Add random forest models to report

results/results/rf/combined.qmd

@@ -0,0 +1,101 @@
+
+### Segmentation
+
+```{r}
+#| code-fold: true
+#| warning: false
+#| results: hide
+chms <- lfa::lfa_visit_all_areas(lfa::lfa_chm)
+patches <- lfa::lfa_get_all_areas()
+patches$chm_mean = NA
+patches$chm_var = NA
+patches$chm_median = NA
+for (area_key in names(chms)) {
+  area <- chms[area_key]
+  area[[area_key]] |> as.vector() -> vec
+  patches[patches$area == area_key, "chm_mean"] <-
+    mean(vec, na.rm = T)
+  patches[patches$area == area_key, "chm_var"] <-
+    var(vec, na.rm = T)
+  patches[patches$area == area_key, "chm_median"] <-
+    median(vec, na.rm = T)
+  
+}
+density <- lfa::lfa_calculate_patch_density(detections = detections)
+
+```
+
+
+```{r}
+#| code-fold: true
+#| warning: false
+#| results: hide
+data <- sf::st_read("data/tree_properties.gpkg")
+detections <- lfa::lfa_get_detections()
+neighbors <- lfa::lfa_get_neighbor_paths() |> lfa::lfa_combine_sf_obj(lfa::lfa_get_all_areas())
+```
+
+
+```{r, cache=TRUE}
+#| code-fold: true
+#| warning: false
+#| results: hide
+combined <- sf::st_join(data,detections,join = sf::st_within)
+
+combined$Z.x = NULL
+names(combined)[names(combined) == 'Z.y'] <- 'Z'
+
+combined$treeID.segmentation <- NULL
+
+combined[["density"]][is.na(combined[["density"]])] <- -1
+combined[["Z.mean"]][is.na(combined[["Z.mean"]])] <- -1
+combined[["Z.var"]][is.na(combined[["Z.var"]])] <- -1
+combined[["Intensity.mean"]][is.na(combined[["Intensity.mean"]])] <- -1
+combined[["Intensity.var"]][is.na(combined[["Intensity.var"]])] <- -1
+combined[["number_of_returns"]][is.na(combined[["number_of_returns"]])] <- -1
+combined[["tree_area"]][is.na(combined[["tree_area"]])] <- -1
+
+neighbors$treeID = NULL
+neighbors$Z = NULL
+neighbors$area = NULL
+neighbors$specie = NULL
+
+combined = sf::st_join(combined, neighbors, sf::st_within)
+combined = dplyr::left_join(combined,patches, c("specie","area"))
+density <- density |> as.data.frame()
+density$id = NULL
+density$geometry = NULL
+density$area_size = NULL
+density$detections = NULL
+colnames(density) = c("specie","area","density")
+combined <- dplyr::left_join(combined, density, c("specie","area"))
+excluded_cols <- c("Z.x", "treeID.detection","treeID.segmentation","name_las_file","treeID","area","specie","geom")
+
+```
+
+
+
+```{r, cache=TRUE}
+#| code-fold: true
+#| warning: false
+#| results: hide
+data <- lfa::lfa_random_forest(tree_data = combined, excluded_input_columns = excluded_cols,response_variable = "specie")
+```
+
+```{r}
+#| code-fold: true
+#| warning: false
+#| fig-cap: Confusion Matrix of randomForest with all parameters derived from tree level.
+#| label: fig-cm-tree-level
+cm <- data$confusion_matrix |> caret::confusionMatrix()
+lfa::lfa_plot_confusion_matrix(cm)
+```
+
+```{r}
+#| code-fold: true
+#| warning: false
+#| fig-cap: Precsion and Recall of randomForest with all parameters derived from tree level.
+#| label: fig-pr-tree-level
+data$confusion_matrix |> lfa::lfa_calculate_rf_metrics() |> lfa::lfa_visualize_rf_metrics()
+```
+

results/results/rf/height.qmd

@@ -0,0 +1,26 @@
+## Predicting species with random forest
+
+### Use height
+
+```{r}
+detections <- lfa::lfa_get_detections()
+density <- lfa::lfa_calculate_patch_density(detections = detections)
+colnames(density) <- c("id","specie","area","geometry","area_size","detections","density") 
+detections <- dplyr::left_join(detections,density |> as.data.frame(), by= c("area","specie"))
+excluded_cols <- c("treeID","geom","area","specie","id","geometry","area_size","detections", "density")
+```
+
+```{r, cache=TRUE}
+
+data <- lfa::lfa_random_forest(tree_data = detections, excluded_input_columns = excluded_cols)
+```
+
+```{r}
+cm <- data$confusion_matrix |> caret::confusionMatrix()
+lfa::lfa_plot_confusion_matrix(cm)
+```
+
+```{r}
+data$confusion_matrix |> lfa::lfa_calculate_rf_metrics() |> lfa::lfa_visualize_rf_metrics()
+```
+

