---
title: "WOAD 45 Years Data analysis"
author: "Viviane Schneider"
output:  
  flexdashboard::flex_dashboard:
    orientation: columns
    vertical_layout: fill
    social: menu
    source_code: embed
---

```{r setup,  include=FALSE, cache=TRUE}




library(rattle)
library(caret)
library(rpart)
library(rpart.plot)
library(corrplot)
library(randomForest)
library(RColorBrewer)
library(dplyr)
library(plotly)
library(ggplot2)
library(tidyr)
library(magrittr)
library(plotrix)
library(rgl)
library(lubridate)
library(ggplot2)
library(GGally)
library(corrplot)
library(corrgram)
library(ppcor)
library(readr)
library(ggvis)
library(gganimate)
library(gifski)
library(av)
library(magick)
library(viridis)
library(hrbrthemes)
library(caret)


```





```{r}
setwd("~/Regression Models")
library(readr)
Cleaning_completo_woad <- read_delim("Cleaning_completo_woad.CSV", 
    ";", escape_double = FALSE, col_types = cols(
    DamageCost_million = col_number(),
    DrillDepth_km = col_number(), 
    WaterDepth_m = col_number(),
    WindSpeed_m_s= col_number(), 
    FatalitiesCrew = col_number(),
    Fatalities3rd_Party = col_number(),
    InjuriesCrew = col_number(),
    Injuries3rd_Party = col_number(),
    Accident_Date = col_date(format = "%m/%d/%Y")),
    trim_ws = TRUE)

panel.hist <- function(x, ...)
{
  usr <- par("usr"); on.exit(par(usr))
  par(usr = c(usr[1:2], 0, 1.5) )
  h <- hist(x, plot = FALSE)
  breaks <- h$breaks; nB <- length(breaks)
  y <- h$counts; y <- y/max(y)
  rect(breaks[-nB], 0, breaks[-1], y, col = "cyan", ...)
}

# 1.2 by Melina de Souza Leite 
panel.lm <- function (x, y, col = par("col"), bg = NA, pch = par("pch"), 
                      cex = 1, col.line="red") {
  points(x, y, pch = pch, col = col, bg = bg, cex = cex)
  ok <- is.finite(x) & is.finite(y)
  if (any(ok)) {
    abline(lm(y[ok]~x[ok]), col = col.line)
  }
}

# 1.3 help(pairs) by Melina de Souza Leite 
panel.cor <- function(x, y, digits = 2, prefix = "", cex.cor, ...)
{
  usr <- par("usr"); on.exit(par(usr))
  par(usr = c(0, 1, 0, 1))
  r <- abs(cor(x, y))
  txt <- format(c(r, 0.123456789), digits = digits)[1]
  txt <- paste0(prefix, txt)
  if(missing(cex.cor)) cex.cor <- 0.8/strwidth(txt)
  text(0.5, 0.5, txt, cex = cex.cor * r)
}


# Transform vector into a data frame with frequency of levels and proportion
.Unianalysis = function (x) {
    y <- as.data.frame(as.table(table(x)))
    y <- mutate(y, percentual = prop.table(y$Freq) *100)#Proportion
    y <- arrange(y, desc(y$Freq))
return(y)
}

.BarPlot <- function (z) {
      z %>% 
    ggplot( aes(x=x, y=Freq)) +
    geom_bar(stat="identity", fill="#f68060", alpha=.6, width=.4) +
    coord_flip() +
    xlab("") +
    theme_bw()

}

