Last active
January 15, 2019 09:55
-
-
Save ridwanbejo/1e6c0e5fd0a972e62d3ee6e0080f374e to your computer and use it in GitHub Desktop.
naive bayes classification with cv
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(e1071) | |
library(gmodels) | |
library(caret) | |
# 1. Load dataset from CSV | |
bank_csv <- read.csv("./Downloads/bank-additional/bank-additional-full.csv", header=TRUE, sep=";") | |
bank_df <- as.data.frame(bank_csv[1:32951,]) | |
summary(bank_df) | |
# 2. Do the preprocessing | |
# 2.1. todo | |
# 2.2. todo | |
# 2.3. todo | |
# 2.4. todo | |
# 3. Train the model | |
model <- naiveBayes(bank_df, bank_df$y, 'nb', laplace=1, trControl=trainControl(method='cv',number=50)) | |
# 4. Test the model | |
term_deposit_test <- predict(model, bank_csv[32952:41188,1:20]) | |
# 5. Evaluate the model | |
CrossTable(term_deposit_test, bank_csv[32952:41188,21], prop.chisq = FALSE, prop.t = FALSE, dnn = c('predicted', 'actual')) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment