Question

**你好每一个，我是R语言的新手，我正在尝试将数据从分类转换为数字，我读了Database.csv，我做了所有的操作，但我在结果中遇到错误，代码没有运行，错误“错误在r-arguments-imply-different-number-of-rows-4 7”

注意：我的数据库只包含一行，我试过其他数据库，包括多行和所有操作。

这是我的数据库，在我的代码下面。 https://my.pcloud.com/publink/show?code=XZbbjNZoNfJRmssXnSj8tQq6qjOyJayKwyX

是的，请帮助我。 **

rm(list=ls(all=TRUE))
setwd("C:/Users/maher/Desktop/R")

# Load required libraries
library(vegan)
library(dummies)
library(dummy)
library(e1071)
attr = c('id', 'age', 'exp', 'inc', 'zip', 'family', 
     'ccavg', 'edu', 'mortgage', 'loan', 
     'securities', 'cd', 'online', 'cc')

# Read the data using csv file
data = read.csv(file = "One.csv", 
            header = TRUE, col.names = attr)

# Removing the id, zip and experience. 
drop_Attr = c("id", "zip", "exp")
attr = setdiff(attr, drop_Attr)
data = data[, attr]
rm(drop_Attr)

# Convert attribute to appropriate type  
cat_Attr = c("family", "edu", "securities", 
         "cd", "online", "cc", "loan")
num_Attr = setdiff(attr, cat_Attr)
cat_Data <- data.frame(sapply(data[,cat_Attr], as.factor))
num_Data <- data.frame(sapply(data[,num_Attr], as.numeric))

data = cbind(num_Data, cat_Data)

# Do the summary statistics and check for missing values and outliers.
summary(data)

#------------------------------------------------------

ind_Num_Attr = num_Attr
rm(num_Attr)
ind_Cat_Attr = setdiff(cat_Attr, "loan")
rm(cat_Attr)

# Standardizing the numeric data
cla_Data = decostand(data[,ind_Num_Attr], "range") 
rm(ind_Num_Attr)

# Convert all categorical attributes to numeric 
# 1. Using dummy function, convert education and family        categorical**strong text** attributes into numeric attributes  
edu = dummy(data.frame(data$edu))
family = dummy(data.frame(data$family))
cla_Data = cbind(cla_Data, edu, family)
ind_Cat_Attr = setdiff(ind_Cat_Attr, c("edu", "family"))
rm(edu, family)

# 2. Using as.numeric function, convert remaining categorical attributes into numeric attributes 
cla_Data = cbind(cla_Data, sapply(data[,ind_Cat_Attr], as.numeric))
ind_Attr = names(cla_Data)
cla_Data = cbind(cla_Data, loan=data[,"loan"]) 
str(cla_Data)
cla_Data <- data.frame(sapply(cla_Data,as.numeric))
summary(cla_Data)
write.csv(cla_Data,"OneAfter.csv")

Answer 1

以下是一些修订后的代码。

- 在sep = ";"

中使用read.csv

- 我在colClasses上使用了read.csv来正确设置初始类型。我更喜欢这个清楚正确的类型。这消除了一些转换

- 我删除了所有rm语句，因为它使代码难以阅读并且通常不是必需的

- 您的剩余转化次数看起来是正确的。

- 注意：我添加了数据[2，]＆lt; - data [1，]以添加第二行测试数据。我相信你的一些sapply没有正常工作，因为只有一行被视为向量。删除此文件以获取完整文件

# Load required libraries
library(vegan)
library(dummies)
library(dummy)
library(e1071)
attr = c('id', 'age', 'exp', 'inc', 'zip', 'family', 
         'ccavg', 'edu', 'mortgage', 'loan', 
         'securities', 'cd', 'online', 'cc')
classes = c("NULL", "numeric", "NULL", "numeric", "NULL", "factor",
            "numeric", "factor", "numeric", "factor",
            "factor", "factor", "factor", "factor")

# Read the data using csv file
data  <- read.csv(file = "~/Downloads/one.csv", sep = ";", 
                  col.names = attr, colClasses = classes)
data[2,] <- data[1,]

num_Attr <- names(data)[sapply(data[1,], class)== "numeric"]
cat_Attr <- names(data)[sapply(data[1,], class)== "factor"]

# Do the summary statistics and check for missing values and outliers.
summary(data)

#------------------------------------------------------

ind_Num_Attr = num_Attr
ind_Cat_Attr = setdiff(cat_Attr, "loan")

# Standardizing the numeric data
cla_Data = decostand(data[,ind_Num_Attr], "range") 

# Convert all categorical attributes to numeric 
# 1. Using dummy function, convert education and family        categorical**strong text** attributes into numeric attributes  
edu = dummy(data.frame(data$edu))
family = dummy(data.frame(data$family))
cla_Data = cbind(cla_Data, edu, family)
ind_Cat_Attr = setdiff(ind_Cat_Attr, c("edu", "family"))

# 2. Using as.numeric function, convert remaining categorical attributes into numeric attributes 
cla_Data = cbind(cla_Data, sapply(data[,ind_Cat_Attr], as.numeric))
ind_Attr = names(cla_Data)
cla_Data = cbind(cla_Data, loan=data[,"loan"]) 
str(cla_Data)
cla_Data <- data.frame(sapply(cla_Data,as.numeric))
summary(cla_Data)
write.csv(cla_Data,"OneAfter.csv")

R语言：将分类转换为数字

1 个答案: