# Vectors
numbers <- c(1, 2, 3, 4, 5)
names <- c("Alice", "Bob", "Charlie")
 
# Data frames
data <- data.frame(
    name = c("Alice", "Bob", "Charlie"),
    age = c(25, 30, 35),
    score = c(95, 87, 92)
)
 
# Lists
results <- list(
    model = lm(score ~ age, data = data),
    summary_stats = summary(data),
    plots = list()
)
 
# Matrices
matrix_data <- matrix(1:12, nrow = 3, ncol = 4)

# Data filtering and selection
filtered_data <- data[dataage > 25, ]
high_scores <- subset(data, score > 90)
 
# Aggregation
aggregate_results <- aggregate(score ~ department, data = employee_data, mean)
 
# Apply functions
means_by_column <- apply(numeric_data, 2, mean)
row_sums <- apply(numeric_data, 1, sum)

library(dplyr)
library(magrittr)
 
# Modern data manipulation
result <- employee_data %>%
    filter(department == "Engineering") %>%
    group_by(level) %>%
    summarise(
        avg_salary = mean(salary),
        count = n(),
        median_experience = median(years_experience)
    ) %>%
    arrange(desc(avg_salary))
 
# Data transformation
transformed_data <- raw_data %>%
    mutate(
        log_value = log(value),
        normalized_score = (score - mean(score)) / sd(score),
        category_factor = as.factor(category)
    ) %>%
    select(id, log_value, normalized_score, category_factor)

library(tidyr)
 
# Pivot operations
wide_data <- long_data %>%
    pivot_wider(
        names_from = variable,
        values_from = value
    )
 
long_data <- wide_data %>%
    pivot_longer(
        cols = c(var1, var2, var3),
        names_to = "variable",
        values_to = "value"
    )
 
# Separate and unite columns
separated <- data %>%
    separate(full_name, into = c("first", "last"), sep = " ")
 
united <- data %>%
    unite("full_address", street, city, state, sep = ", ")

# Summary statistics
summary(data)
str(data)
 
# Custom summaries
descriptive_stats <- data %>%
    summarise(
        mean_value = mean(value, na.rm = TRUE),
        median_value = median(value, na.rm = TRUE),
        sd_value = sd(value, na.rm = TRUE),
        q25 = quantile(value, 0.25, na.rm = TRUE),
        q75 = quantile(value, 0.75, na.rm = TRUE),
        correlation = cor(value1, value2, use = "complete.obs")
    )

# T-tests
t_test_result <- t.test(group_a, group_b)
print(t_test_result)
 
# ANOVA
anova_model <- aov(response ~ factor1 * factor2, data = experimental_data)
summary(anova_model)
TukeyHSD(anova_model)
 
# Chi-square test
chi_square <- chisq.test(contingency_table)
print(chi_square)
 
# Correlation tests
cor_test <- cor.test(x, y, method = "pearson")
print(cor_test)

# Linear regression
linear_model <- lm(dependent_var ~ independent_var1 + independent_var2, 
                   data = dataset)
summary(linear_model)
 
# Model diagnostics
par(mfrow = c(2, 2))
plot(linear_model)
 
# Multiple regression with interaction
complex_model <- lm(y ~ x1 * x2 + x3 + I(x1^2), data = dataset)
anova(linear_model, complex_model)  # Model comparison
 
# Logistic regression
logistic_model <- glm(binary_outcome ~ predictor1 + predictor2, 
                      family = binomial, data = dataset)
summary(logistic_model)

# Basic plots
plot(x, y, main = "Scatter Plot", xlab = "X Variable", ylab = "Y Variable")
lines(x, fitted_values, col = "red", lwd = 2)
 
# Histograms and density plots
hist(datavariable, breaks = 30, main = "Distribution")
lines(density(datavariable), col = "red", lwd = 2)
 
# Box plots
boxplot(value ~ category, data = dataset, main = "Values by Category")
 
# Multiple plots
par(mfrow = c(2, 2))
plot(model1)
par(mfrow = c(1, 1))  # Reset

library(ggplot2)
 
# Grammar of graphics approach
p1 <- ggplot(data, aes(x = variable1, y = variable2)) +
    geom_point(aes(color = category, size = weight)) +
    geom_smooth(method = "lm", se = TRUE) +
    scale_color_brewer(type = "qual", palette = "Set1") +
    labs(
        title = "Relationship between Variables",
        subtitle = "With linear trend line",
        x = "Independent Variable",
        y = "Dependent Variable",
        color = "Category"
    ) +
    theme_minimal() +
    theme(
        plot.title = element_text(hjust = 0.5),
        legend.position = "bottom"
    )
 
# Faceted plots
p2 <- ggplot(time_series_data, aes(x = date, y = value)) +
    geom_line(aes(color = series)) +
    facet_wrap(~ region, scales = "free_y") +
    scale_x_date(date_breaks = "1 month", date_labels = "%b %Y") +
    theme_bw() +
    theme(axis.text.x = element_text(angle = 45, hjust = 1))
 
# Save plots
ggsave("analysis_plot.png", p1, width = 10, height = 6, dpi = 300)

library(plotly)
library(DT)
 
