class NMFImpl():
def __init__(self, n_components=None, init=None, solver='cd', beta_loss='frobenius', tol=0.0001, max_iter=200, random_state=None, alpha=0.0, l1_ratio=0.0, verbose=0, shuffle=False):
self._hyperparams = {
'n_components': n_components,
'init': init,
'solver': solver,
'beta_loss': beta_loss,
'tol': tol,
'max_iter': max_iter,
'random_state': random_state,
'alpha': alpha,
'l1_ratio': l1_ratio,
'verbose': verbose,
'shuffle': shuffle}
def fit(self, X, y=None):
self._sklearn_model = SKLModel(**self._hyperparams)
if (y is not None):
self._sklearn_model.fit(X, y)
else:
self._sklearn_model.fit(X)
return self
def transform(self, X):
return self._sklearn_model.transform(X)
def a():
data_matrix = numpy.ones((7, 5)) * 2.5
data_matrix[0, 0] = data_matrix[0, 1] = data_matrix[0, 2] = 1
data_matrix[1, 0] = data_matrix[1, 1] = data_matrix[1, 2] = 3
data_matrix[2, 0] = data_matrix[2, 1] = data_matrix[2, 2] = 4
data_matrix[3, 0] = data_matrix[3, 1] = data_matrix[3, 2] = 5
data_matrix[4, 3] = data_matrix[4, 4] = 4
data_matrix[4, 1] = 2
data_matrix[5, 3] = data_matrix[5, 4] = 5
data_matrix[6, 3] = data_matrix[6, 4] = 2
print data_matrix
W, H = factorize(data_matrix)
print 'nimfa', numpy.dot(W, H)
rating_vector = numpy.zeros((5, 1)) * 2.5
rating_vector[0, 0] = 4
result = numpy.dot(H, rating_vector)
result = numpy.dot(numpy.transpose(H), result)
print result
svd = NMF(n_components=2);
W = svd.fit_transform(data_matrix)
H = svd.components_
print numpy.dot(W, H)
rating_vector = numpy.ones((5, 1)) * 2.5
rating_vector[0, 0] = 4
result = numpy.dot(H, rating_vector)
result = numpy.dot(numpy.transpose(H), result)
print result
print result.max()
class NMFRecommender(BaseEstimator, RegressorMixin):
def __init__(self, n_components):
self.nmf = NMF(n_components=2, init='random', random_state=0)
self.user_ids_dict = {}
self.book_isbns_dict = {}
def fit(self, X, y=None):
self.sparse_matrix = X['sparse_matrix']
self.user_ids_dict = X['user_ids_dict']
self.book_isbns_dict = X['book_isbns_dict']
self.nmf.fit(X['sparse_matrix'])
def predict(self, X, y=None):
ratings = X['ratings']
user_representations = self.nmf.transform(self.sparse_matrix)
book_representations = self.nmf.components_
estimations = []
for i in tqdm(range(len(ratings))):
estimation = np.dot(
user_representations[self.user_ids_dict[
ratings.iloc[i]['User-ID']]], book_representations)[
self.book_isbns_dict[ratings.iloc[i]['ISBN']]]
estimations.append(estimation)
return estimations
def fit_predict(self, X, y=None):
self.fit(X, y)
return self.predict(X, y)
def factorize_data_matrix(self):
self.logger.info("Going to factorize matrix")
DM_W_FILE = '../../resources/scikit_dm_W.npy'
DM_H_FILE = '../../resources/scikit_dm_H.npy'
if os.path.isfile(DM_W_FILE) and os.path.isfile(DM_H_FILE):
self.W = numpy.load(DM_W_FILE)
self.H = numpy.load(DM_H_FILE)
else:
svd = NMF(n_components=25);
self.W = svd.fit_transform(self.data_matrix)
self.H = svd.components_
self.rmse()
numpy.save(DM_W_FILE, self.W)
numpy.save(DM_H_FILE, self.H)
return self.W, self.H
def fit(self, X, y=None):
self._sklearn_model = SKLModel(**self._hyperparams)
if (y is not None):
self._sklearn_model.fit(X, y)
else:
self._sklearn_model.fit(X)
return self
def __init__(self,
n_components=None,
init=None,
solver='cd',
beta_loss='frobenius',
