K Nearest Neighbor (KNN)

class mlpy.Knn(k, dist='se')

k-Nearest Neighbor (KNN).

Initialize the Knn class.

Input

• k - [integer] number of NN
• dist - [string] adopted distance (‘se’ = SQUARED EUCLIDEAN, ‘e’ = EUCLIDEAN)

compute(x, y)

Store x and y data.

Input

• x - [2D numpy array float] (#sample x #feature) training data
• y - [1D numpy array integer] classes
  • -1 or 1 for binary classification
  • 1, ..., nclasses for multiclass classification

Output

• 1

predict(p)

Predict knn model on a test point(s).

Input

• p - [1D or 2D numpy array float] test point(s)

Output: the predicted value(s) on success:

• -1 or 1 for binary classification
• 1, ..., nclasses for multiclass classification
• 0 on succes with non unique classification
• -2 otherwise