def getPublicPlaylistDashboard():
library = analyze.loadLibraryFromFiles(
str(DATA_DIRECTORY) + "/users/127108998/")
if library is None:
return render_template('dataload.html',
subheader_message="",
library=library,
**session)
playlistName = request.args.get('playlistName')
playlist = None
if playlistName is not None:
subheader_message = "Playlist " + playlistName
for playlist in library['playlists-tracks']:
if playlist['name'] == playlistName:
break
else:
subheader_message = "Playlists count: " + str(
len(library['playlists-tracks']))
tracks = library['playlists-tracks']
#library= {}
#library['tracks'] = tracks
return render_template('playlistDashboard.html',
playlistName=playlistName,
playlist=playlist,
subheader_message=subheader_message,
library=library,
**session)
def getAudioFeatures(file_path='data/'):
#print ("retrieving audio features...")
library = analyze.loadLibraryFromFiles(_getDataPath())
if library is None:
return render_template('dataload.html',
subheader_message="",
library={},
**session)
audioFeatures = library['audio_features']
if audioFeatures == None:
audioFeatures = getAudioFeatures(library['tracks'])
if audioFeatures == None:
return render_template(
'index.html',
subheader_message="Failed to get audio features ",
library=library,
**session)
library['audio_features'] = audioFeatures
#print (" done")
directory = os.path.dirname(file_path)
if not os.path.exists(directory):
os.makedirs(directory)
bar = saagraph.create_dataseries(_getDataPath())
return render_template('timeseries.html',
sortedA=audioFeatures,
subheader_message=str(len(audioFeatures)),
plot=bar,
**session)
def getTopGenres():
library = analyze.loadLibraryFromFiles(_getDataPath())
if library is None:
return render_template('dataload.html',
subheader_message="",
library=library,
**session)
tracks = analyze.getOrphanedTracks(
analyze.loadLibraryFromFiles(_getDataPath()))
library['tracks'] = tracks
genres = analyze.getTopGenreSet(library)
return render_template('topgenres.html',
sortedA=tracks,
subheader_message="Top Genres " +
str(len(library['tracks'])),
library=library,
genres=genres,
**session)
def getlibrary():
ds = request.args
library = analyze.loadLibraryFromFiles(_getDataPath())
if library is None:
logging.info(" library is None")
tracksWoAlbum = []
analyze.process(library)
#for ()
bar = saagraph.create_dataseries()
return render_template('timeseries.html', plot=bar)
def dataload():
dt = analyze.getUpdateDtStr(_getDataPath())
l = None
if dt is not None:
library = analyze.loadLibraryFromFiles(_getDataPath())
l = analyze.getLibrarySize(library)
return render_template('dataload.html',
sortedA=None,
subheader_message="",
library={},
lastmodified=dt,
sizetext=l,
**session)
def getOrphanedTracks():
username = request.args.get('username')
if username is None:
dataPath = _getDataPath()
else:
dataPath = str(DATA_DIRECTORY) + "/users/" + username + "/"
library = analyze.loadLibraryFromFiles(dataPath)
if library is None:
return render_template('dataload.html',
subheader_message="",
library=library,
**session)
tracks = analyze.getOrphanedTracks(analyze.loadLibraryFromFiles(dataPath))
library = {}
library['tracks'] = tracks
return render_template('orphanedTracks.html',
sortedA=tracks,
subheader_message="Orphaned tracks count " +
str(len(library['tracks'])),
library=library,
**session)
def getPlaylistDashboard():
username = request.args.get('username')
if username is None:
dataPath = _getDataPath()
else:
#dataPath = str(DATA_DIRECTORY)+"/"+username+ "/"
dataPath = str(DATA_DIRECTORY) + "/users/127108998/"
library = analyze.loadLibraryFromFiles(dataPath)
if library is None:
return render_template('dataload.html',
subheader_message="",
library=library,
**session)
playlistId = request.args.get('playlistId')
playlistName = None
playlist = None
if playlistId is not None:
playlist = analyze.getPlaylist(session['id'], library['playlists'],
playlistId)
playlist = playlist[0] #getPlaylist always returns a list
playlistName = playlist['name']
subheader_message = "Playlist " + playlistName
else:
subheader_message = "Playlists count: " + str(len(
library['playlists']))
library['playlists-tracks'] = analyze.getPlaylist(
session['id'], library['playlists'])
tracks = library['playlists']
if playlist is None and library['playlists-tracks'] is None:
return render_template('dataload.html',
subheader_message="",
library=library,
**session)
return render_template('playlistDashboard.html',
playlistName=playlistName,
playlist=playlist,
subheader_message=subheader_message,
library=library,
**session)
def generate(sessionLocal):
x = 0
started = str(datetime.datetime.now())
with app.app_context():
#print("generator started...")
