问题:将列作为因子追加到数据框中时,会在r中追加的列中创建NA
我是个新手&试图用插入符号学习ml 问题-在创建问题:将列作为因子追加到数据框中时,会在r中追加的列中创建NA,r,dataframe,machine-learning,r-caret,R,Dataframe,Machine Learning,R Caret,我是个新手&试图用插入符号学习ml 问题-在创建假人并移除NZV变量后,当我将Y即预测变量添加回df作为因子时,它会在同一列中创建NA(问题的步骤5-6)。那么,我如何保持Y变量作为最终df中的因子呢 1。数据(来自uci/kaggle的银行营销响应数据) 2.保存X&Y变量 Y = subset(data, select = y) X = subset(data, select = -y) dim(X) dim(Y) 3.创建了假人 pp_dummy <- dummyVars(y ~
假人
并移除NZV变量
后,当我将Y
即预测变量
添加回df作为因子
时,它会在同一列中创建NA
(问题的步骤5-6)。那么,我如何保持Y
变量作为最终df中的因子呢
1。数据(来自uci/kaggle的银行营销响应数据)
2.保存X&Y变量
Y = subset(data, select = y)
X = subset(data, select = -y)
dim(X)
dim(Y)
3.创建了假人
pp_dummy <- dummyVars(y ~ ., data = data)
data <- predict(pp_dummy, newdata = data)
data <- data.frame(data)
5。问题:在上,将y
附加到数据,作为系数
在列中产生NA
data$y <- as.factor(Y)
str(data)
6.如果我按原样追加Y
,它不会立即创建NA
,但当我将其转换为因子时,它会给出NA
data$y <- Y # as.factor(Y)
data <- data %>% mutate(y = as.factor(y))
str(data)
我如何避免使用pull(data$y)
而只使用data$y
呢?它与pull()无关
即使只有一列,也无法将data.frame转换为向量:
X = subset(iris,select=-Species)
Y = subset(iris,select=Species)
as.factor(Y)
Species
<NA>
Levels: 1:3
.valid.factor(Y)
[1] "factor levels must be \"character\""
levels(Y)
NULL
是的,你是对的@StupidWolf。我不知道为什么我没有在r中区分向量和数据帧的习惯。每次我使用一个列并开始将它作为一个系列/向量处理,其中它是一个数据帧。我想我把一些python
习惯和R
混为一谈了。谢谢你纠正和帮助我:)
nzv_list <- nearZeroVar(data) %>%
as.vector()
data <- data[, -nzv_list ]
str(data)
'data.frame': 4119 obs. of 44 variables:
$ age : num 30 39 25 38 47 32 32 41 31 35 ...
$ job.admin. : num 0 0 0 0 1 0 1 0 0 0 ...
$ job.blue.collar : num 1 0 0 0 0 0 0 0 0 1 ...
$ job.management : num 0 0 0 0 0 0 0 0 0 0 ...
$ job.services : num 0 1 1 1 0 1 0 0 1 0 ...
$ job.technician : num 0 0 0 0 0 0 0 0 0 0 ...
$ marital.divorced : num 0 0 0 0 0 0 0 0 1 0 ...
$ marital.married : num 1 0 1 1 1 0 0 1 0 1 ...
$ marital.single : num 0 1 0 0 0 1 1 0 0 0 ...
$ education.basic.4y : num 0 0 0 0 0 0 0 0 0 0 ...
$ education.basic.6y : num 0 0 0 0 0 0 0 0 0 0 ...
$ education.basic.9y : num 1 0 0 1 0 0 0 0 0 1 ...
$ education.high.school : num 0 1 1 0 0 0 0 0 0 0 ...
$ education.professional.course: num 0 0 0 0 0 0 0 0 1 0 ...
$ education.university.degree : num 0 0 0 0 1 1 1 1 0 0 ...
$ default.no : num 1 1 1 1 1 1 1 0 1 0 ...
$ default.unknown : num 0 0 0 0 0 0 0 1 0 1 ...
$ housing.no : num 0 1 0 0 0 1 0 0 1 1 ...
$ housing.yes : num 1 0 1 0 1 0 1 1 0 0 ...
$ loan.no : num 1 1 1 0 1 1 1 1 1 1 ...
$ loan.yes : num 0 0 0 0 0 0 0 0 0 0 ...
$ contact.cellular : num 1 0 0 0 1 1 1 1 1 0 ...
$ contact.telephone : num 0 1 1 1 0 0 0 0 0 1 ...
$ month.apr : num 0 0 0 0 0 0 0 0 0 0 ...
$ month.aug : num 0 0 0 0 0 0 0 0 0 0 ...
$ month.jul : num 0 0 0 0 0 0 0 0 0 0 ...
$ month.jun : num 0 0 1 1 0 0 0 0 0 0 ...
$ month.may : num 1 1 0 0 0 0 0 0 0 1 ...
$ month.nov : num 0 0 0 0 1 0 0 1 1 0 ...
$ day_of_week.fri : num 1 1 0 1 0 0 0 0 0 0 ...
$ day_of_week.mon : num 0 0 0 0 1 0 1 1 0 0 ...
$ day_of_week.thu : num 0 0 0 0 0 1 0 0 0 1 ...
$ day_of_week.tue : num 0 0 0 0 0 0 0 0 1 0 ...
$ day_of_week.wed : num 0 0 1 0 0 0 0 0 0 0 ...
$ duration : num 487 346 227 17 58 128 290 44 68 170 ...
$ campaign : num 2 4 1 3 1 3 4 2 1 1 ...
$ previous : num 0 0 0 0 0 2 0 0 1 0 ...
