EEB_Mosquito_Project

---
title: 'Mosquito Project: Dec 8, 2022'
author: "Emilie Nero, Julia Marques, Sarah Martinez-Fuller, Simon Sevenier"
output:
  pdf_document: default
---

```{r, eval=FALSE}
library(tidyverse)
```

```{r}
mosquito_data<-read.csv("CDC_host_seeking_mosquitoes_and_MClim_data_NERC.csv") #importing the csv file into R

# Removing the columns that we are not looking at (includes male abundances, and maximum and minimum temperature and humidity)
filtered_mosquito_data<-subset(mosquito_data, select = -c(Agml,Afml,Acml,Acfem, 
                                  OthAn,MaxTemp,MaxHum,MinTemp,MinHum))


sum(is.na(filtered_mosquito_data))  # assessing the number of Na


clean_mosquito_data <- filtered_mosquito_data %>%   # removing the Na
  filter((!is.na(Agfed)) &
           (!is.na(Agunf)) &
           (!is.na(Aggrv)) &
           (!is.na(Affed)) &
           (!is.na(Affunf)) &
           (!is.na(Afgrv)))


sum(is.na(clean_mosquito_data))  # checking the number of Na again



write.csv(clean_mosquito_data, "clean_mosquito_data.csv")  # creating a new csv dataset with only the variables of interest

mosquito <- read.csv("clean_mosquito_data.csv")  # calling this new dataset in R
```


# Rapid Exploratory Analysis

```{r}
str(mosquito)

#Histogram of mean temperatures in each sites

ggplot(data=clean_mosquito_data)+theme_classic()+
  geom_histogram(aes(x=MeanTemp))+
  labs(title= "distribution of the mean temperature recorded in each sites")


#Histogram of mean humidity in each sites

ggplot(data=clean_mosquito_data)+theme_classic()+
  geom_histogram(aes(x=MeanHum))+
  labs(title= "distribution of the mean humidity recorded in each sites")
```