def create_songdet(h5, sngidxfle):
'''
Collects song details for all unique songs heard by 100 raters.
Format of dictionary: { SongID : [ Att_0, Att_1, Att_2 ] }
'''
import hdf5_getters
sngdetfle = open("songdet.txt", "wb")
sngdetdic = dict()
sngidxfle = open(sngidxfle, "rb")
sngidxdic = pickle.load(sngidxfle)
for elem in sngidxdic:
songidx = sngidxdic[elem]
tempo = hdf5_getters.get_tempo(h5, songidx)
loud = hdf5_getters.get_loudness(h5, songidx)
year = hdf5_getters.get_year(h5, songidx)
tmsig = hdf5_getters.get_time_signature(h5, songidx)
key = hdf5_getters.get_key(h5, songidx)
mode = hdf5_getters.get_mode(h5, songidx)
duration = hdf5_getters.get_duration(h5, songidx)
fadein = hdf5_getters.get_end_of_fade_in(h5, songidx)
fadeout = hdf5_getters.get_start_of_fade_out(h5, songidx)
artfam = hdf5_getters.get_artist_familiarity(h5, songidx)
sngdetdic[elem] = [duration, tmsig, tempo,
key, mode, fadein, fadeout, year, loud, artfam]
pickle.dump(sngdetdic, sngdetfle)
sngdetfle.close()
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 create_songdet(h5, sngidxfle):
'''
Collects song details for all unique songs heard by 100 raters.
Format of dictionary: { SongID : [ Att_0, Att_1, Att_2 ] }
'''
import hdf5_getters
sngdetfle = open("songdet.txt", "wb")
sngdetdic = dict()
sngidxfle = open(sngidxfle, "rb")
sngidxdic = pickle.load(sngidxfle)
for elem in sngidxdic:
songidx = sngidxdic[elem]
tempo = hdf5_getters.get_tempo(h5, songidx)
loud = hdf5_getters.get_loudness(h5, songidx)
year = hdf5_getters.get_year(h5, songidx)
tmsig = hdf5_getters.get_time_signature(h5, songidx)
key = hdf5_getters.get_key(h5, songidx)
mode = hdf5_getters.get_mode(h5, songidx)
duration = hdf5_getters.get_duration(h5, songidx)
fadein = hdf5_getters.get_end_of_fade_in(h5, songidx)
fadeout = hdf5_getters.get_start_of_fade_out(h5, songidx)
artfam = hdf5_getters.get_artist_familiarity(h5, songidx)
sngdetdic[elem] = [
duration, tmsig, tempo, key, mode, fadein, fadeout, year, loud,
artfam
]
pickle.dump(sngdetdic, sngdetfle)
sngdetfle.close()
def get_attribute(files):
array = []
count = 0
for f in files:
temp = []
count += 1
print(f)
h5 = hdf5_getters.open_h5_file_read(f)
temp.append(hdf5_getters.get_num_songs(h5))
temp.append(hdf5_getters.get_artist_familiarity(h5))
temp.append(hdf5_getters.get_artist_hotttnesss(h5))
temp.append(hdf5_getters.get_danceability(h5))
temp.append(hdf5_getters.get_energy(h5))
temp.append(hdf5_getters.get_key(h5))
temp.append(hdf5_getters.get_key_confidence(h5))
temp.append(hdf5_getters.get_loudness(h5))
temp.append(hdf5_getters.get_mode(h5))
temp.append(hdf5_getters.get_mode_confidence(h5))
temp.append(hdf5_getters.get_tempo(h5))
temp.append(hdf5_getters.get_time_signature(h5))
temp.append(hdf5_getters.get_time_signature_confidence(h5))
temp.append(hdf5_getters.get_title(h5))
temp.append(hdf5_getters.get_artist_name(h5))
temp = np.nan_to_num(temp)
array.append(temp)
# if count%100 ==0:
# print(array[count-100:count-1])
# kmean.fit(array[count-100:count-1])
h5.close()
return array
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 h5_to_csv_fields(h5,song): '''Converts h5 format to text Inputs: h5, an h5 file object, usable with the wrapper code MSongsDB song, an integer, representing which song in the h5 file to take the info out of (h5 files contain many songs) Output: a string representing all the information of this song, as a single line of a csv file ''' rv=[] ##All these are regular getter functions from wrapper code rv.append(gt.get_artist_name(h5,song)) rv.append(gt.get_title(h5, song)) rv.append(gt.get_release(h5, song)) rv.append(gt.get_year(h5,song)) rv.append(gt.get_duration(h5,song)) rv.append(gt.get_artist_familiarity(h5,song)) rv.append(gt.get_artist_hotttnesss(h5,song)) rv.append(gt.get_song_hotttnesss(h5, song)) ##artist_terms, artist_terms_freq, and artist_terms_weight getter functions ##are all arrays, so we need to turn them into strings first. We used '_' as a separator rv.append(array_to_csv_field(list(gt.get_artist_terms(h5,song)))) rv.append(array_to_csv_field(list(gt.get_artist_terms_freq(h5,song)))) rv.append(array_to_csv_field(list(gt.get_artist_terms_weight(h5,song)))) rv.append(gt.get_mode(h5,song)) rv.append(gt.get_key(h5,song)) rv.append(gt.get_tempo(h5,song)) rv.append(gt.get_loudness(h5,song)) rv.append(gt.get_danceability(h5,song)) rv.append(gt.get_energy(h5,song)) rv.append(gt.get_time_signature(h5,song)) rv.append(array_to_csv_field(list(gt.get_segments_start(h5,song)))) ##These arrays have vectors (Arrays) as items, 12 dimensional each ##An array like [[1,2,3],[4,5,6]] will be written to csv as '1;2;3_4;5;6', i.e. there's two types of separators rv.append(double_Array_to_csv_field(list(gt.get_segments_timbre(h5,song)),'_',';')) rv.append(double_Array_to_csv_field(list(gt.get_segments_pitches(h5,song)),'_',';')) rv.append(array_to_csv_field(list(gt.get_segments_loudness_start(h5,song)))) rv.append(array_to_csv_field(list(gt.get_segments_loudness_max(h5,song)))) rv.append(array_to_csv_field(list(gt.get_segments_loudness_max_time(h5,song)))) rv.append(array_to_csv_field(list(gt.get_sections_start(h5,song)))) ##turn this list into a string with comma separators (i.e. a csv line) rv_string=array_to_csv_field(rv, ",") rv_string+="\n" return rv_string
def get_attribute(f):
temp = []
count += 1
print(f)
h5 = hdf5_getters.open_h5_file_read(f)
temp.append(hdf5_getters.get_num_songs(h5))
temp.append(hdf5_getters.get_artist_familiarity(h5))
temp.append(hdf5_getters.get_artist_hotttnesss(h5))
temp.append(hdf5_getters.get_danceability(h5))
temp.append(hdf5_getters.get_energy(h5))
temp.append(hdf5_getters.get_key(h5))
temp.append(hdf5_getters.get_key_confidence(h5))
temp.append(hdf5_getters.get_loudness(h5))
temp.append(hdf5_getters.get_mode(h5))
temp.append(hdf5_getters.get_mode_confidence(h5))
temp.append(hdf5_getters.get_tempo(h5))
temp.append(hdf5_getters.get_time_signature(h5))
temp.append(hdf5_getters.get_time_signature_confidence(h5))
temp = np.nan_to_num(temp)
array.append(temp)
h5.close()
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 func_to_extract_features(filename):
"""
This function does 3 simple things:
- open the song file
- get artist ID and put it
- close the file
"""
global cntnan
global listfeatures
cf = []
h5 = GETTERS.open_h5_file_read(filename)
nanfound = 0
#Get target feature: song hotness
#FEATURE 0
song_hotness = GETTERS.get_song_hotttnesss(h5)
if math.isnan(song_hotness):
nanfound = 1
cntnan = cntnan + 1
else:
if song_hotness <= 0.2:
song_hotness_class = 0
elif song_hotness <= 0.4:
song_hotness_class = 1
elif song_hotness <= 0.6:
song_hotness_class = 2
elif song_hotness <= 0.8:
song_hotness_class = 3
else:
song_hotness_class = 4
cf.append(song_hotness_class)
#FEATURE 1
#Get song loudness
song_loudness = GETTERS.get_loudness(h5)
if math.isnan(song_loudness):
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(song_loudness)
#FEATURE 2
#Get song year
song_year = GETTERS.get_year(h5)
if song_year == 0:
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(song_year)
#FEATURE 3
#Get song tempo
song_tempo = GETTERS.get_tempo(h5)
cf.append(song_tempo)
#Feature 4
#Artist familarity
artist_familiarity = GETTERS.get_artist_familiarity(h5)
cf.append(artist_familiarity)
#Feature 5
artist_hotness = GETTERS.get_artist_hotttnesss(h5)
if math.isnan(artist_hotness):
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(artist_hotness)
if nanfound == 0:
strlist = list_to_csv(cf)
listfeatures.append(strlist)
h5.close()
if __name__ == "__main__":
with open("fields.csv", "wb") as f:
writer = csv.writer(f) # initialize the csv writer
# for each track in the summary file, get the 11 fields and output to csv
h5_file = hdf5_getters.open_h5_file_read("msd_summary_file.h5")
for k in range(1000000):
print "index!!!: ", k
id = hdf5_getters.get_track_id(h5_file, k) # get track_id TRA13e39..
