R Notebook

iris = read.csv("iris.csv")
iris

ggplot(data = iris, aes(x= variety, y = sepal.length, fill = variety)) + 
  geom_boxplot() +
  labs(title = "This plot is created using ggplot",
       x = "Class",
       y = "Sepal Length",
       caption = "Source: Iris dataset")

ggplot(data = iris, aes(x= variety, y = sepal.length, fill = variety)) + 
  geom_violin() +
  labs(title = "This plot is created using ggplot",
       x = "Class",
       y = "Sepal Length",
       caption = "Source: Iris dataset")

summary(iris)

  sepal.length    sepal.width     petal.length    petal.width      variety         
 Min.   :4.300   Min.   :2.000   Min.   :1.000   Min.   :0.100   Length:150        
 1st Qu.:5.100   1st Qu.:2.800   1st Qu.:1.600   1st Qu.:0.300   Class :character  
 Median :5.800   Median :3.000   Median :4.350   Median :1.300   Mode  :character  
 Mean   :5.843   Mean   :3.057   Mean   :3.758   Mean   :1.199                     
 3rd Qu.:6.400   3rd Qu.:3.300   3rd Qu.:5.100   3rd Qu.:1.800                     
 Max.   :7.900   Max.   :4.400   Max.   :6.900   Max.   :2.500                     

cor(iris$sepal.length, iris$sepal.width)

[1] -0.1175698

cor(iris$sepal.length, iris$sepal.length)

[1] 1

cor_matrix = cor(iris[ ,1:4])
cor_matrix

             sepal.length sepal.width petal.length petal.width
sepal.length    1.0000000  -0.1175698    0.8717538   0.8179411
sepal.width    -0.1175698   1.0000000   -0.4284401  -0.3661259
petal.length    0.8717538  -0.4284401    1.0000000   0.9628654
petal.width     0.8179411  -0.3661259    0.9628654   1.0000000

library(ggcorrplot)
ggcorrplot(cor_matrix)

ggcorrplot(cor_matrix, type = "lower")

ggcorrplot(cor_matrix, type = "upper")

ggcorrplot(cor_matrix, 
           type = "lower",
           colors = c("purple", "white", "red"))

ggcorrplot(cor_matrix, 
           type = "lower",
           colors = c("purple", "white", "red"),
           lab = TRUE)

library(GGally)
ggpairs(iris, aes(colour = variety))

Interactive plots

library(plotly)

fig = iris %>%
  plot_ly(y = ~sepal.length, type = 'violin')
  
fig

library(plotly)

plot_ly(iris, y = ~sepal.length, type = 'violin')

NA
NA
NA

plot_ly(iris, y = ~sepal.length, type = 'box')

plot_ly(iris, x = ~sepal.length, type = 'histogram')

plot_ly(iris, x = ~variety, y = ~ sepal.length, type = 'box')

Principal Component Analysis (PCA)

# dimension = axis = features
library(stats)

iris_pca = prcomp(iris[ , -5], scale = TRUE, center = TRUE)
iris_pca

Standard deviations (1, .., p=4):
[1] 1.7083611 0.9560494 0.3830886 0.1439265

Rotation (n x k) = (4 x 4):
                    PC1         PC2        PC3        PC4
sepal.length  0.5210659 -0.37741762  0.7195664  0.2612863
sepal.width  -0.2693474 -0.92329566 -0.2443818 -0.1235096
petal.length  0.5804131 -0.02449161 -0.1421264 -0.8014492
petal.width   0.5648565 -0.06694199 -0.6342727  0.5235971

summary(iris_pca)

Importance of components:
                          PC1    PC2     PC3     PC4
Standard deviation     1.7084 0.9560 0.38309 0.14393
Proportion of Variance 0.7296 0.2285 0.03669 0.00518
Cumulative Proportion  0.7296 0.9581 0.99482 1.00000

pc_12 = data.frame(iris_pca$x[ , 1:2])
head(pc_12)

pc_12_class = cbind(pc_12, variety = iris$variety)
pc_12_class

ggplot(pc_12_class, aes(PC1, PC2, color=variety)) + 
  geom_point() + 
  theme_minimal()

library(factoextra)
fviz_eig(iris_pca, addlabels = TRUE)

fviz_pca_var(iris_pca,
             col.var = "contrib")

library("corrplot")
var = get_pca_var(iris_pca)
corrplot(var$cos2)

fviz_pca_ind(iris_pca,
             geom.ind = "point",
             col.ind = iris$variety,
             addEllipses = TRUE)

