python打卡DAY42

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

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

# tt <- merge(elder1, elder2, by = "ID", all = FALSE)

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

# attach(tt)

# tt <- transform(tt, SBPD = SBP - 140, bmi = weight / height / height * 10000)

# View(tt) # nolint: commented_code_linter.

# detach(tt)

# attach(tt)

# tt$bmi1[bmi < 18.5] <- 0

# tt$bmi1[bmi >= 18.5 & bmi < 24] <- 1

# tt$bmi1[bmi >= 24 & bmi < 28] <- 2

# tt$bmi1[bmi >= 28] <- 3

# levels(tt$bmi1)

# table(tt$bmi1)

# detach(tt)

# 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$income1[tt$income >= 6] <- 2

# print(table(tt$income1))

# str(tt)

# tt$sex <- factor(tt$sex)

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

# tt$pressure <- factor(tt$pressure)

# tt$income1 <- factor(tt$income1)

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

 

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

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

# tt <- merge(elder1, elder2, by = "ID", all = FALSE)

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

# attach(tt)

# tt <- transform(tt, SBPD = SBP - 140, bmi = weight / height / height * 10000)

# detach(tt)

# attach(tt)

# tt$bmi1[bmi <= 18.5] <- 0

# tt$bmi1[bmi > 18.5 & bmi <= 24] <- 1

# tt$bmi1[bmi > 24 & bmi < 28] <- 2

# tt$bmi1[bmi > 28] <- 3

# levels(tt$bmi1)

# table(tt$bmi1)

# detach(tt)

# tt <- tt$bmitt <- 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$income[tt$income > 6] <- 2

# print(table(tt$income))

# str(tt)

# tt$sex <- factor(tt$sex)

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

# tt$pressure <- factor(tt$pressure)

# tt$income1 <- factor(tt$income1)

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

# print(is.na(elder1$height))

# print(which(is.na(elder1$height)))

# t1 <- elder1[which(is.na(elder1$height) == TRUE), ]

# print(dim(t1))

# t2 <- elder1[which(is.na(elder1$height) == FALSE), ]

# print(dim(t2))

# View(t2)

library(dplyr)

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

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

# 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(t1, SBP >= 140)

t12 <- filter(t1, SBP >= 140, DBP >= 90, sugar > 7)

t13 <- filter(t1, SBP >= 140 | DBP >= 90)

t14 <- filter(t2, sex == 1)

 

# # arrange排列函数

# arrange(t1, SBP)

# arrange(t1, desc(DBP))

# arrange(t1, SBP, DBP)

# arrange(t1, desc(DBP), SBP)

 

# select选择函数

t15 <- select(t1, -DBP, -SBP)

t16 <- select(t1, ID, DBP, HDL, everything())

# mutate变形函数

t19 <- mutate(t1, bmi = weight / (height^2) * 10000)

t20 <- mutate(t1, x1 = weight * 2, x2 = height / 100)

print(table(t2$income))

t2$income <- factor(t2$income)

t2 <- mutate(t2, income1 = recode(income,

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

))

t2$income1 <- factor(t2$income1)

print(table(t2$income1))

# summarise

summarise(t1, DBP_mean = mean(DBP), DBp_median = median(DBP))

t1 %>%

summarise(across(

c(DBP, SBP),

list(

count = ~ n(),

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

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

)

))

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)

summarise(tt01, count = n())

tt02 <- tt01 %>%

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

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

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

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

)))