Refactor/reduce complexity

.Rbuildignore

@@ -146,3 +146,5 @@
 ^lib$
 ^strava_data$
 
+^data-raw$
+^generate_plot_examples\.R$

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: Athlytics
 Title: Academic R Package for Sports Physiology Analysis from Local 'Strava' Data
-Version: 1.0.0
+Version: 1.0.1
 Author: Zhiang He [aut, cre]
 Maintainer: Zhiang He <[email protected]>
 Authors@R: 
@@ -27,7 +27,6 @@ Imports:
     rlang (>= 0.4.0),
     scales,
     tidyr,
-    viridis,
     zoo,
     R.utils,
     tools,

NAMESPACE

@@ -105,6 +105,5 @@ importFrom(tidyr,pivot_wider)
 importFrom(tidyr,unnest)
 importFrom(tools,toTitleCase)
 importFrom(utils,read.csv)
-importFrom(viridis,scale_color_viridis)
 importFrom(zoo,rollapply)
 importFrom(zoo,rollmean)

NEWS.md

@@ -1,4 +1,18 @@
-# Athlytics 1.0.0
+# Athlytics 1.0.1
+
+## Code Quality Improvements
+
+* **Reduced Cyclomatic Complexity**: Refactored `calculate_acwr()` and `calculate_exposure()` by extracting shared load calculation logic into internal helper functions (`calculate_daily_load_internal()`, `compute_single_load()`, `validate_load_metric_params()`). This improves code maintainability and testability without changing the public API.
+
+* **Dependency Cleanup**: Removed unused `viridis` package from Imports. The package was declared as a dependency but never actually called (ggplot2's built-in `scale_color_viridis_d()` was used instead).
+
+* **Documentation Fixes**: Fixed Rd line width issues in `plot_with_reference()` examples.
+
+* **Build Configuration**: Updated `.Rbuildignore` to properly exclude development files.
+
+---
+
+# Athlytics 1.0.0
 
 This major release transitions from Strava API to **local data export processing**, prioritizing user privacy and data ownership while eliminating API rate limits and authentication requirements.
 

R/calculate_acwr.R

@@ -195,11 +195,9 @@ calculate_acwr <- function(activities_data,
   if (!is.numeric(acute_period) || acute_period <= 0) stop("`acute_period` must be a positive integer.")
   if (!is.numeric(chronic_period) || chronic_period <= 0) stop("`chronic_period` must be a positive integer.")
   if (acute_period >= chronic_period) stop("`acute_period` must be less than `chronic_period`.")
-  if (load_metric == "tss" && is.null(user_ftp)) stop("`user_ftp` is required when `load_metric` is 'tss'.")
-
-  valid_load_metrics <- c("duration_mins", "distance_km", "elapsed_time_mins", "tss", "hrss", "elevation_gain_m")
-  if (!load_metric %in% valid_load_metrics) stop("Invalid `load_metric`. Choose from: ", paste(valid_load_metrics, collapse = ", "))
-  if (load_metric == "hrss" && (is.null(user_max_hr) || is.null(user_resting_hr))) stop("`user_max_hr` and `user_resting_hr` are required when `load_metric` is 'hrss'.")
+
+  # Validate load metric parameters using internal helper
+  validate_load_metric_params(load_metric, user_ftp, user_max_hr, user_resting_hr)
 
   # Force explicit activity_type specification to prevent mixing incompatible sports
   if (is.null(activity_type) || length(activity_type) == 0) {
@@ -238,84 +236,15 @@ calculate_acwr <- function(activities_data,
     stop("No activities found in local data for the required date range (", fetch_start_date, " to ", analysis_end_date,").")
   }
 
