tidymodels bake:Error: Please pass a data set to `new_data`
tidymodels bake:Error: Please pass a data set to `new_data`
我在 tidymodels 包中使用 recipe() 函数来插补缺失值和修复不平衡数据。
这是我的数据；
mer_df <- mer2 %>%
filter(!is.na(laststagestatus2)) %>%
select(Id, Age_Range__c, Gender__c, numberoflead, leadduration, firsttouch, lasttouch, laststagestatus2)%>%
mutate_if(is.character, factor) %>%
mutate_if(is.logical, as.integer)
# A tibble: 197,836 x 8
Id Age_Range__c Gender__c numberoflead leadduration firsttouch lasttouch
<fct> <fct> <fct> <int> <dbl> <fct> <fct>
1 0010~ NA NA 2 5.99 Dealer IB~ Walk in
2 0010~ NA NA 1 0 Online Se~ Online S~
3 0010~ NA NA 1 0 Walk in Walk in
4 0010~ NA NA 1 0 Online Se~ Online S~
5 0010~ NA NA 2 0.0128 Dealer IB~ Dealer I~
6 0010~ NA NA 1 0 OB Call OB Call
7 0010~ NA NA 1 0 Dealer IB~ Dealer I~
8 0010~ NA NA 4 73.9 Dealer IB~ Walk in
9 0010~ NA Male 24 0.000208 OB Call OB Call
10 0010~ NA NA 18 0.000150 OB Call OB Call
# ... with 197,826 more rows, and 1 more variable: laststagestatus2 <fct>
这是我的代码；
mer_rec <- recipe(laststagestatus2 ~ ., data = mer_train)%>%
step_medianimpute(numberoflead,leadduration)%>%
step_knnimpute(Gender__c,Age_Range__c,fisrsttouch,lasttouch) %>%
step_other(Id,firsttouch) %>%
step_other(Id,lasttouch) %>%
step_dummy(all_nominal(), -laststagestatus2) %>%
step_smote(laststagestatus2)
mer_rec
mer_rec %>% prep()
到这里为止一切正常；
Data Recipe
Inputs:
role #variables
outcome 1
predictor 7
Training data contained 148377 data points and 147597 incomplete rows.
Operations:
Median Imputation for 2 items [trained]
K-nearest neighbor imputation for Id, ... [trained]
Collapsing factor levels for Id, firsttouch [trained]
Collapsing factor levels for Id, lasttouch [trained]
Dummy variables from Id, ... [trained]
SMOTE based on laststagestatus2 [trained]
但是当 ı 运行 bake() 给出错误的函数说；
mer_rec %>% prep() %>% bake(new_data=NULL) %>% count(laststagestatus2)
Error: Please pass a data set to `new_data`.
谁能帮我解决我在这里遗漏的问题？
配方的开发版本中有一个修复程序可以启动并运行。您可以通过以下方式安装：
devtools::install_github("tidymodels/recipes")
然后你可以bake()和new_data = NULL得到转换后的训练数据。
library(tidymodels)
data(ames)
ames <- mutate(ames, Sale_Price = log10(Sale_Price))
set.seed(123)
ames_split <- initial_split(ames, prob = 0.80, strata = Sale_Price)
ames_train <- training(ames_split)
ames_test <- testing(ames_split)
ames_rec <-
recipe(Sale_Price ~ Neighborhood + Gr_Liv_Area + Year_Built + Bldg_Type +
Latitude + Longitude, data = ames_train) %>%
step_log(Gr_Liv_Area, base = 10) %>%
step_other(Neighborhood, threshold = 0.01) %>%
