def extract_features(filename):
h5 = hdf5_getters.open_h5_file_read(filename)
f = [None] * len(features)
f[features.index('track_id')] = hdf5_getters.get_track_id(h5, 0).item()
f[features.index('song_id')] = hdf5_getters.get_song_id(h5, 0).item()
f[features.index('hotttnesss')] = hdf5_getters.get_artist_hotttnesss(
h5, 0).item()
f[features.index('danceability')] = hdf5_getters.get_danceability(
h5, 0).item()
f[features.index('duration')] = hdf5_getters.get_duration(h5, 0).item()
f[features.index('key')] = hdf5_getters.get_key(h5, 0).item()
f[features.index('energy')] = hdf5_getters.get_energy(h5, 0).item()
f[features.index('loudness')] = hdf5_getters.get_loudness(h5, 0).item()
f[features.index('year')] = hdf5_getters.get_year(h5, 0).item()
f[features.index('time_signature')] = hdf5_getters.get_time_signature(
h5, 0).item()
f[features.index('tempo')] = hdf5_getters.get_tempo(h5, 0).item()
tags = ''
for tag in hdf5_getters.get_artist_terms(h5):
tags += ('%s|' % tag)
# Remove trailing pipe.
tags = tags[:len(tags) - 1]
f[features.index('tags')] = tags
h5.close()
return f
def getSongProperties(songCount = 3000, splitData = True):
songDict = {}
songIdDict = {}
songIdCount = 0
for root, dirs, files in os.walk(msd_subset_data_path):
files = glob.glob(os.path.join(root,'*.h5'))
for f in files:
h5 = GETTERS.open_h5_file_read(f)
tempo = GETTERS.get_tempo(h5)
danceability = GETTERS.get_danceability(h5)
energy = GETTERS.get_energy(h5)
loudness = GETTERS.get_loudness(h5)
#print GETTERS.get_artist_terms(h5)
timbre = GETTERS.get_segments_timbre(h5)
artist_hotness = GETTERS.get_artist_hotttnesss(h5)
song_key = GETTERS.get_key(h5)
songIdDict[GETTERS.get_song_id(h5)] = songIdCount
songDict[songIdCount] = [tempo,danceability,energy,loudness,artist_hotness,song_key]
songIdCount += 1
h5.close()
#if len(songDict) >2:
# break
#if len(songDict) >2:
# break
if songIdCount > songCount and splitData:
break
return songIdDict,songDict
def func_to_extract_features(filename):
"""
This function extracts all features: per-track, per-section and per-segment
"""
# - open the song file
h5 = GETTERS.open_h5_file_read(filename)
# - get per-track features and put them
artist_id = GETTERS.get_artist_id(h5)
song_id = GETTERS.get_song_id(h5)
artist_familiarity = GETTERS.get_artist_familiarity(h5)
artist_hotttnesss = GETTERS.get_artist_hotttnesss(h5)
artist_latitude = GETTERS.get_artist_latitude(h5)
artist_longitude = GETTERS.get_artist_longitude(h5)
danceability = GETTERS.get_danceability(h5)
energy = GETTERS.get_energy(h5)
loudness = GETTERS.get_loudness(h5)
song_hotttnesss = GETTERS.get_song_hotttnesss(h5)
tempo = GETTERS.get_tempo(h5)
year = GETTERS.get_year(h5)
# artist_ids.add(artist_id)
# features_tuple = (artist_id, artist_familiarity, artist_hotttnesss, artist_latitude, artist_longitude, danceability, energy, loudness, song_hotttnesss, tempo, year)
features_tuple = (artist_id, artist_familiarity, artist_hotttnesss, loudness, song_hotttnesss, tempo, year)
# print features_tuple
features_tuples[song_id] = features_tuple
# files_per_artist[artist_id] += 1
# - close the file
h5.close()
def main():
#directory that contain hdf5 files.
basedir = "E://Engineering//7th_sem//AML//Project//AML_Project2018//data//MillionSongSubset//data//"
ext = ".H5"
#dont remove
print(get_headers())
#main loop
for root, _, files in os.walk(basedir):
files = glob.glob(os.path.join(root, '*' + ext))
for file in files:
#open file
songH5File = hdf5_getters.open_h5_file_read(file)
#Get the song object
song = Song(str(hdf5_getters.get_song_id(songH5File)))
#fill the attrobutes in song file
song = fill_attributes(song, songH5File)
#dont remove
print(song.convert_tostring())
songH5File.close()
def extract_data(filename):
h5 = GETTERS.open_h5_file_read(filename)
#what data you want:
track_id = GETTERS.get_song_id(h5)
h5.close()
def process_song(self, song_path):
song_data = h5.open_h5_file_read(song_path)
song_id = h5.get_song_id(song_data).decode('UTF-8')
song_int_id = int(h5.get_track_7digitalid(song_data))
song_name = h5.get_title(song_data).decode('UTF-8').lower()
artist_name = h5.get_artist_name(song_data).decode('UTF-8').lower()
song_year = int(h5.get_year(song_data))
timbre = self.ndarray_list_to_ndlist(h5.get_segments_timbre(song_data))
chroma = self.ndarray_list_to_ndlist(
h5.get_segments_pitches(song_data))
song_data.close()
song_dict = {
'id': song_int_id,
'source_id': song_id,
'name': song_name,
'artist': artist_name,
'year': song_year,
'timbre': timbre,
'chroma': chroma
}
return song_dict
def hdf5_to_features(file_name):
"""
Receives path to HDF5 file, returns 2 lists of identification for the song
as well as the features for the algorithm.
Parameters
----------
file_name : str
Absolute path to the HDF5 file.
Returns
-------
list1 : list
List consisting of ID, song title and artist name.
list2 : list
34 features to represent the song.
"""
with hdf5_getters.open_h5_file_read(file_name) as reader:
# ID
ID = hdf5_getters.get_song_id(reader)
title = hdf5_getters.get_title(reader)
artist = hdf5_getters.get_artist_name(reader)
# Features 1-4
beat_starts = hdf5_getters.get_beats_start(reader)
beat_durations = np.diff(beat_starts, axis=0)
# try:
tempo_10, tempo_90 = np.quantile(beat_durations, [0.1, 0.9])
# except:
# print(beat_durations)
# exit()
temp_var = np.var(beat_durations)
temp_mean = np.mean(beat_durations)
# Features 5-8
segment_loudness = hdf5_getters.get_segments_loudness_max(reader)
loud_10, loud_90 = np.quantile(segment_loudness, [0.1, 0.9])
loud_var = np.var(segment_loudness)
loud_mean = np.mean(segment_loudness)
# Features 9-21
pitch_dominance = hdf5_getters.get_segments_pitches(reader)
pitch_means = pitch_dominance.mean(axis=0)
pitch_var = pitch_means.var()
# Features 22-34
timbre = hdf5_getters.get_segments_timbre(reader)
timbre_means = timbre.mean(axis=0)
timbre_var = timbre_means.var()
return [ID, title, artist], [
tempo_10, tempo_90, temp_var, temp_mean, loud_10, loud_90, loud_var,
loud_mean
] + list(pitch_means) + [pitch_var] + list(timbre_means) + [timbre_var]
def main():
# print("we in")
outputFile1 = open('../Datasets/MSDSubsetCSV.csv', 'w')
csvRowString = ""
csvRowString = "Title,ArtistName"
csvAttributeList = re.split(',', csvRowString)
for i, v in enumerate(csvAttributeList):
csvAttributeList[i] = csvAttributeList[i].lower()
csvRowString += ",\n"
basedir = '/Users/Owner/Desktop/School/2019-2020/COMP400/MillionSongSubset/'
ext = ".h5"
#FOR LOOP
for root, dirs, files in os.walk(basedir):
files = glob.glob(os.path.join(root, '*' + ext))
for f in files:
print(f)
songH5File = hdf5_getters.open_h5_file_read(f)
song = Song(str(hdf5_getters.get_song_id(songH5File)))
song.title = str(hdf5_getters.get_title(songH5File)).replace(
"b'", "").lower()
song.artistName = str(
hdf5_getters.get_artist_name(songH5File)).replace("b'",
"").lower()
song.year = str(hdf5_getters.get_year(songH5File))
if (int(song.year) < 1990):
print('nope', int(song.year))
continue
for attribute in csvAttributeList:
# print "Here is the attribute: " + attribute + " \n"
if attribute == 'ArtistName'.lower():
csvRowString += "\"" + song.artistName.replace(
"'", "") + "\"" #took out "\"" before and after
elif attribute == 'Title'.lower():
csvRowString += "\"" + song.title.replace("'", "") + "\""
else:
csvRowString += "Erm. This didn't work. Error. :( :(\n"
csvRowString += ","
#Remove the final comma from each row in the csv
lastIndex = len(csvRowString)
csvRowString = csvRowString[0:lastIndex - 1]
csvRowString += "\n"
outputFile1.write(csvRowString)
csvRowString = ""
songH5File.close()
outputFile1.close()
def func_to_get_instrumental(filename):
h5 = GETTERS.open_h5_file_read(filename)
tags = set(GETTERS.get_artist_mbtags(h5))
genres = {'classical', 'orchestral'}
if tags.intersection(genres):
d = {}
d['artist'] = GETTERS.get_artist_name(h5)
d['title'] = GETTERS.get_title(h5)
song_id = GETTERS.get_song_id(h5)
classical[song_id] = d
h5.close()
def extract_data(filename):
h5 = GETTERS.open_h5_file_read(filename)
track_id = GETTERS.get_song_id(h5)
if track_id in already:
h5.close()
return
songdata[track_id].append(GETTERS.get_title(h5))
songdata[track_id].append(GETTERS.get_artist_name(h5))
songdata[track_id].append(GETTERS.get_duration)
h5.close()
def getArtistNameAndSongName(filename):
"""
This function does 3 simple things:
- open the song file
- get artist ID and put it
- close the file
"""
h5 = GETTERS.open_h5_file_read(filename)
artist_name = GETTERS.get_artist_name(h5)
song_name = GETTERS.get_title(h5)
song_id = GETTERS.get_song_id(h5)
songsAndArtists[str(song_id)] = tuple((artist_name,song_name))
h5.close()
def getArtistNameAndSongName(filename):
"""
This function does 3 simple things:
- open the song file
- get artist ID and put it
- close the file
"""
h5 = GETTERS.open_h5_file_read(filename)
artist_name = GETTERS.get_artist_name(h5)
song_name = GETTERS.get_title(h5)
song_id = GETTERS.get_song_id(h5)
songsAndArtists[str(song_id)] = tuple((artist_name, song_name))
h5.close()
def _extractSongData(file_path, filename):
# song_id, title, release, artist_name, year
h5 = hdf5_getters.open_h5_file_read(file_path)
track_id = filename[:-3]
song_id = hdf5_getters.get_song_id(h5).decode('UTF-8')
dig7_id = hdf5_getters.get_track_7digitalid(h5)
title = hdf5_getters.get_title(h5).decode('UTF-8')
release = hdf5_getters.get_release(h5).decode('UTF-8')
artist_name = hdf5_getters.get_artist_name(h5).decode('UTF-8')
year = hdf5_getters.get_year(h5)
h5.close()
# print(song_id, track_id, dig7_id, title, release, artist_name, year)
return track_id, song_id, dig7_id, title, release, artist_name, year
def create_idix(h5, msd_path):
'''
Creates indices for the million songs.
The reason is because songs are accessed as indices from 0
to (the maximum number of songs - 1) and not SongIDs.
'''
import hdf5_getters
totsng = hdf5_getters.get_num_songs(h5)
idixdic = dict()
for count in range(0, totsng):
idixdic[hdf5_getters.get_song_id(h5, count)] = count
idixfile = open("songidix.txt", "wb")
pickle.dump(idixdic, idixfile)
idixfile.close()
def create_idix(h5, msd_path):
'''
Creates indices for the million songs.
The reason is because songs are accessed as indices from 0
to (the maximum number of songs - 1) and not SongIDs.
'''
import hdf5_getters
totsng = hdf5_getters.get_num_songs(h5)
idixdic = dict()
for count in range(0, totsng):
idixdic[hdf5_getters.get_song_id(h5, count)] = count
idixfile = open("songidix.txt", "wb")
pickle.dump(idixdic, idixfile)
idixfile.close()
def insert_song():
print('Inserting song tuples')
conn = get_conn()
cursor = get_cursor(conn)
__id = None
__title = None
__avg_rate = None
__release_date = None
__duration = None
__price = None
__provider_name = None
__genre_id = None
__singer_id = None
__download = None
try:
for i in range(hard.NUM_SONGS):
__id = bytes2str(GETTERS.get_song_id(h5, i))
__title = bytes2str(GETTERS.get_title(h5, i))
__avg_rate = 0.0
# use int() to transform the numpy.int32 to int which is supported by Oracle
__release_date = int(GETTERS.get_year(h5, i))
if __release_date == 0:
__release_date = None
__duration = int(GETTERS.get_duration(h5, i))
__price = InfoGenerator.gen_price()
__provider_name = InfoGenerator.get_provider_name()
__genre_id = InfoGenerator.get_genre_id()
__singer_id = bytes2str(GETTERS.get_artist_id(h5, i))
__download = 0
cursor.execute(sql.INSERT_SONG,
id = __id, title = __title, avg_rate = __avg_rate, release_date = __release_date,
duration = __duration, price = __price, provider_name = __provider_name,
genre_id = __genre_id, singer_id = __singer_id, download = __download)
songs[i] = Song(__id, __title, __avg_rate, __release_date, __duration, __price,
__provider_name, __genre_id, __singer_id, __download)
return 0
except Exception as e:
print(e)
print('i:', i, '\nid:',__id, '\ntitle:', __title, '\navg_rate:', __avg_rate,
'\nrelease_date:', __release_date, '\nduration', __duration, '\nprice', __price,
'provider_name:',__provider_name, '\ngenre_id:', __genre_id, '\nsinger_id', __singer_id,
'download:',__download)
return -1
finally:
conn.commit()
close_all(conn, cursor)
def process_song(h5_song_file):
song = {}
song['artist_familiarity'] = hdf5_getters.get_artist_familiarity(h5)
song['artist_id'] = hdf5_getters.get_artist_id(h5)
song['artist_name'] = hdf5_getters.get_artist_name(h5)
song['artist_hotttnesss'] = hdf5_getters.get_artist_hotttnesss(h5);
song['title'] = hdf5_getters.get_title(h5)
terms = hdf5_getters.get_artist_terms(h5)
terms_freq = hdf5_getters.get_artist_terms_freq(h5)
terms_weight = hdf5_getters.get_artist_terms_weight(h5)
terms_array = []
# Creating a array of [term, its frequency, its weight]. Doing this for all terms associated
# with the artist
for i in range(len(terms)):
terms_array.append([terms[i], terms_freq[i], terms_weight[i]])
song['artist_terms'] = terms_array
beats_start = hdf5_getters.get_beats_start(h5)
song['beats_start_variance'] = variance(beats_start) #beats variance in yocto seconds(10^-24s)
song['number_of_beats'] = len(beats_start)
song['duration'] = hdf5_getters.get_duration(h5)
song['loudness'] = hdf5_getters.get_loudness(h5)
sections_start = hdf5_getters.get_sections_start(h5)
song['sections_start_variance'] = variance(sections_start)
song['number_of_sections'] = len(sections_start)
segments_pitches = hdf5_getters.get_segments_pitches(h5)
(a0, a1, a2, a3, a4, a5, a6, a7, a8, a9, a10, a11) = split_segments(segments_pitches)
song['segments_pitches_variance'] = [variance(a0), variance(a1), variance(a2),
variance(a3), variance(a4), variance(a5), variance(a6), variance(a7),
variance(a8), variance(a9), variance(a10), variance(a11)]
song['segments_pitches_mean'] = [mean(a0), mean(a1), mean(a2), mean(a3), mean(a4),
mean(a5), mean(a6), mean(a7), mean(a8), mean(a9), mean(a10), mean(a11)]
segments_timbre = hdf5_getters.get_segments_timbre(h5)
(a0, a1, a2, a3, a4, a5, a6, a7, a8, a9, a10, a11) = split_segments(segments_timbre)
song['segments_timbre_variance'] = [variance(a0), variance(a1), variance(a2),
variance(a3), variance(a4), variance(a5), variance(a6), variance(a7),
variance(a8), variance(a9), variance(a10), variance(a11)]
song['segments_timbre_mean'] = [mean(a0), mean(a1), mean(a2), mean(a3), mean(a4),
mean(a5), mean(a6), mean(a7), mean(a8), mean(a9), mean(a10), mean(a11)]
song['tempo'] = hdf5_getters.get_tempo(h5)
song['_id'] = hdf5_getters.get_song_id(h5)
song['year'] = hdf5_getters.get_year(h5)
return song
def fetch_energy_feature(track,h5=None):
#get energy of the track => uses pyechonest library
close = (h5== None)
if h5==None:
path = "../../msd_dense_subset/mood/"+track[2]+"/"+track[3]+"/"+track[4]+"/"+track+".h5"
h5 = GETTERS.open_h5_file_read(path)
songid = GETTERS.get_song_id(h5)
if close:
h5.close()
results = song.profile(songid)
if len(results) == 0:
return 0
track = results[0]
energy = track.audio_summary['energy']
if (energy != None):
return float(energy)
else :
return 0
def main():
#directory that contain hdf5 files.
