class USTAN:
'''
STAN( k, sample_size=5000, sampling='recent', remind=True, extend=False, lambda_spw=1.02, lambda_snh=5, lambda_inh=2.05 , session_key = 'SessionId', item_key= 'ItemId', time_key= 'Time' )
Parameters
-----------
k : int
Number of neighboring session to calculate the item scores from. (Default value: 100)
sample_size : int
Defines the length of a subset of all training sessions to calculate the nearest neighbors from. (Default value: 500)
sampling : string
String to define the sampling method for sessions (recent, random). (default: recent)
remind : string
String to define the method for the similarity calculation (jaccard, cosine, binary, tanimoto). (default: jaccard)
extend : string
Decay function to determine the importance/weight of individual actions in the current session (linear, same, div, log, quadratic). (default: div)
lambda_spw : string
Decay function to lower the score of candidate items from a neighboring sessions that were selected by less recently clicked items in the current session. (linear, same, div, log, quadratic). (default: div_score)
lambda_snh : boolean
Experimental function to give less weight to items from older sessions (default: False)
lambda_inh : boolean
Experimental function to use the dwelling time for item view actions as a weight in the similarity calculation. (default: False)
session_key : string
Header of the session ID column in the input file. (default: 'SessionId')
item_key : string
Header of the item ID column in the input file. (default: 'ItemId')
time_key : string
Header of the timestamp column in the input file. (default: 'Time')
'''
def __init__( self, k, sample_size=5000, sampling='recent', remind=True, extend=False, lambda_spw=1.02, lambda_snh=5, lambda_inh=2.05 ,
extend_session_length=None, extending_mode='lastViewed', refine_mode=True, boost_own_sessions=None,
reminders=False, remind_strategy='recency', remind_sessions_num=6, reminders_num=3, remind_mode='end', weight_base=1, weight_IRec=0, weight_SSim=0,
session_key = 'SessionId', item_key= 'ItemId', time_key= 'Time', user_key='UserId'):
self.k = k
self.sample_size = sample_size
self.sampling = sampling
self.lambda_spw = lambda_spw
self.lambda_snh = lambda_snh * 24 * 3600
self.lambda_inh = lambda_inh
self.session_key = session_key
self.item_key = item_key
self.time_key = time_key
self.user_key = user_key # user_based
self.extend = extend
self.remind = remind
self.extending_mode = extending_mode
# user_based
self.extend_session_length = extend_session_length
self.refine_mode = refine_mode
self.boost_own_sessions = boost_own_sessions
#updated while recommending
self.session = -1
self.session_items = []
self.relevant_sessions = set()
# user_based
self.items_previous = []
self.last_user_items = {} # to extend the session model
self.recent_user_items = {} # to remind
self.recent_user_sessions = {} # to remind
self.user_item_intensity = dict() # to remind (for 'session_similarity')
# reminders
self.hasReminders = reminders
if self.hasReminders:
if remind_strategy == 'hybrid':
self.reminder = Reminder(remind_strategy=remind_strategy, remind_sessions_num=remind_sessions_num,
weight_base=weight_base, weight_IRec=weight_IRec, weight_SSim=weight_SSim)
else: # basic reminders
self.reminder = Reminder(remind_strategy=remind_strategy, remind_sessions_num=remind_sessions_num,
reminders_num=reminders_num, remind_mode=remind_mode)
# cache relations once at startup
self.session_item_map = dict()
self.item_session_map = dict()
self.session_time = dict()
self.min_time = -1
self.session_user_map = dict() # user_based
self.sim_time = 0
def fit(self, train, test=None, items=None):
'''
Trains the predictor.
Parameters
--------
data: pandas.DataFrame
Training data. It contains the transactions of the sessions. It has one column for session IDs, one for item IDs and one for the timestamp of the events (unix timestamps).
It must have a header. Column names are arbitrary, but must correspond to the ones you set during the initialization of the network (session_key, item_key, time_key properties).
'''
self.num_items = train[self.item_key].max()
index_session = train.columns.get_loc( self.session_key )
index_item = train.columns.get_loc( self.item_key )
index_time = train.columns.get_loc( self.time_key )
index_user = train.columns.get_loc(self.user_key) # user_based
session = -1
session_items = []
time = -1
user = -1 # user_based
#cnt = 0
for row in train.itertuples(index=False):
# cache items of sessions
if row[index_session] != session:
if len(session_items) > 0:
self.session_item_map.update({session : session_items})
# cache the last time stamp of the session
self.session_time.update({session : time})
self.session_user_map.update({session: user}) # user_based
if time < self.min_time:
self.min_time = time
user = row[index_user] # user_based
session = row[index_session]
session_items = []
time = row[index_time]
session_items.append(row[index_item])
# cache sessions involving an item
map_is = self.item_session_map.get( row[index_item] )
if map_is is None:
map_is = set()
self.item_session_map.update({row[index_item] : map_is})
map_is.add(row[index_session])
# add last viewed items (by the user) to the last_user_items dictionary
if self.extend_session_length is not None: # user_based
self.extend_session_in_fit(row, index_user, index_item)
# reminders
if self.hasReminders: # user_based # for 'session_similarity' or 'recency'
self.reminder.reminders_fit_in_loop(row, index_user, index_session, index_item)
# reminders # save item_intensity in the last N session for each user
if self.hasReminders: # user_based
self.reminder.reminders_fit(train, self.user_key, self.item_key, self.time_key)
# Add the last tuple
self.session_item_map.update({session : session_items})
self.session_time.update({session : time})
self.session_user_map.update({session: user}) # user_based
if self.sample_size == 0: #use all session as possible neighbors
print('!!!!! runnig KNN without a sample size (check config)')
def predict_next( self, session_id, input_item_id, input_user_id, predict_for_item_ids=None, timestamp=0, skip=False, type='view'):
'''
Gives predicton scores for a selected set of items on how likely they be the next item in the session.
Parameters
--------
session_id : int or string
The session IDs of the event.
input_item_id : int or string
The item ID of the event. Must be in the set of item IDs of the training set.
predict_for_item_ids : 1D array
IDs of items for which the network should give prediction scores. Every ID must be in the set of item IDs of the training set.
Returns
--------
out : pandas.Series
Prediction scores for selected items on how likely to be the next item of this session. Indexed by the item IDs.
'''
# gc.collect()
# process = psutil.Process(os.getpid())
# print( 'cknn.predict_next: ', process.memory_info().rss, ' memory used')
if( self.session != session_id ): #new session
if( self.extend ):
self.session_item_map[self.session] = self.session_items;
for item in self.session_items:
map_is = self.item_session_map.get( item )
if map_is is None:
map_is = set()
self.item_session_map.update({item : map_is})
map_is.add(self.session)
ts = time.time()
self.session_time.update({self.session : ts})
self.session_user_map.update({self.session: input_user_id}) # user_based
self.session = session_id
self.session_items = list()
self.relevant_sessions = set()
self.items_previous = [] # user_based
self.need_refine = True # user_based
if type == 'view':
self.session_items.append( input_item_id )
if skip:
return
items = self.session_items
# we add extra items form the user profile as long as the session is not long enough!
if self.extend_session_length is not None and input_user_id in self.last_user_items: # user_based
items = self.extend_session_in_predict_next(items, input_user_id)
neighbors = self.find_neighbors( items, input_item_id, session_id, timestamp, input_user_id)
scores = self.score_items( neighbors, items, timestamp )
# Create things in the format ..
predictions = np.zeros(len(predict_for_item_ids))
mask = np.in1d( predict_for_item_ids, list(scores.keys()) )
items = predict_for_item_ids[mask]
values = [scores[x] for x in items]
predictions[mask] = values
series = pd.Series(data=predictions, index=predict_for_item_ids)
if self.hasReminders: # user_based
if self.reminder.remind_strategy == 'hybrid':
if self.reminder.w_SSim == 0:
series = self.reminder.reminders_predict_next(input_user_id, series, self.item_key,
self.time_key, input_timestamp=timestamp)
else:
past_user_sessions = self.calc_similarity(items, self.reminder.recent_user_sessions[input_user_id], timestamp, input_user_id)
series = self.reminder.reminders_predict_next(input_user_id, series, self.item_key, self.time_key,
past_user_sessions=past_user_sessions, session_item_map=self.session_item_map, input_timestamp=timestamp)
else: # basic reminders
if self.reminder.remind_strategy == 'session_similarity':
past_user_sessions = self.calc_similarity(items, self.reminder.recent_user_sessions[input_user_id], timestamp, input_user_id)
series = self.reminder.reminders_predict_next(input_user_id, series, self.item_key, self.time_key,
past_user_sessions=past_user_sessions, session_item_map=self.session_item_map)
if self.reminder.remind_strategy == 'recency':
series = self.reminder.reminders_predict_next(input_user_id, series, self.item_key, self.time_key)
return series
def vec(self, current, neighbor, pos_map):
'''
Calculates the ? for 2 sessions
Parameters
--------
first: Id of a session
second: Id of a session
Returns
--------
out : float value
'''
intersection = current & neighbor
vp_sum = 0
for i in intersection:
vp_sum += pos_map[i]
result = vp_sum / len(pos_map)
return result
def cosine(self, current, neighbor, pos_map):
'''
Calculates the cosine similarity for two sessions
Parameters
--------
first: Id of a session
second: Id of a session
Returns
--------
out : float value
'''
lneighbor = len(neighbor)
intersection = current & neighbor
if pos_map is not None:
vp_sum = 0
current_sum = 0
for i in current:
current_sum += pos_map[i] * pos_map[i]
if i in intersection:
vp_sum += pos_map[i]
else:
vp_sum = len( intersection )
current_sum = len( current )
result = vp_sum / (sqrt(current_sum) * sqrt(lneighbor))
return result
def items_for_session(self, session):
'''
Returns all items in the session
Parameters
--------
session: Id of a session
Returns
--------
out : set
'''
return self.session_item_map.get(session);
def sessions_for_item(self, item_id):
'''
Returns all session for an item
Parameters
--------
item: Id of the item session
Returns
--------
out : set
'''
return self.item_session_map.get( item_id ) if item_id in self.item_session_map else set()
def most_recent_sessions( self, sessions, number ):
'''
Find the most recent sessions in the given set
Parameters
--------
sessions: set of session ids
Returns
--------
out : set
'''
sample = set()
tuples = list()
for session in sessions:
time = self.session_time.get( session )
if time is None:
print(' EMPTY TIMESTAMP!! ', session)
tuples.append((session, time))
tuples = sorted(tuples, key=itemgetter(1), reverse=True)
#print 'sorted list ', sortedList
cnt = 0
for element in tuples:
cnt = cnt + 1
if cnt > number:
break
sample.add( element[0] )
#print 'returning sample of size ', len(sample)
return sample
#-----------------
# Find a set of neighbors, returns a list of tuples (sessionid: similarity)
#-----------------
def find_neighbors( self, session_items, input_item_id, session_id, timestamp, user_id):
'''
Finds the k nearest neighbors for the given session_id and the current item input_item_id.
