def init_rois(self, n_components=100, show=False):
Ain, Cin, center = greedyROI2d(self.Y,
nr=n_components,
gSig=[2, 2],
gSiz=[7, 7],
use_median=False)
Cn = np.mean(self.Y, axis=-1)
if show:
pl1 = pl.imshow(Cn, interpolation='none')
pl.colorbar()
pl.scatter(x=center[:, 1], y=center[:, 0], c='m', s=40)
pl.axis((-0.5, self.Y.shape[1] - 0.5, -0.5, self.Y.shape[0] - 0.5))
pl.gca().invert_yaxis()
active_pixels = np.squeeze(np.nonzero(np.sum(Ain, axis=1)))
Yr = np.reshape(self.Y,
(self.Y.shape[0] * self.Y.shape[1], self.Y.shape[2]),
order='F')
P = arpfit(Yr, p=2, pixels=active_pixels)
Y_res = Yr - np.dot(Ain, Cin)
model = ProjectedGradientNMF(n_components=1,
init='random',
random_state=0)
model.fit(np.maximum(Y_res, 0))
fin = model.components_.squeeze()
self.Yr, self.Cin, self.fin, self.Ain, self.P, self.Cn = Yr, Cin, fin, Ain, P, Cn
def matdecomp(imregion, method):
"""Compute matrix decomposition
Parameters
----------
imregion : 2D array
The image region data
method : str
Options for method ('eigen', 'NMF')
"""
if method == 'eigen':
## columns are eigen vectors
e_vals, e_vecs = LA.eig(imregion)
return e_vecs
if method == 'NMF':
model = ProjectedGradientNMF(n_components=2, init='random',random_state=0)
model.fit(imregion)
comp = model.components_
err = model.reconstruction_err_
return comp
class NMF(method.Method): def __init__(self, params): self.params = params self.dec = ProjectedGradientNMF(**params) def __str__(self): return "Non-Negative matrix factorization by Projected Gradient (NMF)" def train(self, data): """ Train the NMF on the withened data :param data: whitened data, ready to use """ self.dec.fit(data) def encode(self, data): """ Encodes the ready to use data :returns: encoded data with dimension n_components """ return self.dec.transform(data) def decode(self, components): """ Decode the data to return whitened reconstructed data :returns: reconstructed data """ return self.dec.inverse_transform(components)
def _nmf(X, K):
nmf = ProjectedGradientNMF(n_components=K, max_iter=1000)
nmf.fit(X)
B = nmf.components_
A = np.dot(X, np.linalg.pinv(B))
return (A, B)
class SparseApproxSpectrumNonNegative(SparseApproxSpectrum):
"""Non-negative sparse dictionary learning from 2D spectrogram patches
initialization:
patch_size=(12,12) - size of time-frequency 2D patches in spectrogram units (freq,time)
max_samples=1000000 - if num audio patches exceeds this threshold, randomly sample spectrum
"""
def __init__(self, patch_size=(12, 12), max_samples=1000000):
self.patch_size = patch_size
self.max_samples = max_samples
self.D = None
self.data = None
self.components = None
self.zscore = False
self.log_amplitude = False
def extract_codes(self,
X,
n_components=16,
log_amplitude=True,
**nmf_args):
"""Given a spectrogram, learn a dictionary of 2D patch atoms from spectrogram data
inputs:
X - spectrogram data (frequency x time)
n_components - how many components to extract [16]
log_amplitude - weather to apply log amplitude scaling log(1+X)
**nmf_args - keyword arguments for ProjectedGradientNMF(...) [None]
outputs:
self.data - 2D patches of input spectrogram
self.D.components_ - dictionary of 2D NMF components
"""
zscore = False
self._extract_data_patches(X, zscore, log_amplitude)
self.n_components = n_components
nmf_args.setdefault('sparseness', 'components')
nmf_args.setdefault('init', 'nndsvd')
nmf_args.setdefault('beta', 0.5)
print("NMF...")