-  # --- Process Activities into Daily Load ---
-  `%||%` <- function(x, y) if (is.null(x) || length(x) == 0) y else x
-  safe_as_numeric <- function(x) { as.numeric(x %||% 0) }
-
-  # Convert data frame to list format for processing
-  daily_load_df <- purrr::map_dfr(1:nrow(activities_df_filtered), function(i) {
-    activity <- activities_df_filtered[i, ]
-    # Get activity date and type
-    activity_date <- activity$date
-    act_type <- activity$type %||% "Unknown"
-
-    # Extract metrics from data frame columns
-    duration_sec <- safe_as_numeric(activity$moving_time)
-    distance_m <- safe_as_numeric(activity$distance)
-    elapsed_sec <- safe_as_numeric(activity$elapsed_time)
-    avg_hr <- safe_as_numeric(activity$average_heartrate)
-    avg_power <- safe_as_numeric(activity$average_watts)
-    elevation_gain <- safe_as_numeric(activity$elevation_gain)
-    # Use weighted_average_watts if available, otherwise average_watts
-    np_proxy <- safe_as_numeric(activity$weighted_average_watts %||% activity$average_watts %||% 0) 
-    # message(sprintf("    Duration: %.0f sec", duration_sec))
-
-    # --- Added Debugging and Refined Logic --- 
-    # message(sprintf("    Inputs check: load_metric='%s', duration_sec=%.1f, distance_m=%.1f, avg_hr=%.1f, np_proxy=%.1f, user_ftp=%s, user_max_hr=%s, user_resting_hr=%s", 
-    #                 load_metric, duration_sec, distance_m, avg_hr, np_proxy, 
-    #                 deparse(user_ftp), deparse(user_max_hr), deparse(user_resting_hr)))
-
-    if (duration_sec > 0) {
-      # Initialize load_value outside case_when to handle default case cleanly
-      load_value <- 0 
-
-      if (load_metric == "duration_mins") {
-          load_value <- duration_sec / 60
-      } else if (load_metric == "distance_km") {
-          load_value <- distance_m / 1000
-      } else if (load_metric == "elapsed_time_mins") {
-          load_value <- elapsed_sec / 60
-      } else if (load_metric == "elevation_gain_m") {
-          load_value <- elevation_gain
-      } else if (load_metric == "hrss") {
-          # Check required HR parameters before calculating
-          if (!is.null(user_max_hr) && !is.null(user_resting_hr) && is.numeric(user_max_hr) && is.numeric(user_resting_hr) && 
-              user_max_hr > user_resting_hr && avg_hr > user_resting_hr && avg_hr <= user_max_hr) {
-            hr_reserve <- user_max_hr - user_resting_hr
-            avg_hr_rel <- (avg_hr - user_resting_hr) / hr_reserve
-            load_value <- (duration_sec / 60) * avg_hr_rel # Simplified TRIMP
-          } else {
-              # message("    Skipping HRSS calculation: Missing/invalid HR parameters or avg_hr out of range.")
-          }
-      } else if (load_metric == "tss") {
-           # Check required FTP parameter before calculating
-           if (!is.null(user_ftp) && is.numeric(user_ftp) && user_ftp > 0 && np_proxy > 0) {
-             intensity_factor <- np_proxy / user_ftp
-             load_value <- (duration_sec * np_proxy * intensity_factor) / (user_ftp * 3600) * 100
-           } else {
-               # message("    Skipping TSS calculation: Missing/invalid FTP or power data (np_proxy).")
-           }
-      }
-
-      # message(sprintf("    Calculated load_value: %.2f", load_value))
-    } else {
-        # message("    Duration <= 0, load is 0.")
-        load_value <- 0 # Define load_value even if duration is 0
-    }
-
-    if (!is.na(load_value) && load_value > 0) {
-      # message("    -> Activity PASSED filters, returning load data.")
-      data.frame(
-        date = activity_date,
-        load = load_value,
-        stringsAsFactors = FALSE
-      )
-    } else {
-      # message("    -> Activity FAILED final check (load NA or <= 0).")
-      NULL
-    }
-  })
-
+  # --- Process Activities into Daily Load (using internal helper) ---
+  daily_load_df <- calculate_daily_load_internal(
+    activities_df = activities_df_filtered,
+    load_metric = load_metric,
+    user_ftp = user_ftp,
+    user_max_hr = user_max_hr,
+    user_resting_hr = user_resting_hr
+  )
+
   message("Finished processing activity list.")
 
   if (is.null(daily_load_df) || nrow(daily_load_df) == 0) {

R/calculate_exposure.R

@@ -82,20 +82,13 @@ calculate_exposure <- function(activities_data,
     stop("`activities_data` must be a data frame (e.g., from load_local_activities()).")
   }
 
-  load_metric_options <- c("duration_mins", "distance_km", "hrss", "tss", "elevation_gain_m")
-  if (!load_metric %in% load_metric_options) {
-    stop(paste("'load_metric' must be one of:", paste(load_metric_options, collapse=", ")))
-  }
-  if (load_metric == "tss" && is.null(user_ftp)) {
-    stop("user_ftp is required when load_metric = 'tss'.")
-  }
-  if (load_metric == "hrss" && (is.null(user_max_hr) || is.null(user_resting_hr))) {
-    stop("user_max_hr and user_resting_hr are required when load_metric = 'hrss'.")
-  }
   if (acute_period >= chronic_period) {
     stop("acute_period must be less than chronic_period.")
   }
 
