Questions about ANOVA analysis in R of groups

I'm doing ANOVA analysis on a dataset that looks like:

ID	cluster	gender	description	country	age
124	1	F	SMALL	US	32
324	1	M	MEDIUM	CA	12
82	5	F	SMALL	US	45
453	2	F	LARGE	AU	34
...	...	...	...	...	...
473	3	M	SMALL	DK	32
172	4	M	LARGE	US	62
23	4	F	LARGE	US	23

This dataset is a summary of the data. My data is divided into 5 clusters, and I would like to see how all the other variables, except ID, are unique to each cluster. I was recommended to use an ANOVA analysis for this. I got some results, but they didn't quite line up with what I saw graphically. For example, I thought gender would be statistically significant given my bar graph visualization, but it's not. This is okay if true (obviously there is nothing I can do about it), but I wanted to check to be sure I was doing this correctly and to see if there is a different way to do this other than ANOVA.

here is what I have been doing:

one.way.gender <- aov(cluster ~ gender, data = data1)
summary(one.way.gender)

one.way.description <- aov(cluster ~ description, data = data1)
summary(one.way.description)

one.way.country <- aov(cluster ~ country, data = data1)
summary(one.way.country)

one.way.age <- aov(cluster ~ age, data = data1)
summary(one.way.age)

I know this is a very simple way of doing this, and I'm worried I'm missing something. I've went through a few tutorials with more lengthy code to the analysis, but they yield the same results as the simple code.

Solution

for categorical data use chi-square test:

library(dplyr)
library(purrr)

# Categorical variables
variables <- c("gender", "description", "country")

# chi-square test 
result <- variables %>% 
  map(~chisq.test(df$cluster, df[[.]]))

result

# output: 

[[1]]

    Pearson's Chi-squared test

data:  df$cluster and df[[.]]
X-squared = 2.9167, df = 4, p-value = 0.5719


[[2]]

    Pearson's Chi-squared test

data:  df$cluster and df[[.]]
X-squared = 9.3333, df = 8, p-value = 0.315


[[3]]

    Pearson's Chi-squared test

data:  df$cluster and df[[.]]
X-squared = 16.625, df = 12, p-value = 0.1643

for numeric data use Kruskal Wallis test:

# numeric variables
kruskal_age <- kruskal.test(age ~ cluster, data = df)
print(kruskal_age)

# output
    Kruskal-Wallis rank sum test

data:  age by cluster
Kruskal-Wallis chi-squared = 2.5909, df = 4, p-value = 0.6284