title = hdf5_getters.get_title(h5_file, k) # get song title
artist_name = hdf5_getters.get_artist_name(h5_file, k)
year = int(hdf5_getters.get_year(h5_file, k))
hotness = float(hdf5_getters.get_song_hotttnesss(h5_file, k))
artist_familiarity = float(hdf5_getters.get_artist_familiarity(h5_file, k))
f5 = int(hdf5_getters.get_key(h5_file, k)) # get key
f2 = float(hdf5_getters.get_loudness(h5_file, k)) # get loudness
f1 = float(hdf5_getters.get_tempo(h5_file, k)) # get tempo
f4 = int(hdf5_getters.get_duration(h5_file, k)) # get duration
f3 = float(hdf5_getters.get_time_signature(h5_file, k)) # get time signature
# Get rid of missing info and change invalid numbers for meta data
if not artist_name:
artist_name = "unknown"
if not artist_familiarity:
artist_familiarity = 0.0
if not hotness:
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 == 'track_id'.lower():
csvRowString += 'track_id'
elif attribute == 'artist_familiarity'.lower():
csvRowString += 'artist_familiarity'
elif attribute == 'artist_hotttnesss'.lower():
csvRowString += 'artist_hotttnesss'
elif attribute == 'artist_mbid'.lower():
csvRowString += 'artist_mbid'
elif attribute == 'artist_playmeid'.lower():
csvRowString += 'artist_playmeid'
elif attribute == 'artist_7digitalid'.lower():
csvRowString += 'artist_7digitalid'
elif attribute == 'release'.lower():
csvRowString += 'release'
elif attribute == 'release_7digitalid'.lower():
csvRowString += 'release_7digitalid'
elif attribute == 'song_hotttnesss'.lower():
csvRowString += 'song_hotttnesss'
elif attribute == 'track_7digitalid'.lower():
csvRowString += 'track_7digitalid'
elif attribute == 'analysis_sample_rate'.lower():
csvRowString += 'analysis_sample_rate'
elif attribute == 'audio_md5'.lower():
csvRowString += 'audio_md5'
elif attribute == 'end_of_fade_in'.lower():
csvRowString += 'end_of_fade_in'
elif attribute == 'energy'.lower():
csvRowString += 'energy'
elif attribute == 'key'.lower():
csvRowString += 'key'
elif attribute == 'key_confidence'.lower():
csvRowString += 'key_confidence'
elif attribute == 'loudness'.lower():
csvRowString += 'loudness'
elif attribute == 'mode'.lower():
csvRowString += 'mode'
elif attribute == 'mode_confidence'.lower():
csvRowString += 'mode_confidence'
elif attribute == 'start_of_fade_out'.lower():
csvRowString += 'start_of_fade_out'
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,track_id,artist_hotttnesss,artist_mbid,artist_playmeid,artist_7digitalid,"+
"release,release_7digitalid,song_hotttnesss,track_7digitalid,analysis_sample_rate,audio_md5,"+
"end_of_fade_in,energy,key,key_confidence,loudness,mode,mode_confidence,start_of_fade_out")
#################################################
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 = "/vagrant/genrepython/MillionSongSubset" # "." 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))
song.track_id = str(hdf5_getters.get_track_id(songH5File))
song.artist_familiarity = str(hdf5_getters.get_artist_familiarity(songH5File))
song.artist_hotttnesss = str(hdf5_getters.get_artist_hotttnesss(songH5File))
song.artist_mbid = str(hdf5_getters.get_artist_mbid(songH5File))
song.artist_playmeid = str(hdf5_getters.get_artist_playmeid(songH5File))
song.artist_7digitalid = str(hdf5_getters.get_artist_7digitalid(songH5File))
song.release = str(hdf5_getters.get_release(songH5File))
song.release_7digitalid = str(hdf5_getters.get_release_7digitalid(songH5File))
song.song_hotttnesss = str(hdf5_getters.get_song_hotttnesss(songH5File))
song.track_7digitalid = str(hdf5_getters.get_track_7digitalid(songH5File))
song.analysis_sample_rate = str(hdf5_getters.get_analysis_sample_rate(songH5File))
song.audio_md5 = str(hdf5_getters.get_audio_md5(songH5File))
song.end_of_fade_in = 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.key_confidence = str(hdf5_getters.get_key_confidence(songH5File))
song.loudness = str(hdf5_getters.get_loudness(songH5File))
song.mode = str(hdf5_getters.get_mode(songH5File))
song.mode_confidence = str(hdf5_getters.get_mode_confidence(songH5File))
song.start_of_fade_out = str(hdf5_getters.get_start_of_fade_out(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
elif attribute == 'track_id'.lower():
csvRowString += song.track_id
elif attribute == 'artist_familiarity'.lower():
csvRowString += song.artist_familiarity
elif attribute == 'artist_hotttnesss'.lower():
csvRowString += song.artist_hotttnesss
elif attribute == 'artist_mbid'.lower():
csvRowString += song.artist_mbid
elif attribute == 'artist_playmeid'.lower():
csvRowString += song.artist_playmeid
elif attribute == 'artist_7digitalid'.lower():
csvRowString += song.artist_7digitalid
elif attribute == 'release'.lower():
csvRowString += song.release
elif attribute == 'release_7digitalid'.lower():
csvRowString += song.release_7digitalid
elif attribute == 'song_hotttnesss'.lower():
csvRowString += song.song_hotttnesss
elif attribute == 'track_7digitalid'.lower():
csvRowString += song.track_7digitalid
elif attribute == 'analysis_sample_rate'.lower():
csvRowString += song.analysis_sample_rate
elif attribute == 'audio_md5'.lower():
csvRowString += song.audio_md5
elif attribute == 'end_of_fade_in'.lower():
csvRowString += song.end_of_fade_in
elif attribute == 'energy'.lower():
csvRowString += song.energy
elif attribute == 'key'.lower():
csvRowString += song.key
elif attribute == 'key_confidence'.lower():
csvRowString += song.key_confidence
elif attribute == 'loudness'.lower():
csvRowString += song.loudness
elif attribute == 'mode'.lower():
csvRowString += song.mode
elif attribute == 'mode_confidence'.lower():
csvRowString += song.mode_confidence
elif attribute == 'start_of_fade_out'.lower():
csvRowString += song.start_of_fade_out
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()
if __name__ == "__main__":
with open("fields.csv", "wb") as f:
writer = csv.writer(f) #initialize the csv writer
# for each track in the summary file, get the 11 fields and output to csv
h5_file = hdf5_getters.open_h5_file_read('msd_summary_file.h5')
for k in range(1000000):
print "index!!!: ", k
id = hdf5_getters.get_track_id(h5_file,k) #get track_id TRA13e39..
title = hdf5_getters.get_title(h5_file,k) # get song title
artist_name = hdf5_getters.get_artist_name(h5_file,k)
year = int(hdf5_getters.get_year(h5_file,k))
hotness= float(hdf5_getters.get_song_hotttnesss(h5_file,k))
artist_familiarity = float(hdf5_getters.get_artist_familiarity(h5_file,k))
f5 = int(hdf5_getters.get_key(h5_file,k)) #get key
f2 = float(hdf5_getters.get_loudness(h5_file,k)) #get loudness
f1 = float(hdf5_getters.get_tempo(h5_file,k)) #get tempo
f4 = int(hdf5_getters.get_duration(h5_file,k)) #get duration
f3 = float(hdf5_getters.get_time_signature(h5_file,k)) #get time signature
# Get rid of missing info and change invalid numbers for meta data
if not artist_name:
artist_name = "unknown"
if not artist_familiarity:
artist_familiarity=0.0
cnt = 0
loops = 0
for alpha in string.ascii_uppercase:
for root, dirs, files in os.walk('/mnt/million-songs/data/' + alpha):
files = glob.glob(os.path.join(root, '*' + '.h5'))
for f in files:
h5 = GETTERS.open_h5_file_read(f)
num_songs = GETTERS.get_num_songs(h5)
print f, num_songs
for i in range(num_songs):
analysis_sample_rate = GETTERS.get_analysis_sample_rate(h5, i)
artist_7digitalid = GETTERS.get_artist_7digitalid(h5, i)
artist_familiarity = GETTERS.get_artist_familiarity(h5, i)
artist_hotttnesss = GETTERS.get_artist_hotttnesss(h5, i)
artist_id = GETTERS.get_artist_id(h5, i)
artist_latitude = GETTERS.get_artist_latitude(h5, i)
artist_location = GETTERS.get_artist_location(h5, i)
artist_longitude = GETTERS.get_artist_longitude(h5, i)
artist_mbid = GETTERS.get_artist_mbid(h5, i)
artist_mbtags = ','.join(
str(e) for e in GETTERS.get_artist_mbtags(h5, i)) # array
artist_mbtags_count = ','.join(
str(e)
for e in GETTERS.get_artist_mbtags_count(h5, i)) # array
artist_name = GETTERS.get_artist_name(h5, i)
artist_playmeid = GETTERS.get_artist_playmeid(h5, i)
artist_terms = ','.join(
str(e) for e in GETTERS.get_artist_terms(h5, i)) # array
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():
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
row += [h5.get_artist_terms(ds)]
row += [h5.get_artist_terms_freq(ds)]
row += [h5.get_artist_terms_weight(ds)]
row += [h5.get_danceability(ds)]
row += [h5.get_energy(ds)]
row += [h5.get_key(ds)]
row += [h5.get_mode(ds)]
row += [h5.get_loudness(ds)]
row += [
parent_folder + '/' + sub_folder + '/' +
child_folder + '/'
]
row += [file]
row += [h5.get_duration(ds)]
row += [h5.get_artist_familiarity(ds)]
row += [h5.get_similar_artists(ds)]
row += [h5.get_artist_id(ds)]
row += [h5.get_title(ds)]
row += [h5.get_song_hotttnesss(ds)]
row += [h5.get_year(ds)]
row += [h5.get_artist_latitude(ds)]
row += [h5.get_artist_longitude(ds)]