self.model = ProjectedGradientNMF(n_components=self.n_components,
**nmf_args)
self.model.fit(self.data)
self.D = self.model
def reconstruct_spectrum(self, w=None, randomize=False):
"reconstruct by fitting current NMF 2D dictionary to self.data"
if w is None:
self.w = self.model.transform(self.data)
w = self.w
return SparseApproxSpectrum.reconstruct_spectrum(self,
w=w,
randomize=randomize)
def fit(self, trainSamples, trainTargets):
self.dataModel = MemeryDataModel(trainSamples, trainTargets)
#print 'train user:' + str(self.dataModel.getUsersNum())
V = self.dataModel.getData()
model = ProjectedGradientNMF(n_components=self.factors, max_iter=1000, nls_max_iter=1000)
self.pu = model.fit_transform(V)
self.qi = model.fit(V).components_.transpose()
def fit(self, trainSamples, trainTargets):
self.dataModel = MemeryDataModel(trainSamples, trainTargets)
#print 'train user:' + str(self.dataModel.getUsersNum())
V = self.dataModel.getData()
model = ProjectedGradientNMF(n_components=self.factors,
max_iter=1000,
nls_max_iter=1000)
self.pu = model.fit_transform(V)
self.qi = model.fit(V).components_.transpose()
class SparseApproxSpectrumNonNegative(SparseApproxSpectrum):
"""Non-negative sparse dictionary learning from 2D spectrogram patches
initialization:
patch_size=(12,12) - size of time-frequency 2D patches in spectrogram units (freq,time)
max_samples=1000000 - if num audio patches exceeds this threshold, randomly sample spectrum
"""
def __init__(self, patch_size=(12,12), max_samples=1000000):
self.patch_size = patch_size
self.max_samples = max_samples
self.D = None
self.data = None
self.components = None
self.zscore=False
self.log_amplitude=False
def extract_codes(self, X, n_components=16, log_amplitude=True, **nmf_args):
"""Given a spectrogram, learn a dictionary of 2D patch atoms from spectrogram data
inputs:
X - spectrogram data (frequency x time)
n_components - how many components to extract [16]
log_amplitude - weather to apply log amplitude scaling log(1+X)
**nmf_args - keyword arguments for ProjectedGradientNMF(...) [None]
outputs:
self.data - 2D patches of input spectrogram
self.D.components_ - dictionary of 2D NMF components
"""
zscore=False
self._extract_data_patches(X, zscore, log_amplitude)
self.n_components=n_components
nmf_args.setdefault('sparseness','components')
nmf_args.setdefault('init','nndsvd')
nmf_args.setdefault('beta',0.5)
print "NMF..."
self.model = ProjectedGradientNMF(n_components=self.n_components, **nmf_args)
self.model.fit(self.data)
self.D = self.model
def reconstruct_spectrum(self, w=None, randomize=False):
"reconstruct by fitting current NMF 2D dictionary to self.data"
if w is None:
self.w = self.model.transform(self.data)
w = self.w
return SparseApproxSpectrum.reconstruct_spectrum(self, w=w, randomize=randomize)
def recommend(matrix_3filled, matrix_raw, user, numOfNeighbors=5):
# The following 3 lines uses Scikit-learn. For more information, refer to the documentation link in README.
model = ProjectedGradientNMF(n_components=2, init='random', random_state=0)
model.fit(matrix_3filled)
# transformed matrix is the result of non-negative matrix factorization, and we will use this for the recommendations
transformed = np.dot(model.fit_transform(matrix_3filled), model.components_)
neighbors=[]
# Calculate distances from the current user to every other users.
distances = np.sum((transformed-transformed[user])**2, axis=1)
# Find nearest neighbors.
for x in xrange(numOfNeighbors):
distances[np.argmin(distances)] = sys.float_info.max
neighbors.append(np.argmin(distances))
# Get an average for nearest neighbors. average is a vector containing the average rating for each humor.
average=[0.0]*transformed.shape[1]
for x in xrange(numOfNeighbors):
average += transformed[neighbors[x]]
average = average/numOfNeighbors
# Find the unrated items for current users.
unratedItems=[]
for x in xrange(np.shape(matrix_raw)[1]):
if matrix_raw[user][x] == 0:
unratedItems.append(x)
# If there are no unrated items, just return an item with max average rating.
if len(unratedItems) is 0:
item = np.argmax(average)
