Basic R codes
This file provides essential R code to help users get started with data manipulation, analysis, and visualization tasks.
Load dataset
Load a csv file
# mtcars is a built-in dataset in R
# save a csv file
write.csv(mtcars, "/Users/tranchau/Documents/OMG_tutorial/dataset/data.csv")
# load a csv file
data_csv <- read.csv("/Users/tranchau/Documents/OMG_tutorial/dataset/data.csv", header = TRUE, row.names = 1)
# use absolute path which is the complete path to a file or directory from the root directory
# 'header = TRUE' to read the first row as column names, 'row.names = 1' to set the first column as row namesLoad a TSV (Tab-Separated Values) file
# save tsv file
write.table(mtcars, "/Users/tranchau/Documents/OMG_tutorial/dataset/data.tsv", sep = "\t", quote = FALSE)
# load a tsv file
data_tsv <- read.table("/Users/tranchau/Documents/OMG_tutorial/dataset/data.tsv", header = TRUE, row.names = 1, sep = "\t")
# 'sep = "\t"' specifies tab-separated valuesLoad an Excel file (.xlsx, .xls)
#install.packages("readxl", "writexl")
# 'readxl' is not a built-in package in R. It needs to be installed before using it
library(writexl)
write_xlsx(mtcars, "/Users/tranchau/Documents/OMG_tutorial/dataset/data.xlsx")
library(readxl)
data_excel <- read_excel("/Users/tranchau/Documents/OMG_tutorial/dataset/data.xlsx", sheet = 1)
# 'sheet' specifies the sheet number or nameLoad a RDS file, format for a single R object
# Save data as RDS file
saveRDS(mtcars, "/Users/tranchau/Documents/OMG_tutorial/dataset/data.rds")
# Load RDS file
data_rds <- readRDS("/Users/tranchau/Documents/OMG_tutorial/dataset/data.rds")Load RData, save multiple R objects
# Save multiple objects to an RData file
save(mtcars, mtcars, file = "/Users/tranchau/Documents/OMG_tutorial/dataset/data.RData")
# Load an RData file
load("/Users/tranchau/Documents/OMG_tutorial/dataset/data.RData")Data inspection
data(mtcars) # Loads the mtcars dataset
head(mtcars) # Displays the first few rows## mpg cyl disp hp drat wt qsec vs am gear carb
## Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4
## Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4
## Datsun 710 22.8 4 108 93 3.85 2.320 18.61 1 1 4 1
## Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1
## Hornet Sportabout 18.7 8 360 175 3.15 3.440 17.02 0 0 3 2
## Valiant 18.1 6 225 105 2.76 3.460 20.22 1 0 3 1str(mtcars) # Shows structure of the data## 'data.frame': 32 obs. of 11 variables:
## $ mpg : num 21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
## $ cyl : num 6 6 4 6 8 6 8 4 4 6 ...
## $ disp: num 160 160 108 258 360 ...
## $ hp : num 110 110 93 110 175 105 245 62 95 123 ...
## $ drat: num 3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
## $ wt : num 2.62 2.88 2.32 3.21 3.44 ...
## $ qsec: num 16.5 17 18.6 19.4 17 ...
## $ vs : num 0 0 1 1 0 1 0 1 1 1 ...
## $ am : num 1 1 1 0 0 0 0 0 0 0 ...
## $ gear: num 4 4 4 3 3 3 3 4 4 4 ...
## $ carb: num 4 4 1 1 2 1 4 2 2 4 ...summary(mtcars) # Provides a summary of each column## mpg cyl disp hp
## Min. :10.40 Min. :4.000 Min. : 71.1 Min. : 52.0
## 1st Qu.:15.43 1st Qu.:4.000 1st Qu.:120.8 1st Qu.: 96.5
## Median :19.20 Median :6.000 Median :196.3 Median :123.0
## Mean :20.09 Mean :6.188 Mean :230.7 Mean :146.7
## 3rd Qu.:22.80 3rd Qu.:8.000 3rd Qu.:326.0 3rd Qu.:180.0
## Max. :33.90 Max. :8.000 Max. :472.0 Max. :335.0
## drat wt qsec vs
## Min. :2.760 Min. :1.513 Min. :14.50 Min. :0.0000
## 1st Qu.:3.080 1st Qu.:2.581 1st Qu.:16.89 1st Qu.:0.0000
## Median :3.695 Median :3.325 Median :17.71 Median :0.0000
## Mean :3.597 Mean :3.217 Mean :17.85 Mean :0.4375
## 3rd Qu.:3.920 3rd Qu.:3.610 3rd Qu.:18.90 3rd Qu.:1.0000
## Max. :4.930 Max. :5.424 Max. :22.90 Max. :1.0000
## am gear carb
## Min. :0.0000 Min. :3.000 Min. :1.000
## 1st Qu.:0.0000 1st Qu.:3.000 1st Qu.:2.000
## Median :0.0000 Median :4.000 Median :2.000
## Mean :0.4062 Mean :3.688 Mean :2.812
## 3rd Qu.:1.0000 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :1.0000 Max. :5.000 Max. :8.000Data manipulation
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unioncleaned_data <- mtcars %>%
