---
title: "Datenvisualisierung in R mit ggplot2"
author: "Jens Müller"
output:
  pdf_document: default
  html_document: default
date: "2025-04-14"
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

```{r}
library(readxl) # for reading Excel files
library(ggplot2) # for creating charts and plots
library(RColorBrewer) # a popular color palette
library(forcats) # for sorting factor variables
library(sf) # for reading shape files
library(dplyr) # for data manipulation
library(tidyr) # for drop_na
```

# Datenvisualisierung

## Dates des Marteloskops Möllergrab laden

```{r}
df <- read_excel('data/Marteloscope_Möllergrab_2021_DE.xlsx', sheet = '2021')
df
```

## Beschreibende Statistiken

```{r}
summary(df)
```

```{r}
# we ignore the missing data for this notebook
df_clean <- df |>
  drop_na(`h [m]`)
df_clean
```

```{r}
summary(df_clean)
```

## Visualisierungen

```{r}
# consistent colors for tree species
colors_tree_species <- brewer.pal(8, "Set2")
```

### Histogramm

```{r}
ggplot(data = df_clean, aes(x = `h [m]`)) +
  geom_histogram(binwidth=1, fill = 'steelblue', color = 'white') +
  labs(title = 'Histogramm der Baumhöhen',
       x = 'Höhe (m)',
       y = 'Anzahl der Bäume') +
  theme_minimal()
```
### Gestapeltes Säulendiagramm (Stacked Bar Chart)

```{r}
ggplot(data = df_clean, aes(x = `h [m]`, fill = factor(`Baumart`))) +
  geom_histogram(binwidth=1) +
  labs(title = 'Histogramm der Baumhöhen gestapelt nach Baumart',
       x = 'Höhe (m)',
       y = 'Anzahl der Bäume',
       fill = 'Baumart') +
  scale_fill_manual(values = colors_tree_species) +
  theme_minimal()
```

```{r}
ggplot(data = df_clean, aes(x = `h [m]`, fill = factor(`Baumart`))) +
  geom_histogram(position = 'dodge', bins = 40) +
  labs(title = 'Histogramm der Baumhöhen nach Baumart',
       x = 'Höhe (m)',
       y = 'Anzahl der Bäume',
       fill = 'Baumart') +
  scale_fill_manual(values = colors_tree_species) +
  theme_minimal()
```

### Säulendiagramm

```{r}
ggplot(data = df_clean, aes(x = `h [m]`, fill = factor(`Baumart`))) +
  geom_bar(position = 'dodge') +
  labs(title = 'Säulendiagramm der Baumhöhen mit Baumarten',
       x = 'Höhe (m)',
       y = 'Anzahl der Bäume',
       fill = 'Baumart') +
  scale_fill_manual(values = colors_tree_species) +
  theme_minimal()
```

### Balkendiagramm

```{r}
ggplot(data = df_clean, aes(x = `h [m]`, fill = factor(`Baumart`))) +
  geom_histogram(position = 'dodge', bins = 40) +
  coord_flip() + # for a horizontal bar chart
  labs(title = 'Balkendiagramm der Baumhöhen mit Baumarten',
       x = 'Höhe (m)',
       y = 'Anzahl der Bäume',
       fill = 'Baumart') +
  scale_fill_manual(values = colors_tree_species) +
  theme_minimal()
```

### Streudiagramm (Scatter Plot)

```{r}
ggplot(data = df_clean, aes(x = `d 1.3 [cm]`, y = `h [m]`, color = `Baumart`)) +
  geom_point(size = 2, alpha = 0.7) +
  labs(title = 'Brusthöhendurchmesser und Baumhöhe für unterschiedliche Baumarten\nim Marteloskop Möllergrab in 2021',
       x = 'Brusthöhendurchmesser (cm)',
       y = 'Höhe (m)') +
  scale_color_manual(values = colors_tree_species) +
  theme_minimal()
```

### Liniendiagramm (Line Chart)

```{r}
ggplot(data = df_clean |> arrange(`d 1.3 [cm]`), aes(x = `d 1.3 [cm]`, y = `G [m²]`)) +
  geom_point() +
  geom_line() +
  labs(title = 'Grundflächen in Abhängigkeit zum BHD im Marteloskop Möllergrab in 2021',
       x = 'Brusthöhendurchmesser (cm)',
       y = expression('Grundfläche (' * m^2 * ')')) +
  theme_minimal()
```

### Boxplot

```{r}
ggplot(data = df_clean, aes(x = factor(`Baumart`), y = `h [m]`, fill = factor(`Baumart`))) +
  geom_boxplot() +
  labs(title = 'Boxplot der Baumhöhen nach Baumart',
       x = 'Baumart',
       y = 'Höhe (m)',
       fill = 'Baumart') +
  scale_fill_manual(values = colors_tree_species) +
  theme_minimal()
```
### Violinplot

```{r}
ggplot(data = df_clean, aes(x = factor(`Baumart`), y = `h [m]`, fill = factor(`Baumart`))) +
  geom_violin() +
  labs(title = 'Boxplot der Baumhöhen nach Baumart',
       x = 'Baumart',
       y = 'Höhe (m)',
       fill = 'Baumart') +
  scale_fill_manual(values = colors_tree_species) +
  theme_minimal()
```
### Karten

```{r}
quadrants <- st_read('data/Geodaten_Moellergrab/EW_Marteloscop_AOIpolygons_32633.shp')
quadrants
```

```{r}
st_crs(quadrants)$epsg
```

```{r}
ggplot(data = quadrants) +
  geom_sf() +
  geom_sf_text(aes(label = subID), size = 5) +
  theme_minimal()
```
```{r}
trees <- st_read('data/Geodaten_Moellergrab/EW_Marteloscop_TreeXY_32633.shp')
trees
```

```{r}
st_crs(trees)$epsg
```

```{r}
ggplot(data = trees) +
  geom_sf(aes(color = spec_short, size = dbh_cm)) +
  scale_size(range = c(1, 3)) +
  labs(title = 'Baumstandororte mit Baumart und Brusthöhendurchmesser\nim Marteloskop Möllergrab',
       x = 'Easting (EPSG 32633)',
       y = 'Northing (EPSG 32633)',
       color = 'Baumart',
       size = "Brusthöhendurchmesser (cm)") +
  scale_color_manual(values = colors_tree_species) +
  theme_minimal()
```

```{r}
ggplot(data = quadrants) +
  geom_sf() +
  geom_sf(data = trees, aes(color = spec_short, size = dbh_cm, shape = factor(subID))) +
  scale_size(range = c(1, 3)) +
  labs(title = 'Baumstandorte mit Baumart und BHD im\nMarteloskop Möllergrab',
       x = 'Easting (EPSG 32633)',
       y = 'Northing (EPSG 32633)',
       color = 'Baumart',
       size = 'Brusthöhendurchmesser (cm)',
       shape = 'Quadrant',
       caption = "Datenquelle: Marteloskop 2021 | Autor: Jens Müller | Lizenz: CC BY-NC-SA 4.0") +
  scale_color_manual(values = colors_tree_species) +
  theme_minimal() +
  theme(plot.caption = element_text(hjust = 1, size = 7, face = "italic"))
```

```{r}
# save plot in PDF file
ggsave("plot.pdf")
```