def process(user):
tracks = list()
for track in user.tracks:
if track.features is not None:
features = uutils.decode_features(track.features.encode('utf-8'))
tracks.append([5*x for x in features])
for dim in range(2, 16) + [20, 25, 30, 40]:
for k in range(1, 21):
pts = np.array([x[:dim] for x in tracks])
clf = mixture.GMM(n_components=k, covariance_type='full')
clf.fit(pts)
print ("dim = %d, k = %d, cov = full, bic = %f, aic = %f, n = %d"
% (dim, k, clf.bic(pts), clf.aic(pts), len(tracks)))
def process(user):
tracks = list()
for track in user.tracks:
if track.features is not None:
features = uutils.decode_features(track.features.encode('utf-8'))
tracks.append([5 * x for x in features])
for dim in range(2, 16) + [20, 25, 30, 40]:
for k in range(1, 21):
pts = np.array([x[:dim] for x in tracks])
clf = mixture.GMM(n_components=k, covariance_type='full')
clf.fit(pts)
print("dim = %d, k = %d, cov = full, bic = %f, aic = %f, n = %d" %
(dim, k, clf.bic(pts), clf.aic(pts), len(tracks)))
def get_points(dbname, username, start_dim=0, nb_dim=2):
pts = list()
labels = dict()
# Initialize the user / track DB.
store = Store(create_database('sqlite:%s' % dbname))
user = store.find(User, User.name == username).one()
if user is None:
raise LookupError('username not found in database')
for track in user.tracks:
if track.features is not None:
features = uutils.decode_features(track.features.encode('utf-8'))
point = tuple(features[start_dim:start_dim+nb_dim])
pts.append(point)
labels[point] = u"%s - %s" % (track.artist, track.title)
return pts, labels
def get_points(dbname, username, start_dim=0, nb_dim=2):
pts = list()
labels = dict()
# Initialize the user / track DB.
store = Store(create_database('sqlite:%s' % dbname))
user = store.find(User, User.name == username).one()
if user is None:
raise LookupError('username not found in database')
for track in user.tracks:
if track.features is not None:
features = uutils.decode_features(track.features.encode('utf-8'))
point = tuple(features[start_dim:start_dim + nb_dim])
pts.append(point)
labels[point] = u"%s - %s" % (track.artist, track.title)
return pts, labels
def get_points(uid, store, start_dim=0, nb_dim=2):
pts = list()
labels = dict()
user = store.get(User, uid)
if user is None:
raise LookupError('uid %d not found in database' % uid)
entries = store.find(LibEntry, (LibEntry.user == user)
& (LibEntry.is_local == True) & (LibEntry.is_valid == True))
for entry in entries:
track = entry.track
if track.features is not None:
features = uutils.decode_features(track.features)
point = tuple(features[start_dim:start_dim+nb_dim])
pts.append(point)
labels[point] = u"%s - %s" % (track.artist, track.title)
return pts, labels
def get_points(uid, store, start_dim=0, nb_dim=2):
pts = list()
labels = dict()
user = store.get(User, uid)
if user is None:
raise LookupError('uid %d not found in database' % uid)
entries = store.find(LibEntry, (LibEntry.user == user)
& (LibEntry.is_local == True) &
(LibEntry.is_valid == True))
for entry in entries:
track = entry.track
if track.features is not None:
features = uutils.decode_features(track.features)
point = tuple(features[start_dim:start_dim + nb_dim])
pts.append(point)
labels[point] = u"%s - %s" % (track.artist, track.title)
return pts, labels
def pl_generator(user_id, seeds, options = None):
""" Generates a playlist based on the given seeds.
The playlist is generated by fetching the tracks with the nearest tags to
the seeds.
The seeds are stored in a JSONObject of tuples in the form
{<type>:<seeds>[, ...]}
Supported types:
* Tags
The options are stored in a JSONObject of tuples in the form
{<option>:<value>[, ...]}
Supported options:
* Filter
Available values:
- rating>=3 [default]
- rating>=4
- rating>=5
* Size (to be extended)
Available value:
- probabilistic [default]
* Sort
Available values:
- natural [default]
- ratings
- proximity
* Unrated
Available values:
- True [default]
- False
* Title
The given value is the title to be set to the playlist
"""
# Set some default values
default_filter = 'rating>=3' # [rating>=3|rating>=4|rating>=5]
default_size = 'probabilistic' # [probabilistic|ratings|proximity]
default_sort = 'natural' # [natural]
default_unrated = True # [True|False]
default_title = '__unnamed__><((()>' # Reduce probability user chooses the same name
# Check the input
if seeds is None or not seeds:
#TODO Handle error
print 'solo_views.pl_generator: seeds is None'
raise Exception
# Initiate some values
probpl = list() # probabilistic playlist aka playlist with probabilities associated to each tracks
playlist = list() # pure playlist (only data relative to playlist)
# store = utils.get_store()
tagsmatrix = list()
refvect = list()
seeds = json.loads(seeds)
for entry in seeds.items():
type = entry[0]
seedslist = entry[1]
#seedslist.append(entry[1]) # avoids missinterpreting one-element lists
if seedslist is not None:
for seed in seedslist:
if type == 'tags':
vect, weight = utils.tag_features(seed)
# Selection by tracks is not available for now
# if type == 'tracks':
# # TODO: update find condition: UNVALID!
# track = store.find(LibEntry, (LibEntry.user_id == user_id) & LibEntry.is_valid & LibEntry.is_local & (LibEntry.local_id == seed)) # Can't work: seed is not the local_id !