#thread = Thread(target=_retrieveSpotifyData, args=(session))
#thread.start()
lib = analyze.loadLibraryFromFiles(_getDataPath())
#session['dataLoadingProgressMsg'] = userId
while _getUserSessionMsg():
#s = "data: {x:" + str(x) + ', generator ' \
s = 'data: ' + _getUserSessionMsg()
#+ sessionLocal['dataLoadingProgressMsg'] \
#+ ' library: '+analyze.getLibrarySize(lib) \
yield s + "\n\n"
#print("generator yielding: " + s)
x = x + 10
time.sleep(0.3)
def _getTrackTuples(dataPath):
fullLib = analyze.loadLibraryFromFiles(dataPath)
# dataArray list:8 3799
# one row per audio feature
# [[0.469, 0.76, 0.598, 0.706, 0.756, 0.555, 0.53, 0.716, 0.481, 0.415, 0.684, 0.593, 0.395, 0.487, 0.671, 0.691, 0.155, 0.61, 0.171, 0.203, 0.181,
# [0.625, 0.608, 0.509, 0.653, 0.549, 0.71, 0.362, 0.685, 0.491, 0.42, 0.62, 0.626, 0.704, 0.757, 0.603, 0.669, 0
# [4, 9, 9, 7, 7, 10, 5, 4, 11, 3, 0, 4, 5, 0, 4, 1, 10, 11, 7, 2, 10, 10, 10, 0, 8, 9, 11, 6, 11, 6, 10, 1, 0, 3, 0,
datesadded = []
artists = []
# date_time_str = '2020-02-16T19:54:58Z'
# date_time_obj = datetime.datetime.strptime(date_time_str, '%Y-%m-%dT%H:%M:%SZ')
dataSeries = []
for i, item in enumerate(fullLib['tracks']):
dataSeriesItem = []
ts = datetime.datetime.strptime(item['added_at'], '%Y-%m-%dT%H:%M:%SZ')
weekday = calendar.day_name[ts.weekday()]
artist = fullLib['tracks'][i]['track']['artists'][0]['name']
trackname = fullLib['tracks'][i]['track']['name']
# print(str(i)+' '+str(track['track']['artists'][0]['name'])+ ' - '+
# str(track['track']['album']['name'])+ ' - '+
# str(track['track']['name'])+' song '+str(dataOrig[i])+' ' )
# datesadded.append(ts)
# artists.append(artist)
# dataSeries.append((ts,artist,weekday))
# print(str(i) + " " + str(item))
# dataSeries.append(dataArray[i])
dataSeriesItem.append(ts)
dataSeriesItem.append(str(ts)+" - " + str(i) + " - " + artist + " - " + trackname)
dataSeriesItem.append(weekday)
dataSeries.append(dataSeriesItem)
# dataSeries.append(datesadded)
# dataSeries.append(artists)
# dataArray.insert(0,dataSeries)
# 2020-02-16T19:54:58Z
return dataSeries
def getFavoriteArtistsOverTime(file_path='data/'):
#logging.info ("retrieving audio features...")
