Phan tich du lieu R Markdown_ngay 1
Tri Nguyen
2026-01-06
Ngày 1: Giới thiệu R
Việc 1: Tải R
Việc 2: Cài đặt Packages
library(lessR)##
## lessR 4.5 feedback: gerbing@pdx.edu
## --------------------------------------------------------------
## > d <- Read("") Read data file, many formats available, e.g., Excel
## d is the default data frame, data= in analysis routines optional
##
## Many examples of reading, writing, and manipulating data, graphics,
## testing means and proportions, regression, factor analysis,
## customization, forecasting, and aggregation to pivot tables.
## Enter: browseVignettes("lessR")
##
## View lessR updates, now including modern time series forecasting
## and many, new Plotly interactive visualizations output. Most
## visualization functions are now reorganized to three functions:
## Chart(): type="bar", "pie", "radar", "bubble", "treemap", "icicle"
## X(): type="histogram", "density", "vbs" and more
## XY(): type="scatter" for a scatterplot, or "contour", "smooth"
## Most previous function calls still work, such as:
## BarChart(), Histogram, and Plot().
## Enter: news(package="lessR"), or ?Chart, ?X, or ?XY
## There is also Flows() for Sankey flow diagrams, see ?Flows
##
## Interactive data analysis for constructing visualizations.
## Enter: interact()library(table1)##
## Attaching package: 'table1'## The following object is masked from 'package:lessR':
##
## label## The following objects are masked from 'package:base':
##
## units, units<-library(ggplot2)Việc 3: Đọc dữ liệu “Stroke Data.csv” vào R và gọi dữ liệu là “df”
df <- read.csv("Stroke Data.csv")Việc 4: Thông tin về dữ liệu df này
4.1 Có bao nhiêu biến số (variable) và quan sát (observation)
dim(df)## [1] 5110 124.2 Liệt kê 10 quan sát đầu tiên của dữ liệu.
head(df, 10)## id gender age hypertension heart_disease ever_married work_type
## 1 9046 Male 67 0 1 Yes Private
## 2 51676 Female 61 0 0 Yes Self-employed
## 3 31112 Male 80 0 1 Yes Private
## 4 60182 Female 49 0 0 Yes Private
## 5 1665 Female 79 1 0 Yes Self-employed
## 6 56669 Male 81 0 0 Yes Private
## 7 53882 Male 74 1 1 Yes Private
## 8 10434 Female 69 0 0 No Private
## 9 27419 Female 59 0 0 Yes Private
## 10 60491 Female 78 0 0 Yes Private
## Residence_type avg_glucose_level bmi smoking_status stroke
## 1 Urban 228.69 36.6 formerly smoked 1
## 2 Rural 202.21 NA never smoked 1
## 3 Rural 105.92 32.5 never smoked 1
## 4 Urban 171.23 34.4 smokes 1
## 5 Rural 174.12 24.0 never smoked 1
## 6 Urban 186.21 29.0 formerly smoked 1
## 7 Rural 70.09 27.4 never smoked 1
## 8 Urban 94.39 22.8 never smoked 1
## 9 Rural 76.15 NA Unknown 1
## 10 Urban 58.57 24.2 Unknown 14.3 Liệt kê 6 quan sát cuối cùng của dữ liệu
tail(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 04.4 Tóm tắt dữ liệu bằng hàm summary
summary(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 :201Việc 5: Biên tập dữ liệu
5.1 Mã hoá biến sex
5.1 Mã hóa biến gender (Female/Male/Other) thành biến sex với giá trị 0/1/2 (0= Male; 1= Female; 2= Other)
df$sex <- NA
df$sex[df$gender == "Female"] = 0
df$sex[df$gender == "Male"] = 1
df$sex[df$gender == "Other"] = 2
df$sex <- factor(df$sex, levels = c(0,1,2),
labels = c("Male","Female","Other"))
table(df$sex)##
## Male Female Other
## 2994 2115 15.2 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”
df$bmi_cat[df$bmi< 18.5]= "Underweight"
df$bmi_cat[df$bmi>= 18.5 & df$bmi < 25.0]= "Normal"