# Interactive scatter plot
interactive_plot <- plot_ly(
    data = dataset,
    x = ~x_var,
    y = ~y_var,
    color = ~category,
    size = ~size_var,
    text = ~paste("ID:", id, "<br>Value:", value),
    hovertemplate = "%{text}<extra></extra>"
) %>%
    add_markers() %>%
    layout(
        title = "Interactive Scatter Plot",
        xaxis = list(title = "X Variable"),
        yaxis = list(title = "Y Variable")
    )
 
# Interactive data table
datatable(
    dataset,
    options = list(
        pageLength = 25,
        searchHighlight = TRUE,
        scrollX = TRUE
    ),
    filter = "top"
)

library(forecast)
library(tseries)
 
# Time series decomposition
ts_data <- ts(monthly_data, start = c(2020, 1), frequency = 12)
decomposition <- decompose(ts_data)
plot(decomposition)
 
# ARIMA modeling
auto_arima <- auto.arima(ts_data)
summary(auto_arima)
 
# Forecasting
forecast_result <- forecast(auto_arima, h = 12)
plot(forecast_result)
 
# Seasonal adjustment
seasonally_adjusted <- seasadj(decomposition)

library(caret)
library(randomForest)
library(e1071)
 
# Data preparation
set.seed(123)
train_index <- createDataPartition(datatarget, p = 0.8, list = FALSE)
train_data <- data[train_index, ]
test_data <- data[-train_index, ]
 
# Random Forest
rf_model <- randomForest(
    target ~ .,
    data = train_data,
    ntree = 500,
    importance = TRUE
)
 
# Variable importance
importance(rf_model)
varImpPlot(rf_model)
 
# Predictions and evaluation
predictions <- predict(rf_model, test_data)
confusionMatrix(predictions, test_datatarget)
 
# Cross-validation
cv_control <- trainControl(method = "cv", number = 10)
cv_model <- train(
    target ~ .,
    data = train_data,
    method = "rf",
    trControl = cv_control
)

# Install packages
install.packages(c("dplyr", "ggplot2", "tidyr"))
 
# Load packages
library(dplyr)
library(ggplot2)
 
# Check installed packages
installed.packages()
 
# Update packages
update.packages()

# Install from GitHub
devtools::install_github("username/package_name")
 
# Install from Bioconductor
BiocManager::install("package_name")
 
# Package documentation
help(package = "dplyr")
vignette("dplyr")

---
title: "Data Analysis Report"
author: "Data Scientist"
date: "`r Sys.Date()`"
output: 
  html_document:
    toc: true
    toc_float: true
    theme: flatly
---

# Analysis Overview

This report presents findings from our data analysis.

```{r setup, include=FALSE}
knitr::opts_chunkset(echo = TRUE, warning = FALSE, message = FALSE)
library(dplyr)
library(ggplot2)

# Load and analyze data
data <- read.csv("data.csv")
summary_stats <- data %>%
    group_by(category) %>%
    summarise(
        mean_value = mean(value),
        count = n()
    )

knitr::kable(summary_stats, caption = "Summary Statistics by Category")

# Create visualization
ggplot(data, aes(x = category, y = value)) +
    geom_boxplot() +
    theme_minimal() +
    labs(title = "Value Distribution by Category")

## Popular Packages

### Data Manipulation
- **dplyr**: Grammar of data manipulation
- **tidyr**: Tidy messy data
- **data.table**: Fast data manipulation
- **stringr**: String operations

### Visualization
- **ggplot2**: Grammar of graphics
- **plotly**: Interactive visualizations
- **lattice**: Trellis graphics
- **leaflet**: Interactive maps

### Statistical Analysis
- **caret**: Classification and regression training
- **forecast**: Time series forecasting
- **survival**: Survival analysis
- **lme4**: Mixed-effects models

### Specialized Domains
- **Bioconductor**: Bioinformatics packages
- **quantmod**: Quantitative financial modeling
- **sp/sf**: Spatial data analysis
- **tm**: Text mining

## Best Practices

### Code Organization
1. **Project structure**: Use RStudio projects
2. **Reproducibility**: Set random seeds and document versions
3. **Documentation**: Comment code and create README files
4. **Version control**: Use Git for tracking changes

### Data Analysis
1. **Exploratory analysis**: Always explore data first
2. **Data validation**: Check for outliers and missing values
3. **Assumptions**: Verify statistical assumptions
4. **Visualization**: Create informative plots

### Programming Style
```r
# Good practices
clean_data <- function(raw_data) {
    # Clear function purpose and documentation
    """
    Clean and prepare raw data for analysis
    
    Args:
        raw_data: Raw dataset from source
        
    Returns:
        Cleaned dataset ready for analysis
    """
    
    cleaned <- raw_data %>%
        filter(!is.na(key_variable)) %>%
        mutate(
            standardized_name = str_to_lower(str_trim(name)),
            date_formatted = as.Date(date_string, format = "%Y-%m-%d")
        ) %>%
        select(-temporary_columns)
    
    return(cleaned)
}