R 中 CARET 中的训练、验证、测试拆分模型
•浏览 1
train,validation, test split model in CARET in R
我想寻求帮助。我使用此代码运行 Caret 包中的 XGboost 模型。但是，我想使用基于时间的验证拆分。我想要 60% 的训练，20% 的验证，20% 的测试。我已经拆分了数据，但是如果不是交叉验证，我确实知道如何处理验证数据。
谢谢你，
xgb_trainControl = trainControl(
method ="cv",
number = 5,
returnData = FALSE
)
xgb_grid <- expand.grid(nrounds = 1000,
eta = 0.01,
max_depth = 8,
gamma = 1,
colsample_bytree = 1,
min_child_weight = 1,
subsample = 1
)
set.seed(123)
xgb1 = train(sale~., data = trans_train,
trControl = xgb_trainControl,
tuneGrid = xgb_grid,
method ="xgbTree",
)
xgb1
pred = predict(lm1, trans_test)# Define the partition (e.g. 75% of the data for training)
trainIndex <- createDataPartition(data$response, p = .75,
list = FALSE,
times = 1)
# Split the dataset using the defined partition
train_data <- data[trainIndex, ,drop=FALSE]
tune_plus_val_data <- data[-trainIndex, ,drop=FALSE]
# Define a new partition to split the remaining 25%
tune_plus_val_index <- createDataPartition(tune_plus_val_data$response,
p = .6,
list = FALSE,
times = 1)
# Split the remaining ~25% of the data: 40% (tune) and 60% (val)
tune_data <- tune_plus_val_data[-tune_plus_val_index, ,drop=FALSE]
val_data <- tune_plus_val_data[tune_plus_val_index, ,drop=FALSE]
# Outcome of this section is that the data (100%) is split into:
# training (~75%)
# tuning (~10%)
# validation (~15%)lrn_tune <- setHyperPars(lrn, par.vals = mytune$x)
params2 <- list(booster ="gbtree",
objective = lrn_tune$par.vals$objective,
eta=lrn_tune$par.vals$eta, gamma=0,
max_depth=lrn_tune$par.vals$max_depth,
min_child_weight=lrn_tune$par.vals$min_child_weight,
subsample = 0.8,
colsample_bytree=lrn_tune$par.vals$colsample_bytree)
xgb2 <- xgb.train(params = params2,
data = dtrain, nrounds = 50,
watchlist = list(val=dtune, train=dtrain),
print_every_n = 10, early_stopping_rounds = 50,
maximize = FALSE, eval_metric ="error")xgbpred2_keep <- predict(xgb2, dval)
xg2_val <- data.frame("Prediction" = xgbpred2_keep,
"Patient" = rownames(val),
"Response" = val_data$response)
# Reorder Patients according to Response
xg2_val$Patient <- factor(xg2_val$Patient,
levels = xg2_val$Patient[order(xg2_val$Response)])
ggplot(xg2_val, aes(x = Patient, y = Prediction,
fill = Response)) +
geom_bar(stat ="identity") +
theme_bw(base_size = 16) +
labs(title=paste("Patient predictions (xgb2) for the validation dataset (n =",
length(rownames(val)),")", sep =""),
subtitle="Above 0.5 = Non-Responder, Below 0.5 = Responder",
caption=paste("JM", Sys.Date(), sep =""),
x ="") +
theme(axis.text.x = element_text(angle=90, vjust=0.5,
hjust = 1, size = 8)) +
# Distance from red line = confidence of prediction
geom_hline(yintercept = 0.5, colour ="red")
# Convert predictions to binary outcome (responder / non-responder)
xgbpred2_binary <- ifelse(predict(xgb2, dval) > 0.5,1,0)
# Results matrix (i.e. true positives/negatives & false positives/negatives)
confusionMatrix(as.factor(xgbpred2_binary), as.factor(labels_tv))
# Summary of results
Summary_of_results <- data.frame(Patient_ID = rownames(val),
label = labels_tv,
pred = xgbpred2_binary)
Summary_of_results$eval <- ifelse(
Summary_of_results$label != Summary_of_results$pred,
"wrong",
"correct")
Summary_of_results$conf <- round(predict(xgb2, dval), 2)
