Data Visualisation_final.Rmd

---
title: "Data Visualisations"
author: "Essa Taher"
date: "2023-04-16"
output: word_document
---

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

```{r, message=TRUE, warning=FALSE}
setwd("C:/Users/Admins/Desktop")
library(readr)
real_est<-read_csv("ProjectRealEstate_.csv")
```

## Data Cleaning

```{r}
real_est<-real_est[,-c(21:24)]

real_est$price<-as.numeric(gsub(",","",real_est$price))

real_est$statusText[real_est$statusText=="ACTIVE"]<-"Active"
```

## Data Visualisations

### Plot 1

```{r}
real_est %>% 
  group_by(addressCity) %>% 
  summarise(Listings=n()) %>% 
  top_n(10) %>% 
  ggplot(aes(x=reorder(addressCity,Listings,decreasing = F),y=Listings))+
  geom_bar(stat = "identity",fill="#1E3256")+
  labs(x="City",title = "Top 10 Cities with Highest Listings")+
  geom_text(aes(label=Listings),hjust=-0.1)+
  ylim(0,6500)+
  coord_flip()
```

### Plot 2

```{r}
real_est %>% 
  group_by(addressState) %>% 
  summarise(Listings=n()) %>% 
  top_n(10) %>% 
  ggplot(aes(x=reorder(addressState,Listings,decreasing = F),y=Listings))+
  geom_bar(stat = "identity",fill="#1E3256")+
  labs(x="States",title = "Top 10 States with Highest Listings")+
  geom_text(aes(label=Listings),hjust=-0.1)+
  ylim(0,25000)+
  coord_flip()
```

### Plot 3

```{r}
options(scipen = 999)
real_est %>% 
  filter(homeType!="") %>% 
  ggplot(aes(x=homeType,y=log(price)))+
  geom_boxplot()+
  coord_flip()+
  labs(x="Home Type",y="log(Price)",title = "Boxplots of log(Price) by Home Type")
```


### Plot 4

```{r}
real_est %>% 
  filter(homeType!="") %>% 
  group_by(homeType) %>% 
  summarise(Avg.Price = round(mean(price,na.rm = T),2)) %>% 
  ggplot(aes(x=reorder(homeType,Avg.Price),y=Avg.Price))+
  geom_bar(stat = "identity",fill="#1E3256")+
  labs(x="Home Type",title = "Average Price of Different Home Types",y="Average Price")+
  geom_text(aes(label=Avg.Price),hjust=-0.1)+
  ylim(0,1100000)+
  coord_flip()
```

### Plot 5

```{r}
real_est %>% 
  filter(price<100000000 & area <400000) %>% 
  ggplot(aes(x=area,y=price))+
  geom_point(alpha=0.5)+
  geom_smooth(method = lm)+
  labs(x="Area",y="Price",title = "Relationship between Area and Price",
       subtitle = "Price less than 100000000 and Area less than 400000")
```

### Plot 6

```{r, fig.height=10}
counts <- table(real_est$homeType[real_est$homeType!=""])
lbls <- paste(rownames(counts),
              '',
              round(counts / sum(counts), 4) * 100,
              '%') 
pie(counts, labels = lbls, col = c("black","#1E3256","#5D5D50","#5D5D5D","#B2B2B2", "#DDDDDD","#DDDDD0"),
    main = 'Percentages of Listings by Home Type',cex=.6)

```

### Plot 7

```{r}
real_est %>% 
  filter(price<100000000 & beds <150) %>% 
  ggplot(aes(x=beds,y=price))+
  geom_point(alpha=0.5)+
  geom_smooth(method = lm)+
  labs(x="Number of Beds",y="Price",title = "Relationship between Number of Beds and Price",
       subtitle = "Price less than 100000000 and Beds less than 150")
```


### Plot 8

```{r}
real_est %>% 
  filter(price<100000000 & baths <100) %>% 
  ggplot(aes(x=baths,y=price))+
  geom_point(alpha=0.5)+
  geom_smooth(method = lm)+
  labs(x="Number of Baths",y="Price",title = "Relationship between Number of Baths and Price",
       subtitle = "Price less than 100000000 and Baths less than 100")
```

### Plot 9

```{r}
real_est %>% 
  group_by(statusText) %>% 
  summarise(Listings=n()) %>% 
  top_n(10) %>% 
  ggplot(aes(x=reorder(statusText,Listings,decreasing = F),y=Listings))+
  geom_bar(stat = "identity",fill="#1E3256")+
  labs(x="Status Text",title = "Top 10 Status Text with Highest Listings")+
  geom_text(aes(label=Listings),hjust=-0.1)+
  ylim(0,65000)+
  coord_flip()
```

### Plot 10

```{r}
real_est %>% 
  filter(price<100000000 & lotAreaRaw <100000000) %>% 
  ggplot(aes(x=lotAreaRaw,y=price))+
  geom_point(alpha=0.5)+
  geom_smooth(method = lm)+
  labs(x="Lot Area",y="Price",title = "Relationship between Number of Lot Area and Price",
       subtitle = "Price less than 100000000 and Lot Area less than 100000000")
```

### plot 11

```{r}
library(ggplot2)

# create a new data frame with the counts of each state
state_counts <- data.frame(table(real_est$addressState))

# create a pie chart of the state counts
ggplot(state_counts, aes(x="", y=Freq, fill=Var1)) +
  geom_bar(stat="identity", width=1) +
  coord_polar(theta="y") +
  labs(title="State Distribution", x=NULL, y=NULL) +
  scale_fill_discrete(name="State")

# create a new data frame with the counts of each city
city_counts <- data.frame(table(real_est$addressCity))

# create a pie chart of the city counts
ggplot(city_counts, aes(x="", y=Freq, fill=Var1)) +
  geom_bar(stat="identity", width=1) +
  coord_polar(theta="y") +
  labs(title="City Distribution", x=NULL, y=NULL) +
  scale_fill_discrete(name="City")

```

### plot 12

```{r}
library(ggplot2)
library(gridExtra)

# create a new data frame with the counts of each state
state_counts <- data.frame(table(real_est$addressState))

# create a pie chart of the state counts
state_pie <- ggplot(state_counts, aes(x="", y=Freq, fill=Var1)) +
  geom_bar(stat="identity", width=1) +
  coord_polar(theta="y") +
  labs(title="State Distribution", x=NULL, y=NULL) +
  scale_fill_discrete(name="State") +
  theme_void()

# create a new data frame with the counts of each city
city_counts <- data.frame(table(real_est$addressCity))

# create a pie chart of the city counts
city_pie <- ggplot(city_counts, aes(x="", y=Freq, fill=Var1)) +
  geom_bar(stat="identity", width=1) +
  coord_polar(theta="y") +
  labs(title="City Distribution", x=NULL, y=NULL) +
  scale_fill_discrete(name="City") +
  theme_void()

# create a new data frame with the counts of price
price_counts <- data.frame(table(cut(real_est$price, breaks = seq(0, 2000000, by = 50000))))

# create a pie chart of the price counts
price_pie <- ggplot(price_counts, aes(x="", y=Freq, fill=Var1)) +
  geom_bar(stat="identity", width=1) +
  coord_polar(theta="y") +
  labs(title="Price Distribution", x=NULL, y=NULL) +
  scale_fill_brewer(name="Price", palette="Blues") +
  theme_void()

# arrange the pie charts in a grid
grid.arrange(state_pie, city_pie, price_pie, ncol=3)

```