basedir = "E://Engineering//7th_sem//AML//Project//AML_Project2018//data//MillionSongSubset//data//"
ext = ".H5"
ouputcsv = "E://Engineering//7th_sem//AML//Project//AML_Project2018//data//msd_final.csv"
count = 0
#clear contents of file
with open(ouputcsv, 'w') as fd:
print("Cleared existing contents")
#Add headers
with open(ouputcsv, 'a') as fd:
text = get_headers()
fd.write(text)
fd.write("\n")
#main loop
for root, _, files in os.walk(basedir):
files = glob.glob(os.path.join(root, '*' + ext))
for file in files:
#open file
songH5File = hdf5_getters.open_h5_file_read(file)
#Get the song object
song = Song(str(hdf5_getters.get_song_id(songH5File)))
#fill the attrobutes in song file
song = fill_attributes(song, songH5File)
#Add songs line by line
with open(ouputcsv, 'a') as fd:
text = song.convert_tostring()
fd.write(text)
fd.write("\n")
songH5File.close()
count = count + 1
print(count)
def fetch_energy_feature(track, h5=None):
#get energy of the track => uses pyechonest library
close = (h5 == None)
if h5 == None:
path = "../../msd_dense_subset/mood/" + track[2] + "/" + track[
3] + "/" + track[4] + "/" + track + ".h5"
h5 = GETTERS.open_h5_file_read(path)
songid = GETTERS.get_song_id(h5)
if close:
h5.close()
results = song.profile(songid)
if len(results) == 0:
return 0
track = results[0]
energy = track.audio_summary['energy']
if (energy != None):
return float(energy)
else:
return 0
def extract_data(filename):
v = [0,0]
h5 = GETTERS.open_h5_file_read(filename)
#what data you want:
track_id = GETTERS.get_song_id(h5)
data = GETTERS.get_segments_pitches(h5)
mfcc = np.zeros((12,dist))
flag = 0
for i in range(12):
try:
mfcc[i,:] = data[begin:end, i]
except ValueError:
flag = 1
if flag==0:
v[0] = track_id
v[1] = mfcc
h5.close()
return v
def get_all_data(target, basedir, ext='.h5') :
# header
target.write("%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\n" % (
"track_id", "song_id", "title", "artist_name", "artist_location",
"artist_hotttnesss", "release", "year", "song_hotttnesss",
"danceability", "duration", "loudness", "sample_rate", "tempo"
))
count = 0
for root, dirs, files in os.walk(basedir):
files = glob.glob(os.path.join(root,'*'+ext))
for f in files:
for line in f:
new_file = open("tmp.txt", 'w')
new_file.write(line)
h5 = hdf5_getters.open_h5_file_read(new_file)
target.write("%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\n" % (
hdf5_getters.get_track_id(h5),
hdf5_getters.get_song_id(h5),
hdf5_getters.get_title(h5),
hdf5_getters.get_artist_name(h5),
hdf5_getters.get_artist_location(h5),
hdf5_getters.get_artist_hotttnesss(h5),
hdf5_getters.get_release(h5),
hdf5_getters.get_year(h5),
hdf5_getters.get_song_hotttnesss(h5),
hdf5_getters.get_danceability(h5),
hdf5_getters.get_duration(h5),
hdf5_getters.get_loudness(h5),
hdf5_getters.get_analysis_sample_rate(h5),
hdf5_getters.get_tempo(h5)
))
# show progress
count += 1
print "%d/10000" % (count)
h5.close()
def get7DigitalIDs(self, file):
#get the 7digital id
h5 = GETTERS.open_h5_file_read(file)
id7 = GETTERS.get_track_7digitalid(h5)
song_id = GETTERS.get_song_id(h5).decode("UTF-8")
# print(id7)
#put it into the database
try:
self.cursor.execute("UPDATE songs SET track_7digitalid = {} WHERE song_id == '{}';".format(id7, song_id))
self.conn.commit()
except Exception as e:
print ("couldn't insert into database")
print ("reason: ", e)
h5.close()
return -1
#close the h5 file
h5.close()
return 0
def get_all_attributes(filename):
"""
This function does 3 simple things:
- open the song file
- get all required attributes
- write it to a csv file
- close the files
"""
with open('attributes.csv', 'a') as csvfile:
try:
# let's apply the previous function to all files
csvwriter = csv.writer(csvfile, delimiter='\t')
h5 = GETTERS.open_h5_file_read(filename)
RESULTS = []
RESULTS.append(GETTERS.get_year(h5))
RESULTS.append(GETTERS.get_artist_id(h5))
RESULTS.append(GETTERS.get_artist_name(h5))
RESULTS.append(GETTERS.get_artist_mbid(h5))
RESULTS.append(convert_terms(GETTERS.get_artist_terms(h5)))
RESULTS.append(GETTERS.get_artist_hotttnesss(h5))
RESULTS.append(GETTERS.get_artist_latitude(h5))
RESULTS.append(GETTERS.get_artist_longitude(h5))
RESULTS.append(GETTERS.get_artist_familiarity(h5))
RESULTS.append(GETTERS.get_danceability(h5))
RESULTS.append(GETTERS.get_duration(h5))
RESULTS.append(GETTERS.get_energy(h5))
RESULTS.append(GETTERS.get_loudness(h5))
RESULTS.append(GETTERS.get_song_hotttnesss(h5))
RESULTS.append(GETTERS.get_song_id(h5))
RESULTS.append(GETTERS.get_tempo(h5))
RESULTS.append(GETTERS.get_time_signature(h5))
RESULTS.append(GETTERS.get_title(h5))
RESULTS.append(GETTERS.get_track_id(h5))
RESULTS.append(GETTERS.get_release(h5))
csvwriter.writerow(RESULTS)
h5.close()
except AttributeError:
pass
def data_to_flat_file(basedir,ext='.h5') :
""" This function extracts the information from the tables and creates the flat file. """
count = 0; #song counter
list_to_write= []
group_index=0
row_to_write = ""
writer = csv.writer(open("complete.csv", "wb"))
for root, dirs, files in os.walk(basedir):
files = glob.glob(os.path.join(root,'*'+ext))
for f in files:
row=[]
print f
h5 = hdf5_getters.open_h5_file_read(f)
title = hdf5_getters.get_title(h5)
title= title.replace('"','')
row.append(title)
comma=title.find(',')
if comma != -1:
print title
time.sleep(1)
album = hdf5_getters.get_release(h5)
album= album.replace('"','')
row.append(album)
comma=album.find(',')
if comma != -1:
print album
time.sleep(1)
artist_name = hdf5_getters.get_artist_name(h5)
comma=artist_name.find(',')
if comma != -1:
print artist_name
time.sleep(1)
artist_name= artist_name.replace('"','')
row.append(artist_name)
duration = hdf5_getters.get_duration(h5)
row.append(duration)
samp_rt = hdf5_getters.get_analysis_sample_rate(h5)
row.append(samp_rt)
artist_7digitalid = hdf5_getters.get_artist_7digitalid(h5)
row.append(artist_7digitalid)
artist_fam = hdf5_getters.get_artist_familiarity(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(artist_fam) == True:
artist_fam=-1
row.append(artist_fam)
artist_hotness= hdf5_getters.get_artist_hotttnesss(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(artist_hotness) == True:
artist_hotness=-1
row.append(artist_hotness)
artist_id = hdf5_getters.get_artist_id(h5)
row.append(artist_id)
artist_lat = hdf5_getters.get_artist_latitude(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(artist_lat) == True:
artist_lat=-1
row.append(artist_lat)
artist_loc = hdf5_getters.get_artist_location(h5)
row.append(artist_loc)
artist_lon = hdf5_getters.get_artist_longitude(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(artist_lon) == True:
artist_lon=-1
row.append(artist_lon)
artist_mbid = hdf5_getters.get_artist_mbid(h5)
row.append(artist_mbid)
#Getting the genre
art_trm = hdf5_getters.get_artist_terms(h5)
trm_freq = hdf5_getters.get_artist_terms_freq(h5)
trn_wght = hdf5_getters.get_artist_terms_weight(h5)
a_mb_tags = hdf5_getters.get_artist_mbtags(h5)
genre_indexes=get_genre_indexes(trm_freq) #index of the highest freq
genre_set=0 #flag to see if the genre has been set or not
final_genre=[]
genres_so_far=[]
for i in range(len(genre_indexes)):
genre_tmp=get_genre(art_trm,genre_indexes[i]) #genre that corresponds to the highest freq
genres_so_far=genre_dict.get_genre_in_dict(genre_tmp) #getting the genre from the dictionary
if len(genres_so_far) != 0:
for i in genres_so_far:
final_genre.append(i)
genre_set=1
if genre_set == 1:
col_num=[]
for i in final_genre:
column=int(i) #getting the column number of the genre
col_num.append(column)
genre_array=genre_columns(col_num) #genre array
for i in range(len(genre_array)): #appending the genre_array to the row
row.append(genre_array[i])
else:
genre_array=genre_columns(-1) #when there is no genre matched, return an array of [0...0]
for i in range(len(genre_array)): #appending the genre_array to the row
row.append(genre_array[i])
artist_pmid = hdf5_getters.get_artist_playmeid(h5)
row.append(artist_pmid)
audio_md5 = hdf5_getters.get_audio_md5(h5)
row.append(audio_md5)
danceability = hdf5_getters.get_danceability(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(danceability) == True:
danceability=-1
row.append(danceability)
end_fade_in =hdf5_getters.get_end_of_fade_in(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(end_fade_in) == True:
end_fade_in=-1
row.append(end_fade_in)
energy = hdf5_getters.get_energy(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(energy) == True:
energy=-1
row.append(energy)
song_key = hdf5_getters.get_key(h5)
row.append(song_key)
key_c = hdf5_getters.get_key_confidence(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(key_c) == True:
key_c=-1
row.append(key_c)
loudness = hdf5_getters.get_loudness(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(loudness) == True:
loudness=-1
row.append(loudness)
mode = hdf5_getters.get_mode(h5)
row.append(mode)
mode_conf = hdf5_getters.get_mode_confidence(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(mode_conf) == True:
mode_conf=-1
row.append(mode_conf)
release_7digitalid = hdf5_getters.get_release_7digitalid(h5)
row.append(release_7digitalid)
song_hot = hdf5_getters.get_song_hotttnesss(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(song_hot) == True:
song_hot=-1
row.append(song_hot)
song_id = hdf5_getters.get_song_id(h5)
row.append(song_id)
start_fade_out = hdf5_getters.get_start_of_fade_out(h5)
row.append(start_fade_out)
tempo = hdf5_getters.get_tempo(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(tempo) == True:
tempo=-1
row.append(tempo)
time_sig = hdf5_getters.get_time_signature(h5)
row.append(time_sig)
time_sig_c = hdf5_getters.get_time_signature_confidence(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(time_sig_c) == True:
time_sig_c=-1
row.append(time_sig_c)
track_id = hdf5_getters.get_track_id(h5)
row.append(track_id)
track_7digitalid = hdf5_getters.get_track_7digitalid(h5)
row.append(track_7digitalid)
year = hdf5_getters.get_year(h5)
row.append(year)
bars_c = hdf5_getters.get_bars_confidence(h5)
bars_start = hdf5_getters.get_bars_start(h5)
row_bars_padding=padding(245) #this is the array that will be attached at the end of th row
#--------------bars---------------"
gral_info=[]
gral_info=row[:]
empty=[]
for i,item in enumerate(bars_c):
row.append(group_index)
row.append(i)
row.append(bars_c[i])
bars_c_avg= get_avg(bars_c)
row.append(bars_c_avg)
bars_c_max= get_max(bars_c)
row.append(bars_c_max)
bars_c_min = get_min(bars_c)
row.append(bars_c_min)
bars_c_stddev= get_stddev(bars_c)
row.append(bars_c_stddev)
bars_c_count = get_count(bars_c)
row.append(bars_c_count)
bars_c_sum = get_sum(bars_c)
row.append(bars_c_sum)
row.append(bars_start[i])
bars_start_avg = get_avg(bars_start)
row.append(bars_start_avg)
bars_start_max= get_max(bars_start)
row.append(bars_start_max)
bars_start_min = get_min(bars_start)
row.append(bars_start_min)
bars_start_stddev= get_stddev(bars_start)
row.append(bars_start_stddev)
bars_start_count = get_count(bars_start)
row.append(bars_start_count)
bars_start_sum = get_sum(bars_start)
row.append(bars_start_sum)
for i in row_bars_padding:
row.append(i)
writer.writerow(row)
row=[]
row=gral_info[:]
#--------beats---------------"
beats_c = hdf5_getters.get_beats_confidence(h5)
group_index=1
row=[]
row=gral_info[:]
row_front=padding(14) #blanks left in front of the row(empty spaces for bars)
row_beats_padding=padding(231)
for i,item in enumerate(beats_c):
row.append(group_index)
row.append(i)
for index in row_front: #padding blanks in front of the beats
row.append(index)
row.append(beats_c[i])
beats_c_avg= get_avg(beats_c)
row.append(beats_c_avg)
beats_c_max= get_max(beats_c)
row.append(beats_c_max)
beats_c_min = get_min(beats_c)
row.append(beats_c_min)
beats_c_stddev= get_stddev(beats_c)
row.append(beats_c_stddev)
beats_c_count = get_count(beats_c)
row.append(beats_c_count)
beats_c_sum = get_sum(beats_c)
row.append(beats_c_sum)
beats_start = hdf5_getters.get_beats_start(h5)
row.append(beats_start[i])
beats_start_avg = get_avg(beats_start)
row.append(beats_start_avg)
beats_start_max= get_max(beats_start)
row.append(beats_start_max)
beats_start_min = get_min(beats_start)
row.append(beats_start_min)
beats_start_stddev= get_stddev(beats_start)
row.append(beats_start_stddev)
beats_start_count = get_count(beats_start)
row.append(beats_start_count)
beats_start_sum = get_sum(beats_start)
row.append(beats_start_sum)
for i in row_beats_padding:
row.append(i)
writer.writerow(row)
row=[]
row=gral_info[:]
# "--------sections---------------"
row_sec_padding=padding(217) #blank spaces left at the end of the row
sec_c = hdf5_getters.get_sections_confidence(h5)
group_index=2
row=[]
row=gral_info[:]
row_front=padding(28) #blank spaces left in front(empty spaces for bars,beats)
for i,item in enumerate(sec_c):
row.append(group_index)
row.append(i)
for index in row_front: #padding blanks in front of the sections
row.append(index)
row.append(sec_c[i])
sec_c_avg= get_avg(sec_c)
row.append(sec_c_avg)
sec_c_max= get_max(sec_c)
row.append(sec_c_max)
sec_c_min = get_min(sec_c)
row.append(sec_c_min)
sec_c_stddev= get_stddev(sec_c)
row.append(sec_c_stddev)
sec_c_count = get_count(sec_c)
row.append(sec_c_count)
sec_c_sum = get_sum(sec_c)
row.append(sec_c_sum)
sec_start = hdf5_getters.get_sections_start(h5)
row.append(sec_start[i])
sec_start_avg = get_avg(sec_start)
row.append(sec_start_avg)
sec_start_max= get_max(sec_start)
row.append(sec_start_max)
sec_start_min = get_min(sec_start)
row.append(sec_start_min)
sec_start_stddev= get_stddev(sec_start)
row.append(sec_start_stddev)
sec_start_count = get_count(sec_start)
row.append(sec_start_count)
sec_start_sum = get_sum(sec_start)
row.append(sec_start_sum)
for i in row_sec_padding: #appending the blank spaces at the end of the row
row.append(i)
writer.writerow(row)
row=[]
row=gral_info[:]
#--------segments---------------"
row_seg_padding=padding(182) #blank spaces at the end of the row
row_front=padding(42) #blank spaces left in front of segments
seg_c = hdf5_getters.get_segments_confidence(h5)
group_index=3
row=[]
row=gral_info[:]
for i,item in enumerate(seg_c):
row.append(group_index)
row.append(i)
for index in row_front: #padding blanks in front of the segments
row.append(index)
row.append(seg_c[i])
seg_c_avg= get_avg(seg_c)
row.append(seg_c_avg)
seg_c_max= get_max(seg_c)
row.append(seg_c_max)
seg_c_min = get_min(seg_c)
row.append(seg_c_min)
seg_c_stddev= get_stddev(seg_c)
row.append(seg_c_stddev)
seg_c_count = get_count(seg_c)
row.append(seg_c_count)
seg_c_sum = get_sum(seg_c)
row.append(seg_c_sum)
seg_loud_max = hdf5_getters.get_segments_loudness_max(h5)
row.append(seg_loud_max[i])
seg_loud_max_avg= get_avg(seg_loud_max)
row.append(seg_loud_max_avg)
seg_loud_max_max= get_max(seg_loud_max)
row.append(seg_loud_max_max)
seg_loud_max_min = get_min(seg_loud_max)
row.append(seg_loud_max_min)
seg_loud_max_stddev= get_stddev(seg_loud_max)
row.append(seg_loud_max_stddev)
seg_loud_max_count = get_count(seg_loud_max)
row.append(seg_loud_max_count)
seg_loud_max_sum = get_sum(seg_loud_max)
row.append(seg_loud_max_sum)
seg_loud_max_time = hdf5_getters.get_segments_loudness_max_time(h5)
row.append(seg_loud_max_time[i])
seg_loud_max_time_avg= get_avg(seg_loud_max_time)
row.append(seg_loud_max_time_avg)
seg_loud_max_time_max= get_max(seg_loud_max_time)
row.append(seg_loud_max_time_max)
seg_loud_max_time_min = get_min(seg_loud_max_time)
row.append(seg_loud_max_time_min)
seg_loud_max_time_stddev= get_stddev(seg_loud_max_time)
row.append(seg_loud_max_time_stddev)
seg_loud_max_time_count = get_count(seg_loud_max_time)
row.append(seg_loud_max_time_count)
seg_loud_max_time_sum = get_sum(seg_loud_max_time)
row.append(seg_loud_max_time_sum)
seg_loud_start = hdf5_getters.get_segments_loudness_start(h5)
row.append(seg_loud_start[i])
seg_loud_start_avg= get_avg(seg_loud_start)
row.append(seg_loud_start_avg)
seg_loud_start_max= get_max(seg_loud_start)
row.append(seg_loud_start_max)
seg_loud_start_min = get_min(seg_loud_start)
row.append(seg_loud_start_min)
seg_loud_start_stddev= get_stddev(seg_loud_start)
row.append(seg_loud_start_stddev)
seg_loud_start_count = get_count(seg_loud_start)
row.append(seg_loud_start_count)
seg_loud_start_sum = get_sum(seg_loud_start)
row.append(seg_loud_start_sum)
seg_start = hdf5_getters.get_segments_start(h5)
row.append(seg_start[i])
seg_start_avg= get_avg(seg_start)
row.append(seg_start_avg)
seg_start_max= get_max(seg_start)
row.append(seg_start_max)
seg_start_min = get_min(seg_start)
row.append(seg_start_min)
seg_start_stddev= get_stddev(seg_start)
row.append(seg_start_stddev)
seg_start_count = get_count(seg_start)
row.append(seg_start_count)
seg_start_sum = get_sum(seg_start)
row.append(seg_start_sum)
for i in row_seg_padding: #appending blank spaces at the end of the row
row.append(i)
writer.writerow(row)
row=[]
row=gral_info[:]
#----------segments pitch and timbre---------------"
row_seg2_padding=padding(14) #blank spaces left at the end of the row
row_front=padding(77) #blank spaces left at the front of the segments and timbre
seg_pitch = hdf5_getters.get_segments_pitches(h5)
transpose_pitch= seg_pitch.transpose() #this is to tranpose the matrix,so we can have 12 rows
group_index=4
row=[]
row=gral_info[:]
for i,item in enumerate(transpose_pitch[0]):
row.append(group_index)
row.append(i)
for index in row_front: #padding blanks in front of segments and timbre
row.append(index)
row.append(transpose_pitch[0][i])
seg_pitch_avg= get_avg(transpose_pitch[0])
row.append(seg_pitch_avg)
seg_pitch_max= get_max(transpose_pitch[0])
row.append(seg_pitch_max)
seg_pitch_min = get_min(transpose_pitch[0])
row.append(seg_pitch_min)
seg_pitch_stddev= get_stddev(transpose_pitch[0])
row.append(seg_pitch_stddev)
seg_pitch_count = get_count(transpose_pitch[0])
row.append(seg_pitch_count)
seg_pitch_sum = get_sum(transpose_pitch[0])
row.append(seg_pitch_sum)
row.append(transpose_pitch[1][i])
seg_pitch_avg= get_avg(transpose_pitch[1])
row.append(seg_pitch_avg)
seg_pitch_max= get_max(transpose_pitch[1])
row.append(seg_pitch_max)
seg_pitch_min = get_min(transpose_pitch[1])
row.append(seg_pitch_min)
seg_pitch_stddev= get_stddev(transpose_pitch[1])
row.append(seg_pitch_stddev)
seg_pitch_count = get_count(transpose_pitch[1])
row.append(seg_pitch_count)
seg_pitch_sum = get_sum(transpose_pitch[1])
row.append(seg_pitch_sum)
row.append(transpose_pitch[2][i])
seg_pitch_avg= get_avg(transpose_pitch[2])
row.append(seg_pitch_avg)
seg_pitch_max= get_max(transpose_pitch[2])
row.append(seg_pitch_max)
seg_pitch_min = get_min(transpose_pitch[2])
row.append(seg_pitch_min)
seg_pitch_stddev= get_stddev(transpose_pitch[2])
row.append(seg_pitch_stddev)
seg_pitch_count = get_count(transpose_pitch[2])
row.append(seg_pitch_count)
seg_pitch_sum = get_sum(transpose_pitch[2])
row.append(seg_pitch_sum)
row.append(transpose_pitch[3][i])
seg_pitch_avg= get_avg(transpose_pitch[3])
row.append(seg_pitch_avg)
seg_pitch_max= get_max(transpose_pitch[3])
row.append(seg_pitch_max)
seg_pitch_min = get_min(transpose_pitch[3])
row.append(seg_pitch_min)
seg_pitch_stddev= get_stddev(transpose_pitch[3])
row.append(seg_pitch_stddev)
seg_pitch_count = get_count(transpose_pitch[3])
row.append(seg_pitch_count)
seg_pitch_sum = get_sum(transpose_pitch[3])
row.append(seg_pitch_sum)
row.append(transpose_pitch[4][i])
seg_pitch_avg= get_avg(transpose_pitch[4])
row.append(seg_pitch_avg)
seg_pitch_max= get_max(transpose_pitch[4])
row.append(seg_pitch_max)
seg_pitch_min = get_min(transpose_pitch[4])
row.append(seg_pitch_min)
seg_pitch_stddev= get_stddev(transpose_pitch[4])
row.append(seg_pitch_stddev)
seg_pitch_count = get_count(transpose_pitch[4])
row.append(seg_pitch_count)
seg_pitch_sum = get_sum(transpose_pitch[4])
row.append(seg_pitch_sum)
row.append(transpose_pitch[5][i])
seg_pitch_avg= get_avg(transpose_pitch[5])
row.append(seg_pitch_avg)
seg_pitch_max= get_max(transpose_pitch[5])
row.append(seg_pitch_max)
seg_pitch_min = get_min(transpose_pitch[5])
row.append(seg_pitch_min)
seg_pitch_stddev= get_stddev(transpose_pitch[5])
row.append(seg_pitch_stddev)
seg_pitch_count = get_count(transpose_pitch[5])
row.append(seg_pitch_count)
seg_pitch_sum = get_sum(transpose_pitch[5])
row.append(seg_pitch_sum)
row.append(transpose_pitch[6][i])
seg_pitch_avg= get_avg(transpose_pitch[6])
row.append(seg_pitch_avg)
seg_pitch_max= get_max(transpose_pitch[6])
row.append(seg_pitch_max)
seg_pitch_min = get_min(transpose_pitch[6])
row.append(seg_pitch_min)
seg_pitch_stddev= get_stddev(transpose_pitch[6])
row.append(seg_pitch_stddev)
seg_pitch_count = get_count(transpose_pitch[6])
row.append(seg_pitch_count)
seg_pitch_sum = get_sum(transpose_pitch[6])
row.append(seg_pitch_sum)
row.append(transpose_pitch[7][i])
seg_pitch_avg= get_avg(transpose_pitch[7])
row.append(seg_pitch_avg)
seg_pitch_max= get_max(transpose_pitch[7])
row.append(seg_pitch_max)
seg_pitch_min = get_min(transpose_pitch[7])
row.append(seg_pitch_min)
seg_pitch_stddev= get_stddev(transpose_pitch[7])
row.append(seg_pitch_stddev)
seg_pitch_count = get_count(transpose_pitch[7])
row.append(seg_pitch_count)
seg_pitch_sum = get_sum(transpose_pitch[7])
row.append(seg_pitch_sum)
row.append(transpose_pitch[8][i])
seg_pitch_avg= get_avg(transpose_pitch[8])
row.append(seg_pitch_avg)
seg_pitch_max= get_max(transpose_pitch[8])
row.append(seg_pitch_max)
seg_pitch_min = get_min(transpose_pitch[8])
row.append(seg_pitch_min)
seg_pitch_stddev= get_stddev(transpose_pitch[8])
row.append(seg_pitch_stddev)
seg_pitch_count = get_count(transpose_pitch[8])
row.append(seg_pitch_count)
seg_pitch_sum = get_sum(transpose_pitch[8])
row.append(seg_pitch_sum)
row.append(transpose_pitch[9][i])
seg_pitch_avg= get_avg(transpose_pitch[9])
row.append(seg_pitch_avg)
seg_pitch_max= get_max(transpose_pitch[9])
row.append(seg_pitch_max)
seg_pitch_min = get_min(transpose_pitch[9])
row.append(seg_pitch_min)
seg_pitch_stddev= get_stddev(transpose_pitch[9])
row.append(seg_pitch_stddev)
seg_pitch_count = get_count(transpose_pitch[9])
row.append(seg_pitch_count)
seg_pitch_sum = get_sum(transpose_pitch[9])
row.append(seg_pitch_sum)
row.append(transpose_pitch[10][i])
seg_pitch_avg= get_avg(transpose_pitch[10])
row.append(seg_pitch_avg)
seg_pitch_max= get_max(transpose_pitch[10])
row.append(seg_pitch_max)
seg_pitch_min = get_min(transpose_pitch[10])
row.append(seg_pitch_min)
seg_pitch_stddev= get_stddev(transpose_pitch[10])
row.append(seg_pitch_stddev)
seg_pitch_count = get_count(transpose_pitch[10])
row.append(seg_pitch_count)
seg_pitch_sum = get_sum(transpose_pitch[10])
row.append(seg_pitch_sum)
row.append(transpose_pitch[11][i])
seg_pitch_avg= get_avg(transpose_pitch[11])
row.append(seg_pitch_avg)
seg_pitch_max= get_max(transpose_pitch[11])
row.append(seg_pitch_max)
seg_pitch_min = get_min(transpose_pitch[11])
row.append(seg_pitch_min)
seg_pitch_stddev= get_stddev(transpose_pitch[11])
row.append(seg_pitch_stddev)
seg_pitch_count = get_count(transpose_pitch[11])
row.append(seg_pitch_count)
seg_pitch_sum = get_sum(transpose_pitch[11])
row.append(seg_pitch_sum)
#timbre arrays
seg_timbre = hdf5_getters.get_segments_timbre(h5)
transpose_timbre = seg_pitch.transpose() #tranposing matrix, to have 12 rows
row.append(transpose_timbre[0][i])
seg_timbre_avg= get_avg(transpose_timbre[0])
row.append(seg_timbre_avg)
seg_timbre_max= get_max(transpose_timbre[0])
row.append(seg_timbre_max)
seg_timbre_min = get_min(transpose_timbre[0])
row.append(seg_timbre_min)
seg_timbre_stddev=get_stddev(transpose_timbre[0])
row.append(seg_timbre_stddev)
seg_timbre_count = get_count(transpose_timbre[0])
row.append(seg_timbre_count)
seg_timbre_sum = get_sum(transpose_timbre[0])
row.append(seg_timbre_sum)
row.append(transpose_timbre[1][i])
seg_timbre_avg= get_avg(transpose_timbre[1])
row.append(seg_timbre_avg)
seg_timbre_max= get_max(transpose_timbre[1])
row.append(seg_timbre_max)
seg_timbre_min = get_min(transpose_timbre[1])
row.append(seg_timbre_min)
seg_timbre_stddev= get_stddev(transpose_timbre[1])
row.append(seg_timbre_stddev)
seg_timbre_count = get_count(transpose_timbre[1])
row.append(seg_timbre_count)
seg_timbre_sum = get_sum(transpose_timbre[1])
row.append(seg_timbre_sum)
row.append(transpose_timbre[2][i])
seg_timbre_avg= get_avg(transpose_timbre[2])
row.append(seg_timbre_avg)
seg_timbre_max= get_max(transpose_timbre[2])
row.append(seg_timbre_max)
seg_timbre_min = get_min(transpose_timbre[2])
row.append(seg_timbre_min)
