Data Overview

# Read the CSV file
results <- read.csv("eurojackpot_results.csv", stringsAsFactors = FALSE)

# Convert date format to day, month, year
results$draw_date <- as.Date(results$draw_date)
results$day <- format(results$draw_date, "%d")
results$month <- format(results$draw_date, "%m")
results$year <- format(results$draw_date, "%Y")

# Split main numbers into separate columns
main_numbers_split <- strsplit(gsub("\"", "", results$main_numbers), ",")
main_numbers_matrix <- do.call(rbind, main_numbers_split)
colnames(main_numbers_matrix) <- paste0("main_", 1:5)
results <- cbind(results, main_numbers_matrix)

# Split euro numbers into separate columns
euro_numbers_split <- strsplit(gsub("\"", "", results$euro_numbers), ",")
euro_numbers_matrix <- do.call(rbind, euro_numbers_split)
colnames(euro_numbers_matrix) <- paste0("euro_", 1:2)
results <- cbind(results, euro_numbers_matrix)

# Convert number columns to numeric
for (col in c(paste0("main_", 1:5), paste0("euro_", 1:2))) {
    results[[col]] <- as.numeric(results[[col]])
}

# View the first few rows of the processed data
# head(results)

# Summary of the dataset
# Create a data frame with summary information
summary_df <- data.frame(
    Metric = c("Total number of draws", "Date range", "Number of years covered"),
    Value = c(
        nrow(results),
        paste(min(results$draw_date), "to", max(results$draw_date)),
        length(unique(results$year))
    )
)

# Display the summary using kable
knitr::kable(summary_df,
    caption = "Dataset Summary",
    col.names = c("Metric", "Value"),
    align = c("l", "l")
)

Dataset Summary
Metric	Value
Total number of draws	828
Date range	2012-03-23 to 2025-02-25
Number of years covered	14

# Distribution of draws by year
yearly_counts <- table(results$year)
barplot(yearly_counts,
    main = "Number of Draws by Year",
    xlab = "Year", ylab = "Count", col = "steelblue"
)

Number Frequency Analysis

# Analyze frequency of main numbers
main_numbers_freq <- table(unlist(results[, paste0("main_", 1:5)]))
main_numbers_df <- data.frame(
    number = as.numeric(names(main_numbers_freq)),
    frequency = as.numeric(main_numbers_freq)
)
main_numbers_df <- main_numbers_df[order(main_numbers_df$number), ]

# Analyze frequency of euro numbers
euro_numbers_freq <- table(unlist(results[, paste0("euro_", 1:2)]))
euro_numbers_df <- data.frame(
    number = as.numeric(names(euro_numbers_freq)),
    frequency = as.numeric(euro_numbers_freq)
)
euro_numbers_df <- euro_numbers_df[order(euro_numbers_df$number), ]

# Plot main numbers frequency
barplot(main_numbers_df$frequency,
    names.arg = main_numbers_df$number,
    main = "Main Numbers Frequency",
    xlab = "Number",
    ylab = "Frequency",
    col = "skyblue",
    las = 2
)

# Plot euro numbers frequency
barplot(euro_numbers_df$frequency,
    names.arg = euro_numbers_df$number,
    main = "Euro Numbers Frequency",
    xlab = "Number",
    ylab = "Frequency",
    col = "salmon",
    las = 2
)

Pair Analysis

# Function to count pairs of numbers
count_pairs <- function(data, columns) {
    pairs <- combn(columns, 2, function(cols) {
        pair_data <- data[, cols]
        return(paste(pair_data[, 1], pair_data[, 2], sep = "-"))
    }, simplify = FALSE)

    all_pairs <- unlist(pairs)
    pair_counts <- sort(table(all_pairs), decreasing = TRUE)
    return(pair_counts)
}

# Count main number pairs
main_pairs <- count_pairs(results, paste0("main_", 1:5))
top_main_pairs <- head(main_pairs, 10)

# Count euro number pairs
euro_pairs <- count_pairs(results, paste0("euro_", 1:2))

# Plot top main number pairs
par(mar = c(8, 4, 4, 2) + 0.1)
barplot(top_main_pairs,
    main = "Top 10 Main Number Pairs",
    xlab = "",
    ylab = "Frequency",
    col = "lightgreen",
    las = 2
)
mtext("Number Pairs", side = 1, line = 6)

# Plot euro number pairs
barplot(euro_pairs,
    main = "Euro Number Pairs",
    xlab = "Number Pairs",
    ylab = "Frequency",
    col = "lightpink",
    las = 2
)

Odd-Even Distribution

# Calculate odd-even distribution for main numbers
results$main_odd_count <- rowSums(results[, paste0("main_", 1:5)] %% 2 == 1)
results$main_even_count <- 5 - results$main_odd_count

# Calculate odd-even distribution for euro numbers
results$euro_odd_count <- rowSums(results[, paste0("euro_", 1:2)] %% 2 == 1)
results$euro_even_count <- 2 - results$euro_odd_count

# Create a table of odd-even combinations for main numbers
odd_even_table <- table(results$main_odd_count)
odd_even_df <- data.frame(
    odd_count = as.numeric(names(odd_even_table)),
    frequency = as.numeric(odd_even_table)
)

# Plot odd-even distribution for main numbers
barplot(odd_even_df$frequency,
    names.arg = paste(odd_even_df$odd_count, "odd,", 5 - odd_even_df$odd_count, "even"),
    main = "Odd-Even Distribution in Main Numbers",
    xlab = "Distribution",
    ylab = "Frequency",
    col = "orchid"
)

# Plot odd-even distribution for euro numbers
euro_odd_even_table <- table(results$euro_odd_count)
barplot(euro_odd_even_table,
    names.arg = paste(
        as.numeric(names(euro_odd_even_table)), "odd,",
        2 - as.numeric(names(euro_odd_even_table)), "even"
    ),
    main = "Odd-Even Distribution in Euro Numbers",
    xlab = "Distribution",
    ylab = "Frequency",
    col = "gold"
)