def learn_topics(terms_docs_matrix, k_topics, alpha=0.1, eta=0.1, max_iter=10, max_iter_per_doc=1):
"""
Using Collapsed Variational Bayes method (Mahout implementation) to train LDA topic model.
Args:
terms_docs_matrix(Expr or DistArray): the count of each term in each document.
k_topics: the number of topics we need to find.
alpha(float): parameter of LDA model.
eta(float): parameter of LDA model.
max_iter(int):the max iterations to train LDA topic model.
max_iter_per_doc: the max iterations to train each document.
"""
num_terms = terms_docs_matrix.shape[0]
num_docs = terms_docs_matrix.shape[1]
topic_term_counts = expr.rand(k_topics, num_terms)
for i in range(max_iter):
# topic_term_counts = expr.shuffle(expr.retile(terms_docs_matrix, tile_hint=util.calc_tile_hint(terms_docs_matrix, axis=1)),
# _lda_mapper,
# target=expr.ndarray((k_topics, num_terms), dtype=np.float64, reduce_fn=np.add),
# kw={'k_topics': k_topics, 'alpha': alpha, 'eta': eta, 'max_iter_per_doc': max_iter_per_doc,
#'topic_term_counts': topic_term_counts}).optimized()
topic_term_counts = expr.outer(
(terms_docs_matrix, topic_term_counts),
(1, None),
fn=_lda_mapper,
fn_kw={"k_topics": k_topics, "alpha": alpha, "eta": eta, "max_iter_per_doc": max_iter_per_doc},
shape=(k_topics, num_terms),
dtype=np.float64,
reducer=np.add,
)
# calculate the doc-topic inference
# doc_topics = expr.shuffle(expr.retile(terms_docs_matrix, tile_hint=util.calc_tile_hint(terms_docs_matrix, axis=1)),
# _lda_doc_topic_mapper,
# kw={'k_topics': k_topics, 'alpha': alpha, 'eta': eta, 'max_iter_per_doc': max_iter_per_doc,
#'topic_term_counts': topic_term_counts},
# shape_hint=(num_docs, k_topics)).optimized()
doc_topics = expr.outer(
(terms_docs_matrix, topic_term_counts),
(1, None),
fn=_lda_doc_topic_mapper,
fn_kw={"k_topics": k_topics, "alpha": alpha, "eta": eta, "max_iter_per_doc": max_iter_per_doc},
shape=(num_docs, k_topics),
dtype=np.float64,
)
# normalize the topic-term distribution
norm_val = expr.reduce(
topic_term_counts,
axis=1,
dtype_fn=lambda input: input.dtype,
local_reduce_fn=lambda ex, data, axis: np.abs(data).sum(axis),
accumulate_fn=np.add,
)
topic_term_counts = topic_term_counts / norm_val.reshape((k_topics, 1))
topic_term_counts = topic_term_counts.optimized()
return doc_topics, topic_term_counts
def als(A, la=0.065, alpha=40, implicit_feedback=False, num_features=20, num_iter=10, M=None):
'''
compute the factorization A = U M' using the alternating least-squares (ALS) method.
where `A` is the "ratings" matrix which maps from a user and item to a rating score,
`U` and `M` are the factor matrices, which represent user and item preferences.
Args:
A(Expr or DistArray): the rating matrix which maps from a user and item to a rating score.
la(float): the parameter of the als.
alpha(int): confidence parameter used on implicit feedback.
implicit_feedback(bool): whether using implicit_feedback method for als.
num_features(int): dimension of the feature space.
num_iter(int): max iteration to run.
'''
num_users = A.shape[0]
num_items = A.shape[1]
AT = expr.transpose(A)
avg_rating = expr.sum(A, axis=0) * 1.0 / expr.count_nonzero(A, axis=0)
M = expr.rand(num_items, num_features)
M = expr.assign(M, np.s_[:, 0], avg_rating.reshape((avg_rating.shape[0], 1)))
#A = expr.retile(A, tile_hint=util.calc_tile_hint(A, axis=0))
#AT = expr.retile(AT, tile_hint=util.calc_tile_hint(AT, axis=0))
for i in range(num_iter):
# Recomputing U
shape = (num_users, num_features)
U = expr.outer((A, M), (0, None), fn=_solve_U_or_M_mapper,
fn_kw={'la': la, 'alpha': alpha,
'implicit_feedback': implicit_feedback, 'shape': shape},
shape=shape, dtype=np.float)
# Recomputing M
shape = (num_items, num_features)
M = expr.outer((AT, U), (0, None), fn=_solve_U_or_M_mapper,
fn_kw={'la': la, 'alpha': alpha,
'implicit_feedback': implicit_feedback, 'shape': shape},
shape=shape, dtype=np.float)
return U, M
def learn_topics(terms_docs_matrix,
k_topics,
alpha=0.1,
eta=0.1,
max_iter=10,
max_iter_per_doc=1):
'''
Using Collapsed Variational Bayes method (Mahout implementation) to train LDA topic model.