```



```{r}

## Tidying data

trainVariable <- Cleaning_completo_woad %>%
              mutate(HumanCost = (FatalitiesCrew * 10) + (Fatalities3rd_Party * 10) + (InjuriesCrew * 3) +  (Injuries3rd_Party * 3)) %>%
              mutate(Year = year(Accident_Date)) %>% 
              mutate(Month =  month(Accident_Date))

by_Event_Function <-
        trainVariable %>% 
        group_by(MainEvent, Function,TypeofUnit, Damage,SpillType, AccidentCategory,Year, Month) %>%
        summarise(How_Many = n(),
                  Owner = n_distinct(Owner),
                  FatalitiesCrew = sum(FatalitiesCrew),
                  Fatalities3rd_Party = sum(Fatalities3rd_Party),
                  InjuriesCrew = sum(InjuriesCrew),
                  Injuries3rd_Party = sum(Injuries3rd_Party),
                  DamageCost_million= sum(DamageCost_million), 
                  DrillDepth_km = mean(DrillDepth_km), 
                  WaterDepth_m = mean(WaterDepth_m),
                  WindSpeed_m_s= sum(WindSpeed_m_s),
                  HumanCost = sum(HumanCost)) %>%
       mutate(Mean_HumanCost = (FatalitiesCrew + Fatalities3rd_Party + InjuriesCrew + Injuries3rd_Party)/How_Many) %>%
       arrange(desc(How_Many))
   

write.csv2(by_Event_Function, file = "by_Event_Function.CSV")
write.csv2(trainVariable, file = "trainVariable.CSV")



damage <- cbind(by_Event_Function$Damage,
                by_Event_Function$How_Many,
                by_Event_Function$HumanCost,
                by_Event_Function$Mean_HumanCost,
                by_Event_Function$DamageCost_million)

colnames(damage) <- cbind("Damage Degree","Cccurrences", "Total Human Cost", "Mean Human Cost", "Cost in Milion")

damage <- as.data.frame(na.omit(damage))


OverView <- apply(Cleaning_completo_woad, 2, .Unianalysis)

OverView2 <- sapply(OverView, distinct)



by_Year <- trainVariable %>%
          group_by(Year) %>%
          summarise(Freq = n(),
           Owner = n_distinct(Owner),
           FatalitiesCrew = sum(FatalitiesCrew),
           Fatalities3rd_Party = sum(Fatalities3rd_Party),
           InjuriesCrew = sum(InjuriesCrew),
           Injuries3rd_Party = sum(Injuries3rd_Party),
           DamageCost_million= sum(DamageCost_million), 
           HumanCost = sum(HumanCost),   
           WindSpeed_m_s= mean(WindSpeed_m_s)) 
  
  
by_HumanCost <- trainVariable %>%
          filter(HumanCost > 0) %>%
          group_by(HumanCost, AccidentCategory, Damage) %>%
          summarise(Freq = n(),
           Owner = n_distinct(Owner),
           FatalitiesCrew = sum(FatalitiesCrew),
           Fatalities3rd_Party = sum(Fatalities3rd_Party),
           InjuriesCrew = sum(InjuriesCrew),
           Injuries3rd_Party = sum(Injuries3rd_Party),
           DamageCost_million= sum(DamageCost_million), 
           WindSpeed_m_s= mean(WindSpeed_m_s))  %>% 
           filter(Freq > 20)
           

by_Year<- by_Year %>% 
  mutate_all(replace_na, 0)

by_Event_Function <- by_Event_Function %>% 
  mutate_all(replace_na, 0)



```

Accident Category Human and Economic 
=======================================================================

Column {data-width=400}
-----------------------------------------------------------------------

###  What is the human and economic cost per platform unit type and Accident Category? 


```{r}


# FUNÇÃO Grafico do documento

library(plotly)
library(gapminder)
p <- trainVariable %>%
  plot_ly(
    x = ~HumanCost, 
    y = ~TypeofUnit, 
    size = ~DamageCost_million, 
    color = ~as.factor(AccidentCategory), 
    frame = ~DamageCost_million, 
    text = ~DamageCost_million
    , 
    hoverinfo = "text",
    type = 'scatter',
    mode = 'markers'
  ) %>%
  layout(
    xaxis = list(
      type = "log"
    )
  )
p




```




Column {data-width=300}
-----------------------------------------------------------------------


### What is the human and economic cost per platform Main Event and Accident Category?

```{r}

p <- trainVariable %>%
  plot_ly(
    x = ~HumanCost, 
    y = ~MainEvent, 
    size = ~DamageCost_million, 
    color = ~as.factor(AccidentCategory), 
    frame = ~DamageCost_million, 
    text = ~DamageCost_million
    , 
    hoverinfo = "text",
    type = 'scatter',
    mode = 'markers'
  ) %>%
  layout(
    xaxis = list(
      type = "log"
    )
  )
p

