wehub-resource-sync
101 lines
3.7 KiB
R
101 lines
3.7 KiB
R
# Here we are going to try training a model with categorical features
|
|
|
|
# Load libraries
|
|
library(data.table)
|
|
library(lightgbm)
|
|
|
|
# Load data and look at the structure
|
|
#
|
|
# Classes 'data.table' and 'data.frame': 4521 obs. of 17 variables:
|
|
# $ age : int 30 33 35 30 59 35 36 39 41 43 ...
|
|
# $ job : chr "unemployed" "services" "management" "management" ...
|
|
# $ marital : chr "married" "married" "single" "married" ...
|
|
# $ education: chr "primary" "secondary" "tertiary" "tertiary" ...
|
|
# $ default : chr "no" "no" "no" "no" ...
|
|
# $ balance : int 1787 4789 1350 1476 0 747 307 147 221 -88 ...
|
|
# $ housing : chr "no" "yes" "yes" "yes" ...
|
|
# $ loan : chr "no" "yes" "no" "yes" ...
|
|
# $ contact : chr "cellular" "cellular" "cellular" "unknown" ...
|
|
# $ day : int 19 11 16 3 5 23 14 6 14 17 ...
|
|
# $ month : chr "oct" "may" "apr" "jun" ...
|
|
# $ duration : int 79 220 185 199 226 141 341 151 57 313 ...
|
|
# $ campaign : int 1 1 1 4 1 2 1 2 2 1 ...
|
|
# $ pdays : int -1 339 330 -1 -1 176 330 -1 -1 147 ...
|
|
# $ previous : int 0 4 1 0 0 3 2 0 0 2 ...
|
|
# $ poutcome : chr "unknown" "failure" "failure" "unknown" ...
|
|
# $ y : chr "no" "no" "no" "no" ...
|
|
data(bank, package = "lightgbm")
|
|
str(bank)
|
|
|
|
# We are dividing the dataset into two: one train, one validation
|
|
bank_train <- bank[1L:4000L, ]
|
|
bank_test <- bank[4001L:4521L, ]
|
|
|
|
# We must now transform the data to fit in LightGBM
|
|
# For this task, we use lgb.convert_with_rules
|
|
# The function transforms the data into a fittable data
|
|
#
|
|
# Classes 'data.table' and 'data.frame': 521 obs. of 17 variables:
|
|
# $ age : int 53 36 58 26 34 55 55 34 41 38 ...
|
|
# $ job : num 1 10 10 9 10 2 2 3 3 4 ...
|
|
# $ marital : num 1 2 1 3 3 2 2 2 1 1 ...
|
|
# $ education: num 2 2 2 2 2 1 2 3 2 2 ...
|
|
# $ default : num 1 1 1 1 1 1 1 1 1 1 ...
|
|
# $ balance : int 26 191 -123 -147 179 1086 471 105 1588 70 ...
|
|
# $ housing : num 2 1 1 1 1 2 2 2 2 1 ...
|
|
# $ loan : num 1 1 1 1 1 1 1 1 2 1 ...
|
|
# $ contact : num 1 1 1 3 1 1 3 3 3 1 ...
|
|
# $ day : int 7 31 5 4 19 6 30 28 20 27 ...
|
|
# $ month : num 9 2 2 7 2 9 9 9 7 11 ...
|
|
# $ duration : int 56 69 131 95 294 146 58 249 10 255 ...
|
|
# $ campaign : int 1 1 2 2 3 1 2 2 8 3 ...
|
|
# $ pdays : int 359 -1 -1 -1 -1 272 -1 -1 -1 148 ...
|
|
# $ previous : int 1 0 0 0 0 2 0 0 0 1 ...
|
|
# $ poutcome : num 1 4 4 4 4 1 4 4 4 3 ...
|
|
# $ y : num 1 1 1 1 1 1 1 1 1 2 ...
|
|
bank_rules <- lgb.convert_with_rules(data = bank_train)
|
|
bank_train <- bank_rules$data
|
|
bank_test <- lgb.convert_with_rules(data = bank_test, rules = bank_rules$rules)$data
|
|
str(bank_test)
|
|
|
|
# Remove 1 to label because it must be between 0 and 1
|
|
bank_train$y <- bank_train$y - 1L
|
|
bank_test$y <- bank_test$y - 1L
|
|
|
|
# Data input to LightGBM must be a matrix, without the label
|
|
my_data_train <- as.matrix(bank_train[, 1L:16L, with = FALSE])
|
|
my_data_test <- as.matrix(bank_test[, 1L:16L, with = FALSE])
|
|
|
|
# Creating the LightGBM dataset with categorical features
|
|
# The categorical features can be passed to lgb.train to not copy and paste a lot
|
|
dtrain <- lgb.Dataset(
|
|
data = my_data_train
|
|
, label = bank_train$y
|
|
, categorical_feature = c(2L, 3L, 4L, 5L, 7L, 8L, 9L, 11L, 16L)
|
|
)
|
|
dtest <- lgb.Dataset.create.valid(
|
|
dtrain
|
|
, data = my_data_test
|
|
, label = bank_test$y
|
|
)
|
|
|
|
# We can now train a model
|
|
params <- list(
|
|
objective = "binary"
|
|
, metric = "l2"
|
|
, min_data = 1L
|
|
, learning_rate = 0.1
|
|
, min_hessian = 1.0
|
|
, max_depth = 2L
|
|
)
|
|
model <- lgb.train(
|
|
params = params
|
|
, data = dtrain
|
|
, nrounds = 100L
|
|
, valids = list(train = dtrain, valid = dtest)
|
|
)
|
|
|
|
# Try to find split_feature: 11
|
|
# If you find it, it means it used a categorical feature in the first tree
|
|
lgb.dump(model, num_iteration = 1L)
|