Rで学ぶTree-Based ModelsによるMachine Learning
Sandro Raabe
Data Scientist
head(diabetes)
# A tibble: 6 x 9 outcome pregnancies glucose blood_pressure skin_thickness insulin bmi age <fct> <int> <int> <int> <int> <int> <dbl> <int> 1 yes 6 148 72 35 0 33.6 50 2 no 1 85 66 29 0 26.6 31 3 yes 8 183 64 0 0 23.3 32
# 比率で分割（既定: 0.75） diabetes_split <- initial_split(diabetes, prop = 0.9) diabetes_split
<Analysis/Assess/Total> <692/76/768>
diabetes_train <- training(diabetes_split) diabetes_test <- testing(diabetes_split)
diabetes_train <- training(diabetes_split)
diabetes_test <- testing(diabetes_split)
nrow(diabetes_train)/nrow(diabetes)
[1] 0.9007812
# 学習データの 'yes' と 'no' の件数 counts_train <- table(diabetes_train$outcome) counts_train
no yes 490 86
# 学習データの 'yes' の割合 prop_yes_train <- counts_train["yes"]/ sum(counts_train) prop_yes_train
0.15
# テストデータの 'yes' と 'no' の件数 counts_test <- table(diabetes_test$outcome) counts_test
no yes 28 48
# テストデータの 'yes' の割合 prop_yes_test <- counts_test["yes"]/ sum(counts_test) prop_yes_test
0.63
initial_split(diabetes, prop = 0.9, strata = outcome)
outcome
Preparing Video For Download...
