Final Answer from mlrMBO outside of the specified variable ranges (multi objective function)
swaheera opened this issue · 2 comments
swaheera commented
I am working with R, and I am trying to perform multi-objective constrained Bayesian optimization using the "mlrMBO" library (https://cran.r-project.org/web/packages/mlrMBO/mlrMBO.pdf).
I wrote the following code to optimize some arbitrary function I created:
library(mlrMBO)
library(dplyr)
library(ParamHelpers)
a1 = rnorm(1000,100,10)
b1 = rnorm(1000,100,9)
c1 = sample.int(1000, 1000, replace = TRUE)
train_data = data.frame(a1,b1,c1)
obj.fun = makeMultiObjectiveFunction(
name = "Some function",
fn = function(x) {
#bin data according to random criteria
train_data <- train_data %>%
mutate(cat = ifelse(a1 <= x[1] & b1 <= x[3], "a",
ifelse(a1 <= x[2] & b1 <= x[4], "b", "c")))
train_data$cat = as.factor(train_data$cat)
#new splits
a_table = train_data %>%
filter(cat == "a") %>%
select(a1, b1, c1, cat)
b_table = train_data %>%
filter(cat == "b") %>%
select(a1, b1, c1, cat)
c_table = train_data %>%
filter(cat == "c") %>%
select(a1, b1, c1, cat)
#calculate quantile ("quant") for each bin
table_a = data.frame(a_table%>% group_by(cat) %>%
mutate(quant = ifelse(c1 > 150,1,0 )))
table_b = data.frame(b_table%>% group_by(cat) %>%
mutate(quant = ifelse(c1 > 300,1,0 )))
table_c = data.frame(c_table%>% group_by(cat) %>%
mutate(quant = ifelse(c1 > 400,1,0 )))
f1 = mean(table_a$quant)
f2 = mean(table_b$quant)
f3 = mean(table_c$quant)
#group all tables
final_table = rbind(table_a, table_b, table_c)
# calculate the total mean : this is what needs to be optimized
f4 = mean(final_table$quant)
return (f1, f2, f3, f4);
},
par.set = makeParamSet(
makeNumericParam("x[1]", lower = 80, upper = 90),
makeNumericParam("x[2]", lower = 95, upper = 110),
makeNumericParam("x[3]", lower = 80, upper = 90),
makeNumericParam("x[4]", lower = 95, upper = 110),
forbidden = expression(x[2] >x[1] & x[4] >x[3])
),
minimize = TRUE
)
ctrl = makeMBOControl()
ctrl = setMBOControlTermination(ctrl, iters = 20L)
# we can basically do an exhaustive search in 3 values
ctrl = setMBOControlInfill(ctrl, crit = makeMBOInfillCritEI())
# opt.restarts = 1L, opt.focussearch.points = 3L, opt.focussearch.maxit = 1L)
#design = generateDesign(20L, getParamSet(obj.fun), fun = lhs::maximinLHS)
lrn = makeMBOLearner(ctrl, obj.fun)
res = mbo(obj.fun, design = NULL, learner = lrn, control = ctrl, show.info = TRUE)
But when you look at the final result:
Solution Fitness Value: 1.762747e+02
Parameters at the Solution (parameter, gradient):
X[ 1] : 1.994399e+01 G[ 1] : 7.832140e-01
X[ 2] : 1.182418e+01 G[ 2] : 7.563822e-03
X[ 3] : 1.997264e+01 G[ 3] : 6.824901e-01
X[ 4] : 7.681157e+00 G[ 4] : 2.370936e-02
X[ 5] : 7.515392e-05 G[ 5] : 3.824832e-02
These seem to be outside the specified ranges:
par.set = makeParamSet(
makeNumericParam("x[1]", lower = 80, upper = 90),
makeNumericParam("x[2]", lower = 95, upper = 110),
makeNumericParam("x[3]", lower = 80, upper = 90),
makeNumericParam("x[4]", lower = 95, upper = 110)
Am I doing something wrong?
Thanks
jakob-r commented
can you change your example so it does not use x[1] as param ids but x1 etc instead.
swaheera commented
I repaced [x1], x[2], x[3], x[4] with x1, x2, x3, x4:
library(mlrMBO)
library(dplyr)
library(ParamHelpers)
a1 = rnorm(1000,100,10)
b1 = rnorm(1000,100,9)
c1 = sample.int(1000, 1000, replace = TRUE)
train_data = data.frame(a1,b1,c1)
obj.fun = makeMultiObjectiveFunction(
name = "Some function",
fn = function(x1,x2,x3,x4) {
#bin data according to random criteria
train_data <- train_data %>%
mutate(cat = ifelse(a1 <= x1 & b1 <= x3, "a",
ifelse(a1 <= x2 & b1 <= x4, "b", "c")))
train_data$cat = as.factor(train_data$cat)
#new splits
a_table = train_data %>%
filter(cat == "a") %>%
select(a1, b1, c1, cat)
b_table = train_data %>%
filter(cat == "b") %>%
select(a1, b1, c1, cat)
c_table = train_data %>%
filter(cat == "c") %>%
select(a1, b1, c1, cat)
#calculate quantile ("quant") for each bin
table_a = data.frame(a_table%>% group_by(cat) %>%
mutate(quant = ifelse(c1 > 150,1,0 )))
table_b = data.frame(b_table%>% group_by(cat) %>%
mutate(quant = ifelse(c1 > 300,1,0 )))
table_c = data.frame(c_table%>% group_by(cat) %>%
mutate(quant = ifelse(c1 > 400,1,0 )))
f1 = mean(table_a$quant)
f2 = mean(table_b$quant)
f3 = mean(table_c$quant)
#group all tables
final_table = rbind(table_a, table_b, table_c)
# calculate the total mean : this is what needs to be optimized
f4 = mean(final_table$quant)
return (f1, f2, f3, f4);
},
par.set = makeParamSet(
makeNumericParam("x1", lower = 80, upper = 90),
makeNumericParam("x2", lower = 95, upper = 110),
makeNumericParam("x3", lower = 80, upper = 90),
makeNumericParam("x4", lower = 95, upper = 110),
forbidden = expression(x2 >x1 & x4 >x3)
),
minimize = TRUE
)
ctrl = makeMBOControl()
ctrl = setMBOControlTermination(ctrl, iters = 20L)
# we can basically do an exhaustive search in 3 values
ctrl = setMBOControlInfill(ctrl, crit = makeMBOInfillCritEI())
# opt.restarts = 1L, opt.focussearch.points = 3L, opt.focussearch.maxit = 1L)
#design = generateDesign(20L, getParamSet(obj.fun), fun = lhs::maximinLHS)
lrn = makeMBOLearner(ctrl, obj.fun)
res = mbo(obj.fun, design = NULL, learner = lrn, control = ctrl, show.info = TRUE)
But this code has been running for the past few hours ... Am I doing something wrong?
Thank you so much!