Book a Demo!
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
debakarr
GitHub Repository: debakarr/machinelearning
 Path: blob/master/Part 9 - Dimension Reduction/Principal Component Analysis/pca.R
1336 views
1
# PCA

2


3
# Importing the dataset

4
dataset = read.csv('Wine.csv')

5


6
# Splitting the dataset into the Training set and Test set

7
# install.packages('caTools')

8
library(caTools)

9
set.seed(123)

10
split = sample.split(dataset$Customer_Segment, SplitRatio = 0.8)

11
training_set = subset(dataset, split == TRUE)

12
test_set = subset(dataset, split == FALSE)

13


14
# Feature Scaling

15
training_set[-14] = scale(training_set[-14])

16
test_set[-14] = scale(test_set[-14])

17


18
# Applying PCA

19
# install.packages('caret')

20
library(caret)

21
# install.packages('e1071')

22
library(e1071)

23
pca = preProcess(x = training_set[-14], method = 'pca', pcaComp = 2)

24
training_set = predict(pca, training_set)

25
training_set = training_set[c(2, 3, 1)]

26
test_set = predict(pca, test_set)

27
test_set = test_set[c(2, 3, 1)]

28


29
# Fitting SVM to the Training set

30
# install.packages('e1071')

31
library(e1071)

32
classifier = svm(formula = Customer_Segment ~ .,

33
                 data = training_set,

34
                 type = 'C-classification',

35
                 kernel = 'linear')

36


37
# Predicting the Test set results

38
y_pred = predict(classifier, newdata = test_set[-3])

39


40
# Making the Confusion Matrix

41
cm = table(test_set[, 3], y_pred)

42


43
# Visualising the Training set results

44
library(ElemStatLearn)

45
set = training_set

46
X1 = seq(min(set[, 1]) - 1, max(set[, 1]) + 1, by = 0.01)

47
X2 = seq(min(set[, 2]) - 1, max(set[, 2]) + 1, by = 0.01)

48
grid_set = expand.grid(X1, X2)

49
colnames(grid_set) = c('PC1', 'PC2')

50
y_grid = predict(classifier, newdata = grid_set)

51
plot(set[, -3],

52
     main = 'SVM (Training set)',

53
     xlab = 'PC1', ylab = 'PC2',

54
     xlim = range(X1), ylim = range(X2))

55
contour(X1, X2, matrix(as.numeric(y_grid), length(X1), length(X2)), add = TRUE)

56
points(grid_set, pch = '.', col = ifelse(y_grid == 2, 'deepskyblue', ifelse(y_grid == 1, 'springgreen3', 'tomato')))

57
points(set, pch = 21, bg = ifelse(set[, 3] == 2, 'blue3', ifelse(set[, 3] == 1, 'green4', 'red3')))

58


59
# Visualising the Test set results

60
library(ElemStatLearn)

61
set = test_set

62
X1 = seq(min(set[, 1]) - 1, max(set[, 1]) + 1, by = 0.01)

63
X2 = seq(min(set[, 2]) - 1, max(set[, 2]) + 1, by = 0.01)

64
grid_set = expand.grid(X1, X2)

65
colnames(grid_set) = c('PC1', 'PC2')

66
y_grid = predict(classifier, newdata = grid_set)

67
plot(set[, -3], main = 'SVM (Test set)',

68
     xlab = 'PC1', ylab = 'PC2',

69
     xlim = range(X1), ylim = range(X2))

70
contour(X1, X2, matrix(as.numeric(y_grid), length(X1), length(X2)), add = TRUE)

71
points(grid_set, pch = '.', col = ifelse(y_grid == 2, 'deepskyblue', ifelse(y_grid == 1, 'springgreen3', 'tomato')))

72
points(set, pch = 21, bg = ifelse(set[, 3] == 2, 'blue3', ifelse(set[, 3] == 1, 'green4', 'red3')))

73