filter(mpg > 10) %>% #filter rows
select(mpg, cyl, disp) %>% #select columns
mutate(mpg_new = mpg * 2) #create new columns
head(cleaned_data)## mpg cyl disp mpg_new
## Mazda RX4 21.0 6 160 42.0
## Mazda RX4 Wag 21.0 6 160 42.0
## Datsun 710 22.8 4 108 45.6
## Hornet 4 Drive 21.4 6 258 42.8
## Hornet Sportabout 18.7 8 360 37.4
## Valiant 18.1 6 225 36.2Data summarization
# Group data by a column and calculate the mean of another column
summary_data <- mtcars %>%
group_by(cyl) %>%
summarise(mean_mpg = mean(mpg, na.rm = TRUE))
summary_data## # A tibble: 3 × 2
## cyl mean_mpg
## <dbl> <dbl>
## 1 4 26.7
## 2 6 19.7
## 3 8 15.1Data Visualization with ggplot2
# Load the library
library(ggplot2)
# Create a scatter plot with ggplot2
ggplot(mtcars, aes(x = mpg, y = disp)) +
geom_point(color = "pink2") +
labs(x = "mpg", y = "disp") +
theme_minimal() +
theme(
axis.title.x = element_text(size = 15, face = "bold"), #change the size of x-axis title
axis.title.y = element_text(size = 15, face = "bold"), #change the size of y-axis title
axis.text.x = element_text(size = 12), #change the size of text of x-axis
axis.text.y = element_text(size = 12) #change the size of text of y-axis
)
Statistical test
# Run a t-test to compare two groups
t_test_result <- t.test(disp ~ vs, data = mtcars)
t_test_result##
## Welch Two Sample t-test
##
## data: disp by vs
## t = 5.9416, df = 26.977, p-value = 2.477e-06
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
## 114.3628 235.0229
## sample estimates:
## mean in group 0 mean in group 1
## 307.1500 132.4571Linear Regression Model
linear <- lm(disp ~ mpg, data = mtcars)
summary(linear)##
## Call:
## lm(formula = disp ~ mpg, data = mtcars)
##
## Residuals:
## Min 1Q Median 3Q Max
## -103.05 -45.74 -8.17 46.65 153.75
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 580.884 41.740 13.917 1.26e-14 ***
## mpg -17.429 1.993 -8.747 9.38e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 66.86 on 30 degrees of freedom
## Multiple R-squared: 0.7183, Adjusted R-squared: 0.709
## F-statistic: 76.51 on 1 and 30 DF, p-value: 9.38e-10ggplot(mtcars, aes(x = mpg, y = disp)) +
geom_point(color = "pink2") +
geom_smooth(method = "lm", color = "black", se = FALSE) + # Adds the linear regression line
labs(x = "Miles per Gallon (mpg)", y = "Displacement (disp)") +
theme_minimal() +
theme(
axis.title.x = element_text(size = 15, face = "bold"),
axis.title.y = element_text(size = 15, face = "bold"),
axis.text.x = element_text(size = 12),
axis.text.y = element_text(size = 12)
)## `geom_smooth()` using formula = 'y ~ x'
Apply a function to each column in the dataframe
column_means <- sapply(mtcars, mean, na.rm = TRUE)
column_means## mpg cyl disp hp drat wt qsec
## 20.090625 6.187500 230.721875 146.687500 3.596563 3.217250 17.848750
## vs am gear carb
## 0.437500 0.406250 3.687500 2.812500column_means <- sapply(mtcars, max, na.rm = TRUE)
column_means## mpg cyl disp hp drat wt qsec vs am gear
## 33.900 8.000 472.000 335.000 4.930 5.424 22.900 1.000 1.000 5.000
## carb
## 8.000column_means <- sapply(mtcars, min, na.rm = TRUE)
column_means## mpg cyl disp hp drat wt qsec vs am gear carb
## 10.400 4.000 71.100 52.000 2.760 1.513 14.500 0.000 0.000 3.000 1.000Extract a pdf file
plot_linear = ggplot(mtcars, aes(x = mpg, y = disp)) +
geom_point(color = "pink2") +
geom_smooth(method = "lm", color = "black", se = FALSE) +
labs(x = "Miles per Gallon (mpg)", y = "Displacement (disp)") +
theme_minimal() +
theme(
axis.title.x = element_text(size = 15, face = "bold"),
axis.title.y = element_text(size = 15, face = "bold"),
axis.text.x = element_text(size = 12),
axis.text.y = element_text(size = 12)
)
plot_linear## `geom_smooth()` using formula = 'y ~ x'
pdf("/Users/tranchau/Documents/OMG_tutorial/dataset/save.pdf", width = 7, height = 5)
plot_linear ## `geom_smooth()` using formula = 'y ~ x'dev.off()## quartz_off_screen
## 2