---
title: "District_PGI Performance Dashboard"
output: 
  flexdashboard::flex_dashboard:
    orientation: rows
    vertical_layout: scroll
    theme: paper
    social: menu
    source_code: embed
---

```{r setup, include=FALSE}

# Load necessary libraries
library(tidyverse)
library(tidyr) # Explicitly load tidyr
library(ggplot2)
library(skimr)
library(dplyr)
library(flexdashboard)
library(DT)
# Set default figure width and height
knitr::opts_chunk$set(fig.width = 8, fig.height = 6)

```

# Missing values

### checking for missing values
```{r}
# Load Dataset from CSV file
district_data <- read.csv("District_PGI_Table_1.csv")
```
```{r}

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

### Create Region column based on States
```{r}
# Create Region column based on States
district_data <- district_data %>%
  mutate(Region = case_when(
    State.UT %in% c("Andhra Pradesh", "Karnataka", "Kerala", "Tamil Nadu", "Telangana") ~ "Southern",
    State.UT %in% c("Punjab", "Haryana", "Uttar Pradesh", "Bihar") ~ "Northern",
    TRUE ~ "Other"
  ))

# Print a sample to verify
print(head(district_data))

```

# dataset description {.tabset}

### summary
```{r}
# Summary Statistics for the dataset
skim(district_data)

```

# structure of the data
```{r}
# Structure of the dataset
str(district_data)

```




## Univariate Analysis {.tabset .tabset-fade}

### Histogram of Overall Scores
```{r}

ggplot(district_data, aes(x = District.score.2021.22...Overall)) +
  geom_histogram(binwidth = 5, fill = "skyblue", color = "black") +
  labs(title = "Histogram of District Overall Scores (2021-22)",
       x = "Overall District Score", y = "Count")

```

### Boxplot of Overall Scores
```{r}
ggplot(district_data, aes(y = District.score.2021.22...Overall)) +
  geom_boxplot(fill = "lightblue", color = "black") +
  labs(title = "Boxplot of District Overall Scores", y = "Overall Score")

```

## Bivariate Analysis {.tabset .tabset-fade}

### Scatter Plot: ECT Score vs Overall Score
```{r}
ggplot(district_data, aes(x = District.score.2021.22...Category...2..ECT..90., y = District.score.2021.22...Overall)) +
  geom_point(color = "blue") +
  geom_smooth(method = "lm", color = "red", se = FALSE) +
  labs(title = "Scatter Plot: ECT Score vs Overall Score",
       x = "ECT Score", y = "Overall Score")

```

### Boxplot of Overall Scores by Region
```{r}
ggplot(district_data, aes(x = Region, y = District.score.2021.22...Overall, fill = Region)) +
  geom_boxplot() +
  labs(title = "Boxplot of Overall Scores by Region", x = "Region", y = "Overall Score")

```

## Multivariate Analysis {.tabset .tabset-fade}

### Correlation Matrix of Scores

```{r}
# Correlation Matrix for Selected Columns
cor_matrix <- cor(district_data[, c("District.score.2021.22...Overall", 
                           "District.score.2021.22...Category...1.Outcome..290.", 
                           "District.score.2021.22...Category...2..ECT..90.")], use = "complete.obs")
cor_matrix

```


### Heatmap: State-wise PGI Performance
```{r}
ggplot(district_data, aes(x = State.UT, y = District.score.2021.22...Category...1.Outcome..290., fill = District.score.2021.22...Overall)) +
  geom_tile() +
  scale_fill_gradient(low = "white", high = "red") +
  theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
  labs(title = "Heatmap of State-wise PGI Scores", x = "State/UT", y = "Outcome Score")

```

### lineplot
```{r}
# Rename the dataset to avoid conflicts with any existing functions
district_data <- read.csv("District_PGI_Table_1.csv")

# Reshape the data for multivariate line plot
district_data_long <- district_data %>%
  pivot_longer(cols = c("District.score.2021.22...Overall", 
                        "District.score.2021.22...Category...1.Outcome..290.", 
                        "District.score.2021.22...Category...2..ECT..90."),
               names_to = "Score_Type", values_to = "Score_Value")

# Line plot comparing district scores across different categories by State/UT
ggplot(district_data_long, aes(x = State.UT, y = Score_Value, color = Score_Type, group = Score_Type)) +
  geom_line(size = 1) +
  geom_point(size = 2) +
  theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
  labs(title = "Line Plot: District Scores by State/UT and Score Category",
       x = "State/UT", y = "Score Value", color = "Score Category")

```