step_dummy(all_nominal()) %>%
step_interact( ~ Gr_Liv_Area:starts_with("Bldg_Type_") ) %>%
step_ns(Latitude, Longitude, deg_free = 20)
ames_rec %>% prep() %>% bake(new_data = NULL)
#> # A tibble: 2,199 x 71
#> Gr_Liv_Area Year_Built Sale_Price Neighborhood_Co… Neighborhood_Ol…
#> <dbl> <int> <dbl> <dbl> <dbl>
#> 1 3.22 1960 5.33 0 0
#> 2 2.95 1961 5.02 0 0
#> 3 3.12 1958 5.24 0 0
#> 4 3.21 1997 5.28 0 0
#> 5 3.21 1998 5.29 0 0
#> 6 3.13 2001 5.33 0 0
#> 7 3.11 1992 5.28 0 0
#> 8 3.21 1995 5.37 0 0
#> 9 3.22 1993 5.25 0 0
#> 10 3.17 1998 5.26 0 0
#> # … with 2,189 more rows, and 66 more variables: Neighborhood_Edwards <dbl>,
#> # Neighborhood_Somerset <dbl>, Neighborhood_Northridge_Heights <dbl>,
#> # Neighborhood_Gilbert <dbl>, Neighborhood_Sawyer <dbl>,
#> # Neighborhood_Northwest_Ames <dbl>, Neighborhood_Sawyer_West <dbl>,
#> # Neighborhood_Mitchell <dbl>, Neighborhood_Brookside <dbl>,
#> # Neighborhood_Crawford <dbl>, Neighborhood_Iowa_DOT_and_Rail_Road <dbl>,
#> # Neighborhood_Timberland <dbl>, Neighborhood_Northridge <dbl>,
#> # Neighborhood_Stone_Brook <dbl>,
#> # Neighborhood_South_and_West_of_Iowa_State_University <dbl>,
#> # Neighborhood_Clear_Creek <dbl>, Neighborhood_Meadow_Village <dbl>,
#> # Neighborhood_other <dbl>, Bldg_Type_TwoFmCon <dbl>, Bldg_Type_Duplex <dbl>,
#> # Bldg_Type_Twnhs <dbl>, Bldg_Type_TwnhsE <dbl>,
#> # Gr_Liv_Area_x_Bldg_Type_TwoFmCon <dbl>,
#> # Gr_Liv_Area_x_Bldg_Type_Duplex <dbl>, Gr_Liv_Area_x_Bldg_Type_Twnhs <dbl>,
#> # Gr_Liv_Area_x_Bldg_Type_TwnhsE <dbl>, Latitude_ns_01 <dbl>,
#> # Latitude_ns_02 <dbl>, Latitude_ns_03 <dbl>, Latitude_ns_04 <dbl>,
#> # Latitude_ns_05 <dbl>, Latitude_ns_06 <dbl>, Latitude_ns_07 <dbl>,
#> # Latitude_ns_08 <dbl>, Latitude_ns_09 <dbl>, Latitude_ns_10 <dbl>,
#> # Latitude_ns_11 <dbl>, Latitude_ns_12 <dbl>, Latitude_ns_13 <dbl>,
#> # Latitude_ns_14 <dbl>, Latitude_ns_15 <dbl>, Latitude_ns_16 <dbl>,
#> # Latitude_ns_17 <dbl>, Latitude_ns_18 <dbl>, Latitude_ns_19 <dbl>,
#> # Latitude_ns_20 <dbl>, Longitude_ns_01 <dbl>, Longitude_ns_02 <dbl>,
#> # Longitude_ns_03 <dbl>, Longitude_ns_04 <dbl>, Longitude_ns_05 <dbl>,
#> # Longitude_ns_06 <dbl>, Longitude_ns_07 <dbl>, Longitude_ns_08 <dbl>,
#> # Longitude_ns_09 <dbl>, Longitude_ns_10 <dbl>, Longitude_ns_11 <dbl>,
#> # Longitude_ns_12 <dbl>, Longitude_ns_13 <dbl>, Longitude_ns_14 <dbl>,
#> # Longitude_ns_15 <dbl>, Longitude_ns_16 <dbl>, Longitude_ns_17 <dbl>,
#> # Longitude_ns_18 <dbl>, Longitude_ns_19 <dbl>, Longitude_ns_20 <dbl>