seg_timbre_stddev= get_stddev(transpose_timbre[2])
row.append(seg_timbre_stddev)
seg_timbre_count = get_count(transpose_timbre[2])
row.append(seg_timbre_count)
seg_timbre_sum = get_sum(transpose_timbre[2])
row.append(seg_timbre_sum)
row.append(transpose_timbre[3][i])
seg_timbre_avg= get_avg(transpose_timbre[3])
row.append(seg_timbre_avg)
seg_timbre_max= get_max(transpose_timbre[3])
row.append(seg_timbre_max)
seg_timbre_min = get_min(transpose_timbre[3])
row.append(seg_timbre_min)
seg_timbre_stddev= get_stddev(transpose_timbre[3])
row.append(seg_timbre_stddev)
seg_timbre_count = get_count(transpose_timbre[3])
row.append(seg_timbre_count)
seg_timbre_sum = get_sum(transpose_timbre[3])
row.append(seg_timbre_sum)
row.append(transpose_timbre[4][i])
seg_timbre_avg= get_avg(transpose_timbre[4])
row.append(seg_timbre_avg)
seg_timbre_max= get_max(transpose_timbre[4])
row.append(seg_timbre_max)
seg_timbre_min = get_min(transpose_timbre[4])
row.append(seg_timbre_min)
seg_timbre_stddev= get_stddev(transpose_timbre[4])
row.append(seg_timbre_stddev)
seg_timbre_count = get_count(transpose_timbre[4])
row.append(seg_timbre_count)
seg_timbre_sum = get_sum(transpose_timbre[4])
row.append(seg_timbre_sum)
row.append(transpose_timbre[5][i])
seg_timbre_avg= get_avg(transpose_timbre[5])
row.append(seg_timbre_avg)
seg_timbre_max= get_max(transpose_timbre[5])
row.append(seg_timbre_max)
seg_timbre_min = get_min(transpose_timbre[5])
row.append(seg_timbre_min)
seg_timbre_stddev= get_stddev(transpose_timbre[5])
row.append(seg_timbre_stddev)
seg_timbre_count = get_count(transpose_timbre[5])
row.append(seg_timbre_count)
seg_timbre_sum = get_sum(transpose_timbre[5])
row.append(seg_timbre_sum)
row.append(transpose_timbre[6][i])
seg_timbre_avg= get_avg(transpose_timbre[6])
row.append(seg_timbre_avg)
seg_timbre_max= get_max(transpose_timbre[6])
row.append(seg_timbre_max)
seg_timbre_min = get_min(transpose_timbre[6])
row.append(seg_timbre_min)
seg_timbre_stddev= get_stddev(transpose_timbre[6])
row.append(seg_timbre_stddev)
seg_timbre_count = get_count(transpose_timbre[6])
row.append(seg_timbre_count)
seg_timbre_sum = get_sum(transpose_timbre[6])
row.append(seg_timbre_sum)
row.append(transpose_timbre[7][i])
seg_timbre_avg= get_avg(transpose_timbre[7])
row.append(seg_timbre_avg)
seg_timbre_max= get_max(transpose_timbre[7])
row.append(seg_timbre_max)
seg_timbre_min = get_min(transpose_timbre[7])
row.append(seg_timbre_min)
seg_timbre_stddev= get_stddev(transpose_timbre[7])
row.append(seg_timbre_stddev)
seg_timbre_count = get_count(transpose_timbre[7])
row.append(seg_timbre_count)
seg_timbre_sum = get_sum(transpose_timbre[7])
row.append(seg_timbre_sum)
row.append(transpose_timbre[8][i])
seg_timbre_avg= get_avg(transpose_timbre[8])
row.append(seg_timbre_avg)
seg_timbre_max= get_max(transpose_timbre[8])
row.append(seg_timbre_max)
seg_timbre_min = get_min(transpose_timbre[8])
row.append(seg_timbre_min)
seg_timbre_stddev= get_stddev(transpose_timbre[8])
row.append(seg_timbre_stddev)
seg_timbre_count = get_count(transpose_timbre[8])
row.append(seg_timbre_count)
seg_timbre_sum = get_sum(transpose_timbre[8])
row.append(seg_timbre_sum)
row.append(transpose_timbre[9][i])
seg_timbre_avg= get_avg(transpose_timbre[9])
row.append(seg_timbre_avg)
seg_timbre_max= get_max(transpose_timbre[9])
row.append(seg_timbre_max)
seg_timbre_min = get_min(transpose_timbre[9])
row.append(seg_timbre_min)
seg_timbre_stddev= get_stddev(transpose_timbre[9])
row.append(seg_timbre_stddev)
seg_timbre_count = get_count(transpose_timbre[9])
row.append(seg_timbre_count)
seg_timbre_sum = get_sum(transpose_timbre[9])
row.append(seg_timbre_sum)
row.append(transpose_timbre[10][i])
seg_timbre_avg= get_avg(transpose_timbre[10])
row.append(seg_timbre_avg)
seg_timbre_max= get_max(transpose_timbre[10])
row.append(seg_timbre_max)
seg_timbre_min = get_min(transpose_timbre[10])
row.append(seg_timbre_min)
seg_timbre_stddev= get_stddev(transpose_timbre[10])
row.append(seg_timbre_stddev)
seg_timbre_count = get_count(transpose_timbre[10])
row.append(seg_timbre_count)
seg_timbre_sum = get_sum(transpose_timbre[10])
row.append(seg_timbre_sum)
row.append(transpose_timbre[11][i])
seg_timbre_avg= get_avg(transpose_timbre[11])
row.append(seg_timbre_avg)
seg_timbre_max= get_max(transpose_timbre[11])
row.append(seg_timbre_max)
seg_timbre_min = get_min(transpose_timbre[11])
row.append(seg_timbre_min)
seg_timbre_stddev= get_stddev(transpose_timbre[11])
row.append(seg_timbre_stddev)
seg_timbre_count = get_count(transpose_timbre[11])
row.append(seg_timbre_count)
seg_timbre_sum = get_sum(transpose_timbre[11])
row.append(seg_timbre_sum)
for item in row_seg2_padding:
row.append(item)
writer.writerow(row)
row=[]
row=gral_info[:]
# "--------tatums---------------"
tatms_c = hdf5_getters.get_tatums_confidence(h5)
group_index=5
row_front=padding(245) #blank spaces left in front of tatums
row=[]
row=gral_info[:]
for i,item in enumerate(tatms_c):
row.append(group_index)
row.append(i)
for item in row_front: #appending blank spaces at the front of the row
row.append(item)
row.append(tatms_c[i])
tatms_c_avg= get_avg(tatms_c)
row.append(tatms_c_avg)
tatms_c_max= get_max(tatms_c)
row.append(tatms_c_max)
tatms_c_min = get_min(tatms_c)
row.append(tatms_c_min)
tatms_c_stddev= get_stddev(tatms_c)
row.append(tatms_c_stddev)
tatms_c_count = get_count(tatms_c)
row.append(tatms_c_count)
tatms_c_sum = get_sum(tatms_c)
row.append(tatms_c_sum)
tatms_start = hdf5_getters.get_tatums_start(h5)
row.append(tatms_start[i])
tatms_start_avg= get_avg(tatms_start)
row.append(tatms_start_avg)
tatms_start_max= get_max(tatms_start)
row.append(tatms_start_max)
tatms_start_min = get_min(tatms_start)
row.append(tatms_start_min)
tatms_start_stddev= get_stddev(tatms_start)
row.append(tatms_start_stddev)
tatms_start_count = get_count(tatms_start)
row.append(tatms_start_count)
tatms_start_sum = get_sum(tatms_start)
row.append(tatms_start_sum)
writer.writerow(row)
row=[]
row=gral_info[:]
transpose_pitch= seg_pitch.transpose() #this is to tranpose the matrix,so we can have 12 rows
#arrays containing the aggregate values of the 12 rows
seg_pitch_avg=[]
seg_pitch_max=[]
seg_pitch_min=[]
seg_pitch_stddev=[]
seg_pitch_count=[]
seg_pitch_sum=[]
i=0
#Getting the aggregate values in the pitches array
for row in transpose_pitch:
seg_pitch_avg.append(get_avg(row))
seg_pitch_max.append(get_max(row))
seg_pitch_min.append(get_min(row))
seg_pitch_stddev.append(get_stddev(row))
seg_pitch_count.append(get_count(row))
seg_pitch_sum.append(get_sum(row))
i=i+1
#extracting information from the timbre array
transpose_timbre = seg_pitch.transpose() #tranposing matrix, to have 12 rows
#arrays containing the aggregate values of the 12 rows
seg_timbre_avg=[]
seg_timbre_max=[]
seg_timbre_min=[]
seg_timbre_stddev=[]
seg_timbre_count=[]
seg_timbre_sum=[]
i=0
for row in transpose_timbre:
seg_timbre_avg.append(get_avg(row))
seg_timbre_max.append(get_max(row))
seg_timbre_min.append(get_min(row))
seg_timbre_stddev.append(get_stddev(row))
seg_timbre_count.append(get_count(row))
seg_timbre_sum.append(get_sum(row))
i=i+1
h5.close()
count=count+1;
print count;
def main(argv):
if len(argv) != 1:
print "Specify data directory"
return
basedir = argv[0]
outputFile1 = open('SongCSV.csv', 'w')
outputFile2 = open('TagsCSV.csv', 'w')
csvRowString = ""
csvLabelString = ""
#################################################
#if you want to prompt the user for the order of attributes in the csv,
#leave the prompt boolean set to True
#else, set 'prompt' to False and set the order of attributes in the 'else'
#clause
prompt = False
#################################################
if prompt == True:
while prompt:
prompt = False
csvAttributeString = raw_input("\n\nIn what order would you like the colums of the CSV file?\n" +
"Please delineate with commas. The options are: " +
"AlbumName, AlbumID, ArtistID, ArtistLatitude, ArtistLocation, ArtistLongitude,"+
" ArtistName, Danceability, Duration, KeySignature, KeySignatureConfidence, Tempo," +
" SongID, TimeSignature, TimeSignatureConfidence, Title, and Year.\n\n" +
"For example, you may write \"Title, Tempo, Duration\"...\n\n" +
"...or exit by typing 'exit'.\n\n")
csvAttributeList = re.split('\W+', csvAttributeString)
for i, v in enumerate(csvAttributeList):
csvAttributeList[i] = csvAttributeList[i].lower()
for attribute in csvAttributeList:
# print "Here is the attribute: " + attribute + " \n"
if attribute == 'AlbumID'.lower():
csvRowString += 'AlbumID'
elif attribute == 'AlbumName'.lower():
csvRowString += 'AlbumName'
elif attribute == 'ArtistID'.lower():
csvRowString += 'ArtistID'
elif attribute == 'ArtistLatitude'.lower():
csvRowString += 'ArtistLatitude'
elif attribute == 'ArtistLocation'.lower():
csvRowString += 'ArtistLocation'
elif attribute == 'ArtistLongitude'.lower():
csvRowString += 'ArtistLongitude'
elif attribute == 'ArtistName'.lower():
csvRowString += 'ArtistName'
elif attribute == 'Danceability'.lower():
csvRowString += 'Danceability'
elif attribute == 'Duration'.lower():
csvRowString += 'Duration'
elif attribute == 'KeySignature'.lower():
csvRowString += 'KeySignature'
elif attribute == 'KeySignatureConfidence'.lower():
csvRowString += 'KeySignatureConfidence'
elif attribute == 'SongID'.lower():
csvRowString += "SongID"
elif attribute == 'Tempo'.lower():
csvRowString += 'Tempo'
elif attribute == 'TimeSignature'.lower():
csvRowString += 'TimeSignature'
elif attribute == 'TimeSignatureConfidence'.lower():
csvRowString += 'TimeSignatureConfidence'
elif attribute == 'Title'.lower():
csvRowString += 'Title'
elif attribute == 'Year'.lower():
csvRowString += 'Year'
elif attribute == 'Exit'.lower():
sys.exit()
else:
prompt = True
print "=============="
print "I believe there has been an error with the input."
print "=============="
break
csvRowString += ","
lastIndex = len(csvRowString)
csvRowString = csvRowString[0:lastIndex-1]
csvRowString += "\n"
outputFile1.write(csvRowString);
csvRowString = ""
#else, if you want to hard code the order of the csv file and not prompt
#the user,
else:
#################################################
#change the order of the csv file here
#Default is to list all available attributes (in alphabetical order)
#csvRowString = ("SongID,AlbumID,AlbumName,ArtistID,ArtistLatitude,ArtistLocation,"+
# "ArtistLongitude,ArtistName,Danceability,Duration,KeySignature,"+
# "KeySignatureConfidence,Tempo,TimeSignature,TimeSignatureConfidence,"+
# "Title,Year")
csvRowString = ("ArtistFamiliarity,ArtistHotttnesss,"+
"BarsConfidence,BarsStart,BeatsConfidence,BeatsStart,Duration,"+
"EndOfFadeIn,Key,KeyConfidence,Loudness,Mode,ModeConfidence,"+
"SectionsConfidence,SectionsStart,SegmentsConfidence,SegmentsLoudnessMax,"+
"SegmentsLoudnessMaxTime,SegmentsLoudnessStart,SegmentsStart,"+
"SongHotttnesss,StartOfFadeOut,TatumsConfidence,TatumsStart,Tempo,TimeSignature,TimeSignatureConfidence,"+
"SegmentsPitches,SegmentsTimbre,Title,Year,Decade,ArtistMbtags")
#################################################
header = str()
csvAttributeList = re.split('\W+', csvRowString)
arrayAttributes = ["BarsConfidence","BarsStart","BeatsConfidence","BeatsStart",
"SectionsConfidence","SectionsStart","SegmentsConfidence","SegmentsLoudnessMax",
"SegmentsLoudnessMaxTime","SegmentsLoudnessStart","SegmentsStart",
"TatumsConfidence","TatumsStart"]
for i, v in enumerate(csvAttributeList):
csvAttributeList[i] = csvAttributeList[i].lower()
if(v=="SegmentsPitches"):
for i in range(90):
header = header + "SegmentsPitches" + str(i) + ","
elif(v=="SegmentsTimbre"):
for i in range(90):
header = header + "SegmentsTimbre" + str(i) + ","
elif(v in arrayAttributes):
header = header + v + str(0) + ","
header = header + v + str(1) + ","
else:
header = header + v + ","
outputFile1.write("SongNumber,");
#outputFile1.write(csvRowString + "\n");
outputFile1.write(header + "\n");
csvRowString = ""
#################################################
#Set the basedir here, the root directory from which the search
#for files stored in a (hierarchical data structure) will originate
#basedir = "MillionSongSubset/data/A/A/" # "." As the default means the current directory
ext = ".h5" #Set the extension here. H5 is the extension for HDF5 files.
#################################################
#FOR LOOP
all = sorted(os.walk(basedir))
for root, dirs, files in all:
files = sorted(glob.glob(os.path.join(root,'*'+ext)))
for f in files:
print f
songH5File = hdf5_getters.open_h5_file_read(f)
song = Song(str(hdf5_getters.get_song_id(songH5File)))
#testDanceability = hdf5_getters.get_danceability(songH5File)
# print type(testDanceability)
# print ("Here is the danceability: ") + str(testDanceability)
song.analysisSampleRate = str(hdf5_getters.get_analysis_sample_rate(songH5File))
song.artistFamiliarity = str(hdf5_getters.get_artist_familiarity(songH5File))
song.artistHotttnesss = str(hdf5_getters.get_artist_hotttnesss(songH5File))
song.artistLatitude = str(hdf5_getters.get_artist_latitude(songH5File))
song.artistLongitude = str(hdf5_getters.get_artist_longitude(songH5File))
song.artistMbid = str(hdf5_getters.get_artist_mbid(songH5File))
song.barsConfidence = np.array(hdf5_getters.get_bars_confidence(songH5File))
song.barsStart = np.array(hdf5_getters.get_bars_start(songH5File))
song.beatsConfidence = np.array(hdf5_getters.get_beats_confidence(songH5File))
song.beatsStart = np.array(hdf5_getters.get_beats_start(songH5File))
song.danceability = str(hdf5_getters.get_danceability(songH5File))
song.duration = str(hdf5_getters.get_duration(songH5File))
song.endOfFadeIn = str(hdf5_getters.get_end_of_fade_in(songH5File))
song.energy = str(hdf5_getters.get_energy(songH5File))
song.key = str(hdf5_getters.get_key(songH5File))
song.keyConfidence = str(hdf5_getters.get_key_confidence(songH5File))
song.loudness = str(hdf5_getters.get_loudness(songH5File))
song.mode = str(hdf5_getters.get_mode(songH5File))
song.modeConfidence = str(hdf5_getters.get_mode_confidence(songH5File))
song.sectionsConfidence = np.array(hdf5_getters.get_sections_confidence(songH5File))
song.sectionsStart = np.array(hdf5_getters.get_sections_start(songH5File))
song.segmentsConfidence = np.array(hdf5_getters.get_segments_confidence(songH5File))
song.segmentsLoudnessMax = np.array(hdf5_getters.get_segments_loudness_max(songH5File))
song.segmentsLoudnessMaxTime = np.array(hdf5_getters.get_segments_loudness_max_time(songH5File))
song.segmentsLoudnessStart = np.array(hdf5_getters.get_segments_loudness_start(songH5File))
song.segmentsPitches = np.array(hdf5_getters.get_segments_pitches(songH5File))
song.segmentsStart = np.array(hdf5_getters.get_segments_start(songH5File))
song.segmentsTimbre = np.array(hdf5_getters.get_segments_timbre(songH5File))
song.songHotttnesss = str(hdf5_getters.get_song_hotttnesss(songH5File))
song.startOfFadeOut = str(hdf5_getters.get_start_of_fade_out(songH5File))
song.tatumsConfidence = np.array(hdf5_getters.get_tatums_confidence(songH5File))
song.tatumsStart = np.array(hdf5_getters.get_tatums_start(songH5File))
song.tempo = str(hdf5_getters.get_tempo(songH5File))
song.timeSignature = str(hdf5_getters.get_time_signature(songH5File))
song.timeSignatureConfidence = str(hdf5_getters.get_time_signature_confidence(songH5File))
song.songid = str(hdf5_getters.get_song_id(songH5File))
song.title = str(hdf5_getters.get_title(songH5File))
song.year = str(hdf5_getters.get_year(songH5File))
song.artistMbtags = str(hdf5_getters.get_artist_mbtags(songH5File))
#print song count
csvRowString += str(song.songCount) + ","
csvLabelString += str(song.songCount) + ","
for attribute in csvAttributeList:
# print "Here is the attribute: " + attribute + " \n"
if attribute == 'AnalysisSampleRate'.lower():
csvRowString += song.analysisSampleRate
elif attribute == 'ArtistFamiliarity'.lower():
csvRowString += song.artistFamiliarity
elif attribute == 'ArtistHotttnesss'.lower():
csvRowString += song.artistHotttnesss
elif attribute == 'ArtistLatitude'.lower():
latitude = song.artistLatitude
if latitude == 'nan':
latitude = ''
csvRowString += latitude
elif attribute == 'ArtistLongitude'.lower():
longitude = song.artistLongitude
if longitude == 'nan':
longitude = ''
csvRowString += longitude
elif attribute == 'ArtistMbid'.lower():
csvRowString += song.artistMbid
elif attribute == 'BarsConfidence'.lower():
arr = song.barsConfidence
if arr.shape[0] == 0:
arrmean = ''
arrnorm = ''
else:
arrmean = np.mean(arr)
arrnorm = np.linalg.norm(arr)
csvRowString += str(arrmean) + ',' + str(arrnorm)
elif attribute == 'BarsStart'.lower():
arr = song.barsStart
if arr.shape[0] == 0:
arrmean = ''
arrnorm = ''
else:
arrmean = np.mean(arr)
arrnorm = np.linalg.norm(arr)
csvRowString += str(arrmean) + ',' + str(arrnorm)
elif attribute == 'BeatsConfidence'.lower():
arr = song.beatsConfidence
if arr.shape[0] == 0:
arrmean = ''
arrnorm = ''
else:
arrmean = np.mean(arr)
arrnorm = np.linalg.norm(arr)
csvRowString += str(arrmean) + ',' + str(arrnorm)
elif attribute == 'BeatsStart'.lower():
arr = song.beatsStart
if arr.shape[0] == 0:
arrmean = ''
arrnorm = ''
else:
arrmean = np.mean(arr)
arrnorm = np.linalg.norm(arr)
csvRowString += str(arrmean) + ',' + str(arrnorm)
elif attribute == 'Danceability'.lower():
csvRowString += song.danceability
elif attribute == 'Duration'.lower():
csvRowString += song.duration
elif attribute == 'EndOfFadeIn'.lower():
csvRowString += song.endOfFadeIn
elif attribute == 'Energy'.lower():
csvRowString += song.energy
elif attribute == 'Key'.lower():
csvRowString += song.key
elif attribute == 'KeyConfidence'.lower():
csvRowString += song.keyConfidence
elif attribute == 'Loudness'.lower():
csvRowString += song.loudness
elif attribute == 'Mode'.lower():
csvRowString += song.mode
elif attribute == 'ModeConfidence'.lower():
csvRowString += song.modeConfidence
elif attribute == 'SectionsConfidence'.lower():
arr = song.sectionsConfidence
if arr.shape[0] == 0:
arrmean = ''
arrnorm = ''
else:
arrmean = np.mean(arr)
arrnorm = np.linalg.norm(arr)
csvRowString += str(arrmean) + ',' + str(arrnorm)
elif attribute == 'SectionsStart'.lower():
arr = song.sectionsStart
if arr.shape[0] == 0:
arrmean = ''
arrnorm = ''
else:
arrmean = np.mean(arr)
arrnorm = np.linalg.norm(arr)
csvRowString += str(arrmean) + ',' + str(arrnorm)
elif attribute == 'SegmentsConfidence'.lower():
arr = song.segmentsConfidence
if arr.shape[0] == 0:
arrmean = ''
arrnorm = ''
else:
arrmean = np.mean(arr)
arrnorm = np.linalg.norm(arr)
csvRowString += str(arrmean) + ',' + str(arrnorm)
elif attribute == 'SegmentsLoudnessMax'.lower():
arr = song.segmentsLoudnessMax
if arr.shape[0] == 0:
arrmean = ''
arrnorm = ''
else:
arrmean = np.mean(arr)
arrnorm = np.linalg.norm(arr)
csvRowString += str(arrmean) + ',' + str(arrnorm)
elif attribute == 'SegmentsLoudnessMaxTime'.lower():
arr = song.segmentsLoudnessMaxTime
if arr.shape[0] == 0:
arrmean = ''
arrnorm = ''
else:
arrmean = np.mean(arr)
arrnorm = np.linalg.norm(arr)
csvRowString += str(arrmean) + ',' + str(arrnorm)
elif attribute == 'SegmentsLoudnessStart'.lower():
arr = song.segmentsLoudnessStart
if arr.shape[0] == 0:
arrmean = ''
arrnorm = ''
else:
arrmean = np.mean(arr)
arrnorm = np.linalg.norm(arr)
csvRowString += str(arrmean) + ',' + str(arrnorm)
elif attribute == 'SegmentsStart'.lower():
arr = song.segmentsStart
if arr.shape[0] == 0:
arrmean = ''
arrnorm = ''
else:
arrmean = np.mean(arr)
arrnorm = np.linalg.norm(arr)
csvRowString += str(arrmean) + ',' + str(arrnorm)
elif attribute == 'SongHotttnesss'.lower():
hotttnesss = song.songHotttnesss
if hotttnesss == 'nan':
hotttnesss = 'NaN'
csvRowString += hotttnesss
elif attribute == 'StartOfFadeOut'.lower():
csvRowString += song.startOfFadeOut
elif attribute == 'TatumsConfidence'.lower():
arr = song.tatumsConfidence
if arr.shape[0] == 0:
arrmean = ''
arrnorm = ''
else:
arrmean = np.mean(arr)
arrnorm = np.linalg.norm(arr)
csvRowString += str(arrmean) + ',' + str(arrnorm)
elif attribute == 'TatumsStart'.lower():
arr = song.tatumsStart
if arr.shape[0] == 0:
arrmean = ''
arrnorm = ''
else:
arrmean = np.mean(arr)
arrnorm = np.linalg.norm(arr)
csvRowString += str(arrmean) + ',' + str(arrnorm)
elif attribute == 'Tempo'.lower():
# print "Tempo: " + song.tempo
csvRowString += song.tempo
elif attribute == 'TimeSignature'.lower():
csvRowString += song.timeSignature
elif attribute == 'TimeSignatureConfidence'.lower():
# print "time sig conf: " + song.timeSignatureConfidence
csvRowString += song.timeSignatureConfidence
elif attribute == 'SegmentsPitches'.lower():
colmean = np.mean(song.segmentsPitches,axis=0)
for m in colmean:
csvRowString += str(m) + ","
cov = np.dot(song.segmentsPitches.T,song.segmentsPitches)
utriind = np.triu_indices(cov.shape[0])
feats = cov[utriind]
for feat in feats:
csvRowString += str(feat) + ","
lastIndex = len(csvRowString)
csvRowString = csvRowString[0:lastIndex-1]
elif attribute == 'SegmentsTimbre'.lower():
colmean = np.mean(song.segmentsTimbre,axis=0)
for m in colmean:
csvRowString += str(m) + ","
cov = np.dot(song.segmentsTimbre.T,song.segmentsTimbre)
utriind = np.triu_indices(cov.shape[0])
feats = cov[utriind]
for feat in feats:
csvRowString += str(feat) + ","
lastIndex = len(csvRowString)
csvRowString = csvRowString[0:lastIndex-1]
elif attribute == 'SongID'.lower():
csvRowString += "\"" + song.id + "\""
elif attribute == 'Title'.lower():
csvRowString += "\"" + song.title + "\""
elif attribute == 'Year'.lower():
csvRowString += song.year
elif attribute == 'Decade'.lower():
yr = song.year
if yr > 0:
decade = song.year[:-1] + '0'
else:
decade = '0'
csvRowString += decade
elif attribute == 'ArtistMbtags'.lower():
tags = song.artistMbtags[1:-1]
tags = "\"" + tags + "\""
tags = tags.replace("\n",'')
csvRowString += tags
tagsarray = shlex.split(tags)
for t in tagsarray:
csvLabelString += t + ","
else:
csvRowString += "Erm. This didn't work. Error. :( :(\n"
csvRowString += ","
'''
if attribute == 'AlbumID'.lower():
csvRowString += song.albumID
elif attribute == 'AlbumName'.lower():
albumName = song.albumName
albumName = albumName.replace(',',"")
csvRowString += "\"" + albumName + "\""
elif attribute == 'ArtistID'.lower():
csvRowString += "\"" + song.artistID + "\""
elif attribute == 'ArtistLatitude'.lower():
latitude = song.artistLatitude
if latitude == 'nan':
latitude = ''
csvRowString += latitude
elif attribute == 'ArtistLocation'.lower():
location = song.artistLocation
location = location.replace(',','')
csvRowString += "\"" + location + "\""
elif attribute == 'ArtistLongitude'.lower():
longitude = song.artistLongitude
if longitude == 'nan':
longitude = ''
csvRowString += longitude
elif attribute == 'ArtistName'.lower():
csvRowString += "\"" + song.artistName + "\""
elif attribute == 'Danceability'.lower():
csvRowString += song.danceability
elif attribute == 'Duration'.lower():
csvRowString += song.duration
elif attribute == 'KeySignature'.lower():
csvRowString += song.keySignature
elif attribute == 'KeySignatureConfidence'.lower():
# print "key sig conf: " + song.timeSignatureConfidence
csvRowString += song.keySignatureConfidence
elif attribute == 'SongID'.lower():
csvRowString += "\"" + song.id + "\""
elif attribute == 'Tempo'.lower():
# print "Tempo: " + song.tempo
csvRowString += song.tempo
elif attribute == 'TimeSignature'.lower():
csvRowString += song.timeSignature
elif attribute == 'TimeSignatureConfidence'.lower():
# print "time sig conf: " + song.timeSignatureConfidence
csvRowString += song.timeSignatureConfidence
elif attribute == 'Title'.lower():
csvRowString += "\"" + song.title + "\""
elif attribute == 'Year'.lower():
csvRowString += song.year
else:
csvRowString += "Erm. This didn't work. Error. :( :(\n"
csvRowString += ","
'''
#Remove the final comma from each row in the csv
lastIndex = len(csvRowString)
csvRowString = csvRowString[0:lastIndex-1]
csvRowString += "\n"
outputFile1.write(csvRowString)
csvRowString = ""
lastIndex = len(csvLabelString)
csvLabelString = csvLabelString[0:lastIndex-1]
csvLabelString += "\n"
outputFile2.write(csvLabelString)
csvLabelString = ""
songH5File.close()
outputFile1.close()
outputFile2.close()
def timbreData(h5_file):
# grab the tambre data
h5 = GETTERS.open_h5_file_read(h5_file)
full_timbre = np.array(GETTERS.get_segments_timbre(h5))
# get how big the size of the array is
row, col = full_timbre.shape
# get the average values for the 12 tambre profile vectors
avg_timbre = np.mean(full_timbre, axis=0)
