---
title: "EDA - Used Car from Ebay Kleinanzeigen"
output: 
  flexdashboard::flex_dashboard:
    orientation: rows
    social: menu
    source_code: embed
---

```{r setup, include=FALSE}
library(ggplot2)
library(plotly)
library(plyr)
library(flexdashboard)
library(data.table)
library(ggplot2)
library(lubridate)
library(dplyr)
library(gridExtra)

auto <- read.csv("autoCleaned.csv")
```

Freq. Distribute
=======================================================================

Row
-----------------------------------------------------------------------

### Histgram - Age

```{r}
ggplot(aes(as.integer(auto$age)), data=auto) +
  geom_histogram(color='black', fill=I('#F79420')) +
  scale_x_continuous(limit=c(0, 35), breaks=seq(0, 35, 2)) +
  labs(x= 'Car Age', y= 'Count', title= 'Car Age Histogram')
```


### Histgram - Mileage

```{r}
ggplot(aes(auto$mileage), data=auto) +
  geom_bar(color='black', fill=I('#F79420')) +
  scale_x_continuous(limit=c(0, 100000), breaks=seq(0, 100000, 25000)) +
  xlab("Mileage") +
  ylab("Count")
```

Row
-----------------------------------------------------------------------

### Histgram - Engine Power

```{r}
ggplot(auto, aes(auto$powerPS)) +
  geom_histogram(fill= I('#F79420'), color='black', binwidth=15) +
  labs(x= 'Engine Power', y= 'Count') +
  ggtitle('Histogram of Engine Power (PowerPS)') +
  scale_x_continuous(limit=c(0, 250), breaks=seq(0, 250, 50))
```

### Histgram - Vehicle Type

```{r}
ggplot(auto, aes(x=vehicleType)) + 
  geom_bar(fill= I('#F79420'), color='black') +
  scale_fill_brewer(type= 'div') +
  labs(x= 'Vehicle Type', y= 'Count') +
  ggtitle('Vehicle Type Frequency Diagram')
```

Price vs. Engine Power
=======================================================================

Column {.tabset}
-----------------------------------------------------------------------

### Price, EnginePower, Type

```{r}
ggplot(data = subset(auto, !is.na(powerPS)), aes(x = powerPS, y = price)) +
  geom_point(alpha = 1/50, color = I("#F79420"), position = 'jitter') +
  geom_smooth() +
  facet_wrap(~vehicleType) +
  xlab('Engine Power') +
  ylab('Price')
```


### Price vs. EnginPower

```{r}
ggplot(data= subset(auto, !is.na(powerPS)), aes(x= vehicleType, y= powerPS)) +
  geom_boxplot(alpha = 1/50, color = I("#F79420")) +
  stat_summary(fun.y = mean, geom="point", size=2) +
  xlab('Vehicle Type') +
  ylab('Engine Power')

```



Price vs. Age
=======================================================================

Column {.tabset}
-----------------------------------------------------------------------

### Price, Type, Age

```{r}
ggplot(data = subset(auto, !is.na(age)), aes(x = age, y = price)) +
  geom_point(alpha = 1/50, color = I("#F79420"), position = 'jitter') +
  geom_smooth() +
  facet_wrap(~vehicleType) +
  xlab('Age of cars') +
  ylab('Price')

```


### Price vs. Age

```{r}
ggplot(data= subset(auto, !is.na(age)), aes(x= vehicleType, y= age)) +
  geom_boxplot(alpha = 1/50, color = I("#F79420")) +
  stat_summary(fun.y = mean, geom="point", size=2) +
  xlab('Vehicle Type') +
  ylab('Age')

```


Selling Time vs. Price
=======================================================================

Column {.tabset}
-----------------------------------------------------------------------

### Selling Time vs. Price + Type


```{r}
ggplot(data = subset(auto, !is.na(sellingTime)), aes(x = price, y = sellingTime)) +
  geom_point(alpha = 1/50, color = I("#F79420"), position = 'jitter') +
  geom_smooth() +
  facet_wrap(~vehicleType) +
  xlab('Price') +
  ylab('Selling Time') 

```


### Correlation Between Price and SellingTime

Not a strong correlation!

```{r}
cor.test(auto$price, auto$sellingTime)
```