+  # Validate load metric parameters using internal helper
+  validate_load_metric_params(load_metric, user_ftp, user_max_hr, user_resting_hr)
+
   `%||%` <- function(x, y) if (is.null(x) || length(x) == 0) y else x
 
   analysis_end_date <- tryCatch(lubridate::as_date(end_date %||% Sys.Date()), error = function(e) Sys.Date())
@@ -124,58 +117,16 @@ calculate_exposure <- function(activities_data,
     stop("No activities found in local data for the required date range (", fetch_start_date, " to ", analysis_end_date,").")
   }
 
-  # --- Process Activities into Daily Load ---
-  safe_as_numeric <- function(x) { as.numeric(x %||% 0) }
-
-  daily_load_df <- purrr::map_dfr(1:nrow(activities_df_filtered), function(i) {
-    activity <- activities_df_filtered[i, ]
-    activity_date <- activity$date
-    act_type <- activity$type %||% "Unknown"
-
-    duration_sec <- safe_as_numeric(activity$moving_time)
-    distance_m <- safe_as_numeric(activity$distance)
-    elapsed_sec <- safe_as_numeric(activity$elapsed_time)
-    avg_hr <- safe_as_numeric(activity$average_heartrate)
-    avg_power <- safe_as_numeric(activity$average_watts)
-    elevation_gain <- safe_as_numeric(activity$elevation_gain)
-    np_proxy <- safe_as_numeric(activity$weighted_average_watts %||% activity$average_watts %||% 0)
-
-    current_load <- 0
-    if (load_metric == "duration_mins") {
-      current_load <- duration_sec / 60
-    } else if (load_metric == "distance_km") {
-      current_load <- distance_m / 1000
-    } else if (load_metric == "hrss") {
-      if (avg_hr > 0 && !is.null(user_max_hr) && !is.null(user_resting_hr)) {
-        hr_reserve <- user_max_hr - user_resting_hr
-        if (hr_reserve > 0) {
-          percent_hrr <- (avg_hr - user_resting_hr) / hr_reserve
-          if (percent_hrr > 0) {
-            current_load <- (duration_sec / 3600) * percent_hrr * 100
-          }
-        }
-      }
-    } else if (load_metric == "tss") {
-      if (np_proxy > 0 && !is.null(user_ftp) && user_ftp > 0) {
-        intensity_factor <- np_proxy / user_ftp
-        current_load <- (duration_sec / 3600) * (intensity_factor^2) * 100
-      }
-    } else if (load_metric == "elevation_gain_m") {
-      current_load <- elevation_gain
-    }
-
-    if (current_load > 0) {
-      data.frame(
-        date = activity_date,
-        load = current_load,
-        stringsAsFactors = FALSE
-      )
-    } else {
-      NULL
-    }
-  })
+  # --- Process Activities into Daily Load (using internal helper) ---
+  daily_load_df <- calculate_daily_load_internal(
+    activities_df = activities_df_filtered,
+    load_metric = load_metric,
+    user_ftp = user_ftp,
+    user_max_hr = user_max_hr,
+    user_resting_hr = user_resting_hr
+  )
 
-  if (nrow(daily_load_df) == 0) {
+  if (is.null(daily_load_df) || nrow(daily_load_df) == 0) {
     stop("No valid load data could be calculated from activities. Check if activities have the required metrics (HR, power, duration, distance).")
   }
 

R/cohort_reference.R

@@ -278,7 +278,10 @@ add_reference_bands <- function(p,
 #' reference_data <- data.frame(
 #'   date = as.Date(c("2023-01-01", "2023-04-01", "2023-07-01", "2023-10-01")),
 #'   percentile = rep(c("p05", "p25", "p50", "p75", "p95"), 4),
-#'   value = c(0.7, 0.9, 1.1, 1.3, 1.5, 0.7, 0.9, 1.1, 1.3, 1.5, 0.7, 0.9, 1.1, 1.3, 1.5, 0.7, 0.9, 1.1, 1.3, 1.5)
+#'   value = c(0.7, 0.9, 1.1, 1.3, 1.5,
+#'             0.7, 0.9, 1.1, 1.3, 1.5,
+#'             0.7, 0.9, 1.1, 1.3, 1.5,
+#'             0.7, 0.9, 1.1, 1.3, 1.5)
 #' )
 #' 
 #' p <- plot_with_reference(