EF003" "EF004" "EF006" "EF014" "EF015"
## [15] "EF017" "EF018" "EF022" "EF027a"
trans <- as(TECH_V2V_FL1, "transactions")
m <- data.frame(itemFrequency(trans, type = "relative"))
library(data.table)
m1 <- setDT(m, keep.rownames = TRUE)[]
colnames(m1)[1] <- "Attribute"
colnames(m1)[2] <- "Perc"
head(m1, 2)
## Attribute Perc
## 1: CF003=collision with fixed object 0.30481283
## 2: CF003=collision with non-fixed object 0.01604278
library(tidyr)
m2 <-arrange(m1,desc(Perc))
m3 <- head(m2, 10)
m3$Perc1 <- round(m3$Perc*100,2)
ggplot(m3, aes(x = reorder(Attribute, -Perc1), y = Perc1), fill="#798E87") +
geom_bar(stat = "identity")+theme_bw()+coord_flip()+labs(x="Attribute", y="Percentage")+geom_text(aes(label=Perc1), vjust=1, color="white", size=3.5)
rules <- apriori(
trans,
parameter = list( support = 0.25, confidence = 0.75, minlen = 2, maxlen = 3))
## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.75 0.1 1 none FALSE TRUE 5 0.25 2
## maxlen target ext
## 3 rules FALSE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 46
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[121 item(s), 187 transaction(s)] done [0.00s].
## sorting and recoding items ... [26 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3
## Warning in apriori(trans, parameter = list(support = 0.25, confidence =
## 0.75, : Mining stopped (maxlen reached). Only patterns up to a length of 3
## returned!
## done [0.00s].
## writing ... [179 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].
rules_dt <- data.table(lhs = labels(lhs(rules)),
rhs = labels(rhs(rules)),
quality(rules))[order(-lift),]
mm <- rules_dt %>% mutate_if(is.numeric, funs(round(., 3)))
DT::datatable(mm)
#########################################################
################################################### Countermeasure 3: SPEED_FL
TECH_V2V_FL <- subset(data1, SPEED_FL==1| SPEED_FL==2)
TECH_V2V_FL1 <- TECH_V2V_FL[c(2:19)]
names(TECH_V2V_FL1)
## [1] "CF003" "EF007" "CF006" "FF004" "CF011" "CF013" "EF005"
## [8] "CF010" "EF002" "EF003" "EF004" "EF006" "EF014" "EF015"
## [15] "EF017" "EF018" "EF022" "EF027a"
trans <- as(TECH_V2V_FL1, "transactions")
m <- data.frame(itemFrequency(trans, type = "relative"))
library(data.table)
m1 <- setDT(m, keep.rownames = TRUE)[]
colnames(m1)[1] <- "Attribute"
colnames(m1)[2] <- "Perc"
head(m1, 2)
## Attribute Perc
## 1: CF003=collision with fixed object 0.5362319
## 2: CF003=collision with non-fixed object 0.0000000
m2 <-arrange(m1,desc(Perc))
m3 <- head(m2, 10)
m3$Perc1 <- round(m3$Perc*100,2)
ggplot(m3, aes(x = reorder(Attribute, -Perc1), y = Perc1), fill="#798E87") +
geom_bar(stat = "identity")+theme_bw()+coord_flip()+labs(x="Attribute", y="Percentage")+geom_text(aes(label=Perc1), vjust=1, color="white", size=3.5)
rules <- apriori(
trans,
parameter = list( support = 0.25, confidence = 0.75, minlen = 2, maxlen = 3))
## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.75 0.1 1 none FALSE TRUE 5 0.25 2
## maxlen target ext
## 3 rules FALSE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 17
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[96 item(s), 69 transaction(s)] done [0.00s].
