class KNNDynamicsResidual:
def __init__(self, args, env_params):
# Save args
self.args, self.env_params = args, env_params
# Create the KNN model
self.knn_model = RadiusNeighborsRegressor(radius=args.neighbor_radius,
weights='uniform')
# Flag
self.is_fit = False
def fit(self, X, y):
'''
X should be the data matrix N x d, where each row is a 4D vector
consisting of object pos and gripper pos
y should be target matrix N x d, where each row is a 4D vector
consisting of next object pos and next gripper pos
'''
self.knn_model.fit(X, y)
self.is_fit = True
return self.loss(X, y)
def predict(self, X):
'''
X should be the data matrix N x d, where each row is a 4D vector
consisting of object pos and gripper pos
'''
ypred = np.zeros(X.shape)
if not self.is_fit:
# KNN model is not fit
return ypred
# Get neighbors of X
neighbors = self.knn_model.radius_neighbors(X)
# Check if any of the X doesn't have any neighbors by getting nonzero mask
neighbor_mask = [x.shape[0] != 0 for x in neighbors[1]]
# If none of X has any neighbors
if X[neighbor_mask].shape[0] == 0:
return ypred
# Else, for the X that have neighbors use the KNN prediction
ypred[neighbor_mask] = self.knn_model.predict(X[neighbor_mask])
return ypred
def get_num_neighbors(self, X):
if not self.is_fit:
return np.zeros(X.shape[0])
neighbors = self.knn_model.radius_neighbors(X)
num_neighbors = np.array([x.shape[0] for x in neighbors[1]])
return num_neighbors
def loss(self, X, y):
ypred = self.predict(X)
# Loss is just the mean distance between predictions and true targets
loss = np.linalg.norm(ypred - y, axis=1).mean()
return loss
def get_author_list_with_pruning_method(feature_list, author_list, qp, radius):
"""
feature_list - the feature list to indicate the stylometric features
author_list - the author list to indicate a paragraph is written by whom
qp - the query point, mostly represents a document
This function will return a shortened author list, which can greatly
reduce the size of training set by removing those data points too far
from the query point. Since it takes time to calculate the Hausdorff
distance, reducing the size of testing set can speed up the process
Please refer to the following link for more information
http://scikit-learn.org/stable/modules/generated/sklearn.neighbors.RadiusNeighborsRegressor.html#sklearn.neighbors.RadiusNeighborsRegressor
"""
neigh = RadiusNeighborsRegressor(radius=radius, algorithm='brute', p=2)
neigh.fit(feature_list, author_list)
return neigh.radius_neighbors(qp, return_distance=True)