library = analyze.loadLibraryFromFiles(_getDataPath())
if library is None or library.get('topartists_short_term') is None:
return render_template('dataload.html',
subheader_message="",
library={},
**session)
directory = os.path.dirname(file_path)
if not os.path.exists(directory):
os.makedirs(directory)
bar = saagraph.create_top_artists_graph(_getDataPath())
return render_template('favorite_artists_over_time.html',
sortedA=None,
subheader_message='',
plot=bar,
**session)
def index():
session['hellomsg'] = 'Welcome to Spotify Analyzer'
hellomsg = 'Welcome to Additive Spotify Analyzer'
_setUserSessionMsg(None)
library = analyze.loadLibraryFromFiles(_getDataPath())
if session.get('username'):
genres = analyze.getTopGenreSet(library)
hellomsg = 'Welcome ' + session.get('username')
profile = None
if library is not None:
profile = library.get('profile')
if profile is None:
profileimageurl = None
display_name = session.get('username')
else:
profileimageurl = profile['images'][0]['url']
display_name = profile['display_name']
session['profileimageurl'] = profile['images'][0]['url']
l = analyze.getLibrarySize(library)
lastModifiedDt = analyze.getUpdateDtStr(_getDataPath())
#_setUserSessionMsg("Library size: "+l)
return render_template('index.html',
subheader_message=hellomsg,
genres=genres,
library=library,
sizetext=l,
lastmodified=lastModifiedDt,
display_name=display_name,
**session)
else:
return render_template('index.html',
subheader_message=hellomsg,
genres={},
library={},
**session)
def analyzeLocal():
library = analyze.loadLibraryFromFiles(_getDataPath())
if library is None:
return render_template('dataload.html',
subheader_message="",
library=library,
**session)
if library:
start = time.process_time()
sortedA = analyze.process(library)
trackCount = 0
for l in sortedA:
trackCount += len(sortedA[l])
#data = {'First Column Name': ['First value', 'Second value', ...],
# 'Second Column Name': ['First value', 'Second value', ...],
# ....
# }
#data = pd
return render_template('trackslist.html',
subheader_message="Local data processed in " +
str(time.process_time() - start) +
"ms. Artist count " + str(len(sortedA)) +
". Track count " + str(trackCount),
sortedA=sortedA,
diagramVersion="test",
library=library,
**session)
else:
return render_template(
'index.html',
subheader_message="Local data not found. Click to retrieve.",
library={},
**session)
def create_sol_multiview():
dataOrig = analyze.loadAudioFeatures()
fullLib = analyze.loadLibraryFromFiles()
# list: 3799 of dict:18
# [{'danceability': 0.469, 'energy': 0.625, 'key': 4, 'loudness': -5.381, 'mode': 0, 'speechiness': 0.0306, 'acousticness': 0.00515, 'instrumentalness': 2.03e-05, 'liveness': 0.0682, 'valence': 0.325, 'tempo': 76.785, 'type': 'audio_features', 'id': '6PBzdsMi6YNdYAevzozBRi', 'uri': 'spotify:track:6PBzdsMi6YNdYAevzozBRi', 'track_href': 'https://api.spotify.com/v1/tracks/6PBzdsMi6YNdYAevzozBRi', 'analysis_url': 'https://api.spotify
# {'danceability': 0.76, 'energy': 0.608, 'key': 9, 'loudness': -8.673, 'mode': 0, 'speechiness': 0.0347, 'acousticness': 0.315, 'instrumentalness': 0.79, 'liveness': 0.121, 'valence': 0.727, 'tempo': 119.032, 'type': 'audio_features', 'id': '4dJYJTPbUgFK5pCQ5bYD4g', 'uri': 'spotify:track:4dJYJTPbUgFK5pCQ5bYD4g', 'track_href': 'https://api.spotify.com/v1/tracks/4dJYJTPbUgFK5pCQ5bYD4g', 'analysis_url': 'https://api.spotify.com/v1/audio-analysis/4dJYJTPbUgFK5pCQ5bYD4g', 'duration_ms': 254118, 'time_signature': 4}
