svd.md

Using SVD to reduce dimensions example

from sklearn import decomposition, datasets

X, y = datasets.load_iris(return_X_y=True)

svd = decomposition.TruncatedSVD(n_components=2)
svd.fit(X)
X = svd.transform(X)

• from sklearn import - import module from lib:scikit-learn
• load_iris - loads Iris dataset
• .TruncatedSVD( - creates dimensionality reduction model based on truncated SVD
• .fit( - train reduction model
• .transform( - transform original data and return reduced dimensions data

group: pca

Example:

from sklearn import decomposition, datasets

X, y = datasets.load_iris(return_X_y=True)
print('Original:', X.shape)

svd = decomposition.TruncatedSVD(n_components=2)
svd.fit(X)
X = svd.transform(X)

print('Reduced: ', X.shape)

Original: (150, 4)
Reduced:  (150, 2)