# make it a two dimentional numpy array so things later will work...
avg_timbre = np.expand_dims(avg_timbre, axis=0)
# find the step size (this will throw out up to NUM_COV_SAMPLES -1 segments)
step = (row - (row % NUM_COV_SAMPLES)) / NUM_COV_SAMPLES
# print (avg_timbre.shape)
# print (step)
# setup some basic counters and indexes
i = 0
index1 = 0
index2 = step - 1
data = []
# for each chunk of the song
while i < NUM_COV_SAMPLES:
sample = []
# in each of the 12 timbre signitures
for j in range(col):
# print(j)
# compute the variance of of the chunk, and put it in the sample array
sample.append(np.var(full_timbre[index1:index2][j]))
# put the full sample array into the data
data.append(sample)
# update everything
i += 1
index1 += step
index2 += step
# convert the completed data aray to a numpy array
data_np = np.array(data)
print(avg_timbre.shape)
print(data_np.shape)
# put the average timbre and other data together in the same numpy array
ret = np.concatenate((avg_timbre, data_np))
song_id = GETTERS.get_song_id(h5)
song_id = song_id.decode("UTF-8")
# print(ret.shape)
# print(ret)
# close the file
h5.close()
return avg_timbre, data_np, song_id
file_io_counter = 0
for root, dirs, files in os.walk(os.getcwd()):
for name in files:
if name.endswith(".h5"):
if process_completion % 10000 == 0:
print "done :", process_completion/10000.0, "%"
process_completion += 1
else:
process_completion += 1
tempPath = os.path.abspath(os.path.join(root,name))
h5file = hdf5_getters.open_h5_file_read(tempPath)
#meta info
track_id_str = hdf5_getters.get_track_id(h5file).replace(",","")
song_id_str = hdf5_getters.get_song_id(h5file).replace(",","")
title_str = hdf5_getters.get_title(h5file).replace(","," ")
artist_name_str = hdf5_getters.get_artist_name(h5file).replace(","," ")
artist_location_str = hdf5_getters.get_artist_location(h5file).replace(","," ")
# song-level data info
duration = hdf5_getters.get_duration(h5file)
key = hdf5_getters.get_key(h5file)
mode = hdf5_getters.get_mode(h5file)
tempo = hdf5_getters.get_tempo(h5file)
time_signature = hdf5_getters.get_time_signature(h5file)
h5file.close()
counter += 1
file_io_counter += 1
file_io_counter = 0
for root, dirs, files in os.walk(os.getcwd()):
for name in files:
if name.endswith(".h5"):
if process_completion % 10000 == 0:
print "done :", process_completion/10000.0, "%"
process_completion += 1
else:
process_completion += 1
tempPath = os.path.abspath(os.path.join(root,name))
h5file = hdf5_getters.open_h5_file_read(tempPath)
#data extract 1
track_id_str = hdf5_getters.get_track_id(h5file)
song_id_str = hdf5_getters.get_song_id(h5file)
album_name_str = unicodedata.normalize('NFKD', unicode(hdf5_getters.get_release(h5file),encoding='ASCII',errors='ignore'))
album_name_str = str(album_name_str).replace(","," ").replace("'","").replace("-"," ").replace("("," ").replace(")"," ").replace("/"," ").replace("\\"," ")
year_str = str(hdf5_getters.get_year(h5file))
counter += 1
file_io_counter += 1
if file_io_counter % 100 == 0:
if counter == 1:
my_array_data_extract_1 = numpy.array([track_id_str, song_id_str, album_name_str, year_str])
else :
my_array_data_extract_1 = numpy.vstack((my_array_data_extract_1,numpy.array([track_id_str, song_id_str, album_name_str, year_str])))
f_handle = file('msd_data_extract_1.bin','a')
numpy.savetxt(f_handle, my_array_data_extract_1, delimiter='|',fmt='%s')
f_handle.close()
def tambreData(self, h5_file):
#grab the tambre data
h5 = GETTERS.open_h5_file_read(h5_file)
full_timbre = np.array(GETTERS.get_segments_timbre(h5))
#get how big the size of the array is
row, col = full_timbre.shape
#get the song id
song_id = GETTERS.get_song_id(h5)
#convert it into a string so it can be actually used
song_id = song_id.decode("UTF-8")
#throw out songs that don't have enough samples
if row < NUM_SAMPLES *13:
h5.close()
return np.array([0,0]), np.array([0,0]), song_id
#get the average values for the 12 tambre profile vectors
avg_timbre = np.mean(full_timbre, axis = 0)
#make it a two dimentional numpy array so things later will work...
avg_timbre = np.expand_dims(avg_timbre, axis = 0)
#find the step size (this will throw out up to NUM_COV_SAMPLES -1 segments)
step = (row - (row % NUM_SAMPLES)) / NUM_SAMPLES
#setup some basic counters and indexes
i = 0
index1 = 0
index2 = step - 1
data = []
#for each chunk of the song
while (i < NUM_SAMPLES):
sample = []
#in each of the 12 timbre signitures
for j in range(col):
#compute the variance of of the chunk, and put it in the sample array
sample.append(np.var(full_timbre[index1:index2][j]))
#put the full sample array into the data
data.append(sample)
#update everything
i+=1
index1 += step
index2 += step
#convert the completed data aray to a numpy array
data_np = np.array(data)
#put the average timbre and other data together in the same numpy array
# ret = np.concatenate((avg_timbre, data_np))
#close the file
h5.close()
#return everything in a tuple, so can be individually inserted into the db
return avg_timbre, data_np, song_id
import glob
import hdf5_getters
import csv
from tqdm import tqdm
myfile = open('info.csv', 'wb')
wr = csv.writer(myfile, quoting=csv.QUOTE_ALL)
glob_path = '/Users/andrew/Documents/datamining/Project/MillionSongSubset/data/*/*/*/*'
filepaths = glob.glob(glob_path)
for filepath in tqdm(filepaths):
h5 = hdf5_getters.open_h5_file_read(filepath)
n = hdf5_getters.get_num_songs(h5)
# print n
for row in range(n):
artist = hdf5_getters.get_artist_name(h5,songidx=row)
song_id = hdf5_getters.get_song_id(h5,songidx=row)
title= hdf5_getters.get_title(h5,songidx=row)
info = [song_id, title, artist]
wr.writerow(info)
h5.close()
import hdf5_getters
h5 = hdf5_getters.open_h5_file_read(path to some file)
duration = hdf5_getters.get_duration(h5)
h5.close()
def writeSingleHDF5FileToTxtFile(songHDF5FileName):
global maximumArtistNameLen
global maximumArtistTagLen
global maximumSongNameLen
global maximumAlbumNameLen
"""
This function does 3 simple things:
- open the song file
- get artist ID and put it
- close the file
"""
songHDF5File = GETTERS.open_h5_file_read(songHDF5FileName)
songID = GETTERS.get_song_id(songHDF5File)
songName = GETTERS.get_title(songHDF5File)
artistID = GETTERS.get_artist_id(songHDF5File)
songAlbum = GETTERS.get_release(songHDF5File)
songYear = GETTERS.get_year(songHDF5File)
songTempo = GETTERS.get_tempo(songHDF5File)
songDanceability = GETTERS.get_danceability(songHDF5File)
songDuration = GETTERS.get_duration(songHDF5File)
songEnergy = GETTERS.get_energy(songHDF5File)
songKey = GETTERS.get_key(songHDF5File)
songLoudness = GETTERS.get_loudness(songHDF5File)
songMode = GETTERS.get_mode(songHDF5File)
songTimeSignature = GETTERS.get_time_signature(songHDF5File)
songsTableFile.write(songID + "\t" + songName + "\t" + artistID + "\t" +
songAlbum + "\t" + str(songYear) + "\t" +
str(songTempo) + "\t" + str(songDanceability) + "\t" +
str(songDuration) + "\t" + str(songEnergy) + "\t" +
str(songKey) + "\t" + str(songLoudness) + "\t" +
str(songMode) + "\t" + str(songTimeSignature) +
"\t\n")
artistName = GETTERS.get_artist_name(songHDF5File)
artistFamiliarity = GETTERS.get_artist_familiarity(songHDF5File)
artistTagsArray = GETTERS.get_artist_mbtags(songHDF5File)
artistsTableFile.write(artistID + "\t" + artistName + "\t" +
str(artistFamiliarity) + "\t\n")
if len(songName) > maximumSongNameLen:
maximumSongNameLen = len(songName)
if len(songAlbum) > maximumAlbumNameLen:
maximumAlbumNameLen = len(songAlbum)
if len(artistName) > maximumArtistNameLen:
maximumArtistNameLen = len(artistName)
for artistTag in artistTagsArray:
if artistTag in allowedTagsSet:
artistsTagsTableFile.write(artistID + "\t" + artistTag + "\t\n")
if artistTag not in tagsSet:
tagsTableFile.write(artistTag + "\t\n")
tagsSet.add(artistTag)
if len(artistTag) > maximumArtistTagLen:
maximumArtistTagLen = len(artistTag)
similarArtists = GETTERS.get_similar_artists(songHDF5File)
for similarArtist in similarArtists:
similarArtistsPairsList.add((artistID, similarArtist))
artistsIDsSet.add(artistID)
artistsNamesSet.add(artistName)
songHDF5File.close()
import hdf5_getters
h5 = hdf5_getters.open_h5_file_read("data/msd_summary_file.h5")
for i in range(hdf5_getters.get_num_songs(h5)):
print(hdf5_getters.get_song_id(h5, i))
h5.close()
def main():
outputFile = open('songs.csv', 'w')
writer = csv.writer(outputFile)
csvRowString = "song_number,artist_familiarity,artist_hotttnesss,artist_id,artist_mbid,artist_playmeid,artist_7digitalid,artist_latitude,artist_longitude,artist_location,artist_name,release,release_7digitalid,song_id,song_hotttnesss,title,track_7digitalid,analysis_sample_rate,audio_md5,danceability,duration,end_of_fade_in,energy,key,key_confidence,loudness,mode,mode_confidence,start_of_fade_out,tempo,time_signature,time_signature_confidence,track_id,year"
outputFile.write(csvRowString + "\n")
csvRowString = ""
#################################################
#Set the basedir here, the root directory from which the search
#for files stored in a (hierarchical data structure) will originate
basedir = "." # "." As the default means the current directory
ext = ".H5" #Set the extension here. H5 is the extension for HDF5 files.
#################################################
#FOR LOOP
songCount = 0
for root, dirs, files in os.walk(basedir):
files = glob.glob(os.path.join(root, '*' + ext))
for f in files:
print(f)
songH5File = hdf5_getters.open_h5_file_read(f)
values = [
songCount,
hdf5_getters.get_artist_familiarity(songH5File),
hdf5_getters.get_artist_hotttnesss(songH5File),
hdf5_getters.get_artist_id(songH5File),
hdf5_getters.get_artist_mbid(songH5File),
hdf5_getters.get_artist_playmeid(songH5File),
hdf5_getters.get_artist_7digitalid(songH5File),
hdf5_getters.get_artist_latitude(songH5File),
hdf5_getters.get_artist_longitude(songH5File),
hdf5_getters.get_artist_location(songH5File),
hdf5_getters.get_artist_name(songH5File),
hdf5_getters.get_release(songH5File),
hdf5_getters.get_release_7digitalid(songH5File),
hdf5_getters.get_song_id(songH5File),
hdf5_getters.get_song_hotttnesss(songH5File),
hdf5_getters.get_title(songH5File),
hdf5_getters.get_track_7digitalid(songH5File),
hdf5_getters.get_analysis_sample_rate(songH5File),
hdf5_getters.get_audio_md5(songH5File),
hdf5_getters.get_danceability(songH5File),
hdf5_getters.get_duration(songH5File),
hdf5_getters.get_end_of_fade_in(songH5File),
hdf5_getters.get_energy(songH5File),
hdf5_getters.get_key(songH5File),
hdf5_getters.get_key_confidence(songH5File),
hdf5_getters.get_loudness(songH5File),
hdf5_getters.get_mode(songH5File),
hdf5_getters.get_mode_confidence(songH5File),
hdf5_getters.get_start_of_fade_out(songH5File),
hdf5_getters.get_tempo(songH5File),
hdf5_getters.get_time_signature(songH5File),
hdf5_getters.get_time_signature_confidence(songH5File),
hdf5_getters.get_track_id(songH5File),
hdf5_getters.get_year(songH5File)
]
songH5File.close()
songCount = songCount + 1
writer.writerow(values)
outputFile.close()
#3
tmp.append(hdf5_getters.get_artist_latitude(h5, songidx=i))
#4
tmp.append(hdf5_getters.get_artist_longitude(h5, songidx=i))
#5
tmp.append(
str(hdf5_getters.get_artist_location(h5, songidx=i)).replace(
"b'", "").replace("'", ""))
#6
tmp.append(
str(hdf5_getters.get_artist_name(h5, songidx=i)).replace("b'",
"").replace(
"'", ""))
#7
tmp.append(
str(hdf5_getters.get_song_id(h5,
songidx=i)).replace("b'",
"").replace("'", ""))
data.append(tmp)
print(count)
h5.close()
data = sorted(data, key=operator.itemgetter(1))
#print hdf5_getters.get_artist_location(h5,songidx=8540))
print("writing...")
f = open('files/TrackIdAndInformation.csv', 'w+')
w = csv.writer(f, delimiter=',')
w.writerows(data)
f.close()
def main():
outputFile1 = open('SongCSV.csv', 'w')
csvRowString = ""
#################################################
#if you want to prompt the user for the order of attributes in the csv,
#leave the prompt boolean set to True
#else, set 'prompt' to False and set the order of attributes in the 'else'
#clause
prompt = False
#################################################
if prompt == True:
while prompt:
prompt = False
csvAttributeString = raw_input("\n\nIn what order would you like the colums of the CSV file?\n" +
"Please delineate with commas. The options are: " +
"AlbumName, AlbumID, ArtistID, ArtistLatitude, ArtistLocation, ArtistLongitude,"+
" ArtistName, Danceability, Duration, KeySignature, KeySignatureConfidence, Tempo," +
" SongID, TimeSignature, TimeSignatureConfidence, Title, and Year.\n\n" +
"For example, you may write \"Title, Tempo, Duration\"...\n\n" +
"...or exit by typing 'exit'.\n\n")
csvAttributeList = re.split('\W+', csvAttributeString)
for i, v in enumerate(csvAttributeList):
csvAttributeList[i] = csvAttributeList[i].lower()
for attribute in csvAttributeList:
# print "Here is the attribute: " + attribute + " \n"
if attribute == 'AlbumID'.lower():
csvRowString += 'AlbumID'
elif attribute == 'AlbumName'.lower():
csvRowString += 'AlbumName'
elif attribute == 'ArtistID'.lower():
csvRowString += 'ArtistID'
elif attribute == 'ArtistLatitude'.lower():
csvRowString += 'ArtistLatitude'
elif attribute == 'ArtistLocation'.lower():
csvRowString += 'ArtistLocation'
elif attribute == 'ArtistLongitude'.lower():
csvRowString += 'ArtistLongitude'
elif attribute == 'ArtistName'.lower():
csvRowString += 'ArtistName'
elif attribute == 'Danceability'.lower():
csvRowString += 'Danceability'
elif attribute == 'Duration'.lower():
csvRowString += 'Duration'
elif attribute == 'KeySignature'.lower():
csvRowString += 'KeySignature'
elif attribute == 'KeySignatureConfidence'.lower():
csvRowString += 'KeySignatureConfidence'
elif attribute == 'SongID'.lower():
csvRowString += "SongID"
elif attribute == 'Tempo'.lower():
csvRowString += 'Tempo'
elif attribute == 'TimeSignature'.lower():
csvRowString += 'TimeSignature'
elif attribute == 'TimeSignatureConfidence'.lower():
csvRowString += 'TimeSignatureConfidence'
elif attribute == 'Title'.lower():
csvRowString += 'Title'
elif attribute == 'Year'.lower():
csvRowString += 'Year'
elif attribute == 'Exit'.lower():
sys.exit()
else:
prompt = True
print "=============="
print "I believe there has been an error with the input."
print "=============="
break
csvRowString += ","
lastIndex = len(csvRowString)
csvRowString = csvRowString[0:lastIndex-1]
csvRowString += "\n"
outputFile1.write(csvRowString);
csvRowString = ""
#else, if you want to hard code the order of the csv file and not prompt
#the user,
else:
#################################################
#change the order of the csv file here
#Default is to list all available attributes (in alphabetical order)
csvRowString = ("SongID,AlbumID,AlbumName,ArtistID,ArtistLatitude,ArtistLocation,"+
"ArtistLongitude,ArtistName,Danceability,Duration,KeySignature,"+
"KeySignatureConfidence,Tempo,TimeSignature,TimeSignatureConfidence,"+
"Title,Year")
#################################################
csvAttributeList = re.split('\W+', csvRowString)
for i, v in enumerate(csvAttributeList):
csvAttributeList[i] = csvAttributeList[i].lower()
outputFile1.write("SongNumber,");
outputFile1.write(csvRowString + "\n");
csvRowString = ""
#################################################
#Set the basedir here, the root directory from which the search
#for files stored in a (hierarchical data structure) will originate
basedir = "." # "." As the default means the current directory
ext = ".H5" #Set the extension here. H5 is the extension for HDF5 files.