return item
# Else, return an unrated item with max average rating.
else:
maxAverage = 0
item = np.argmax(average)
for x in xrange(len(unratedItems)):
if average[unratedItems[x]] > maxAverage:
maxAverage = average[unratedItems[x]]
item = unratedItems[x]
return item
def matrixFactorization(inmatrix, p_components=False): from sklearn.decomposition import PCA from sklearn.decomposition import ProjectedGradientNMF import pdb if p_components: p_comp = p_components else: pca = PCA(n_components=inmatrix.shape[1]) pca.fit(inmatrix) explained_variance = pca.explained_variance_ratio_.cumsum() explained_variance = explained_variance[explained_variance <= .9] p_comp = len(explained_variance) model = ProjectedGradientNMF(n_components=p_comp, init='nndsvd', beta=1, sparseness=None) #pdb.set_trace() model.fit(inmatrix) return model
def init_rois(self, n_components=100, show=False):
Ain,Cin,center = greedyROI2d(self.Y, nr=n_components, gSig=[2,2], gSiz=[7,7], use_median=False)
Cn = np.mean(self.Y, axis=-1)
if show:
pl1 = pl.imshow(Cn,interpolation='none')
pl.colorbar()
pl.scatter(x=center[:,1], y=center[:,0], c='m', s=40)
pl.axis((-0.5,self.Y.shape[1]-0.5,-0.5,self.Y.shape[0]-0.5))
pl.gca().invert_yaxis()
active_pixels = np.squeeze(np.nonzero(np.sum(Ain,axis=1)))
Yr = np.reshape(self.Y,(self.Y.shape[0]*self.Y.shape[1],self.Y.shape[2]),order='F')
P = arpfit(Yr, p=2, pixels=active_pixels)
Y_res = Yr - np.dot(Ain,Cin)
model = ProjectedGradientNMF(n_components=1, init='random', random_state=0)
model.fit(np.maximum(Y_res,0))
fin = model.components_.squeeze()
self.Yr,self.Cin,self.fin,self.Ain,self.P,self.Cn = Yr,Cin,fin,Ain,P,Cn
class NMFSpectrum(SparseApproxSpectrum):
def __init__(self, **kwargs):
SparseApproxSpectrum.__init__(self,**kwargs)
def extract_codes(self, X, **kwargs):
self.standardize=False
self._extract_data_patches(X)
kwargs.setdefault('sparseness','components')
kwargs.setdefault('init','nndsvd')
kwargs.setdefault('beta',0.5)
print "NMF..."
self.model = ProjectedGradientNMF(n_components=self.n_components, **kwargs)
self.model.fit(self.data)
self.D = self.model
return self
def reconstruct_spectrum(self, w=None, randomize=False):
if w is None:
self.w = self.model.transform(self.data)
w = self.w
return SparseApproxSpectrum.reconstruct_spectrum(self, w=w, randomize=randomize)
def decomposition(V, W, H, n_components, solver='mu', update_H=True):
if solver != 'project':
W, H, _ = non_negative_factorization(V,
W=W,
H=H,
n_components=n_components,
update_H=update_H,
max_iter=1000,
solver=solver)
#regularization='transformation', l1_ratio=0.1)
else:
model = ProjectedGradientNMF(n_components=n_components,
init='random',
random_state=0,
sparseness='data',
beta=0,
max_iter=100000)
model.fit(V)
H = model.components_
W = model.fit_transform(V)
return W, H
class NMFSpectrum(SparseApproxSpectrum):
def __init__(self, **kwargs):
SparseApproxSpectrum.__init__(self,**kwargs)
def extract_codes(self, X, **kwargs):
self.standardize=False
self._extract_data_patches(X)
kwargs.setdefault('sparseness','components')
kwargs.setdefault('init','nndsvd')
kwargs.setdefault('beta',0.5)
print("NMF...")