# {'danc..
dtype = [('danceability', '<f8'), ('energy', '<f8'), ('key', '<f8'), ('loudness', '<f8'), ('mode', '<f8'),
('speechiness', '<f8'), ('acousticness', '<f8'), ('instrumentalness', '<f8'), ('liveness', '<f8'),
('valence', '<f8'),
('tempo', '<f8'), ('type', '<f8'), ('id', '<f8'), ('duration_ms', '<f8'), ('time_signature', '<f8'), ]
keys = ['danceability', 'energy', 'key', 'loudness', 'speechiness', 'acousticness', 'instrumentalness']
keys = ['danceability', 'energy', 'key', 'loudness', 'valence', 'speechiness', 'tempo', 'time_signature']
# keys = ['danceability', 'energy', 'loudness']
# keys = ['danceability', 'energy']
# ('danceability','energy','key', 'loudness', 'mode', 'speechiness', 'acousticness', 'instrumentalness', 'liveness',
# 'valence', 'tempo'):
dataArray = []
for key in dataOrig[0]:
if key in keys:
# data[key] = [li[key] for li in dataOrig]
dataArray.append([li[key] for li in dataOrig])
# dataArray list:8 3799
# one row per audio feature
# [[0.469, 0.76, 0.598, 0.706, 0.756, 0.555, 0.53, 0.716, 0.481, 0.415, 0.684, 0.593, 0.395, 0.487, 0.671, 0.691, 0.155, 0.61, 0.171, 0.203, 0.181,
# [0.625, 0.608, 0.509, 0.653, 0.549, 0.71, 0.362, 0.685, 0.491, 0.42, 0.62, 0.626, 0.704, 0.757, 0.603, 0.669, 0
# [4, 9, 9, 7, 7, 10, 5, 4, 11, 3, 0, 4, 5, 0, 4, 1, 10, 11, 7, 2, 10, 10, 10, 0, 8, 9, 11, 6, 11, 6, 10, 1, 0, 3, 0,
dataArray = np.array(dataArray)
# call MinMaxScaler object
min_max_scaler = MinMaxScaler()
# feed in a numpy array
minmaxscaled = min_max_scaler.fit_transform(dataArray)
# wrap it up if you need a dataframe
# df = pd.DataFrame(X_train_norm)
dataArrayMean = np.mean(dataArray)
dataArrayStd = np.std(dataArray)
allsongsstandardized = (dataArray - dataArrayMean) / dataArrayStd
X_train_norm = allsongsstandardized
X_train_norm = np.flip(np.rot90(X_train_norm, 3))
dataToDisplay = np.flip(np.rot90(dataArray, 3))
# allsongs: list:3799 x 8\
# one row per song
# [[0.469, 0.625, 4, -5.381, 0, 0.0306, 0.00515, 2.03e-05],
# [0.76, 0.608, 9, -8.673, 0, 0.0347, 0.315, 0.79],
# [0.598, 0.509, 9, -9.719, 1, 0.0269, 0.593, 0.0503],
kmeans = KMeans(n_clusters=7)
kmeans.fit(X_train_norm)
predict = kmeans.predict(X_train_norm)
centroids = kmeans.cluster_centers_
correct = 0
# for i in range(len(X1)):
# predict_me = np.array(X1[i].astype(float))
# predict_me = predict_me.reshape(-1, len(predict_me))
# prediction = kmeans.predict(predict_me)
# print(prediction[0])
cs2 = kmeans.labels_.astype(float)
fig = go.Figure(data=go.Splom(
dimensions=[dict(label=keys[0],
values=dataToDisplay[:, 0]),
dict(label=keys[1],
values=dataToDisplay[:, 1]),
dict(label=keys[2],
values=dataToDisplay[:, 2]),
dict(label=keys[3],
values=dataToDisplay[:, 3]),
dict(label=keys[4],
values=dataToDisplay[:, 4]),
dict(label=keys[5],
values=dataToDisplay[:, 5]),
dict(label=keys[6],
values=dataToDisplay[:, 6]),
dict(label=keys[7],
values=dataToDisplay[:, 7])
],
