#Loading and Looking at the Data in R<\/p>\n
> taxi <- read.csv("C:\/Users\/doh1\/Desktop\/INFO 5550 QM\/Datasets\/2ndTerm2021_taxi-cancellation-case.csv")<\/p>\n
library(dplyr)<\/p>\n
library(ggplot2)<\/p>\n
library(adabag)<\/p>\n
library(rpart) <\/p>\n
library(caret)<\/p>\n
library(randomForest)<\/p>\n
#The percentage of Car Cancellation<\/p>\n
Car_Cancellation.Frequency <- table(taxi$Car_Cancellation)<\/p>\n
Car_Cancellation.Percent <- prop.table(table(taxi$Car_Cancellation)) * 100<\/p>\n
Car_Cancellation.Table <- cbind(Car_Cancellation.Frequency, Car_Cancellation.Percent)<\/p>\n
Car_Cancellation.Table<\/p>\n
class(taxi$Car_Cancellation)<\/p>\n
hist(taxi$Car_Cancellation,main =”Car Cancellation Histogram”, xlab=”Car Cancellation”)<\/p>\n
#Variable Handling <\/p>\n
class(taxi$Car_Cancellation)<\/p>\n
taxi$Car_Cancellation <- as.factor(taxi$Car_Cancellation)<\/p>\n
class(taxi$Car_Cancellation)<\/p>\n
# Used the values of to_lat, to_long, from_lat and from_long to calculate effective distance between #pick up and drop off points using the concept of Manhattan distance ()<\/p>\n
taxi$distance <- NA<\/p>\n
nonna <- which(!is.na(taxi$to_lat) & !is.na(taxi$to_long) & !is.na(taxi$from_lat) & !is.na(taxi$from_long))<\/p>\n
taxi$to_lat <- as.numeric(taxi$to_lat)<\/p>\n
taxi$to_long <- as.numeric(taxi$to_long)<\/p>\n
taxi$from_lat <- as.numeric(taxi$from_lat)<\/p>\n
taxi$from_long <- as.numeric(taxi$from_long)<\/p>\n
taxi$distance[nonna] <- sqrt((taxi$to_long[nonna] – taxi$from_long[nonna])^2 + (taxi$to_lat[nonna] – taxi$from_lat[nonna])^2)<\/p>\n
taxi$distance[is.na(taxi$distance)] <- mean(taxi$distance, na.rm = T)<\/p>\n
taxi$distance<\/p>\n
#let’s see how booking method influences cancellation<\/p>\n
taxi$booking_method <- NA<\/p>\n
taxi$booking_method[which(taxi$mobile_site_booking == 1)] <- "Mobile Site"<\/p>\n
taxi$booking_method[which(taxi$online_booking == 1)] <- "Online"<\/p>\n
taxi$booking_method[is.na(taxi$booking_method)] <- "Traditional"<\/p>\n
method % group_by(booking_method) %>% summarise(Cancellation = length(which(Car_Cancellation == 1))\/length(Car_Cancellation))<\/p>\n
# Cancellation rate by booking method, Bar plot that shows cancellation rate for each type of booking method<\/p>\n
ggplot(method, aes(y = Cancellation, x = booking_method, fill = booking_method)) + geom_bar(stat = “identity”, position = “Stack”) + scale_fill_brewer(palette = “Set1”) + theme_light() + ggtitle(“Cancellation rate by method of booking”)<\/p>\n
#Vehicle_model_id<\/p>\n
table(taxi$vehicle_model_id)<\/p>\n
aggregate(Car_Cancellation ~ vehicle_model_id, taxi, mean)<\/p>\n
taxi$vehicle_avg_cancelation<\/p>\n
taxi$vehicle_model_id[ taxi$vehicle_model_id %in% c(1,13,17,30,36,70,91) ] <- 100<\/p>\n
table(taxi$vehicle_model_id)<\/p>\n
taxi$vehicle_model_id[ taxi$vehicle_model_id %in% c(10,23,54,64,86,100) ] <- 101<\/p>\n
table(taxi$vehicle_model_id)<\/p>\n
length(taxi$vehicle_model_id)<\/p>\n
colnames(taxi)<\/p>\n
#Travel_type_id -> Dummy variable<\/p>\n
table(taxi$travel_type_id)<\/p>\n
length(taxi$travel_type_id)<\/p>\n
taxi$travel_type_id<\/p>\n
taxi$Longdistance <- ifelse(taxi$travel_type_id==1,1,0)<\/p>\n
taxi$Longdistance<\/p>\n
taxi$PointToPoint <- ifelse(taxi$travel_type_id==2,1,0)<\/p>\n
taxi$PointToPoint<\/p>\n
str(taxi)<\/p>\n
#Cancellation rate by type of car<\/p>\n
car % group_by(vehicle_model_id) %>% summarise(Rides = length(vehicle_model_id), Cancellations = sum(Car_Cancellation == 1), Cancellation_rate = mean(Car_Cancellation == 1)) %>% ungroup()<\/p>\n