row += [
get_midi_name_from_matched(
file[:-3], matched_scores)
]
ds.close()
csv_writer.writerow(row)
def func_to_extract_features(filename):
"""
This function does 3 simple things:
- open the song file
- get artist ID and put it
- close the file
"""
global cntnan
global listfeatures
cf = []
h5 = GETTERS.open_h5_file_read(filename)
nanfound = 0
#Get target feature: song hotness
#FEATURE 0
song_hotness = GETTERS.get_song_hotttnesss(h5)
if math.isnan(song_hotness):
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(song_hotness)
#FEATURE 1
#Get song loudness
song_loudness = GETTERS.get_loudness(h5)
if math.isnan(song_loudness):
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(song_loudness)
#FEATURE 2
#Get key of the song
song_key = GETTERS.get_key(h5)
if math.isnan(song_key):
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(song_key)
#FEATURE 3
#Get duration of the song
song_duration = GETTERS.get_duration(h5)
if math.isnan(song_duration):
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(song_duration)
#FEATURE 4-15
#Get Average Pitch Class across all segments
#Get the pitches (12 pitches histogram for each segment)
pitches = GETTERS.get_segments_pitches(h5)
M = np.mat(pitches)
meanpitches = M.mean(axis=0)
pitches_arr = np.asarray(meanpitches)
pitches_list = []
for i in range(0,12):
pitches_list.append(pitches_arr[0][i])
cf.append(pitches_list)
#FEATURE 16, 27
#Get Average Timbre Class across all segments
timbres = GETTERS.get_segments_timbre(h5)
M = np.mat(timbres)
meantimbres = M.mean(axis=0)
timbre_arr = np.asarray(meantimbres)
timbre_list = []
for i in range(0,12):
timbre_list.append(timbre_arr[0][i])
cf.append(timbre_list)
#FEATURE 28
#Get song year
song_year = GETTERS.get_year(h5)
if song_year == 0:
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(song_year)
#FEATURE 29
#Get song tempo
song_tempo = GETTERS.get_tempo(h5)
cf.append(song_tempo)
#Feature 30
#Get max loudness for each segment
max_loudness_arr = GETTERS.get_segments_loudness_max(h5)
start_loudness_arr = GETTERS.get_segments_loudness_start(h5)
if nanfound == 0:
cf.append(max(max_loudness_arr)-min(start_loudness_arr))
#Feature 31
artist_familiarity = GETTERS.get_artist_familiarity(h5)
cf.append(artist_familiarity)
#Feature 32
artist_hotness = GETTERS.get_artist_hotttnesss(h5)
if math.isnan(artist_hotness):
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(artist_hotness)
if nanfound == 0:
strlist = list_to_csv(cf)
listfeatures.append(strlist)
h5.close()
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
counter = 0
for subdir, dirs, files in os.walk("data/"):
for file in files:
f = os.path.join(subdir, file)
if ".h5" in f:
h5 = h.open_h5_file_read(f)
print("----------")
''' Store artist tuples '''
artist_id = h.get_artist_id(h5, 0)
artist_name = h.get_artist_name(h5, 0)
artist_name = artist_name.replace("'", "")
artist_hottness = str(h.get_artist_hotttnesss(h5, 0))
print artist_hottness
if artist_hottness == "nan":
artist_hottness = "0.0"
artist_familiarity = str(h.get_artist_familiarity(h5, 0))
if artist_familiarity == "nan":
artist_familiarity = "0.0"
cursor.execute("SELECT * FROM artist WHERE artist_id = '" +
artist_id + "'")
rs = cursor.fetchall()
if cursor.rowcount != 1:
cursor.execute("INSERT INTO artist VALUES ('" + artist_id +
"','" + artist_name + "'," + artist_hottness +
"," + artist_familiarity + ");")
''' Store artist_genres tuples '''
terms = h.get_artist_terms(h5, 0)
mbtags = h.get_artist_mbtags(h5, 0)
for term in terms:
term = term.replace("'", "")
def get_all_rows(basedir, ext='.h5'):
rows = []
for root, dirs, files in os.walk(basedir):
files = glob.glob(os.path.join(root, '*' + ext))
for f in files:
# print(os.path.join(root, f))
h5 = hdf5_getters.open_h5_file_read(f)
num_songs = hdf5_getters.get_num_songs(h5)
# print(num_songs)
for i in range(num_songs):
print(i)
obj = {}
obj['artist_name'] = hdf5_getters.get_artist_name(
h5, i).decode('UTF-8')
obj['artist_familiarity'] = hdf5_getters.get_artist_familiarity(
h5, i)
obj['artist_hotness'] = hdf5_getters.get_artist_hotttnesss(
h5, i)
obj['artist_id'] = hdf5_getters.get_artist_id(
h5, i).decode('UTF-8')
# obj['artist_mbid']=hdf5_getters.get_artist_mbid(h5,i).decode('UTF-8')
obj['artist_playmeid'] = hdf5_getters.get_artist_playmeid(
h5, i)
obj['artist_7digitalid'] = hdf5_getters.get_artist_7digitalid(
h5, i)
# obj['artist_latitude']=hdf5_getters.get_artist_latitude(h5,i)
# obj['artist_longitude']=hdf5_getters.get_artist_longitude(h5,i)
# obj['artist_location']=hdf5_getters.get_artist_location(h5,i).decode('UTF-8')
obj['artist_name'] = hdf5_getters.get_artist_name(
h5, i).decode('UTF-8')
obj['release'] = hdf5_getters.get_release(h5,
i).decode('UTF-8')
obj['song_hotttnesss'] = hdf5_getters.get_song_hotttnesss(
h5, i)
obj['title'] = hdf5_getters.get_title(h5, i).decode('UTF-8')
# obj['artist_terms']=hdf5_getters.get_artist_terms(h5)
# obj['artist_terms_freq']=hdf5_getters.get_artist_terms_freq(h5)
# obj['artist_terms_weight']=hdf5_getters.get_artist_terms_weight(h5)
# obj['audio_md5']=hdf5_getters.get_audio_md5(h5).decode('UTF-8')
obj['danceability'] = hdf5_getters.get_danceability(h5, i)
obj['duration'] = hdf5_getters.get_duration(h5, i)
obj['end_of_fade_in'] = hdf5_getters.get_end_of_fade_in(h5, i)
obj['energy'] = hdf5_getters.get_energy(h5, i)
obj['key'] = hdf5_getters.get_key(h5, i)
obj['key_confidence'] = hdf5_getters.get_key_confidence(h5, i)
obj['loudness'] = hdf5_getters.get_loudness(h5, i)
obj['mode'] = hdf5_getters.get_mode(h5, i)
# obj['start_of_fade_out']=hdf5_getters.get_start_of_fade_out(h5)
obj['tempo'] = hdf5_getters.get_tempo(h5, i)
obj['time_signature'] = hdf5_getters.get_time_signature(h5, i)
# obj['time_signature_confidence']=hdf5_getters.get_time_signature_confidence(h5)
obj['track_id'] = hdf5_getters.get_track_id(h5,
i).decode('UTF-8')
# obj['segments_start']=hdf5_getters.get_segments_start(h5)
# obj['segments_confidence']=hdf5_getters.get_segments_confidence(h5)
# obj['segments_pitches']=hdf5_getters.get_segments_pitches(h5)
# obj['segments_timbre']=hdf5_getters.get_segments_timbre(h5)
# obj['segments_loudness_max']=hdf5_getters.get_segments_loudness_max(h5)
# obj['segments_loudness_max_time']=hdf5_getters.get_segments_loudness_max_time(h5)
# obj['segments_confidence']=hdf5_getters.get_segments_confidence(h5)
# obj['segments_loudness_start']=hdf5_getters.get_segments_loudness_start(h5)
# obj['sections_start']=hdf5_getters.get_sections_start(h5)
# obj['sections_confidence']=hdf5_getters.get_sections_confidence(h5)
# obj['beats_start']=hdf5_getters.get_beats_start(h5)
# obj['beats_confidence']=hdf5_getters.get_beats_confidence(h5)
# obj['bars_start']=hdf5_getters.get_bars_start(h5)
# obj['bars_confidence']=hdf5_getters.get_bars_confidence(h5)
# obj['tatums_start']=hdf5_getters.get_tatums_start(h5)
# obj['artist_mbtags']=hdf5_getters.get_artist_mbtags(h5)
# obj['artist_mbtags_count']=hdf5_getters.get_artist_mbtags_count(h5)
obj['year'] = hdf5_getters.get_year(h5, i)
rows.append(obj)
h5.close()
return rows
def func_to_extract_features(filename):
"""
This function does 3 simple things:
- open the song file
- get artist ID and put it
- close the file
"""
global cntnan
global listfeatures
cf = []
h5 = GETTERS.open_h5_file_read(filename)
nanfound = 0
#Get target feature: song hotness
#FEATURE 0
song_hotness = GETTERS.get_song_hotttnesss(h5)
if math.isnan(song_hotness):
nanfound = 1
cntnan = cntnan + 1
h5.close()
return 0
elif song_hotness > 0.3 and song_hotness < 0.6:
h5.close()
return 0
else:
if song_hotness <= 0.3:
hotness_class = 0
elif song_hotness >= 0.6:
hotness_class = 1
cf.append(hotness_class)
#FEATURE 1
#Get song loudness
song_loudness = GETTERS.get_loudness(h5)
if math.isnan(song_loudness):
nanfound = 1
cntnan = cntnan + 1
else:
#cf.append(song_loudness)
pass
#FEATURE 2
#Get key of the song
song_key = GETTERS.get_key(h5)
if math.isnan(song_key):
nanfound = 1
cntnan = cntnan + 1
else:
# cf.append(song_key)
pass
#FEATURE 3
song_duration = GETTERS.get_duration(h5)
if math.isnan(song_duration):
nanfound = 1
cntnan = cntnan + 1
else:
# cf.append(song_duration)
pass
#Feature 4
#Get song tempo
song_tempo = GETTERS.get_tempo(h5)
if math.isnan(song_tempo):
nanfound = 1
cntnan = cntnan + 1
else:
# cf.append(song_tempo)
pass
#Feature 5: artist familarity
artist_familiarity = GETTERS.get_artist_familiarity(h5)
if math.isnan(artist_familiarity):
nanfound = 1
cntnan = cntnan + 1
else:
# cf.append(artist_familiarity)
pass
#Feature 6: artist_hotness
artist_hotness = GETTERS.get_artist_hotttnesss(h5)
if math.isnan(artist_hotness):
nanfound = 1
cntnan = cntnan + 1
else:
# cf.append(artist_hotness)
pass
#Feature 7 time signature
time_signature = GETTERS.get_time_signature(h5)
# cf.append(time_signature)
#Feature 8
#Loudness COV