由 reprex package (v0.3.0.9001)
于 2020-10-12 创建
如果您无法从 GitHub 安装软件包，您可以 。
我在 tidymodels 包中使用 recipe() 函数来插补缺失值和修复不平衡数据。
这是我的数据；
mer_df <- mer2 %>%
filter(!is.na(laststagestatus2)) %>%
select(Id, Age_Range__c, Gender__c, numberoflead, leadduration, firsttouch, lasttouch, laststagestatus2)%>%
mutate_if(is.character, factor) %>%
mutate_if(is.logical, as.integer)
# A tibble: 197,836 x 8
Id Age_Range__c Gender__c numberoflead leadduration firsttouch lasttouch
<fct> <fct> <fct> <int> <dbl> <fct> <fct>
1 0010~ NA NA 2 5.99 Dealer IB~ Walk in
2 0010~ NA NA 1 0 Online Se~ Online S~
3 0010~ NA NA 1 0 Walk in Walk in
4 0010~ NA NA 1 0 Online Se~ Online S~
5 0010~ NA NA 2 0.0128 Dealer IB~ Dealer I~
6 0010~ NA NA 1 0 OB Call OB Call
7 0010~ NA NA 1 0 Dealer IB~ Dealer I~
8 0010~ NA NA 4 73.9 Dealer IB~ Walk in
9 0010~ NA Male 24 0.000208 OB Call OB Call
10 0010~ NA NA 18 0.000150 OB Call OB Call
# ... with 197,826 more rows, and 1 more variable: laststagestatus2 <fct>
这是我的代码；
mer_rec <- recipe(laststagestatus2 ~ ., data = mer_train)%>%
step_medianimpute(numberoflead,leadduration)%>%
step_knnimpute(Gender__c,Age_Range__c,fisrsttouch,lasttouch) %>%
step_other(Id,firsttouch) %>%
step_other(Id,lasttouch) %>%
step_dummy(all_nominal(), -laststagestatus2) %>%
step_smote(laststagestatus2)
mer_rec
mer_rec %>% prep()
到这里为止一切正常；
Data Recipe
Inputs:
role #variables
outcome 1
predictor 7
Training data contained 148377 data points and 147597 incomplete rows.
Operations:
Median Imputation for 2 items [trained]
K-nearest neighbor imputation for Id, ... [trained]
Collapsing factor levels for Id, firsttouch [trained]
Collapsing factor levels for Id, lasttouch [trained]
Dummy variables from Id, ... [trained]
SMOTE based on laststagestatus2 [trained]
但是当 ı 运行 bake() 给出错误的函数说；
mer_rec %>% prep() %>% bake(new_data=NULL) %>% count(laststagestatus2)
Error: Please pass a data set to `new_data`.
谁能帮我解决我在这里遗漏的问题？
配方的开发版本中有一个修复程序可以启动并运行。您可以通过以下方式安装：
devtools::install_github("tidymodels/recipes")
然后你可以bake()和new_data = NULL得到转换后的训练数据。
library(tidymodels)
data(ames)
ames <- mutate(ames, Sale_Price = log10(Sale_Price))
set.seed(123)
ames_split <- initial_split(ames, prob = 0.80, strata = Sale_Price)
ames_train <- training(ames_split)
ames_test <- testing(ames_split)
ames_rec <-
recipe(Sale_Price ~ Neighborhood + Gr_Liv_Area + Year_Built + Bldg_Type +
Latitude + Longitude, data = ames_train) %>%
step_log(Gr_Liv_Area, base = 10) %>%
step_other(Neighborhood, threshold = 0.01) %>%
step_dummy(all_nominal()) %>%
