Vector oluşturma

a<-c(1,2,3,4,5,6,7)
b<-c(4,3,4,4,6,7,8)
c<-c(“a”,”b”,”c”,”ç”,”d”,”e”,”f”)
d<-c(“male”,”female”,”female”,”female”,”female”,”male”,”female”)
e<-c(“white”,”white”,”red”,”red”,”blue”,”blue”,”blue”)

vector’lerden dataframe oluşturma

df<-data.frame(a,b,c,d,e)

dataframe özellikleri

str(df)

ggplot grafiği

ggplot(df, aes(x=a, y=b)) + geom_point()

The most basic barplot you can do:

barplot(height=df$b, names=df$c, col=”#69b3a2″)

The most basic barplot you can do:

barplot(height=df$b, names=df$c, col=”#69b3a2″, horiz=T , las=1)

ggplot(df, aes(x=b, y=c)) + geom_bar(stat = “identity”) + coord_flip()

https://sparkbyexamples.com/r-programming/

filter

library(dplyr)

filter(df, c==’ç’)

df_filtered <- filter(df, c %in% c(“a”, “d”, “f”))

df_filtered

filter() by multiple conditions

filter(df, b == 4 & c==’c’)

filter() by row number

slice(df, 2)

group by çalışması

grp_tbl_1 <- df %>% group_by(d)
agg_tbl_2 <- grp_tbl %>% summarise(sum(a))
agg_tbl_2

Group by on multiple columns

& multiple aggregations

agg_tbl <- df %>% group_by(d, e) %>%
summarise(total_b=sum(b),
total_a = sum(a),
min_b = min(b),
max_b = max(b),
.groups = ‘drop’
)
agg_tbl

distinct() usage on all columns

df2 <- df %>% distinct()
df2

Distinct on select columns

df3 <- df %>% distinct(d,e)
df3

Distinct of single column

df4 <- df %>% distinct(d, .keep_all = TRUE)
df4

lag dplyr

lag(b)
lead(b)

gruba göre bir önceki farkı alıyor.

mutate(df, diff = b – lag(b), .by = e)

library(ggplot2)
library(dplyr)
library(broom)
library(ggpubr)

histogram çizimi

plot(a,b)

correlation

cor(a,b)

regresyon ve özeti

lm(a~b, df)
summary(lm(a~b, df))

summary(lm(a~b, df))

lm(a~b+lag(b), df)

df_regression<-lm(a~b, df)
df_regression

par(mfrow=c(2,2))
plot(df_regression)
par(mfrow=c(1,1))

grafik

https://www.scribbr.com/statistics/linear-regression-in-r/

graph_df<-ggplot(df, aes(a,b))+geom_point()
graph_df

regresyon eklendi

graph_df<-graph_df+geom_smooth(method = “lm”, col=”blue”)
graph_df

regresyon denklemi eklendi.

graph_df<-graph_df+stat_regline_equation(label.x = 3, label.y = 8)
graph_df

başlık ve açıklama eklemeleri

graph_df+theme_bw() +
labs(title = “This is the example of Title”,
x = “Value of b (x$10,000)”,
y = “Value of a (0 to 10)”)

correlation grafikleri

https://r-graph-gallery.com/199-correlation-matrix-with-ggally.html

library(GGally)

Create data

data <- data.frame( var1 = 1:100 + rnorm(100,sd=20), v2 = 1:100 + rnorm(100,sd=27), v3 = rep(1, 100) + rnorm(100, sd = 1))
data$v4 = data$var1 ** 2
data$v5 = -(data$var1 ** 2)

Check correlations (as scatterplots), distribution and print corrleation coefficient

ggpairs(data, title=”correlogram with ggpairs()”)

Nice visualization of correlations

ggcorr(data, method = c(“everything”, “pearson”))

gruplayarak correlation

data(flea)
ggpairs(flea, columns = 2:4, ggplot2::aes(colour=species))

data(tips, package = “reshape”)
ggpairs(
tips[, c(1, 3, 4, 2)],
upper = list(continuous = “density”, combo = “box_no_facet”),
lower = list(continuous = “points”, combo = “dot_no_facet”)
)