---
title: "EDA Assignment_2"
output: 
  flexdashboard::flex_dashboard:
    orientation: rows
    vertical_layout: scroll
    theme: journal
    social: menu
    source_code: embed
---

```{r setup, include=FALSE}
library(dplyr)
library(tidyr)
library(ggplot2)
library(DT)
df <- read.csv("rain.csv")
rain<-na.omit(df)
```

## Dataset 

```{r}
datatable(
  rain,
  extensions='Buttons',
  option=list(
    dom ='Bfrtip',
    Buttons=c('copy','csv','print','pdf')
    )
  )
```

## Dataset Description {.tabset}

### About the dataset
```{r}
str(rain)
```

### Summary of the Dataset
```{r}
summary(rain)
```

## Rainfaall Distribution
```{r}
ggplot(rain,aes(x=ANNUAL)) +
  geom_histogram()+
  geom_vline(xintercept = mean(rain$ANNUAL),color="red") +
  geom_vline(xintercept = median(rain$ANNUAL),color="blue") +
  labs(title = "Distribution of Rainfall ", x = "Rainfall", y = "Count")
```

## Year Wise {.tabset}

### Year Rainfall Distribution
```{r}

group_by_year<-group_by(
  dplyr::select(rain,
                YEAR,ANNUAL,JF,MAM,JJAS,OND)
  %>% group_by(YEAR) %>%
    summarise(
      ANNUAL_sum=sum(ANNUAL),
      JF_sum=sum(JF),
      MAM_sum=sum(MAM),
      JJAS_sum=sum(JJAS),
      OND_sum=sum(OND)
    )
)


ggplot(group_by_year,aes(x=ANNUAL_sum)) +
  geom_histogram( fill = "blue", color = "white") +
  labs(title = "Distribution of Rainfall year", x = "Rainfall", y = "Count") +
  geom_vline(xintercept = mean(group_by_year$ANNUAL_sum),color="green") +
  geom_vline(xintercept = median(group_by_year$ANNUAL_sum),color="red")


```

### Stacked season
```{r}
#year wise analysis using seasons
long_data_season <- group_by_year %>%
  pivot_longer(cols = c( MAM_sum, JJAS_sum, OND_sum,JF_sum), 
               names_to = "Season", values_to = "Seasonal_sum")
#head(long_data_season)

# stacked bar plot
ggplot(long_data_season, aes(x = YEAR, y = Seasonal_sum, fill = Season)) +
  geom_bar(stat = "identity") +
  geom_hline(yintercept = mean(group_by_year$ANNUAL_sum), color = "black") +
  geom_hline(yintercept = mean(group_by_year$JF_sum), color = "red") +
  geom_hline(yintercept = mean(group_by_year$JJAS_sum), color = "green") +
  geom_hline(yintercept = mean(group_by_year$MAM_sum), color = "blue") +
  geom_hline(yintercept = mean(group_by_year$OND_sum), color = "purple") +
  labs(title = "Annual Sum by Year (Stacked by Season)", x = "Year", y = "Sum") 

```


## State wise analysis {.tabset}
```{r}
group_by_state<-group_by(
  rain
  %>% group_by(SUBDIVISION) %>%
    summarise(
      ANNUAL_avg=mean(ANNUAL),
      JF_avg=mean(JF),
      MAM_avg=mean(MAM),
      JJAS_avg=mean(JJAS),
      OND_avg=mean(OND)
    )
)
#head(group_by_state)
```

### State wise
```{r}


#average rain fall each state
ggplot(group_by_state,aes(x=SUBDIVISION, y= ANNUAL_avg)) +
  geom_bar(stat = "identity") +
  geom_hline(yintercept = mean(group_by_state$ANNUAL_avg),color="green") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))
```

### minimun rainfall
```{r}
group_by_state_min<- filter(group_by_state,ANNUAL_avg<mean(ANNUAL_avg))
#head(group_by_state_min)

long_data_state_min <-group_by_state_min %>% 
  pivot_longer(cols = JF_avg:OND_avg,names_to = "name",values_to = "Values")

ggplot(long_data_state_min,aes(x=SUBDIVISION,y=ANNUAL_avg,fill=name))+
  geom_bar(stat="identity")+
  theme(axis.text.x = element_text(angle = 45, hjust = 1))
```

### maximum rainfall
```{r}
group_by_state_max<- filter(group_by_state,ANNUAL_avg>mean(ANNUAL_avg))
#head(group_by_state_max)

long_data_state_max <-group_by_state_max %>% 
  pivot_longer(cols = JF_avg:OND_avg,names_to = "name",values_to = "Values")

ggplot(long_data_state_max,aes(x=SUBDIVISION,y=ANNUAL_avg,fill=name))+
  geom_bar(stat="identity")+
  theme(axis.text.x = element_text(angle = 45, hjust = 1))
```

## Month wise Analysis {.tabset}

### Average Monthly rainfall
```{r}
df_long_month <- rain %>%
  pivot_longer(cols = JAN:DEC, names_to = "Month", values_to = "Value")

# Boxplot for monthly values across all subdivisions
ggplot(df_long_month, aes(x = Month, y = Value)) +
  geom_boxplot() +
  labs(title = "Monthly Data Distribution", x = "Month", y = "Value") +
  theme_minimal()


```

### Minimun rainfall
```{r}
for_month <-group_by(
  rain
  %>% group_by(SUBDIVISION) %>%
    summarise(
      ANNUAL=mean(ANNUAL),
      JAN=mean(JAN),
      FEB=mean(FEB),
      MAR=mean(MAR),
      APR=mean(APR),
      MAY=mean(MAY),
      JUN=mean(JUN),
      JUL=mean(JUL),
      AUG=mean(AUG),
      SEP=mean(SEP),
      OCT=mean(OCT),
      NOV=mean(NOV),
      DEC=mean(DEC),
     
               )
    )

#names(for_month)

#for min 
for_month_min <- for_month %>%
  filter(ANNUAL < mean(ANNUAL))
#head(for_month_min)

for_month_long_min <- for_month_min  %>% 
  pivot_longer(cols = JAN:DEC, names_to = "Month", values_to = "Value")

#head(for_month_long_min)

ggplot(for_month_long_min,aes(x=Month, y= Value)) +
  geom_bar(stat = "identity") +
  facet_wrap(~SUBDIVISION) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

```

### Maximum rainfall
```{r}
for_month_max <- for_month %>%
  filter(ANNUAL > mean(ANNUAL))
#head(for_month_max)

for_month_long_max <- for_month_max  %>% 
  pivot_longer(cols = JAN:DEC, names_to = "Month", values_to = "Value")

#head(for_month_long_max)

ggplot(for_month_long_max,aes(x=Month, y= Value)) +
  geom_bar(stat = "identity") +
  facet_wrap(~SUBDIVISION) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))
```