loudness_segments = np.array(GETTERS.get_segments_loudness_max(h5))
loudness_cov = abs(variation(loudness_segments))
if math.isnan(loudness_cov):
nanfound = 1
cntnan = cntnan + 1
else:
# cf.append(loudness_cov)
pass
#Feature 9
#Beat COV
beat_segments = np.array(GETTERS.get_beats_start(h5))
beat_cov = abs(variation(beat_segments))
if math.isnan(beat_cov):
nanfound = 1
cntnan = cntnan + 1
else:
# cf.append(beat_cov)
pass
#Feature 10
#Year
song_year = GETTERS.get_year(h5)
if song_year == 0:
nanfound = 1
cntnan = cntnan + 1
else:
# cf.append(song_year)
pass
title = GETTERS.get_title(h5)
if title in energydict:
audio_summary = energydict[title]
energy = audio_summary['energy']
danceability = audio_summary['danceability']
speechiness = audio_summary['speechiness']
liveness = audio_summary['liveness']
else:
stitle = re.sub(r'\([^)]*\)','', title)
if stitle in energydict:
audio_summary = energydict[stitle]
energy = audio_summary['energy']
danceability = audio_summary['danceability']
speechiness = audio_summary['speechiness']
liveness = audio_summary['liveness']
else:
energy = 0.0
danceability = 0.0
speechiness = 0.0
liveness = 0.0
# Feature 11
cf.append(energy)
# Feature 12
# cf.append(danceability)
# Feature 13
# cf.append(speechiness)
# Feature 14
# cf.append(liveness)
if nanfound == 0:
strlist = list_to_csv(cf)
listfeatures.append(strlist)
h5.close()
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(
str(hdf5_getters.get_artist_location(songH5File))).replace(
',', ':')
song.artistLongitude = remove_trap_characters(
str(hdf5_getters.get_artist_longitude(songH5File)))
song.artistFamiliarity = remove_trap_characters(
str(hdf5_getters.get_artist_familiarity(songH5File)))
song.artistHotttnesss = remove_trap_characters(
str(hdf5_getters.get_artist_hotttnesss(songH5File)))
song.artistmbid = remove_trap_characters(
str(hdf5_getters.get_artist_mbid(songH5File)))
song.artistPlaymeid = remove_trap_characters(
str(hdf5_getters.get_artist_playmeid(songH5File)))
song.artist7digitalid = remove_trap_characters(
str(hdf5_getters.get_artist_7digitalid(songH5File)))
temp = hdf5_getters.get_artist_terms(songH5File)
song.artistTerms = remove_trap_characters(str(list(temp)))
song.artistTermsCount = get_list_length(temp)
song.artistTermsFreq = remove_trap_characters(
str(list(hdf5_getters.get_artist_terms_freq(songH5File))))
song.artistTermsWeight = remove_trap_characters(
def main():
outputFile1 = open('SongCSVFinal.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,mbID,Energy,ArtistFamiliarity,Hotness,end_of_fade_in,key,keyConfidence,Loudness,"
+ "mode,mode_confidence,start_of_fade_out")
#################################################
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.
#################################################
#files = glob.glob(os.path.join(root,'*'+ext))
#FOR LOOP
for root, dirs, files in os.walk(basedir):
files = glob.glob(os.path.join(root, '*' + ext))
print(files)
for f in files:
songH5File = hdf5_getters.open_h5_file_read(f)
print('hello 1')
print(songH5File)
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))
song.mbID = str(hdf5_getters.get_artist_mbid(songH5File))
song.energy = str(hdf5_getters.get_energy(songH5File))
#song.beatConfidence = str(hdf5_getters.get_beats_confidence(songH5File))
song.tempo = str(hdf5_getters.get_tempo(songH5File))
song.loudness = str(hdf5_getters.get_loudness(songH5File))
song.key = str(hdf5_getters.get_key(songH5File))
song.artistFamiliarity = str(
hdf5_getters.get_artist_familiarity(songH5File))
song.keyConfidence = str(
hdf5_getters.get_key_confidence(songH5File))
song.hotness = str(hdf5_getters.get_artist_hotttnesss(songH5File))
#song.sampleRate= str(hdf5_getters.get_analysis_sample_rate(songH5File))
song.end_of_fade_in = str(
hdf5_getters.get_end_of_fade_in(songH5File))
song.mode = str(hdf5_getters.get_mode(songH5File))
song.mode_confidence = str(
hdf5_getters.get_mode_confidence(songH5File))
song.start_of_fade_out = str(
hdf5_getters.get_start_of_fade_out(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
elif attribute == 'mbID'.lower():
csvRowString += song.mbID
elif attribute == 'Energy'.lower():
csvRowString += song.energy
elif attribute == 'ArtistFamiliarity'.lower():
csvRowString += song.artistFamiliarity
elif attribute == 'Hotness'.lower():
csvRowString += song.hotness
#elif attribute == 'SampleRate'.lower():
#csvRowString += song.sampleRate
elif attribute == 'end_of_fade_in'.lower():
csvRowString += song.end_of_fade_in
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 == 'mode_confidence'.lower():
csvRowString += song.mode_confidence
elif attribute == 'start_of_fade_out'.lower():
csvRowString += song.start_of_fade_out
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 main():
dataset_dir = sys.argv[1]
feat =[]
feat1=[]
feat2=[]
feat3=[]
feat4=[]
print "Forming Dataset..."
listing1 = os.listdir(dataset_dir)
for a in listing1:
listing2 = os.listdir(dataset_dir+a+'/')
for b in listing2:
listing3 = os.listdir(dataset_dir+a+'/'+b+'/')
for c in listing3:
listing4 = os.listdir(dataset_dir+a+'/'+b+'/'+c+'/')
for d in listing4:
h5 = hdf5_getters.open_h5_file_read(dataset_dir+a+'/'+b+'/'+c+'/'+d)
feat =[]
feat1=[]
feat2=[]
feat3=[]
feat4=[]
temp = hdf5_getters.get_artist_hotttnesss(h5)
if (math.isnan(temp) or temp==0.0):
h5.close()
continue
temp = hdf5_getters.get_artist_familiarity(h5)
if (math.isnan(temp) or temp==0.0):
h5.close()
continue
temp = hdf5_getters.get_end_of_fade_in(h5)
if (math.isnan(temp)):
h5.close()
continue
temp = hdf5_getters.get_key_confidence(h5)
if (math.isnan(temp)):
h5.close()
continue
temp = hdf5_getters.get_loudness(h5)
if (math.isnan(temp)):
h5.close()
continue
temp = hdf5_getters.get_mode_confidence(h5)
if (math.isnan(temp)):
h5.close()
continue
temp = hdf5_getters.get_sections_confidence(h5)
if temp.size == 0:
h5.close()
continue
temp = hdf5_getters.get_segments_confidence(h5)
if temp.size == 0:
h5.close()
continue
temp = hdf5_getters.get_segments_loudness_max(h5)
if temp.size == 0:
h5.close()
continue
temp = hdf5_getters.get_segments_loudness_max_time(h5)
if temp.size == 0:
h5.close()
continue
temp = hdf5_getters.get_segments_pitches(h5)
if temp.size == 0:
h5.close()
continue
temp = hdf5_getters.get_segments_timbre(h5)
if temp.size == 0:
h5.close()
continue
temp = hdf5_getters.get_start_of_fade_out(h5)
if (math.isnan(temp)):
h5.close()
continue
temp = hdf5_getters.get_tempo(h5)
if (math.isnan(temp)):
h5.close()
continue
temp = hdf5_getters.get_time_signature_confidence(h5)
if (math.isnan(temp)):
h5.close()
continue
temp = hdf5_getters.get_year(h5)
if temp == 0:
h5.close()
continue
temp = hdf5_getters.get_artist_terms(h5)
if temp.size == 0:
h5.close()
continue
temp_ = hdf5_getters.get_artist_terms_weight(h5)
if temp_.size == 0:
continue
temp = hdf5_getters.get_bars_confidence(h5)
sz = temp.size
if sz<50:
h5.close()
continue
temp = hdf5_getters.get_beats_confidence(h5)
sz = temp.size
if sz <50:
h5.close()
continue
mm = np.mean(temp)
vv = np.var(temp)
if mm==0.0 and vv==0.0:
h5.close()
continue
temp = hdf5_getters.get_segments_confidence(h5)
sz = temp.size
if sz <50:
h5.close()
continue
temp = hdf5_getters.get_tatums_confidence(h5)
sz = temp.size
if sz <50:
h5.close()
continue
temp = hdf5_getters.get_song_hotttnesss(h5)
if (math.isnan(temp) or temp==0.0):
h5.close()
continue
temp = hdf5_getters.get_bars_confidence(h5)
sz = temp.size
sz1 = sz/50
i=1
j=0
while i<=50:
if i == 50:
sz2 = sz
else:
sz2 = i*sz1
num=0.0
acc = 0
while j<sz2:
acc += temp[j]
j+=1
num+=1.0
mm = acc/num
feat1.append(mm)
i+=1
temp = hdf5_getters.get_beats_confidence(h5)
sz = temp.size
sz1 = sz/50
i=1
j=0
while i<=50:
if i == 50:
sz2 = sz
else:
sz2 = i*sz1
num=0.0
acc = 0
while j<sz2:
acc += temp[j]
j+=1
num+=1.0
mm = acc/num
feat2.append(mm)
i+=1
temp = hdf5_getters.get_segments_confidence(h5)
sz = temp.size
sz1 = sz/50
i=1
j=0
while i<=50:
if i == 50:
sz2 = sz
else:
sz2 = i*sz1
num=0.0
acc = 0
while j<sz2:
acc += temp[j]
j+=1
num+=1.0
mm = acc/num
feat3.append(mm)
i+=1
temp = hdf5_getters.get_tatums_confidence(h5)
sz = temp.size
sz1 = sz/50
i=1
j=0
while i<=50:
if i == 50:
sz2 = sz
else:
sz2 = i*sz1
num=0.0
acc = 0
while j<sz2:
acc += temp[j]
j+=1
num+=1.0
mm = acc/num
feat4.append(mm)
i+=1
i=0
avg = 0.0
while i<50:
avg = (feat1[i] + feat2[i] + feat3[i] + feat4[i])/4.0
feat.append(avg)
i++
temp = hdf5_getters.get_song_hotttnesss(h5)
hott = 0
if temp >=0.75:
hott = 1
elif temp >=0.40 and temp <0.75:
hott = 2
else:
hott = 3
feat.append(hott)
h5.close()
count = 1
f=open('MSD_DATASET_LSTM.txt', 'a')
outstring=''
cnt = 0
feat_size = len(feat)
for i in feat:
cnt+=1
outstring+=str(i)
if (cnt!=feat_size):
outstring+=','
outstring+='\n'
f.write(outstring)
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 == 'Familiarity'.lower(): ####Added by us!
