import numpy as np
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))
import matplotlib.pyplot as plt
import pandas as pd
import sys
import os
from functions import importMappedData, trackMeta, mbzMeta, getUsers
from collections import OrderedDict, Counter
from operator import itemgetter
user = sys.argv[1]
data = importMappedData()
userData = getUsers()
userInfo = userData[userData["user_id"] == user]
gender = ""
age = 0
country = ""
try:
gender = userInfo['gender'].values[0]
age = userInfo['age'].values[0]
country = userInfo['country'].values[0]
except IndexError as err:
pass
print(user)
print("gender: " + gender)
print("age: " + str(age))
print("country: " + country)
# Create a DF with data relevant to the specified user
userPlays = pd.DataFrame(data[data["user_id"] == user],
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)