# Multiple Linear Regression

# Importing the dataset
dataset = read.csv('worldcricket.csv')

dataset=dataset[2:7]
# Encoding categorical data
# Taking care of missing data
dataset$WC.in.India.W.L = ifelse(is.na(dataset$WC.in.India.W.L),
                     ave(dataset$WC.in.India.W.L, FUN = function(x) mean(x, na.rm = TRUE)),
                     dataset$WC.in.India.W.L)


# Splitting the dataset into the Training set and Test set
# install.packages('caTools')
library(caTools)
set.seed(123)
split = sample.split(dataset$Last.18.Match.Perform.btw.WQ, SplitRatio = 0.8)
training_set = subset(dataset, split == TRUE)
test_set = subset(dataset, split == FALSE)

# Feature Scaling
#training_set = scale(training_set)
#test_set = scale(test_set)

# Fitting Multiple Linear Regression to the Training set
regressor = lm(formula = Last.18.Match.Perform.btw.WQ ~ .,
               data = training_set)
summary(regressor)

# Predicting the Test set results
y_pred = predict(regressor, newdata = test_set)
x_pred = predict(regressor, newdata = training_set)
A_pred= c(x_pred,y_pred)


#Display Bar-chart
barplot(A_pred, xlab = "X-axis",
        ylab = "Y-axis", main ="Bar-Chart")

#Display Bar chart with prediction
df=read.csv('worldcup_prediction.csv')
#install.packages('plotly')
library(plotly)
library(ggplot2)

#Color Bar Chart 
colormap <- setNames(object = c("lightblue", "yellow", "darkgreen","red","blue","orange","black","green","greenyellow","darkblue"),
                     nm = df$Team)
Win_pred=df$Prediction
plot_ly(data = df,
        x = ~Team,
        y = ~Win_pred,
        type = "bar",
        color = ~Team,
        colors = colormap)