results/results/rf/neighbors.qmd

@@ -0,0 +1,39 @@
+
+### Use neighbors and height
+
+```{r}
+#| code-fold: true
+#| warning: false
+#| results: hide
+detections <- lfa::lfa_get_detections()
+neighbors <- lfa::lfa_get_neighbor_paths() |> lfa::lfa_combine_sf_obj(lfa::lfa_get_all_areas())
+neighbors <- sf::st_join(neighbors,detections, join = sf::st_within)
+names(neighbors)[names(neighbors) == 'specie.x'] <- 'specie'
+names(neighbors)[names(neighbors) == 'area.x'] <- 'area'
+excluded_cols <- c("area.x","specie.x","treeID.y","Z.y","area.y","specie.y","geom","treeID.x","Z.x")
+```
+
+```{r, cache=TRUE}
+#| code-fold: true
+#| warning: false
+#| results: hide
+data <- lfa::lfa_random_forest(tree_data = neighbors, excluded_input_columns = excluded_cols,response_variable = "specie")
+```
+
+```{r}
+#| code-fold: true
+#| warning: false
+#| label: fig-cm-neighbors
+#| fig-cap: Confusion Matrix of randomForest on the distance to 100 nearest neighbors.
+cm <- data$confusion_matrix |> caret::confusionMatrix()
+lfa::lfa_plot_confusion_matrix(cm)
+```
+
+```{r}
+#| code-fold: true
+#| warning: false
+#| label: fig-pr-neighbors
+#| fig-cap: Class wise precision and recall for randomForest-Classification with distance to the 100 nearest neighbors. 
+data$confusion_matrix |> lfa::lfa_calculate_rf_metrics() |> lfa::lfa_visualize_rf_metrics()
+```
+

results/results/rf/patch-level.qmd

@@ -0,0 +1,84 @@
+
+### Train with patch level information
+
+```{r}
+#| code-fold: true
+#| warning: false
+#| results: hide
+chms <- lfa::lfa_visit_all_areas(lfa::lfa_chm)
+patches <- lfa::lfa_get_all_areas()
+patches$chm_mean = NA
+patches$chm_var = NA
+patches$chm_median = NA
+for (area_key in names(chms)) {
+  area <- chms[area_key]
+  area[[area_key]] |> as.vector() -> vec
+  patches[patches$area == area_key, "chm_mean"] <-
+    mean(vec, na.rm = T)
+  patches[patches$area == area_key, "chm_var"] <-
+    var(vec, na.rm = T)
+  patches[patches$area == area_key, "chm_median"] <-
+    median(vec, na.rm = T)
+  
+}
+```
+
+```{r}
+#| code-fold: true
+#| warning: false
+#| results: hide
+neighbors <- lfa::lfa_get_neighbor_paths() |> lfa::lfa_combine_sf_obj(lfa::lfa_get_all_areas())
+```
+
+
+```{r}
+#| code-fold: true
+#| warning: false
+#| results: hide
+detections <- lfa::lfa_get_detections()
+density <- lfa::lfa_calculate_patch_density(detections = detections)
+colnames(density) <- c("id","specie","area","geometry","area_size","detections","density")
+detections <- dplyr::left_join(detections,density |> as.data.frame(),by=c("area","specie"))
+detections <- dplyr::left_join(detections,patches, by = c("area","specie"))
+
+detections <- sf::st_join(detections, neighbors, join = sf::st_within)
+
+detections$treeID.x = NULL
+names(detections)[names(detections) == 'treeID.y'] <- 'treeID'
+
+detections$Z.x = NULL
+names(detections)[names(detections) == 'Z.y'] <- 'Z'
+
+detections$area.x = NULL
+names(detections)[names(detections) == 'area.y'] <- 'area'
+
+detections$specie.x = NULL
+names(detections)[names(detections) == 'specie.y'] <- 'specie'
+
+excluded_cols = c("treeID","geom","area","specie","id","geometry","area_size","detections","geometry")
+```
+
+```{r, cache=TRUE}
+#| code-fold: true
+#| warning: false
+#| results: hide
+data <- lfa::lfa_random_forest(tree_data = detections, excluded_input_columns = excluded_cols,response_variable = "specie")
+```
+
+```{r}
+#| code-fold: true
+#| warning: false
+#| label: fig-cm-patch
+#| fig-cap: Confusion Matrix of randomForest on returns per Tree.
+cm <- data$confusion_matrix |> caret::confusionMatrix()
+lfa::lfa_plot_confusion_matrix(cm)
+```
+
+```{r}
+#| code-fold: true
+#| warning: false
+#| label: fig-pr-patch
+#| fig-cap: Class wise precision and recall for randomForest-Classification with LiDAR returns per tree. 
+data$confusion_matrix |> lfa::lfa_calculate_rf_metrics() |> lfa::lfa_visualize_rf_metrics()
+```
+

