Project_EDA_Critical.Rmd

---
title: "Project_EDA"
author: "Maria Martinez"
date: "2024-10-22"
output: html_document
---

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

## R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see <http://rmarkdown.rstudio.com>.

When you click the **Knit** button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

```{r cars}
summary(cars)
```

## Including Plots

You can also embed plots, for example:

```{r pressure, echo=FALSE}
plot(pressure)
```

Note that the `echo = FALSE` parameter was added to the code chunk to prevent printing of the R code that generated the plot.
```{r}
```


```{r}
# Packages and Libraries 
library(tidyverse)
library(readr)
library(Ecdat)
library(ggplot2)
library(ISLR)
library(GGally)
library(car)
library (scatterplot3d)
library (corrplot)
library(corrgram)
library(stats)
library(dplyr)
library(outliers)


```


```{r}
# Setting Directory and clean 
getwd()
rm(list = ls())
set.seed(28)

```
## Read the data

```{r}
data <- read.csv("health_data.csv")
head(data)
View(head(data,10))
str(data)


```
## Data to variable type and creating the main dummy variables for exploratory step
```{r}
data$Outcome <- as.factor(data$Outcome)
data$Gender<- as.factor(data$Gender)
data$SmokingStatus <- as.factor(data$SmokingStatus)
data$AlcoholConsumption <- as.factor(data$AlcoholConsumption)
data$ExerciseFrequency <- as.factor(data$ExerciseFrequency) 
data$Diabetes <- as.factor(data$Diabetes)
data$HeartDisease <- as.factor(data$HeartDisease)
data$PhysicalActivityLevel <- as.factor(data$PhysicalActivityLevel) 
data$DietQuality <- as.factor(data$DietQuality)
data$MedicationAdherence <- as.factor(data$MedicationAdherence)

head(data)
data <-data %>% mutate (Critical = ifelse (Outcome == "Critical" , 1,0)) %>% mutate (At_Risk = ifelse (Outcome == "At Risk" , 1,0)) %>% mutate (Healthy = ifelse (Outcome == "Healthy" , 1,0))
view(head(data))
str(data)

```

## Percentage (Darren Warren)
```{r}
Table <- data %>% group_by(Outcome) %>%
  summarise( count = n())
table <- as.data.frame(Table)
str(table)

total = sum(table$count)
table$percentage <- round(table$count/total*100,0)
table
```


```{r}
data_critical <- data %>% filter (Outcome == "Critical")
head(data_critical)

```


```{r}
data_critical <- data_critical[,1:17]
str(data_critical)
```


```{r}
data_critical %>% group_by(HeartDisease, Diabetes) %>%
summarise (heart_diabetes_disease= n())
```

## Cholesterol Level in the dataset for Critical group

```{r}
TableCh <- data_critical %>% 
  summarise( count = n(), avg_Cholesterol = mean(CholesterolLevel), min(CholesterolLevel), max(CholesterolLevel))
TableCh
```
## Diabetes in the dataset for Outcome group

```{r}
TableD <- data_critical %>% group_by(Diabetes) %>%
  summarise ( count =n())
TableD

```

## Demographic - Gender in the data set for Outcome Group
```{r}
TableG <- data %>% group_by(Gender) %>%
  summarise ( count =n())
TableG

```

## Demographic - Age in the data set for Outcome Group
```{r}
TableAg <- data %>% group_by(Age) %>%
  summarise ( count =n())
TableAg

```


## Histogram by Age

```{r}

ggplot(data=data_critical, aes(data_critical$Age)) + 
                 geom_histogram(breaks=seq(18, 90, by =2), 
                 col="red", 
                 fill="green", 
                 alpha = .2) + 
  labs(title="Histogram for age") +
  labs(x="Age", y="Count")

```
## Histogram by BMI

```{r}
ggplot(data=data_critical, aes(data_critical$BMI)) + 
                 geom_histogram(breaks=seq(10, 50, by =2), 
                 col="red", 
                 fill="green", 
                 alpha = .2) + 
  labs(title="Histogram for BMI") +
  labs(x="BMI", y="Count")



```
## Histogram by Genetic Risk

```{r}

ggplot(data=data_critical, aes(data_critical$GeneticRisk)) + 
                 geom_histogram(breaks=seq(0, 1, by =.01), 
                 col="red", 
                 fill="green", 
                 alpha = .2) + 
  labs(title="Histogram for Genetic Risk") +
  labs(x="Genetic Risk", y="Count")

```
## Histogram by Cholesterol Level

```{r}
min(data_critical$CholesterolLevel)
max(data_critical$CholesterolLevel)

ggplot(data=data_critical, aes(data_critical$CholesterolLevel)) + 
                 geom_histogram(breaks=seq(100, 300, by =2), 
                 col="red", 
                 fill="green", 
                 alpha = .2) + 
  labs(title="Histogram for Cholesterol Level") +
  labs(x="Cholesterol Level", y="Count")



```


```{r}
```

## Extract a ramdon sample "A subset from the data set". Recommend 1000 thousand data points.


```{r}
sample_1 <- sample_n(data_critical,1000)
head(sample_1)
```