csvRowString += song.familiarity
elif attribute == 'artist_mbid'.lower():
csvRowString += song.artist_mbid
elif attribute == 'artist_playmeid'.lower():
csvRowString += song.artist_playmeid
elif attribute == 'artist_7digid'.lower():
csvRowString += song.artist_7digid
elif attribute == 'hottness'.lower():
csvRowString += song.hottness
elif attribute == 'song_hottness'.lower():
csvRowString += song.song_hottness
elif attribute == 'digitalid7'.lower():
csvRowString += song.digitalid7
elif attribute == 'similar_artists'.lower():
csvRowString += song.similar_artists
elif attribute == 'artist_terms'.lower():
csvRowString += song.artist_terms
elif attribute == 'art_terms_freq'.lower():
csvRowString += song.art_terms_freq
elif attribute == 'art_terms_weight'.lower():
csvRowString += song.art_terms_weight
elif attribute == 'a_sample_rate'.lower():
csvRowString += song.a_sample_rate
elif attribute == 'audio_md5'.lower():
csvRowString += song.audio_md5
elif attribute == 'end_of_fade_in'.lower():
csvRowString += song.end_of_fade_in
elif attribute == 'energy'.lower():
csvRowString += song.energy
elif attribute == 'loudness'.lower():
csvRowString += song.loudness
elif attribute == 'mode'.lower():
csvRowString += song.mode
elif attribute == 'mode_conf'.lower():
csvRowString += song.mode_conf
elif attribute == 'start_of_fade_out'.lower():
csvRowString += song.start_of_fade_out
elif attribute == 'trackid'.lower():
csvRowString += song.trackid
elif attribute == 'segm_start'.lower():
csvRowString += song.segm_start
elif attribute == 'segm_conf'.lower():
csvRowString += song.segm_conf
elif attribute == 'segm_pitch'.lower():
csvRowString += song.segm_pitch
elif attribute == 'segm_timbre'.lower():
csvRowString += song.segm_timbre
elif attribute == 'segm_max_loud'.lower():
csvRowString += song.segm_max_loud
elif attribute == 'segm_max_loud_time'.lower():
csvRowString += song.segm_max_loud_time
elif attribute == 'segm_loud_start'.lower():
csvRowString += song.segm_loud_start
elif attribute == 'sect_start'.lower():
csvRowString += song.sect_start
elif attribute == 'sect_conf'.lower():
csvRowString += song.sect_conf
elif attribute == 'beats_start'.lower():
csvRowString += song.beats_start
elif attribute == 'beats_conf'.lower():
csvRowString += song.beats_conf
elif attribute == 'bars_start'.lower():
csvRowString += song.bars_start
elif attribute == 'bars_conf'.lower():
csvRowString += song.bars_conf
elif attribute == 'tatums_start'.lower():
csvRowString += song.tatums_start
elif attribute == 'tatums_conf'.lower():
csvRowString += song.tatums_conf
elif attribute == 'artist_mbtags'.lower():
csvRowString += song.artist_mbtags
elif attribute == 'artist_mbtags_count'.lower():
csvRowString += song.artist_mbtags_count
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,Familiarity,Artist_Mbid,Artist_PlaymeId,Artist_7didId,Hottness,Song_Hottness,7digitalid,A_Sample_Rate,Audio_Md5,End_Of_Fade_In,Energy,Loudness,Mode,Mode_Conf,Start_Of_Fade_Out,TrackId"
#################################################
csvAttributeList = re.split(',', csvRowString)
for i, v in enumerate(csvAttributeList):
csvAttributeList[i] = csvAttributeList[i].lower()
csvRowString += "\n"
outputFile1.write(csvRowString)
csvRowString = ""
#################################################
#Set the basedir here, the root directory from which the search
#for files stored in a (hierarchical data structure) will originate
basedir = "/home/bigdata/smalltest/" # "." 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))
#########Added by us!
song.familiarity = str(
hdf5_getters.get_artist_familiarity(songH5File))
song.artist_mbid = str(hdf5_getters.get_artist_mbid(songH5File))
song.artist_playmeid = str(
hdf5_getters.get_artist_playmeid(songH5File))
song.artist_7digid = str(
hdf5_getters.get_artist_7digitalid(songH5File))
song.hottness = str(hdf5_getters.get_artist_hotttnesss(songH5File))
song.song_hottness = str(
hdf5_getters.get_song_hotttnesss(songH5File))
song.digitalid7 = str(
hdf5_getters.get_track_7digitalid(songH5File))
#song.similar_artists = str(hdf5_getters.get_similar_artists(songH5File))
#song.artist_terms = str(hdf5_getters.get_artist_terms(songH5File))
#song.art_terms_freq = str(hdf5_getters.get_artist_terms_freq(songH5File))
#song.art_terms_weight = str(hdf5_getters.get_artist_terms_weight(songH5File))
song.a_sample_rate = str(
hdf5_getters.get_analysis_sample_rate(songH5File))
song.audio_md5 = str(hdf5_getters.get_audio_md5(songH5File))
song.end_of_fade_in = str(
hdf5_getters.get_end_of_fade_in(songH5File))
song.energy = str(hdf5_getters.get_energy(songH5File))
song.loudness = str(hdf5_getters.get_loudness(songH5File))
song.mode = str(hdf5_getters.get_mode(songH5File))
song.mode_conf = str(hdf5_getters.get_mode_confidence(songH5File))
song.start_of_fade_out = str(
hdf5_getters.get_start_of_fade_out(songH5File))
song.trackid = str(hdf5_getters.get_track_id(songH5File))
#song.segm_start = str(hdf5_getters.get_segments_start(songH5File))
#song.segm_conf = str(hdf5_getters.get_segments_confidence(songH5File))
#song.segm_pitch = str(hdf5_getters.get_segments_pitches(songH5File))
#song.segm_timbre = str(hdf5_getters.get_segments_timbre(songH5File))
#song.segm_max_loud = str(hdf5_getters.get_segments_loudness_max(songH5File))
#song.segm_max_loud_time = str(hdf5_getters.get_segments_loudness_max_time(songH5File))
#song.segm_loud_start = str(hdf5_getters.get_segments_loudness_start(songH5File))
#song.sect_start = str(hdf5_getters.get_sections_start(songH5File))
#song.sect_conf = str(hdf5_getters.get_sections_confidence(songH5File))
#song.beats_start = str(hdf5_getters.get_beats_start(songH5File))
#song.beats_conf = str(hdf5_getters.get_beats_confidence(songH5File))
#song.bars_start = str(hdf5_getters.get_bars_start(songH5File))
#song.bars_conf = str(hdf5_getters.get_bars_confidence(songH5File))
#song.tatums_start = str(hdf5_getters.get_tatums_start(songH5File))
#song.tatums_conf = str(hdf5_getters.get_tatums_confidence(songH5File))
#song.artist_mbtags = str(hdf5_getters.get_artist_mbtags(songH5File))
#song.artist_mbtags_count = str(hdf5_getters.get_artist_mbtags_count(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("b\"", "")
albumName = albumName.replace("\"", "")
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(',', '')
location = location.replace("b\"", "")
location = location.replace("\"", "")
csvRowString += "\"" + location + "\""
elif attribute == 'ArtistLongitude'.lower():
longitude = song.artistLongitude
if longitude == 'nan':
longitude = ''
csvRowString += longitude
elif attribute == 'ArtistName'.lower():
artistName = song.artistName
artistName = artistName.replace("b\"", "")
artistName = artistName.replace("\"", "")
csvRowString += "\"" + 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():
t = song.title
t = t.replace("b\"", "")
t = t.replace("\"", "")
csvRowString += "\"" + t + "\""
elif attribute == 'Year'.lower():
csvRowString += song.year
elif attribute == 'Familiarity'.lower(): ####Added by us!
