def printUsage():
print("Usage: python songsPerYear.py {user_id}")
try:
user = sys.argv[1]
except IndexError as err:
printUsage()
sys.exit(1)
user_folder = './'+user
# Set up data
allData = importMappedData(user_folder+'/mapped_data.tsv')
data = mbzMeta(user_folder+'/meta.tsv',allData)
data = data.merge(allData, on='track_id')
# Select the attribute we want to visualise
attribute = data['year'].value_counts()
labels = attribute.index.values
# Deal with unknown (empty string)
labels = ["Unknown" if x == '' else x for x in labels]
frequency = attribute.tolist()
# Generate the y positions. Later, replace them with labels
y_pos = range(len(labels))
fig,ax = plt.subplots()
])
if userPlays.empty:
print(user + " does not exist! ")
sys.exit(1)
# Sort by playcount
sortedPlays = userPlays.sort_values(by='normalised_pc', ascending=False)
num = 1
print(user + "'s listened to tracks in order of preference desc:")
for index, row in sortedPlays.iterrows():
track_name, artist_name = trackMeta(sortedPlays, row['track_id'])
print(str(num) + " " + track_name + " by " + artist_name)
num = num + 1
print(sortedPlays)
songData = mbzMeta(sortedPlays)
# Clean-up genres column
songData['genres'] = songData['genres'].apply(
lambda x: x.replace("[", "").replace("]", "").replace("'", ""))
genres = songData["genres"].tolist()
genreList = []
for group in genres:
genreList.append(group.split(", "))
d = {}
for item in genreList:
for genre in item:
if genre in d:
d[genre] = d[genre] + 1
from operator import itemgetter
from sklearn.model_selection import cross_val_score
from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score, make_scorer
from sklearn.preprocessing import LabelEncoder, MultiLabelBinarizer
from sklearn.svm import SVR
import matplotlib.pyplot as plt
from functions import importMappedData, mbzMeta
def mean_absolute_percentage_error(y_true, y_pred):
y_true, y_pred = np.array(y_true), np.array(y_pred)
return np.mean(np.abs((y_true - y_pred) / y_true)) * 100
# SET UP DATA
# Include the metadata for every song
data = mbzMeta(importMappedData())
# Clean-up genres column
data['genres'] = data['genres'].apply(lambda x: x.replace("[","").replace("]","").replace("'","") )
# For joining two dataframes use track_id as key
trackids = data.index
# Convert artist_id to numerical
artistids = data["artist_id"].tolist()
artistle = LabelEncoder()
artistle.fit_transform(artistids)
artist_classes = artistle.classes_
encoded_artists = artistle.transform(artistids)
encoded_artists = pd.Series(encoded_artists)