## sorting and recoding items ... [26 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3
## Warning in apriori(trans, parameter = list(support = 0.25, confidence =
## 0.75, : Mining stopped (maxlen reached). Only patterns up to a length of 3
## returned!
## done [0.00s].
## writing ... [158 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].
rules_dt <- data.table(lhs = labels(lhs(rules)),
rhs = labels(rhs(rules)),
quality(rules))[order(-lift),]
mm <- rules_dt %>% mutate_if(is.numeric, funs(round(., 3)))
DT::datatable(mm)
######################################################################
############################################## Countermeasure 4: DUI_FL
TECH_V2V_FL <- subset(data1, DUI_FL==1| DUI_FL==2| DUI_FL==3 )
TECH_V2V_FL1 <- TECH_V2V_FL[c(2:19)]
names(TECH_V2V_FL1)
## [1] "CF003" "EF007" "CF006" "FF004" "CF011" "CF013" "EF005"
## [8] "CF010" "EF002" "EF003" "EF004" "EF006" "EF014" "EF015"
## [15] "EF017" "EF018" "EF022" "EF027a"
trans <- as(TECH_V2V_FL1, "transactions")
m <- data.frame(itemFrequency(trans, type = "relative"))
library(data.table)
m1 <- setDT(m, keep.rownames = TRUE)[]
colnames(m1)[1] <- "Attribute"
colnames(m1)[2] <- "Perc"
head(m1, 2)
## Attribute Perc
## 1: CF003=collision with fixed object 0.5652174
## 2: CF003=collision with non-fixed object 0.0000000
library(dplyr)
library(tidyr)
m2 <-arrange(m1,desc(Perc))
m3 <- head(m2, 10)
m3$Perc1 <- round(m3$Perc*100,2)
ggplot(m3, aes(x = reorder(Attribute, -Perc1), y = Perc1), fill="#798E87") +
geom_bar(stat = "identity")+theme_bw()+coord_flip()+labs(x="Attribute", y="Percentage")+geom_text(aes(label=Perc1), vjust=1, color="white", size=3.5)
rules <- apriori(
trans,
parameter = list( support = 0.25, confidence = 0.75, minlen = 2, maxlen = 3))
## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.75 0.1 1 none FALSE TRUE 5 0.25 2
## maxlen target ext
## 3 rules FALSE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 11
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[92 item(s), 46 transaction(s)] done [0.00s].
## sorting and recoding items ... [27 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3
## Warning in apriori(trans, parameter = list(support = 0.25, confidence =
## 0.75, : Mining stopped (maxlen reached). Only patterns up to a length of 3
## returned!
## done [0.00s].
## writing ... [123 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].
rules_dt <- data.table(lhs = labels(lhs(rules)),
rhs = labels(rhs(rules)),
quality(rules))[order(-lift),]
mm <- rules_dt %>% mutate_if(is.numeric, funs(round(., 3)))
DT::datatable(mm)
##################################################################
############################################ Countermeasure 5: SIGHT_DIST_FL
TECH_V2V_FL <- subset(data1, SIGHT_DIST_FL==1)
TECH_V2V_FL1 <- TECH_V2V_FL[c(2:19)]
names(TECH_V2V_FL1)
## [1] "CF003" "EF007" "CF006" "FF004" "CF011" "CF013" "EF005"
## [8] "CF010" "EF002" "EF003" "EF004" "EF006" "EF014" "EF015"
## [15] "EF017" "EF018" "EF022" "EF027a"
trans <- as(TECH_V2V_FL1, "transactions")
m <- data.frame(itemFrequency(trans, type = "relative"))
library(data.table)
m1 <- setDT(m, keep.rownames = TRUE)[]
colnames(m1)[1] <- "Attribute"
colnames(m1)[2] <- "Perc"
head(m1, 2)
## Attribute Perc
## 1: CF003=collision with fixed object 0.21621622
## 2: CF003=collision with non-fixed object 0.02702703
library(dplyr)
library(tidyr)
m2 <-arrange(m1,desc(Perc))
m3 <- head(m2, 10)
m3$Perc1 <- round(m3$Perc*100,2)
ggplot(m3, aes(x = reorder(Attribute, -Perc1), y = Perc1), fill="#798E87") +
geom_bar(stat = "identity")+theme_bw()+coord_flip()+labs(x="Attribute", y="Percentage")+geom_text(aes(label=Perc1), vjust=1, color="white", size=3.5)
rules <- apriori(
trans,
parameter = list( support = 0.25, confidence = 0.75, minlen = 2, maxlen = 3))
## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.75 0.1 1 none FALSE TRUE 5 0.25 2
## maxlen target ext
## 3 rules FALSE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 9
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[88 item(s), 37 transaction(s)] done [0.00s].
