def run_factorization(self, N, S, X, Z, I, K, k, n):
# Smart initialization
rat = k / n
nans = np.isnan(rat)
scaled_rat = scale_allelic_ratios(rat)
ppca = PPCA()
ppca.fit(data=np.transpose(scaled_rat), d=K, verbose=True)
U = ppca.C
V = ppca.transform()
pickle.dump(ppca, open(self.output_root + '_model', 'wb'))
np.savetxt(self.output_root + '_temper_U.txt',
U,
fmt="%s",
delimiter='\t')
np.savetxt(self.output_root + '_temper_V.txt',
V.T,
fmt="%s",
delimiter='\t')
def remove_nan_test(self):
N = 101
k = 23
p_nan = 0.02
n_components = 3
data = np.random.random((N, k))
for n in range(N):
for _k in range(k):
if random.random() < p_nan:
data[n, _k] = np.nan
pca = PPCA()
pca.fit(data, n_components)
self.assertEqual(pca.data[np.isnan(pca.data)].shape, (0, ))
self.assertEqual(pca.C.shape, (k, n_components))
self.assertEqual(pca.transform().shape, (N, n_components))
for i in range(len(X)):
Y = np.fromstring(X[i], dtype=int, sep = ' ')
Y = np.reshape(Y,(48, 48))
E.append(Y)
X_inp = np.array(E)
#X_train = X_inp.reshape(-1,X_inp.shape[1], X_inp.shape[2],1)
X_train = X_inp.astype('float32')
print X_inp
inp_img = X_train[0,:,:]
ppca = PPCA(inp_img)
ppca.fit(d=20, verbose=False)
component_mat = ppca.transform()
E_y = component_mat.reshape(1,component_mat.shape[0],component_mat.shape[1])
for i in range(1,len(X_train)):
print i
inp_img = X_train[i,:,:]
ppca = PPCA(inp_img)
try:
ppca.fit(d=20, verbose=False)
component_mat = ppca.transform()
shape = component_mat.shape
component_mat = component_mat.reshape(1,component_mat.shape[0],component_mat.shape[1])
if shape[1] == 20:
E_y = concatenate((E_y,component_mat))
except numpy.linalg.linalg.LinAlgError:
print "Numpy Error"
SelectedImage = showImagesRandomImages(
3) #select and image randomly from MNSIT dataset
missingPercentage = 0.2 # missing rate percentage
missingImage = generateMissingFig(
SelectedImage,
missingPercentage) #inserting missing values to the original image
imputer = KNNImputer(n_neighbors=2, weights="uniform")
imputed_by_KNN = imputer.fit_transform(missingImage)
KNNImputed_RMSE = mean_squared_error(SelectedImage, imputed_by_KNN)
#plt.imshow(imputed_by_KNN, cmap='gray', vmin=0, vmax=1)
#plt.show()
imputer = MissForest()
MissForest_imputed = imputer.fit_transform(missingImage)
MissForest_RMSE = mean_squared_error(SelectedImage, MissForest_imputed)
#plt.imshow(MissForest_imputed, cmap='gray', vmin=0, vmax=1)
#plt.show()
imputer = IterativeImputer()
MICE_imputed = imputer.fit_transform(missingImage)
MICE_RMSE = mean_squared_error(SelectedImage, MICE_imputed)
#plt.imshow(MICE_imputed, cmap='gray', vmin=0, vmax=1)
#plt.show()
ppca = PPCA()
ppca.fit(data=SelectedImage, d=100, verbose=True)
PPCA_imputed = ppca.transform(missingImage)
PPCA_RMSE = mean_squared_error(SelectedImage, PPCA_imputed)
#plt.imshow(PPCA_imputed, cmap='gray', vmin=0, vmax=1)
#plt.show()
# @Date: 2020-07-07 11:22:28
# @Last Modified by: ashayaan
# @Last Modified time: 2020-07-07 12:44:33
import torch
import pandas as pd
import numpy as np
import json
from ppca import PPCA
import pickle
if __name__ == '__main__':
roberta_features = pd.read_csv('../data/roberta.csv')
roberta_features = roberta_features.set_index('idx')
mca_features = pd.read_csv('../data/mca.csv')
mca_features = mca_features.set_index('idx')
pca_features = pd.read_csv('../data/pca.csv')
pca_features = pca_features.set_index('idx')
links = pd.read_csv('../data/ml-20m/links.csv')
df = pd.concat([roberta_features, mca_features, pca_features], axis=1)
ppca = PPCA()
ppca.fit(data=df.values.astype(float),d=128,verbose=True)
print(ppca.var_exp)
transformed = ppca.transform()
films_dict = dict([(k, torch.tensor(transformed[i]).float()) for k, i in zip(df.index, range(transformed.shape[0]))])
pickle.dump(films_dict, open('../data//ml20_pca128.pkl', 'wb'))
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()