EDA for Gov data set

---
title: "EDA for Gov data set"
output: 
  flexdashboard::flex_dashboard:
    orientation: rows
    vertical_layout: scroll
    theme: journal
    social: menu
    source_code: embed
---

```{r setup, include=FALSE}
library(flexdashboard)
library(ggplot2)
library(dplyr)
library(reshape2)
library(corrplot)
```

## load data  {.tabset}
### view the data set

```{r}
# Load the dataset
df <- read.csv("Defence_Production_22082024.csv")

# Data Cleaning: Remove commas and convert to numeric
df$Defence.Public.Sector.Undertakings..in.Rs.Cr. <- as.numeric(gsub(",", "", df$Defence.Public.Sector.Undertakings..in.Rs.Cr.))
df$New.Defence.Public.Sector.Undertakings..in.Rs.Cr. <- as.numeric(gsub(",", "", df$New.Defence.Public.Sector.Undertakings..in.Rs.Cr.))
df$Other.Public.Sector.Undertakings.Joint.Ventures..in.Rs.Cr. <- as.numeric(gsub(",", "", df$Other.Public.Sector.Undertakings.Joint.Ventures..in.Rs.Cr.))
df$Defence.Private.Companies..in.Rs.Cr. <- as.numeric(gsub(",", "", df$Defence.Private.Companies..in.Rs.Cr.))
df$Total.Production..in.Rs.Cr. <- as.numeric(gsub(",", "", df$Total.Production..in.Rs.Cr.))

# Convert Year to a factor for better plotting
df$Year <- as.factor(df$Year)

# Display the first few rows of the dataset
head(df)


```

### summary
```{r}
# Summary of the dataset
summary(df)

# Check for any missing values
colSums(is.na(df))
```


## plots {.tabset}
### Histogram of Total Production
```{r}
# 1. Histogram of Total Production
ggplot(df, aes(x = Total.Production..in.Rs.Cr.)) +
  geom_histogram(binwidth = 5000, fill = "blue", color = "black") +
  labs(title = "Histogram of Total Production", x = "Total Production (Rs Cr)", y = "Frequency")

```

###  Boxplot of Total Production by Year

```{r}
# 2. Boxplot for comparison across categories
ggplot(df, aes(x = Year, y = Total.Production..in.Rs.Cr.)) +
  geom_boxplot(fill = "green") +
  labs(title = "Boxplot of Total Production by Year", x = "Year", y = "Total Production (Rs Cr)")

```

### Scatter Plot of Defence Public Sector Undertakings vs Total Production

```{r}
# 3. Scatter plot: Total Production vs Defence Public Sector Undertakings
ggplot(df, aes(x = Defence.Public.Sector.Undertakings..in.Rs.Cr., y = Total.Production..in.Rs.Cr.)) +
  geom_point(color = "red") +
  geom_smooth(method = "lm", se = FALSE) +
  labs(title = "Scatter Plot of Defence Public Sector Undertakings vs Total Production", 
       x = "Defence Public Sector Undertakings (Rs Cr)", 
       y = "Total Production (Rs Cr)")

```
### Bar Chart: Production of Different Sectors across the Years

```{r}

# 4. Bar Chart: Production of Different Sectors across the Years
df_melted <- melt(df, id.vars = 'Year', measure.vars = c(
  'Defence.Public.Sector.Undertakings..in.Rs.Cr.', 
  'New.Defence.Public.Sector.Undertakings..in.Rs.Cr.', 
  'Other.Public.Sector.Undertakings.Joint.Ventures..in.Rs.Cr.', 
  'Defence.Private.Companies..in.Rs.Cr.'
))

ggplot(df_melted, aes(x = Year, y = value, fill = variable)) +
  geom_bar(stat = "identity", position = "dodge") +
  labs(title = "Sector-Wise Production over the Years", x = "Year", y = "Production (Rs Cr)", fill = "Sector") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))
```

### Line Plot: Trend in Total Production over the Years

```{r}
# 5. Line Plot: Trend in Total Production over the Years
ggplot(df, aes(x = Year, y = Total.Production..in.Rs.Cr.)) +
  geom_line(group = 1, color = "blue", size = 1.2) +
  geom_point(color = "red", size = 3) +
  labs(title = "Trend of Total Production over the Years", x = "Year", y = "Total Production (Rs Cr)")
```