# if (track is not None):
# vect, weight = utils.track_features(track.track.features)
# print 'solo_views.pl_generator: added features for track %s to refvect' %(track.track.title)
# else:
# #TODO Handle error
# vect = list()
else:
#TODO handle error: undefined seed type
print 'solo_views.pl_generator: unknown type of tag: %s' % type
vect = list()
tagsmatrix.append(vect)
for i in xrange(len(tagsmatrix[0])):
vsum = 0
for tagvect in tagsmatrix: # ugly, find something better, like sympy
vsum += tagvect[i]
refvect.append(vsum)
# Normalization
refvect = normalize(refvect)
if refvect is None or not refvect:
#TODO Handle error
print 'solo_views.pl_generator: refvect is None'
raise Exception
# Get options from input
if options is not None and options:
options = json.loads(options)
try:
filter = options.value('filter')
except:
filter = None
try:
size = option.value('size')
except:
size = None
try:
sort = option.value('sort')
except:
sort = None
try:
unrated = option.value('unrated')
except:
unrated = None
try:
title = option.value('title')
except:
title = None
else:
filter = None
size = None
sort = None
unrated = None
title = None
# Set default values
if filter is None:
filter = default_filter
if size is None:
size = default_size
if sort is None:
sort = default_sort
if unrated is None:
unrated = default_unrated
if title is None:
title = default_title
# Fetch LibEntries
if unrated:
entries = g.store.find(LibEntry, (LibEntry.user_id == user_id) & LibEntry.is_valid & LibEntry.is_local)
else:
# TODO find if possibility to filter on existing result set entries.
entries = g.store.find(LibEntry, (LibEntry.user_id == user_id) & LibEntry.is_valid & LibEntry.is_local & (LibEntry.rating != None) & (LibEntry.rating > 0))
if entries.any() is not None and entries.any():
for entry in entries:
added = False
proximity=0 # 0=far away, 1=identical
if entry.track.features is not None:
tagvect = utils.decode_features(entry.track.features)
# Not sure if tagvect is normalized, so in doubt normalize it.
tagvect = normalize(tagvect)
# Compute cosine similarity (dot product), and "normalize" it in [0,1]
proximity = sum( [ fabs(sum([refvect[i] * tagvect[i] for i in range(len(tagvect))])), 1 ] ) / 2
# TODO optimization: filter ASAP, to avoid useless computations
# Ideal: filter at find() time
# Filters
if filter is not None:
if entry.rating == None:
if unrated:
added = True
else:
if unrated and (entry.rating <= 0):
added = True
if not added:
if filter == 'rating>=3':
if entry.rating >= 3 :
added = True
elif filter == 'rating>=4':
if entry.rating >= 4 :
added = True
elif filter == 'rating>=5':
if entry.rating >= 5 :
added = True
# No filtering
else:
added = True
if added:
prob = proximity # Associate a probability
if (size != 'probabilistic') or (size == 'probabilistic' and prob >= random()) :
probpl.append((entry, prob))
else:
raise helpers.NotFound(errors.NO_TAGGED_TRACKS, "Could not generate a playlist: no tagged tracks were found.")
if probpl is not None and probpl:
# Randomize the order before reshaping
probpl = pl_randomizer(probpl)
# Here should happen the size reshaping
# Idea: parse the size if not probabilistic to fetch the criteria
# Criterion could be: [>|<]=XX% of probpl; [>|<]=XX (fixed length);
# Sorting
if sort is not None and sort:
if sort == 'ratings':
probpl = sorted(probpl, key=lambda x: x[0].rating)
elif sort == 'proximity':
probpl = sorted(probpl, key=lambda x: x[1])
# Default: 'natural' sorting, does nothing (aka random)
# Remove the probabilities
for pair in probpl:
playlist.append(pair[0])
# Keep only the relevant fields from the tracks
tracks = list()
index = 1 # First index
for entry in playlist:
tracks.append({
'artist': entry.track.artist,
'title': entry.track.title,
'local_id': entry.local_id,
'play_order': index # Postion of the track in the playlist, used by android
})
index = index + 1
# Store the playlist in the playlist table
jsonify(tracks=tracks)
pldb = Playlist(user_id, unicode(title), len(playlist), seeds, options, unicode(refvect), tracks)
g.store.add(pldb)
g.store.flush() # See Storm Tutorial: https://storm.canonical.com/Tutorial#Flushing
if title == default_title:
g.store.find(Playlist, Playlist.id == pldb.id).set(title=u"playlist_%s" % pldb.id)
# Add it to the user playlist library
pledb = PllibEntry(user_id, pldb.id)
g.store.add(pledb)
g.store.flush()
# Make the changes persistent in the DB, see Storm Tutorial: https://storm.canonical.com/Tutorial#Committing
g.store.commit()
# Craft JSON
playlistdescriptor = to_dict(pledb)
return playlistdescriptor
raise helpers.NotFound(errors.IS_EMPTY, "Could not generate a playlist: no tracks were found in user library.")
