##Việc 1 ##Việc 2
#install.packages(c("lessR", "table1", "simpleboot", "boot", "gapminder", "ggfortify", "DescTools", "epiDisplay", "BMA", "ggplot2", "gridExtra", "metafor", "MatchIt", "cobalt"), dependencies = T)##Viec 3
df <- read.csv(file.choose())
dim(df)## [1] 5110 12tail(df,6)## id gender age hypertension heart_disease ever_married work_type
## 5105 14180 Female 13 0 0 No children
## 5106 18234 Female 80 1 0 Yes Private
## 5107 44873 Female 81 0 0 Yes Self-employed
## 5108 19723 Female 35 0 0 Yes Self-employed
## 5109 37544 Male 51 0 0 Yes Private
## 5110 44679 Female 44 0 0 Yes Govt_job
## Residence_type avg_glucose_level bmi smoking_status stroke
## 5105 Rural 103.08 18.6 Unknown 0
## 5106 Urban 83.75 NA never smoked 0
## 5107 Urban 125.20 40.0 never smoked 0
## 5108 Rural 82.99 30.6 never smoked 0
## 5109 Rural 166.29 25.6 formerly smoked 0
## 5110 Urban 85.28 26.2 Unknown 0summary(df)## id gender age hypertension
## Min. : 67 Length:5110 Min. : 0.08 Min. :0.00000
## 1st Qu.:17741 Class :character 1st Qu.:25.00 1st Qu.:0.00000
## Median :36932 Mode :character Median :45.00 Median :0.00000
## Mean :36518 Mean :43.23 Mean :0.09746
## 3rd Qu.:54682 3rd Qu.:61.00 3rd Qu.:0.00000
## Max. :72940 Max. :82.00 Max. :1.00000
##
## heart_disease ever_married work_type Residence_type
## Min. :0.00000 Length:5110 Length:5110 Length:5110
## 1st Qu.:0.00000 Class :character Class :character Class :character
## Median :0.00000 Mode :character Mode :character Mode :character
## Mean :0.05401
## 3rd Qu.:0.00000
## Max. :1.00000
##
## avg_glucose_level bmi smoking_status stroke
## Min. : 55.12 Min. :10.30 Length:5110 Min. :0.00000
## 1st Qu.: 77.25 1st Qu.:23.50 Class :character 1st Qu.:0.00000
## Median : 91.89 Median :28.10 Mode :character Median :0.00000
## Mean :106.15 Mean :28.89 Mean :0.04873
## 3rd Qu.:114.09 3rd Qu.:33.10 3rd Qu.:0.00000
## Max. :271.74 Max. :97.60 Max. :1.00000
## NA's :201df$sex[df$gender=="Female"] = 0
df$sex[df$gender=="Male"] = 1
df$sex[df$gender=="Other"] = 2
#head(df)
#table(df$gender,df$sex)###Mã hoá biến bmi
Nếu bmi < 18.5 thì bmi_cat = “Underweight”
Nếu 18.5 bmi < 25.0 thì bmi_cat = “Normal”
Nếu 25.0 bmi < 30 thì bmi_cat = “Overweight”
Nếu bmi ≥ 30.0 thì bmi = “Obese” library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, uniondf <- df %>%
mutate(bmi_cat = case_when(
bmi < 18.5 ~ "Underweight",
bmi >= 18.5 & bmi < 25 ~ "Normal",
bmi >= 25 & bmi < 30 ~ "Overweight",
bmi >= 30 ~ "Obese"
))
table(df$bmi_cat)##
## Normal Obese Overweight Underweight
## 1243 1920 1409 337###factor
df$stroke1= as.factor(df$stroke)###mo ta
library(table1)##
## Attaching package: 'table1'## The following objects are masked from 'package:base':
##
## units, units<-table1(~ gender + age + hypertension + heart_disease +
work_type + smoking_status | stroke,
data = df)## Warning in table1.formula(~gender + age + hypertension + heart_disease + :
## Terms to the right of '|' in formula 'x' define table columns and are expected
## to be factors with meaningful labels.| 0 (N=4861) |
1 (N=249) |
Overall (N=5110) |
|
|---|---|---|---|
| gender | |||
| Female | 2853 (58.7%) | 141 (56.6%) | 2994 (58.6%) |
| Male | 2007 (41.3%) | 108 (43.4%) | 2115 (41.4%) |
| Other | 1 (0.0%) | 0 (0%) | 1 (0.0%) |
| age | |||
| Mean (SD) | 42.0 (22.3) | 67.7 (12.7) | 43.2 (22.6) |
| Median [Min, Max] | 43.0 [0.0800, 82.0] | 71.0 [1.32, 82.0] | 45.0 [0.0800, 82.0] |
| hypertension | |||
| Mean (SD) | 0.0889 (0.285) | 0.265 (0.442) | 0.0975 (0.297) |
| Median [Min, Max] | 0 [0, 1.00] | 0 [0, 1.00] | 0 [0, 1.00] |
| heart_disease | |||
| Mean (SD) | 0.0471 (0.212) | 0.189 (0.392) | 0.0540 (0.226) |
| Median [Min, Max] | 0 [0, 1.00] | 0 [0, 1.00] | 0 [0, 1.00] |
| work_type | |||
| children | 685 (14.1%) | 2 (0.8%) | 687 (13.4%) |
| Govt_job | 624 (12.8%) | 33 (13.3%) | 657 (12.9%) |
| Never_worked | 22 (0.5%) | 0 (0%) | 22 (0.4%) |
| Private | 2776 (57.1%) | 149 (59.8%) | 2925 (57.2%) |
| Self-employed | 754 (15.5%) | 65 (26.1%) | 819 (16.0%) |
| smoking_status | |||
| formerly smoked | 815 (16.8%) | 70 (28.1%) | 885 (17.3%) |
| never smoked | 1802 (37.1%) | 90 (36.1%) | 1892 (37.0%) |
| smokes | 747 (15.4%) | 42 (16.9%) | 789 (15.4%) |
| Unknown | 1497 (30.8%) | 47 (18.9%) | 1544 (30.2%) |
library(table1)
df$hypertension <- factor(df$hypertension,
levels = c(0, 1),
labels = c("No", "Yes"))
table1(~ hypertension +
work_type + smoking_status | stroke,
data = df)## Warning in table1.formula(~hypertension + work_type + smoking_status | stroke,
## : Terms to the right of '|' in formula 'x' define table columns and are
## expected to be factors with meaningful labels.| 0 (N=4861) |
1 (N=249) |
Overall (N=5110) |
|
|---|---|---|---|
| hypertension | |||
| No | 4429 (91.1%) | 183 (73.5%) | 4612 (90.3%) |
| Yes | 432 (8.9%) | 66 (26.5%) | 498 (9.7%) |
| work_type | |||
| children | 685 (14.1%) | 2 (0.8%) | 687 (13.4%) |
| Govt_job | 624 (12.8%) | 33 (13.3%) | 657 (12.9%) |
| Never_worked | 22 (0.5%) | 0 (0%) | 22 (0.4%) |
| Private | 2776 (57.1%) | 149 (59.8%) | 2925 (57.2%) |
| Self-employed | 754 (15.5%) | 65 (26.1%) | 819 (16.0%) |
| smoking_status | |||
| formerly smoked | 815 (16.8%) | 70 (28.1%) | 885 (17.3%) |
| never smoked | 1802 (37.1%) | 90 (36.1%) | 1892 (37.0%) |
| smokes | 747 (15.4%) | 42 (16.9%) | 789 (15.4%) |
| Unknown | 1497 (30.8%) | 47 (18.9%) | 1544 (30.2%) |