def preprocess(x_train: np.ndarray, y_train: np.ndarray,
x_test: np.ndarray) -> Tuple[np.ndarray, np.ndarray]:
"""
Prepocesses data.
:param x_train: the training data.
:param y_train: the training labels.
:param x_test: the test data.
:return: Preprocessed x_train and x_test.
"""
logger.log('Prepocessing...')
# Scale data.
logger.log('\tScaling data with params:')
scaler = MinMaxScaler()
logger.log('\t{}'.format(scaler.get_params()))
x_train = scaler.fit_transform(x_train)
x_test = scaler.transform(x_test)
# Apply LLE.
logger.log('\tApplying LLE with params:')
embedding = LocallyLinearEmbedding(n_neighbors=100,
n_jobs=-1,
random_state=0)
embedding_params = embedding.get_params()
logger.log('\t' + str(embedding_params))
x_train = embedding.fit_transform(x_train)
x_test = embedding.transform(x_test)
# Plot the graph embedding result.
if PLOTTING_MODE != 'none':
plotter.subfolder = 'graphs/LLE'
plotter.filename = 'embedding'
plotter.xlabel = 'first feature'
plotter.ylabel = 'second feature'
plotter.title = 'LLE'
plotter.scatter(x_train,
y_train,
class_labels=helpers.datasets.get_gene_name)
return x_train, x_test
#Use iso_model.transform(x_test) to fit the isomap from the training set onto the test set
'''
-------------------------------------------------------------------------------
-------------------------------Modified LLE------------------------------------
-------------------------------------------------------------------------------
'''
#Apply modified LLE, keeping n components < the number of original features
#method = 'standard' for LLE, 'hessian' for HELLE, or 'modified' for modified LLE
mlle_model = LocallyLinearEmbedding(n_neighbors=5,
n_components=2,
method='modified',
random_state=seed)
mlle_model.fit_transform(x_std)
print(mlle_model.get_params())
mlle_dim = mlle_model.embedding_
print(mlle_dim.shape) #There should be 2 latent variables represented
#Plot first 2 extracted features and the observation class
plt.figure(figsize=(10, 5))
plt.xlabel('Latent Variable 1 (explains most variance)')
plt.ylabel('Latent Variable 2 (explains second most variance)')
plt.title('Modified LLE 2-Dimension Plot with Observation Class, 5 neighbors')
plt.scatter(mlle_dim[:, 0], mlle_dim[:, 1], c=y)
plt.colorbar()
plt.show()
#Try a different number of neighbors
mlle_model = LocallyLinearEmbedding(n_neighbors=15,
n_components=2,