## sorting and recoding items ... [27 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3
## Warning in apriori(trans, parameter = list(support = 0.25, confidence =
## 0.75, : Mining stopped (maxlen reached). Only patterns up to a length of 3
## returned!
## done [0.00s].
## writing ... [364 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].
rules_dt <- data.table(lhs = labels(lhs(rules)),
rhs = labels(rhs(rules)),
quality(rules))[order(-lift),]
mm <- rules_dt %>% mutate_if(is.numeric, funs(round(., 3)))
DT::datatable(mm)
#########################################################
################################################### Countermeasure 6: IDEAL_SIGNAL_FL
TECH_V2V_FL <- subset(data1, IDEAL_SIGNAL_FL==1)
TECH_V2V_FL1 <- TECH_V2V_FL[c(2:19)]
names(TECH_V2V_FL1)
## [1] "CF003" "EF007" "CF006" "FF004" "CF011" "CF013" "EF005"
## [8] "CF010" "EF002" "EF003" "EF004" "EF006" "EF014" "EF015"
## [15] "EF017" "EF018" "EF022" "EF027a"
trans <- as(TECH_V2V_FL1, "transactions")
m <- data.frame(itemFrequency(trans, type = "relative"))
library(data.table)
m1 <- setDT(m, keep.rownames = TRUE)[]
colnames(m1)[1] <- "Attribute"
colnames(m1)[2] <- "Perc"
head(m1, 2)
## Attribute Perc
## 1: CF003=collision with fixed object 0.08333333
## 2: CF003=collision with non-fixed object 0.00000000
m2 <-arrange(m1,desc(Perc))
m3 <- head(m2, 10)
m3$Perc1 <- round(m3$Perc*100,2)
ggplot(m3, aes(x = reorder(Attribute, -Perc1), y = Perc1), fill="#798E87") +
geom_bar(stat = "identity")+theme_bw()+coord_flip()+labs(x="Attribute", y="Percentage")+geom_text(aes(label=Perc1), vjust=1, color="white", size=3.5)
rules <- apriori(
trans,
parameter = list( support = 0.25, confidence = 0.75, minlen = 2, maxlen = 3))
## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.75 0.1 1 none FALSE TRUE 5 0.25 2
## maxlen target ext
## 3 rules FALSE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 6
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[64 item(s), 24 transaction(s)] done [0.00s].
## sorting and recoding items ... [28 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3
## Warning in apriori(trans, parameter = list(support = 0.25, confidence =
## 0.75, : Mining stopped (maxlen reached). Only patterns up to a length of 3
## returned!
## done [0.00s].
## writing ... [1437 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].
rules_dt <- data.table(lhs = labels(lhs(rules)),
rhs = labels(rhs(rules)),
quality(rules))[order(-lift),]
mm <- rules_dt %>% mutate_if(is.numeric, funs(round(., 3)))
DT::datatable(mm)
######################################################################
############################################## Countermeasure 7: NEW_SIG_FL
TECH_V2V_FL <- subset(data1, NEW_SIG_FL==1)
TECH_V2V_FL1 <- TECH_V2V_FL[c(2:19)]
names(TECH_V2V_FL1)
## [1] "CF003" "EF007" "CF006" "FF004" "CF011" "CF013" "EF005"
## [8] "CF010" "EF002" "EF003" "EF004" "EF006" "EF014" "EF015"
## [15] "EF017" "EF018" "EF022" "EF027a"
trans <- as(TECH_V2V_FL1, "transactions")
m <- data.frame(itemFrequency(trans, type = "relative"))
library(data.table)
m1 <- setDT(m, keep.rownames = TRUE)[]
colnames(m1)[1] <- "Attribute"
colnames(m1)[2] <- "Perc"
head(m1, 2)
## Attribute Perc
## 1: CF003=collision with fixed object 0.2083333
## 2: CF003=collision with non-fixed object 0.0000000
library(dplyr)
library(tidyr)
m2 <-arrange(m1,desc(Perc))
m3 <- head(m2, 10)
m3$Perc1 <- round(m3$Perc*100,2)
ggplot(m3, aes(x = reorder(Attribute, -Perc1), y = Perc1), fill="#798E87") +
geom_bar(stat = "identity")+theme_bw()+coord_flip()+labs(x="Attribute", y="Percentage")+geom_text(aes(label=Perc1), vjust=1, color="white", size=3.5)
rules <- apriori(
trans,
parameter = list( support = 0.25, confidence = 0.75, minlen = 2, maxlen = 3))
## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.75 0.1 1 none FALSE TRUE 5 0.25 2
## maxlen target ext
## 3 rules FALSE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 6
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[57 item(s), 24 transaction(s)] done [0.00s].