Parameters
--------
session_items: set of item ids
input_item_id: int
session_id: int
Returns
--------
out : list of tuple (session_id, similarity)
'''
possible_neighbors = self.possible_neighbor_sessions( session_items, input_item_id, session_id, user_id)
possible_neighbors = self.calc_similarity( session_items, possible_neighbors, timestamp, user_id)
possible_neighbors = sorted( possible_neighbors, reverse=True, key=lambda x: x[1] )
possible_neighbors = possible_neighbors[:self.k]
return possible_neighbors
def possible_neighbor_sessions(self, session_items, input_item_id, session_id, user_id):
'''
Find a set of session to later on find neighbors in.
A self.sample_size of 0 uses all sessions in which any item of the current session appears.
self.sampling can be performed with the options "recent" or "random".
"recent" selects the self.sample_size most recent sessions while "random" just choses randomly.
Parameters
--------
sessions: set of session ids
Returns
--------
out : set
'''
self.relevant_sessions = self.relevant_sessions | self.sessions_for_item( input_item_id )
if self.sample_size == 0: #use all session as possible neighbors
#print('!!!!! runnig KNN without a sample size (check config)')
return self.relevant_sessions
else: #sample some sessions
if len(self.relevant_sessions) > self.sample_size:
if self.sampling == 'recent':
sample = self.most_recent_sessions( self.relevant_sessions, self.sample_size )
elif self.sampling == 'random':
sample = random.sample( self.relevant_sessions, self.sample_size )
else:
sample = self.relevant_sessions[:self.sample_size]
return sample
else:
return self.relevant_sessions
def calc_similarity(self, session_items, sessions, timestamp, user_id):
'''
Calculates the configured similarity for the items in session_items and each session in sessions.
Parameters
--------
session_items: set of item ids
sessions: list of session ids
Returns
--------
out : list of tuple (session_id,similarity)
'''
pos_map = None
if self.lambda_spw:
pos_map = {}
length = len( session_items )
pos = 1
for item in session_items:
if self.lambda_spw is not None:
pos_map[item] = self.session_pos_weight( pos, length, self.lambda_spw )
pos += 1
#print 'nb of sessions to test ', len(sessionsToTest), ' metric: ', self.metric
items = set(session_items)
neighbors = []
cnt = 0
for session in sessions:
cnt = cnt + 1
# get items of the session, look up the cache first
n_items = self.items_for_session( session )
similarity = self.cosine(items, set(n_items), pos_map)
if self.lambda_snh is not None:
sts = self.session_time[session]
decay = self.session_time_weight(timestamp, sts, self.lambda_snh)
similarity *= decay
if self.boost_own_sessions is not None: # user_based
similarity = self.apply_boost(session, user_id, similarity)
neighbors.append((session, similarity))
return neighbors
def session_pos_weight(self, position, length, lambda_spw):
diff = position - length
return exp( diff / lambda_spw )
def session_time_weight(self, ts_current, ts_neighbor, lambda_snh):
diff = ts_current - ts_neighbor
return exp( - diff / lambda_snh )
def score_items(self, neighbors, current_session, timestamp):
'''
Compute a set of scores for all items given a set of neighbors.
Parameters
--------
neighbors: set of session ids
Returns
--------
out : list of tuple (item, score)
'''
# now we have the set of relevant items to make predictions
scores = dict()
s_items = set( current_session )
# iterate over the sessions
for session in neighbors:
# get the items in this session
n_items = self.items_for_session( session[0] )
pos_last = {}
pos_i_star = None
for i in range( len( n_items ) ):
if n_items[i] in s_items:
pos_i_star = i + 1
pos_last[n_items[i]] = i + 1
n_items = set( n_items )
for item in n_items:
if not self.remind and item in s_items:
continue
old_score = scores.get( item )
new_score = session[1]
if self.lambda_inh is not None:
new_score = new_score * self.item_pos_weight( pos_last[item], pos_i_star, self.lambda_inh )
if not old_score is None:
new_score = old_score + new_score
scores.update({item : new_score})
return scores
def item_pos_weight(self, pos_candidate, pos_item, lambda_inh):
diff = abs( pos_candidate - pos_item )
return exp( - diff / lambda_inh )
def clear(self):
self.session = -1
self.session_items = []
self.relevant_sessions = set()
self.session_item_map = dict()
self.item_session_map = dict()
self.session_time = dict()
self.session_user_map = dict() # user_based
def support_users(self):
'''
whether it is a session-based or session-aware algorithm
(if returns True, method "predict_with_training_data" must be defined as well)
Parameters
--------
Returns
--------
True : if it is session-aware
False : if it is session-based
'''
return True
def predict_with_training_data(self):
'''
(this method must be defined if "support_users is True")
whether it also needs to make prediction for training data or not (should we concatenate training and test data for making predictions)
Parameters
--------
Returns
--------
True : e.g. hgru4rec
False : e.g. uvsknn
'''
return False
def extend_session_in_fit(self, row, index_user, index_item):
if not row[index_user] in self.last_user_items:
# create a new list to save the user's last viewed items
self.last_user_items[row[index_user]] = []
self.last_user_items[row[index_user]].append(row[index_item])
if len(self.last_user_items[row[index_user]]) > self.extend_session_length:
self.last_user_items[row[index_user]] = self.last_user_items[row[index_user]][
-self.extend_session_length:]
def extend_session_in_predict_next(self, items, input_user_id):
if len(items) < self.extend_session_length:
# update the session with items from the users past
n = len(self.session_items)
addItems = self.extend_session_length - n
prev_items = self.last_user_items[input_user_id][-addItems:]
items = prev_items + self.session_items
# if it is beginning of the session => find relevant sessions for added items
if len(self.items_previous) == 0:
for item in set(prev_items):
self.relevant_sessions = self.relevant_sessions | self.sessions_for_item(item)
# not beginning of the session, so we already retrieved neighbours for the extended session
elif self.refine_mode:
# if the first item that was in the previous step, is not in the current step anymore => refine the self.relevant_sessions
if not self.items_previous[0] in items:
self.relevant_sessions = set()
for item in set(items):
self.relevant_sessions = self.relevant_sessions | self.sessions_for_item(item)
# update self.items_previous
self.items_previous = items
# the session is long enough => refine the self.relevant_sessions to just consider current session's items
elif self.refine_mode and self.need_refine:
self.relevant_sessions = set()
for item in set(self.session_items):
# then we can continue with just adding related sessions for the current item
self.relevant_sessions = self.relevant_sessions | self.sessions_for_item(item)
# refined once after reach to the defined length, no need to do refine anymore
self.need_refine = False
return items
def apply_boost(self, session, user_id, similarity):
if self.boost_own_sessions > 0.0 and self.session_user_map[session] == user_id:
similarity = similarity + (similarity * self.boost_own_sessions)
return similarity
class UNARM:
'''
Code based on work by Li et al., Neural Attentive Session-based Recommendation, CIKM 2017.
NARM(factors=100, session_key='SessionId', item_key='ItemId')
Popularity predictor that gives higher scores to items with larger support.
The score is given by:
.. math::
r_{i}=\\frac{supp_i}{(1+supp_i)}
Parameters
--------
top_n : int
Only give back non-zero scores to the top N ranking items. Should be higher or equal than the cut-off of your evaluation. (Default value: 100)
item_key : string
The header of the item IDs in the training data. (Default value: 'ItemId')
support_by_key : string or None
If not None, count the number of unique values of the attribute of the training data given by the specified header. If None, count the events. (Default value: None)
'''
def __init__(self,
factors=100,
hidden_units=100,
epochs=30,
lr=0.001,
extend_session_length=None,
reminders=False,
remind_strategy='recency',
remind_sessions_num=6,
reminders_num=3,
remind_mode='end',
weight_base=1,
weight_IRec=0,
session_key='SessionId',
item_key='ItemId',
time_key='Time',
user_key='UserId'):
self.factors = factors
self.hidden_units = hidden_units
self.factors = factors
self.epochs = epochs
self.lr = lr
self.session_key = session_key
self.item_key = item_key
self.session = -1
self.session_items = list()
self.floatX = theano.config.floatX
# user_based
self.time_key = time_key
self.user_key = user_key
self.extend_session_length = extend_session_length
self.last_user_items = {}
self.recent_user_items = {}
self.recent_user_sessions = {}
self.hasReminders = reminders
self.hasReminders = reminders
if self.hasReminders:
if remind_strategy == 'hybrid':
self.reminder = Reminder(
remind_strategy=remind_strategy,
remind_sessions_num=remind_sessions_num,
weight_base=weight_base,
weight_IRec=weight_IRec)
else: # basic reminders
self.reminder = Reminder(
remind_strategy=remind_strategy,
remind_sessions_num=remind_sessions_num,
reminders_num=reminders_num,
remind_mode=remind_mode)
def fit(self, data, test=None):
'''
Trains the predictor.