tol=0.0001,
max_iter=200,
random_state=None,
alpha=0.0,
l1_ratio=0.0,
verbose=0,
shuffle=False):
self._hyperparams = {
'n_components': n_components,
'init': init,
'solver': solver,
'beta_loss': beta_loss,
'tol': tol,
'max_iter': max_iter,
'random_state': random_state,
'alpha': alpha,
'l1_ratio': l1_ratio,
'verbose': verbose,
'shuffle': shuffle
}
self._wrapped_model = Op(**self._hyperparams)
def nmf(data, components):
nmf = NMF(n_components=components, init="random", random_state=0)
W = nmf.fit_transform(data)
H = nmf.components_
R = np.dot(W, H)
return W
'MDS':MDS(), 'MLPClassifier':MLPClassifier(), 'MLPRegressor':MLPRegressor(), 'MaxAbsScaler':MaxAbsScaler(), 'MeanShift':MeanShift(), 'MinCovDet':MinCovDet(), 'MinMaxScaler':MinMaxScaler(), 'MiniBatchDictionaryLearning':MiniBatchDictionaryLearning(), 'MiniBatchKMeans':MiniBatchKMeans(), 'MiniBatchSparsePCA':MiniBatchSparsePCA(), 'MultiTaskElasticNet':MultiTaskElasticNet(), 'MultiTaskElasticNetCV':MultiTaskElasticNetCV(), 'MultiTaskLasso':MultiTaskLasso(), 'MultiTaskLassoCV':MultiTaskLassoCV(), 'MultinomialNB':MultinomialNB(), 'NMF':NMF(), 'NearestCentroid':NearestCentroid(), 'NearestNeighbors':NearestNeighbors(), 'Normalizer':Normalizer(), 'NuSVC':NuSVC(), 'NuSVR':NuSVR(), 'Nystroem':Nystroem(), 'OAS':OAS(), 'OneClassSVM':OneClassSVM(), 'OrthogonalMatchingPursuit':OrthogonalMatchingPursuit(), 'OrthogonalMatchingPursuitCV':OrthogonalMatchingPursuitCV(), 'PCA':PCA(), 'PLSCanonical':PLSCanonical(), 'PLSRegression':PLSRegression(), 'PLSSVD':PLSSVD(), 'PassiveAggressiveClassifier':PassiveAggressiveClassifier(),
def __init__(self, n_components):
self.nmf = NMF(n_components=2, init='random', random_state=0)
self.user_ids_dict = {}
self.book_isbns_dict = {}
def benchmark(samples_range, features_range, rank=50, tolerance=1e-5):
timeset = defaultdict(lambda: [])
err = defaultdict(lambda: [])
for n_samples in samples_range:
for n_features in features_range:
print("%2d samples, %2d features" % (n_samples, n_features))
print('=======================')
X = np.abs(
make_low_rank_matrix(n_samples,
n_features,
effective_rank=rank,
tail_strength=0.2))
gc.collect()
print("benchmarking nndsvd-nmf: ")
tstart = time()
m = NMF(n_components=30, tol=tolerance, init='nndsvd').fit(X)
tend = time() - tstart
timeset['nndsvd-nmf'].append(tend)
err['nndsvd-nmf'].append(m.reconstruction_err_)
report(m.reconstruction_err_, tend)
gc.collect()
print("benchmarking nndsvda-nmf: ")
tstart = time()
m = NMF(n_components=30, init='nndsvda', tol=tolerance).fit(X)
tend = time() - tstart
timeset['nndsvda-nmf'].append(tend)
err['nndsvda-nmf'].append(m.reconstruction_err_)
report(m.reconstruction_err_, tend)
gc.collect()
print("benchmarking nndsvdar-nmf: ")
tstart = time()
m = NMF(n_components=30, init='nndsvdar', tol=tolerance).fit(X)
tend = time() - tstart
timeset['nndsvdar-nmf'].append(tend)
err['nndsvdar-nmf'].append(m.reconstruction_err_)
report(m.reconstruction_err_, tend)
gc.collect()
print("benchmarking random-nmf")
tstart = time()
m = NMF(n_components=30,
init='random',
max_iter=1000,
tol=tolerance).fit(X)
tend = time() - tstart
timeset['random-nmf'].append(tend)
err['random-nmf'].append(m.reconstruction_err_)
report(m.reconstruction_err_, tend)
gc.collect()
print("benchmarking alt-random-nmf")
tstart = time()
