Introduction
Principal Component Analysis (PCA) reduces dimensionality by finding principal components that explain variance.
Implementing PCA
# Using prcomp
pca <- prcomp(df_scaled)
# Summary
summary(pca)
# Print components
print(pca)
# Get scores
pca$x
Variance Explained
# Scree plot
plot(pca)
# Proportion of variance
pca$sdev^2 / sum(pca$sdev^2)
# Cumulative variance
cumsum(pca$sdev^2 / sum(pca$sdev^2))
Biplot
biplot(pca)
Using for Prediction
# Predict on new data
predict(pca, newdata = new_df_scaled)
Summary
PCA reduces dimensions while preserving variance. Choose components that explain sufficient variance.