Regression

library(datasets)
data(iris)

lm_model = lm(Sepal.Length ~ Petal.Length, data = iris)
summary(lm_model)

Call:
lm(formula = Sepal.Length ~ Petal.Length, data = iris)

Residuals:
     Min       1Q   Median       3Q      Max 
-1.24675 -0.29657 -0.01515  0.27676  1.00269 

Coefficients:
             Estimate Std. Error t value Pr(>|t|)    
(Intercept)   4.30660    0.07839   54.94   <2e-16 ***
Petal.Length  0.40892    0.01889   21.65   <2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.4071 on 148 degrees of freedom
Multiple R-squared:   0.76, Adjusted R-squared:  0.7583 
F-statistic: 468.6 on 1 and 148 DF,  p-value: < 2.2e-16

x = iris$Petal.Length
y = iris$Sepal.Length

plot(x, y)

pred = predict(lm_model)
ix = sort(x, index.return = T)$ix # sort and return index not the acrtual values

plot(x, y)
lines(x[ix], pred[ix])

NA
NA

ggplot(iris, aes(x = Petal.Length, y=Sepal.Length)) + 
  geom_point() +
  geom_smooth(method = "lm", level = 0.95)

ggplot(iris, aes(x = Petal.Length, y=Sepal.Length, color = Species)) + 
  geom_point() +
  geom_smooth(method = "lm", level = 0.95)

ggplot(iris, aes(x = Petal.Length, y=Sepal.Length, color = Species)) + 
  geom_point() +
  geom_smooth(method = "lm", formula = y~poly(x, 2), level = 0.95)

Clustering

kmeans_result = kmeans(iris[ , 1:4], centers = 3 )
kmeans_result

K-means clustering with 3 clusters of sizes 50, 38, 62

Cluster means:
  Sepal.Length Sepal.Width Petal.Length Petal.Width
1     5.006000    3.428000     1.462000    0.246000
2     6.850000    3.073684     5.742105    2.071053
3     5.901613    2.748387     4.393548    1.433871

Clustering vector:
  [1] 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 3 3 2 3 3 3
 [57] 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 2 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 2 3 2 2 2 2 3 2 2 2 2 2
[113] 2 3 3 2 2 2 2 3 2 3 2 3 2 2 3 3 2 2 2 2 2 3 2 2 2 2 3 2 2 2 3 2 2 2 3 2 2 3

Within cluster sum of squares by cluster:
[1] 15.15100 23.87947 39.82097
 (between_SS / total_SS =  88.4 %)

Available components:

[1] "cluster"      "centers"      "totss"        "withinss"     "tot.withinss" "betweenss"    "size"        
[8] "iter"         "ifault"      

library(cluster)
clusplot(iris, kmeans_result$cluster)

Classification

library(lattice)
library(e1071)
library(caret)

train_ix = createDataPartition(iris$Species, p = 0.8, list = FALSE)
train_data = iris[train_ix, ]
test_data = iris[-train_ix, ]

train_data

test_data

svm_model = svm(Species ~ Sepal.Length+Sepal.Width+Petal.Length, data = train_data, kernel = "linear")

test_data[24, ]

predict(svm_model, newdata = test_data[24, -5])

      120 
virginica 
Levels: setosa versicolor virginica

predictions = predict(svm_model, newdata = test_data)
conf_max = confusionMatrix(predictions, test_data$Species)
conf_max

Confusion Matrix and Statistics

            Reference
Prediction   setosa versicolor virginica
  setosa         10          0         0
  versicolor      0         10         1
  virginica       0          0         9

Overall Statistics
                                          
               Accuracy : 0.9667          
                 95% CI : (0.8278, 0.9992)
    No Information Rate : 0.3333          
    P-Value [Acc > NIR] : 2.963e-13       
                                          
                  Kappa : 0.95            
                                          
 Mcnemar's Test P-Value : NA              

Statistics by Class:

                     Class: setosa Class: versicolor Class: virginica
Sensitivity                 1.0000            1.0000           0.9000
Specificity                 1.0000            0.9500           1.0000
Pos Pred Value              1.0000            0.9091           1.0000
Neg Pred Value              1.0000            1.0000           0.9524
Prevalence                  0.3333            0.3333           0.3333
Detection Rate              0.3333            0.3333           0.3000
Detection Prevalence        0.3333            0.3667           0.3000
Balanced Accuracy           1.0000            0.9750           0.9500

cm = as.data.frame(conf_max$table)

ggplot(cm, aes(Prediction, Reference, fill = Freq)) + 
  geom_tile() +
  geom_text(aes(label = Freq)) + 
  scale_fill_gradient(low="white", high="skyblue")