Explain with a case study how to visualize the train and test data of a Decision Classification system in R

711 Asked by NiharikaDeshpande in Data Science , Asked on Nov 7, 2019

Answered by Niharika Deshpande

First we import and split the dataset

# Classification template

# Importing the dataset

dataset = read.csv('Social_Network_Ads.csv')

dataset = dataset[3:5]

# Encoding the target feature as factor

dataset$Purchased = factor(dataset$Purchased, levels = c(0, 1))

# Splitting the dataset into the Training set and Test set

# install.packages('caTools')

library(caTools)

set.seed(123)

split = sample.split(dataset$Purchased, SplitRatio = 0.75)

training_set = subset(dataset, split == TRUE)

test_set = subset(dataset, split == FALSE)

Now we scale, fit and predict the model

# Feature Scaling

training_set[-3] = scale(training_set[-3])

test_set[-3] = scale(test_set[-3])

# Fitting classifier to the Training set

# Create your classifier here

# Predicting the Test set results

y_pred = predict(classifier, newdata = test_set[-3])

# Making the Confusion Matrix

cm = table(test_set[, 3], y_pred)

Now we visualize the training data

library(ElemStatLearn)

set = training_set

X1 = seq(min(set[, 1]) - 1, max(set[, 1]) + 1, by = 0.01)

X2 = seq(min(set[, 2]) - 1, max(set[, 2]) + 1, by = 0.01)

grid_set = expand.grid(X1, X2)

colnames(grid_set) = c('Age', 'EstimatedSalary')

y_grid = predict(classifier, newdata = grid_set)

plot(set[, -3],

main = 'Classifier (Training set)',

xlab = 'Age', ylab = 'Estimated Salary',

xlim = range(X1), ylim = range(X2))

contour(X1, X2, matrix(as.numeric(y_grid), length(X1), length(X2)), add = TRUE)

points(grid_set, pch = '.', col = ifelse(y_grid == 1, 'springgreen3', 'tomato'))

points(set, pch = 21, bg = ifelse(set[, 3] == 1, 'green4', 'red3'))

Finally we visualize the test data

# Visualising the Test set results