I'm building my own 1-NN clasifier in python cause I need max speed in certain operations for testing it, because I want to use it in genetic algorithm and every milisecond its important for speed.
I'm trying to implement a leave one out test inside of my KNN class with numpy, but I obtain about 50% of success with this test. I try the scikit learn knn with the same leave one out and returns about 97% of success.
This is my KNN class:
class KNN(object):
"""Documentation for KNK-clasifier"""
def __init__(self):
super(KNN, self).__init__()
# self.args = args
def fit(self, entrenamiento, clases):
self.entrenamiento = np.asarray(entrenamiento)
self.n_examples = len(self.entrenamiento)
self.n_features = len(self.entrenamiento[1])
self.clases = np.asarray(clases)
self.createDistenceMatrix()
def createDistenceMatrix(self):
self.distances = np.zeros([len(self.entrenamiento),
len(self.entrenamiento),
len(self.entrenamiento[1])])
for i in range(self.n_examples):
for j in range(self.n_examples):
if i is not j:
self.distances[i][j] = self.distance(self.entrenamiento[i],
self.entrenamiento[j])
else:
self.distances[i][j] = np.full(len(self.entrenamiento[1]),
10000.0)
def distance(self, x, y):
return (x-y)*(x-y)
def predict(self, test, pesos=None):
dist = 100000
class_index = 0
for i in range(self.n_examples):
aux = self.distance(self.entrenamiento[i], test)
if pesos is not None:
aux = pesos*aux
if aux < dist:
dist = aux
class_index = i
return self.clases[class_index]
def leave_one_out(self, pesos=None):
# DONE: solo tengo que buscar el minimo de cada columna
dist = np.zeros(self.n_examples)
aciertos = 0
for i in range(self.n_examples):
for j in range(self.n_examples):
if pesos is not None:
dist[i] = np.linalg.norm(
np.multiply(self.distances[i][j], pesos))
else:
dist[i] = np.linalg.norm(self.distances[i][j])
if self.clases[i] == self.clases[np.argmin(dist)]:
aciertos = aciertos + 1
return 100*(aciertos/self.n_examples)
where create createDistanceMatrix precalculate all the possible x,y distances for all the features and save it to a vector. This vector will be multiplied for a weitght vector. This vector represent a feature weights learning problem that I'm trying to solve. I passed two days trying to find where the mistake is but I cand find, but my clasifier doesn't give me a decent percent of good classification in leave one out.
For sklearn knn this is the leave one out that I'm testing:
aciertos = 0
knn = neighbors.KNeighborsClassifier(n_neighbors=1)
start = time.clock()
for i in range(len(train)):
knn.fit(train[1:], cls[1:])
if knn.predict(train[0])[0] == cls[0]:
aciertos = aciertos + 1
train[0], train[-1] = train[-1], train[0]
cls[0], cls[-1] = cls[-1], cls[0]
end = time.clock()
print(str(end - start) + " segundos")
print(str(100*(aciertos/len(train))))
this same code with my own clasifier returns similar percent of succes.