marker=dict(color=cs2,
showscale=False, # colors encode categorical variables
line_color='white', line_width=0.5)
))
fig.show()
return fig
def create_figure_backup():
dataOrig = analyze.loadAudioFeatures()
fullLib = analyze.loadLibraryFromFiles()
# list: 3799 of dict:18
# [{'danceability': 0.469, 'energy': 0.625, 'key': 4, 'loudness': -5.381, 'mode': 0, 'speechiness': 0.0306, 'acousticness': 0.00515, 'instrumentalness': 2.03e-05, 'liveness': 0.0682, 'valence': 0.325, 'tempo': 76.785, 'type': 'audio_features', 'id': '6PBzdsMi6YNdYAevzozBRi', 'uri': 'spotify:track:6PBzdsMi6YNdYAevzozBRi', 'track_href': 'https://api.spotify.com/v1/tracks/6PBzdsMi6YNdYAevzozBRi', 'analysis_url': 'https://api.spotify
# {'danceability': 0.76, 'energy': 0.608, 'key': 9, 'loudness': -8.673, 'mode': 0, 'speechiness': 0.0347, 'acousticness': 0.315, 'instrumentalness': 0.79, 'liveness': 0.121, 'valence': 0.727, 'tempo': 119.032, 'type': 'audio_features', 'id': '4dJYJTPbUgFK5pCQ5bYD4g', 'uri': 'spotify:track:4dJYJTPbUgFK5pCQ5bYD4g', 'track_href': 'https://api.spotify.com/v1/tracks/4dJYJTPbUgFK5pCQ5bYD4g', 'analysis_url': 'https://api.spotify.com/v1/audio-analysis/4dJYJTPbUgFK5pCQ5bYD4g', 'duration_ms': 254118, 'time_signature': 4}
# {'danc..
dtype = [('danceability', '<f8'), ('energy', '<f8'), ('key', '<f8'), ('loudness', '<f8'), ('mode', '<f8'),
('speechiness', '<f8'), ('acousticness', '<f8'), ('instrumentalness', '<f8'), ('liveness', '<f8'),
('valence', '<f8'),
('tempo', '<f8'), ('type', '<f8'), ('id', '<f8'), ('duration_ms', '<f8'), ('time_signature', '<f8'), ]
keys = ['danceability', 'energy', 'key', 'loudness', 'speechiness', 'acousticness', 'instrumentalness']
keys = ['danceability', 'energy', 'key', 'loudness', 'valence', 'speechiness', 'tempo', 'time_signature']
# keys = ['danceability', 'energy', 'loudness']
# keys = ['danceability', 'energy']
# ('danceability','energy','key', 'loudness', 'mode', 'speechiness', 'acousticness', 'instrumentalness', 'liveness',
# 'valence', 'tempo'):
dataArray = []
for key in dataOrig[0]:
if key in keys:
# data[key] = [li[key] for li in dataOrig]
dataArray.append([li[key] for li in dataOrig])
# dataArray list:8 3799
# one row per audio feature
# [[0.469, 0.76, 0.598, 0.706, 0.756, 0.555, 0.53, 0.716, 0.481, 0.415, 0.684, 0.593, 0.395, 0.487, 0.671, 0.691, 0.155, 0.61, 0.171, 0.203, 0.181,
# [0.625, 0.608, 0.509, 0.653, 0.549, 0.71, 0.362, 0.685, 0.491, 0.42, 0.62, 0.626, 0.704, 0.757, 0.603, 0.669, 0
# [4, 9, 9, 7, 7, 10, 5, 4, 11, 3, 0, 4, 5, 0, 4, 1, 10, 11, 7, 2, 10, 10, 10, 0, 8, 9, 11, 6, 11, 6, 10, 1, 0, 3, 0,
dataArray = np.array(dataArray)
dataArrayMean = np.mean(dataArray)
dataArrayStd = np.std(dataArray)
allsongsstandardized = (dataArray - dataArrayMean) / dataArrayStd
X_train_norm = allsongsstandardized
X_train_norm = np.flip(np.rot90(X_train_norm, 3))
dataToDisplay = np.flip(np.rot90(dataArray, 3))