Parameters
--------
data: pandas.DataFrame
Training data. It contains the transactions of the sessions. It has one column for session IDs, one for item IDs and one for the timestamp of the events (unix timestamps).
It must have a header. Column names are arbitrary, but must correspond to the ones you set during the initialization of the network (session_key, item_key, time_key properties).
'''
nis = data[self.item_key].nunique()
self.itemmap = pd.Series(index=data[self.item_key].unique(),
data=range(1, nis + 1))
data = data.merge(self.itemmap.to_frame('ItemIdx'),
how='inner',
right_index=True,
left_on=self.item_key)
data.sort_values(['SessionId', 'Time'], inplace=True)
self.traindata = self.create_training_data(data)
self.dataload = (self.load_data, self.prepare_data)
self.layers = {'gru': (self.param_init_gru, self.gru_layer)}
self.train_gru(self.factors,
self.hidden_units,
max_epochs=self.epochs,
lrate=self.lr,
n_items=nis + 1)
def train_gru(
self,
dim_proj=50, # embeding dimension
hidden_units=100, # GRU number of hidden units.
patience=5, # Number of epoch to wait before early stop if no progress
max_epochs=30, # The maximum number of epoch to run
dispFreq=10000, # Display to stdout the training progress every N updates
lrate=0.001, # Learning rate
n_items=37484, # Vocabulary size
encoder='gru', # TODO: can be removed must be gru.
saveto='gru_model.npz', # The best model will be saved there
is_valid=True, # Compute the validation error after this number of update.
is_save=False, # Save the parameters after every saveFreq updates
batch_size=512, # The batch size during training.
valid_batch_size=512, # The batch size used for validation/test set.
# Parameter for extra option
use_dropout=True, # if False slightly faster, but worst test error
# This frequently need a bigger model.
reload_model=None, # Path to a saved model we want to start from.
test_size=-1, # If >0, we keep only this number of test example.
):
# Model options
model_options = locals().copy()
print("model options", model_options)
load_data, prepare_data = self.get_dataset()
print('Loading data')
train, valid = load_data()
print('Building model')
# This create the initial parameters as numpy ndarrays.
# Dict name (string) -> numpy ndarray
params = self.init_params(model_options)
if reload_model:
self.load_params('gru_model.npz', params)
# This create Theano Shared Variable from the parameters.
# Dict name (string) -> Theano Tensor Shared Variable
# params and tparams have different copy of the weights.
tparams = self.init_tparams(params)
# use_noise is for dropout
(use_noise, x, mask, y, f_pred_prob,
cost) = self.build_model(tparams, model_options)
self.pred_function = f_pred_prob
all_params = list(tparams.values())
updates = self.adam(cost, all_params, lrate)
train_function = theano.function(inputs=[x, mask, y],
outputs=cost,
updates=updates)
print('Optimization')
print("%d train examples" % len(train[0]))
print("%d valid examples" % len(valid[0]))
history_errs = []
history_vali = []
best_p = None
bad_count = 0
uidx = 0 # the number of update done
estop = False # early stop
try:
for eidx in range(max_epochs):
start_time = time.time()
n_samples = 0
epoch_loss = []
# Get new shuffled index for the training set.
kf = self.get_minibatches_idx(len(train[0]),
batch_size,
shuffle=True)
kf_valid = self.get_minibatches_idx(len(valid[0]),
valid_batch_size,
shuffle=True)
for _, train_index in kf:
uidx += 1
use_noise.set_value(1.)
# Select the random examples for this minibatch
y = [train[1][t] for t in train_index]
x = [train[0][t] for t in train_index]
# Get the data in numpy.ndarray format
# This swap the axis!
# Return something of shape (minibatch maxlen, n samples)
x, mask, y = prepare_data(x, y)
n_samples += x.shape[1]
loss = train_function(x, mask, y)
epoch_loss.append(loss)
if np.isnan(loss) or np.isinf(loss):
print('bad loss detected: ', loss)
return 1., 1., 1.
if np.mod(uidx, dispFreq) == 0:
print('Epoch ', eidx, 'Update ', uidx, 'Loss ',
np.mean(epoch_loss))
if saveto and is_save:
print('Saving...')
if best_p is not None:
params = best_p
else:
params = self.unzip(tparams)
np.savez(saveto, history_errs=history_errs, **params)
print('Saving done')
if is_valid:
use_noise.set_value(0.)
valid_evaluation = self.pred_evaluation(
f_pred_prob, prepare_data, valid, kf_valid)
history_errs.append([valid_evaluation])
if best_p is None or valid_evaluation[1] >= np.array(
history_vali).max():
best_p = self.unzip(tparams)
print('Best perfomance updated!')
bad_count = 0
print('Valid Recall@20:', valid_evaluation[0],
' Valid Mrr@20:', valid_evaluation[1])
if len(history_vali) > 10 and valid_evaluation[
1] <= np.array(history_vali).max():
bad_count += 1
print('===========================>Bad counter: ' +
str(bad_count))
print('current validation mrr: ' +
str(valid_evaluation[1]) +
' history max mrr:' +
str(np.array(history_vali).max()))
if bad_count > patience:
print('Early Stop!')
estop = True
history_vali.append(valid_evaluation[1])
end_time = time.time()
print('Seen %d samples' % n_samples)
print(('This epoch took %.1fs' % (end_time - start_time)),
file=sys.stderr)
if estop:
break
except KeyboardInterrupt:
print("Training interupted")
if best_p is not None:
self.zipp(best_p, tparams)
else:
best_p = self.unzip(tparams)
use_noise.set_value(0.)
valid_evaluation = self.pred_evaluation(f_pred_prob, prepare_data,
valid, kf_valid)
print('=================Best performance=================')
print('Valid Recall@20:', valid_evaluation[0], ' Valid Mrr@20:',
valid_evaluation[1])
print('==================================================')
if saveto and is_save:
np.savez('Best_performance',
valid_evaluation=valid_evaluation,
history_errs=history_errs,
**best_p)
self.params = params
self.tparams = tparams
return valid_evaluation
def create_training_data(self, data):
index_session = data.columns.get_loc(self.session_key)
index_item = data.columns.get_loc('ItemIdx')
index_item_original = data.columns.get_loc('ItemId')
index_user = data.columns.get_loc('UserId')
out_seqs = []
labs = []
session = -1
session_items = []
for row in data.itertuples(index=False):
# add last viewed items (by the user) to the last_user_items dictionary
if self.extend_session_length is not None: # user_based
self.extend_session_model_in_loop(row, index_user,
index_item_original)
# reminders
if self.hasReminders: # user_based # for 'session_similarity' or 'recency'
self.reminder.reminders_fit_in_loop(row, index_user,
index_session,
index_item_original)
# cache items of sessions
if row[index_session] != session:
session = row[index_session]
session_items = list()
session_items.append(row[index_item])
if len(session_items) > 1:
out_seqs += [session_items[:-1]]
labs += [session_items[-1]]
# reminders
if self.hasReminders: # user_based
self.reminder.reminders_fit(data, self.user_key, self.item_key,
self.time_key)
return out_seqs, labs
def prepare_data(self, seqs, labels):
"""Create the matrices from the datasets.
This pad each sequence to the same lenght: the lenght of the
longuest sequence or maxlen.
if maxlen is set, we will cut all sequence to this maximum
lenght.
This swap the axis!
"""
# x: a list of sentences
lengths = [len(s) for s in seqs]
n_samples = len(seqs)
maxlen = np.max(lengths)
x = np.zeros((maxlen, n_samples)).astype('int64')
x_mask = np.ones((maxlen, n_samples)).astype(self.floatX)
for idx, s in enumerate(seqs):
x[:lengths[idx], idx] = s
x_mask *= (1 - (x == 0))
return x, x_mask, labels
def load_data(self, valid_portion=0.1, maxlen=19, sort_by_len=False):
'''Loads the dataset
:type path: String
:param path: The path to the dataset (here RSC2015)
:type n_items: int
:param n_items: The number of items.
:type valid_portion: float
:param valid_portion: The proportion of the full train set used for
the validation set.
:type maxlen: None or positive int
:param maxlen: the max sequence length we use in the train/valid set.
:type sort_by_len: bool
:name sort_by_len: Sort by the sequence lenght for the train,
valid and test set. This allow faster execution as it cause
less padding per minibatch. Another mechanism must be used to
shuffle the train set at each epoch.
'''
#############
# LOAD DATA #
#############
train_set = self.traindata
if maxlen:
new_train_set_x = []
new_train_set_y = []
for x, y in zip(train_set[0], train_set[1]):
if len(x) < maxlen:
new_train_set_x.append(x)
new_train_set_y.append(y)
else:
new_train_set_x.append(x[:maxlen])
new_train_set_y.append(y)
train_set = (new_train_set_x, new_train_set_y)
del new_train_set_x, new_train_set_y
# split training set into validation set
train_set_x, train_set_y = train_set
n_samples = len(train_set_x)
sidx = np.arange(n_samples, dtype='int32')
np.random.shuffle(sidx)
n_train = int(np.round(n_samples * (1. - valid_portion)))
valid_set_x = [train_set_x[s] for s in sidx[n_train:]]
valid_set_y = [train_set_y[s] for s in sidx[n_train:]]
train_set_x = [train_set_x[s] for s in sidx[:n_train]]
train_set_y = [train_set_y[s] for s in sidx[:n_train]]
train_set = (train_set_x, train_set_y)
valid_set = (valid_set_x, valid_set_y)
valid_set_x, valid_set_y = valid_set
train_set_x, train_set_y = train_set
def len_argsort(seq):
return sorted(range(len(seq)), key=lambda x: len(seq[x]))
if sort_by_len:
sorted_index = len_argsort(valid_set_x)
valid_set_x = [valid_set_x[i] for i in sorted_index]
valid_set_y = [valid_set_y[i] for i in sorted_index]
train = (train_set_x, train_set_y)
valid = (valid_set_x, valid_set_y)
return train, valid
def get_minibatches_idx(self, n, minibatch_size, shuffle=False):
"""
Used to shuffle the dataset at each iteration.