## sorting and recoding items ... [28 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3
## Warning in apriori(trans, parameter = list(support = 0.25, confidence =
## 0.75, : Mining stopped (maxlen reached). Only patterns up to a length of 3
## returned!
## done [0.00s].
## writing ... [1446 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].
rules_dt <- data.table(lhs = labels(lhs(rules)),
rhs = labels(rhs(rules)),
quality(rules))[order(-lift),]
mm <- rules_dt %>% mutate_if(is.numeric, funs(round(., 3)))
DT::datatable(mm)
##################################################################
############################################ Countermeasure 8: RETROREFLECT_FL
TECH_V2V_FL <- subset(data1, RETROREFLECT_FL==1)
TECH_V2V_FL1 <- TECH_V2V_FL[c(2:19)]
names(TECH_V2V_FL1)
## [1] "CF003" "EF007" "CF006" "FF004" "CF011" "CF013" "EF005"
## [8] "CF010" "EF002" "EF003" "EF004" "EF006" "EF014" "EF015"
## [15] "EF017" "EF018" "EF022" "EF027a"
trans <- as(TECH_V2V_FL1, "transactions")
m <- data.frame(itemFrequency(trans, type = "relative"))
library(data.table)
m1 <- setDT(m, keep.rownames = TRUE)[]
colnames(m1)[1] <- "Attribute"
colnames(m1)[2] <- "Perc"
head(m1, 2)
## Attribute Perc
## 1: CF003=collision with fixed object 0.6521739
## 2: CF003=collision with non-fixed object 0.0000000
library(dplyr)
library(tidyr)
m2 <-arrange(m1,desc(Perc))
m3 <- head(m2, 10)
m3$Perc1 <- round(m3$Perc*100,2)
ggplot(m3, aes(x = reorder(Attribute, -Perc1), y = Perc1), fill="#798E87") +
geom_bar(stat = "identity")+theme_bw()+coord_flip()+labs(x="Attribute", y="Percentage")+geom_text(aes(label=Perc1), vjust=1, color="white", size=3.5)
rules <- apriori(
trans,
parameter = list( support = 0.25, confidence = 0.75, minlen = 2, maxlen = 3))
## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.75 0.1 1 none FALSE TRUE 5 0.25 2
## maxlen target ext
## 3 rules FALSE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 5
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[76 item(s), 23 transaction(s)] done [0.00s].
## sorting and recoding items ... [31 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3
## Warning in apriori(trans, parameter = list(support = 0.25, confidence =
## 0.75, : Mining stopped (maxlen reached). Only patterns up to a length of 3
## returned!
## done [0.00s].
## writing ... [501 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].
rules_dt <- data.table(lhs = labels(lhs(rules)),
rhs = labels(rhs(rules)),
quality(rules))[order(-lift),]
mm <- rules_dt %>% mutate_if(is.numeric, funs(round(., 3)))
DT::datatable(mm)
#########################################################
################################################### Countermeasure 9: RETROREFLECT_FL
TECH_V2V_FL <- subset(data1, RETROREFLECT_FL==1)
TECH_V2V_FL1 <- TECH_V2V_FL[c(2:19)]
names(TECH_V2V_FL1)
## [1] "CF003" "EF007" "CF006" "FF004" "CF011" "CF013" "EF005"
## [8] "CF010" "EF002" "EF003" "EF004" "EF006" "EF014" "EF015"
## [15] "EF017" "EF018" "EF022" "EF027a"
trans <- as(TECH_V2V_FL1, "transactions")
m <- data.frame(itemFrequency(trans, type = "relative"))
library(data.table)
m1 <- setDT(m, keep.rownames = TRUE)[]
colnames(m1)[1] <- "Attribute"
colnames(m1)[2] <- "Perc"
head(m1, 2)
## Attribute Perc
## 1: CF003=collision with fixed object 0.6521739
## 2: CF003=collision with non-fixed object 0.0000000
m2 <-arrange(m1,desc(Perc))
m3 <- head(m2, 10)
m3$Perc1 <- round(m3$Perc*100,2)
ggplot(m3, aes(x = reorder(Attribute, -Perc1), y = Perc1), fill="#798E87") +
geom_bar(stat = "identity")+theme_bw()+coord_flip()+labs(x="Attribute", y="Percentage")+geom_text(aes(label=Perc1), vjust=1, color="white", size=3.5)
rules <- apriori(
trans,
parameter = list( support = 0.25, confidence = 0.75, minlen = 2, maxlen = 3))
## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.75 0.1 1 none FALSE TRUE 5 0.25 2
## maxlen target ext
## 3 rules FALSE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 5
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[76 item(s), 23 transaction(s)] done [0.00s].
