作者热门文章
- html - 出于某种原因,IE8 对我的 Sass 文件中继承的 html5 CSS 不友好?
- JMeter 在响应断言中使用 span 标签的问题
- html - 在 :hover and :active? 上具有不同效果的 CSS 动画
- html - 相对于居中的 html 内容固定的 CSS 重复背景?
数据集可以在这里找到:
https://www.kaggle.com/mlg-ulb/creditcardfraud
我正在尝试使用 tidymodels 在此数据集上运行具有 5 折交叉验证的游侠。
我有 2 个代码块。第一个代码块是包含完整数据的原始代码。第二个代码块几乎与第一个代码块相同,只是我有一部分数据的子集,因此代码运行得更快。第二个代码块只是为了确保我的代码在我在原始数据集上运行之前可以正常工作。
这是包含完整数据的第一个代码块:
#load packages
library(tidyverse)
library(tidymodels)
library(tune)
library(workflows)
#load data
df <- read.csv("~creditcard.csv")
#check for NAs and convert Class to factor
anyNA(df)
df$Class <- as.factor(df$Class)
#set seed and split data into training and testing
set.seed(123)
df_split <- initial_split(df)
df_train <- training(df_split)
df_test <- testing(df_split)
#in the training and testing datasets, how many are fraudulent transactions?
df_train %>% count(Class)
df_test %>% count(Class)
#ranger model with 5-fold cross validation
rf_spec <-
rand_forest() %>%
set_engine("ranger", importance = "impurity") %>%
set_mode("classification")
all_wf <-
workflow() %>%
add_formula(Class ~ .) %>%
add_model(rf_spec)
cv_folds <- vfold_cv(df_train, v = 5)
cv_folds
rf_results <-
all_wf %>%
fit_resamples(resamples = cv_folds)
rf_results %>%
collect_metrics()
#load packages
library(tidyverse)
library(tidymodels)
library(tune)
library(workflows)
#load data
df <- read.csv("~creditcard.csv")
###################################################################################
#Testing area#
df <- df %>% arrange(-Class) %>% head(1000)
###################################################################################
#check for NAs and convert Class to factor
anyNA(df)
df$Class <- as.factor(df$Class)
#set seed and split data into training and testing
set.seed(123)
df_split <- initial_split(df)
df_train <- training(df_split)
df_test <- testing(df_split)
#in the training and testing datasets, how many are fraudulent transactions?
df_train %>% count(Class)
df_test %>% count(Class)
#ranger model with 5-fold cross validation
rf_spec <-
rand_forest() %>%
set_engine("ranger", importance = "impurity") %>%
set_mode("classification")
all_wf <-
workflow() %>%
add_formula(Class ~ .) %>%
add_model(rf_spec)
cv_folds <- vfold_cv(df_train, v = 5)
cv_folds
rf_results <-
all_wf %>%
fit_resamples(resamples = cv_folds)
rf_results %>%
collect_metrics()
I think the Predictions portion of this article might be what I'm aiming for.
https://rviews.rstudio.com/2019/06/19/a-gentle-intro-to-tidymodels/
rf_fit <- get_tree_fit(all_wf)
vip::vip(rf_fit, geom = "point")
#ranger model with 5-fold cross validation
rf_recipe <- recipe(Class ~ ., data = df_train)
rf_engine <-
rand_forest(mtry = tune(), trees = tune(), min_n = tune()) %>%
set_engine("ranger", importance = "impurity") %>%
set_mode("classification")
rf_grid <- grid_random(
mtry() %>% range_set(c(1, 20)),
trees() %>% range_set(c(500, 1000)),
min_n() %>% range_set(c(2, 10)),
size = 30)
all_wf <-
workflow() %>%
add_recipe(rf_recipe) %>%
add_model(rf_engine)
cv_folds <- vfold_cv(df_train, v = 5)
cv_folds
#####
rf_fit <- tune_grid(
all_wf,
resamples = cv_folds,
grid = rf_grid,
metrics = metric_set(roc_auc),
control = control_grid(save_pred = TRUE)
)
collect_metrics(rf_fit)
rf_fit_best <- select_best(rf_fit)
(wf_rf_best <- finalize_workflow(all_wf, rf_fit_best))
最佳答案
我从您的最后一段代码开始,并进行了一些编辑以具有功能性工作流程。我在代码中回答了您的问题。我冒昧地给你一些建议并重新格式化你的代码。
## Packages, seed and data
library(tidyverse)
library(tidymodels)
set.seed(123)
df <- read_csv("creditcard.csv")
df <-
df %>%
arrange(-Class) %>%
head(1000) %>%
mutate(Class = as_factor(Class))
## Modelisation
# Initial split
df_split <- initial_split(df)
df_train <- training(df_split)
df_test <- testing(df_split)
df_split
返回
<750/250/1000>
(见下文)。
# Models
model_rf <-
rand_forest(mtry = tune(), trees = tune(), min_n = tune()) %>%
set_engine("ranger", importance = "impurity") %>%
set_mode("classification")
model_xgboost <-
boost_tree(mtry = tune(), trees = tune(), min_n = tune()) %>%
set_engine("xgboost", importance = "impurity") %>%
set_mode("classification")
# Grid of hyperparameters
grid_rf <-
grid_max_entropy(
mtry(range = c(1, 20)),
trees(range = c(500, 1000)),
min_n(range = c(2, 10)),
size = 30)
# Workflow
wkfl_rf <-
workflow() %>%
add_formula(Class ~ .) %>%
add_model(model_rf)
wkfl_wgboost <-
workflow() %>%
add_formula(Class ~ .) %>%
add_model(model_xgboost)
<600/150/750>
意味着您的训练集中有 600 个观测值,验证集中有 150 个观测值,原始数据集中共有 750 个观测值。请注意,此处为 600 + 150 = 750,但并非总是如此(例如,使用带有重采样的 boostrap 方法)。
# Cross validation method
cv_folds <- vfold_cv(df_train, v = 5)
cv_folds
# Choose metrics
my_metrics <- metric_set(roc_auc, accuracy, sens, spec, precision, recall)
# Tuning
rf_fit <- tune_grid(
wkfl_rf,
resamples = cv_folds,
grid = grid_rf,
metrics = my_metrics,
control = control_grid(verbose = TRUE) # don't save prediction (imho)
)
rf_fit
的一些有用功能。目的。
# Inspect tuning
rf_fit
collect_metrics(rf_fit)
autoplot(rf_fit, metric = "accuracy")
show_best(rf_fit, metric = "accuracy", maximize = TRUE)
select_best(rf_fit, metric = "accuracy", maximize = TRUE)
# Fit best model
tuned_model <-
wkfl_rf %>%
finalize_workflow(select_best(rf_fit, metric = "accuracy", maximize = TRUE)) %>%
fit(data = df_train)
predict(tuned_model, df_train)
predict(tuned_model, df_test)
randomForest
的方法
parnsnip
中的对象通常不可用输出
关于r - tidymodels:具有交叉验证的游侠,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/60368047/
我生成了一个如下所示的随机森林树,并尝试绘制它但出现错误,我在哪里出错了?我怎样才能以正确的方式绘制它? Actmodel <- train(Activity ~ Section + Author,
我是一名优秀的程序员,十分优秀!