"""
idx_list = np.arange(n, dtype="int32")
if shuffle:
np.random.shuffle(idx_list)
minibatches = []
minibatch_start = 0
for i in range(n // minibatch_size):
minibatches.append(idx_list[minibatch_start:minibatch_start +
minibatch_size])
minibatch_start += minibatch_size
if minibatch_start != n:
# Make a minibatch out of what is left
minibatches.append(idx_list[minibatch_start:])
return zip(range(len(minibatches)), minibatches)
def get_dataset(self):
return self.dataload[0], self.dataload[1]
def predict_next(self,
session_id,
input_item_id,
input_user_id,
predict_for_item_ids,
timestamp=0,
skip=False,
mode_type='view'):
'''
Gives predicton scores for a selected set of items on how likely they be the next item in the session.
Parameters
--------
session_id : int or string
The session IDs of the event.
input_item_id : int or string
The item ID of the event.
predict_for_item_ids : 1D array
IDs of items for which the network should give prediction scores. Every ID must be in the set of item IDs of the training set.
Returns
--------
out : pandas.Series
Prediction scores for selected items on how likely to be the next item of this session. Indexed by the item IDs.
'''
if (self.session != session_id): #new session
self.session = session_id
self.session_items = list()
if mode_type == 'view':
self.session_items.append(input_item_id)
if skip:
return
x = [self.itemmap[self.session_items].values]
y = x
x, mask, y = self.prepare_data(x, y)
preds = self.pred_function(x, mask)
series = pd.Series(data=preds[0][1:], index=self.itemmap.index)
if self.hasReminders: # user_based
if self.reminder.remind_strategy == 'hybrid':
series = self.reminder.reminders_predict_next(
input_user_id,
series,
self.item_key,
self.time_key,
input_timestamp=timestamp)
else: # basic reminders
series = self.reminder.reminders_predict_next(
input_user_id, series, self.item_key, self.time_key)
return series
def zipp(self, params, tparams):
"""
When we reload the model. Needed for the GPU stuff.
"""
for kk, vv in params.items():
tparams[kk].set_value(vv)
def unzip(self, zipped):
"""
When we pickle the model. Needed for the GPU stuff.
"""
new_params = OrderedDict()
for kk, vv in zipped.items():
new_params[kk] = vv.get_value()
return new_params
def dropout_layer(self, state_before, use_noise, trng, drop_p=0.5):
retain = 1. - drop_p
proj = T.switch(use_noise, (state_before * trng.binomial(
state_before.shape, p=retain, n=1, dtype=state_before.dtype)),
state_before * retain)
return proj
def _p(self, pp, name):
return '%s_%s' % (pp, name)
def init_params(self, options):
"""
Global (not GRU) parameter. For the embeding and the classifier.
"""
params = OrderedDict()
# embedding
params['Wemb'] = self.init_weights(
(options['n_items'], options['dim_proj']))
params = self.get_layer(options['encoder'])[0](
options, params, prefix=options['encoder'])
# attention
params['W_encoder'] = self.init_weights(
(options['hidden_units'], options['hidden_units']))
params['W_decoder'] = self.init_weights(
(options['hidden_units'], options['hidden_units']))
params['bl_vector'] = self.init_weights((1, options['hidden_units']))
# classifier
# params['U'] = init_weights((2*options['hidden_units'], options['n_items']))
# params['b'] = np.zeros((options['n_items'],)).astype(config.floatX)
params['bili'] = self.init_weights(
(options['dim_proj'], 2 * options['hidden_units']))
return params
def load_params(self, path, params):
pp = np.load(path)
for kk, vv in params.items():
if kk not in pp:
raise Warning('%s is not in the archive' % kk)
params[kk] = pp[kk]
return params
def init_tparams(self, params):
tparams = OrderedDict()
for kk, pp in params.items():
tparams[kk] = theano.shared(params[kk], name=kk)
return tparams
def get_layer(self, name):
fns = self.layers[name]
return fns
def init_weights(self, shape):
sigma = np.sqrt(2. / shape[0])
return self.numpy_floatX(np.random.randn(*shape) * sigma)
def ortho_weight(self, ndim):
W = np.random.randn(ndim, ndim)
u, s, v = np.linalg.svd(W)
return u.astype(self.floatX)
def param_init_gru(self, options, params, prefix='gru'):
"""
Init the GRU parameter:
:see: init_params
"""
Wxrz = np.concatenate([
self.init_weights((options['dim_proj'], options['hidden_units'])),
self.init_weights((options['dim_proj'], options['hidden_units'])),
self.init_weights((options['dim_proj'], options['hidden_units']))
],
axis=1)
params[self._p(prefix, 'Wxrz')] = Wxrz
Urz = np.concatenate([
self.ortho_weight(options['hidden_units']),
self.ortho_weight(options['hidden_units'])
],
axis=1)
params[self._p(prefix, 'Urz')] = Urz
Uh = self.ortho_weight(options['hidden_units'])
params[self._p(prefix, 'Uh')] = Uh
b = np.zeros((3 * options['hidden_units'], ))
params[self._p(prefix, 'b')] = b.astype(self.floatX)
return params
def gru_layer(self,
tparams,
state_below,
options,
prefix='gru',
mask=None):
nsteps = state_below.shape[0]
if state_below.ndim == 3:
n_samples = state_below.shape[1]
else:
n_samples = 1
assert mask is not None
def _slice(_x, n, dim):
if _x.ndim == 3:
return _x[:, :, n * dim:(n + 1) * dim]
return _x[:, n * dim:(n + 1) * dim]
def _step(m_, x_, h_):
preact = T.dot(h_, tparams[self._p(prefix, 'Urz')])
preact += x_[:, 0:2 * options['hidden_units']]
z = T.nnet.hard_sigmoid(_slice(preact, 0, options['hidden_units']))
r = T.nnet.hard_sigmoid(_slice(preact, 1, options['hidden_units']))
h = T.tanh(
T.dot((h_ * r), tparams[self._p(prefix, 'Uh')]) +
_slice(x_, 2, options['hidden_units']))
h = (1.0 - z) * h_ + z * h
h = m_[:, None] * h + (1. - m_)[:, None] * h_
return h
state_below = (T.dot(state_below, tparams[self._p(prefix, 'Wxrz')]) +
tparams[self._p(prefix, 'b')])
hidden_units = options['hidden_units']
rval, updates = theano.scan(_step,
sequences=[mask, state_below],
outputs_info=T.alloc(
self.numpy_floatX(0.), n_samples,
hidden_units),
name=self._p(prefix, '_layers'),
n_steps=nsteps)
return rval
def adam(self,
loss,
all_params,
learning_rate=0.001,
b1=0.9,
b2=0.999,
e=1e-8,
gamma=1 - 1e-8):
"""
ADAM update rules
Default values are taken from [Kingma2014]
References:
[Kingma2014] Kingma, Diederik, and Jimmy Ba.
"Adam: A Method for Stochastic Optimization."
arXiv preprint arXiv:1412.6980 (2014).
http://arxiv.org/pdf/1412.6980v4.pdf
"""
updates = OrderedDict()
all_grads = theano.grad(loss, all_params)
alpha = learning_rate
t = theano.shared(np.float32(1).astype(self.floatX))
b1_t = b1 * gamma**(
t - 1) #(Decay the first moment running average coefficient)
for theta_previous, g in zip(all_params, all_grads):
m_previous = theano.shared(
np.zeros(theta_previous.get_value().shape, dtype=self.floatX))
v_previous = theano.shared(
np.zeros(theta_previous.get_value().shape, dtype=self.floatX))
m = b1_t * m_previous + (
1 - b1_t) * g # (Update biased first moment estimate)
v = b2 * v_previous + (
1 - b2) * g**2 # (Update biased second raw moment estimate)
m_hat = m / (1 - b1**t
) # (Compute bias-corrected first moment estimate)
v_hat = v / (
1 - b2**t
) # (Compute bias-corrected second raw moment estimate)
theta = theta_previous - (alpha * m_hat) / (T.sqrt(v_hat) + e
) #(Update parameters)
updates[m_previous] = m
updates[v_previous] = v
updates[theta_previous] = theta
updates[t] = t + 1.
return updates
def build_model(self, tparams, options):
trng = RandomStreams(SEED)
# Used for dropout.
use_noise = theano.shared(self.numpy_floatX(0.))
