R Code

# Importing the dataset dataset = read.csv('Ads_CTR_Optimisation.csv') # Implementing Thompson Sampling N = 10000 d = 10 ads_selected = integer(0) numbers_of_rewards_1 = integer(d) numbers_of_rewards_0 = integer(d) total_reward = 0 for (n in 1:N) {   ad = 0   max_random = 0   for (i in 1:d) {     random_beta = rbeta(n = 1,                         shape1 = numbers_of_rewards_1[i] + 1,                         shape2 = numbers_of_rewards_0[i] + 1)     if (random_beta > max_random) {       max_random = random_beta       ad = i     }   }   ads_selected = append(ads_selected, ad)   reward = dataset[n, ad]   if (reward == 1) {     numbers_of_rewards_1[ad] = numbers_of_rewards_1[ad] + 1   } else {     numbers_of_rewards_0[ad] = numbers_of_rewards_0[ad] + 1   }   total_reward = total_reward + reward } # Visualising the results hist(ads_selected,      col = 'blue',      main = 'Histogram of ads selections',      xlab = 'Ads&

# Upper Confidence Bound # Importing the dataset dataset = read.csv('Ads_CTR_Optimisation.csv') # Implementing UCB N = 10000 d = 10 ads_selected = integer(0) #d is vector has only zero's numbers_of_selections = integer(d) sums_of_rewards = integer(d) total_reward = 0 for (n in 1:N) {   ad = 0   max_upper_bound = 0   for (i in 1:d) {     if (numbers_of_selections[i] > 0) {       average_reward = sums_of_rewards[i] / numbers_of_selections[i]       #upper confidence limit       delta_i = sqrt(3/2 * log(n) / numbers_of_selections[i])       upper_bound = average_reward + delta_i     } else {         upper_bound = 1e400     }     if (upper_bound > max_upper_bound) {       max_upper_bound = upper_bound       ad = i     }   }   ads_selected = append(ads_selected, ad)   numbers_of_selections[ad] = numbers_of_selections[ad] + 1   reward = dataset[n, ad]   sums_of_rewards[ad] = sums_of_rewards[ad] + reward   total_reward = total_reward + rewar

# Data Preprocessing # install.packages('arules') library(arules) dataset = read.csv('Market_Basket_Optimisation.csv') dataset = read.transactions('Market_Basket_Optimisation.csv', sep = ',', rm.duplicates = TRUE) Output distribution of transactions with duplicates: 1 5 summary(dataset) transactions as itemMatrix in sparse format with  7501 rows (elements/itemsets/transactions) and  119 columns (items) and a density of 0.03288973 most frequent items: mineral water          eggs     spaghetti  french fries     chocolate       (Other)          1788          1348          1306          1282          1229         22405 element (itemset/transaction) length distribution: sizes    1    2    3    4    5    6    7    8    9   10   11   12   13   14   15   16   18 1754 1358 1044  816  667  493  391  324  259  139  102   67   40   22   17    4    1   19   20    2    1    Min. 1st Qu.  Median    Mean 3rd Qu. 

# Data Preprocessing # install.packages('arules') library(arules) dataset = read.csv('Market_Basket_Optimisation.csv', header = FALSE) #sparce matrix dataset = read.transactions('Market_Basket_Optimisation.csv', sep = ',', rm.duplicates = TRUE) distribution of transactions with duplicates: 1  5  summary(dataset) transactions as itemMatrix in sparse format with  7501 rows (elements/itemsets/transactions) and  119 columns (items) and a density of 0.03288973  most frequent items: mineral water          eggs     spaghetti  french fries     chocolate       (Other)           1788          1348          1306          1282          1229         22405  element (itemset/transaction) length distribution: sizes    1    2    3    4    5    6    7    8    9   10   11   12   13   14   15   16   18   19   20  1754 1358 1044  816  667  493  391  324  259  139  102   67   40   22   17    4    1    2    1 

# Importing the dataset dataset = read.csv('Mall_Customers.csv') dataset = dataset[4:5] # Splitting the dataset into the Training set and Test set # install.packages('caTools') # library(caTools) # set.seed(123) # split = sample.split(dataset$DependentVariable, SplitRatio = 0.8) # training_set = subset(dataset, split == TRUE) # test_set = subset(dataset, split == FALSE) # Feature Scaling # training_set = scale(training_set) # test_set = scale(test_set) # Using the elbow method to find the optimal number of clusters set.seed(6) wcss = vector() for (i in 1:10) wcss[i] = sum(kmeans(dataset, i)$withinss) plot(1:10,       wcss,       type = 'b',       main = paste('The Elbow Method'),       xlab = 'Number of clusters',       ylab = 'WCSS') # Fitting K-Means to the dataset set.seed(29) kmeans = kmeans(x = dataset, centers = 5) y_kmeans = kmeans$cluster # Visualising the clusters library(cluster) clusplo

# 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$Purchased, SplitRatio = 0.75) training_set = subset(dataset, split == TRUE) test_set = subset(dataset, split == FALSE) # Feature Scaling training_set[-3] = scale(training_set[-3]) test_set[-3] = scale(test_set[-3]) # Fitting Random Forest Classification to the Training set # install.packages('randomForest') library(randomForest) set.seed(123) classifier = randomForest(x = training_set[-3],                           y = training_set$Purchased,                           ntree = 500) # Predicting the Test set results y_pred = predict(classifier, newdata = test