From 1c21515f4fd99adad75672b02ea9f7dd6426f506 Mon Sep 17 00:00:00 2001
From: git <git@fredericofalcao.com>
Date: Mon, 16 Mar 2026 13:13:15 +0000
Subject: [PATCH] Add main.r

---
 main.r | 129 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 129 insertions(+)
 create mode 100644 main.r

diff --git a/main.r b/main.r
new file mode 100644
index 0000000..672db93
--- /dev/null
+++ b/main.r
@@ -0,0 +1,129 @@
+GetECBHistoricalExchangeRateData <- function() {
+    # 1. Setup temporary files and download the data
+    temp_zip <- tempfile(fileext = ".zip")
+    url <- "https://www.ecb.europa.eu/stats/eurofxref/eurofxref-hist.zip"
+
+    message("Downloading data from ECB...")
+    download.file(url, temp_zip, quiet = TRUE)
+
+    # 2. Unzip and identify the CSV file
+    unzipped_files <- unzip(temp_zip, exdir = tempdir())
+    csv_file <- unzipped_files[grep("\\.csv$", unzipped_files)]
+
+    # 3. Load the data into R
+    message("Loading data...")
+    df <- read.csv(csv_file, na.strings = c("N/A", "NA", ""), stringsAsFactors = FALSE)
+    
+    # Clean up temp files
+    unlink(temp_zip)
+    unlink(csv_file)
+    
+    return(df)
+}
+PreProcessData <- function(df, target_currencies, last_n_days = NULL) {
+    
+    # Preprocess Dates and Time
+    df$Date <- as.Date(df$Date)
+    df <- df[order(df$Date), ] 
+	
+	# Filter by the last N days if specified
+	if (!is.null(last_n_days)) {
+	  cutoff_date <- max(df$Date, na.rm = TRUE) - last_n_days
+	  df <- df[df$Date >= cutoff_date, ]
+	  message(sprintf("Filtered data to the last %d days (since %s).", last_n_days, cutoff_date))
+	}
+
+    # Create a Time Index for the regression
+    df$TimeIndex <- as.numeric(df$Date - min(df$Date))
+    
+    # Ensure targets actually exist in the dataframe to prevent errors
+    valid_targets <- intersect(target_currencies, names(df))
+
+    # Filter the data frame down to Date, TimeIndex, and those specific targets
+    df <- df[, c("Date", "TimeIndex", valid_targets)]
+
+    # Create the new cross pairs dynamically
+    # combn(valid_targets, 2) creates all unique 2-pair combinations
+    if (length(valid_targets) >= 2) {
+        pair_combos <- combn(valid_targets, 2)
+        
+        for (i in 1:ncol(pair_combos)) {
+            base_curr <- pair_combos[1, i]
+            quote_curr <- pair_combos[2, i]
+            
+            # Create column name, e.g., "USD_JPY"
+            pair_name <- paste0(base_curr, "_", quote_curr)
+            
+            # Math: To get Base/Quote, divide the ECB Quote column by the ECB Base column
+            df[[pair_name]] <- df[[quote_curr]] / df[[base_curr]]
+        }
+    }
+
+    # Update the 'currencies' vector so the loop analyzes original and new columns
+    currencies <- setdiff(names(df), c("Date", "TimeIndex"))
+    
+    return(list(currencies = currencies, df = df))
+}
+CalculateMetrics <- function(df,currencies) {
+    # 5. Loop through each currency, run regression, and calculate metrics
+    results_list <- list()
+
+    message("Running regressions...")
+    for (curr in currencies) {
+      valid_data <- df[!is.na(df[[curr]]), ]
+  
+      if (nrow(valid_data) > 2) {
+    
+        # Simple linear regression: Exchange Rate ~ Time
+        model <- lm(valid_data[[curr]] ~ valid_data$TimeIndex)
+    
+        # Extract Beta (slope) and Residual Standard Error (RSE)
+        beta <- coef(model)[2]
+        rse <- summary(model)$sigma 
+    
+        # Calculate Signal-to-Noise Ratio: |Beta| / RSE
+        if (!is.na(rse) && rse > 0) {
+          signal_to_noise <- abs(beta) / rse
+        } else {
+          signal_to_noise <- NA
+        }
+    
+        # Store results
+        results_list[[curr]] <- data.frame(
+          Currency = curr,
+          Beta = beta,
+          AbsBeta = abs(beta),
+          RSE = rse,
+          SignalToNoise = signal_to_noise,
+          stringsAsFactors = FALSE,
+          row.names = NULL
+        )
+      }
+    }
+
+    # Combine all results
+    results_df <- do.call(rbind, results_list)
+    
+    return (results_df)
+    
+}
+OrderBySignalToNoiseRatio <- function(results_df) {
+    
+    # 6. Order by the Signal-to-Noise ratio and get the top 3
+    top_3_currencies <- results_df[order(results_df$SignalToNoise, decreasing = TRUE), ]
+    top_3_currencies <- head(top_3_currencies, 3)
+    return (top_3_currencies)
+}
+
+#
+#  10. RUNTIME
+#
+
+df               <- GetECBHistoricalExchangeRateData()
+res              <- PreProcessData(df,c("USD", "JPY", "GBP","CAD","NOK"),720)
+results_df       <- CalculateMetrics(res$df,res$currencies)
+top_3_currencies <- OrderBySignalToNoiseRatio(results_df)
+
+# Print the final output
+message("\nTop 3 currencies by Trend Predictability (|Beta| / RSE):")
+print(top_3_currencies)
\ No newline at end of file