# allsongs = []
# for songOrig in dataArray:
# song = []
# for key in keys:
# song.append(dataArray[key])
# allsongs.append(song)
# allsongs: list:3799 x 8\
# one row per song
# [[0.469, 0.625, 4, -5.381, 0, 0.0306, 0.00515, 2.03e-05],
# [0.76, 0.608, 9, -8.673, 0, 0.0347, 0.315, 0.79],
# [0.598, 0.509, 9, -9.719, 1, 0.0269, 0.593, 0.0503],
# X1 = np.array(dataArray)
# y = np.array(dataArray2)
# kmeans = KMeans(algorithm='auto', copy_x=True, init='k-means++', max_iter=3000,
# n_clusters=5, n_init=10, n_jobs=1, precompute_distances='auto',
# random_state=None, tol=0.0001, verbose=0)
kmeans = KMeans(n_clusters=7)
kmeans.fit(X_train_norm)
predict = kmeans.predict(X_train_norm)
# data['cluster'] = predict
# df = px.data.gapminder().query("country=='Canada'")
# fig = px.line(df, x="year", y="lifeExp", title='Life expectancy in Canada')
# fig.show()
# fig = go.Figure(data=X_train_norm.__array__())
# fig.write_html('first_figure.html', auto_open=True)
# fig = px.scatter(kmeans.cluster_centers_)
# pd.plotting.parallel_coordinates(pd.array(X_train_norm),0)
# plt.show()
# print(numpy.info(X1))
centroids = kmeans.cluster_centers_
correct = 0
# for i in range(len(X1)):
# predict_me = np.array(X1[i].astype(float))
# predict_me = predict_me.reshape(-1, len(predict_me))
# prediction = kmeans.predict(predict_me)
# print(prediction[0])
# print(correct / len(X1))
X2 = dataArray[0]
nCols = len(X2)
nRows = dataArray.shape[0]
# colors = cm.rainbow(np.linspace(0, 1, len(dataArray)))
# cs1 = [colors[i // len(dataArray)] for i in range(len(dataArray) * len(dataArray))] # could be done with numpy's repmat
cs2 = kmeans.labels_.astype(float)
# cs3 = cs2 ** nRows
# cs3 = np.repeat(cs2, nRows)
# Xs1 = dataArray * nRows # use list multiplication for repetition
fig = go.Figure()
# fig.add_trace(go.Scatter(x=dataArray[0], y=dataArray[1] ** 2, mode='markers', marker_color=cs2))
# fig.show()
fig = go.Figure(data=go.Splom(
dimensions=[dict(label=keys[0],
values=dataToDisplay[:, 0]),
dict(label=keys[1],
values=dataToDisplay[:, 1]),
dict(label=keys[2],
values=dataToDisplay[:, 2]),
dict(label=keys[3],
values=dataToDisplay[:, 3]),
dict(label=keys[4],
values=dataToDisplay[:, 4]),
dict(label=keys[5],
values=dataToDisplay[:, 5]),
dict(label=keys[6],
values=dataToDisplay[:, 6]),
dict(label=keys[7],
values=dataToDisplay[:, 7])
],
marker=dict(color=cs2,
showscale=False, # colors encode categorical variables
line_color='white', line_width=0.5)
))
fig.show()
for i, center in enumerate(kmeans.cluster_centers_):
j = i % len(X_train_norm[0])
k = (i + 1) % len(X_train_norm[0])
# plt.figure(i)
# plt.suptitle("scatterplot "+str(i)+" "+str(j)+":"+str(k))
# plt.scatter(X_train_norm[:, j], X_train_norm[:, k], c=cs2, s=5, alpha=0.4)
# plt.scatter(centroids[:,j], centroids[:,k], c='black', s=5)
fig.add_trace(go.Scatter(x=X_train_norm[:, j], y=np.arange(min(X_train_norm[:, j]), max(X_train_norm[:, j])),
