---
title: "EDA for CWC(Agency) Dataset"
output:
  flexdashboard::flex_dashboard:
    orientation: rows
    vertical_layout: scroll
    theme: flatly
    social: menu
    source_code: embed
    color: blue
---


```{r setup, include=FALSE}
library(flexdashboard)
library(flexdashboard)
library(MASS)
library(lattice)
library(dplyr)
library(ggplot2)
library(shiny)
library(DT)
```

# Dataset Description

## View of dataset

```{r}
daf <- read.csv("/cloud/project/Daily_data_of_reservoir_level_of_Central_Water_Commission_(CWC)_Agency_during_June_2024.csv")

datatable(daf, extensions = "Buttons",options=list(dom='Bfrtip',Buttons=c('copy','csv','print','pdf')))


```

# About

## Structure of the dataset

### Structure of the dataset

```{r}
str(daf)
```


## Missing values and outliers detection

### Missing values and outliers detection

```{r}
#Identifying missing values in the dataset
missing_value <- sapply(Insurance, function(x) sum(is.na(x)))
missing_value

#Impute missing values with the mean for numeric columns
Insurance <- Insurance %>% 
  mutate(across(where(is.numeric), ~ifelse(is.na(.), mean(., na.rm = TRUE), .)))

#Function to detect outliers (assuming you have a custom function or using a standard approach)
detect_outliers <- function(data, column_name) {
  # Calculate z-scores
  z_scores <- abs((data[[column_name]] - mean(data[[column_name]], na.rm = TRUE)) / sd(data[[column_name]], na.rm = TRUE))
  # Identify outliers (those with z-scores greater than a threshold, e.g., 3)
  outliers <- data[z_scores > 3, column_name]
  return(outliers)
}

#Detect outliers in 'Holders' and 'Claims' columns
outliers_holders <- detect_outliers(Insurance, "Holders")
outliers_claims <- detect_outliers(Insurance, "Claims")

#Filter out the outliers from the Insurance dataset
Insurance_Clean <- Insurance %>% 
  filter(!(Holders %in% outliers_holders)) %>% 
  filter(!(Claims %in% outliers_claims))
```

# Summary

## summary

### summary

```{r}
summary(daf)
```



# Piechart


```{r}
total_Long =sum(daf$Long, na.rm = TRUE)
total_fullreservoirlevel=sum(daf$Full_reservoir_level, na.rm = TRUE)
total_Lat=sum(daf$Lat, na.rm = TRUE)
total_Level = sum(daf$Live_capacity_FRL, na.rm = TRUE)

summary_data =data.frame(
  Category = c("Total Longtitude", "Total full revservoirlevel", "Total Latitude", "Total Level"),
  Value = c(total_Long, total_fullreservoirlevel, total_Lat, total_Level)
)

ggplot(summary_data, aes(x = "", y = Value, fill = Category)) +
  geom_bar(width = 1, stat = "identity") +
  coord_polar(theta = "y") +
  theme_void() +
  geom_text(aes(label = paste0(round(Value / sum(Value) * 100, 1), "%")), position = position_stack(vjust = 0.5)) +
  labs(title = "Distribution of Attributes")
```

# Uni-variate Analysis {#bivariate-analysis}

## Histogram for single variable

### Histogram for Longitude

```{r}
ggplot(daf, aes(x = Long)) +
  geom_histogram(fill = "lightblue", color = "black") +
  geom_vline(aes(xintercept = mean(Long)), color = "red", lwd = 1) +
  labs(title = "Histogram of Longitude", x = "Longitude")
```

### Histogram for Latitude

```{r}
ggplot(daf, aes(x = Lat)) +
  geom_histogram(fill = "violet", color = "black") +
  geom_vline(aes(xintercept = mean(Lat)), color = "red", lwd = 1) +
  labs(title = "Histogram of Latidude", x = "Latidude")
```

### Histogram for population density

```{r}
ggplot(daf, aes(x = Level)) +
  geom_histogram(bins = 100, fill = 'blue', color = 'black') +
  geom_vline(aes(xintercept = mean(Level)), color = 'red', lwd = 1) +
  labs(title = "Histogram of Level", x = "Popden", y = "Frequency")

```



### Histogram for Long

```{r}
hist(daf$Long ,breaks=500,xlim=c(0,1000),main="distriubution of Logtitude",col=c('blue','orange'))

```

### Histogram for Lat

```{r}
hist(daf$Lat ,breaks=500,xlim=c(0,1000),main="distriubution of Latitude",col=c('pink','yellow'))
```

### Histogram for Level

```{r}
hist(daf$Level ,breaks=500,xlim=c(0,1000),main="distriubution of Level",col=c('violet','gray'))
```



# Bivariate Analysis

## Box plot

### Box Plot for Long

```{r}
boxplot(daf$Long)
```

### Box Plot for Full_reservoir_level

```{r}
boxplot(daf$Full_reservoir_level)
```

### Box Plot for Lat

```{r}
boxplot(daf$Lat)
```

### Box Plot for Live_capacity_FRL 

```{r}
boxplot(daf$Live_capacity_FRL)
```

### Box Plot for Year

```{r}
boxplot(daf$Year)
```

### Box Plot for Month

```{r}
boxplot(daf$Month)
```



# Multi-variate Analysis

## Scatter plot

### Scater plot Longtidude vs Latitude

```{r}
ggplot(daf, aes(x = Long, y = Lat)) +
  geom_point() +
  labs(title = "Scatter plot of long vs. lat")
```


### Scater plot for  Level vs Latidude

```{r}

ggplot(daf, aes(x = Level, y = Lat)) +
  geom_point() +
  labs(title = "Scatter plot of level vs. lat")
```


### Scater plot for Longtidude vs Storage

```{r}
ggplot(daf, aes(x = Long, y = Storage)) +
  geom_point() +
  labs(title = "Scatter plot of long vs. storage")
```


### Scater plot for Level vs Storage

```{r}

ggplot(daf, aes(x = Level, y =Storage)) +
  geom_point() +
  labs(title = "Scatter plot of level vs. storage")
```




# insights and inference


### insights and inference in pdf



```{r}

# This code generates the HTML to display the PDF
pdf_path ="https://github.com/mvjayaruthra14/INSIGHTS_AND_INFERENCES_OF_EDA/blob/main/file_show.pdf"  
htmltools::tags$iframe(src = pdf_path, width = "100%", height = "600px")

```