---
title: "EDA_furniture"
output:
flexdashboard::flex_dashboard:
orientation: rows
vertical_layout: scroll
theme: flatly
social: menu
source_code: embed
navbar:
- { title: "Dataset Description", href: "#dataset-description" }
- { title: "Univariate Analysis", href: "#univariate-analysis" }
- { title: "Bivariate Analysis", href: "#bivariate-analysis" }
- { title: "Multivariate Analysis", href: "#multivariate-analysis" }
---
```{r setup, include=FALSE}
library(flexdashboard)
library(readr)
library(ggplot2)
library(dplyr)
library(reshape2)
library(lubridate)
library(corrplot)
```
## Dataset Description {.tabset}
### view of the dataset
```{r}
# Load the dataset
df <- read_csv("Furniture.csv")
head(df)
tail(df)
```
### About the dataset
```{r}
# View the structure of the dataset
str(df)
```
### summary of the dataset
```{r}
# Summary statistics for numeric columns
summary(df)
```
### Head of DataSet
```{r}
# View the first few rows
head(df)
```
### Checking for missing values
```{r}
# Checking for missing values
colSums(is.na(df))
```
## Univariate Analysis {.tabset}
### Histogram for 'price'
```{r}
ggplot(df, aes(x = price)) +
geom_histogram(binwidth = 50, fill = "blue", color = "black") +
labs(title = "Histogram of Price", x = "Price", y = "Frequency") +
theme_minimal()
```
### Histogram for 'cost'
```{r}
# Histogram for 'cost'
ggplot(df, aes(x = cost)) +
geom_histogram(binwidth = 50, fill = "green", color = "black") +
labs(title = "Histogram of Cost", x = "Cost", y = "Frequency") +
theme_minimal()
```
### Histogram for 'sales'
```{r}
# Histogram for 'sales'
ggplot(df, aes(x = sales)) +
geom_histogram(binwidth = 5, fill = "orange", color = "black") +
labs(title = "Histogram of Sales", x = "Sales", y = "Frequency") +
theme_minimal()
```
### Histogram for 'profit_margin'
```{r}
# Histogram for 'profit_margin'
ggplot(df, aes(x = profit_margin)) +
geom_histogram(binwidth = 5, fill = "purple", color = "black") +
labs(title = "Histogram of Profit Margin", x = "Profit Margin (%)", y = "Frequency") +
theme_minimal()
```
### Histogram for 'inventory'
```{r}
# Histogram for 'inventory'
ggplot(df, aes(x = inventory)) +
geom_histogram(binwidth = 10, fill = "red", color = "black") +
labs(title = "Histogram of Inventory", x = "Inventory", y = "Frequency") +
theme_minimal()
```
### Histogram for 'discount_percentage'
```{r}
# Histogram for 'discount_percentage'
ggplot(df, aes(x = discount_percentage)) +
geom_histogram(binwidth = 5, fill = "cyan", color = "black") +
labs(title = "Histogram of Discount Percentage", x = "Discount Percentage", y = "Frequency") +
theme_minimal()
```
### Histogram for 'delivery_days'
```{r}
# Histogram for 'delivery_days'
ggplot(df, aes(x = delivery_days)) +
geom_histogram(binwidth = 2, fill = "yellow", color = "black") +
labs(title = "Histogram of Delivery Days", x = "Delivery Days", y = "Frequency") +
theme_minimal()
```
### Histogram for 'price'
```{r}
ggplot(df, aes(x = price)) +
geom_histogram(binwidth = 50, fill = "blue", color = "black") +
labs(title = "Histogram of Price", x = "Price", y = "Frequency") +
theme_minimal()
```
## Bivariate Analysis {.tabset}
### Scatter plot for 'price' vs 'sales'
```{r}
# Scatter plot for 'price' vs 'sales'
ggplot(df, aes(x = price, y = sales)) +
geom_point(color = "blue", size = 3, alpha = 0.6) +
labs(title = "Scatter Plot of Price vs Sales", x = "Price", y = "Sales") +
theme_minimal()
```
### Scatter plot for 'cost' vs 'revenue'
```{r}
# Scatter plot for 'cost' vs 'revenue'
ggplot(df, aes(x = cost, y = revenue)) +
geom_point(color = "green", size = 3, alpha = 0.6) +
labs(title = "Scatter Plot of Cost vs Revenue", x = "Cost", y = "Revenue") +
theme_minimal()
```
### Scatter plot for 'inventory' vs 'profit_margin'
```{r}
# Scatter plot for 'inventory' vs 'profit_margin'
ggplot(df, aes(x = inventory, y = profit_margin)) +
geom_point(color = "red", size = 3, alpha = 0.6) +
labs(title = "Scatter Plot of Inventory vs Profit Margin", x = "Inventory", y = "Profit Margin") +
theme_minimal()
```
### Scatter plot for 'discount_percentage' vs 'delivery_days'
```{r}
# Scatter plot for 'discount_percentage' vs 'delivery_days'
ggplot(df, aes(x = discount_percentage, y = delivery_days)) +
geom_point(color = "purple", size = 3, alpha = 0.6) +
labs(title = "Scatter Plot of Discount Percentage vs Delivery Days", x = "Discount Percentage", y = "Delivery Days") +
theme_minimal()
```
## Multivariate Analysis {.tabset}
### heatmap
```{r}
# Select only numeric columns
numeric_df <- df %>% select_if(is.numeric)
# Compute the correlation matrix
cor_matrix <- cor(numeric_df, use = "complete.obs")
# Create the heatmap
corrplot(cor_matrix, method = "color", type = "full",
col = colorRampPalette(c("blue", "white", "red"))(200),
tl.col = "black", tl.srt = 45,
addCoef.col = "black", number.cex = 0.7,
title = "Correlation Heatmap", mar = c(0, 0, 1, 0))
```
