midproject code.Rmd

---
title: "mid project"
output:
  pdf_document: default
  html_document: default
date: "2024-11-22"
---

```{r}
require(tidyverse)
require(deSolve)
```

```{r}
Big_data <- read_csv("/Users/andrewbatmunkh/Desktop/eeb313/Big.csv")
head(Big_data)
```
**Test if the log(mass) is normally distributed
```{r}
Big_data<- Big_data %>%
  mutate(log_mass = log(mass))

hist(Big_data$log_mass, breaks = 30, main = "Histogram of log(mass)", xlab = "log(mass)")

hist(Big_data$log_mass, breaks = 30, probability = TRUE, main = "Histogram with Normal Curve", xlab = "log(mass)")
curve(dnorm(x, mean = mean(Big_data$log_mass), sd = sd(Big_data$log_mass)), add = TRUE, col = "red")


```

**Violin Plot of Log(Mass) by Disease Group and Sex**
```{r}
data_sex <- Big_data %>%
  mutate(disease_group = ifelse(disease_time_step == "pre-invasion", 
                                "Pre-Invasion", 
                                "Post-Invasion")) %>%
  mutate(log_mass = log(mass))

ggplot(data_sex, aes(x = disease_group, y = log_mass, fill = disease_group)) +
  geom_violin(trim = FALSE) +
  geom_point(alpha = 0.01, position = "jitter") +  
   stat_summary(fun = mean, geom = "crossbar", 
               width = 0.3, color = "red", size = 0.3) +  
  facet_wrap(~sex) +
  labs(
    title = "Violin Plot of Log(Mass) by Disease Group and Sex",
    x = "Disease Group",
    y = "Log(Mass)"
  ) 
```

```{r}
glm_model <- glm(log_mass ~ disease_group * sex, data = data_sex)

summary(glm_model)
```


**Violin Plot of Log(Mass) by Disease Group and Age**
```{r}
data_age <- Big_data %>%
  mutate(disease_group = ifelse(disease_time_step == "pre-invasion", 
                                "Pre-Invasion", 
                                "Post-Invasion")) %>%
  mutate(log_mass = log(mass))

ggplot(data_age, aes(x = disease_group, y = log_mass, fill = disease_group)) +
 geom_violin(alpha = 1) +
  geom_point(alpha = 0.01, position = "jitter") +
  stat_summary(fun = mean, geom = "crossbar", 
               width = 0.3, color = "red", size = 0.3) + 
  facet_wrap(~age) +
  labs(
    title = "Violin Plot of Log(Mass) by Disease Group and Age",
    x = "Disease Group",
    y = "Log(Mass)"
  ) 
```

```{r}
glm_age <- glm(log_mass ~ disease_group * age, data = data_age)

summary(glm_age)
```
**Violin Plot of Log(Mass) by Disease Group and Pregnancy Status**
```{r}

data_pregnant <- Big_data %>%
  mutate(pregnancy_status = ifelse(repstat == "pregnant", 
                                   "Pregnant", 
                                   "Not Pregnant")) %>%
  mutate(disease_group = ifelse(disease_time_step == "pre-invasion", 
                                "Pre-Invasion", 
                                "Post-Invasion")) %>%
  mutate(log_mass = log(mass))

ggplot(data_pregnant, aes(x = disease_group, y = log_mass, fill = disease_group)) +
  geom_violin(alpha = 0.02) +
  geom_point(alpha = 0.01, position = "jitter") +
   stat_summary(fun = mean, geom = "crossbar", 
               width = 0.3, color = "red", size = 0.3) + 
  facet_wrap(~pregnancy_status) +
  labs(
    title = "Violin Plot of Log(Mass) by Disease Group and Pregnancy Status",
    x = "Disease Group",
    y = "Log(Mass)"
  ) 
```

```{r}
glm_pregnancy <- glm(log_mass ~ disease_group * pregnancy_status, data = data_pregnant)

summary(glm_pregnancy)
```