csvRowString += song.familiarity
elif attribute == 'artist_mbid'.lower():
csvRowString += "\"" + song.artist_mbid + "\""
elif attribute == 'artist_playmeid'.lower():
csvRowString += song.artist_playmeid
elif attribute == 'artist_7digid'.lower():
csvRowString += song.artist_7digid
elif attribute == 'hottness'.lower():
csvRowString += song.hottness
elif attribute == 'song_hottness'.lower():
csvRowString += song.song_hottness
elif attribute == 'digitalid7'.lower():
csvRowString += song.digitalid7
elif attribute == 'similar_artists'.lower():
csvRowString += song.similar_artists
elif attribute == 'artist_terms'.lower():
csvRowString += song.artist_terms
elif attribute == 'art_terms_freq'.lower():
csvRowString += song.art_terms_freq
elif attribute == 'art_terms_weight'.lower():
csvRowString += song.art_terms_weight
elif attribute == 'a_sample_rate'.lower():
csvRowString += song.a_sample_rate
elif attribute == 'audio_md5'.lower():
csvRowString += "\"" + song.audio_md5 + "\""
elif attribute == 'end_of_fade_in'.lower():
csvRowString += song.end_of_fade_in
elif attribute == 'energy'.lower():
csvRowString += song.energy
elif attribute == 'loudness'.lower():
csvRowString += song.loudness
elif attribute == 'mode'.lower():
csvRowString += song.mode
elif attribute == 'mode_conf'.lower():
csvRowString += song.mode_conf
elif attribute == 'start_of_fade_out'.lower():
csvRowString += song.start_of_fade_out
elif attribute == 'trackid'.lower():
csvRowString += "\"" + song.trackid + "\""
elif attribute == 'segm_start'.lower():
csvRowString += song.segm_start
elif attribute == 'segm_conf'.lower():
csvRowString += song.segm_conf
elif attribute == 'segm_pitch'.lower():
csvRowString += song.segm_pitch
elif attribute == 'segm_timbre'.lower():
csvRowString += song.segm_timbre
elif attribute == 'segm_max_loud'.lower():
csvRowString += song.segm_max_loud
elif attribute == 'segm_max_loud_time'.lower():
csvRowString += song.segm_max_loud_time
elif attribute == 'segm_loud_start'.lower():
csvRowString += song.segm_loud_start
elif attribute == 'sect_start'.lower():
csvRowString += song.sect_start
elif attribute == 'sect_conf'.lower():
csvRowString += song.sect_conf
elif attribute == 'beats_start'.lower():
csvRowString += song.beats_start
elif attribute == 'beats_conf'.lower():
csvRowString += song.beats_conf
elif attribute == 'bars_start'.lower():
csvRowString += song.bars_start
elif attribute == 'bars_conf'.lower():
csvRowString += song.bars_conf
elif attribute == 'tatums_start'.lower():
csvRowString += song.tatums_start
elif attribute == 'tatums_conf'.lower():
csvRowString += song.tatums_conf
elif attribute == 'artist_mbtags'.lower():
csvRowString += song.artist_mbtags
elif attribute == 'artist_mbtags_count'.lower():
csvRowString += song.artist_mbtags_count
else:
csvRowString += "\"ERR\""
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_extract_features(filename):
"""
This function does 3 simple things:
- open the song file
- get artist ID and put it
- close the file
"""
global cntnan
global listfeatures
cf = []
h5 = GETTERS.open_h5_file_read(filename)
nanfound = 0
# Get target feature: song hotness
# FEATURE 0
song_hotness = GETTERS.get_song_hotttnesss(h5)
if math.isnan(song_hotness):
nanfound = 1
cntnan = cntnan + 1
h5.close()
return 0
elif song_hotness > 0.3 and song_hotness < 0.6:
h5.close()
return 0
else:
cf.append(song_hotness)
# FEATURE 1
# Get song loudness
song_loudness = GETTERS.get_loudness(h5)
if math.isnan(song_loudness):
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(song_loudness)
# FEATURE 2
# Get key of the song
song_key = GETTERS.get_key(h5)
if math.isnan(song_key):
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(song_key)
# FEATURE 3
# Get duration of the song
song_duration = GETTERS.get_duration(h5)
if math.isnan(song_duration):
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(song_duration)
# Feature 4
# Get song tempo
song_tempo = GETTERS.get_tempo(h5)
if math.isnan(song_tempo):
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(song_tempo)
# Feature 5: artist familarity
artist_familiarity = GETTERS.get_artist_familiarity(h5)
if math.isnan(artist_familiarity):
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(artist_familiarity)
# Feature 6: artist_hotness
artist_hotness = GETTERS.get_artist_hotttnesss(h5)
if math.isnan(artist_hotness):
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(artist_hotness)
# Feature 7 time signature
time_signature = GETTERS.get_time_signature(h5)
cf.append(time_signature)
# Feature 8
# Loudness COV
loudness_segments = np.array(GETTERS.get_segments_loudness_max(h5))
loudness_cov = abs(variation(loudness_segments))
if math.isnan(loudness_cov):
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(loudness_cov)
# Feature 9
# Beat COV
beat_segments = np.array(GETTERS.get_beats_start(h5))
beat_cov = abs(variation(beat_segments))
if math.isnan(beat_cov):
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(beat_cov)
# Feature 10
# Year
song_year = GETTERS.get_year(h5)
if song_year == 0:
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(song_year)
if nanfound == 0:
strlist = list_to_csv(cf)
listfeatures.append(strlist)
strtitle = GETTERS.get_title(h5)
listtitle.append(strtitle)
h5.close()
def main():
basedir = "./../songMetaInfo.txt"
ext = ".h5"
if len(sys.argv) > 1:
basedir = sys.argv[1]
outputfile = 'SongFileMetaData.csv'
if len(sys.argv) > 2:
outputfile = sys.argv[2]
csvWriter = open(outputfile, 'w')
csvWriter.write(
"title,songId,artistId,artistfamilarity,artistHotness,songHotness," +
"songEnfOfFadeIn,startFadeout,energy,loudness,albumID,albumName,artistName,danceability,duration,keySignatureConfidence,tempo,timeSignature,timeSignatureConfidence,year\n"
)
with open(basedir) as file:
for line in file.readlines():
f = line.strip()
#newf = f + "text"
print f
#print f
try:
songH5File = hdf5_getters.open_h5_file_read(f)
csvStr = ""
#0
title = str(hdf5_getters.get_title(songH5File))
csvStr += title + ","
#1
songId = str(hdf5_getters.get_song_id(songH5File))
csvStr += songId + ","
#2
artistId = str(hdf5_getters.get_artist_id(songH5File))
csvStr += artistId + ","
#3
artistfamilarity = str(
hdf5_getters.get_artist_familiarity(songH5File))
csvStr += artistfamilarity + ","
#4
artistHotness = str(
hdf5_getters.get_artist_hotttnesss(songH5File))
csvStr += artistHotness + ","
#5
songHotness = str(hdf5_getters.get_song_hotttnesss(songH5File))
csvStr += songHotness + ","
#6
songEnfOfFadeIn = str(
hdf5_getters.get_end_of_fade_in(songH5File))
csvStr += songEnfOfFadeIn + ","
#7
startFadeOut = str(
hdf5_getters.get_start_of_fade_out(songH5File))
csvStr += startFadeOut + ","
#8
energy = str(hdf5_getters.get_energy(songH5File))
csvStr += energy + ","
#9
loudness = str(hdf5_getters.get_loudness(songH5File))
csvStr += loudness + ","
#10
albumID = str(hdf5_getters.get_release_7digitalid(songH5File))
csvStr += albumID + ","
#11
albumName = str(hdf5_getters.get_release(songH5File))
csvStr += albumName + ","
#12
artistName = str(hdf5_getters.get_artist_name(songH5File))
csvStr += artistName + ","
#13
danceability = str(hdf5_getters.get_danceability(songH5File))
csvStr += danceability + ","
#14
duration = str(hdf5_getters.get_duration(songH5File))
csvStr += duration + ","
#15
keySignatureConfidence = str(
hdf5_getters.get_key_confidence(songH5File))
csvStr += keySignatureConfidence + ","
#16
tempo = str(hdf5_getters.get_tempo(songH5File))
csvStr += tempo + ","
## 17
timeSignature = str(
hdf5_getters.get_time_signature(songH5File))
csvStr += timeSignature + ","
#18
timeSignatureConfidence = str(
hdf5_getters.get_time_signature_confidence(songH5File))
csvStr += timeSignatureConfidence + ","
#19
year = str(hdf5_getters.get_year(songH5File))
csvStr += year + ","
#print song count
csvStr += "\n"
csvWriter.write(csvStr)
#print csvStr
songH5File.close()
except:
print "Error in processing file"
csvWriter.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.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;
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 get_all_files(basedir,ext='.h5') :
"""
From a root directory, go through all subdirectories
and find all files with the given extension.
Return all absolute paths in a list.
"""
c=0
title=[]#get_title(h5)
name=[]#get_artist_name`
familiarity=[]#get_artist_familiarity()
artist_hotness=[]#get_artist_hotttnesss
song_hotness=[]# get_song_hotttnesss
danceability=[]#get_danceability
energy=[]#get_energy
loudness=[]#get_loudness
tempo=[]#get_tempo
mode_confidence=[]#get_mode_confidence()
time_sig_confidence=[]#get_time_signature_confidence()
no_segments=[]#len(get_segments_start())
avg_segment_confidence=[]#np.mean(hdf5_getters.get_segments_confidence(h5))
avg_segment_pitches=[]#np.mean(hdf5_getters.get_segments_pitches(h51))
no_sections=[]#len(hdf5_getters.get_sections_start())
avg_sections_confidence=[]#np.mean(hdf5_getters.get_sections_confidence(h51))
no_beats_start=[]#len(hdf5_getters.get_beats_start(h51))
avg_beats_confidence=[]#np.mean(hdf5_getters.get_beats_confidence(h51))
no_bars=[]#len(hdf5_getters.get_bars_start(h5))
avg_bar_confidence=[]#np.mean(hdf5_getters.get_bars_confidence((h51))
no_tatums_start=[]#len(hdf5_getters.get_tatums_start(h5))
avg_tatums_start=[]#np.mean(get_tatums_confidence())
billboard_presence=[]#returned value from web scraper
key=[]
duration=[]
mode=[]
target=pd.read_csv('Billboard.csv')
j=0
if(not(os.path.isfile('./data.csv'))):
for root, dirs, files in os.walk(basedir):
files = glob.glob(os.path.join(root,'*'+ext))
for f in files :
h5 = hdf5_getters.open_h5_file_read(f)
songnme=hdf5_getters.get_title(h5)
artst=hdf5_getters.get_artist_name(h5)
for i in range(len(target)):
if(target.Title[i]==songnme and target.Name[i]==artst):
billboard_presence.append(target.Presence[i])
title.append(songnme)
name.append(artst)
familiarity.append(hdf5_getters.get_artist_familiarity(h5))
artist_hotness.append(hdf5_getters.get_artist_hotttnesss(h5))
song_hotness.append(hdf5_getters. get_song_hotttnesss(h5))
danceability.append(hdf5_getters.get_danceability(h5))
key.append(hdf5_getters.get_key(h5))
duration.append(hdf5_getters.get_duration(h5))
mode.append(hdf5_getters.get_mode(h5))
energy.append(hdf5_getters.get_energy(h5))
loudness.append(hdf5_getters.get_loudness(h5))
tempo.append(hdf5_getters.get_tempo(h5))
mode_confidence.append(hdf5_getters.get_mode_confidence(h5))
time_sig_confidence.append(hdf5_getters.get_time_signature_confidence(h5))
no_segments.append(len(hdf5_getters.get_segments_start(h5)))
avg_segment_confidence.append(np.mean(hdf5_getters.get_segments_confidence(h5)))
avg_segment_pitches.append(np.mean(hdf5_getters.get_segments_pitches(h5)))
no_sections.append(len(hdf5_getters.get_sections_start(h5)))
avg_sections_confidence.append(np.mean(hdf5_getters.get_sections_confidence(h5)))
no_beats_start.append(len(hdf5_getters.get_beats_start(h5)))
avg_beats_confidence.append(np.mean(hdf5_getters.get_beats_confidence(h5)))
no_bars.append(len(hdf5_getters.get_bars_start(h5)))
avg_bar_confidence.append(np.mean(hdf5_getters.get_bars_confidence(h5)))
no_tatums_start.append(len(hdf5_getters.get_tatums_start(h5)))
avg_tatums_start.append(np.mean(hdf5_getters.get_tatums_confidence(h5)))
j+=1
print j #prints the index number of each song, to keep track of the song being saved to the database, and to identify errors.
