class PCAImputer:
def __init__(self, n_dimension):
self._q = n_dimension
def fit_transform(self,
data,
method='eig',
probabilistic=False,
n_iteration=100):
"""fitting a PCA to the original data by iterativly filling the missing entries
with value generated from PCA. Each missing entries are initialized with the
row mean."""
self._data = data.copy()
self._missing = np.isnan(data)
self._observed = ~self._missing
self._pca = PPCA(n_dimension=self._q)
row_defau = np.zeros(self._data.shape[0])
row_means = np.repeat(np.nanmean(self._data, axis=1, out=row_defau).reshape(-1, 1), \
self._data.shape[1], axis=1)
self._data[self._missing] = row_means[self._missing]
for i in range(n_iteration):
self._pca.fit(self._data, method=method)
self._data[self._missing] = self._pca.inverse_transform(self._pca.transform(self._data, \
probabilistic), probabilistic)[self._missing]
return self._data
plt.show()
print('\n\n\n\n**TEST CALCULATING LIKELIHOOD**')
ppca1 = PPCA(n_dimension=2)
loglikelihoods = ppca1.fit(data, method='EM', keep_loglikes=True)
plt.plot(loglikelihoods)
plt.show()
print('\n\n\n\n**TEST DIMENSION REDUCTION AND RECOVERING**')
plt.matshow(data)
print('\n\noriginal data')
plt.show()
ppca3 = PPCA(n_dimension=2)
ppca3.fit(data, method='EM')
plt.matshow( ppca3.inverse_transform( ppca3.transform(data) ) )
print('\n\nrecovered data: 2-component')
plt.show()
ppca4 = PPCA(n_dimension=2)
ppca4.fit(data, batchsize=16, n_iteration=2000, method='EM')
plt.matshow( ppca4.inverse_transform( ppca4.transform(data) ) )
print('\n\nrecovered data: 2-component (mini-batch)')
plt.show()
ppca5 = PPCA(n_dimension=63)
ppca5.fit(data, method='EM')
plt.matshow( ppca5.inverse_transform( ppca5.transform(data) ) )
print('\n\nrecovered data: 63-component')
plt.show()