Summary_of_results$CDS <- val_data$`variants`
Summary_of_results在创建模型时不应使用验证分区 - 应将其"搁置一旁"，直到使用"训练"和"调整"分区对模型进行训练和调整，然后您可以应用模型进行预测验证数据集的结果并总结预测的准确性。
例如，在我自己的工作中，我创建了三个分区：训练(75%)、调整(10%)和测试/验证(15%)使用
xgb_trainControl = trainControl(
method ="cv",
number = 5,
returnData = FALSE
)
xgb_grid <- expand.grid(nrounds = 1000,
eta = 0.01,
max_depth = 8,
gamma = 1,
colsample_bytree = 1,
min_child_weight = 1,
subsample = 1
)
set.seed(123)
xgb1 = train(sale~., data = trans_train,
trControl = xgb_trainControl,
tuneGrid = xgb_grid,
method ="xgbTree",
)
xgb1
pred = predict(lm1, trans_test)# Define the partition (e.g. 75% of the data for training)
trainIndex <- createDataPartition(data$response, p = .75,
list = FALSE,
times = 1)
# Split the dataset using the defined partition
train_data <- data[trainIndex, ,drop=FALSE]
tune_plus_val_data <- data[-trainIndex, ,drop=FALSE]
# Define a new partition to split the remaining 25%
tune_plus_val_index <- createDataPartition(tune_plus_val_data$response,
p = .6,
list = FALSE,
times = 1)
# Split the remaining ~25% of the data: 40% (tune) and 60% (val)
tune_data <- tune_plus_val_data[-tune_plus_val_index, ,drop=FALSE]
val_data <- tune_plus_val_data[tune_plus_val_index, ,drop=FALSE]
# Outcome of this section is that the data (100%) is split into:
# training (~75%)
# tuning (~10%)
# validation (~15%)lrn_tune <- setHyperPars(lrn, par.vals = mytune$x)
params2 <- list(booster ="gbtree",
objective = lrn_tune$par.vals$objective,
eta=lrn_tune$par.vals$eta, gamma=0,
max_depth=lrn_tune$par.vals$max_depth,
min_child_weight=lrn_tune$par.vals$min_child_weight,
subsample = 0.8,
colsample_bytree=lrn_tune$par.vals$colsample_bytree)
xgb2 <- xgb.train(params = params2,
data = dtrain, nrounds = 50,
watchlist = list(val=dtune, train=dtrain),
print_every_n = 10, early_stopping_rounds = 50,
maximize = FALSE, eval_metric ="error")xgbpred2_keep <- predict(xgb2, dval)
xg2_val <- data.frame("Prediction" = xgbpred2_keep,
"Patient" = rownames(val),
"Response" = val_data$response)
# Reorder Patients according to Response
xg2_val$Patient <- factor(xg2_val$Patient,
levels = xg2_val$Patient[order(xg2_val$Response)])
ggplot(xg2_val, aes(x = Patient, y = Prediction,
fill = Response)) +
geom_bar(stat ="identity") +
theme_bw(base_size = 16) +
labs(title=paste("Patient predictions (xgb2) for the validation dataset (n =",
length(rownames(val)),")", sep =""),
subtitle="Above 0.5 = Non-Responder, Below 0.5 = Responder",
caption=paste("JM", Sys.Date(), sep =""),
x ="") +
theme(axis.text.x = element_text(angle=90, vjust=0.5,
hjust = 1, size = 8)) +
# Distance from red line = confidence of prediction
geom_hline(yintercept = 0.5, colour ="red")
# Convert predictions to binary outcome (responder / non-responder)
xgbpred2_binary <- ifelse(predict(xgb2, dval) > 0.5,1,0)
# Results matrix (i.e. true positives/negatives & false positives/negatives)
confusionMatrix(as.factor(xgbpred2_binary), as.factor(labels_tv))
# Summary of results
Summary_of_results <- data.frame(Patient_ID = rownames(val),
label = labels_tv,
pred = xgbpred2_binary)
Summary_of_results$eval <- ifelse(
Summary_of_results$label != Summary_of_results$pred,
"wrong",
"correct")
Summary_of_results$conf <- round(predict(xgb2, dval), 2)