```



### What is the human and economic cost per platform function and Accident Category?

```{r}

p <- trainVariable %>%
  plot_ly(
    x = ~HumanCost, 
    y = ~Function, 
    size = ~DamageCost_million, 
    color = ~as.factor(AccidentCategory), 
    frame = ~DamageCost_million, 
    text = ~DamageCost_million
    , 
    hoverinfo = "text",
    type = 'scatter',
    mode = 'markers'
  ) %>%
  layout(
    xaxis = list(
      type = "log"
    )
  )
p

```


Decision Tree
=======================================================================

Column {data-width=600}
-----------------------------------------------------------------------

### Formula: HumanCost ~ WindSpeed_m_s + WaterDepth_m + DrillDepth_km, method = "poisson", data = with outliers

```{r}
library(rpart)
library(rpart.plot)

arvore <- rpart(HumanCost ~ WindSpeed_m_s + WaterDepth_m + DrillDepth_km, method = "poisson", data = trainVariable)

rpart.plot(arvore)


```




Column {data-width=300}
-----------------------------------------------------------------------


### Formula: formula = HumanCost ~ WindSpeed_m_s, data = no outliers

```{r}
outliers <- boxplot(trainVariable$HumanCost, plot=FALSE)$out
no_outliers <- trainVariable 
no_outliers <-no_outliers[which(no_outliers$HumanCost %in% outliers),]

ver <- lm(formula = HumanCost ~ WindSpeed_m_s + as.factor(MainEvent) +  - 1, data = no_outliers)
arvore <- rpart(HumanCost ~ WindSpeed_m_s, data = no_outliers)
rpart.plot(arvore)

```

### Formula: HumanCost ~ WindSpeed_m_s + WaterDepth_m + DrillDepth_km + as.factor(AccidentCategory), data = with outliers


```{r}
arvore_V_E <- rpart(HumanCost ~ WindSpeed_m_s + WaterDepth_m + DrillDepth_km + as.factor(AccidentCategory) , data = trainVariable)
rpart.plot(arvore_V_E)

```




Damage Human and Economic Cost 
=======================================================================

Column {data-width=400}
-----------------------------------------------------------------------

###  Which major operation causes the most cost in accidents in percentiles? 

```{r}
ggplot(trainVariable, aes(fill=Damage, y=MainOperation, x=DamageCost_million)) + 
    geom_bar(position="fill", stat="identity") + ggtitle("Main Operation per cost in millions and type of damage") + xlab("Percentil Cost") + ylab("Main Operation")


```

Column {data-width=400}
-----------------------------------------------------------------------

###  Which Function causes the most cost in accidents in percentiles? 

```{r}

ggplot(trainVariable, aes(fill=Damage, y=Function, x=DamageCost_million)) + geom_bar(position="fill", stat="identity") + ggtitle("Funtions per Damage cost in millions") + xlab("Percentil") + ylab("Platform function")
```

###  Which Main events causes the most cost in accidents in percentiles? 

```{r}

ggplot(trainVariable, aes(fill=Damage, y=MainEvent, x=DamageCost_million)) + geom_bar(position="fill", stat="identity") + ggtitle("Main Events per cost in million") + xlab("Percentil") + ylab("Main Events")
```

Heatmap
=======================================================================


Column {data-width=600}
-----------------------------------------------------------------------

###  Heatmap by Main Operation and Damage Cost in million

```{r}
library("lattice")
 
# Dummy data
data <- trainVariable %>% 
         filter(DamageCost_million > 40)
data <- table(data$MainOperation, data$DamageCost_million)


# plot it flipping the axis
levelplot( t(data[c(nrow(data):1) , ]),
           col.regions=heat.colors(100), pretty = TRUE, ylab = "Main Operation",
            xlab = "Damage Cost per million",) 

```

Column {data-width=600}
-----------------------------------------------------------------------

###  Heatmap by Main Events and Damage Cost in million


```{r}
library("lattice")
 
# Dummy data
data <- trainVariable %>% 
         filter(DamageCost_million > 40)
data <- table(data$MainEvent, data$DamageCost_million)


# plot it flipping the axis
levelplot( t(data[c(nrow(data):1) , ]),
           col.regions=heat.colors(100), pretty = TRUE, ylab = "Main Operation",
            xlab = "Damage Cost per million",) 

```