#################################################
#FOR LOOP
for root, dirs, files in os.walk(basedir):
files = glob.glob(os.path.join(root,'*'+ext))
for f in files:
print f
songH5File = hdf5_getters.open_h5_file_read(f)
song = Song(str(hdf5_getters.get_song_id(songH5File)))
testDanceability = hdf5_getters.get_danceability(songH5File)
# print type(testDanceability)
# print ("Here is the danceability: ") + str(testDanceability)
song.artistID = str(hdf5_getters.get_artist_id(songH5File))
song.albumID = str(hdf5_getters.get_release_7digitalid(songH5File))
song.albumName = str(hdf5_getters.get_release(songH5File))
song.artistLatitude = str(hdf5_getters.get_artist_latitude(songH5File))
song.artistLocation = str(hdf5_getters.get_artist_location(songH5File))
song.artistLongitude = str(hdf5_getters.get_artist_longitude(songH5File))
song.artistName = str(hdf5_getters.get_artist_name(songH5File))
song.danceability = str(hdf5_getters.get_danceability(songH5File))
song.duration = str(hdf5_getters.get_duration(songH5File))
# song.setGenreList()
song.keySignature = str(hdf5_getters.get_key(songH5File))
song.keySignatureConfidence = str(hdf5_getters.get_key_confidence(songH5File))
# song.lyrics = None
# song.popularity = None
song.tempo = str(hdf5_getters.get_tempo(songH5File))
song.timeSignature = str(hdf5_getters.get_time_signature(songH5File))
song.timeSignatureConfidence = str(hdf5_getters.get_time_signature_confidence(songH5File))
song.title = str(hdf5_getters.get_title(songH5File))
song.year = str(hdf5_getters.get_year(songH5File))
#print song count
csvRowString += str(song.songCount) + ","
for attribute in csvAttributeList:
# print "Here is the attribute: " + attribute + " \n"
if attribute == 'AlbumID'.lower():
csvRowString += song.albumID
elif attribute == 'AlbumName'.lower():
albumName = song.albumName
albumName = albumName.replace(',',"")
csvRowString += "\"" + albumName + "\""
elif attribute == 'ArtistID'.lower():
csvRowString += "\"" + song.artistID + "\""
elif attribute == 'ArtistLatitude'.lower():
latitude = song.artistLatitude
if latitude == 'nan':
latitude = ''
csvRowString += latitude
elif attribute == 'ArtistLocation'.lower():
location = song.artistLocation
location = location.replace(',','')
csvRowString += "\"" + location + "\""
elif attribute == 'ArtistLongitude'.lower():
longitude = song.artistLongitude
if longitude == 'nan':
longitude = ''
csvRowString += longitude
elif attribute == 'ArtistName'.lower():
csvRowString += "\"" + song.artistName + "\""
elif attribute == 'Danceability'.lower():
csvRowString += song.danceability
elif attribute == 'Duration'.lower():
csvRowString += song.duration
elif attribute == 'KeySignature'.lower():
csvRowString += song.keySignature
elif attribute == 'KeySignatureConfidence'.lower():
# print "key sig conf: " + song.timeSignatureConfidence
csvRowString += song.keySignatureConfidence
elif attribute == 'SongID'.lower():
csvRowString += "\"" + song.id + "\""
elif attribute == 'Tempo'.lower():
# print "Tempo: " + song.tempo
csvRowString += song.tempo
elif attribute == 'TimeSignature'.lower():
csvRowString += song.timeSignature
elif attribute == 'TimeSignatureConfidence'.lower():
# print "time sig conf: " + song.timeSignatureConfidence
csvRowString += song.timeSignatureConfidence
elif attribute == 'Title'.lower():
csvRowString += "\"" + song.title + "\""
elif attribute == 'Year'.lower():
csvRowString += song.year
else:
csvRowString += "Erm. This didn't work. Error. :( :(\n"
csvRowString += ","
#Remove the final comma from each row in the csv
lastIndex = len(csvRowString)
csvRowString = csvRowString[0:lastIndex-1]
csvRowString += "\n"
outputFile1.write(csvRowString)
csvRowString = ""
songH5File.close()
outputFile1.close()
for i in range(0,length):
tmp = [];
if hdf5_getters.get_year(h5,songidx=i) == 0 :
continue;
#if math.isnan(hdf5_getters.get_artist_latitude(h5,songidx=i)) and hdf5_getters.get_artist_location(h5,songidx=i) =='':
# continue;
count+=1;
tmp.append(str(hdf5_getters.get_track_id(h5,songidx=i)).replace("b'","").replace("'",""));
tmp.append(hdf5_getters.get_year(h5,songidx=i)); #0
tmp.append(hdf5_getters.get_song_hotttnesss(h5,songidx=i)); #1
tmp.append(str(hdf5_getters.get_title(h5,songidx=i)).replace("b'","").replace("'","")); #2
tmp.append(str(hdf5_getters.get_artist_id(h5,songidx=i)).replace("b'","").replace("'","")); #3
tmp.append(hdf5_getters.get_artist_latitude(h5,songidx=i)); #4
tmp.append(hdf5_getters.get_artist_longitude(h5,songidx=i)); #5
tmp.append(str(hdf5_getters.get_artist_location(h5,songidx=i)).replace("b'","").replace("'","")); #6
tmp.append(str(hdf5_getters.get_artist_name(h5,songidx=i)).replace("b'","").replace("'","")); #7
tmp.append(str(hdf5_getters.get_song_id(h5,songidx=i)).replace("b'","").replace("'",""));
data.append(tmp)
print(count)
h5.close()
data = sorted(data, key = operator.itemgetter(1))
#print hdf5_getters.get_artist_location(h5,songidx=8540))
print("writing...")
f = open('files/TrackIdAndInformation.csv','w+')
w = csv.writer(f,delimiter=',')
w.writerows(data)
f.close()
def get_all_data(dir,ext,outDir):
for root, dirs, files in os.walk(dir):
files = glob.glob(os.path.join(root,'*'+ext))
for f in files:
h5 = get.open_h5_file_read(f)
keys = {}
keys['trackId'] = get.get_track_id(h5)
#keys['analysisSampleRate'] = get.get_analysis_sample_rate(h5)
#keys['artistMbTags'] = arrToStr(get.get_artist_mbtags(h5))
#keys['artistMbId'] = get.get_artist_mbid(h5)
#keys['artistName'] = get.get_artist_name(h5)
#keys['artistPlayMeId'] = get.get_artist_playmeid(h5)
#keys['artistTermsWeightArr'] = arrToStr(get.get_artist_terms_weight(h5)) #array
#keys['artistTermsFreqArr'] = arrToStr(get.get_artist_terms_freq(h5)) #array
#keys['artistTermsArr'] = arrToStr(get.get_artist_terms(h5)) # array"""
#keys['audioMd5'] = get.get_audio_md5(h5)
#keys['barsConfidence'] = arrToStr(get.get_bars_confidence(h5)) #
#keys['barsStart'] = arrToStr(get.get_bars_start(h5)) #
#keys['beatsConfidence'] = arrToStr(get.get_beats_confidence(h5)) #
#keys['beatsStart']= arrToStr(get.get_beats_start(h5)) #
#keys['danceability'] = get.get_danceability(h5)
#keys['duration'] = get.get_duration(h5)
#keys['endofFadeIn'] = get.get_end_of_fade_in(h5)
#keys['energy'] = get.get_energy(h5)
#keys['key'] = get.get_key(h5)
keys['loudness'] = get.get_loudness(h5)
#keys['keyConfidence'] = get.get_key_confidence(h5)
#keys['mode'] = get.get_mode(h5)
#keys['release'] = get.get_release(h5)
#keys['release7DigitalId'] = get.get_release_7digitalid(h5)
#keys['modeConfidence'] = get.get_mode_confidence(h5)
#keys['sectionsConfidenceArr'] = arrToStr(get.get_sections_confidence(h5)) #
#keys['sectionsStartArr'] = arrToStr(get.get_sections_start(h5))
#Segments data begin
keys['segmentsStartArr'] = arrToStr(get.get_segments_start(h5)) #
#keys['segmentsConfidenceArr'] = arrToStr(get.get_segments_confidence(h5)) #
#keys['segmentsLoudnessMaxArr'] = arrToStr(get.get_segments_loudness_max_time(h5)) #
#keys['segmentsLoudnessMaxTimeArr'] = arrToStr(get.get_segments_loudness_max_time(h5)) #
#keys['segmentsLoudnessStartArr'] = arrToStr(get.get_segments_loudness_start(h5)) #
keys['segmentsPitchesArr'] = arrToStr((np.array(get.get_segments_pitches(h5))).flatten()) #
keys['segmentsTimbreArr'] = arrToStr((np.array(get.get_segments_timbre(h5))).flatten()) #Timbre data
#Segments data End
#keys['similarArtists'] = arrToStr(get.get_similar_artists(h5))
#keys['songHotness'] = get.get_song_hotttnesss(h5)
keys['songId'] = get.get_song_id(h5)
#keys['startOfFadeOut'] = get.get_start_of_fade_out(h5)
#keys['tatumsConfidence'] = arrToStr(get.get_tatums_confidence(h5)) #
#keys['tatumsStart'] = arrToStr(get.get_tatums_start(h5)) #
#keys['tempo'] = get.get_tempo(h5)
#keys['timeSignature'] = get.get_time_signature(h5)
#keys['timeSignatureConfidence'] = get.get_time_signature_confidence(h5)
keys['title'] = get.get_title(h5)
#keys['track7DigitalId'] = get.get_track_7digitalid(h5)
#keys['year'] = get.get_year(h5)
with open(outDir,'a') as f:
for key in ordering:
f.write('{0}\t'.format(keys[key]))
f.write('\n')
"""
for key in keys:
print key
print "---> "
print keys[key]
"""
h5.close()
song_time_signatures =[]
song_tatum = []
song_modes = []
song_keys = []
for f in files:
h5 = tables.open_file(f)
filepath = f
artist_name = g.get_artist_name(h5)
artist_familar = g.get_artist_familiarity(h5)
artist_hot = g.get_artist_hotttnesss(h5)
artist_ids = g.get_artist_id(h5)
artist_lat = g.get_artist_latitude(h5)
artist_long = g.get_artist_longitude(h5)
artist_loc = g.get_artist_location(h5)
song_idss = g.get_song_id(h5)
song_speed = g.get_tempo(h5)
song_bar = g.get_bars_start(h5)
song_beat = g.get_beats_start(h5)
song_time_signature = g.get_time_signature(h5)
song_tat = g.get_tatums_start(h5)
song_mode = g.get_mode(h5)
song_key = g.get_key(h5)
song_idss = g.get_song_id(h5)
song_title = g.get_title(h5)
song_duration = g.get_duration(h5)
song_release_years = g.get_year(h5)
song_hot = g.get_song_hotttnesss (h5)
track_idss = g.get_track_id(h5)
file_path.append(filepath)
def preprocess(filename, all_data, i):
data, all_artist_names, all_artist_ids, all_artist_locations, all_titles, all_song_ids, all_years, all_durations, all_modes, all_tempos, all_artist_mbtags = all_data
# data = [[]]
j = 0
h5 = GETTERS.open_h5_file_read(filename)
artist_name = GETTERS.get_artist_name(h5).decode("utf-8")
value = get_key_value(all_artist_names, artist_name)
data[i, j] = value
j += 1
artist_id = GETTERS.get_artist_id(h5).decode("utf-8")
value = get_key_value(all_artist_ids, artist_id)
data[i, j] = value
j += 1
artist_location = GETTERS.get_artist_location(h5).decode("utf-8")
value = get_key_value(all_artist_locations, artist_location)
data[i, j] = value
j += 1
title = GETTERS.get_title(h5).decode("utf-8")
value = get_key_value(all_titles, title)
data[i, j] = value
j += 1
song_id = GETTERS.get_song_id(h5).decode("utf-8")
value = get_key_value(all_song_ids, song_id)
data[i, j] = value
j += 1
year = GETTERS.get_year(h5)
all_years.add(year)
data[i, j] = year
j += 1
duration = GETTERS.get_duration(h5)
all_durations.add(duration)
data[i, j] = duration
j += 1
mode = GETTERS.get_mode(h5)
all_modes.add(mode)
data[i, j] = mode
j += 1
tempo = GETTERS.get_tempo(h5)
all_tempos.add(tempo)
data[i, j] = tempo
j += 1
artist_mbtags = GETTERS.get_artist_mbtags(h5)
k = 0
for artist_mbtag in artist_mbtags:
if k <= 4:
value = get_key_value(all_artist_mbtags,
artist_mbtag.decode("utf-8"))
data[i, j] = value
j += 1
k += 1
h5.close()
for root, dirs, files in os.walk(base_dir):
fs = glob.glob(os.path.join(root, '*' + ext))
for f in fs:
counter += 1
if (counter % 1000) == 0:
print "Progress: {0}".format(counter)
if (counter % 10000) == 0:
outputFile1.close()
file_counter += 1
outputFile1 = open(
os.path.join(output_dir,
base_file_name).format(file_counter), 'w')
writeheader(outputFile1, csvHeaderString, ';')
songH5File = hdf5_getters.open_h5_file_read(f)
song = Song(str(hdf5_getters.get_song_id(songH5File)))
testDanceability = hdf5_getters.get_danceability(songH5File)
# print type(testDanceability)
# print ("Here is the danceability: ") + str(testDanceability)
song.artistName = remove_trap_characters(
str(hdf5_getters.get_artist_name(songH5File)))
song.artistID = remove_trap_characters(
str(hdf5_getters.get_artist_id(songH5File)))
song.albumID = remove_trap_characters(
str(hdf5_getters.get_release_7digitalid(songH5File)))
song.artistLatitude = remove_trap_characters(
str(hdf5_getters.get_artist_latitude(songH5File)))
# Replace the comma in the location (if there is one), since this will displace the entire row
song.artistLocation = remove_trap_characters(
def data_to_flat_file(basedir,ext='.h5') :
"""This function extract the information from the tables and creates the flat file."""
count = 0; #song counter
list_to_write= []
row_to_write = ""
writer = csv.writer(open("metadata_wholeA.csv", "wb"))
for root, dirs, files in os.walk(basedir):
files = glob.glob(os.path.join(root,'*'+ext))
for f in files:
print f #the name of the file
h5 = hdf5_getters.open_h5_file_read(f)
title = hdf5_getters.get_title(h5)
title= title.replace('"','')
comma=title.find(',') #eliminating commas in the title
if comma != -1:
print title
time.sleep(1)
album = hdf5_getters.get_release(h5)
album= album.replace('"','') #eliminating commas in the album
comma=album.find(',')
if comma != -1:
print album
time.sleep(1)
artist_name = hdf5_getters.get_artist_name(h5)
comma=artist_name.find(',')
if comma != -1:
print artist_name
time.sleep(1)
artist_name= artist_name.replace('"','') #eliminating double quotes
duration = hdf5_getters.get_duration(h5)
samp_rt = hdf5_getters.get_analysis_sample_rate(h5)
artist_7digitalid = hdf5_getters.get_artist_7digitalid(h5)
artist_fam = hdf5_getters.get_artist_familiarity(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(artist_fam) == True:
artist_fam=-1
artist_hotness= hdf5_getters.get_artist_hotttnesss(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(artist_hotness) == True:
artist_hotness=-1
artist_id = hdf5_getters.get_artist_id(h5)
artist_lat = hdf5_getters.get_artist_latitude(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(artist_lat) == True:
artist_lat=-1
artist_loc = hdf5_getters.get_artist_location(h5)
#checks artist_loc to see if it is a hyperlink if it is set as empty string
artist_loc = artist_loc.replace(",", "\,");
if artist_loc.startswith("<a"):
artist_loc = ""
if len(artist_loc) > 100:
artist_loc = ""
artist_lon = hdf5_getters.get_artist_longitude(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(artist_lon) == True:
artist_lon=-1
artist_mbid = hdf5_getters.get_artist_mbid(h5)
artist_pmid = hdf5_getters.get_artist_playmeid(h5)
audio_md5 = hdf5_getters.get_audio_md5(h5)
danceability = hdf5_getters.get_danceability(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(danceability) == True:
danceability=-1
end_fade_in =hdf5_getters.get_end_of_fade_in(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(end_fade_in) == True:
end_fade_in=-1
energy = hdf5_getters.get_energy(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(energy) == True:
energy=-1
song_key = hdf5_getters.get_key(h5)
key_c = hdf5_getters.get_key_confidence(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(key_c) == True:
key_c=-1
loudness = hdf5_getters.get_loudness(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(loudness) == True:
loudness=-1
mode = hdf5_getters.get_mode(h5)
mode_conf = hdf5_getters.get_mode_confidence(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(mode_conf) == True:
mode_conf=-1
release_7digitalid = hdf5_getters.get_release_7digitalid(h5)
song_hot = hdf5_getters.get_song_hotttnesss(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(song_hot) == True:
song_hot=-1
song_id = hdf5_getters.get_song_id(h5)
start_fade_out = hdf5_getters.get_start_of_fade_out(h5)
tempo = hdf5_getters.get_tempo(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(tempo) == True:
tempo=-1
time_sig = hdf5_getters.get_time_signature(h5)
time_sig_c = hdf5_getters.get_time_signature_confidence(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(time_sig_c) == True:
time_sig_c=-1
track_id = hdf5_getters.get_track_id(h5)
track_7digitalid = hdf5_getters.get_track_7digitalid(h5)
year = hdf5_getters.get_year(h5)
bars_c = hdf5_getters.get_bars_confidence(h5)
bars_c_avg= get_avg(bars_c)
bars_c_max= get_max(bars_c)
bars_c_min = get_min(bars_c)
bars_c_stddev= get_stddev(bars_c)
bars_c_count = get_count(bars_c)
bars_c_sum = get_sum(bars_c)
bars_start = hdf5_getters.get_bars_start(h5)
bars_start_avg = get_avg(bars_start)
bars_start_max= get_max(bars_start)
bars_start_min = get_min(bars_start)
bars_start_stddev= get_stddev(bars_start)
bars_start_count = get_count(bars_start)
bars_start_sum = get_sum(bars_start)
beats_c = hdf5_getters.get_beats_confidence(h5)
beats_c_avg= get_avg(beats_c)
beats_c_max= get_max(beats_c)
beats_c_min = get_min(beats_c)
beats_c_stddev= get_stddev(beats_c)
beats_c_count = get_count(beats_c)
beats_c_sum = get_sum(beats_c)
beats_start = hdf5_getters.get_beats_start(h5)
beats_start_avg = get_avg(beats_start)
beats_start_max= get_max(beats_start)
beats_start_min = get_min(beats_start)
beats_start_stddev= get_stddev(beats_start)
beats_start_count = get_count(beats_start)
beats_start_sum = get_sum(beats_start)
sec_c = hdf5_getters.get_sections_confidence(h5)
sec_c_avg= get_avg(sec_c)
sec_c_max= get_max(sec_c)
sec_c_min = get_min(sec_c)
sec_c_stddev= get_stddev(sec_c)
sec_c_count = get_count(sec_c)
sec_c_sum = get_sum(sec_c)
sec_start = hdf5_getters.get_sections_start(h5)
sec_start_avg = get_avg(sec_start)
sec_start_max= get_max(sec_start)
sec_start_min = get_min(sec_start)
sec_start_stddev= get_stddev(sec_start)
sec_start_count = get_count(sec_start)
sec_start_sum = get_sum(sec_start)
seg_c = hdf5_getters.get_segments_confidence(h5)
seg_c_avg= get_avg(seg_c)
seg_c_max= get_max(seg_c)
seg_c_min = get_min(seg_c)
seg_c_stddev= get_stddev(seg_c)
seg_c_count = get_count(seg_c)
seg_c_sum = get_sum(seg_c)
seg_loud_max = hdf5_getters.get_segments_loudness_max(h5)
seg_loud_max_avg= get_avg(seg_loud_max)
seg_loud_max_max= get_max(seg_loud_max)
seg_loud_max_min = get_min(seg_loud_max)
seg_loud_max_stddev= get_stddev(seg_loud_max)
seg_loud_max_count = get_count(seg_loud_max)
seg_loud_max_sum = get_sum(seg_loud_max)
seg_loud_max_time = hdf5_getters.get_segments_loudness_max_time(h5)
seg_loud_max_time_avg= get_avg(seg_loud_max_time)
seg_loud_max_time_max= get_max(seg_loud_max_time)
seg_loud_max_time_min = get_min(seg_loud_max_time)
seg_loud_max_time_stddev= get_stddev(seg_loud_max_time)
seg_loud_max_time_count = get_count(seg_loud_max_time)
seg_loud_max_time_sum = get_sum(seg_loud_max_time)
seg_loud_start = hdf5_getters.get_segments_loudness_start(h5)
seg_loud_start_avg= get_avg(seg_loud_start)
seg_loud_start_max= get_max(seg_loud_start)
seg_loud_start_min = get_min(seg_loud_start)
seg_loud_start_stddev= get_stddev(seg_loud_start)
seg_loud_start_count = get_count(seg_loud_start)
seg_loud_start_sum = get_sum(seg_loud_start)
seg_pitch = hdf5_getters.get_segments_pitches(h5)
pitch_size = len(seg_pitch)
seg_start = hdf5_getters.get_segments_start(h5)
seg_start_avg= get_avg(seg_start)
seg_start_max= get_max(seg_start)
seg_start_min = get_min(seg_start)
seg_start_stddev= get_stddev(seg_start)
seg_start_count = get_count(seg_start)
seg_start_sum = get_sum(seg_start)
seg_timbre = hdf5_getters.get_segments_timbre(h5)
tatms_c = hdf5_getters.get_tatums_confidence(h5)
tatms_c_avg= get_avg(tatms_c)
tatms_c_max= get_max(tatms_c)
tatms_c_min = get_min(tatms_c)
tatms_c_stddev= get_stddev(tatms_c)
tatms_c_count = get_count(tatms_c)
tatms_c_sum = get_sum(tatms_c)
tatms_start = hdf5_getters.get_tatums_start(h5)
tatms_start_avg= get_avg(tatms_start)
tatms_start_max= get_max(tatms_start)
tatms_start_min = get_min(tatms_start)
tatms_start_stddev= get_stddev(tatms_start)
tatms_start_count = get_count(tatms_start)
tatms_start_sum = get_sum(tatms_start)
#Getting the genres
genre_set = 0 #flag to see if the genre has been set or not
art_trm = hdf5_getters.get_artist_terms(h5)
trm_freq = hdf5_getters.get_artist_terms_freq(h5)
trn_wght = hdf5_getters.get_artist_terms_weight(h5)
a_mb_tags = hdf5_getters.get_artist_mbtags(h5)
genre_indexes=get_genre_indexes(trm_freq) #index of the highest freq
final_genre=[]
genres_so_far=[]
for i in range(len(genre_indexes)):
genre_tmp=get_genre(art_trm,genre_indexes[i]) #genre that corresponds to the highest freq
genres_so_far=genre_dict.get_genre_in_dict(genre_tmp) #getting the genre from the dictionary
if len(genres_so_far) != 0:
for i in genres_so_far:
final_genre.append(i)
genre_set=1 #genre was found in dictionary
if genre_set == 1:
col_num=[]
for genre in final_genre:
column=int(genre) #getting the column number of the genre
col_num.append(column)
genre_array=genre_columns(col_num) #genre array
else:
genre_array=genre_columns(-1) #the genre was not found in the dictionary
transpose_pitch= seg_pitch.transpose() #this is to tranpose the matrix,so we can have 12 rows
#arrays containing the aggregate values of the 12 rows
seg_pitch_avg=[]
seg_pitch_max=[]
seg_pitch_min=[]
seg_pitch_stddev=[]
seg_pitch_count=[]
seg_pitch_sum=[]
i=0
#Getting the aggregate values in the pitches array
for row in transpose_pitch:
seg_pitch_avg.append(get_avg(row))
seg_pitch_max.append(get_max(row))
seg_pitch_min.append(get_min(row))
seg_pitch_stddev.append(get_stddev(row))
seg_pitch_count.append(get_count(row))
seg_pitch_sum.append(get_sum(row))
i=i+1
#extracting information from the timbre array
transpose_timbre = seg_pitch.transpose() #tranposing matrix, to have 12 rows
#arrays containing the aggregate values of the 12 rows
seg_timbre_avg=[]
seg_timbre_max=[]
seg_timbre_min=[]
seg_timbre_stddev=[]
seg_timbre_count=[]
seg_timbre_sum=[]
i=0
for row in transpose_timbre:
seg_timbre_avg.append(get_avg(row))
seg_timbre_max.append(get_max(row))
seg_timbre_min.append(get_min(row))
seg_timbre_stddev.append(get_stddev(row))
seg_timbre_count.append(get_count(row))
seg_timbre_sum.append(get_sum(row))
i=i+1
#Writing to the flat file
writer.writerow([title,album,artist_name,year,duration,seg_start_count, tempo])
h5.close()
count=count+1;
print count;
def apply_to_all_files_mod(basedir,
song_list,
filename='songs.npy',
func=lambda x: x,
ext='.h5'):
"""
From a base directory, goes through all subdirectories, finds all files with the given ext,
and reads each song from each file. For each song in song_list, gets the title, artist, tempo,
familiarity, hottness, terms, dancebility, duration, energy, loudness, and the timbre matrix.
