python打卡DAY44

t1 <- read.csv("elder1.csv")

t2 <- read.csv("elder2.csv")

library(dplyr)

tt <- merge(t1, t2, by = "ID", all = FALSE)

write.csv(tt, file = "ttnew.csv")

tt <- mutate(tt, bmi = weight / (height^2) * 10000)

 

tt$bmi[tt$bmi < 18.5] <- 0

tt$bmi[tt$bmi >= 18.5 & tt$bmi < 24] <- 1

tt$bmi[tt$bmi >= 24 & tt$bmi < 28] <- 2

tt$bmi[tt$bmi > 28] <- 3

tt$bmi2 <- tt$bmi

tt <- within(tt, {

bmi2 <- NA

bmi2[bmi < 18.5] <- 0

bmi2[bmi >= 18.5 & bmi < 24] <- 1

bmi2[bmi >= 24 & bmi < 28] <- 2

bmi2[bmi > 28] <- 3

bmi2 <- factor(bmi2, levels = c(0, 1, 2, 3))

})

print(levels(tt$bmi2))

print(table((tt$bmi2)))

tt$pressure <- ifelse(tt$SBP >= 140 | tt$DBP >= 90, 2, 1)

print(table(tt$pressure))

tt$sugar <- ifelse(tt$sugar > 7, 2, 1)

print(table(tt$sugar))

table(tt$income)

tt$income1[tt$income < 3] <- 0

tt$income1[tt$income >= 3 & tt$income < 6] <- 1

tt$incmoe1[tt$income >= 6] <- 2

print(table(tt$income1))

str(tt)

tt$sex <- factor(tt$sex)

tt$bmi1 <- factor(tt$bmi, levels = c(1, 0, 2, 3))

tt$pressure <- factor(tt$pressure)

tt$marriage <- factor(tt$marriage, levels = c(2, 1, 3, 4, 5))

str(tt)

# join数据合并

tt <- inner_join(t1, t2, by = c("ID"))

tt1 <- full_join(t1, t2, by = c("ID"))

tt2 <- left_join(t1, t2, by = c("ID"))

tt3 <- right_join(t1, t2, by = c("ID"))

# filter数据筛选

t11 <- filter(tt, SBP >= 140)

t12 <- filter(tt, SBP >= 140, DBP >= 90, sugar > 7)

t13 <- filter(tt, SBP >= 140 | DBP >= 90)

t14 <- filter(tt, sex == 1)

# arrange排列函数

t15 <- arrange(tt, SBP)

t16 <- arrange(tt, desc(DBP))

t17 <- arrange(tt, SBP, DBP)

t18 <- arrange(tt, desc(DBP), SBP)

# select选择函数

t19 <- select(tt, -DBP, -SBP)

t20 <- select(tt, DBP, HDL, everything(), -ID)

# mutate变形函数

t21 <- mutate(tt, x1 = weight * 2, x2 = height / 100)

print(table(tt$income))

t22 <- mutate(tt, income = recode(income,

"1" = 1, "2" = 1, "3" = 2, "4" = 2, "5" = 3, "6" = 3, "7" = 4, "8" = 4

))

t22$income <- factor(t22$income)

print(table(t22$income))

str(t22)

# summarise

t23 <- summarise(tt, DBP_mean = mean(DBP), DBP_median = median(DBP))

t24 <- t1 %>%

summarise(across(

c(DBP, SBP),

list(

count = ~ n(),

mean = ~ mean(., na.rm = TRUE),

median = ~ median(., na.rm = TRUE)

)

))

t25 <- t1 %>%

summarise(across(

where(is.numeric),

list(

count = ~ n(),

mean = ~ mean(., na.rm = TRUE),

median = ~ median(., na.rm = TRUE)

)

))

# group by

tt01 <- group_by(tt, sex)

tt02 <- summarise(tt01, count = n())

tt03 <- tt01 %>%

summarise(across(c(DBP, SBP), list(

mean = ~ mean(., na.rm = TRUE),

median = ~ median(., na.rm = TRUE),

count = ~ sum(!is.na(.))

)))