## sorting and recoding items ... [31 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3
## Warning in apriori(trans, parameter = list(support = 0.25, confidence =
## 0.75, : Mining stopped (maxlen reached). Only patterns up to a length of 3
## returned!
## done [0.00s].
## writing ... [501 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].
rules_dt <- data.table(lhs = labels(lhs(rules)),
rhs = labels(rhs(rules)),
quality(rules))[order(-lift),]
mm <- rules_dt %>% mutate_if(is.numeric, funs(round(., 3)))
DT::datatable(mm)
######################################################################
############################################## Countermeasure 10: RLVW_FL
TECH_V2V_FL <- subset(data1, RLVW_FL==1)
TECH_V2V_FL1 <- TECH_V2V_FL[c(2:19)]
names(TECH_V2V_FL1)
## [1] "CF003" "EF007" "CF006" "FF004" "CF011" "CF013" "EF005"
## [8] "CF010" "EF002" "EF003" "EF004" "EF006" "EF014" "EF015"
## [15] "EF017" "EF018" "EF022" "EF027a"
trans <- as(TECH_V2V_FL1, "transactions")
m <- data.frame(itemFrequency(trans, type = "relative"))
library(data.table)
m1 <- setDT(m, keep.rownames = TRUE)[]
colnames(m1)[1] <- "Attribute"
colnames(m1)[2] <- "Perc"
head(m1, 2)
## Attribute Perc
## 1: CF003=collision with fixed object 0.0952381
## 2: CF003=collision with non-fixed object 0.0000000
library(dplyr)
library(tidyr)
m2 <-arrange(m1,desc(Perc))
m3 <- head(m2, 10)
m3$Perc1 <- round(m3$Perc*100,2)
ggplot(m3, aes(x = reorder(Attribute, -Perc1), y = Perc1), fill="#798E87") +
geom_bar(stat = "identity")+theme_bw()+coord_flip()+labs(x="Attribute", y="Percentage")+geom_text(aes(label=Perc1), vjust=1, color="white", size=3.5)
rules <- apriori(
trans,
parameter = list( support = 0.25, confidence = 0.75, minlen = 2, maxlen = 3))
## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.75 0.1 1 none FALSE TRUE 5 0.25 2
## maxlen target ext
## 3 rules FALSE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 5
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[73 item(s), 21 transaction(s)] done [0.00s].