x = T.matrix('x', dtype='int64')
mask = T.matrix('mask', dtype=self.floatX)
y = T.vector('y', dtype='int64')
n_timesteps = x.shape[0]
n_samples = x.shape[1]
emb = tparams['Wemb'][x.flatten()].reshape(
[n_timesteps, n_samples, options['dim_proj']])
if options['use_dropout']:
emb = self.dropout_layer(emb, use_noise, trng, drop_p=0.25)
proj = self.get_layer(options['encoder'])[1](tparams,
emb,
options,
prefix=options['encoder'],
mask=mask)
def compute_alpha(state1, state2):
tmp = T.nnet.hard_sigmoid(
T.dot(tparams['W_encoder'], state1.T) +
T.dot(tparams['W_decoder'], state2.T))
alpha = T.dot(tparams['bl_vector'], tmp)
res = T.sum(alpha, axis=0)
return res
last_h = proj[-1]
sim_matrix, _ = theano.scan(fn=compute_alpha,
sequences=proj,
non_sequences=proj[-1])
att = T.nnet.softmax(sim_matrix.T * mask.T) * mask.T
p = att.sum(axis=1)[:, None]
weight = att / p
atttention_proj = (proj * weight.T[:, :, None]).sum(axis=0)
proj = T.concatenate([atttention_proj, last_h], axis=1)
if options['use_dropout']:
proj = self.dropout_layer(proj, use_noise, trng, drop_p=0.5)
ytem = T.dot(tparams['Wemb'], tparams['bili'])
pred = T.nnet.softmax(T.dot(proj, ytem.T))
# pred = T.nnet.softmax(T.dot(proj, tparams['U']) + tparams['b'])
f_pred_prob = theano.function([x, mask], pred, name='f_pred_prob')
# f_weight = theano.function([x, mask], weight, name='f_weight')
off = 1e-8
if pred.dtype == 'float16':
off = 1e-6
cost = -T.log(pred[T.arange(n_samples), y] + off).mean()
return use_noise, x, mask, y, f_pred_prob, cost
def pred_evaluation(self, f_pred_prob, prepare_data, data, iterator):
"""
Compute recall@20 and mrr@20
f_pred_prob: Theano fct computing the prediction
prepare_data: usual prepare_data for that dataset.
"""
recall = 0.0
mrr = 0.0
evalutation_point_count = 0
# pred_res = []
# att = []
for _, valid_index in iterator:
x, mask, y = prepare_data([data[0][t] for t in valid_index],
np.array(data[1])[valid_index])
preds = f_pred_prob(x, mask)
# weights = f_weight(x, mask)
targets = y
ranks = (preds.T > np.diag(preds.T[targets])).sum(axis=0) + 1
rank_ok = (ranks <= 20)
# pred_res += list(rank_ok)
recall += rank_ok.sum()
mrr += (1.0 / ranks[rank_ok]).sum()
evalutation_point_count += len(ranks)
# att.append(weights)
recall = self.numpy_floatX(recall) / evalutation_point_count
mrr = self.numpy_floatX(mrr) / evalutation_point_count
eval_score = (recall, mrr)
# ff = open('/storage/lijing/mydataset/res_attention_correct.pkl', 'wb')
# pickle.dump(pred_res, ff)
# ff.close()
# ff2 = open('/storage/lijing/mydataset/attention_weights.pkl', 'wb')
# pickle.dump(att, ff2)
# ff2.close()
return eval_score
def numpy_floatX(self, data):
return np.asarray(data, dtype=self.floatX)
def clear(self):
if hasattr(self, 'tparams'):
for kk, vv in self.tparams.items():
if len(self.params[kk].shape) == 1:
self.tparams[kk].set_value([])
else:
self.tparams[kk].set_value([[]])
def support_users(self):
'''
whether it is a session-based or session-aware algorithm
(if returns True, method "predict_with_training_data" must be defined as well)
Parameters
--------
Returns
--------
True : if it is session-aware
False : if it is session-based
'''
return True
def predict_with_training_data(self):
'''
(this method must be defined if "support_users is True")
whether it also needs to make prediction for training data or not (should we concatenate training and test data for making predictions)
Parameters
--------
Returns
--------
True : e.g. hgru4rec
False : e.g. uvsknn
'''
return False
def extend_session_model_in_loop(self, row, index_user, index_item):
if not row[index_user] in self.last_user_items:
self.last_user_items[row[index_user]] = [
] # create a new list to save the user's last viewed items
self.last_user_items[row[index_user]].append(row[index_item])
if len(self.last_user_items[
row[index_user]]) > self.extend_session_length:
self.last_user_items[row[index_user]] = self.last_user_items[
row[index_user]][-self.extend_session_length:]
def predict_for_extended_model(
self, input_user_id
): # will be called in "evaluation_user_based" and "evaluation_user_based_multiple"
prev_items = []
# we add extra items form the user profile at the begening of the session
self.session_items = list()
if self.extend_session_length is not None and input_user_id in self.last_user_items: # user_based
prev_items = self.last_user_items[input_user_id]
return prev_items
class UVMContextKNN:
'''
VMContextKNN( k, sample_size=1000, sampling='recent', similarity='cosine', weighting='div', dwelling_time=False, last_n_days=None, last_n_clicks=None, extend=False, weighting_score='div_score', weighting_time=False, normalize=True, session_key = 'SessionId', item_key= 'ItemId', time_key= 'Time')
Parameters
-----------
k : int
Number of neighboring session to calculate the item scores from. (Default value: 100)
sample_size : int
Defines the length of a subset of all training sessions to calculate the nearest neighbors from. (Default value: 500)
sampling : string
String to define the sampling method for sessions (recent, random). (default: recent)
similarity : string
String to define the method for the similarity calculation (jaccard, cosine, binary, tanimoto). (default: jaccard)
weighting : string
Decay function to determine the importance/weight of individual actions in the current session (linear, same, div, log, quadratic). (default: div)
weighting_score : string
Decay function to lower the score of candidate items from a neighboring sessions that were selected by less recently clicked items in the current session. (linear, same, div, log, quadratic). (default: div_score)
weighting_time : boolean
Experimental function to give less weight to items from older sessions (default: False)
dwelling_time : boolean
Experimental function to use the dwelling time for item view actions as a weight in the similarity calculation. (default: False)
last_n_days : int
Use only data from the last N days. (default: None)
last_n_clicks : int
Use only the last N clicks of the current session when recommending. (default: None)
extend : bool
Add evaluated sessions to the maps.
normalize : bool
Normalize the scores in the end.
session_key : string
Header of the session ID column in the input file. (default: 'SessionId')
item_key : string
Header of the item ID column in the input file. (default: 'ItemId')
time_key : string
Header of the timestamp column in the input file. (default: 'Time')
user_key : string
Header of the user ID column in the input file. (default: 'UserId')
extend_session_length: int
extend the current user's session
extending_mode: string
how extend the user session (default: lastViewed)
lastViewed: extend the current user's session with the his/her last viewed items #TODO: now it saves just X last items, and they might be exactly the same: can try as well: save 5 distinctive items
score_based: higher score: if the items appeared in more previous sessions AND more recently #TODO
boost_own_sessions: double
to increase the impact of (give weight more weight to) the sessions which belong to the user. (default: None)
the value will be added to 1.0. For example for boost_own_sessions=0.2, weight will be 1.2
past_neighbors: bool
Include the neighbours of the past user's similar sessions (to the current session) as neighbours (default: False)
reminders: bool
Include reminding items in the (main) recommendation list. (default: False)
remind_strategy: string
Ranking strategy of the reminding list (recency, session_similarity). (default: recency)
remind_sessions_num: int
Number of the last user's sessions that the possible items for reminding are taken from (default: 6)
reminders_num: int
length of the reminding list (default: 3)
remind_mode: string
The postion of the remining items in recommendation list (top, end). (default: end)
'''
def __init__(self,
k,
sample_size=1000,
sampling='recent',
similarity='cosine',
weighting='div',
dwelling_time=False,
last_n_days=None,
last_n_clicks=None,
weighting_score='div',
weighting_time=False,
normalize=True,
idf_weighting=False,
idf_weighting_session=False,
remind=True,
push_reminders=False,
add_reminders=False,
extend=False,
extending_mode='lastViewed',
extend_session_length=None,
refine_mode=True,
boost_own_sessions=None,
past_neighbors=False,
reminders=False,
remind_strategy='recency',
remind_sessions_num=6,
reminders_num=3,
remind_mode='end',
weight_base=1,
weight_IRec=0,
weight_SSim=0,
session_key='SessionId',
item_key='ItemId',
time_key='Time',
user_key='UserId'):
self.k = k
self.sample_size = sample_size
self.sampling = sampling
self.weighting = weighting
self.dwelling_time = dwelling_time
self.weighting_score = weighting_score
self.weighting_time = weighting_time
self.similarity = similarity
self.session_key = session_key
self.item_key = item_key
self.time_key = time_key
self.user_key = user_key # user_based
self.idf_weighting = idf_weighting
self.idf_weighting_session = idf_weighting_session
self.normalize = normalize
self.last_n_days = last_n_days
self.last_n_clicks = last_n_clicks
self.remind = remind # True/False. If False: items form the current session will be excluded
self.push_reminders = push_reminders
self.add_reminders = add_reminders
self.extend = extend
self.extending_mode = extending_mode
# user_based
self.extend_session_length = extend_session_length
self.boost_own_sessions = boost_own_sessions
self.past_neighbors = past_neighbors
self.refine_mode = refine_mode
# reminders
self.hasReminders = reminders
if self.hasReminders:
if remind_strategy == 'hybrid':
self.reminder = Reminder(
remind_strategy=remind_strategy,
remind_sessions_num=remind_sessions_num,
weight_base=weight_base,
weight_IRec=weight_IRec,
weight_SSim=weight_SSim)
else: # basic reminders
self.reminder = Reminder(
remind_strategy=remind_strategy,
remind_sessions_num=remind_sessions_num,
reminders_num=reminders_num,
remind_mode=remind_mode)
# updated while recommending
self.session = -1
self.session_items = []
self.relevant_sessions = set()
# user_based
self.items_previous = []
self.last_user_items = {} # to extend the session model
self.recent_user_items = {} # to remind
self.recent_user_sessions = {} # to remind
self.user_item_intensity = dict(
) # to remind (for 'session_similarity')
# cache relations once at startup (in fit)
self.session_item_map = dict()
self.item_session_map = dict()
self.session_time = dict()
self.min_time = -1
self.session_user_map = dict() # user_based
self.sim_time = 0
def fit(self, data, items=None):
'''
Trains the predictor.