Summary_of_results$CDS <- val_data$`variants`
Summary_of_results这些数据分区被转换为 xgb.DMatrix 矩阵("dtrain"、"dtune"、"dval")。然后，我使用"训练"分区来训练模型，并使用"调整"分区来调整超参数(例如随机网格搜索)并评估模型训练(例如交叉验证)。这?相当于您问题中的代码。
xgb_trainControl = trainControl(
method ="cv",
number = 5,
returnData = FALSE
)
xgb_grid <- expand.grid(nrounds = 1000,
eta = 0.01,
max_depth = 8,
gamma = 1,
colsample_bytree = 1,
min_child_weight = 1,
subsample = 1
)
set.seed(123)
xgb1 = train(sale~., data = trans_train,
trControl = xgb_trainControl,
tuneGrid = xgb_grid,
method ="xgbTree",
)
xgb1
pred = predict(lm1, trans_test)# Define the partition (e.g. 75% of the data for training)
trainIndex <- createDataPartition(data$response, p = .75,
list = FALSE,
times = 1)
# Split the dataset using the defined partition
train_data <- data[trainIndex, ,drop=FALSE]
tune_plus_val_data <- data[-trainIndex, ,drop=FALSE]
# Define a new partition to split the remaining 25%
tune_plus_val_index <- createDataPartition(tune_plus_val_data$response,
p = .6,
list = FALSE,
times = 1)
# Split the remaining ~25% of the data: 40% (tune) and 60% (val)
tune_data <- tune_plus_val_data[-tune_plus_val_index, ,drop=FALSE]
val_data <- tune_plus_val_data[tune_plus_val_index, ,drop=FALSE]
# Outcome of this section is that the data (100%) is split into:
# training (~75%)
# tuning (~10%)
# validation (~15%)lrn_tune <- setHyperPars(lrn, par.vals = mytune$x)
params2 <- list(booster ="gbtree",
objective = lrn_tune$par.vals$objective,
eta=lrn_tune$par.vals$eta, gamma=0,
max_depth=lrn_tune$par.vals$max_depth,
min_child_weight=lrn_tune$par.vals$min_child_weight,
subsample = 0.8,
colsample_bytree=lrn_tune$par.vals$colsample_bytree)
xgb2 <- xgb.train(params = params2,
data = dtrain, nrounds = 50,
watchlist = list(val=dtune, train=dtrain),
print_every_n = 10, early_stopping_rounds = 50,
maximize = FALSE, eval_metric ="error")xgbpred2_keep <- predict(xgb2, dval)
xg2_val <- data.frame("Prediction" = xgbpred2_keep,
"Patient" = rownames(val),
"Response" = val_data$response)
# Reorder Patients according to Response
xg2_val$Patient <- factor(xg2_val$Patient,
levels = xg2_val$Patient[order(xg2_val$Response)])
ggplot(xg2_val, aes(x = Patient, y = Prediction,
fill = Response)) +
geom_bar(stat ="identity") +
theme_bw(base_size = 16) +
labs(title=paste("Patient predictions (xgb2) for the validation dataset (n =",
length(rownames(val)),")", sep =""),
subtitle="Above 0.5 = Non-Responder, Below 0.5 = Responder",
caption=paste("JM", Sys.Date(), sep =""),
x ="") +
theme(axis.text.x = element_text(angle=90, vjust=0.5,
hjust = 1, size = 8)) +
# Distance from red line = confidence of prediction
geom_hline(yintercept = 0.5, colour ="red")
# Convert predictions to binary outcome (responder / non-responder)
xgbpred2_binary <- ifelse(predict(xgb2, dval) > 0.5,1,0)
# Results matrix (i.e. true positives/negatives & false positives/negatives)
confusionMatrix(as.factor(xgbpred2_binary), as.factor(labels_tv))
# Summary of results
Summary_of_results <- data.frame(Patient_ID = rownames(val),
label = labels_tv,
pred = xgbpred2_binary)
Summary_of_results$eval <- ifelse(
Summary_of_results$label != Summary_of_results$pred,
"wrong",
"correct")
Summary_of_results$conf <- round(predict(xgb2, dval), 2)