## sorting and recoding items ... [22 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3
## Warning in apriori(trans, parameter = list(support = 0.25, confidence =
## 0.75, : Mining stopped (maxlen reached). Only patterns up to a length of 3
## returned!
## done [0.00s].
## writing ... [779 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].
rules_dt <- data.table(lhs = labels(lhs(rules)),
rhs = labels(rhs(rules)),
quality(rules))[order(-lift),]
mm <- rules_dt %>% mutate_if(is.numeric, funs(round(., 3)))
DT::datatable(mm)
##################################################################
############################################ Countermeasure 11: SIG_PHASE_FL
TECH_V2V_FL <- subset(data1,SIG_PHASE_FL==1)
TECH_V2V_FL1 <- TECH_V2V_FL[c(2:19)]
names(TECH_V2V_FL1)
## [1] "CF003" "EF007" "CF006" "FF004" "CF011" "CF013" "EF005"
## [8] "CF010" "EF002" "EF003" "EF004" "EF006" "EF014" "EF015"
## [15] "EF017" "EF018" "EF022" "EF027a"
trans <- as(TECH_V2V_FL1, "transactions")
m <- data.frame(itemFrequency(trans, type = "relative"))
library(data.table)
m1 <- setDT(m, keep.rownames = TRUE)[]
colnames(m1)[1] <- "Attribute"
colnames(m1)[2] <- "Perc"
head(m1, 2)
## Attribute Perc
## 1: CF003=collision with fixed object 0.0952381
## 2: CF003=collision with non-fixed object 0.0000000
library(dplyr)
library(tidyr)
m2 <-arrange(m1,desc(Perc))
m3 <- head(m2, 10)
m3$Perc1 <- round(m3$Perc*100,2)
ggplot(m3, aes(x = reorder(Attribute, -Perc1), y = Perc1), fill="#798E87") +
geom_bar(stat = "identity")+theme_bw()+coord_flip()+labs(x="Attribute", y="Percentage")+geom_text(aes(label=Perc1), vjust=1, color="white", size=3.5)
rules <- apriori(
trans,
parameter = list( support = 0.25, confidence = 0.75, minlen = 2, maxlen = 3))
## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.75 0.1 1 none FALSE TRUE 5 0.25 2
## maxlen target ext
## 3 rules FALSE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 5
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[67 item(s), 21 transaction(s)] done [0.00s].
## sorting and recoding items ... [21 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3
## Warning in apriori(trans, parameter = list(support = 0.25, confidence =
## 0.75, : Mining stopped (maxlen reached). Only patterns up to a length of 3
## returned!
## done [0.00s].
## writing ... [707 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].
rules_dt <- data.table(lhs = labels(lhs(rules)),
rhs = labels(rhs(rules)),
quality(rules))[order(-lift),]
mm <- rules_dt %>% mutate_if(is.numeric, funs(round(., 3)))
DT::datatable(mm)
#########################################################
################################################### Countermeasure 12: CSW_FL
TECH_V2V_FL <- subset(data1, CSW_FL==1)
TECH_V2V_FL1 <- TECH_V2V_FL[c(2:19)]
names(TECH_V2V_FL1)
## [1] "CF003" "EF007" "CF006" "FF004" "CF011" "CF013" "EF005"
## [8] "CF010" "EF002" "EF003" "EF004" "EF006" "EF014" "EF015"
## [15] "EF017" "EF018" "EF022" "EF027a"
trans <- as(TECH_V2V_FL1, "transactions")
m <- data.frame(itemFrequency(trans, type = "relative"))
library(data.table)
m1 <- setDT(m, keep.rownames = TRUE)[]
colnames(m1)[1] <- "Attribute"
colnames(m1)[2] <- "Perc"
head(m1, 2)
## Attribute Perc
## 1: CF003=collision with fixed object 0.58823529
## 2: CF003=collision with non-fixed object 0.05882353
m2 <-arrange(m1,desc(Perc))
m3 <- head(m2, 10)
m3$Perc1 <- round(m3$Perc*100,2)
ggplot(m3, aes(x = reorder(Attribute, -Perc1), y = Perc1), fill="#798E87") +
geom_bar(stat = "identity")+theme_bw()+coord_flip()+labs(x="Attribute", y="Percentage")+geom_text(aes(label=Perc1), vjust=1, color="white", size=3.5)
rules <- apriori(
trans,
parameter = list( support = 0.25, confidence = 0.75, minlen = 2, maxlen = 3))
## Apriori
##
## Parameter specification:
## confidence minval smax arem aval originalSupport maxtime support minlen
## 0.75 0.1 1 none FALSE TRUE 5 0.25 2
## maxlen target ext
## 3 rules FALSE
##
## Algorithmic control:
## filter tree heap memopt load sort verbose
## 0.1 TRUE TRUE FALSE TRUE 2 TRUE
##
## Absolute minimum support count: 4
##
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[73 item(s), 17 transaction(s)] done [0.00s].
## sorting and recoding items ... [21 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3
## Warning in apriori(trans, parameter = list(support = 0.25, confidence =
## 0.75, : Mining stopped (maxlen reached). Only patterns up to a length of 3
## returned!
## done [0.00s].
## writing ... [550 rule(s)] done [0.00s].
## creating S4 object ... done [0.00s].
rules_dt <- data.table(lhs = labels(lhs(rules)),
rhs = labels(rhs(rules)),
quality(rules))[order(-lift),]
mm <- rules_dt %>% mutate_if(is.numeric, funs(round(., 3)))
DT::datatable(mm)
######################################################################