r-expert

R Statistical Computing Expert

Expert guidance for R programming, statistical analysis, data visualization, and data science.

Core Concepts

R Fundamentals

• Vectors and data frames
• Factors and lists
• Functions and apply family
• Packages and libraries
• R Markdown
• Tidyverse ecosystem

Statistical Analysis

• Descriptive statistics
• Hypothesis testing
• Regression analysis
• ANOVA
• Time series analysis
• Machine learning

Data Visualization

• ggplot2
• Base R graphics
• Interactive plots (plotly)
• Statistical charts
• Maps and spatial data

R Basics

# Vectors
numbers <- c(1, 2, 3, 4, 5)
names <- c("Alice", "Bob", "Charlie")

# Data frames
df <- data.frame(
  id = 1:5,
  name = c("Alice", "Bob", "Charlie", "David", "Eve"),
  age = c(25, 30, 35, 28, 32),
  salary = c(50000, 60000, 55000, 52000, 58000)
)

# Subsetting
df[df$age > 30, ]  # Rows where age > 30
df[, c("name", "age")]  # Select columns

# Functions
calculate_mean <- function(x) {
  sum(x) / length(x)
}

# Apply family
sapply(df$age, function(x) x * 2)
lapply(list(1:5, 6:10), sum)

# Control structures
if (mean(df$age) > 30) {
  print("Average age is above 30")
} else {
  print("Average age is 30 or below")
}

# Loops
for (i in 1:nrow(df)) {
  print(df$name[i])
}

Tidyverse

library(dplyr)
library(tidyr)
library(stringr)

# dplyr operations
df %>%
  filter(age > 28) %>%
  select(name, age, salary) %>%
  mutate(
    salary_bonus = salary * 1.1,
    age_group = case_when(
      age < 30 ~ "Young",
      age < 35 ~ "Mid-career",
      TRUE ~ "Senior"
    )
  ) %>%
  arrange(desc(salary)) %>%
  group_by(age_group) %>%
  summarise(
    count = n(),
    avg_salary = mean(salary),
    total_salary = sum(salary)
  )

# Reshaping data
wide_data <- data.frame(
  id = 1:3,
  year_2021 = c(100, 200, 150),
  year_2022 = c(120, 210, 160)
)

# Wide to long
long_data <- wide_data %>%
  pivot_longer(
    cols = starts_with("year"),
    names_to = "year",
    values_to = "value",
    names_prefix = "year_"
  )

# Long to wide
wide_again <- long_data %>%
  pivot_wider(
    names_from = year,
    values_from = value,
    names_prefix = "year_"
  )

# String operations
df %>%
  mutate(
    name_upper = str_to_upper(name),
    name_length = str_length(name),
    first_letter = str_sub(name, 1, 1)
  )

# Joining data
df1 <- data.frame(id = 1:3, value1 = c("A", "B", "C"))
df2 <- data.frame(id = 2:4, value2 = c("X", "Y", "Z"))

inner_join(df1, df2, by = "id")
left_join(df1, df2, by = "id")
full_join(df1, df2, by = "id")