results/results/rf/returns_per_tree.qmd

@@ -0,0 +1,35 @@
+
+### LiDAR point cloud returns per Tree
+
+```{r}
+#| code-fold: true
+#| warning: false
+#| results: hide
+returns <- lfa::lfa_count_returns_all_areas()
+excluded_cols = c("Var1","specie","area")
+```
+
+```{r, cache=TRUE}
+#| code-fold: true
+#| warning: false
+#| results: hide
+data <- lfa::lfa_random_forest(tree_data = returns, excluded_input_columns = excluded_cols,response_variable = "specie")
+```
+
+```{r}
+#| code-fold: true
+#| warning: false
+#| label: fig-cm-returns
+#| fig-cap: Confusion Matrix of randomForest on returns per Tree.
+cm <- data$confusion_matrix |> caret::confusionMatrix()
+lfa::lfa_plot_confusion_matrix(cm)
+```
+
+```{r}
+#| code-fold: true
+#| warning: false
+#| label: fig-pr-returns
+#| fig-cap: Class wise precision and recall for randomForest-Classification with LiDAR returns per tree. 
+data$confusion_matrix |> lfa::lfa_calculate_rf_metrics() |> lfa::lfa_visualize_rf_metrics()
+```
+

results/results/rf/segmentation.qmd

@@ -0,0 +1,64 @@
+
+### Segmentation
+
+```{r}
+#| code-fold: true
+#| warning: false
+#| results: hide
+data <- sf::st_read("data/tree_properties.gpkg")
+detections <- lfa::lfa_get_detections()
+neighbors <- lfa::lfa_get_neighbor_paths() |> lfa::lfa_combine_sf_obj(lfa::lfa_get_all_areas())
+```
+```{r}
+#| code-fold: true
+#| warning: false
+#| results: hide
+combined <- sf::st_join(data,detections,join = sf::st_within)
+
+combined$Z.x = NULL
+names(combined)[names(combined) == 'Z.y'] <- 'Z'
+
+combined$treeID.segmentation <- NULL
+
+combined[["density"]][is.na(combined[["density"]])] <- -1
+combined[["Z.mean"]][is.na(combined[["Z.mean"]])] <- -1
+combined[["Z.var"]][is.na(combined[["Z.var"]])] <- -1
+combined[["Intensity.mean"]][is.na(combined[["Intensity.mean"]])] <- -1
+combined[["Intensity.var"]][is.na(combined[["Intensity.var"]])] <- -1
+combined[["number_of_returns"]][is.na(combined[["number_of_returns"]])] <- -1
+combined[["tree_area"]][is.na(combined[["tree_area"]])] <- -1
+
+neighbors$treeID = NULL
+neighbors$Z = NULL
+neighbors$area = NULL
+neighbors$specie = NULL
+
+combined = sf::st_join(combined, neighbors, sf::st_within)
+excluded_cols <- c("Z.x", "treeID.detection","treeID.segmentation","name_las_file","treeID","area","specie","geom")
+
+```
+
+```{r, cache=TRUE}
+#| code-fold: true
+#| warning: false
+#| results: hide
+data <- lfa::lfa_random_forest(tree_data = combined, excluded_input_columns = excluded_cols,response_variable = "specie")
+```
+
+```{r}
+#| code-fold: true
+#| warning: false
+#| fig-cap: Confusion Matrix of randomForest with all parameters derived from tree level.
+#| label: fig-cm-tree-level
+cm <- data$confusion_matrix |> caret::confusionMatrix()
+lfa::lfa_plot_confusion_matrix(cm)
+```
+
+```{r}
+#| code-fold: true
+#| warning: false
+#| fig-cap: Precsion and Recall of randomForest with all parameters derived from tree level.
+#| label: fig-pr-tree-level
+data$confusion_matrix |> lfa::lfa_calculate_rf_metrics() |> lfa::lfa_visualize_rf_metrics()
+```
+