Ringkasan dan tinjauan

Unsupervised Learning di R

Hank Roark

Senior Data Scientist at Boeing

Penutup studi kasus

Proses analisis data lengkap dengan pembelajaran tanpa pengawas
Pendekatan kreatif untuk pemodelan
Siap menghadapi masalah dunia nyata

Jenis pengelompokan

k-means vs dendrogram

Reduksi dimensi

proyeksi PCA

Seleksi model

# Initialize total within sum of squares error: wss
wss <- 0

# Look over 1 to 15 possible clusters
for (i in 1:15) {
  # Fit the model: km.out
  km.out <- kmeans(pokemon, centers = i, nstart = 20, iter.max = 50)
  # Save the within cluster sum of squares
  wss[i] <- km.out$tot.withinss
}

# Produce a scree plot
plot(1:15, wss, type = "b", 
     xlab = "Number of Clusters", 
     ylab = "Within groups sum of squares")

Menafsirkan hasil PCA

biplot dan screeplot

Pentingnya penskalaan data

membandingkan feature importance yang diskalakan dan tidak

Tinjauan kursus

pr.iris <- prcomp(x = iris[-5],
                  scale = FALSE,
                  center = TRUE)
summary(pr.iris)

Importance of components:
                          PC1     PC2    PC3     PC4
Standard deviation     2.0563 0.49262 0.2797 0.15439
Proportion of Variance 0.9246 0.05307 0.0171 0.00521
Cumulative Proportion  0.9246 0.97769 0.9948 1.00000

Dendrogram

dendrogram

Kelebihan dan kekurangan tiap algoritme

hasil pengelompokan yang berbeda

Tinjauan kursus

# Repeat for components 1 and 3
plot(wisc.pr$x[, c(1, 3)], col = (diagnosis + 1), 
     xlab = "PC1", ylab = "PC3")

komponen utama

Asah keterampilan Anda!

Unsupervised Learning di R