Merge pull request #61 from jakobdanel/results/direct-neigbours

Results/direct neigbours

NAMESPACE

@@ -12,6 +12,8 @@ export(lfa_count_returns_all_areas)
 export(lfa_count_returns_per_tree)
 export(lfa_create_boxplot)
 export(lfa_create_density_plots)
+export(lfa_create_neighbor_mean_curves)
+export(lfa_create_plot_per_area)
 export(lfa_create_stacked_distributions_plot)
 export(lfa_create_stacked_histogram)
 export(lfa_create_tile_location_objects)

R/create_density_plots.R

@@ -26,8 +26,8 @@
 lfa_create_density_plots <-
   function(data,
            value_column,
-           category_column1,
-           category_column2,
+           category_column1 = "area",
+           category_column2 = "specie",
            title = NULL,
            xlims = NULL,
            ylims = NULL) {

R/create_neighbour_mean_curves.R

@@ -0,0 +1,56 @@
+#' Create neighbor mean curves for specified areas
+#'
+#' This function generates mean curves for a specified set of areas based on neighbor data.
+#' The user can choose to compute mean curves for individual neighbors or averages across neighbors.
+#'
+#' @param neighbors A data frame containing information about neighbors, where each column represents
+#'   a specific neighbor, and each row corresponds to an area.
+#' @param use_avg Logical. If TRUE, the function computes average curves across all neighbors.
+#'   If FALSE, it computes curves for individual neighbors.
+#' @return A data frame with mean curves for each specified area.
+#'   Columns represent areas, and rows represent index values.
+#'
+#' @examples
+#' # Assuming you have a data frame 'your_neighbors_data' with neighbor information
+#' mean_curves <- lfa_create_neighbor_mean_curves(your_neighbors_data, use_avg = TRUE)
+#' print(mean_curves)
+#'
+#' @export
+lfa_create_neighbor_mean_curves <- function(neighbors, use_avg = FALSE) {
+  # Get information about all areas
+  all_areas <- lfa::lfa_get_all_areas()
+
+  # Create a data frame with an 'index' column ranging from 1 to 100
+  df <- data.frame(index = 1:100)
+
+  # Define column names based on whether to use averages or individual neighbors
+  if (use_avg) {
+    names <- paste0("avg_", 1:100)
+  } else {
+    names <- paste0("Neighbor_", 1:100)
+  }
+
+  # Iterate over each area and compute mean curves
+  for (area in 1:nrow(all_areas)) {
+    area_name <- all_areas[area, "area"]
+
+    # Subset data for the current area
+    subset <- neighbors[neighbors$area == area_name, ]
+
+    # Initialize an empty vector to store mean values
+    vec <- NULL
+
+    # Compute mean values for each neighbor
+    for (name in names) {
+      vec <- c(vec, mean(subset[[name]], na.rm = TRUE))
+    }
+
+    # Add the vector as a new column to the data frame
+    df[[area_name]] <- vec
+  }
+
+  # Remove the 'index' column
+  df$index <- NULL
+
+  return(df)
+}

R/create_plot_per_area.R

@@ -0,0 +1,44 @@
+#' Create a line plot per area with one color per specie
+#'
+#' This function takes a data frame containing numeric columns and creates a line plot
+#' using ggplot2. Each line in the plot represents a different area, with one color per specie.
+#'
+#' @param data A data frame with numeric columns and a column named 'specie' for species information.
+#' @return A ggplot2 line plot.
+#' @export
+#'
+#' @examples
+#' data <- data.frame(
+#'   specie = rep(c("Species1", "Species2", "Species3"), each = 10),
+#'   column1 = rnorm(30),
+#'   column2 = rnorm(30),
+#'   column3 = rnorm(30)
+#' )
+#' lfa_create_plot_per_area(data)
+#'
+#'@export
+lfa_create_plot_per_area <- function(data) {
+  # Get all areas and species information
+  areas_specie <- lfa::lfa_get_all_areas()
+
+  # Create an "index" column using the row numbers
+  data$index <- seq_len(nrow(data))
+
+  # Reshape the data using tidyr's gather function
+  data_long <- tidyr::gather(data, key = "area", value = "value", -index)
+
+  # Perform a left join with areas_specie
+  data_long <- dplyr::left_join(data_long, areas_specie, by = "area")
+
+  # Create a line plot using ggplot2 with colors based on specie and one line per area
+  return(
+    ggplot2::ggplot(data_long, ggplot2::aes(x = index, y = value, color = specie, group = area)) +
+      ggplot2::geom_line() +
+      ggplot2::labs(
+        title = "Average Distance to n-nearest Neighbors across all patches",
+        x = "n",
+        y = "Average Distance to n-nearest Neighbor (m)"
+      ) +
+      ggplot2::theme_minimal()
+  )
+}

results/appendix/build_quantitativ_results.py

@@ -127,6 +127,14 @@ def main():
     content = build_quantitativ_results("z-values", "Distribution of Z-Values", '"Z"', header_size=3)
     write_file("z_values.qmd", content)
 
+    preprocessing_nearest ="data <- lfa::lfa_combine_sf_obj(lfa::lfa_get_neighbor_paths(),lfa::lfa_get_all_areas())"
+    write_file("nearest_1.qmd", build_quantitativ_results("nearest-neighbor-1", "Distribution of nearest neighbor distances", '"Neighbor_1"', header_size=4, preprocessing=preprocessing_nearest))
+    write_file("nearest_100.qmd", build_quantitativ_results("nearest-neighbor-100", "Distribution of distances to 100th nearest neighbor", '"Neighbor_100"', header_size=4, preprocessing=preprocessing_nearest))
+
+    preprocessing_nearest_avg= preprocessing_nearest+ "\n" +"""names <- paste0("Neighbor_",1:100)
+data$avg = rowMeans(dplyr::select(as.data.frame(data),names))"""
+    write_file("nearest_avg.qmd", build_quantitativ_results("nearest-neighbor-avg", "Distribution of average nearest neighbor distances", '"avg"', header_size=4, preprocessing=preprocessing_nearest_avg))
+
 
     preprocessing_number_of_returns = """data <- sf::st_read("data/tree_properties.gpkg")
 neighbors <- lfa::lfa_get_neighbor_paths() |> lfa::lfa_combine_sf_obj(lfa::lfa_get_all_areas())