data analysis in r

main.r
library(readxl) # for read_excel()

# read a csv file
data <- read.csv("path/to/file.csv")

# read a tab-separated file
data <- read.table("path/to/file.txt", header = TRUE, sep = "\t")

# read an Excel file
data <- read_excel("path/to/file.xlsx", sheet = "Sheet1")
266 chars
11 lines

main.r
# view the structure of the data
str(data)

# get summary statistics for the data
summary(data)

# view the first few rows of the data
head(data)
146 chars
9 lines

main.r
# subset the data to select specific rows and columns
subset(data, select = c("column1", "column2"), subset = column3 > 0)

# merge multiple data frames together by a common variable
merged_data <- merge(data1, data2, by = "column_name")

# reshape the data from wide to long format using `reshape2` package
library(reshape2)
melted_data <- melt(data, id.vars = c("variable1", "variable2"), 
                    measure.vars = c("column1", "column2"))
452 chars
11 lines

main.r
# calculate the correlation between two variables
cor(data$column1, data$column2)

# perform a two-sample t-test
t.test(data$column1 ~ data$column2)

# fit a linear regression model
model <- lm(column1 ~ column2 + column3, data = data)
summary(model)
251 chars
10 lines

main.r
# plot a histogram of a variable
library(ggplot2)
ggplot(data, aes(x = column1)) +
  geom_histogram()

# create a scatter plot of two variables
ggplot(data, aes(x = column1, y = column2)) +
  geom_point()

# create a bar chart of a categorical variable
ggplot(data, aes(x = category, fill = group)) +
  geom_bar()
314 chars
13 lines