## Cholesterol Level in the sample 1 

```{r}
TableCh_1 <- sample_1 %>% 
  summarise( count = n(), n_Cholesterol = mean(CholesterolLevel), min(CholesterolLevel), max(CholesterolLevel))
TableCh_1

```
`

## Boxplot graph between Age vs Diabetes
```{r}
ggplot(data=sample_1, aes(x= factor(Diabetes), y = Age, fill= factor(Diabetes))) + geom_boxplot() + ggtitle("BoxPlot for Age vs. Diabetes") + labs(x="Diabetes", y="Age")

```
## Boxplot graph between Age vs HeartDisease

```{r}
ggplot(data=sample_1, aes(x=factor(HeartDisease), y = Age, fill=factor(HeartDisease))) + geom_boxplot() + ggtitle("BoxPlot for Age vs. Heart Disease") + labs(x="Heart Disease", y="Age")

```
## Boxplot Graph between Cholesterol vs Heart Disease

```{r}
ggplot(data=sample_1, aes(x=factor(HeartDisease), y = CholesterolLevel, fill= factor(HeartDisease))) + geom_boxplot() + ggtitle("BoxPlot for Cholesterol Level vs. Heart Disease") + labs(x="Heart Disease", y="Cholesterol Level")
```


## Boxplot Graph between Cholesterol vs Diabetes

```{r}
ggplot(data=sample_1, aes(x= factor(Diabetes), y = CholesterolLevel, fill= factor(Diabetes))) + geom_boxplot() + ggtitle("BoxPlot for Cholesterol Level vs. Diabetes") + labs(x="Diabetes", y="Cholesterol Level")

```
## Boxplot Graph between Genetic Risk vs Heart Disease


```{r}
ggplot(data=sample_1, aes(x= factor(HeartDisease), y = GeneticRisk, fill= factor(HeartDisease))) + geom_boxplot() + ggtitle("BoxPlot for Genetic Risk vs. Heart Disease") + labs(x="Heart Disease", y="Genetic Risk")

```
## Boxplot Graph between Annual Checkups  vs Heart Disease


```{r}
ggplot(data=sample_1, aes(x= factor(HeartDisease), y = AnnualCheckups, fill= factor(HeartDisease))) + geom_boxplot() + ggtitle("BoxPlot for Annual Checups vs. Heart Disease") + labs(x="Heart Disease", y="Annual Chech Ups")
```



```{r}

ggplot(data=sample_1, aes(x= factor(Diabetes), y = AnnualCheckups, fill= factor(Diabetes))) + geom_boxplot() + ggtitle("BoxPlot for Annual Checups vs. Diabetes") + labs(x="Diabetes", y="Annual Chech Ups")
```
# Mapping

## Age vs BMI  and Heart Disease

```{r}
ggplot(data = sample_1) + 
  geom_point(mapping = aes(x = Age, y = BMI, color = HeartDisease)) + 
  theme(axis.text.x = element_text(size=15), axis.text.y = element_text(size=15), 
  axis.title=element_text(size=15,face="bold"))

```
## Age vs BMI  and Diabetes

```{r}
ggplot(data = sample_1) + 
  geom_point(mapping = aes(x = Age, y = BMI, color = Diabetes)) + 
  theme(axis.text.x = element_text(size=15), axis.text.y = element_text(size=15), 
  axis.title=element_text(size=15,face="bold"))
```
Genetic Risk vs BMI and Diabetes

```{r}
ggplot(data = sample_1) + 
  geom_point(mapping = aes(x = GeneticRisk, y = BMI, color = Diabetes)) + 
  theme(axis.text.x = element_text(size=15), axis.text.y = element_text(size=15), 
  axis.title=element_text(size=15,face="bold"))

```
# BMI vs Genetic Risk and Heart Disease

```{r}

ggplot(data = sample_1) + 
  geom_point(mapping = aes(x = GeneticRisk, y = BMI, color = HeartDisease)) + 
  theme(axis.text.x = element_text(size=15), axis.text.y = element_text(size=15), 
  axis.title=element_text(size=15,face="bold"))


```
## Diabetes vs Genetic Risk

```{r}
ggplot(sample_1, aes(x=GeneticRisk, y=Diabetes)) + geom_point() + 
# add logit curve
  stat_smooth(method="glm", method.args=list(family="binomial"), se=FALSE) +
#add the regression line
    geom_smooth(method=lm,  color="red", # Add linear regression lines
              se=FALSE,    # Don't add shaded confidence region
              fullrange=TRUE) 


```

## Diabetes vs BMI

```{r}

ggplot(sample_1, aes(x=BMI, y=Diabetes)) + geom_point() + 
# add logit curve
  stat_smooth(method="glm", method.args=list(family="binomial"), se=FALSE) +
#add the regression line
    geom_smooth(method=lm,  color="red", # Add linear regression lines
              se=FALSE,    # Don't add shaded confidence region
              fullrange=TRUE) 





```


```{r}
```


```{r}
```


```{r}