W, H = alt_nnmf(X, r=30, init='random', tol=tolerance)
tend = time() - tstart
timeset['alt-random-nmf'].append(tend)
err['alt-random-nmf'].append(np.linalg.norm(X - np.dot(W, H)))
report(norm(X - np.dot(W, H)), tend)
return timeset, err
def compute_bench(samples_range, features_range, rank=50, tolerance=1e-7):
it = 0
timeset = defaultdict(lambda: [])
err = defaultdict(lambda: [])
max_it = len(samples_range) * len(features_range)
for n_samples in samples_range:
for n_features in features_range:
it += 1
print '===================='
print 'Iteration %03d of %03d' % (it, max_it)
print '===================='
X = np.abs(
make_low_rank_matrix(n_samples,
n_features,
effective_rank=rank,
tail_strength=0.2))
gc.collect()
print "benching nndsvd-nmf: "
tstart = time()
m = NMF(n_components=30, tol=tolerance, init='nndsvd').fit(X)
tend = time() - tstart
timeset['nndsvd-nmf'].append(tend)
err['nndsvd-nmf'].append(m.reconstruction_err_)
print m.reconstruction_err_, tend
gc.collect()
print "benching nndsvda-nmf: "
tstart = time()
m = NMF(n_components=30, init='nndsvda', tol=tolerance).fit(X)
tend = time() - tstart
timeset['nndsvda-nmf'].append(tend)
err['nndsvda-nmf'].append(m.reconstruction_err_)
print m.reconstruction_err_, tend
gc.collect()
print "benching nndsvdar-nmf: "
tstart = time()
m = NMF(n_components=30, init='nndsvdar', tol=tolerance).fit(X)
tend = time() - tstart
timeset['nndsvdar-nmf'].append(tend)
err['nndsvdar-nmf'].append(m.reconstruction_err_)
print m.reconstruction_err_, tend
gc.collect()
print "benching random-nmf"
tstart = time()
m = NMF(n_components=30, init=None, max_iter=1000,
tol=tolerance).fit(X)
tend = time() - tstart
timeset['random-nmf'].append(tend)
err['random-nmf'].append(m.reconstruction_err_)
print m.reconstruction_err_, tend
gc.collect()
print "benching alt-random-nmf"
tstart = time()
W, H = alt_nnmf(X, r=30, R=None, tol=tolerance)
tend = time() - tstart
timeset['alt-random-nmf'].append(tend)
err['alt-random-nmf'].append(np.linalg.norm(X - np.dot(W, H)))
print np.linalg.norm(X - np.dot(W, H)), tend
return timeset, err
scorer = make_scorer(score_func=singleLabelScore, greater_is_better=False)
# PREPROCESSING
# SCALING
minMaxScaler = MinMaxScaler(feature_range=(0.0, 1.0))
#normalizer = skprep.Normalizer()
columnDeleter = fs.FeatureDeleter()
# FEATURE SELECTION
varianceThresholdSelector = VarianceThreshold(threshold=(0))
percentileSelector = SelectPercentile(score_func=f_classif, percentile=20)
kBestSelector = SelectKBest(f_classif, 1000)
# FEATURE EXTRACTION
#rbmPipe = skpipe.Pipeline(steps=[('scaling', minMaxScaler), ('rbm', rbm)])
nmf = NMF(n_components=150)
pca = PCA(n_components=80)
sparse_pca = SparsePCA(n_components=700, max_iter=3, verbose=2)
kernel_pca = KernelPCA(n_components=150) # Costs huge amounts of ram
randomized_pca = RandomizedPCA(n_components=500)
# REGRESSORS
random_forest_regressor = RandomForestRegressor(n_estimators=256)
gradient_boosting_regressor = GradientBoostingRegressor(n_estimators=60)
support_vector_regressor = svm.SVR()
# CLASSIFIERS
support_vector_classifier = svm.SVC(probability=True, verbose=True)
linear_support_vector_classifier = svm.LinearSVC(dual=False)
nearest_neighbor_classifier = KNeighborsClassifier()
extra_trees_classifier = ExtraTreesClassifier(n_estimators=256)
