def _get_neighbors(self, sample_i):
neighbors = []
for _sample_i, _sample in enumerate(self.X):
if _sample_i != sample_i and euclidean_distance(
self.X[sample_i], _sample) < self.eps:
neighbors.append(_sample_i)
return np.array(neighbors)
def _get_neighbors(self, sample_i):
neighbors = []
for _sample_i, _sample in enumerate(self.X):
if _sample_i != sample_i and euclidean_distance(
self.X[sample_i], _sample) < self.eps:
neighbors.append(_sample_i)
return np.array(neighbors)
def _calculate_cost(self, X, clusters, medoids):
cost = 0
# For each cluster
for i, cluster in enumerate(clusters):
medoid = medoids[i]
for sample_i in cluster:
# Add distance between sample and medoid as cost
cost += euclidean_distance(X[sample_i], medoid)
return cost
def _closest_medoid(self, sample, medoids):
closest_i = None
closest_distance = float("inf")
for i, medoid in enumerate(medoids):
distance = euclidean_distance(sample, medoid)
if distance < closest_distance:
closest_i = i
closest_distance = distance
return closest_i
def _calculate_cost(self, X, clusters, medoids):
cost = 0
# For each cluster
for i, cluster in enumerate(clusters):
medoid = medoids[i]
for sample_i in cluster:
# Add distance between sample and medoid as cost
cost += euclidean_distance(X[sample_i], medoid)
return cost
def _closest_medoid(self, sample, medoids):
closest_i = None
closest_distance = float("inf")
for i, medoid in enumerate(medoids):
distance = euclidean_distance(sample, medoid)
if distance < closest_distance:
closest_i = i
closest_distance = distance
return closest_i
def _closest_centroid(self, sample, centroids):
""" Return the index of the closest centroid to the sample """
closest_i = None
closest_distance = float("inf")
for i, centroid in enumerate(centroids):
distance = euclidean_distance(sample, centroid)
if distance < closest_distance:
closest_i = i
closest_distance = distance
return closest_i
def _get_neighbors(self, sample_i):
""" Return a list of indexes of neighboring samples
A sample_2 is considered a neighbor of sample_1 if the distance between
them is smaller than epsilon """
neighbors = []
for _sample_i, _sample in enumerate(self.X):
if _sample_i != sample_i and euclidean_distance(
self.X[sample_i], _sample) < self.eps:
neighbors.append(_sample_i)
return np.array(neighbors)
def predict(self, X_test, X_train, y_train):
classes = np.unique(y_train)
y_pred = []
# Determine the class of each sample
for test_sample in X_test:
neighbors = []
# Calculate the distance form each observed sample to the
# sample we wish to predict
for j, observed_sample in enumerate(X_train):
distance = euclidean_distance(test_sample, observed_sample)
label = y_train[j]
# Add neighbor information
neighbors.append([distance, label])
neighbors = np.array(neighbors)
# Sort the list of observed samples from lowest to highest distance
# and select the k first
k_nearest_neighbors = neighbors[neighbors[:, 0].argsort()][:self.k]
# Do a majority vote among the k neighbors and set prediction as the
# class receing the most votes
label = self._majority_vote(k_nearest_neighbors, classes)
y_pred.append(label)
return np.array(y_pred)
def predict(self, X_test, X_train, y_train):
classes = np.unique(y_train)
y_pred = []
# Determine the class of each sample
for test_sample in X_test:
neighbors = []
# Calculate the distance form each observed sample to the
# sample we wish to predict
for j, observed_sample in enumerate(X_train):
distance = euclidean_distance(test_sample, observed_sample)
label = y_train[j]
# Add neighbor information
neighbors.append([distance, label])
neighbors = np.array(neighbors)
# Sort the list of observed samples from lowest to highest distance
# and select the k first
k_nearest_neighbors = neighbors[neighbors[:, 0].argsort()][:self.k]
# Do a majority vote among the k neighbors and set prediction as the
# class receing the most votes
label = self._majority_vote(k_nearest_neighbors, classes)
y_pred.append(label)
return np.array(y_pred)