Summary_of_results$CDS <- val_data$`variants`
Summary_of_results一旦模型经过训练，我将使用 predict():
将模型应用于验证数据
xgb_trainControl = trainControl(
method ="cv",
number = 5,
returnData = FALSE
)
xgb_grid <- expand.grid(nrounds = 1000,
eta = 0.01,
max_depth = 8,
gamma = 1,
colsample_bytree = 1,
min_child_weight = 1,
subsample = 1
)
set.seed(123)
xgb1 = train(sale~., data = trans_train,
trControl = xgb_trainControl,
tuneGrid = xgb_grid,
method ="xgbTree",
)
xgb1
pred = predict(lm1, trans_test)# Define the partition (e.g. 75% of the data for training)
trainIndex <- createDataPartition(data$response, p = .75,
list = FALSE,
times = 1)
# Split the dataset using the defined partition
train_data <- data[trainIndex, ,drop=FALSE]
tune_plus_val_data <- data[-trainIndex, ,drop=FALSE]
# Define a new partition to split the remaining 25%
tune_plus_val_index <- createDataPartition(tune_plus_val_data$response,
p = .6,
list = FALSE,
times = 1)
# Split the remaining ~25% of the data: 40% (tune) and 60% (val)
tune_data <- tune_plus_val_data[-tune_plus_val_index, ,drop=FALSE]
val_data <- tune_plus_val_data[tune_plus_val_index, ,drop=FALSE]
# Outcome of this section is that the data (100%) is split into:
# training (~75%)
# tuning (~10%)
# validation (~15%)lrn_tune <- setHyperPars(lrn, par.vals = mytune$x)
params2 <- list(booster ="gbtree",
objective = lrn_tune$par.vals$objective,
eta=lrn_tune$par.vals$eta, gamma=0,
max_depth=lrn_tune$par.vals$max_depth,
min_child_weight=lrn_tune$par.vals$min_child_weight,
subsample = 0.8,
colsample_bytree=lrn_tune$par.vals$colsample_bytree)
xgb2 <- xgb.train(params = params2,
data = dtrain, nrounds = 50,
watchlist = list(val=dtune, train=dtrain),
print_every_n = 10, early_stopping_rounds = 50,
maximize = FALSE, eval_metric ="error")xgbpred2_keep <- predict(xgb2, dval)
xg2_val <- data.frame("Prediction" = xgbpred2_keep,
"Patient" = rownames(val),
"Response" = val_data$response)
# Reorder Patients according to Response
xg2_val$Patient <- factor(xg2_val$Patient,
levels = xg2_val$Patient[order(xg2_val$Response)])
ggplot(xg2_val, aes(x = Patient, y = Prediction,
fill = Response)) +
geom_bar(stat ="identity") +
theme_bw(base_size = 16) +
labs(title=paste("Patient predictions (xgb2) for the validation dataset (n =",
length(rownames(val)),")", sep =""),
subtitle="Above 0.5 = Non-Responder, Below 0.5 = Responder",
caption=paste("JM", Sys.Date(), sep =""),
x ="") +
theme(axis.text.x = element_text(angle=90, vjust=0.5,
hjust = 1, size = 8)) +
# Distance from red line = confidence of prediction
geom_hline(yintercept = 0.5, colour ="red")
# Convert predictions to binary outcome (responder / non-responder)
xgbpred2_binary <- ifelse(predict(xgb2, dval) > 0.5,1,0)
# Results matrix (i.e. true positives/negatives & false positives/negatives)
confusionMatrix(as.factor(xgbpred2_binary), as.factor(labels_tv))
# Summary of results
Summary_of_results <- data.frame(Patient_ID = rownames(val),
label = labels_tv,
pred = xgbpred2_binary)
Summary_of_results$eval <- ifelse(
Summary_of_results$label != Summary_of_results$pred,
"wrong",
"correct")
Summary_of_results$conf <- round(predict(xgb2, dval), 2)
Summary_of_results$CDS <- val_data$`variants`
Summary_of_results这为您提供了模型在验证数据上的"工作"效果的摘要。