self.model = ProjectedGradientNMF(n_components=self.n_components, **kwargs)
self.model.fit(self.data)
self.D = self.model
return self
def reconstruct_spectrum(self, w=None, randomize=False):
if w is None:
self.w = self.model.transform(self.data)
w = self.w
return SparseApproxSpectrum.reconstruct_spectrum(self, w=w, randomize=randomize)
def _nmf_fixed_component(self, i, X):
"""
Uses sklearn to make the non negative factorization
input: i, number of clusters for this NMF instance
author: Arthur Desjardins
"""
model = ProjectedGradientNMF(n_components=i, init='nndsvd')
model.fit(X)
# H-matrix (clusters x words)
H = model.components_
# W-matrix (documents x clusters)
W = model.transform(X)
# word matrix
words = open(attributFile).read().split()
# processing extremely basic cluster bush
most_relevant_words = np.argmax(H, axis=1)
docs_per_cluster = [0]*i
for tweet in W:
most_relevant_cluster = np.argmax(tweet)
docs_per_cluster[most_relevant_cluster] += 1
clusters = dict(((words[most_relevant_words[i]], docs_per_cluster[i])
for i in range(0, i)))
return clusters
def _nonNegativeFactorization(self):
"""
Uses sklearn to make the non negative factorization
"""
print 'Loading data..'
X = np.asmatrix(np.loadtxt(dataFile))
print 'Data loaded. Making model..'
model = ProjectedGradientNMF(init='nndsvd')
print 'Fitting model..'
model.fit(X)
print 'Model fit'
print 'Error rate is', model.reconstruction_err_
# H-matrix
outFile1 = open(factoredHMatrix, 'w')
np.savetxt(outFile1, model.components_, fmt='%i')
outFile1.close
# W-matrix
outFile2 = open(factoredWMatrix, 'w')
np.savetxt(outFile2, model.transform(X), fmt='%i')
outFile2.close
def perform_nmf(X, w_dir):
# factorize composition into components
print "Performing NMF..."
n_com = 48
model = ProjectedGradientNMF(n_components=n_com,
sparseness='data',
beta=1,
eta=0.9,
tol=0.000001,
max_iter=2000,
nls_max_iter=5000,
random_state=None)
model.fit(X)
print model.reconstruction_err_
nmf_components = model.components_
print "done."
# visualize Base Rules
# nmf_components = project_data(nmf_components)
f_name = w_dir + "base_rules_48.png"
visualize_base_rules(nmf_components, n_com, f_name)
return model
def train_model(self):
print 'begin'
RATE_MATRIX = np.zeros((9238, 7973))
for line in self.train.values:
print line
uid = int(float(line[1]))
iid = int(float(line[2]))
RATE_MATRIX[uid][iid] = int(float(line[3]))
V = spr.csr_matrix(RATE_MATRIX)
model = ProjectedGradientNMF(n_components=self.n_features, max_iter=1000, nls_max_iter=10000)
self.pu = model.fit_transform(V)
self.qi = model.fit(V).components_.transpose()
print model.reconstruction_err_
self.ValidateF1()
t = pd.DataFrame(np.array(self.pu))
t.to_csv('50pu')
t = pd.DataFrame(np.array(self.qi))
t.to_csv('50qi')
print("model generation over")
Ain,Cin,center = greedyROI2d(Y, nr = nr, gSig = [4,4], gSiz = [9,9]) t_elGREEDY = time()-t1 #%% arpfit active_pixels = np.squeeze(np.nonzero(np.sum(Ain,axis=1))) Yr = np.reshape(Y,(d1*d2,T),order='F') p = 2; P = arpfit(Yr,p=2,pixels = active_pixels) #%% nmf Y_res = Yr - np.dot(Ain,Cin) model = ProjectedGradientNMF(n_components=1, init='random', random_state=0) model.fit(np.maximum(Y_res,0)) fin = model.components_.squeeze() #%% update spatial components t1 = time() A,b = update_spatial_components(Yr, Cin, fin, Ain, d1=d1, d2=d2, sn = P['sn']) t_elSPATIAL = time() - t1 #%% t1 = time() C,f,Y_res,Pnew = update_temporal_components(Yr,A,b,Cin,fin,ITER=2) t_elTEMPORAL1 = time() - t1 #%% solving using spgl1 for deconvolution
