def transform(self, sdf_list):
features = np.array([])
for file_ in sdf_list:
#print file_
converted = SDF(file_)
my_windows = np.array(converted.make_windows(self.W, self.S, self.FILTER))
prediction = histogramize(self.Kmeans_model.predict(my_windows), self.NUM_CLUSTERS)
if len(features) == 0:
features = prediction
else:
features = np.concatenate((features,prediction), axis=0)
return features
def transform(self, sdf_list):
features = np.array([])
for file_ in sdf_list:
#print file_
converted = SDF(file_)
my_windows = np.array(
converted.make_windows(self.W, self.S, self.FILTER))
prediction = histogramize(self.Kmeans_model.predict(my_windows),
self.NUM_CLUSTERS)
if len(features) == 0:
features = prediction
else:
features = np.concatenate((features, prediction), axis=0)
return features
def fit(self, sdf_list, K):
windows = np.array([])
for file_ in sdf_list:
#print file_
converted = SDF(file_)
my_windows = np.array(converted.make_windows(self.W, self.S, self.FILTER))
#print my_windows.shape
if len(windows) == 0:
windows = my_windows
else:
windows = np.concatenate((windows,my_windows), axis=0)
self.Kmeans_model = KMeans(n_clusters=K)
self.Kmeans_model.fit(windows)
#print windows.shape, 'win shape'
self.cluster_centers = self.Kmeans_model.cluster_centers_
return self.transform(sdf_list) #used to map back for sdf_class purposes/LSH pipeline
def fit(self, sdf_list, K):
windows = np.array([])
for file_ in sdf_list:
#print file_
converted = SDF(file_)
my_windows = np.array(
converted.make_windows(self.W, self.S, self.FILTER))
#print my_windows.shape
if len(windows) == 0:
windows = my_windows
else:
windows = np.concatenate((windows, my_windows), axis=0)
self.Kmeans_model = KMeans(n_clusters=K)
self.Kmeans_model.fit(windows)
#print windows.shape, 'win shape'
self.cluster_centers = self.Kmeans_model.cluster_centers_
return self.transform(
sdf_list) #used to map back for sdf_class purposes/LSH pipeline