step_interact( ~ Gr_Liv_Area:starts_with("Bldg_Type_") ) %>%
step_ns(Latitude, Longitude, deg_free = 20)
ames_rec %>% prep() %>% bake(new_data = NULL)
#> # A tibble: 2,199 x 71
#> Gr_Liv_Area Year_Built Sale_Price Neighborhood_Co… Neighborhood_Ol…
#> <dbl> <int> <dbl> <dbl> <dbl>
#> 1 3.22 1960 5.33 0 0
#> 2 2.95 1961 5.02 0 0
#> 3 3.12 1958 5.24 0 0
#> 4 3.21 1997 5.28 0 0
#> 5 3.21 1998 5.29 0 0
#> 6 3.13 2001 5.33 0 0
#> 7 3.11 1992 5.28 0 0
#> 8 3.21 1995 5.37 0 0
#> 9 3.22 1993 5.25 0 0
#> 10 3.17 1998 5.26 0 0
#> # … with 2,189 more rows, and 66 more variables: Neighborhood_Edwards <dbl>,
#> # Neighborhood_Somerset <dbl>, Neighborhood_Northridge_Heights <dbl>,
#> # Neighborhood_Gilbert <dbl>, Neighborhood_Sawyer <dbl>,
#> # Neighborhood_Northwest_Ames <dbl>, Neighborhood_Sawyer_West <dbl>,
#> # Neighborhood_Mitchell <dbl>, Neighborhood_Brookside <dbl>,
#> # Neighborhood_Crawford <dbl>, Neighborhood_Iowa_DOT_and_Rail_Road <dbl>,
#> # Neighborhood_Timberland <dbl>, Neighborhood_Northridge <dbl>,
#> # Neighborhood_Stone_Brook <dbl>,
#> # Neighborhood_South_and_West_of_Iowa_State_University <dbl>,
#> # Neighborhood_Clear_Creek <dbl>, Neighborhood_Meadow_Village <dbl>,
#> # Neighborhood_other <dbl>, Bldg_Type_TwoFmCon <dbl>, Bldg_Type_Duplex <dbl>,
#> # Bldg_Type_Twnhs <dbl>, Bldg_Type_TwnhsE <dbl>,
#> # Gr_Liv_Area_x_Bldg_Type_TwoFmCon <dbl>,
#> # Gr_Liv_Area_x_Bldg_Type_Duplex <dbl>, Gr_Liv_Area_x_Bldg_Type_Twnhs <dbl>,
#> # Gr_Liv_Area_x_Bldg_Type_TwnhsE <dbl>, Latitude_ns_01 <dbl>,
#> # Latitude_ns_02 <dbl>, Latitude_ns_03 <dbl>, Latitude_ns_04 <dbl>,
#> # Latitude_ns_05 <dbl>, Latitude_ns_06 <dbl>, Latitude_ns_07 <dbl>,
#> # Latitude_ns_08 <dbl>, Latitude_ns_09 <dbl>, Latitude_ns_10 <dbl>,
#> # Latitude_ns_11 <dbl>, Latitude_ns_12 <dbl>, Latitude_ns_13 <dbl>,
#> # Latitude_ns_14 <dbl>, Latitude_ns_15 <dbl>, Latitude_ns_16 <dbl>,
#> # Latitude_ns_17 <dbl>, Latitude_ns_18 <dbl>, Latitude_ns_19 <dbl>,
#> # Latitude_ns_20 <dbl>, Longitude_ns_01 <dbl>, Longitude_ns_02 <dbl>,
#> # Longitude_ns_03 <dbl>, Longitude_ns_04 <dbl>, Longitude_ns_05 <dbl>,
#> # Longitude_ns_06 <dbl>, Longitude_ns_07 <dbl>, Longitude_ns_08 <dbl>,
#> # Longitude_ns_09 <dbl>, Longitude_ns_10 <dbl>, Longitude_ns_11 <dbl>,
#> # Longitude_ns_12 <dbl>, Longitude_ns_13 <dbl>, Longitude_ns_14 <dbl>,
#> # Longitude_ns_15 <dbl>, Longitude_ns_16 <dbl>, Longitude_ns_17 <dbl>,
#> # Longitude_ns_18 <dbl>, Longitude_ns_19 <dbl>, Longitude_ns_20 <dbl>
由 reprex package (v0.3.0.9001)
于 2020-10-12 创建如果您无法从 GitHub 安装软件包，您可以