mode='lines'))
# fig.add_trace(go.Scatter(centroids[:,j], 'b.', markersize=2))
fig.show()
# plt.scatter(X_train_norm[:, 0], X_train_norm[:, 1], c=cs2, s=5, alpha=0.4)
# plt.scatter(X_train_norm[:, 0], X_train_norm[:, 2], c=cs2, s=5, alpha=0.4)
# plt.plot(allsongsstandardized)
# plt.figure(2)
# plt.plot(dataArray[0],' r.', markersize=1)
# plt.figure(3)
# plt.plot(dataArray[1], 'b.', markersize=1)
# plt.figure(4)
# plt.plot(dataArray[2], 'y.', markersize=1)
# plt.scatter(dataArray[0], dataArray[3], c="blue", alpha=0.1)
# plt.figure(5)
# plt.scatter(dataArray[0], dataArray[0], c="blue", alpha=0.1)
# plt.subplot(321, label="one")
# plt.hist(dataArray[0], bins=200)
# plt.title("exess")
# plt.subplot(322, label="two")
# plt.hist(dataArray[1], bins=200)
# plt.title("222222")
# plt.subplot(323)
# plt.hist(dataArray[2], bins=200)
# plt.title("ex333333ess")
# plt.scatter(Xs1[1], Ys[1], c="blue", alpha=0.1)
# plt.scatter(Xs1, Ys.flatten(), color=cs)
# plt.grid(True)
# plt.show()
clusteredSongs = [[] for i in range(kmeans.n_clusters)]
for i, cluster in enumerate(cs2):
songCluster = clusteredSongs[int(cluster)]
track = next((item for item in fullLib['tracks'] if item['track']['id'] == dataOrig[i]['id']), None)
if (track is not None):
songCluster.append({**track, **dataOrig[i]})
# print(str(i)+' '+str(track['track']['artists'][0]['name'])+ ' - '+
# str(track['track']['album']['name'])+ ' - '+
# str(track['track']['name'])+' song '+str(dataOrig[i])+' ' )
return fig
def create_top_artists_graph(dataPath):
fullLib = analyze.loadLibraryFromFiles(dataPath)
topartists = []
topartists.append([art['name'] for i, art in enumerate(fullLib['topartists_long_term'])][:50])
topartists.append([art['name'] for art in fullLib['topartists_medium_term']][:50])
topartists.append([art['name'] for art in fullLib['topartists_short_term']][:20])
#topartists = np.array(topartists)
#topartists = topartists.reshape(-1,1)
topartistsranking = []
topartistsrankingM = {}
for i, artistlist in enumerate(topartists):
topartistsranking.append([])
for j, artist in enumerate(artistlist):
topartistsrankingM.setdefault(artist, [None, None, None])
for i in range(50):
for j in range(3):
artist = topartists[j][i:i+1]
if len(artist) > 0:
a = topartistsrankingM.get(artist[0])
a[j] = i+1 # so that most favorite artist is at position 1 instead of 0
#print(' done')
#colors = [plotly.colors.DEFAULT_PLOTLY_COLORS[random.randrange(1, 10)] for i in range(len(topartistsrankingM))]
color = ('rgba(' + str(np.random.randint(0, high=200)) + ',' +
str(np.random.randint(0, high=250)) + ',' +
str(np.random.randint(0, high=100)))
colors = ['rgba(200,121,121','rgba(60,121,60','rgba(121,60,256','rgba(33,33,33',
'rgba(200,180,60','rgba(121,200,33','rgba(33,121,255','rgba(121,66,33',
'rgba(255,60,121', 'rgba(33,170,121', 'rgba(0,66,66', 'rgba(121,66,121',
'rgba(255,60,0', 'rgba(33,155,0', 'rgba(66,200,0', 'rgba(121,66,0',