import numpy as np
X = np.array([[1, 1], [2, 1], [3, 1.2], [4, 1], [5, 0.8], [6, 1]])
from sklearn.decomposition import ProjectedGradientNMF
model = ProjectedGradientNMF(n_components=10, init='random', random_state=0)
model.fit(X)
print model.components_
U = X.dot(model.components_.T)
print U
print U.dot(model.components_)
model.reconstruction_err_
model = ProjectedGradientNMF(
n_components=2, sparseness='components', init='random', random_state=0)
model.fit(X)
ProjectedGradientNMF(beta=1, eta=0.1, init='random', max_iter=200,
n_components=2, nls_max_iter=2000, random_state=0,
sparseness='components', tol=0.0001)
model.components_
model.reconstruction_err_
import numpy as np X = np.array([[1,1,2,3], [2, 1,4,5], [3, 2,4,5], [4, 1,2,1], [5, 4,3,1], [6, 1,4,3]]) from sklearn.decomposition import ProjectedGradientNMF model = ProjectedGradientNMF(n_components=2, init='random', random_state=0) print model.fit(X) #ProjectedGradientNMF(beta=1, eta=0.1, init='random', max_iter=200, # n_components=2, nls_max_iter=2000, random_state=0, sparseness=None, # tol=0.0001) print model.components_ #array([[ 0.77032744, 0.11118662], # [ 0.38526873, 0.38228063]]) print model.reconstruction_err_ #0.00746... W = model.fit_transform(X); H = model.components_; print 'w: ' + str(W) print 'h: ' + str(H) model = ProjectedGradientNMF(n_components=2, sparseness='components', init='random', random_state=0) print model.fit(X) #ProjectedGradientNMF(beta=1, eta=0.1, init='random', max_iter=200, # n_components=2, nls_max_iter=2000, random_state=0, # sparseness='components', tol=0.0001)
def select_features_nmf(train_X, train_y, test_X, k):
selector = ProjectedGradientNMF(n_components=k, init='nndsvd', random_state=42)
selector.fit(train_X)
train_X = selector.transform(train_X)
test_X = selector.transform(test_X)
return train_X, test_X
def driver_movie_data_test_sklearn(train_filename,test_filename,k):
(A,movie_ids,user_ids,m_count,u_count) = read_data(train_filename)
# Do nnmf
#(U1,V1) = hack_nmf_iter(A,k,.07,16*A.nnz)
model = ProjectedGradientNMF(n_components=k)
model.fit(A)
V1 = model.components_
U1 = model.transform(A)
print A.shape
print U1.shape
print V1.shape
# Read test data
(A,movie_ids,user_ids,m_count,u_count) = read_data(test_filename,movie_ids,user_ids,m_count,u_count,discard=True)
(error,del_U,del_V,random_pairs) = evaluate_gradients(A,U1,V1,.07,16*A.nnz,hard=True)
reverse_user = inverse_map(user_ids)
reverse_movie = inverse_map(movie_ids)
# Test on Ratings!
outfile = open("test.sklearn.predictions","w")
print ("Doing %d test ratings" % A.nnz)
(n,m) = A.shape
for row in xrange(n):
for row_col_index in xrange(A.indptr[row],A.indptr[row+1]):
col = A.indices[row_col_index]
elt = A.data[row_col_index]
print >> outfile, "%s,%s,%0.5f" % (reverse_movie[row],reverse_user[col], nd.dot(U1[row,:],V1[:,col]))
# Test on completely random pairs
outfile = open("test.sklearn.rndpairs.predictions","w")
for n_pairs in xrange(1000):
row = r.randint(0,n-1)
col = r.randint(0,m)
print >> outfile, "%s,%s,%0.5f" % (reverse_movie[row],reverse_user[col], nd.dot(U1[row,:],V1[:,col]))