break;
h5.close()
print "Created Arrays"
df=pd.DataFrame(title,columns=['Title'])
df['Artist_Name']=name
df['Familiarity']=familiarity
df['Hotness']=artist_hotness
df['Song_hotness']=song_hotness
df['Danceability']=danceability
df['energy']=energy
df['loudness']=loudness
df['tempo']=tempo
df['mode_confidence']=mode_confidence
df['time_sig_confidence']=time_sig_confidence
df['no_segments']=no_segments
df['avg_segment_confidence']=avg_segment_confidence
df['avg_segment_pitches']=avg_segment_pitches
df['no_sections']=no_sections
df['avg_sections_confidence']=avg_sections_confidence
df['no_beats_start']=no_beats_start
df['avg_beats_confidence']=avg_beats_confidence
df['no_bars']=no_bars
df['avg_bar_confidence']=avg_bar_confidence
df['no_tatums_start']=no_tatums_start
df['avg_tatums_start']=avg_tatums_start
df['key']=key
df['Mode']=mode
df['duration']=duration
df['Presence']=billboard_presence
print df.head()
print billboard_presence
df.to_csv("data.csv")
else:
df=pd.read_csv('data.csv',index_col=0)
print "Number of features in the created dataset:",
print len(df.keys())
print
return df
def hd5_single_random_file_parser():
# Open an h5 file in read mode
h5 = hdf5_getters.open_h5_file_read(
'/home/skalogerakis/Documents/MillionSong/MillionSongSubset/A/M/G/TRAMGDX12903CEF79F.h5'
)
function_tracker = filter(
lambda x: x.startswith('get'),
hdf5_getters.__dict__.keys()) # Detects all the getter functions
for f in function_tracker: # Print everything in function tracker
print(f)
# First effort to check what each field contains.
print() # 55 available fields (exluding number of songs fields)
print("Num of songs -- ",
hdf5_getters.get_num_songs(h5)) # One song per file
print("Title -- ",
hdf5_getters.get_title(h5)) # Print the title of a specific h5 file
print("Artist familiarity -- ", hdf5_getters.get_artist_familiarity(h5))
print("Artist hotness -- ", hdf5_getters.get_artist_hotttnesss(h5))
print("Artist ID -- ", hdf5_getters.get_artist_id(h5))
print("Artist mbID -- ", hdf5_getters.get_artist_mbid(h5))
print("Artist playmeid -- ", hdf5_getters.get_artist_playmeid(h5))
print("Artist 7DigitalID -- ", hdf5_getters.get_artist_7digitalid(h5))
print("Artist latitude -- ", hdf5_getters.get_artist_latitude(h5))
print("Artist longitude -- ", hdf5_getters.get_artist_longitude(h5))
print("Artist location -- ", hdf5_getters.get_artist_location(h5))
print("Artist Name -- ", hdf5_getters.get_artist_name(h5))
print("Release -- ", hdf5_getters.get_release(h5))
print("Release 7DigitalID -- ", hdf5_getters.get_release_7digitalid(h5))
print("Song ID -- ", hdf5_getters.get_song_id(h5))
print("Song Hotness -- ", hdf5_getters.get_song_hotttnesss(h5))
print("Track 7Digital -- ", hdf5_getters.get_track_7digitalid(h5))
print("Similar artists -- ", hdf5_getters.get_similar_artists(h5))
print("Artist terms -- ", hdf5_getters.get_artist_terms(h5))
print("Artist terms freq -- ", hdf5_getters.get_artist_terms_freq(h5))
print("Artist terms weight -- ", hdf5_getters.get_artist_terms_weight(h5))
print("Analysis sample rate -- ",
hdf5_getters.get_analysis_sample_rate(h5))
print("Audio md5 -- ", hdf5_getters.get_audio_md5(h5))
print("Danceability -- ", hdf5_getters.get_danceability(h5))
print("Duration -- ", hdf5_getters.get_duration(h5))
print("End of Fade -- ", hdf5_getters.get_end_of_fade_in(h5))
print("Energy -- ", hdf5_getters.get_energy(h5))
print("Key -- ", hdf5_getters.get_key(h5))
print("Key Confidence -- ", hdf5_getters.get_key_confidence(h5))
print("Loudness -- ", hdf5_getters.get_loudness(h5))
print("Mode -- ", hdf5_getters.get_mode(h5))
print("Mode Confidence -- ", hdf5_getters.get_mode_confidence(h5))
print("Start of fade out -- ", hdf5_getters.get_start_of_fade_out(h5))
print("Tempo -- ", hdf5_getters.get_tempo(h5))
print("Time signature -- ", hdf5_getters.get_time_signature(h5))
print("Time signature confidence -- ",
hdf5_getters.get_time_signature_confidence(h5))
print("Track ID -- ", hdf5_getters.get_track_id(h5))
print("Segments Start -- ", hdf5_getters.get_segments_start(h5))
print("Segments Confidence -- ", hdf5_getters.get_segments_confidence(h5))
print("Segments Pitches -- ", hdf5_getters.get_segments_pitches(h5))
print("Segments Timbre -- ", hdf5_getters.get_segments_timbre(h5))
print("Segments Loudness max -- ",
hdf5_getters.get_segments_loudness_max(h5))
print("Segments Loudness max time-- ",
hdf5_getters.get_segments_loudness_max_time(h5))
print("Segments Loudness start -- ",
hdf5_getters.get_segments_loudness_start(h5))
print("Sections start -- ", hdf5_getters.get_sections_start(h5))
print("Sections Confidence -- ", hdf5_getters.get_sections_confidence(h5))
print("Beats start -- ", hdf5_getters.get_beats_start(h5))
print("Beats confidence -- ", hdf5_getters.get_beats_confidence(h5))
print("Bars start -- ", hdf5_getters.get_bars_start(h5))
print("Bars confidence -- ", hdf5_getters.get_bars_confidence(h5))
print("Tatums start -- ", hdf5_getters.get_tatums_start(h5))
print("Tatums confidence -- ", hdf5_getters.get_tatums_confidence(h5))
print("Artist mbtags -- ", hdf5_getters.get_artist_mbtags(h5))
print("Artist mbtags count -- ", hdf5_getters.get_artist_mbtags_count(h5))
print("Year -- ", hdf5_getters.get_year(h5))
fields = ['Title', 'Artist ID']
with open('Tester2.csv', 'w', newline='') as csvfile:
csv_writer = csv.writer(csvfile, delimiter=';')
# writing the fields
csv_writer.writerow(fields)
# writing the data rows
csv_writer.writerow(
[hdf5_getters.get_title(h5),
hdf5_getters.get_artist_id(h5)])
h5.close() # close h5 when completed in the end
song_release_year = []
song_hotness = []
track_id = []
song_tempo = []
song_bars = []
song_beats = []
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)
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()
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)
# Get release
release_song = hdf5_getters.get_release(h5)
release = release_song.translate(None, string.punctuation)
# Get artist HOTTTNESSSSSS
hotttness = hdf5_getters.get_artist_hotttnesss(h5)
# Get artist familiarity
familiarity = hdf5_getters.get_artist_familiarity(h5)
# Get danceability
danceability = hdf5_getters.get_danceability(h5)
# Get duration
duration = hdf5_getters.get_duration(h5)
# Get energy
#*****useless... column is filled with 0's?
energy = hdf5_getters.get_energy(h5)
# Get loudness
loudness = hdf5_getters.get_loudness(h5)
# Get year
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 main():
dataset_dir = sys.argv[1]
global feat
Create_BoW(dataset_dir)
Size_BoW = Index_BoW(Bag_Words)
count = Frequency(Size_BoW, dataset_dir)
Size_BoW = Prune(count)
Lablify()
print "Forming Dataset..."