car = 100) #Filter out cars with less than 100 rides<\/p>\n
car$vehicle_model_id = factor(car$vehicle_model_id)<\/p>\n
ggplot(car, aes(y = Cancellation_rate, x = vehicle_model_id)) + geom_bar(stat = “identity”, position = “Stack”) + theme_light() + ggtitle(“Cancellation rate by vehicle (min 100 rides)”) + xlab(“vehicle id”) + ylab(“Average cancellation rate”)<\/p>\n
rm(car)<\/p>\n
####Suggested predictive models#########<\/p>\n
set.seed(1) <\/p>\n
train.index <- sample(c(1:dim(taxi)[1]), dim(taxi)[1]*0.6) <\/p>\n
train.df <- taxi[train.index, ]<\/p>\n
valid.df <- taxi[-train.index, ]<\/p>\n
# Decision Trees<\/p>\n
tr <- rpart(Car_Cancellation ~ .,data=train.df, method="class",cp=0.00001,xval=5)<\/p>\n
pred <- predict(tr, valid.df, type = "class")<\/p>\n
confusionMatrix(pred, valid.df$ Car_Cancellation) <\/p>\n
# Bagging<\/p>\n
bag <- bagging(Car_Cancellation ~ ., data = train.df)<\/p>\n
pred <- predict(bag, valid.df, type = "class")<\/p>\n
confusionMatrix(as.factor(pred$class), valid.df$ Car_Cancellation) <\/p>\n
# Boosting<\/p>\n
boost <- boosting(Car_Cancellation ~ ., data = train.df, n.tree=200)<\/p>\n
pred <- predict(boost, valid.df, type = "class")<\/p>\n
confusionMatrix(as.factor(pred$class), valid.df$ Car_Cancellation) <\/p>\n
# Random Forest<\/p>\n
rf <- randomForest(as.factor(Car_Cancellation) ~ ., data = train.df, ntree = 200, mtry = 4, nodesize = 5, importance = TRUE) <\/p>\n
rf.pred <- predict(rf, valid.df)<\/p>\n
confusionMatrix(rf.pred, as.factor(valid.df$ Car_Cancellation))<\/p>\n","protected":false},"excerpt":{"rendered":"
#Loading and Looking at the Data in R > taxi <- read.csv("C:\/Users\/doh1\/Desktop\/INFO 5550 QM\/Datasets\/2ndTerm2021_taxi-cancellation-case.csv") library(dplyr) library(ggplot2) library(adabag) library(rpart) library(caret) library(randomForest) #The percentage of Car Cancellation Car_Cancellation.Frequency <- table(taxi$Car_Cancellation) Car_Cancellation.Percent <- prop.table(table(taxi$Car_Cancellation)) * 100 Car_Cancellation.Table <- cbind(Car_Cancellation.Frequency, Car_Cancellation.Percent) Car_Cancellation.Table class(taxi$Car_Cancellation) hist(taxi$Car_Cancellation,main =”Car Cancellation Histogram”, xlab=”Car Cancellation”) #Variable Handling class(taxi$Car_Cancellation) taxi$Car_Cancellation <- as.factor(taxi$Car_Cancellation) class(taxi$Car_Cancellation) # Used the […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[10],"class_list":["post-78810","post","type-post","status-publish","format-standard","hentry","category-research-paper-writing","tag-writing"],"_links":{"self":[{"href":"https:\/\/papersspot.com\/blog\/wp-json\/wp\/v2\/posts\/78810","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/papersspot.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/papersspot.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/papersspot.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/papersspot.com\/blog\/wp-json\/wp\/v2\/comments?post=78810"}],"version-history":[{"count":0,"href":"https:\/\/papersspot.com\/blog\/wp-json\/wp\/v2\/posts\/78810\/revisions"}],"wp:attachment":[{"href":"https:\/\/papersspot.com\/blog\/wp-json\/wp\/v2\/media?parent=78810"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/papersspot.com\/blog\/wp-json\/wp\/v2\/categories?post=78810"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/papersspot.com\/blog\/wp-json\/wp\/v2\/tags?post=78810"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}