$ poutcome.failure : num 0 0 0 0 0 1 0 0 1 0 ...
$ poutcome.nonexistent : num 1 1 1 1 1 0 1 1 0 1 ...
$ emp.var.rate : num -1.8 1.1 1.4 1.4 -0.1 -1.1 -1.1 -0.1 -0.1 1.1 ...
$ cons.price.idx : num 92.9 94 94.5 94.5 93.2 ...
$ cons.conf.idx : num -46.2 -36.4 -41.8 -41.8 -42 -37.5 -37.5 -42 -42 -36.4 ...
$ euribor3m : num 1.31 4.86 4.96 4.96 4.19 ...
$ nr.employed : num 5099 5191 5228 5228 5196 ...
data$y <- as.factor(Y)
str(data)
'data.frame': 4119 obs. of 45 variables:
$ age : num 30 39 25 38 47 32 32 41 31 35 ...
$ job.admin. : num 0 0 0 0 1 0 1 0 0 0 ...
$ job.blue.collar : num 1 0 0 0 0 0 0 0 0 1 ...
$ job.management : num 0 0 0 0 0 0 0 0 0 0 ...
$ job.services : num 0 1 1 1 0 1 0 0 1 0 ...
$ job.technician : num 0 0 0 0 0 0 0 0 0 0 ...
$ marital.divorced : num 0 0 0 0 0 0 0 0 1 0 ...
$ marital.married : num 1 0 1 1 1 0 0 1 0 1 ...
$ marital.single : num 0 1 0 0 0 1 1 0 0 0 ...
$ education.basic.4y : num 0 0 0 0 0 0 0 0 0 0 ...
$ education.basic.6y : num 0 0 0 0 0 0 0 0 0 0 ...
$ education.basic.9y : num 1 0 0 1 0 0 0 0 0 1 ...
$ education.high.school : num 0 1 1 0 0 0 0 0 0 0 ...
$ education.professional.course: num 0 0 0 0 0 0 0 0 1 0 ...
$ education.university.degree : num 0 0 0 0 1 1 1 1 0 0 ...
$ default.no : num 1 1 1 1 1 1 1 0 1 0 ...
$ default.unknown : num 0 0 0 0 0 0 0 1 0 1 ...
$ housing.no : num 0 1 0 0 0 1 0 0 1 1 ...
$ housing.yes : num 1 0 1 0 1 0 1 1 0 0 ...
$ loan.no : num 1 1 1 0 1 1 1 1 1 1 ...
$ loan.yes : num 0 0 0 0 0 0 0 0 0 0 ...
$ contact.cellular : num 1 0 0 0 1 1 1 1 1 0 ...
$ contact.telephone : num 0 1 1 1 0 0 0 0 0 1 ...
$ month.apr : num 0 0 0 0 0 0 0 0 0 0 ...
$ month.aug : num 0 0 0 0 0 0 0 0 0 0 ...
$ month.jul : num 0 0 0 0 0 0 0 0 0 0 ...
$ month.jun : num 0 0 1 1 0 0 0 0 0 0 ...
$ month.may : num 1 1 0 0 0 0 0 0 0 1 ...
$ month.nov : num 0 0 0 0 1 0 0 1 1 0 ...
$ day_of_week.fri : num 1 1 0 1 0 0 0 0 0 0 ...
$ day_of_week.mon : num 0 0 0 0 1 0 1 1 0 0 ...
$ day_of_week.thu : num 0 0 0 0 0 1 0 0 0 1 ...
$ day_of_week.tue : num 0 0 0 0 0 0 0 0 1 0 ...
$ day_of_week.wed : num 0 0 1 0 0 0 0 0 0 0 ...
$ duration : num 487 346 227 17 58 128 290 44 68 170 ...
$ campaign : num 2 4 1 3 1 3 4 2 1 1 ...
$ previous : num 0 0 0 0 0 2 0 0 1 0 ...
$ poutcome.failure : num 0 0 0 0 0 1 0 0 1 0 ...
$ poutcome.nonexistent : num 1 1 1 1 1 0 1 1 0 1 ...
$ emp.var.rate : num -1.8 1.1 1.4 1.4 -0.1 -1.1 -1.1 -0.1 -0.1 1.1 ...
$ cons.price.idx : num 92.9 94 94.5 94.5 93.2 ...
$ cons.conf.idx : num -46.2 -36.4 -41.8 -41.8 -42 -37.5 -37.5 -42 -42 -36.4 ...
$ euribor3m : num 1.31 4.86 4.96 4.96 4.19 ...
$ nr.employed : num 5099 5191 5228 5228 5196 ...
$ y : Factor w/ 1 level "1:2": NA NA NA NA NA NA NA NA NA NA ...
data$y <- Y # as.factor(Y)
data <- data %>% mutate(y = as.factor(y))
str(data)
subsets <- c(7, 10, 12, 15, 20)
control <- rfeControl(functions = rfFuncs, method = "cv", verbose = FALSE)
system.time(
RFE_res <- rfe(x = data[, 1:44], # subset(train, select = -y)
y = pull(data$y),
sizes = subsets,
rfeControl = control
)
)
X = subset(iris,select=-Species)
Y = subset(iris,select=Species)
as.factor(Y)
Species
<NA>
Levels: 1:3
.valid.factor(Y)
[1] "factor levels must be \"character\""
levels(Y)
NULL
X$y = as.factor(Y$Species)
# or X %>% mutate(y = as.factor(Y$Species))
> str(X)
'data.frame': 150 obs. of 5 variables:
$ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
$ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
$ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
$ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
$ y : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...