Args:
terms_docs_matrix(Expr or DistArray): the count of each term in each document.
k_topics: the number of topics we need to find.
alpha(float): parameter of LDA model.
eta(float): parameter of LDA model.
max_iter(int):the max iterations to train LDA topic model.
max_iter_per_doc: the max iterations to train each document.
'''
num_terms = terms_docs_matrix.shape[0]
num_docs = terms_docs_matrix.shape[1]
topic_term_counts = expr.rand(k_topics, num_terms)
for i in range(max_iter):
#topic_term_counts = expr.shuffle(expr.retile(terms_docs_matrix, tile_hint=util.calc_tile_hint(terms_docs_matrix, axis=1)),
#_lda_mapper,
#target=expr.ndarray((k_topics, num_terms), dtype=np.float64, reduce_fn=np.add),
#kw={'k_topics': k_topics, 'alpha': alpha, 'eta': eta, 'max_iter_per_doc': max_iter_per_doc,
#'topic_term_counts': topic_term_counts}).optimized()
topic_term_counts = expr.outer(
(terms_docs_matrix, topic_term_counts), (1, None),
fn=_lda_mapper,
fn_kw={
'k_topics': k_topics,
'alpha': alpha,
'eta': eta,
'max_iter_per_doc': max_iter_per_doc
},
shape=(k_topics, num_terms),
dtype=np.float64,
reducer=np.add)
# calculate the doc-topic inference
#doc_topics = expr.shuffle(expr.retile(terms_docs_matrix, tile_hint=util.calc_tile_hint(terms_docs_matrix, axis=1)),
#_lda_doc_topic_mapper,
#kw={'k_topics': k_topics, 'alpha': alpha, 'eta': eta, 'max_iter_per_doc': max_iter_per_doc,
#'topic_term_counts': topic_term_counts},
#shape_hint=(num_docs, k_topics)).optimized()
doc_topics = expr.outer(
(terms_docs_matrix, topic_term_counts), (1, None),
fn=_lda_doc_topic_mapper,
fn_kw={
'k_topics': k_topics,
'alpha': alpha,
'eta': eta,
'max_iter_per_doc': max_iter_per_doc
},
shape=(num_docs, k_topics),
dtype=np.float64)
# normalize the topic-term distribution
norm_val = expr.reduce(
topic_term_counts,
axis=1,
dtype_fn=lambda input: input.dtype,
local_reduce_fn=lambda ex, data, axis: np.abs(data).sum(axis),
accumulate_fn=np.add)
topic_term_counts = topic_term_counts / norm_val.reshape((k_topics, 1))
return doc_topics, topic_term_counts
def fit(self, X, centers=None, implementation='outer'):
"""Compute k-means clustering.
Parameters
----------
X : spartan matrix, shape=(n_samples, n_features). It should be tiled by rows.
centers : numpy.ndarray. The initial centers. If None, it will be randomly generated.
"""
num_dim = X.shape[1]
num_points = X.shape[0]
labels = expr.zeros((num_points, 1), dtype=np.int)
if implementation == 'map2':
if centers is None:
centers = np.random.rand(self.n_clusters, num_dim)
for i in range(self.n_iter):
labels = expr.map2(X, 0, fn=kmeans_map2_dist_mapper, fn_kw={"centers": centers},
shape=(X.shape[0], ))
counts = expr.map2(labels, 0, fn=kmeans_count_mapper,
fn_kw={'centers_count': self.n_clusters},
shape=(centers.shape[0], ))
new_centers = expr.map2((X, labels), (0, 0), fn=kmeans_center_mapper,
fn_kw={'centers_count': self.n_clusters},
shape=(centers.shape[0], centers.shape[1]))
counts = counts.optimized().glom()
centers = new_centers.optimized().glom()