# Test on difficult distribution that ephasizes non-rated pairs where movies and users
# are chosen based on rating count.
outfile = open("test.sklearn.hard.rndpairs.predictions","w")
for n_pairs in xrange(1000):
i = r.randint(0,A.nnz -1)
row = find_index(A.indptr,i)
j = r.randint(0,A.nnz -1)
col = A.indices[j]
if (row > A.shape[0]-1):
print row, A.shape, "what is going on"
continue
if (col > A.shape[1]-1):
print col, A.shape, "what is going on"
continue
#print "shape,row,col", A.shape,row,col
# if (A[row][col] > 0):
# continue
print >> outfile, "%s,%s,%0.5f" % (reverse_movie[row],reverse_user[col], nd.dot(U1[row,:],V1[:,col]))
print ("test rsme", math.sqrt(error))
for i in xrange(k):
print ("Factor:", i)
print_movie_factor(U1,reverse_movie, i)
return(U1,V1,reverse_movie,reverse_user)
####THEIRS- not needed
# Example data matrix X
###MINE
X = DataFrame(matrix)
X_imputed = X.copy()
X = pa.DataFrame(matrix)# DataFrame(toy_vals, index = range(nrows), columns = range(ncols))
###use some way to mask only a few vals.... thst too either 0 or 1
msk = (X.values + np.random.randn(*X.shape) - X.values) < 0.8
X_imputed.values[~msk] = 0
##THEIRS
# Hiding values to test imputation
# Initializing model
nmf_model = ProjectedGradientNMF(n_components = 600, init='nndsvda', random_state=0,max_iter=300, eta=0.01, alpha = 0.01)
nmf_model.fit(X_imputed.values)
# iterate model
#while nmf_model.reconstruction_err_**2 > 10:
#nmf_model = NMF( n_components = 600, init='nndsvda', random_state=0,max_iter=300, eta=0.01, alpha = 0.01)
W = nmf_model.fit_transform(X_imputed.values)
X_imputed.values[~msk] = W.dot(nmf_model.components_)[~msk]
print nmf_model.reconstruction_err_
H = nmf_model.components_
rHat = np.dot(W,H)
np.savetxt("rHat.txt" ,rHat)
def driver_movie_data_test_sklearn(train_filename, test_filename, k):
(A, movie_ids, user_ids, m_count, u_count) = read_data(train_filename)
# Do nnmf
#(U1,V1) = hack_nmf_iter(A,k,.07,16*A.nnz)
model = ProjectedGradientNMF(n_components=k)
model.fit(A)
V1 = model.components_
U1 = model.transform(A)
print A.shape
print U1.shape
print V1.shape
# Read test data
(A, movie_ids, user_ids, m_count, u_count) = read_data(test_filename,
movie_ids,
user_ids,
m_count,
u_count,
discard=True)
(error, del_U, del_V, random_pairs) = evaluate_gradients(A,
U1,
V1,
.07,
16 * A.nnz,
hard=True)
reverse_user = inverse_map(user_ids)
reverse_movie = inverse_map(movie_ids)
# Test on Ratings!
outfile = open("test.sklearn.predictions", "w")
print("Doing %d test ratings" % A.nnz)
(n, m) = A.shape
for row in xrange(n):
for row_col_index in xrange(A.indptr[row], A.indptr[row + 1]):
col = A.indices[row_col_index]
elt = A.data[row_col_index]
print >> outfile, "%s,%s,%0.5f" % (reverse_movie[row],
reverse_user[col],
nd.dot(U1[row, :], V1[:, col]))
# Test on completely random pairs
outfile = open("test.sklearn.rndpairs.predictions", "w")
for n_pairs in xrange(1000):
row = r.randint(0, n - 1)
col = r.randint(0, m)
print >> outfile, "%s,%s,%0.5f" % (reverse_movie[row],
reverse_user[col],
nd.dot(U1[row, :], V1[:, col]))