Parameters
--------
data: pandas.DataFrame
Training data. It contains the transactions of the sessions. It has one column for session IDs, one for item IDs and one for the timestamp of the events (unix timestamps).
It must have a header. Column names are arbitrary, but must correspond to the ones you set during the initialization of the network (session_key, item_key, time_key properties).
'''
if self.last_n_days != None:
max_time = dt.fromtimestamp(data[self.time_key].max())
date_threshold = max_time.date() - td(self.last_n_days)
stamp = dt.combine(date_threshold, dt.min.time()).timestamp()
train = data[data[self.time_key] >= stamp]
else:
train = data
self.num_items = train[self.item_key].max()
# get the position of the columns
index_session = train.columns.get_loc(self.session_key)
index_item = train.columns.get_loc(self.item_key)
index_time = train.columns.get_loc(self.time_key)
index_user = train.columns.get_loc(self.user_key) # user_based
session = -1
session_items = set()
time = -1
user = -1 # user_based
# cnt = 0
prev_s_id = -1
for row in train.itertuples(index=False):
# cache items of sessions
if row[index_session] != session:
if len(session_items) > 0:
self.session_item_map.update({session: session_items})
# cache the last time stamp of the session
self.session_time.update({session: time})
self.session_user_map.update({session: user}) # user_based
if time < self.min_time:
self.min_time = time
user = row[index_user] # user_based
session = row[index_session]
session_items = set()
time = row[index_time]
session_items.add(row[index_item])
# cache sessions involving an item
map_is = self.item_session_map.get(row[index_item])
if map_is is None:
map_is = set()
self.item_session_map.update({row[index_item]: map_is})
map_is.add(row[index_session])
# add last viewed items (by the user) to the last_user_items dictionary
if self.extend_session_length is not None: # user_based
self.extend_session_in_fit(row, index_user, index_item)
# reminders
if self.hasReminders: # user_based # for 'session_similarity' or 'recency'
self.reminder.reminders_fit_in_loop(row, index_user,
index_session, index_item)
# reminders # save item_intensity in the last N session for each user
if self.hasReminders: # user_based
self.reminder.reminders_fit(train, self.user_key, self.item_key,
self.time_key)
# Add the last tuple
self.session_item_map.update({session: session_items})
self.session_time.update({session: time})
self.session_user_map.update({session: user}) # user_based
if self.idf_weighting or self.idf_weighting_session:
self.idf = pd.DataFrame()
self.idf['idf'] = train.groupby(self.item_key).size()
self.idf['idf'] = np.log(train[self.session_key].nunique() /
self.idf['idf'])
self.idf = self.idf['idf'].to_dict()
def predict_next(self,
session_id,
input_item_id,
input_user_id,
predict_for_item_ids=None,
skip=False,
mode_type='view',
timestamp=0):
'''
Gives predicton scores for a selected set of items on how likely they be the next item in the session.
Parameters
--------
session_id : int or string
The session IDs of the event.
input_item_id : int or string
The item ID of the event. Must be in the set of item IDs of the training set.
predict_for_item_ids : 1D array
IDs of items for which the network should give prediction scores. Every ID must be in the set of item IDs of the training set.
Returns
--------
out : pandas.Series
Prediction scores for selected items on how likely to be the next item of this session. Indexed by the item IDs.
'''
# gc.collect()
# process = psutil.Process(os.getpid())
# print( 'cknn.predict_next: ', process.memory_info().rss, ' memory used')
if (self.session != session_id): # new session
if (self.extend): # add evaluated sessions to the maps.
item_set = set(self.session_items)
self.session_item_map[self.session] = item_set
for item in item_set:
map_is = self.item_session_map.get(item)
if map_is is None:
map_is = set()
self.item_session_map.update({item: map_is})
map_is.add(self.session)
ts = time.time()
self.session_time.update({self.session: ts})
self.session_user_map.update({self.session:
input_user_id}) # user_based
self.last_ts = -1
self.session = session_id
self.session_items = list()
self.dwelling_times = list()
self.relevant_sessions = set()
self.items_previous = [] # user_based
self.need_refine = True # user_based
if mode_type == 'view':
self.session_items.append(input_item_id)
if self.dwelling_time:
if self.last_ts > 0:
self.dwelling_times.append(timestamp - self.last_ts)
self.last_ts = timestamp
if skip:
return
items = self.session_items if self.last_n_clicks is None else self.session_items[
-self.last_n_clicks:]
# we add extra items form the user profile as long as the session is not long enough!
if self.extend_session_length is not None and input_user_id in self.last_user_items: # user_based
items = self.extend_session_in_predict_next(items, input_user_id)
neighbors = self.find_neighbors(items, input_item_id, session_id,
self.dwelling_times, timestamp,
input_user_id)
scores = self.score_items(neighbors, items, timestamp)
# Create things in the format ..
predictions = np.zeros(len(predict_for_item_ids))
mask = np.in1d(predict_for_item_ids, list(scores.keys()))
predict_for_items = predict_for_item_ids[mask]
values = [scores[x] for x in predict_for_items]
predictions[mask] = values
series = pd.Series(data=predictions, index=predict_for_item_ids)
if self.hasReminders: # user_based
if self.reminder.remind_strategy == 'hybrid':
if self.reminder.w_SSim == 0:
series = self.reminder.reminders_predict_next(
input_user_id,
series,
self.item_key,
self.time_key,
input_timestamp=timestamp)
else:
past_user_sessions = self.calc_similarity(
items,
self.reminder.recent_user_sessions[input_user_id],
self.dwelling_times, timestamp, input_user_id)
series = self.reminder.reminders_predict_next(
input_user_id,
series,
self.item_key,
self.time_key,
past_user_sessions=past_user_sessions,
session_item_map=self.session_item_map,
input_timestamp=timestamp)
else: # basic reminders
if self.reminder.remind_strategy == 'session_similarity':
past_user_sessions = self.calc_similarity(
items,
self.reminder.recent_user_sessions[input_user_id],
self.dwelling_times, timestamp, input_user_id)
series = self.reminder.reminders_predict_next(
input_user_id,
series,
self.item_key,
self.time_key,
past_user_sessions=past_user_sessions,
session_item_map=self.session_item_map)
if self.reminder.remind_strategy == 'recency':
series = self.reminder.reminders_predict_next(
input_user_id, series, self.item_key, self.time_key)
if self.push_reminders: # give more score to the items that belongs to the current session
if self.extend_session_length is not None and self.need_refine:
session_items_series = pd.Series(items)
else:
session_items_series = pd.Series(self.session_items)
session_count = session_items_series.groupby(
session_items_series).count() + 1
# multiply the score of the item in the current session by its number of time in the current session
series[
session_count.
index] *= session_count # TODO: contains the same item several times
if self.add_reminders: # force the last 3 items of the current session to be in the top 20 recommendable items
if self.extend_session_length is not None and self.need_refine:
# scores of the items that are belong to the current session
session_series = pd.Series(index=items, data=series[items])
else:
# scores of the items that are belong to the current session
session_series = pd.Series(index=self.session_items,
data=series[self.session_items])
session_series = session_series[session_series >
0] # keep them if their scores > 0
if len(session_series) > 0:
session_series = session_series.iloc[:
3] # keep the first 3 items
# sort the predictions (sort recommendable items according to their scores)
series.sort_values(ascending=False, inplace=True)
session_series = session_series[session_series <
series.iloc[19 -
3]] # TODO: 19-3
series[session_series.
index] = series.iloc[19 - 3] + 1e-4 # TODO: 1e-4
if self.normalize:
series = series / series.max()
return series
def item_pop(self, sessions):
'''
Returns a dict(item,score) of the item popularity for the given list of sessions (only a set of ids)
Parameters
--------
sessions: set
Returns
--------
out : dict
'''
result = dict()
max_pop = 0
for session, weight in sessions:
items = self.items_for_session(session)
for item in items:
count = result.get(item)
if count is None:
result.update({item: 1})
else:
result.update({item: count + 1})
if (result.get(item) > max_pop):
max_pop = result.get(item)
for key in result:
result.update({key: (result[key] / max_pop)})
return result
def jaccard(self, first, second):
'''
Calculates the jaccard index for two sessions
Parameters
--------
first: Id of a session
second: Id of a session
Returns
--------
out : float value
'''
sc = time.clock()
intersection = len(first & second)
union = len(first | second)
res = intersection / union
self.sim_time += (time.clock() - sc)
return res
def cosine(self, first, second):
'''
Calculates the cosine similarity for two sessions
Parameters
--------
first: Id of a session
second: Id of a session
Returns
--------
out : float value
'''
li = len(first & second)
la = len(first)
lb = len(second)
result = li / sqrt(la) * sqrt(lb)
return result
def tanimoto(self, first, second):
'''
Calculates the cosine tanimoto similarity for two sessions
Parameters
--------
first: Id of a session
second: Id of a session
Returns
--------
out : float value
'''
li = len(first & second)
la = len(first)
lb = len(second)
result = li / (la + lb - li)
return result
def binary(self, first, second):
'''
Calculates the ? for 2 sessions
Parameters
--------
first: Id of a session
second: Id of a session
Returns
--------
out : float value
'''
a = len(first & second)
b = len(first)
c = len(second)
result = (2 * a) / ((2 * a) + b + c)
return result
def vec(self, first, second, map):
'''
Calculates the ? for 2 sessions
Parameters
--------
first: Id of a session
second: Id of a session
Returns
--------
out : float value
'''
a = first & second
sum = 0
for i in a:
sum += map[i]
result = sum / len(map)
return result
def items_for_session(self, session):
'''
Returns all items in the session
Parameters
--------
session: Id of a session
Returns
--------
out : set
'''
return self.session_item_map.get(session)
def vec_for_session(self, session):
'''
Returns all items in the session
Parameters
--------
session: Id of a session
Returns
--------
out : set
'''
return self.session_vec_map.get(session)
def sessions_for_item(self, item_id):
'''
Returns all session for an item
Parameters
--------
item: Id of the item session
Returns
--------
out : set
'''
return self.item_session_map.get(
item_id) if item_id in self.item_session_map else set()
def most_recent_sessions(self, sessions, number):
'''
Find the most recent sessions in the given set
Parameters
--------
sessions: set of session ids
Returns
--------
out : set
'''
sample = set()
tuples = list()
for session in sessions:
time = self.session_time.get(session)
if time is None:
print(' EMPTY TIMESTAMP!! ', session)
tuples.append((session, time))
tuples = sorted(tuples, key=itemgetter(1), reverse=True)
# print 'sorted list ', sortedList
cnt = 0
for element in tuples:
cnt = cnt + 1
if cnt > number:
break
sample.add(element[0])
# print 'returning sample of size ', len(sample)
return sample
def possible_neighbor_sessions(self, session_items, input_item_id,
session_id, user_id):
'''
Find a set of session to later on find neighbors in.