'rgba(255,0,33','rgba(66,121,255','rgba(66,66,255','rgba(66,200,200']
#weights = [random.randint(15, 35) for i in range(50)]
xaxis = ['Long Term (several years)','Medium Term (last six months)', 'Very recent (last four weeks)']
data = []
for i, (artist, yaxis) in enumerate(topartistsrankingM.items()):
#weights2 = [*range(11, len(topartistsrankingM)+5)]
#weights3 = [x/2 for x in range(1,len(topartistsrankingM))]
weights2 = 10
#color = colors[i % len(colors)]
red = 200*((len(topartistsrankingM)-i)/len(topartistsrankingM))
color = ('rgba(' + str(red) + ',' + \
str(np.random.randint(0, high=100)) + ',' + \
str(np.random.randint(0, high=120)))
#color = yaxis
#visibletrace = 'legendonly'
yaxisStrings = yaxis.copy()
for i,y in enumerate(yaxisStrings):
if y is None:
yaxisStrings[i] = '--'
else:
yaxisStrings[i] = str(yaxis[i])
hovertemplatetext = '<b>' + artist + ' </b><br>All time popularity: ' + yaxisStrings[0] + \
'<br>In the last six months: ' + yaxisStrings[1] + '<br>Recently: ' + yaxisStrings[2] + \
'<extra></extra>'
if len(list(filter(None, yaxis))) > 1:
visibletrace = True
mode = "markers+text+lines"
text = ['<b>'+artist+'</b>','<b>'+artist+'</b>','<b>'+artist+'</b>']
hovertemplate=hovertemplatetext
marker = {'opacity': 0.1, 'size': 11, 'symbol': 'diamond-wide-dot'}
else:
mode = "markers+lines"
text= ''
visibletrace = True
hovertemplate=hovertemplatetext
marker = {'opacity': 0.7, 'size': 11, 'symbol': 'diamond-wide-dot'}
#print("")
data.append(go.Scatter(x=xaxis, y=yaxis,
mode=mode,
marker=marker,
line={'color':color+',0.5)', 'width':1, 'dash':'dot'},
#line={'width': 1, 'dash': 'dot'},
name = artist,
#hoverinfo='text',
text=text,
#hovertext = text,
hovertemplate=hovertemplate,
#color=color,
textfont={'size': weights2, 'color': color+',1)'},
#textfont={'size': weights2},
visible=visibletrace
)
)
tickvals = [1,5,10,15,20,25,30,35,40,45,50]
ticktext = ['1', '5', '10', 'Seven', 'Nine', 'Eleven']
default_linewidth = 2
highlighted_linewidth_delta = 2
layout = go.Layout({'title':'Change of artist popularity over time',
'font':{ 'size':15},
'xaxis': {'showgrid': False, 'showticklabels': True, 'zeroline': False},
'yaxis': {'showgrid': True, 'showticklabels': True, 'zeroline': False,
'autorange':'reversed',
#'tick0':1, 'dtick':'2', 'nticks':10,
'tickvals': tickvals,
#'tickmode':'array', 'tickvals':tickvals, 'ticktext':ticktext
},
'legend':{ 'font':{ 'size':11 }},
'hovermode':'y',
'hoverlabel_align' : 'right',
#'width' : 1200,
'height' : 750,
'margin' : { 'l':50, 'r':50, 'b':50, 't':80,'pad':4 }
})
#fig = go.Figure(data=data, layout=layout)
#fig.update_yaxes(automargin=True)
#fig.update_traces(textposition='top right')
fig = go.FigureWidget(data=data, layout=layout)
fig.layout.hovermode = 'closest'
fig.layout.hoverdistance = -1 # ensures no "gaps" for selecting sparse data
#fig.show()
graphJSON = fig.to_json()
return graphJSON