Tab delimits terms, flattens the timbre matrix, adds them all to a np array, and saves the array
with the information from each song to filename.
"""
#Initial list of desired song info
csv_data = []
count = 0
done_gg = False
song_dict = construct_song_dict(song_list)
# iterate over all files in all subdirectories
for root, dirs, files in os.walk(basedir):
files = glob.glob(os.path.join(root, '*' + ext))
#Iterates through each file in files
for filename in files:
count += 1
if count % 1000 == 0:
print count
h5 = GETTERS.open_h5_file_read(filename)
#Scrapes desired data
title = GETTERS.get_title(h5)
artist = GETTERS.get_artist_name(h5)
tempo = GETTERS.get_tempo(h5)
familiarity = GETTERS.get_artist_familiarity(h5)
hotness = GETTERS.get_artist_hotttnesss(h5)
terms = GETTERS.get_artist_terms(h5)
danceability = GETTERS.get_danceability(h5)
duration = GETTERS.get_duration(h5)
energy = GETTERS.get_energy(h5)
loudness = GETTERS.get_loudness(h5)
timbre = GETTERS.get_segments_timbre(h5)
#Tab delimits terms
terms_tabs = "\t".join(terms)
#Flattens timbre
timbre_flattened = timbre.flatten()
#Creates np array of everything but timbre matrix
everything_but_timbre = np.array([
title, artist, tempo, familiarity, hotness, terms_tabs,
danceability, duration, energy, loudness
])
#Combines everything else with timbre matrix
row = np.concatenate((everything_but_timbre, timbre_flattened))
#Checks if artist, song combination was in the list and, if so, adds it.
if artist in song_dict:
if title in song_dict[artist]:
print("Adding {} by {}. Song ID is: {}".format(
title, artist, GETTERS.get_song_id(h5)))
csv_data.append(row)
#Prevents duplicates
song_dict[artist][song_dict[artist].index(title)] = ''
h5.close()
print("Number of songs: {}, artists {}".format(len(csv_data),
len(song_dict)))
csv_array = np.array(csv_data)
#Saves data
np.save(filename, csv_array)
mode = GETTERS.get_mode(h5, i)
mode_confidence = GETTERS.get_mode_confidence(h5, i)
release = GETTERS.get_release(h5, i)
release_7digitalid = GETTERS.get_release_7digitalid(h5, i)
#sections_confidence = ','.join(str(e) for e in GETTERS.get_sections_confidence(h5, i)) # array
#sections_start = ','.join(str(e) for e in GETTERS.get_sections_start(h5, i)) # array
#segments_confidence = ','.join(str(e) for e in GETTERS.get_segments_confidence(h5, i)) # array
#segments_loudness_max = ','.join(str(e) for e in GETTERS.get_segments_loudness_max(h5, i)) # array
#segments_loudness_max_time = ','.join(str(e) for e in GETTERS.get_segments_loudness_max_time(h5, i)) # array
#segments_loudness_start = ','.join(str(e) for e in GETTERS.get_segments_loudness_start(h5, i)) # array
#segments_pitches = ','.join(str(e) for e in GETTERS.get_segments_pitches(h5, i)) # array
#segments_start = ','.join(str(e) for e in GETTERS.get_segments_start(h5, i)) # array
#segments_timbre = ','.join(str(e) for e in GETTERS.get_segments_timbre(h5, i)) # array
similar_artists = ','.join(str(e) for e in GETTERS.get_similar_artists(h5, i)) # array
song_hotttnesss = GETTERS.get_song_hotttnesss(h5, i)
song_id = GETTERS.get_song_id(h5, i)
start_of_fade_out = GETTERS.get_start_of_fade_out(h5, i)
#tatums_confidence = ','.join(str(e) for e in GETTERS.get_tatums_confidence(h5, i)) # array
#tatums_start = ','.join(str(e) for e in GETTERS.get_tatums_start(h5, i)) # array
tempo = GETTERS.get_tempo(h5, i)
time_signature = GETTERS.get_time_signature(h5, i)
time_signature_confidence = GETTERS.get_time_signature_confidence(h5, i)
title = GETTERS.get_title(h5, i)
track_7digitalid = GETTERS.get_track_7digitalid(h5, i)
track_id = GETTERS.get_track_id(h5, i)
year = GETTERS.get_year(h5, i)
loops += 1
release = GETTERS.get_release(h5, i)
release_7digitalid = GETTERS.get_release_7digitalid(h5, i)
#sections_confidence = ','.join(str(e) for e in GETTERS.get_sections_confidence(h5, i)) # array
#sections_start = ','.join(str(e) for e in GETTERS.get_sections_start(h5, i)) # array
#segments_confidence = ','.join(str(e) for e in GETTERS.get_segments_confidence(h5, i)) # array
#segments_loudness_max = ','.join(str(e) for e in GETTERS.get_segments_loudness_max(h5, i)) # array
#segments_loudness_max_time = ','.join(str(e) for e in GETTERS.get_segments_loudness_max_time(h5, i)) # array
#segments_loudness_start = ','.join(str(e) for e in GETTERS.get_segments_loudness_start(h5, i)) # array
#segments_pitches = ','.join(str(e) for e in GETTERS.get_segments_pitches(h5, i)) # array
#segments_start = ','.join(str(e) for e in GETTERS.get_segments_start(h5, i)) # array
#segments_timbre = ','.join(str(e) for e in GETTERS.get_segments_timbre(h5, i)) # array
similar_artists = ','.join(
str(e)
for e in GETTERS.get_similar_artists(h5, i)) # array
song_hotttnesss = GETTERS.get_song_hotttnesss(h5, i)
song_id = GETTERS.get_song_id(h5, i)
start_of_fade_out = GETTERS.get_start_of_fade_out(h5, i)
#tatums_confidence = ','.join(str(e) for e in GETTERS.get_tatums_confidence(h5, i)) # array
#tatums_start = ','.join(str(e) for e in GETTERS.get_tatums_start(h5, i)) # array
tempo = GETTERS.get_tempo(h5, i)
time_signature = GETTERS.get_time_signature(h5, i)
time_signature_confidence = GETTERS.get_time_signature_confidence(
h5, i)
title = GETTERS.get_title(h5, i)
track_7digitalid = GETTERS.get_track_7digitalid(h5, i)
track_id = GETTERS.get_track_id(h5, i)
year = GETTERS.get_year(h5, i)
loops += 1
#row = {'analysis_sample_rate':analysis_sample_rate,'artist_7digitalid':artist_7digitalid,'artist_familiarity':artist_familiarity,'artist_hotttnesss':artist_hotttnesss,'artist_id':artist_id,'artist_latitude':artist_latitude,'artist_location':artist_location,'artist_longitude':artist_longitude,'artist_mbid':artist_mbid,'artist_mbtags_count':artist_mbtags_count,'artist_mbtags':artist_mbtags,'artist_name':artist_name,'artist_terms_freq':artist_terms_freq,'artist_terms_weight':artist_terms_weight,'artist_terms':artist_terms,'audio_md5':audio_md5,'bars_confidence':bars_confidence,'bars_start':bars_start,'beats_confidence':beats_confidence,'beats_start':beats_start,'danceability':danceability,'duration':duration,'end_of_fade_in':end_of_fade_in,'energy':energy,'key_confidence':key_confidence,'key':key,'loudness':loudness,'mode_confidence':mode_confidence,'mode':mode,'release_7digitalid':release_7digitalid,'release':release,'sections_confidence':sections_confidence,'sections_start':sections_start,'segments_confidence':segments_confidence,'segments_loudness_max_time':segments_loudness_max_time,'segments_loudness_max':segments_loudness_max,'segments_loudness_start':segments_loudness_start,'segments_pitches':segments_pitches,'segments_start':segments_start,'segments_timbre':segments_timbre,'similar_artists':similar_artists,'song_hotttnesss':song_hotttnesss,'song_id':song_id,'start_of_fade_out':start_of_fade_out,'tatums_confidence':tatums_confidence,'tatums_start':tatums_start,'tempo':tempo,'time_signature_confidence':time_signature_confidence,'time_signature':time_signature,'title':title,'track_7digitalid':track_7digitalid,'track_id':track_id,'year':year,}
row = {
segments_loudness_start REAL DEFAULT NULL,
segments_pitches REAL DEFAULT NULL,
segments_timbre REAL DEFAULT NULL,
INDEX songID (songID)
);'''
cursor.execute(sql)
connection.commit()
glob_path = '/Users/kenleejr92/MillionSongSubset/data/*/*/*/*'
filepaths = glob.glob(glob_path)
for filepath in tqdm(filepaths):
h5 = hdf5_getters.open_h5_file_read(filepath)
n = hdf5_getters.get_num_songs(h5)
for row in range(n):
song_id = hdf5_getters.get_song_id(h5, songidx=row).decode('UTF-8')
# artist = hdf5_getters.get_artist_name(h5,songidx=row).decode('UTF-8')
# title= hdf5_getters.get_title(h5,songidx=row)#.decode('UTF-8')
# artist = "".join(c for c in unicodedata.normalize('NFD', str(artist.decode("utf8"))) if unicodedata.category(c) != "Mn")
# title = "".join(c for c in unicodedata.normalize('NFD', str(title.decode("utf8"))) if unicodedata.category(c) != "Mn")
#single number features
danceability = hdf5_getters.get_danceability(h5, songidx=row)
duration = hdf5_getters.get_duration(h5, songidx=row)
energy = hdf5_getters.get_energy(h5, songidx=row)
loudness = hdf5_getters.get_loudness(h5, songidx=row)
musicalKey = hdf5_getters.get_key(h5, songidx=row)
mode = hdf5_getters.get_mode(h5, songidx=row)
tempo = hdf5_getters.get_tempo(h5, songidx=row)
time_signature = hdf5_getters.get_time_signature(h5, songidx=row)
year = hdf5_getters.get_year(h5, songidx=row)
def main():
outputFileName = sys.argv[2]
outputFile1 = open(outputFileName, 'w')
csvRowString = ""
#################################################
#if you want to prompt the user for the order of attributes in the csv,
#leave the prompt boolean set to True
#else, set 'prompt' to False and set the order of attributes in the 'else'
#clause
prompt = False
#################################################
if prompt == True:
while prompt:
prompt = False
csvAttributeString = raw_input(
"\n\nIn what order would you like the colums of the CSV file?\n"
+ "Please delineate with commas. The options are: " +
"AlbumName, AlbumID, ArtistID, ArtistLatitude, ArtistLocation, ArtistLongitude,"
+
" ArtistName, Danceability, Duration, KeySignature, KeySignatureConfidence, Tempo,"
+
" SongID, TimeSignature, TimeSignatureConfidence, Title, and Year.\n\n"
+
"For example, you may write \"Title, Tempo, Duration\"...\n\n"
+ "...or exit by typing 'exit'.\n\n")
csvAttributeList = re.split('\W+', csvAttributeString)
for i, v in enumerate(csvAttributeList):
csvAttributeList[i] = csvAttributeList[i].lower()
for attribute in csvAttributeList:
# print "Here is the attribute: " + attribute + " \n"
if attribute == 'AlbumID'.lower():
csvRowString += 'AlbumID'
elif attribute == 'AlbumName'.lower():
csvRowString += 'AlbumName'
elif attribute == 'ArtistID'.lower():
csvRowString += 'ArtistID'
elif attribute == 'ArtistLatitude'.lower():
csvRowString += 'ArtistLatitude'
elif attribute == 'ArtistLocation'.lower():
csvRowString += 'ArtistLocation'
elif attribute == 'ArtistLongitude'.lower():
csvRowString += 'ArtistLongitude'
elif attribute == 'ArtistName'.lower():
csvRowString += 'ArtistName'
elif attribute == 'Danceability'.lower():
csvRowString += 'Danceability'
elif attribute == 'Duration'.lower():
csvRowString += 'Duration'
elif attribute == 'KeySignature'.lower():
csvRowString += 'KeySignature'
elif attribute == 'KeySignatureConfidence'.lower():
csvRowString += 'KeySignatureConfidence'
elif attribute == 'SongID'.lower():
csvRowString += "SongID"
elif attribute == 'Tempo'.lower():
csvRowString += 'Tempo'
elif attribute == 'TimeSignature'.lower():
csvRowString += 'TimeSignature'
elif attribute == 'TimeSignatureConfidence'.lower():
csvRowString += 'TimeSignatureConfidence'
elif attribute == 'Title'.lower():
csvRowString += 'Title'
elif attribute == 'Year'.lower():
csvRowString += 'Year'
elif attribute == 'Exit'.lower():
sys.exit()
else:
prompt = True
print "=============="
print "I believe there has been an error with the input."
print "=============="
break
csvRowString += ","
lastIndex = len(csvRowString)
csvRowString = csvRowString[0:lastIndex - 1]
csvRowString += "\n"
# outputFile1.write(csvRowString);
csvRowString = ""
#else, if you want to hard code the order of the csv file and not prompt
#the user,
else:
#################################################
#change the order of the csv file here
#Default is to list all available attributes (in alphabetical order)
csvRowString = (
"SongID,AlbumID,AlbumName,ArtistID,ArtistLatitude,ArtistLocation,"
+
"ArtistLongitude,ArtistFamiliarity,ArtistHotttnesss,ArtistName," +
"ArtistMBTags,ArtistTerms," +
"Danceability,Energy,Duration,KeySignature," +
"KeySignatureConfidence,Loudness,Mode,Hotttnesss,Tempo,TimeSignature,TimeSignatureConfidence,"
+ "Title,Year")
#################################################
csvAttributeList = re.split('\W+', csvRowString)
for i, v in enumerate(csvAttributeList):
csvAttributeList[i] = csvAttributeList[i].lower()
# outputFile1.write("SongNumber,");
# outputFile1.write(csvRowString + "\n");
csvRowString = ""
#################################################
#Set the basedir here, the root directory from which the search
#for files stored in a (hierarchical data structure) will originate
basedir = sys.argv[1] # "." As the default means the current directory
ext = ".h5" #Set the extension here. H5 is the extension for HDF5 files.
#################################################
#FOR LOOP
for root, dirs, files in os.walk(basedir):
files = glob.glob(os.path.join(root, '*' + ext))
for f in files:
print f
songH5File = hdf5_getters.open_h5_file_read(f)
song = Song(str(hdf5_getters.get_song_id(songH5File)))
testDanceability = hdf5_getters.get_danceability(songH5File)
# print type(testDanceability)
# print ("Here is the danceability: ") + str(testDanceability)
song.artistID = str(hdf5_getters.get_artist_id(songH5File))
song.albumID = str(hdf5_getters.get_release_7digitalid(songH5File))
song.albumName = str(hdf5_getters.get_release(songH5File))
song.artistLatitude = str(
hdf5_getters.get_artist_latitude(songH5File))
song.artistLocation = str(
hdf5_getters.get_artist_location(songH5File))
song.artistLongitude = str(
hdf5_getters.get_artist_longitude(songH5File))
song.artistFamiliarity = str(
hdf5_getters.get_artist_familiarity(songH5File))
song.artistHotttnesss = str(
hdf5_getters.get_artist_hotttnesss(songH5File))
song.artistName = str(hdf5_getters.get_artist_name(songH5File))
song.artistMBTags = ','.join(
hdf5_getters.get_artist_mbtags(songH5File))
# song.artistMBTagsCount = ','.join(hdf5_getters.get_artist_mbtags_count(songH5File))
song.artistTerms = ','.join(
hdf5_getters.get_artist_terms(songH5File))
song.danceability = str(hdf5_getters.get_danceability(songH5File))
song.energy = str(hdf5_getters.get_energy(songH5File))
song.duration = str(hdf5_getters.get_duration(songH5File))
# song.setGenreList()
song.keySignature = str(hdf5_getters.get_key(songH5File))
song.keySignatureConfidence = str(
hdf5_getters.get_key_confidence(songH5File))
song.loudness = str(hdf5_getters.get_loudness(songH5File))
song.mode = str(hdf5_getters.get_mode(songH5File))
# song.lyrics = None
# song.popularity = None
song.hotttnesss = str(hdf5_getters.get_song_hotttnesss(songH5File))
song.tempo = str(hdf5_getters.get_tempo(songH5File))
song.timeSignature = str(
hdf5_getters.get_time_signature(songH5File))
song.timeSignatureConfidence = str(
hdf5_getters.get_time_signature_confidence(songH5File))
song.title = str(hdf5_getters.get_title(songH5File))
song.year = str(hdf5_getters.get_year(songH5File))
#print song count
# csvRowString += str(song.songCount) + ","
rowString = json.dumps({
'AlbumID': song.albumID,
'AlbumName': song.albumName,
'ArtistID': song.artistID,
'ArtistLatitude': song.artistLatitude,
'ArtistLocation': song.artistLocation,
'ArtistLongitude': song.artistLongitude,
'ArtistFamiliarity': song.artistFamiliarity,
'ArtistHotttnesss': song.artistHotttnesss,
'ArtistName': song.artistName,
'ArtistMBTags': song.artistMBTags,
'ArtistTerms': song.artistTerms,
'Danceability': song.danceability,
'Energy': song.energy,
'Duration': song.duration,
'KeySignature': song.keySignature,
'KeySignatureConfidence': song.keySignatureConfidence,
'Loudness': song.loudness,
'Mode': song.mode,
'Hotttnesss': song.hotttnesss,
'Tempo': song.tempo,
'SongID': song.id,
'TimeSignature': song.timeSignature,
'TimeSignatureConfidence': song.timeSignatureConfidence,
'Title': song.title,
'Year': song.year,
})
#Remove the final comma from each row in the csv
rowString += "\n"
outputFile1.write(rowString)
songH5File.close()
outputFile1.close()
def data_to_flat_file(basedir, ext='.h5'):
"""This function extract the information from the tables and creates the flat file."""