A self.sample_size of 0 uses all sessions in which any item of the current session appears.
self.sampling can be performed with the options "recent" or "random".
"recent" selects the self.sample_size most recent sessions while "random" just choses randomly.
Parameters
--------
sessions: set of session ids
Returns
--------
out : set
'''
# add relevant sessions for the current item
self.relevant_sessions = self.relevant_sessions | self.sessions_for_item(
input_item_id)
if self.past_neighbors: # user-based
self.retrieve_past_neighbors(user_id)
if self.sample_size == 0: # use all session as possible neighbors
print('!!!!! runnig KNN without a sample size (check config)')
possible_neighbors = self.relevant_sessions
else: # sample some sessions
if len(self.relevant_sessions) > self.sample_size:
if self.sampling == 'recent':
sample = self.most_recent_sessions(self.relevant_sessions,
self.sample_size)
elif self.sampling == 'random':
sample = random.sample(self.relevant_sessions,
self.sample_size)
else:
sample = self.relevant_sessions[:self.sample_size]
possible_neighbors = sample
else:
possible_neighbors = self.relevant_sessions
return possible_neighbors
def calc_similarity(self, session_items, sessions, dwelling_times,
timestamp, user_id):
'''
Calculates the configured similarity for the items in session_items and each session in sessions.
Parameters
--------
session_items: set of item ids
sessions: list of session ids
Returns
--------
out : list of tuple (session_id,similarity)
'''
pos_map = {}
length = len(session_items)
count = 1
for item in session_items:
if self.weighting is not None:
pos_map[item] = getattr(self, self.weighting)(count, length)
count += 1
else:
pos_map[item] = 1
if self.dwelling_time:
dt = dwelling_times.copy()
dt.append(0)
dt = pd.Series(dt, index=session_items)
dt = dt / dt.max()
# dt[session_items[-1]] = dt.mean() if len(session_items) > 1 else 1
dt[session_items[-1]] = 1
# print(dt)
for i in range(len(dt)):
pos_map[session_items[i]] *= dt.iloc[i]
# print(pos_map)
if self.idf_weighting_session:
max = -1
for item in session_items:
pos_map[item] = self.idf[item] if item in self.idf else 0
# if pos_map[item] > max:
# max = pos_map[item]
# for item in session_items:
# pos_map[item] = pos_map[item] / max
# print 'nb of sessions to test ', len(sessionsToTest), ' metric: ', self.metric
items = set(session_items)
neighbors = []
cnt = 0
for session in sessions:
cnt = cnt + 1
# get items of the session, look up the cache first
n_items = self.items_for_session(session)
sts = self.session_time[session]
# dot product
similarity = self.vec(items, n_items, pos_map)
if similarity > 0:
if self.weighting_time:
diff = timestamp - sts
days = round(diff / 60 / 60 / 24)
decay = pow(7 / 8, days)
similarity *= decay
# print("days:",days," => ",decay)
if self.boost_own_sessions is not None: # user_based
similarity = self.apply_boost(session, user_id, similarity)
neighbors.append((session, similarity))
return neighbors
# -----------------
# Find a set of neighbors, returns a list of tuples (sessionid: similarity)
# -----------------
def find_neighbors(self, session_items, input_item_id, session_id,
dwelling_times, timestamp, user_id):
'''
Finds the k nearest neighbors for the given session_id and the current item input_item_id.
Parameters
--------
session_items: set of item ids
input_item_id: int
session_id: int
Returns
--------
out : list of tuple (session_id, similarity)
'''
possible_neighbors = self.possible_neighbor_sessions(
session_items, input_item_id, session_id, user_id) # user_based
possible_neighbors = self.calc_similarity(session_items,
possible_neighbors,
dwelling_times, timestamp,
user_id) # user_based
possible_neighbors = sorted(possible_neighbors,
reverse=True,
key=lambda x: x[1])
possible_neighbors = possible_neighbors[:self.k]
return possible_neighbors
def score_items(self, neighbors, current_session, timestamp):
'''
Compute a set of scores for all items given a set of neighbors.
Parameters
--------
neighbors: set of session ids
Returns
--------
out : list of tuple (item, score)
'''
# now we have the set of relevant items to make predictions
scores = dict()
item_set = set(current_session)
# iterate over the sessions
for session in neighbors:
# get the items in this session
items = self.items_for_session(session[0])
step = 1
for item in reversed(current_session):
if item in items:
decay = getattr(self,
self.weighting_score + '_score')(step)
break
step += 1
for item in items:
if not self.remind and item in item_set: # d=0* (exclude items form the current session)
continue # dont want to remind user the item that is already is his current (extended) session
old_score = scores.get(item)
new_score = session[1]
new_score = new_score if not self.idf_weighting else new_score + (
new_score * self.idf[item] * self.idf_weighting)
new_score = new_score * decay
if not old_score is None:
new_score = old_score + new_score
scores.update({item: new_score})
return scores
def linear_score(self, i):
return 1 - (0.1 * i) if i <= 100 else 0
def same_score(self, i):
return 1
def div_score(self, i):
return 1 / i
def log_score(self, i):
return 1 / (log10(i + 1.7))
def quadratic_score(self, i):
return 1 / (i * i)
def linear(self, i, length):
return 1 - (0.1 * (length - i)) if i <= 10 else 0
def same(self, i, length):
return 1
def div(self, i, length):
return i / length
def log(self, i, length):
return 1 / (log10((length - i) + 1.7))
def quadratic(self, i, length):
return (i / length)**2
def clear(self):
self.session = -1
self.session_items = []
self.relevant_sessions = set()
self.session_item_map = dict()
self.item_session_map = dict()
self.session_time = dict()
self.session_user_map = dict() # user_based
def support_users(self):
'''
whether it is a session-based or session-aware algorithm
(if returns True, method "predict_with_training_data" must be defined as well)
Parameters
--------
Returns
--------
True : if it is session-aware
False : if it is session-based
'''
return True
def predict_with_training_data(self):
'''
(this method must be defined if "support_users is True")
whether it also needs to make prediction for training data or not (should we concatenate training and test data for making predictions)
Parameters
--------
Returns
--------
True : e.g. hgru4rec
False : e.g. uvsknn
'''
return False
def extend_session_in_fit(self, row, index_user, index_item):
if not row[index_user] in self.last_user_items:
# create a new list to save the user's last viewed items
self.last_user_items[row[index_user]] = []
self.last_user_items[row[index_user]].append(row[index_item])
if len(self.last_user_items[
row[index_user]]) > self.extend_session_length:
self.last_user_items[row[index_user]] = self.last_user_items[
row[index_user]][-self.extend_session_length:]
def extend_session_in_predict_next(self, items, input_user_id):
if len(items) < self.extend_session_length:
# update the session with items from the users past
n = len(self.session_items)
addItems = self.extend_session_length - n
prev_items = self.last_user_items[input_user_id][-addItems:]
items = prev_items + self.session_items
# if it is beginning of the session => find relevant sessions for added items
if len(self.items_previous) == 0:
for item in set(prev_items):
self.relevant_sessions = self.relevant_sessions | self.sessions_for_item(
item)
# not beginning of the session, so we already retrieved neighbours for the extended session
elif self.refine_mode:
# if the first item that was in the previous step, is not in the current step anymore => refine the self.relevant_sessions
if not self.items_previous[0] in items:
self.relevant_sessions = set()
for item in set(items):
self.relevant_sessions = self.relevant_sessions | self.sessions_for_item(
item)
# update self.items_previous
self.items_previous = items
# the session is long enough => refine the self.relevant_sessions to just consider current session's items
elif self.refine_mode and self.need_refine:
self.relevant_sessions = set()
for item in set(self.session_items):
# then we can continue with just adding related sessions for the current item
self.relevant_sessions = self.relevant_sessions | self.sessions_for_item(
item)
# refined once after reach to the defined length, no need to do refine anymore
self.need_refine = False
return items
def apply_boost(self, session, user_id, similarity):
if self.boost_own_sessions > 0.0 and self.session_user_map[
session] == user_id:
similarity = similarity + (similarity * self.boost_own_sessions)
return similarity
def retrieve_past_neighbors(self, user_id):
for neighbor_sid in self.relevant_sessions:
if self.session_user_map[neighbor_sid] == user_id:
for item in self.items_for_session(neighbor_sid):
self.relevant_sessions = self.relevant_sessions | self.sessions_for_item(
item)
class USequentialRules:
'''
Code based on work by Kamehkhosh et al.,A Comparison of Frequent Pattern Techniques and a Deep Learning Method for Session-Based Recommendation, TempRec Workshop at ACM RecSys 2017.