# If any centroids don't have any points assigined to them.
zcount_indices = (counts == 0).reshape(self.n_clusters)
if np.any(zcount_indices):
# One or more centroids may not have any points assigned to them,
# which results in their position being the zero-vector. We reseed these
# centroids with new random values.
n_points = np.count_nonzero(zcount_indices)
# In order to get rid of dividing by zero.
counts[zcount_indices] = 1
centers[zcount_indices, :] = np.random.randn(n_points, num_dim)
centers = centers / counts.reshape(centers.shape[0], 1)
return centers, labels
elif implementation == 'outer':
if centers is None:
centers = expr.rand(self.n_clusters, num_dim)
for i in range(self.n_iter):
labels = expr.outer((X, centers), (0, None), fn=kmeans_outer_dist_mapper,
shape=(X.shape[0],))
#labels = expr.argmin(distances, axis=1)
counts = expr.map2(labels, 0, fn=kmeans_count_mapper,
fn_kw={'centers_count': self.n_clusters},
shape=(centers.shape[0], ))
new_centers = expr.map2((X, labels), (0, 0), fn=kmeans_center_mapper,
fn_kw={'centers_count': self.n_clusters},
shape=(centers.shape[0], centers.shape[1]))
counts = counts.optimized().glom()
centers = new_centers.optimized().glom()
# If any centroids don't have any points assigined to them.
zcount_indices = (counts == 0).reshape(self.n_clusters)
if np.any(zcount_indices):
# One or more centroids may not have any points assigned to them,
# which results in their position being the zero-vector. We reseed these
# centroids with new random values.
n_points = np.count_nonzero(zcount_indices)
# In order to get rid of dividing by zero.
counts[zcount_indices] = 1
centers[zcount_indices, :] = np.random.randn(n_points, num_dim)
centers = centers / counts.reshape(centers.shape[0], 1)
centers = expr.from_numpy(centers)
return centers, labels
elif implementation == 'broadcast':
if centers is None:
centers = expr.rand(self.n_clusters, num_dim)
for i in range(self.n_iter):
util.log_warn("k_means_ %d %d", i, time.time())
X_broadcast = expr.reshape(X, (X.shape[0], 1, X.shape[1]))
centers_broadcast = expr.reshape(centers, (1, centers.shape[0],
centers.shape[1]))
distances = expr.sum(expr.square(X_broadcast - centers_broadcast), axis=2)
labels = expr.argmin(distances, axis=1)
center_idx = expr.arange((1, centers.shape[0]))
matches = expr.reshape(labels, (labels.shape[0], 1)) == center_idx
matches = matches.astype(np.int64)
counts = expr.sum(matches, axis=0)
centers = expr.sum(X_broadcast * expr.reshape(matches, (matches.shape[0],
matches.shape[1], 1)),
axis=0)
counts = counts.optimized().glom()
centers = centers.optimized().glom()
# If any centroids don't have any points assigined to them.
zcount_indices = (counts == 0).reshape(self.n_clusters)
if np.any(zcount_indices):
# One or more centroids may not have any points assigned to them,
# which results in their position being the zero-vector. We reseed these
# centroids with new random values.
n_points = np.count_nonzero(zcount_indices)
# In order to get rid of dividing by zero.
counts[zcount_indices] = 1
centers[zcount_indices, :] = np.random.randn(n_points, num_dim)
centers = centers / counts.reshape(centers.shape[0], 1)
centers = expr.from_numpy(centers)
return centers, labels
elif implementation == 'shuffle':
if centers is None:
centers = np.random.rand(self.n_clusters, num_dim)
for i in range(self.n_iter):
# Reset them to zero.
new_centers = expr.ndarray((self.n_clusters, num_dim),
reduce_fn=lambda a, b: a + b)
new_counts = expr.ndarray((self.n_clusters, 1), dtype=np.int,
reduce_fn=lambda a, b: a + b)
_ = expr.shuffle(X,
_find_cluster_mapper,
kw={'d_pts': X,
'old_centers': centers,
'new_centers': new_centers,
'new_counts': new_counts,
'labels': labels},
shape_hint=(1,),
cost_hint={hash(labels): {'00': 0,
'01': np.prod(labels.shape)}})
_.force()
new_counts = new_counts.glom()
new_centers = new_centers.glom()