count = 0
#song counter
list_to_write = []
row_to_write = ""
writer = csv.writer(open("metadata_wholeA.csv", "wb"))
for root, dirs, files in os.walk(basedir):
files = glob.glob(os.path.join(root, '*' + ext))
for f in files:
print f #the name of the file
h5 = hdf5_getters.open_h5_file_read(f)
title = hdf5_getters.get_title(h5)
title = title.replace('"', '')
comma = title.find(',') #eliminating commas in the title
if comma != -1:
print title
time.sleep(1)
album = hdf5_getters.get_release(h5)
album = album.replace('"', '') #eliminating commas in the album
comma = album.find(',')
if comma != -1:
print album
time.sleep(1)
artist_name = hdf5_getters.get_artist_name(h5)
comma = artist_name.find(',')
if comma != -1:
print artist_name
time.sleep(1)
artist_name = artist_name.replace('"',
'') #eliminating double quotes
duration = hdf5_getters.get_duration(h5)
samp_rt = hdf5_getters.get_analysis_sample_rate(h5)
artist_7digitalid = hdf5_getters.get_artist_7digitalid(h5)
artist_fam = hdf5_getters.get_artist_familiarity(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(artist_fam) == True:
artist_fam = -1
artist_hotness = hdf5_getters.get_artist_hotttnesss(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(artist_hotness) == True:
artist_hotness = -1
artist_id = hdf5_getters.get_artist_id(h5)
artist_lat = hdf5_getters.get_artist_latitude(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(artist_lat) == True:
artist_lat = -1
artist_loc = hdf5_getters.get_artist_location(h5)
#checks artist_loc to see if it is a hyperlink if it is set as empty string
artist_loc = artist_loc.replace(",", "\,")
if artist_loc.startswith("<a"):
artist_loc = ""
if len(artist_loc) > 100:
artist_loc = ""
artist_lon = hdf5_getters.get_artist_longitude(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(artist_lon) == True:
artist_lon = -1
artist_mbid = hdf5_getters.get_artist_mbid(h5)
artist_pmid = hdf5_getters.get_artist_playmeid(h5)
audio_md5 = hdf5_getters.get_audio_md5(h5)
danceability = hdf5_getters.get_danceability(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(danceability) == True:
danceability = -1
end_fade_in = hdf5_getters.get_end_of_fade_in(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(end_fade_in) == True:
end_fade_in = -1
energy = hdf5_getters.get_energy(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(energy) == True:
energy = -1
song_key = hdf5_getters.get_key(h5)
key_c = hdf5_getters.get_key_confidence(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(key_c) == True:
key_c = -1
loudness = hdf5_getters.get_loudness(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(loudness) == True:
loudness = -1
mode = hdf5_getters.get_mode(h5)
mode_conf = hdf5_getters.get_mode_confidence(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(mode_conf) == True:
mode_conf = -1
release_7digitalid = hdf5_getters.get_release_7digitalid(h5)
song_hot = hdf5_getters.get_song_hotttnesss(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(song_hot) == True:
song_hot = -1
song_id = hdf5_getters.get_song_id(h5)
start_fade_out = hdf5_getters.get_start_of_fade_out(h5)
tempo = hdf5_getters.get_tempo(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(tempo) == True:
tempo = -1
time_sig = hdf5_getters.get_time_signature(h5)
time_sig_c = hdf5_getters.get_time_signature_confidence(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(time_sig_c) == True:
time_sig_c = -1
track_id = hdf5_getters.get_track_id(h5)
track_7digitalid = hdf5_getters.get_track_7digitalid(h5)
year = hdf5_getters.get_year(h5)
bars_c = hdf5_getters.get_bars_confidence(h5)
bars_c_avg = get_avg(bars_c)
bars_c_max = get_max(bars_c)
bars_c_min = get_min(bars_c)
bars_c_stddev = get_stddev(bars_c)
bars_c_count = get_count(bars_c)
bars_c_sum = get_sum(bars_c)
bars_start = hdf5_getters.get_bars_start(h5)
bars_start_avg = get_avg(bars_start)
bars_start_max = get_max(bars_start)
bars_start_min = get_min(bars_start)
bars_start_stddev = get_stddev(bars_start)
bars_start_count = get_count(bars_start)
bars_start_sum = get_sum(bars_start)
beats_c = hdf5_getters.get_beats_confidence(h5)
beats_c_avg = get_avg(beats_c)
beats_c_max = get_max(beats_c)
beats_c_min = get_min(beats_c)
beats_c_stddev = get_stddev(beats_c)
beats_c_count = get_count(beats_c)
beats_c_sum = get_sum(beats_c)
beats_start = hdf5_getters.get_beats_start(h5)
beats_start_avg = get_avg(beats_start)
beats_start_max = get_max(beats_start)
beats_start_min = get_min(beats_start)
beats_start_stddev = get_stddev(beats_start)
beats_start_count = get_count(beats_start)
beats_start_sum = get_sum(beats_start)
sec_c = hdf5_getters.get_sections_confidence(h5)
sec_c_avg = get_avg(sec_c)
sec_c_max = get_max(sec_c)
sec_c_min = get_min(sec_c)
sec_c_stddev = get_stddev(sec_c)
sec_c_count = get_count(sec_c)
sec_c_sum = get_sum(sec_c)
sec_start = hdf5_getters.get_sections_start(h5)
sec_start_avg = get_avg(sec_start)
sec_start_max = get_max(sec_start)
sec_start_min = get_min(sec_start)
sec_start_stddev = get_stddev(sec_start)
sec_start_count = get_count(sec_start)
sec_start_sum = get_sum(sec_start)
seg_c = hdf5_getters.get_segments_confidence(h5)
seg_c_avg = get_avg(seg_c)
seg_c_max = get_max(seg_c)
seg_c_min = get_min(seg_c)
seg_c_stddev = get_stddev(seg_c)
seg_c_count = get_count(seg_c)
seg_c_sum = get_sum(seg_c)
seg_loud_max = hdf5_getters.get_segments_loudness_max(h5)
seg_loud_max_avg = get_avg(seg_loud_max)
seg_loud_max_max = get_max(seg_loud_max)
seg_loud_max_min = get_min(seg_loud_max)
seg_loud_max_stddev = get_stddev(seg_loud_max)
seg_loud_max_count = get_count(seg_loud_max)
seg_loud_max_sum = get_sum(seg_loud_max)
seg_loud_max_time = hdf5_getters.get_segments_loudness_max_time(h5)
seg_loud_max_time_avg = get_avg(seg_loud_max_time)
seg_loud_max_time_max = get_max(seg_loud_max_time)
seg_loud_max_time_min = get_min(seg_loud_max_time)
seg_loud_max_time_stddev = get_stddev(seg_loud_max_time)
seg_loud_max_time_count = get_count(seg_loud_max_time)
seg_loud_max_time_sum = get_sum(seg_loud_max_time)
seg_loud_start = hdf5_getters.get_segments_loudness_start(h5)
seg_loud_start_avg = get_avg(seg_loud_start)
seg_loud_start_max = get_max(seg_loud_start)
seg_loud_start_min = get_min(seg_loud_start)
seg_loud_start_stddev = get_stddev(seg_loud_start)
seg_loud_start_count = get_count(seg_loud_start)
seg_loud_start_sum = get_sum(seg_loud_start)
seg_pitch = hdf5_getters.get_segments_pitches(h5)
pitch_size = len(seg_pitch)
seg_start = hdf5_getters.get_segments_start(h5)
seg_start_avg = get_avg(seg_start)
seg_start_max = get_max(seg_start)
seg_start_min = get_min(seg_start)
seg_start_stddev = get_stddev(seg_start)
seg_start_count = get_count(seg_start)
seg_start_sum = get_sum(seg_start)
seg_timbre = hdf5_getters.get_segments_timbre(h5)
tatms_c = hdf5_getters.get_tatums_confidence(h5)
tatms_c_avg = get_avg(tatms_c)
tatms_c_max = get_max(tatms_c)
tatms_c_min = get_min(tatms_c)
tatms_c_stddev = get_stddev(tatms_c)
tatms_c_count = get_count(tatms_c)
tatms_c_sum = get_sum(tatms_c)
tatms_start = hdf5_getters.get_tatums_start(h5)
tatms_start_avg = get_avg(tatms_start)
tatms_start_max = get_max(tatms_start)
tatms_start_min = get_min(tatms_start)
tatms_start_stddev = get_stddev(tatms_start)
tatms_start_count = get_count(tatms_start)
tatms_start_sum = get_sum(tatms_start)
#Getting the genres
genre_set = 0 #flag to see if the genre has been set or not
art_trm = hdf5_getters.get_artist_terms(h5)
trm_freq = hdf5_getters.get_artist_terms_freq(h5)
trn_wght = hdf5_getters.get_artist_terms_weight(h5)
a_mb_tags = hdf5_getters.get_artist_mbtags(h5)
genre_indexes = get_genre_indexes(
trm_freq) #index of the highest freq
final_genre = []
genres_so_far = []
for i in range(len(genre_indexes)):
genre_tmp = get_genre(
art_trm, genre_indexes[i]
) #genre that corresponds to the highest freq
genres_so_far = genre_dict.get_genre_in_dict(
genre_tmp) #getting the genre from the dictionary
if len(genres_so_far) != 0:
for i in genres_so_far:
final_genre.append(i)
genre_set = 1 #genre was found in dictionary
if genre_set == 1:
col_num = []
for genre in final_genre:
column = int(
genre) #getting the column number of the genre
col_num.append(column)
genre_array = genre_columns(col_num) #genre array
else:
genre_array = genre_columns(
-1) #the genre was not found in the dictionary
transpose_pitch = seg_pitch.transpose(
) #this is to tranpose the matrix,so we can have 12 rows
#arrays containing the aggregate values of the 12 rows
seg_pitch_avg = []
seg_pitch_max = []
seg_pitch_min = []
seg_pitch_stddev = []
seg_pitch_count = []
seg_pitch_sum = []
i = 0
#Getting the aggregate values in the pitches array
for row in transpose_pitch:
seg_pitch_avg.append(get_avg(row))
seg_pitch_max.append(get_max(row))
seg_pitch_min.append(get_min(row))
seg_pitch_stddev.append(get_stddev(row))
seg_pitch_count.append(get_count(row))
seg_pitch_sum.append(get_sum(row))
i = i + 1
#extracting information from the timbre array
transpose_timbre = seg_pitch.transpose(
) #tranposing matrix, to have 12 rows
#arrays containing the aggregate values of the 12 rows
seg_timbre_avg = []
seg_timbre_max = []
seg_timbre_min = []
seg_timbre_stddev = []
seg_timbre_count = []
seg_timbre_sum = []
i = 0
for row in transpose_timbre:
seg_timbre_avg.append(get_avg(row))
seg_timbre_max.append(get_max(row))
seg_timbre_min.append(get_min(row))
seg_timbre_stddev.append(get_stddev(row))
seg_timbre_count.append(get_count(row))
seg_timbre_sum.append(get_sum(row))
i = i + 1
#Writing to the flat file
writer.writerow([
title, album, artist_name, year, duration, seg_start_count,
tempo
])
h5.close()
count = count + 1
print count
def data_to_flat_file(basedir,ext='.h5') :
"""This function extract the information from the tables and creates the flat file."""
count = 0; #song counter
list_to_write= []
row_to_write = ""
writer = csv.writer(open("metadata.csv", "wb"))
for root, dirs, files in os.walk(basedir):
files = glob.glob(os.path.join(root,'*'+ext))
for f in files:
print f #the name of the file
h5 = hdf5_getters.open_h5_file_read(f)
title = hdf5_getters.get_title(h5)
title= title.replace('"','')
comma=title.find(',') #eliminating commas in the title
if comma != -1:
print title
time.sleep(1)
album = hdf5_getters.get_release(h5)
album= album.replace('"','') #eliminating commas in the album
comma=album.find(',')
if comma != -1:
print album
time.sleep(1)
artist_name = hdf5_getters.get_artist_name(h5)
comma=artist_name.find(',')
if comma != -1:
print artist_name
time.sleep(1)
artist_name= artist_name.replace('"','') #eliminating double quotes
duration = hdf5_getters.get_duration(h5)
samp_rt = hdf5_getters.get_analysis_sample_rate(h5)
artist_7digitalid = hdf5_getters.get_artist_7digitalid(h5)
artist_fam = hdf5_getters.get_artist_familiarity(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(artist_fam) == True:
artist_fam=-1
artist_hotness= hdf5_getters.get_artist_hotttnesss(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(artist_hotness) == True:
artist_hotness=-1
artist_id = hdf5_getters.get_artist_id(h5)
artist_lat = hdf5_getters.get_artist_latitude(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(artist_lat) == True:
artist_lat=-1
artist_loc = hdf5_getters.get_artist_location(h5)
#checks artist_loc to see if it is a hyperlink if it is set as empty string
artist_loc = artist_loc.replace(",", "\,");
if artist_loc.startswith("<a"):
artist_loc = ""
if len(artist_loc) > 100:
artist_loc = ""
artist_lon = hdf5_getters.get_artist_longitude(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(artist_lon) == True:
artist_lon=-1
artist_mbid = hdf5_getters.get_artist_mbid(h5)
artist_pmid = hdf5_getters.get_artist_playmeid(h5)
audio_md5 = hdf5_getters.get_audio_md5(h5)
danceability = hdf5_getters.get_danceability(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(danceability) == True:
danceability=-1
end_fade_in =hdf5_getters.get_end_of_fade_in(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(end_fade_in) == True:
end_fade_in=-1
energy = hdf5_getters.get_energy(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(energy) == True:
energy=-1
song_key = hdf5_getters.get_key(h5)
key_c = hdf5_getters.get_key_confidence(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(key_c) == True:
key_c=-1
loudness = hdf5_getters.get_loudness(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(loudness) == True:
loudness=-1
mode = hdf5_getters.get_mode(h5)
mode_conf = hdf5_getters.get_mode_confidence(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(mode_conf) == True:
mode_conf=-1
release_7digitalid = hdf5_getters.get_release_7digitalid(h5)
song_hot = hdf5_getters.get_song_hotttnesss(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(song_hot) == True:
song_hot=-1
song_id = hdf5_getters.get_song_id(h5)
start_fade_out = hdf5_getters.get_start_of_fade_out(h5)
tempo = hdf5_getters.get_tempo(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(tempo) == True:
tempo=-1
time_sig = hdf5_getters.get_time_signature(h5)
time_sig_c = hdf5_getters.get_time_signature_confidence(h5)
#checking if we get a "nan" if we do we change it to -1
if numpy.isnan(time_sig_c) == True:
time_sig_c=-1
track_id = hdf5_getters.get_track_id(h5)
track_7digitalid = hdf5_getters.get_track_7digitalid(h5)
year = hdf5_getters.get_year(h5)
bars_c = hdf5_getters.get_bars_confidence(h5)
bars_c_avg= get_avg(bars_c)
bars_c_max= get_max(bars_c)
bars_c_min = get_min(bars_c)
bars_c_stddev= get_stddev(bars_c)
bars_c_count = get_count(bars_c)
bars_c_sum = get_sum(bars_c)
bars_start = hdf5_getters.get_bars_start(h5)
bars_start_avg = get_avg(bars_start)
bars_start_max= get_max(bars_start)
bars_start_min = get_min(bars_start)
bars_start_stddev= get_stddev(bars_start)
bars_start_count = get_count(bars_start)
bars_start_sum = get_sum(bars_start)
beats_c = hdf5_getters.get_beats_confidence(h5)
beats_c_avg= get_avg(beats_c)
beats_c_max= get_max(beats_c)
beats_c_min = get_min(beats_c)
beats_c_stddev= get_stddev(beats_c)
beats_c_count = get_count(beats_c)
beats_c_sum = get_sum(beats_c)
beats_start = hdf5_getters.get_beats_start(h5)
beats_start_avg = get_avg(beats_start)
beats_start_max= get_max(beats_start)
beats_start_min = get_min(beats_start)
beats_start_stddev= get_stddev(beats_start)
beats_start_count = get_count(beats_start)
beats_start_sum = get_sum(beats_start)
sec_c = hdf5_getters.get_sections_confidence(h5)
sec_c_avg= get_avg(sec_c)
sec_c_max= get_max(sec_c)
sec_c_min = get_min(sec_c)
sec_c_stddev= get_stddev(sec_c)
sec_c_count = get_count(sec_c)
sec_c_sum = get_sum(sec_c)
sec_start = hdf5_getters.get_sections_start(h5)
sec_start_avg = get_avg(sec_start)
sec_start_max= get_max(sec_start)
sec_start_min = get_min(sec_start)
sec_start_stddev= get_stddev(sec_start)
sec_start_count = get_count(sec_start)
sec_start_sum = get_sum(sec_start)
seg_c = hdf5_getters.get_segments_confidence(h5)
seg_c_avg= get_avg(seg_c)
seg_c_max= get_max(seg_c)
seg_c_min = get_min(seg_c)
seg_c_stddev= get_stddev(seg_c)
seg_c_count = get_count(seg_c)
seg_c_sum = get_sum(seg_c)
seg_loud_max = hdf5_getters.get_segments_loudness_max(h5)
seg_loud_max_avg= get_avg(seg_loud_max)
seg_loud_max_max= get_max(seg_loud_max)
seg_loud_max_min = get_min(seg_loud_max)
seg_loud_max_stddev= get_stddev(seg_loud_max)
seg_loud_max_count = get_count(seg_loud_max)
seg_loud_max_sum = get_sum(seg_loud_max)
seg_loud_max_time = hdf5_getters.get_segments_loudness_max_time(h5)
seg_loud_max_time_avg= get_avg(seg_loud_max_time)
seg_loud_max_time_max= get_max(seg_loud_max_time)
seg_loud_max_time_min = get_min(seg_loud_max_time)
seg_loud_max_time_stddev= get_stddev(seg_loud_max_time)
seg_loud_max_time_count = get_count(seg_loud_max_time)
seg_loud_max_time_sum = get_sum(seg_loud_max_time)
seg_loud_start = hdf5_getters.get_segments_loudness_start(h5)
seg_loud_start_avg= get_avg(seg_loud_start)
seg_loud_start_max= get_max(seg_loud_start)
seg_loud_start_min = get_min(seg_loud_start)
seg_loud_start_stddev= get_stddev(seg_loud_start)
seg_loud_start_count = get_count(seg_loud_start)
seg_loud_start_sum = get_sum(seg_loud_start)
seg_pitch = hdf5_getters.get_segments_pitches(h5)
pitch_size = len(seg_pitch)
seg_start = hdf5_getters.get_segments_start(h5)
seg_start_avg= get_avg(seg_start)
seg_start_max= get_max(seg_start)
seg_start_min = get_min(seg_start)
seg_start_stddev= get_stddev(seg_start)
seg_start_count = get_count(seg_start)
seg_start_sum = get_sum(seg_start)
seg_timbre = hdf5_getters.get_segments_timbre(h5)
tatms_c = hdf5_getters.get_tatums_confidence(h5)
tatms_c_avg= get_avg(tatms_c)
tatms_c_max= get_max(tatms_c)
tatms_c_min = get_min(tatms_c)
tatms_c_stddev= get_stddev(tatms_c)
tatms_c_count = get_count(tatms_c)
tatms_c_sum = get_sum(tatms_c)
tatms_start = hdf5_getters.get_tatums_start(h5)
tatms_start_avg= get_avg(tatms_start)
tatms_start_max= get_max(tatms_start)
tatms_start_min = get_min(tatms_start)
tatms_start_stddev= get_stddev(tatms_start)
tatms_start_count = get_count(tatms_start)
tatms_start_sum = get_sum(tatms_start)
#Getting the genres
genre_set = 0 #flag to see if the genre has been set or not
art_trm = hdf5_getters.get_artist_terms(h5)
trm_freq = hdf5_getters.get_artist_terms_freq(h5)
trn_wght = hdf5_getters.get_artist_terms_weight(h5)
a_mb_tags = hdf5_getters.get_artist_mbtags(h5)
genre_indexes=get_genre_indexes(trm_freq) #index of the highest freq
final_genre=[]
genres_so_far=[]
for i in range(len(genre_indexes)):
genre_tmp=get_genre(art_trm,genre_indexes[i]) #genre that corresponds to the highest freq
genres_so_far=genre_dict.get_genre_in_dict(genre_tmp) #getting the genre from the dictionary
if len(genres_so_far) != 0:
for i in genres_so_far:
final_genre.append(i)
genre_set=1 #genre was found in dictionary
if genre_set == 1:
col_num=[]
for genre in final_genre:
column=int(genre) #getting the column number of the genre
col_num.append(column)
genre_array=genre_columns(col_num) #genre array
else:
genre_array=genre_columns(-1) #the genre was not found in the dictionary
transpose_pitch= seg_pitch.transpose() #this is to tranpose the matrix,so we can have 12 rows
#arrays containing the aggregate values of the 12 rows
seg_pitch_avg=[]
seg_pitch_max=[]
seg_pitch_min=[]
seg_pitch_stddev=[]
seg_pitch_count=[]
seg_pitch_sum=[]
i=0
#Getting the aggregate values in the pitches array
for row in transpose_pitch:
seg_pitch_avg.append(get_avg(row))
seg_pitch_max.append(get_max(row))
seg_pitch_min.append(get_min(row))
seg_pitch_stddev.append(get_stddev(row))
seg_pitch_count.append(get_count(row))
seg_pitch_sum.append(get_sum(row))
i=i+1
#extracting information from the timbre array
transpose_timbre = seg_pitch.transpose() #tranposing matrix, to have 12 rows
#arrays containing the aggregate values of the 12 rows
seg_timbre_avg=[]
seg_timbre_max=[]
seg_timbre_min=[]
seg_timbre_stddev=[]
seg_timbre_count=[]
seg_timbre_sum=[]
i=0
for row in transpose_timbre:
seg_timbre_avg.append(get_avg(row))
seg_timbre_max.append(get_max(row))
seg_timbre_min.append(get_min(row))
seg_timbre_stddev.append(get_stddev(row))
seg_timbre_count.append(get_count(row))
seg_timbre_sum.append(get_sum(row))
i=i+1
#Writing to the flat file
writer.writerow([title,album,artist_name,duration,samp_rt,artist_7digitalid,artist_fam,artist_hotness,artist_id,artist_lat,artist_loc,artist_lon,artist_mbid,genre_array[0],genre_array[1],genre_array[2],
genre_array[3],genre_array[4],genre_array[5],genre_array[6],genre_array[7],genre_array[8],genre_array[9],genre_array[10],genre_array[11],genre_array[12],genre_array[13],genre_array[14],genre_array[15],
genre_array[16],genre_array[17],genre_array[18],genre_array[19],genre_array[20],genre_array[21],genre_array[22],genre_array[23],genre_array[24],genre_array[25],genre_array[26],
genre_array[27],genre_array[28],genre_array[29],genre_array[30],genre_array[31],genre_array[32],genre_array[33],genre_array[34],genre_array[35],genre_array[36],genre_array[37],genre_array[38],
genre_array[39],genre_array[40],genre_array[41],genre_array[42],genre_array[43],genre_array[44],genre_array[45],genre_array[46],genre_array[47],genre_array[48],genre_array[49],
genre_array[50],genre_array[51],genre_array[52],genre_array[53],genre_array[54],genre_array[55],genre_array[56],genre_array[57],genre_array[58],genre_array[59],
genre_array[60],genre_array[61],genre_array[62],genre_array[63],genre_array[64],genre_array[65],genre_array[66],genre_array[67],genre_array[68],genre_array[69],
genre_array[70],genre_array[71],genre_array[72],genre_array[73],genre_array[74],genre_array[75],genre_array[76],genre_array[77],genre_array[78],genre_array[79],
genre_array[80],genre_array[81],genre_array[82],genre_array[83],genre_array[84],genre_array[85],genre_array[86],genre_array[87],genre_array[88],genre_array[89],
genre_array[90],genre_array[91],genre_array[92],genre_array[93],genre_array[94],genre_array[95],genre_array[96],genre_array[97],genre_array[98],genre_array[99],genre_array[100],genre_array[101],
genre_array[102],genre_array[103],genre_array[104],genre_array[105],genre_array[106],genre_array[107],genre_array[108],genre_array[109],genre_array[110],genre_array[111],genre_array[112],
genre_array[113],genre_array[114],genre_array[115],genre_array[116],genre_array[117],genre_array[118],genre_array[119],genre_array[120],genre_array[121],genre_array[122],genre_array[123],
