stroke-prediction/visualize2.R at main · men1164/stroke-prediction · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
library(tidyverse)
df <- read.csv("healthcare-dataset-stroke-data.csv")

df %>%
  group_by(gender) %>%
  filter(bmi != "N/A",gender != "Other") %>%
  mutate(hypertension = factor(ifelse(hypertension == 1, "yes", "no")),
         heart_disease = factor(ifelse(heart_disease == 1, "yes", "no")),
         stroke = factor(ifelse(stroke == 1, "yes", "no")),
         bmi = as.double(bmi)) %>%
  mutate_if(is.character, as.factor) -> stroke_mod

  summary(stroke_mod)

#gender
  ggplot(stroke_mod,aes(gender,fill = stroke)) +
  geom_bar() +
    labs(title = "Gender:stroke")

#hypertension
  ggplot(stroke_mod,aes(hypertension,fill = stroke))+
    geom_bar()+
    labs(title = "Hypertension:stroke")

#heart disease
  ggplot(stroke_mod,aes(heart_disease,fill = stroke))+
    geom_bar()+
    labs(title = "Heart disease:stroke")

#married
  ggplot(stroke_mod,aes(ever_married,fill = stroke))+
    geom_bar()+
    labs(title = "Ever-married:stroke")


#work-type
  ggplot(stroke_mod,aes(work_type,fill = stroke))+
    geom_bar() +
      labs(title = "Hypertension:stroke")


#residence
  ggplot(stroke_mod,aes(Residence_type,fill = stroke))+
    geom_bar()+
      labs(title = "Residence:stroke")

#smoking status
  ggplot(stroke_mod,aes(smoking_status,fill = stroke))+
    geom_bar()+
      labs(title = "Smoking status:stroke")