Hi everybody!
I wrote a script using xgboost to predict a new class. With iris it works like this:
library(xgboost)
library(tidyverse)
library(caret)
library(readxl)
library(caret)
library(data.table)
library(mlr)
data <- iris
righe_train <- sample(nrow(data),nrow(data)*0.8)
train <- data[righe_train,]
test <- data[-righe_train,]
setDT(train)
setDT(test)
labels <- train$Species
ts_label <- test$Species
new_tr <- model.matrix(~.+0,data = train[,-c("Species"),with=F])
new_ts <- model.matrix(~.+0,data = test[,-c("Species"),with=F])
#convert factor to numeric
labels <- as.numeric(labels)-1
ts_label <- as.numeric(ts_label)-1
class(new_tr)
#preparing matrix
dtrain <- xgb.DMatrix(data = new_tr,label = labels)
dtest <- xgb.DMatrix(data = new_ts,label=ts_label)
#default parameters
params <- list(booster = "gbtree",
objective = "multi:softmax",
num_class = 3,
eta=0.3,
gamma=0,
max_depth=6,
min_child_weight=1,
subsample=1,
colsample_bytree=1)
xgbcv <- xgb.cv( params = params,
data = dtrain,
nrounds = 100,
nfold = 5,
showsd = T,
stratified = T,
print_every_n = 10,
early_stopping_round = 20,
maximize = F)
##best iteration
min(xgbcv$test.error.mean)
#first default - model training
xgb1 <- xgb.train (params = params,
data = dtrain,
nrounds = 21,
watchlist = list(val=dtest,train=dtrain),
print.every.n = 10,
early.stop.round = 10,
maximize = F ,
merror = "error")
# eval_metric = "error")
#model prediction
xgbpred <- predict (xgb1,dtest)
xgbpred <- ifelse (xgbpred > 0.5,1,0)
#confusion matrix
factors_both <- as.factor(c(xgbpred, ts_label))
xgbpred_f <- factors_both[1:length(xgbpred)]
ts_label_f <- factors_both[length(xgbpred)+1:length(xgbpred)*2]
confusionMatrix (xgbpred_f,ts_label_f)
#new record
(new_record_raw <- c(5.3,3.2,2.0,0.2))
(new_record_mat <- matrix(new_record_raw,nrow = 1))
(new_record_dmat <- xgb.DMatrix(data = new_record_mat))
predict(xgb1,newdata=new_record_dmat)
but when I run the part > #new record using my dataset, I have this error:
Error in predict.xgb.Booster(xgb1, newdata = xgb.DMatrix(data = as.matrix(test))) :
Feature names stored in `object` and `newdata` are different!
Why I have this error? Where could I have gone wrong? can anyone suggest me some new ideas?