SVM is not generating forecast using R

120 views Asked by At

I have sales data for 5 different product along with weather information.To read the data, we have daily sales data at a particular store and daily weather information like what is the temperature, average speed of the area where store is located. I am using Support Vector Machine for prediction. It works well for all the products except one. Its giving me following error:

tunedModelLOG
named numeric(0)

Below is the code:

# load the packages
library(zoo) 
library(MASS)
library(e1071)
library(rpart)
library(caret)


normalize <- function(x) {
  a <- min(x, na.rm=TRUE)
  b <- max(x, na.rm=TRUE)
  (x - a)/(b - a)
}

# Define the train and test data

test_data <- train[1:23,]
train_data<-train[24:nrow(train),]

# Define the factors for the categorical data

names<-c("year","month","dom","holiday","blackfriday","after1","back1","after2","back2","after3","back3","is_weekend","weeday")
train_data[,names]<- lapply(train_data[,names],factor)
test_data[,names] <- lapply(test_data[,names],factor)

# Normalized the continuous data
normalized<-c("snowfall","depart","cool","preciptotal","sealevel","stnpressure","resultspeed","resultdir")
train_data[,normalized] <- data.frame(lapply(train_data[,normalized], normalize))
test_data[,normalized] <- data.frame(lapply(test_data[,normalized], normalize))

# Define the same level in train and test data
levels(test_data$month)<-levels(train_data$month)
levels(test_data$dom)<-levels(train_data$dom)
levels(test_data$year)<-levels(train_data$year)
levels(test_data$after1)<-levels(train_data$after1)
levels(test_data$after2)<-levels(train_data$after2)
levels(test_data$after3)<-levels(train_data$after3)
levels(test_data$back1)<-levels(train_data$back1)
levels(test_data$back2)<-levels(train_data$back2)
levels(test_data$back3)<-levels(train_data$back3)
levels(test_data$holiday)<-levels(train_data$holiday)
levels(test_data$is_weekend)<-levels(train_data$is_weekend)
levels(test_data$blackfriday)<-levels(train_data$blackfriday)
levels(test_data$is_weekend)<-levels(train_data$is_weekend)
levels(test_data$weeday)<-levels(train_data$weeday)

# Fit the SVM model and tune the parameters

svmReFitLOG=tune(svm,logunits~year+month+dom+holiday+blackfriday+after1+after2+after3+back1+back2+back3+is_weekend+depart+cool+preciptotal+sealevel+stnpressure+resultspeed+resultdir,data=train_data,ranges = list(epsilon = c(0,0.1,0.01,0.001), cost = 2^(2:9)))
retunedModeLOG <- svmReFitLOG$best.model
tunedModelLOG <- predict(retunedModeLOG,test_data)

Working file is available at the below link https://drive.google.com/file/d/0BzCJ8ytbECPMVVJ1UUg2RHhQNFk/view?usp=sharing

What I am doing wrong? I would appreciate any kind of help. Thanks in advance.

0

There are 0 answers