I have created a model in KERAS R, using a data table, with the following script:
data <- 'csv filename' data %<>% mutate_if(is.factor, as.numeric) data <- data[, c(1:35,30)] data <- data[ -c(31) ] data <- as.matrix(data) set.seed(1234) ind <- sample(2, nrow(data), replace = T, prob = c(.7, .3)) training <- data[ind==1,6:29] test <- data[ind==2,6:29] trainingtarget <- data[ind==1,31] testtarget <- data[ind==2,31] m <- colMeans(training) s <- apply(training, 2, sd) training <- scale(training, center = m, scale = s) test <- scale(test, center = m, scale = s) model <- keras_model_sequential() model %>% layer_dense(units = 10, activation = 'relu', input_shape = c(24)) %>% layer_dense(units = 5, activation = 'relu') %>% layer_dense (units = 1) model %>% compile(loss = 'mse', optimizer = 'rmsprop', metrics = 'mae') mymodel <- model %>% fit(training, trainingtarget, epochs = 100, batch_size = 32, validation_spit = 0.2)
I use this model to make predictions on another table, called 'newtest', using the following command:
y_data_pred=predict_classes(model, newdata) glimpse(y_data_pred)
I have installed LIME into R Studio, however I am struggling to get the correct LIME script syntax to explain my model predictions, to plot these in a chart, etc.
Any help would be greatly appreciated.