# Test on difficult distribution that ephasizes non-rated pairs where movies and users
# are chosen based on rating count.
outfile = open("test.sklearn.hard.rndpairs.predictions", "w")
for n_pairs in xrange(1000):
i = r.randint(0, A.nnz - 1)
row = find_index(A.indptr, i)
j = r.randint(0, A.nnz - 1)
col = A.indices[j]
if (row > A.shape[0] - 1):
print row, A.shape, "what is going on"
continue
if (col > A.shape[1] - 1):
print col, A.shape, "what is going on"
continue
#print "shape,row,col", A.shape,row,col
# if (A[row][col] > 0):
# continue
print >> outfile, "%s,%s,%0.5f" % (reverse_movie[row],
reverse_user[col],
nd.dot(U1[row, :], V1[:, col]))
print("test rsme", math.sqrt(error))
for i in xrange(k):
print("Factor:", i)
print_movie_factor(U1, reverse_movie, i)
return (U1, V1, reverse_movie, reverse_user)
if ans != "y":
exit()
from sklearn.cluster import MiniBatchKMeans, KMeans
km = MiniBatchKMeans(n_clusters=k,
init='k-means++',
n_init=1,
init_size=1000,
batch_size=1000,
verbose=1)
km2 = KMeans(n_clusters=k, init='k-means++', verbose=1)
y2 = km2.fit_transform(X)
topics5 = [[(km.cluster_centers_[l][i], feature_names[i])
for i in np.argsort(-np.abs(km.cluster_centers_[l]))[:10]]
for l in range(k)]
print topics5
### NMF #######################
ans = raw_input("Start NMF with Scikit ? ")
if ans != "y":
exit()
from sklearn.decomposition import ProjectedGradientNMF
# BEWARE : THIS IS COMPUTATIONNALY INTENSIVE
nmf = ProjectedGradientNMF(n_components=k, max_iter=10, nls_max_iter=100)
nmf.fit(X)
topics6 = [[(nmf.components_[l][i], feature_names[i])
for i in np.argsort(-np.abs(nmf.components_[l]))[:10]]
for l in range(k)]
import numpy as np
X = np.array([[1, 1], [2, 1], [3, 1.2], [4, 1], [5, 0.8], [6, 1]])
from sklearn.decomposition import ProjectedGradientNMF
model = ProjectedGradientNMF(n_components=10, init='random', random_state=0)
model.fit(X)
print model.components_
U = X.dot(model.components_.T)
print U
print U.dot(model.components_)
model.reconstruction_err_
model = ProjectedGradientNMF(n_components=2,
sparseness='components',
init='random',
random_state=0)
model.fit(X)
ProjectedGradientNMF(beta=1,
eta=0.1,
init='random',
max_iter=200,
n_components=2,
nls_max_iter=2000,
random_state=0,
sparseness='components',
tol=0.0001)
model.components_
model.reconstruction_err_
plt1 = plt.imshow(Cn,interpolation='none') plt.colorbar() plt.scatter(x=center[:,1], y=center[:,0], c='m', s=40) plt.axis((-0.5,d2-0.5,-0.5,d1-0.5)) plt.gca().invert_yaxis() #%% crd = plot_contours(coo_matrix(Ain[:,::-1]),Cn,thr=0.9) #%% active_pixels = np.squeeze(np.nonzero(np.sum(Ain,axis=1))) Yr = np.reshape(Y,(d1*d2,T),order='F') p = 2; P = arpfit(Yr,p=1,pixels = active_pixels) Y_res = Yr - np.dot(Ain,Cin) model = ProjectedGradientNMF(n_components=1, init='random', random_state=0) model.fit(np.maximum(Y_res,0)) fin = model.components_.squeeze() #%% t1 = time() A,b,Cin = update_spatial_components(Yr, Cin, fin, Ain, d1=d1, d2=d2, sn = P['sn'],dist=2,max_size=8,min_size=3) t_elSPATIAL = time() - t1 #%% crd = plot_contours(A,Cn2,thr=0.9,cmap=pl.cm.gray) #%% t1 = time() C,f,Y_res,Pnew = update_temporal_components(Yr,A,b,Cin,fin,ITER=2,deconv_method = 'spgl1') t_elTEMPORAL2 = time() - t1 #%% t1 = time() A_sp=A.tocsc();
genreMat4 = np.vstack(genreMat4)
print genreMat4
index = filmsbygenre['Action']
E = y[index, :]
### K-Means ###################
ans = raw_input("Start K-Means with Scikit ? ")
if ans != "y":
exit()
from sklearn.cluster import MiniBatchKMeans, KMeans
km = MiniBatchKMeans(n_clusters=k, init='k-means++', n_init=1, init_size=1000, batch_size=1000, verbose=1)
km2 = KMeans(n_clusters = k, init='k-means++', verbose=1)
y2 = km2.fit_transform(X)
topics5 = [[(km.cluster_centers_[l][i], feature_names[i]) for i in np.argsort(-np.abs(km.cluster_centers_[l]))[:10]] for l in range(k)]
print topics5
### NMF #######################
ans = raw_input("Start NMF with Scikit ? ")
if ans != "y":
exit()
from sklearn.decomposition import ProjectedGradientNMF
# BEWARE : THIS IS COMPUTATIONNALY INTENSIVE
nmf = ProjectedGradientNMF(n_components=k, max_iter = 10, nls_max_iter=100)
nmf.fit(X)
topics6 = [[(nmf.components_[l][i], feature_names[i]) for i in np.argsort(-np.abs(nmf.components_[l]))[:10]] for l in range(k)]