# If any centroids don't have any points assigined to them.
zcount_indices = (new_counts == 0).reshape(self.n_clusters)
if np.any(zcount_indices):
# One or more centroids may not have any points assigned to them,
# which results in their position being the zero-vector. We reseed these
# centroids with new random values.
n_points = np.count_nonzero(zcount_indices)
# In order to get rid of dividing by zero.
new_counts[zcount_indices] = 1
new_centers[zcount_indices, :] = np.random.randn(n_points, num_dim)
new_centers = new_centers / new_counts
centers = new_centers
return centers, labels
def fit(self, X, centers=None, implementation='map2'):
"""Compute k-means clustering.
Parameters
----------
X : spartan matrix, shape=(n_samples, n_features). It should be tiled by rows.
centers : numpy.ndarray. The initial centers. If None, it will be randomly generated.
"""
num_dim = X.shape[1]
num_points = X.shape[0]
labels = expr.zeros((num_points, 1), dtype=np.int)
if implementation == 'map2':
if centers is None:
centers = np.random.rand(self.n_clusters, num_dim)
for i in range(self.n_iter):
labels = expr.map2(X,
0,
fn=kmeans_map2_dist_mapper,
fn_kw={"centers": centers},
shape=(X.shape[0], ))
counts = expr.map2(labels,
0,
fn=kmeans_count_mapper,
fn_kw={'centers_count': self.n_clusters},
shape=(centers.shape[0], ))
new_centers = expr.map2(
(X, labels), (0, 0),
fn=kmeans_center_mapper,
fn_kw={'centers_count': self.n_clusters},
shape=(centers.shape[0], centers.shape[1]))
counts = counts.optimized().glom()
centers = new_centers.optimized().glom()
# If any centroids don't have any points assigined to them.
zcount_indices = (counts == 0).reshape(self.n_clusters)
if np.any(zcount_indices):
# One or more centroids may not have any points assigned to them,
# which results in their position being the zero-vector. We reseed these
# centroids with new random values.
n_points = np.count_nonzero(zcount_indices)
# In order to get rid of dividing by zero.
counts[zcount_indices] = 1
centers[zcount_indices, :] = np.random.randn(
n_points, num_dim)
centers = centers / counts.reshape(centers.shape[0], 1)
return centers, labels
elif implementation == 'outer':
if centers is None:
centers = expr.rand(self.n_clusters, num_dim)
for i in range(self.n_iter):
labels = expr.outer((X, centers), (0, None),
fn=kmeans_outer_dist_mapper,
shape=(X.shape[0], ))
#labels = expr.argmin(distances, axis=1)
counts = expr.map2(labels,
0,
fn=kmeans_count_mapper,
fn_kw={'centers_count': self.n_clusters},
shape=(centers.shape[0], ))
new_centers = expr.map2(
(X, labels), (0, 0),
fn=kmeans_center_mapper,
fn_kw={'centers_count': self.n_clusters},
shape=(centers.shape[0], centers.shape[1]))
counts = counts.optimized().glom()
centers = new_centers.optimized().glom()
# If any centroids don't have any points assigined to them.
zcount_indices = (counts == 0).reshape(self.n_clusters)
if np.any(zcount_indices):
# One or more centroids may not have any points assigned to them,
# which results in their position being the zero-vector. We reseed these
# centroids with new random values.
n_points = np.count_nonzero(zcount_indices)
# In order to get rid of dividing by zero.
counts[zcount_indices] = 1
centers[zcount_indices, :] = np.random.randn(
n_points, num_dim)
centers = centers / counts.reshape(centers.shape[0], 1)
centers = expr.from_numpy(centers)
return centers, labels
elif implementation == 'broadcast':
if centers is None:
centers = expr.rand(self.n_clusters, num_dim)
for i in range(self.n_iter):
util.log_warn("k_means_ %d %d", i, time.time())
X_broadcast = expr.reshape(X, (X.shape[0], 1, X.shape[1]))
centers_broadcast = expr.reshape(
centers, (1, centers.shape[0], centers.shape[1]))
distances = expr.sum(expr.square(X_broadcast -
centers_broadcast),
axis=2)
labels = expr.argmin(distances, axis=1)
center_idx = expr.arange((1, centers.shape[0]))
matches = expr.reshape(labels,
(labels.shape[0], 1)) == center_idx
matches = matches.astype(np.int64)
counts = expr.sum(matches, axis=0)
centers = expr.sum(
X_broadcast *
expr.reshape(matches,
(matches.shape[0], matches.shape[1], 1)),
axis=0)
counts = counts.optimized().glom()
centers = centers.optimized().glom()