SequentialRules(steps = 3, weighting='div', pruning=0.0)
Parameters
--------
steps : int
TODO. (Default value: 3)
weighting : string
TODO. (Default value: 3)
pruning : float
TODO. (Default value: 0)
session_key : string
Header of the session ID column in the input file. (default: 'SessionId')
item_key : string
Header of the item ID column in the input file. (default: 'ItemId')
time_key : string
Header of the timestamp column in the input file. (default: 'Time')
user_key : string
Header of the user ID column in the input file. (default: 'UserId')
boost_own_sessions: double
to increase the impact of (give weight more weight to) the sessions which belong to the user. (default: None)
the value will be added to 1.0. For example for boost_own_sessions=0.2, weight will be 1.2
reminders: bool
Include reminding items in the (main) recommendation list. (default: False)
remind_strategy: string
Ranking strategy of the reminding list (default: recency)
remind_sessions_num: int
Number of the last user's sessions that the possible items for reminding are taken from (default: 6)
reminders_num: int
length of the reminding list (default: 3)
remind_mode: string
The postion of the remining items in recommendation list (top, end). (default: end)
'''
def __init__(self,
steps=10,
weighting='div',
pruning=20,
last_n_days=None,
idf_weight=False,
last_in_session=False,
session_weighting='div',
boost_own_sessions=None,
reminders=False,
remind_strategy='recency',
remind_sessions_num=6,
reminders_num=3,
remind_mode='end',
weight_base=1,
weight_IRec=0,
session_key='SessionId',
item_key='ItemId',
time_key='Time',
user_key='UserId'):
self.steps = steps
self.pruning = pruning
self.weighting = weighting
self.session_weighting = session_weighting
self.last_n_days = last_n_days
self.idf_weight = idf_weight
self.last_in_session = last_in_session
self.session_key = session_key
self.item_key = item_key
self.time_key = time_key
self.session = -1
self.session_items = []
# user_based
self.user_key = user_key
self.boost_own_sessions = boost_own_sessions
self.hasReminders = reminders
if self.hasReminders:
if remind_strategy == 'hybrid':
self.reminder = Reminder(
remind_strategy=remind_strategy,
remind_sessions_num=remind_sessions_num,
weight_base=weight_base,
weight_IRec=weight_IRec)
else: # basic reminders
self.reminder = Reminder(
remind_strategy=remind_strategy,
remind_sessions_num=remind_sessions_num,
reminders_num=reminders_num,
remind_mode=remind_mode)
def fit(self, data, test=None):
'''
Trains the predictor.
Parameters
--------
data: pandas.DataFrame
Training data. It contains the transactions of the sessions. It has one column for session IDs, one for item IDs and one for the timestamp of the events (unix timestamps).
It must have a header. Column names are arbitrary, but must correspond to the ones you set during the initialization of the network (session_key, item_key, time_key properties).
'''
if self.last_n_days != None:
max_time = dt.fromtimestamp(data[self.time_key].max())
date_threshold = max_time.date() - td(self.last_n_days)
stamp = dt.combine(date_threshold, dt.min.time()).timestamp()
train = data[data[self.time_key] >= stamp]
else:
train = data
if self.idf_weight:
self.idf = self.compute_idf(data,
item_key=self.item_key,
session_key=self.session_key)
cur_session = -1
last_items = []
rules = dict()
# In SR: rule-set is a dic like: {item_a: {item_b: score}, item_b: {item_c: score, item_d: score, item_a: score}}
# In user-based SR: rule-set is a dic like: {item_a: {item_b: [score, {userId1}]}, item_b: {item_c: [score, {userId_1, userId_2}], item_d: [score, {userId_2, userId_3}], item_a: [score, {userId_4}]}}
# fist element of the list is : score, the rest is a SET of user ids who had this rule in their past sessions
# get the position of the columns
index_session = train.columns.get_loc(self.session_key)
index_item = train.columns.get_loc(self.item_key)
index_user = train.columns.get_loc(self.user_key) # user_based
for row in train.itertuples(index=False):
session_id, item_id, user_id = row[index_session], row[
index_item], row[index_user]
if session_id != cur_session:
cur_session = session_id
last_items = []
else:
for i in range(
1, self.steps + 1 if len(last_items) >= self.steps else
len(last_items) + 1):
prev_item = last_items[-i]
if not prev_item in rules:
rules[prev_item] = dict()
if not item_id in rules[prev_item]:
userSet = set()
rules[prev_item][item_id] = [0, userSet]
if not user_id in rules[prev_item][item_id][
1]: # in userSet
rules[prev_item][item_id][1].add(user_id)
weight = getattr(self, self.weighting)(i)
if self.idf_weight:
if self.idf_weight == 1:
weight *= self.idf[prev_item]
elif self.idf_weight == 2:
weight += self.idf[prev_item]
rules[prev_item][item_id][0] += weight
last_items.append(item_id)
# reminders
if self.hasReminders: # user_based # for 'session_similarity' or 'recency'
self.reminder.reminders_fit_in_loop(row, index_user,
index_session, index_item)
# prev_s_id = self.reminder.reminders_fit_in_loop(row, index_user, index_session, index_item, prev_s_id)
if self.pruning > 0:
self.prune(rules)
self.rules = rules
# reminders
if self.hasReminders: # user_based
self.reminder.reminders_fit(train, self.user_key, self.item_key,
self.time_key)
# print( 'Size of map: ', asizeof.asizeof(self.rules))
def linear(self, i):
return 1 - (0.1 * i) if i <= 100 else 0
def same(self, i):
return 1
def div(self, i):
return 1 / i
def log(self, i):
return 1 / (log10(i + 1.7))
def quadratic(self, i):
return 1 / (i * i)
def predict_next(self,
session_id,
input_item_id,
input_user_id,
predict_for_item_ids,
skip=False,
mode_type='view',
timestamp=0):
'''
Gives predicton scores for a selected set of items on how likely they be the next item in the session.
Parameters
--------
session_id : int or string
The session IDs of the event.
input_item_id : int or string
The item ID of the event.
predict_for_item_ids : 1D array
IDs of items for which the network should give prediction scores. Every ID must be in the set of item IDs of the training set.
Returns
--------
out : pandas.Series
Prediction scores for selected items on how likely to be the next item of this session. Indexed by the item IDs.
'''
if session_id != self.session:
self.session_items = []
self.session = session_id
if mode_type == 'view':
self.session_items.append(input_item_id)
if skip:
return
preds = np.zeros(len(predict_for_item_ids))
# useless: add extend_session_length to make predictions
if input_item_id in self.rules:
for key in self.rules[input_item_id]:
# preds[predict_for_item_ids == key] = self.rules[input_item_id][key]
preds[predict_for_item_ids ==
key] = self.rules[input_item_id][key][0]
if self.boost_own_sessions is not None and self.boost_own_sessions > 0.0 and input_user_id in self.rules[
input_item_id][key][
1]: # if the rule also belong to the same user_id, then boost its score!
preds[predict_for_item_ids == key] = preds[
predict_for_item_ids == key] + self.rules[
input_item_id][key][0] * self.boost_own_sessions
if self.last_in_session:
for i in range(2, self.last_in_session + 2):
if len(self.session_items) >= i:
item = self.session_items[-i]
if item in self.rules:
for key in self.rules[item]:
preds[predict_for_item_ids ==
key] += self.rules[item][key] * getattr(
self, self.session_weighting)(i)
else:
break
# test
# for i in range(2,4):
# if len(self.session_items) >= i :
# item = self.session_items[-i]
# for key in self.rules[ item ]:
# preds[ predict_for_item_ids == key ] += self.rules[item][key] * (1/i)
series = pd.Series(data=preds, index=predict_for_item_ids)
series = series / series.max()
if self.hasReminders: # user_based
if self.reminder.remind_strategy == 'hybrid':
series = self.reminder.reminders_predict_next(
input_user_id,
series,
self.item_key,
self.time_key,
input_timestamp=timestamp)
else: # basic reminders
series = self.reminder.reminders_predict_next(
input_user_id, series, self.item_key, self.time_key)
return series
def prune(self, rules):
'''
Gives predicton scores for a selected set of items on how likely they be the next item in the session.
Parameters
--------
rules : dict of dicts
The rules mined from the training data
'''
for k1 in rules:
tmp = rules[k1]
if self.pruning < 1:
keep = len(tmp) - int(len(tmp) * self.pruning)
elif self.pruning >= 1:
keep = self.pruning
counter = col.Counter(tmp)
rules[k1] = dict()
for k2, v in counter.most_common(keep):
rules[k1][k2] = v
def compute_idf(self, train, item_key="ItemId", session_key="SessionId"):
idf = pd.DataFrame()
idf['idf'] = train.groupby(item_key).size()
idf['idf'] = np.log(train[session_key].nunique() / idf['idf'])
idf['idf'] = (idf['idf'] - idf['idf'].min()) / (idf['idf'].max() -
idf['idf'].min())
idf = idf['idf'].to_dict()
return idf
def clear(self):
self.rules = {}
def support_users(self):
'''
whether it is a session-based or session-aware algorithm
(if returns True, method "predict_with_training_data" must be defined as well)
Parameters
--------
Returns
--------
True : if it is session-aware
False : if it is session-based
'''
return True
def predict_with_training_data(self):
'''
(this method must be defined if "support_users is True")
whether it also needs to make prediction for training data or not (should we concatenate training and test data for making predictions)
Parameters
--------
Returns
--------
True : e.g. hgru4rec
False : e.g. uvsknn
'''
return False