def popularity(data, pidtotracks=None, name="DefaultName"):
if (pickle_utility.exists_file(name)):
return pickle_utility.load(name)
if (pidtotracks == None):
pidtotracks = pickle_utility.load("pidtotracks")
occurences = pickle_utility.load("trackOccurences")
pop_dict = {}
counter = 0
print("Start popularity ranking...")
for key, pid_predictions in data.items():
track_pop_dict = Counter()
for pid in pid_predictions:
tracks = pidtotracks[int(pid)]
for track in tracks.split():
track_pop_dict[track] = occurences[track]
pop_dict[key] = [i[0] for i in track_pop_dict.most_common(1000)]
counter += 1
if (counter % 100 == 0):
print("Processed {} playlists".format(counter))
pickle_utility.dump(pop_dict, name)
return pop_dict
def getPopularityRankedTracks(playlists, name):
trackPopularityDict = pickle_utility.load("trackOccurences")
rankedTrackDict = dict()
rankedSimilarTrackDict = dict()
counter = 0
for pid, similarPids in playlists.items():
print (counter," / ", len(playlists.items()))
counter+=1
for similarPid in similarPids:
tracks = pid_dict[int(float(similarPid))]
tracks = tracks.split(" ")
for track in tracks:
if not track in rankedTrackDict:
rankedTrackDict[track] = trackPopularityDict[track]
# rearrange the similar playlists for this pid so that the most popular are at the beginning
sortedSimilarTracks = dict(sorted(rankedTrackDict.items(), key=operator.itemgetter(1), reverse=True))
rankedSimilarTrackDict[pid] = list(sortedSimilarTracks.keys())
sortedSimilarTracks.clear()
pickle_utility.dump(rankedSimilarTrackDict, "rankedTracks", name)
return rankedSimilarTrackDict
def create_pid_dict(fileCount):
pids, tracks = process_mpd(app_settings.MPD_SET, fileCount)
print("Concat lists")
pid_dict = {}
for pid, track in zip(pids, tracks):
pid_dict[pid] = track
print("Dump")
pickle_utility.dump(pid_dict, "pidtotracks")
return
def create_yearDict():
years = dict()
for k in lookupDict:
playlist = re.split(' ', k)
id = playlist[-1]
name = []
for j in range(len(playlist) - 1):
name.append(playlist[j])
match = re.match(".*([1-2][0-9]{3})", str(name))
if match is not None:
# year = re.split(".*([1-2][0-9]{3})", str(name))
search = re.search('\d{4}', str(match))
date = search.group()
if date not in years:
years[date] = [id]
else:
years[date].append(id)
pickle_utility.dump(years, "yearsDict")
def create_wordDict():
words = dict()
for k in lookupDict:
playlist = k.split(" ")
name = []
out = ""
for j in range(len(playlist) - 1):
name.append(playlist[j])
id = playlist[-1]
for i in range(len(name)):
tmp = name[i]
tmp = re.sub("[^\w\s\_]", "", tmp)
tmp = tmp.lower()
out = out + tmp
if out not in words:
words[out] = [id]
else:
words[out].append(id)
pickle_utility.dump(words, "wordDict_NamesNotSplitted")
def getPopularityRankedPlaylists(playlists, name):
pidPopularityDict = pickle_utility.load("pidPopularityDict")
rankedPidDict = dict()
rankedSimilarTrackDict = dict()
for pid, similarPids in playlists.items():
for similarPid in similarPids:
rankedPidDict[similarPid] = pidPopularityDict[int(float(similarPid))]
# rearrange the similar playlists for this pid so that the most popular are at the beginning
sortedSimilarPlaylists = dict(sorted(rankedPidDict.items(), key=operator.itemgetter(1), reverse=True))
rankedSimilarTrackDict[pid] = list(sortedSimilarPlaylists.keys())
rankedPidDict.clear()
pickle_utility.dump(rankedSimilarTrackDict, "rankedPlaylists", name)
return rankedSimilarTrackDict
def enrich_playlists(playlists, nr_new_tracks_per_track):
# playlists=playlists.values()
file = open(FILEPATH + "count_chain_file_dict", "rb")
dic = pickle.load(file)
outPl = []
outDict = dict()
for k, pl in playlists.items():
trackSet = set(pl)
tempList = []
tempList.extend(pl)
for track in pl:
onlyTracks = [
e[0] for e in dic[track].most_common(nr_new_tracks_per_track)
if e[0] not in trackSet
]
tempList.extend(onlyTracks)
outPl.append(tempList)
outDict[k] = tempList
pickle_utility.dump(outDict, "MarkovOut")
return outDict
def create_wordDict():
words = dict()
for k in lookupDict:
playlist = re.split(' |_|-', k)
name = []
out = ""
for j in range(len(playlist)-1):
name.append(playlist[j])
id = playlist[-1]
for i in range(len(name)):
tmp = name[i]
tmp = re.sub("[^\w\s\_]", "", tmp)
tmp = tmp.lower()
if tmp not in irrelevant:
out = out + tmp
if out not in words:
words[out] = [id]
else:
words[out].append(id)
# if hasNumbers(out):
# years.append(out)
pickle_utility.dump(words, "wordDict_withoutIrrelevant")