# If any centroids don't have any points assigined to them.
zcount_indices = (counts == 0).reshape(self.n_clusters)
if np.any(zcount_indices):
# One or more centroids may not have any points assigned to them,
# which results in their position being the zero-vector. We reseed these
# centroids with new random values.
n_points = np.count_nonzero(zcount_indices)
# In order to get rid of dividing by zero.
counts[zcount_indices] = 1
centers[zcount_indices, :] = np.random.randn(
n_points, num_dim)
centers = centers / counts.reshape(centers.shape[0], 1)
centers = expr.from_numpy(centers)
return centers, labels
elif implementation == 'shuffle':
if centers is None:
centers = np.random.rand(self.n_clusters, num_dim)
for i in range(self.n_iter):
# Reset them to zero.
new_centers = expr.ndarray((self.n_clusters, num_dim),
reduce_fn=lambda a, b: a + b)
new_counts = expr.ndarray((self.n_clusters, 1),
dtype=np.int,
reduce_fn=lambda a, b: a + b)
_ = expr.shuffle(X,
_find_cluster_mapper,
kw={
'd_pts': X,
'old_centers': centers,
'new_centers': new_centers,
'new_counts': new_counts,
'labels': labels
},
shape_hint=(1, ),
cost_hint={
hash(labels): {
'00': 0,
'01': np.prod(labels.shape)
}
})
_.force()
new_counts = new_counts.glom()
new_centers = new_centers.glom()
# If any centroids don't have any points assigined to them.
zcount_indices = (new_counts == 0).reshape(self.n_clusters)
if np.any(zcount_indices):
# One or more centroids may not have any points assigned to them,
# which results in their position being the zero-vector. We reseed these
# centroids with new random values.
n_points = np.count_nonzero(zcount_indices)
# In order to get rid of dividing by zero.
new_counts[zcount_indices] = 1
new_centers[zcount_indices, :] = np.random.randn(
n_points, num_dim)
new_centers = new_centers / new_counts
centers = new_centers
return centers, labels
def als(A,
la=0.065,
alpha=40,
implicit_feedback=False,
num_features=20,
num_iter=10,
M=None):
'''
compute the factorization A = U M' using the alternating least-squares (ALS) method.
where `A` is the "ratings" matrix which maps from a user and item to a rating score,
`U` and `M` are the factor matrices, which represent user and item preferences.
Args:
A(Expr or DistArray): the rating matrix which maps from a user and item to a rating score.
la(float): the parameter of the als.
alpha(int): confidence parameter used on implicit feedback.
implicit_feedback(bool): whether using implicit_feedback method for als.
num_features(int): dimension of the feature space.
num_iter(int): max iteration to run.
'''
num_users = A.shape[0]
num_items = A.shape[1]
AT = expr.transpose(A)
avg_rating = expr.sum(A, axis=0) * 1.0 / expr.count_nonzero(A, axis=0)
M = expr.rand(num_items, num_features)
M = expr.assign(M, np.s_[:, 0], avg_rating.reshape(
(avg_rating.shape[0], 1)))
#A = expr.retile(A, tile_hint=util.calc_tile_hint(A, axis=0))
#AT = expr.retile(AT, tile_hint=util.calc_tile_hint(AT, axis=0))
for i in range(num_iter):
# Recomputing U
shape = (num_users, num_features)
U = expr.outer(
(A, M), (0, None),
fn=_solve_U_or_M_mapper,
fn_kw={
'la': la,
'alpha': alpha,
'implicit_feedback': implicit_feedback,
'shape': shape
},
shape=shape,
dtype=np.float)
# Recomputing M
shape = (num_items, num_features)
M = expr.outer(
(AT, U), (0, None),
fn=_solve_U_or_M_mapper,
fn_kw={
'la': la,
'alpha': alpha,
'implicit_feedback': implicit_feedback,
'shape': shape
},
shape=shape,
dtype=np.float)
return U, M