genre_array[124],genre_array[125],genre_array[126],genre_array[127],genre_array[128],genre_array[129],genre_array[130],genre_array[131],genre_array[132],
artist_pmid,audio_md5,danceability,end_fade_in,energy,song_key,key_c,loudness,mode,mode_conf,release_7digitalid,song_hot,song_id,start_fade_out,tempo,time_sig,time_sig_c,track_id,track_7digitalid,year,bars_c_avg,bars_c_max,bars_c_min,bars_c_stddev,bars_c_count,bars_c_sum,bars_start_avg,bars_start_max,bars_start_min,bars_start_stddev,bars_start_count,bars_start_sum,beats_c_avg,beats_c_max,beats_c_min,beats_c_stddev,beats_c_count,beats_c_sum,beats_start_avg,beats_start_max,beats_start_min, beats_start_stddev,beats_start_count,beats_start_sum, sec_c_avg,sec_c_max,sec_c_min,sec_c_stddev,sec_c_count,sec_c_sum,sec_start_avg,sec_start_max,sec_start_min,sec_start_stddev,sec_start_count,sec_start_sum,seg_c_avg,seg_c_max,seg_c_min,seg_c_stddev,seg_c_count,seg_c_sum,seg_loud_max_avg,seg_loud_max_max,seg_loud_max_min,seg_loud_max_stddev,seg_loud_max_count,seg_loud_max_sum,seg_loud_max_time_avg,seg_loud_max_time_max,seg_loud_max_time_min,seg_loud_max_time_stddev,seg_loud_max_time_count,seg_loud_max_time_sum,seg_loud_start_avg,seg_loud_start_max,seg_loud_start_min,seg_loud_start_stddev,seg_loud_start_count,seg_loud_start_sum,seg_pitch_avg[0],seg_pitch_max[0],seg_pitch_min[0],seg_pitch_stddev[0],seg_pitch_count[0],seg_pitch_sum[0],seg_pitch_avg[1],seg_pitch_max[1],seg_pitch_min[1],seg_pitch_stddev[1],seg_pitch_count[1],seg_pitch_sum[1],seg_pitch_avg[2],seg_pitch_max[2],seg_pitch_min[2],seg_pitch_stddev[2],seg_pitch_count[2],seg_pitch_sum[2],seg_pitch_avg[3],seg_pitch_max[3],seg_pitch_min[3],seg_pitch_stddev[3],seg_pitch_count[3],seg_pitch_sum[3],seg_pitch_avg[4],seg_pitch_max[4],seg_pitch_min[4],seg_pitch_stddev[4],seg_pitch_count[4],seg_pitch_sum[4],seg_pitch_avg[5],seg_pitch_max[5],seg_pitch_min[5],seg_pitch_stddev[5],seg_pitch_count[5],seg_pitch_sum[5],seg_pitch_avg[6],seg_pitch_max[6],seg_pitch_min[6],seg_pitch_stddev[6],seg_pitch_count[6],seg_pitch_sum[6],seg_pitch_avg[7],seg_pitch_max[7],seg_pitch_min[7],seg_pitch_stddev[7],seg_pitch_count[7],seg_pitch_sum[7],seg_pitch_avg[8],seg_pitch_max[8],seg_pitch_min[8],seg_pitch_stddev[8],seg_pitch_count[8],seg_pitch_sum[8],seg_pitch_avg[9],seg_pitch_max[9],seg_pitch_min[9],seg_pitch_stddev[9],seg_pitch_count[9],seg_pitch_sum[9],seg_pitch_avg[10],seg_pitch_max[10],seg_pitch_min[10],seg_pitch_stddev[10],seg_pitch_count[10],seg_pitch_sum[10],seg_pitch_avg[11],seg_pitch_max[11],seg_pitch_min[11],
seg_pitch_stddev[11],seg_pitch_count[11],seg_pitch_sum[11],seg_start_avg,seg_start_max,seg_start_min,seg_start_stddev,
seg_start_count,seg_start_sum,seg_timbre_avg[0],seg_timbre_max[0],seg_timbre_min[0],seg_timbre_stddev[0],seg_timbre_count[0],
seg_timbre_sum[0],seg_timbre_avg[1],seg_timbre_max[1],seg_timbre_min[1],seg_timbre_stddev[1],seg_timbre_count[1],
seg_timbre_sum[1],seg_timbre_avg[2],seg_timbre_max[2],seg_timbre_min[2],seg_timbre_stddev[2],seg_timbre_count[2],
seg_timbre_sum[2],seg_timbre_avg[3],seg_timbre_max[3],seg_timbre_min[3],seg_timbre_stddev[3],seg_timbre_count[3],
seg_timbre_sum[3],seg_timbre_avg[4],seg_timbre_max[4],seg_timbre_min[4],seg_timbre_stddev[4],seg_timbre_count[4],
seg_timbre_sum[4],seg_timbre_avg[5],seg_timbre_max[5],seg_timbre_min[5],seg_timbre_stddev[5],seg_timbre_count[5],
seg_timbre_sum[5],seg_timbre_avg[6],seg_timbre_max[6],seg_timbre_min[6],seg_timbre_stddev[6],seg_timbre_count[6],
seg_timbre_sum[6],seg_timbre_avg[7],seg_timbre_max[7],seg_timbre_min[7],seg_timbre_stddev[7],seg_timbre_count[7],
seg_timbre_sum[7],seg_timbre_avg[8],seg_timbre_max[8],seg_timbre_min[8],seg_timbre_stddev[8],seg_timbre_count[8],
seg_timbre_sum[8],seg_timbre_avg[9],seg_timbre_max[9],seg_timbre_min[9],seg_timbre_stddev[9],seg_timbre_count[9],
seg_timbre_sum[9],seg_timbre_avg[10],seg_timbre_max[10],seg_timbre_min[10],seg_timbre_stddev[10],seg_timbre_count[10],
seg_timbre_sum[10],seg_timbre_avg[11],seg_timbre_max[11],seg_timbre_min[11],seg_timbre_stddev[11],seg_timbre_count[11],
seg_timbre_sum[11],tatms_c_avg,tatms_c_max,tatms_c_min,tatms_c_stddev,tatms_c_count,tatms_c_sum,tatms_start_avg,tatms_start_max,tatms_start_min,tatms_start_stddev,tatms_start_count,tatms_start_sum])
h5.close()
count=count+1;
print count;
song_order = dict()
for line in songs_file:
song = re.split(r'[ ]', line)
song_order[song[0]] = song[1]
outputDir = output_dir
i = 0
hits = 0
for dirpath, dirnames, filenames in os.walk(input_dir):
for track_file in filenames:
#print track_file
#song = re.split(r'[ ]', songs[i])
output = "<song xmlns=\'http://labrosa.ee.columbia.edu/millionsong/\'>\n"
h5 = hdf5_getters.open_h5_file_read(os.path.join(dirpath, track_file))
song_id = hdf5_getters.get_song_id(h5)
for getter in getters:
try:
res = hdf5_getters.__getattribute__(getter)(h5)
except AttributeError, e:
continue
if res.__class__.__name__ == 'ndarray':
output = output + "<"+getter[4:]+">"+str(res.shape)+"</"+getter[4:]+">\n"
else:
output = output + "<"+getter[4:]+">"+str(res)+"</"+getter[4:]+">\n"
h5.close()
if song_id in song_order:
output = output + "<order>" + song_order[song_id][:-1] + "</order>\n"
logger.debug(track_file +' HIT')
hits = hits + 1
# Recursively visit each sub-dir till we reach the h5 files
# Strip punctuation from features that are strings
for root, dirs, filenames in os.walk(data_dir):
for f in filenames:
if f[-3:] != '.h5':
continue
#log = open(os.path.join(root, f),'r')
#print os.path.join(root, f)
# Use the hd5 wrappers to open the h5 file
h5 = hdf5_getters.open_h5_file_read(os.path.join(root, f))
# EXTRACTING FEATURES
# See hd5_getter.py for the various features that we can extract from each h5 file
#Get song id
song_id = hdf5_getters.get_song_id(h5)
if song_id not in songSet:
continue
# Get the artist name
artist_name = hdf5_getters.get_artist_name(h5)
artist = artist_name.translate(None, string.punctuation)
# Get the title of the song
title_song = hdf5_getters.get_title(h5)
title = title_song.translate(None, string.punctuation)
# Get artist location
artist_location = hdf5_getters.get_artist_location(h5)
artist_loc = artist_location.translate(None, string.punctuation)
def save_songs():
'''
Reads the song infos for all songs in the directory specified in
MSD_DATA_PATH, imputes missing data, normalizes the data and stores it as
a JSON file.
'''
# read all relevant infos from the songs and store them in a dictionary
print('Reading song infos from the h5 files ...')
song_dict = {}
i = -1
ids = set()
for root, dirs, files in os.walk(MSD_DATA_PATH):
files = glob.glob(os.path.join(root, '*' + '.h5'))
for file in files:
h5 = GETTERS.open_h5_file_read(file)
id = GETTERS.get_song_id(h5).decode('UTF-8')
# if there are multiple song files with the same id only the first
# is saved
if id not in ids:
i += 1
ids.add(id)
song_dict[i] = {}
song_dict[i]['id'] = id # save the song id
song_dict[i]['title'] = GETTERS.get_title(h5).decode(
'UTF-8').replace("'", "") # save the title
song_dict[i]['artist'] = GETTERS.get_artist_name(h5).decode(
'UTF-8').replace("'", "") # save the artist
# save the remaining parameters or, whenever a value is
# missing, save np.NaN instead
for key, method in zip(PARS, METHODS):
value = getattr(GETTERS, method)(h5)
if math.isnan(value):
song_dict[i][key] = np.NaN
else:
song_dict[i][key] = value
h5.close()
# impute missing values via fancyimpute MICE imputation and store the new
# values in the dictionary
print('Building the array for MICE ...')
song_array = []
for index in range(0, len(song_dict)):
song_array.append([song_dict[index][par] for par in PARS])
print('MICE ...')
mc = MICE()
a = mc.complete(np.array(song_array))
print('Storing imputed data in song dictionary ...')
# store the values for each parameter in a list for the normalization
# in the next step
val_lists = []
for par in PARS:
val_lists.append([])
for index in range(0, len(song_dict)):
for par, val_list, nr in zip(PARS, val_lists, range(0, len(PARS))):
value = a[index, nr]
song_dict[index][par] = value
val_list.append(value)
# normalize the values
print('Normalizing the values ...')
for par, val_list in zip(PARS, val_lists):
max_value = -float("inf")
min_value = float("inf")
for index in song_dict:
max_value = max(max_value, song_dict[index][par])
min_value = min(min_value, song_dict[index][par])
for index in song_dict:
song_dict[index][par] = (
song_dict[index][par] - np.mean(val_list)) / \
(max_value - min_value) * 100
# save the data as a JSON file
print('Saving JSON ...')
with open(INITIAL_OUTPUT_FILE_PATH, 'w') as outfile:
json.dump(song_dict, outfile)
print('done')
if name.endswith(".h5"):
if process_completion % 2350 == 0:
print "done :", process_completion/2350.0, "%"
process_completion += 1
header_counter += 1
else:
process_completion += 1
header_counter += 1
tempPath = os.path.abspath(os.path.join(root,name))
h5SongFile = hdf5_getters.open_h5_file_read(tempPath)
# create the sample row for feature matrix
# initialize the list with track ID and song ID
sampleRow = [hdf5_getters.get_track_id(h5SongFile),
hdf5_getters.get_song_id(h5SongFile)]
cnt = 0
for func in featureFunctions:
cnt += 1
# print "functionNumber: ", cnt
# print "BarStrctr: ", hdf5_getters.get_bars_start(h5SongFile)
sampleRow += func(h5SongFile)
# Construct the feature matrix that contains all the songs...
# Data structure for featureMatrix will be list of lists, so that...
# Numpy will be able to convert it to a matrix in a way that...
# All list elements will become rows
# featureMatrix += [sampleRow]
featureMatrix = [sampleRow]
def main():
outputFile1 = open('SongCSV.csv', 'w')
csvRowString = ""
#################################################
#if you want to prompt the user for the order of attributes in the csv,
#leave the prompt boolean set to True
#else, set 'prompt' to False and set the order of attributes in the 'else'
#clause
prompt = False
#################################################
if prompt == True:
while prompt:
prompt = False
csvAttributeString = raw_input(
"\n\nIn what order would you like the colums of the CSV file?\n"
+ "Please delineate with commas. The options are: " +
"AlbumName, AlbumID, ArtistID, ArtistLatitude, ArtistLocation, ArtistLongitude,"
+
" ArtistName, Danceability, Duration, KeySignature, KeySignatureConfidence, Tempo,"
+
" SongID, TimeSignature, TimeSignatureConfidence, Title, and Year.\n\n"
+
"For example, you may write \"Title, Tempo, Duration\"...\n\n"
+ "...or exit by typing 'exit'.\n\n")
csvAttributeList = re.split('\W+', csvAttributeString)
for i, v in enumerate(csvAttributeList):
csvAttributeList[i] = csvAttributeList[i].lower()
for attribute in csvAttributeList:
# print "Here is the attribute: " + attribute + " \n"
if attribute == 'AlbumID'.lower():
csvRowString += 'AlbumID'
elif attribute == 'AlbumName'.lower():
csvRowString += 'AlbumName'
elif attribute == 'ArtistID'.lower():
csvRowString += 'ArtistID'
elif attribute == 'ArtistLatitude'.lower():
csvRowString += 'ArtistLatitude'
elif attribute == 'ArtistLocation'.lower():
csvRowString += 'ArtistLocation'
elif attribute == 'ArtistLongitude'.lower():
csvRowString += 'ArtistLongitude'
elif attribute == 'ArtistName'.lower():
csvRowString += 'ArtistName'
elif attribute == 'Danceability'.lower():
csvRowString += 'Danceability'
elif attribute == 'Duration'.lower():
csvRowString += 'Duration'
elif attribute == 'KeySignature'.lower():
csvRowString += 'KeySignature'
elif attribute == 'KeySignatureConfidence'.lower():
csvRowString += 'KeySignatureConfidence'
elif attribute == 'SongID'.lower():
csvRowString += "SongID"
elif attribute == 'Tempo'.lower():
csvRowString += 'Tempo'
elif attribute == 'TimeSignature'.lower():
csvRowString += 'TimeSignature'
elif attribute == 'TimeSignatureConfidence'.lower():
csvRowString += 'TimeSignatureConfidence'
elif attribute == 'Title'.lower():
csvRowString += 'Title'
elif attribute == 'Year'.lower():
csvRowString += 'Year'
elif attribute == 'Exit'.lower():
sys.exit()
else:
prompt = True
print "=============="
print "I believe there has been an error with the input."
print "=============="
break
csvRowString += ","
lastIndex = len(csvRowString)
csvRowString = csvRowString[0:lastIndex - 1]
csvRowString += "\n"
outputFile1.write(csvRowString)
csvRowString = ""
#else, if you want to hard code the order of the csv file and not prompt
#the user,
else:
#################################################
#change the order of the csv file here
#Default is to list all available attributes (in alphabetical order)
csvRowString = (
"SongID,AlbumID,AlbumName,TrackId,ArtistID,ArtistLatitude,ArtistLocation,"
+
"ArtistLongitude,ArtistName,Danceability,Duration,KeySignature," +
"KeySignatureConfidence,Tempo,TimeSignature,TimeSignatureConfidence,"
+ "Title,Year")
#################################################
csvAttributeList = re.split('\W+', csvRowString)
for i, v in enumerate(csvAttributeList):
csvAttributeList[i] = csvAttributeList[i].lower()
outputFile1.write("SongNumber,")
outputFile1.write(csvRowString + "\n")
csvRowString = ""
#################################################
#Set the basedir here, the root directory from which the search
#for files stored in a (hierarchical data structure) will originate
basedir = "/home/umwangye/millonsong/MillionSongSubset/data/" # "." As the default means the current directory
ext = ".h5" #Set the extension here. H5 is the extension for HDF5 files.
#################################################
#FOR LOOP
for root, dirs, files in os.walk(basedir):
files = glob.glob(os.path.join(root, '*' + ext))
for f in files:
print f
songH5File = hdf5_getters.open_h5_file_read(f)
#song = Song(str(hdf5_getters.get_song_id(songH5File)))
#testDanceability = hdf5_getters.get_danceability(songH5File)
# print type(testDanceability)
# print ("Here is the danceability: ") + str(testDanceability)
numPerH5 = hdf5_getters.get_num_songs(songH5File)
for cnt in range(numPerH5):
song = Song(str(hdf5_getters.get_song_id(songH5File, cnt)))
song.trackId = str(hdf5_getters.get_track_id(songH5File, cnt))
song.artistID = str(hdf5_getters.get_artist_id(
songH5File, cnt))
song.albumID = str(
hdf5_getters.get_release_7digitalid(songH5File, cnt))
song.albumName = str(hdf5_getters.get_release(songH5File, cnt))
song.artistLatitude = str(
hdf5_getters.get_artist_latitude(songH5File, cnt))
song.artistLocation = str(
hdf5_getters.get_artist_location(songH5File, cnt))
song.artistLongitude = str(
hdf5_getters.get_artist_longitude(songH5File, cnt))
song.artistName = str(
hdf5_getters.get_artist_name(songH5File, cnt))
song.danceability = str(
hdf5_getters.get_danceability(songH5File, cnt))
song.duration = str(hdf5_getters.get_duration(songH5File, cnt))
# song.setGenreList()
song.keySignature = str(hdf5_getters.get_key(songH5File, cnt))
song.keySignatureConfidence = str(
hdf5_getters.get_key_confidence(songH5File, cnt))
# song.lyrics = None
# song.popularity = None
song.tempo = str(hdf5_getters.get_tempo(songH5File, cnt))
song.timeSignature = str(
hdf5_getters.get_time_signature(songH5File, cnt))
song.timeSignatureConfidence = str(
hdf5_getters.get_time_signature_confidence(
songH5File, cnt))
song.title = str(hdf5_getters.get_title(songH5File, cnt))
song.year = str(hdf5_getters.get_year(songH5File, cnt))
#print song count
csvRowString += str(song.songCount) + ","
for attribute in csvAttributeList:
# print "Here is the attribute: " + attribute + " \n"
if attribute == 'AlbumID'.lower():
csvRowString += song.albumID
elif attribute == 'AlbumName'.lower():
albumName = song.albumName
albumName = albumName.replace(',', "")
csvRowString += "\"" + albumName + "\""
elif attribute == 'TrackId'.lower():
csvRowString += song.trackId
elif attribute == 'ArtistID'.lower():
csvRowString += "\"" + song.artistID + "\""
elif attribute == 'ArtistLatitude'.lower():
latitude = song.artistLatitude
if latitude == 'nan':
latitude = ''
csvRowString += latitude
elif attribute == 'ArtistLocation'.lower():
location = song.artistLocation
location = location.replace(',', '')
csvRowString += "\"" + location + "\""
elif attribute == 'ArtistLongitude'.lower():
longitude = song.artistLongitude
if longitude == 'nan':
longitude = ''
csvRowString += longitude
elif attribute == 'ArtistName'.lower():
csvRowString += "\"" + song.artistName + "\""
elif attribute == 'Danceability'.lower():
csvRowString += song.danceability
elif attribute == 'Duration'.lower():
csvRowString += song.duration
elif attribute == 'KeySignature'.lower():
csvRowString += song.keySignature
elif attribute == 'KeySignatureConfidence'.lower():
# print "key sig conf: " + song.timeSignatureConfidence
csvRowString += song.keySignatureConfidence
elif attribute == 'SongID'.lower():
csvRowString += "\"" + song.id + "\""
elif attribute == 'Tempo'.lower():
# print "Tempo: " + song.tempo
csvRowString += song.tempo
elif attribute == 'TimeSignature'.lower():
csvRowString += song.timeSignature
elif attribute == 'TimeSignatureConfidence'.lower():
# print "time sig conf: " + song.timeSignatureConfidence
csvRowString += song.timeSignatureConfidence
elif attribute == 'Title'.lower():
csvRowString += "\"" + song.title + "\""
elif attribute == 'Year'.lower():
csvRowString += song.year
else:
csvRowString += "Erm. This didn't work. Error. :( :(\n"
csvRowString += ","
#Remove the final comma from each row in the csv
lastIndex = len(csvRowString)
csvRowString = csvRowString[0:lastIndex - 1]
csvRowString += "\n"
outputFile1.write(csvRowString)
csvRowString = ""
songH5File.close()
outputFile1.close()
def getInfo(files):
data = []
build_str = ''
with open(sys.argv[1], 'r') as f:
contents = f.read()
c = contents.split()
f.close()
print("creating csv with following fields:" + contents)
for i in c:
build_str = build_str + i + ','
build_str = build_str[:-1]
build_str = build_str + '\n'
for fil in files:
curFile = getters.open_h5_file_read(fil)
d2 = {}
get_table = {'track_id': getters.get_track_id(curFile), 'segments_pitches': getters.get_segments_pitches(curFile), 'time_signature_confidence': getters.get_time_signature_confidence(curFile), 'song_hotttnesss': getters.get_song_hotttnesss(curFile), 'artist_longitude': getters.get_artist_longitude(curFile), 'tatums_confidence': getters.get_tatums_confidence(curFile), 'num_songs': getters.get_num_songs(curFile), 'duration': getters.get_duration(curFile), 'start_of_fade_out': getters.get_start_of_fade_out(curFile), 'artist_name': getters.get_artist_name(curFile), 'similar_artists': getters.get_similar_artists(curFile), 'artist_mbtags': getters.get_artist_mbtags(curFile), 'artist_terms_freq': getters.get_artist_terms_freq(curFile), 'release': getters.get_release(curFile), 'song_id': getters.get_song_id(curFile), 'track_7digitalid': getters.get_track_7digitalid(curFile), 'title': getters.get_title(curFile), 'artist_latitude': getters.get_artist_latitude(curFile), 'energy': getters.get_energy(curFile), 'key': getters.get_key(curFile), 'release_7digitalid': getters.get_release_7digitalid(curFile), 'artist_mbid': getters.get_artist_mbid(curFile), 'segments_confidence': getters.get_segments_confidence(curFile), 'artist_hotttnesss': getters.get_artist_hotttnesss(curFile), 'time_signature': getters.get_time_signature(curFile), 'segments_loudness_max_time': getters.get_segments_loudness_max_time(curFile), 'mode': getters.get_mode(curFile), 'segments_loudness_start': getters.get_segments_loudness_start(curFile), 'tempo': getters.get_tempo(curFile), 'key_confidence': getters.get_key_confidence(curFile), 'analysis_sample_rate': getters.get_analysis_sample_rate(curFile), 'bars_confidence': getters.get_bars_confidence(curFile), 'artist_playmeid': getters.get_artist_playmeid(curFile), 'artist_terms_weight': getters.get_artist_terms_weight(curFile), 'segments_start': getters.get_segments_start(curFile), 'artist_location': getters.get_artist_location(curFile), 'loudness': getters.get_loudness(curFile), 'year': getters.get_year(curFile), 'artist_7digitalid': getters.get_artist_7digitalid(curFile), 'audio_md5': getters.get_audio_md5(curFile), 'segments_timbre': getters.get_segments_timbre(curFile), 'mode_confidence': getters.get_mode_confidence(curFile), 'end_of_fade_in': getters.get_end_of_fade_in(curFile), 'danceability': getters.get_danceability(curFile), 'artist_familiarity': getters.get_artist_familiarity(curFile), 'artist_mbtags_count': getters.get_artist_mbtags_count(curFile), 'tatums_start': getters.get_tatums_start(curFile), 'artist_id': getters.get_artist_id(curFile), 'segments_loudness_max': getters.get_segments_loudness_max(curFile), 'bars_start': getters.get_bars_start(curFile), 'beats_start': getters.get_beats_start(curFile), 'artist_terms': getters.get_artist_terms(curFile), 'sections_start': getters.get_sections_start(curFile), 'beats_confidence': getters.get_beats_confidence(curFile), 'sections_confidence': getters.get_sections_confidence(curFile)}
tid = fil.split('/')[-1].split('.')[0]
# print(c)
for i in c:
if i in get_table:
d2[i] = get_table[i]
d2[i] = str(d2[i]).replace('\n','')
build_str = build_str + d2[i] + ','
else:
print('error: unspecified field')
exit(0)
build_str = build_str[:-1]
# print(build_str[:-1])
build_str = build_str + '\n'
curFile.close()
build_str = build_str.replace('b','').replace("'",'').replace('"','')
return (build_str)
