def get_recommendations(self):
userid = self.data.fields.userid
itemid = self.data.fields.itemid
u = self.factors[userid]
v = self.factors[itemid]
s = self.factors['singular_values']
if self.use_raw_features:
item_info = self.item_features.reindex(
self.data.index.itemid.training.old.values, fill_value=[])
item_features, feature_labels = stack_features(item_info,
normalize=False)
w = item_features.T.dot(v).T
wwt_inv = np.linalg.pinv(w @ w.T)
cold_info = self.item_features.reindex(
self.data.index.itemid.cold_start.old.values, fill_value=[])
cold_item_features, _ = stack_features(cold_info,
labels=feature_labels,
normalize=False)
else:
w = self.data.item_relations.T.dot(v).T
wwt_inv = np.linalg.pinv(w @ w.T)
cold_item_features = self.data.cold_items_similarity
cold_items_factors = cold_item_features.dot(w.T) @ wwt_inv
scores = cold_items_factors @ (u * s[None, :]).T
top_similar_users = self.get_topk_elements(scores).astype(np.intp)
return top_similar_users
def build(self):
self._model = LightFM(no_components=self.rank,
item_alpha=self.item_alpha,
user_alpha=self.user_alpha,
loss=self.loss,
learning_rate=self.learning_rate,
learning_schedule=self.learning_schedule,
max_sampled=self.max_sampled,
random_state=self.seed)
fit = getattr(self._model, self.fit_method)
matrix = self.get_training_matrix()
if self.item_features is not None:
item_features = self.item_features.reindex(
self.data.index.itemid.old.values, fill_value=[])
self._item_features_csr, self.item_feature_labels = stack_features(
item_features,
add_identity=self.item_identity,
normalize=True,
dtype='f4')
if self.user_features is not None:
user_features = self.user_features.reindex(
self.data.index.userid.training.old.values, fill_value=[])
self._user_features_csr, self.user_feature_labels = stack_features(
user_features,
add_identity=self.user_identity,
normalize=True,
dtype='f4')
with Timer(self.method, verbose=self.verbose):
fit(matrix,
item_features=self._item_features_csr,
user_features=self._user_features_csr)
def build(self):
# prepare input matrix for learning the model
Xs, lbls = stack_features(self.item_data, normalize=False) # item-features sparse matrix
Xu = self.get_training_matrix().T # item-user sparse matrix
n_nbrs = min(self.max_neighbours, int(math.sqrt(Xs.shape[0])))
A = construct_A(Xs, n_nbrs, binary=self.binary_features)
with track_time(self.training_time, verbose=self.verbose, model=self.method):
W, Hu, Hs = LCE(Xs, Xu, A,
k=self.rank,
alpha=self.alpha,
beta=self.beta,
lamb=self.regularization,
epsilon=self.tolerance,
maxiter=self.max_iterations,
seed=self.seed,
verbose=self.show_error)
userid = self.data.fields.userid
itemid = self.data.fields.itemid
self.factors[userid] = Hu.T
self.factors[itemid] = W
self.factors['item_features'] = Hs.T
self.feature_labels = lbls
def get_similarity_data(meta_info,
metric='common',
assume_binary=True,
fill_diagonal=True):
feat_mat, lbls = stack_features(meta_info, normalize=False)
if metric == 'common':
item_similarity = feat_mat.dot(feat_mat.T)
item_similarity = item_similarity / item_similarity.data.max()
item_similarity.setdiag(1.0)
if (metric == 'cosine') or (metric == 'salton'):
item_similarity = cosine_similarity(feat_mat,
assume_binary=assume_binary,
fill_diagonal=fill_diagonal)
if item_similarity.format == 'csr':
item_similarity = item_similarity.T # ensure CSC format (matrix is symmetric)
userid = 'userid'
itemid = meta_info.index.name
similarities = {userid: None, itemid: item_similarity}
indices = {userid: None, itemid: meta_info.index}
labels = {userid: None, itemid: lbls}
return similarities, indices, labels
def build(self):
self._model = LightFM(no_components=self.rank,
item_alpha=self.item_alpha,
user_alpha=self.user_alpha,
loss=self.loss,
learning_rate=self.learning_rate,
learning_schedule=self.learning_schedule,
max_sampled=self.max_sampled,
random_state=self.seed)
fit = getattr(self._model, self.fit_method)
matrix = self.get_training_matrix(
sparse_format='coo') # as reqired by LightFM
try:
item_index = self.data.index.itemid.training
except AttributeError:
item_index = self.data.index.itemid
if self.item_features is not None:
item_features = self.item_features.reindex(item_index.old.values,
fill_value=[])
self._item_features_csr, self.item_features_labels = stack_features(
item_features,
add_identity=self.item_identity,
normalize=self.normalize_item_features,
dtype='f4')
if self.user_features is not None:
user_features = self.user_features.reindex(
self.data.index.userid.training.old.values, fill_value=[])
self._user_features_csr, self.user_features_labels = stack_features(
user_features,
add_identity=self.user_identity,
normalize=self.normalize_user_features,
dtype='f4')
with track_time(self.training_time,
verbose=self.verbose,
model=self.method):
fit(matrix,
item_features=self._item_features_csr,
user_features=self._user_features_csr,
**self.fit_params)
def get_recommendations(self):
userid = self.data.fields.userid
itemid = self.data.fields.itemid
Hu = self.factors[userid].T
Hs = self.factors['item_features'].T
cold_info = self.item_features.reindex(self.data.index.itemid.cold_start.old.values,
fill_value=[])
cold_item_features, _ = stack_features(cold_info, labels=self.feature_labels, normalize=False)
cold_items_factors = cold_item_features.dot(Hs.T).dot(np.linalg.pinv(Hs @ Hs.T))
cold_items_factors[cold_items_factors < 0] = 0
scores = cold_items_factors @ Hu
top_relevant_users = self.get_topk_elements(scores).astype(np.intp)
return top_relevant_users