df$bmi_cat[df$bmi>= 25.0 & df$bmi < 30.0]= "Overweight"
df$bmi_cat[df$bmi>= 30]= "Obese"
table(df$bmi_cat)##
## Normal Obese Overweight Underweight
## 1243 1920 1409 3375.3 Biến Stroke 1
5.3 Chuyển biến số stroke thành biếnfactor với giá trị mới (0= No; 1= Yes)
df$stroke1 = as.factor(df$stroke)
df$stroke2 = as.factor(df$stroke)
table(df$stroke1, df$stroke)##
## 0 1
## 0 4861 0
## 1 0 249head(df)## id gender age hypertension heart_disease ever_married work_type
## 1 9046 Male 67 0 1 Yes Private
## 2 51676 Female 61 0 0 Yes Self-employed
## 3 31112 Male 80 0 1 Yes Private
## 4 60182 Female 49 0 0 Yes Private
## 5 1665 Female 79 1 0 Yes Self-employed
## 6 56669 Male 81 0 0 Yes Private
## Residence_type avg_glucose_level bmi smoking_status stroke sex
## 1 Urban 228.69 36.6 formerly smoked 1 Female
## 2 Rural 202.21 NA never smoked 1 Male
## 3 Rural 105.92 32.5 never smoked 1 Female
## 4 Urban 171.23 34.4 smokes 1 Male
## 5 Rural 174.12 24.0 never smoked 1 Male
## 6 Urban 186.21 29.0 formerly smoked 1 Female
## bmi_cat stroke1 stroke2
## 1 Obese 1 1
## 2 <NA> 1 1
## 3 Obese 1 1
## 4 Obese 1 1
## 5 Normal 1 1
## 6 Overweight 1 1Việc 6: Phân tích mô tả
6.1 Mô tả đặc điểm tuổi (age), giới tính (gender), bệnh cao huyết áp (hypertension), bệnh tim (heart_disease), tình trạng gia đình (ever_married), việc làm (work_type), nơi ở (Residence_type), nồng độ đường huyết (avg_glucose_level), chỉ số khối cơ thể (bmi), và tình trạng hút thuốc (smoking_status) theo tình trạng đột quị (stroke)
library(table1)
table1(~age + gender + hypertension + heart_disease + work_type + Residence_type + avg_glucose_level + bmi + smoking_status | stroke, data = df)## Warning in table1.formula(~age + gender + 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) |
|
|---|---|---|---|
| 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] |
| 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%) |
| 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%) |
| Residence_type | |||
| Rural | 2400 (49.4%) | 114 (45.8%) | 2514 (49.2%) |
| Urban | 2461 (50.6%) | 135 (54.2%) | 2596 (50.8%) |
| avg_glucose_level | |||
| Mean (SD) | 105 (43.8) | 133 (61.9) | 106 (45.3) |
| Median [Min, Max] | 91.5 [55.1, 268] | 105 [56.1, 272] | 91.9 [55.1, 272] |
| bmi | |||
| Mean (SD) | 28.8 (7.91) | 30.5 (6.33) | 28.9 (7.85) |
| Median [Min, Max] | 28.0 [10.3, 97.6] | 29.7 [16.9, 56.6] | 28.1 [10.3, 97.6] |
| Missing | 161 (3.3%) | 40 (16.1%) | 201 (3.9%) |
| 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%) |
table1(~age + hypertension + heart_disease + bmi + smoking_status | stroke, data = df)## Warning in table1.formula(~age + hypertension + heart_disease + bmi +
## smoking_status | : 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) |
|
|---|---|---|---|
| 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] |
| bmi | |||
| Mean (SD) | 28.8 (7.91) | 30.5 (6.33) | 28.9 (7.85) |
| Median [Min, Max] | 28.0 [10.3, 97.6] | 29.7 [16.9, 56.6] | 28.1 [10.3, 97.6] |
| Missing | 161 (3.3%) | 40 (16.1%) | 201 (3.9%) |
| 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%) |
6.2 Bạn nhận xét như thế nào về kết quả của bệnh cao huyết áp và bệnh tim. Làm cách nào để trình bày kết quả tốt hơn?
library(ggplot2)
ggplot(df, aes(x = factor(stroke), fill = factor(hypertension))) +
geom_bar(position = "fill") +
labs(x = "Stroke", y = "Tỷ lệ", fill = "Hypertension")