listing1 = os.listdir(dataset_dir)
for a in listing1:
listing2 = os.listdir(dataset_dir+a+'/')
for b in listing2:
listing3 = os.listdir(dataset_dir+a+'/'+b+'/')
for c in listing3:
listing4 = os.listdir(dataset_dir+a+'/'+b+'/'+c+'/')
for d in listing4:
h5 = hdf5_getters.open_h5_file_read(dataset_dir+a+'/'+b+'/'+c+'/'+d)
feat = []
temp = hdf5_getters.get_artist_hotttnesss(h5)
if (math.isnan(temp) or temp==0.0):
h5.close()
continue
feat.append(temp)
temp = hdf5_getters.get_artist_familiarity(h5)
if (math.isnan(temp) or temp==0.0):
h5.close()
continue
feat.append(temp)
temp = hdf5_getters.get_bars_confidence(h5)
if temp.size == 0:
h5.close()
continue
MeanVar(temp)
temp = hdf5_getters.get_beats_confidence(h5)
if temp.size == 0:
h5.close()
continue
mm = np.mean(temp)
vv = np.var(temp)
if mm==0.0 and vv==0.0:
h5.close()
continue
feat.append(mm)
feat.append(vv)
feat.append(hdf5_getters.get_duration(h5))
temp = hdf5_getters.get_end_of_fade_in(h5)
if (math.isnan(temp)):
h5.close()
continue
feat.append(temp)
feat.append(hdf5_getters.get_key(h5))
temp = hdf5_getters.get_key_confidence(h5)
if (math.isnan(temp)):
h5.close()
continue
feat.append(temp)
temp = hdf5_getters.get_loudness(h5)
if (math.isnan(temp)):
h5.close()
continue
feat.append(temp)
feat.append(hdf5_getters.get_mode(h5))
temp = hdf5_getters.get_mode_confidence(h5)
if (math.isnan(temp)):
h5.close()
continue
feat.append(temp)
temp = hdf5_getters.get_sections_confidence(h5)
if temp.size == 0:
h5.close()
continue
MeanVar(temp)
temp = hdf5_getters.get_segments_confidence(h5)
if temp.size == 0:
h5.close()
continue
MeanVar(temp)
temp = hdf5_getters.get_segments_loudness_max(h5)
if temp.size == 0:
h5.close()
continue
MeanVar(temp)
temp = hdf5_getters.get_segments_loudness_max_time(h5)
if temp.size == 0:
h5.close()
continue
MeanVar(temp)
temp = hdf5_getters.get_segments_pitches(h5)
if temp.size == 0:
h5.close()
continue
MeanVar(temp)
temp = hdf5_getters.get_segments_timbre(h5)
if temp.size == 0:
h5.close()
continue
MeanVar(temp)
temp = hdf5_getters.get_start_of_fade_out(h5)
if (math.isnan(temp)):
h5.close()
continue
feat.append(temp)
temp = hdf5_getters.get_tatums_confidence(h5)
if temp.size == 0:
h5.close()
continue
MeanVar(temp)
temp = hdf5_getters.get_tempo(h5)
if (math.isnan(temp)):
h5.close()
continue
feat.append(temp)
feat.append(hdf5_getters.get_time_signature(h5))
temp = hdf5_getters.get_time_signature_confidence(h5)
if (math.isnan(temp)):
h5.close()
continue
feat.append(temp)
temp = hdf5_getters.get_year(h5)
if temp == 0:
h5.close()
continue
feat.append(temp)
temp = hdf5_getters.get_artist_terms(h5)
if temp.size == 0:
h5.close()
continue
temp_ = hdf5_getters.get_artist_terms_weight(h5)
if temp_.size == 0:
continue
for j in Final_BoW:
if j in temp:
x = np.where(temp==j)
x = x[0][0]
feat.append(temp_[x])
else:
x = 0.0
feat.append(x)
temp = hdf5_getters.get_song_hotttnesss(h5)
if (math.isnan(temp) or temp==0.0):
h5.close()
continue
hott = 0
if temp >=0.75:
hott = 1
elif temp >=0.40 and temp <0.75:
hott = 2
else:
hott = 3
feat.append(hott)
h5.close()
count = 1
f=open('MSD_DATASET.txt', 'a')
outstring=''
cnt = 0
feat_size = len(feat)
for i in feat:
cnt+=1
outstring+=str(i)
if (cnt!=feat_size):
outstring+=','
outstring+='\n'
f.write(outstring)
f.close()
duration=[]
artist_familiarity=[]
artist_hotttnesss=[]
tempo=[]
loudness=[]
key=[]
time_signature=[]
end_of_fade_in=[]
mode=[]
start_of_fade_out=[]
song_hotttnesss=[]
for i in range(0,len(file)):
h5 = yay.open_h5_file_read('F:\sem4\ml\project\MillionSongSubset\data\A\{}'.format(file[i]))
duration.append(yay.get_duration(h5))
artist_familiarity.append(yay.get_artist_familiarity(h5))
artist_hotttnesss.append(yay.get_artist_hotttnesss(h5))
tempo.append(yay.get_tempo(h5))
loudness.append(yay.get_loudness(h5))
key.append(yay.get_key(h5))
time_signature.append(yay.get_time_signature(h5))
end_of_fade_in.append(yay.get_end_of_fade_in(h5))
mode.append(yay.get_mode(h5))
start_of_fade_out.append(yay.get_start_of_fade_out(h5))
song_hotttnesss.append(yay.get_song_hotttnesss(h5))
rows = zip(duration,artist_familiarity,artist_hotttnesss,tempo,loudness,key,time_signature,
end_of_fade_in,mode,start_of_fade_out,song_hotttnesss)
import csv
def complete_hd5_to_csv(basedir):
ext = '.h5' # Get all files with extension .h5
# Header title. Essentially it is a schema for all the following songs
header = [
'Title', 'Artist familiarity', 'Artist hotness', 'Artist ID',
'Artist mbID', 'Artist playmeid', 'Artist 7DigitalID',
'Artist latitude', 'Artist longitude', 'Artist location',
'Artist Name', 'Release', 'Release 7DigitalID', 'Song ID',
'Song Hotness', 'Track 7Digital', 'Analysis sample rate', 'Audio md5',
'Danceability', 'Duration', 'End of Fade', 'Energy', 'Key',
'Key Confidence', 'Loudness', 'Mode', 'Mode Confidence',
'Start of fade out', 'Tempo', 'Time signature',
'Time signature confidence', 'Track ID', 'Year'
]
with open('Tester2.csv', 'w', newline='') as csvfile:
csv_writer = csv.writer(csvfile, delimiter=';')
# writing the header line. This line contains the schema of the data
csv_writer.writerow(header)
# Read all files from the given directories
for root, dirs, files in os.walk(basedir):
files = glob.glob(os.path.join(root, '*' + ext))
print(files)
for f in files:
h5 = hdf5_getters.open_h5_file_read(f)
# Write as row all elements. NOTE: Only the serialized elements are parsed and not arrays
csv_writer.writerow([
hdf5_getters.get_title(h5),
hdf5_getters.get_artist_familiarity(h5),
hdf5_getters.get_artist_hotttnesss(h5),
hdf5_getters.get_artist_id(h5),
hdf5_getters.get_artist_mbid(h5),
hdf5_getters.get_artist_playmeid(h5),
hdf5_getters.get_artist_7digitalid(h5),
hdf5_getters.get_artist_latitude(h5),
hdf5_getters.get_artist_longitude(h5),
hdf5_getters.get_artist_location(h5),
hdf5_getters.get_artist_name(h5),
hdf5_getters.get_release(h5),
hdf5_getters.get_release_7digitalid(h5),
hdf5_getters.get_song_id(h5),
hdf5_getters.get_song_hotttnesss(h5),
hdf5_getters.get_track_7digitalid(h5),
hdf5_getters.get_analysis_sample_rate(h5),
hdf5_getters.get_audio_md5(h5),
hdf5_getters.get_danceability(h5),
hdf5_getters.get_duration(h5),
hdf5_getters.get_end_of_fade_in(h5),
hdf5_getters.get_energy(h5),
hdf5_getters.get_key(h5),
hdf5_getters.get_key_confidence(h5),
hdf5_getters.get_loudness(h5),
hdf5_getters.get_mode(h5),
hdf5_getters.get_mode_confidence(h5),
hdf5_getters.get_start_of_fade_out(h5),
hdf5_getters.get_tempo(h5),
hdf5_getters.get_time_signature(h5),
hdf5_getters.get_time_signature_confidence(h5),
hdf5_getters.get_track_id(h5),
hdf5_getters.get_year(h5)
])
# For debugging purposes. Everything as expected
# print()
# print("Num of songs -- ", hdf5_getters.get_num_songs(h5)) # One song per file
# print("Title -- ", hdf5_getters.get_title(h5)) # Print the title of a specific h5 file
# print("Artist familiarity -- ", hdf5_getters.get_artist_familiarity(h5))
# print("Artist hotness -- ", hdf5_getters.get_artist_hotttnesss(h5))
# print("Artist ID -- ", hdf5_getters.get_artist_id(h5))
# print("Artist mbID -- ", hdf5_getters.get_artist_mbid(h5))
# print("Artist playmeid -- ", hdf5_getters.get_artist_playmeid(h5))
# print("Artist 7DigitalID -- ", hdf5_getters.get_artist_7digitalid(h5))
# print("Artist latitude -- ", hdf5_getters.get_artist_latitude(h5))
# print("Artist longitude -- ", hdf5_getters.get_artist_longitude(h5))
# print("Artist location -- ", hdf5_getters.get_artist_location(h5))
# print("Artist Name -- ", hdf5_getters.get_artist_name(h5))
# print("Release -- ", hdf5_getters.get_release(h5))
# print("Release 7DigitalID -- ", hdf5_getters.get_release_7digitalid(h5))
# print("Song ID -- ", hdf5_getters.get_song_id(h5))
# print("Song Hotness -- ", hdf5_getters.get_song_hotttnesss(h5))
# print("Track 7Digital -- ", hdf5_getters.get_track_7digitalid(h5))
# print("Analysis sample rate -- ", hdf5_getters.get_analysis_sample_rate(h5))
# print("Audio md5 -- ", hdf5_getters.get_audio_md5(h5))
# print("Danceability -- ", hdf5_getters.get_danceability(h5))
# print("Duration -- ", hdf5_getters.get_duration(h5))
# print("End of Fade -- ", hdf5_getters.get_end_of_fade_in(h5))
# print("Energy -- ", hdf5_getters.get_energy(h5))
# print("Key -- ", hdf5_getters.get_key(h5))
# print("Key Confidence -- ", hdf5_getters.get_key_confidence(h5))
# print("Loudness -- ", hdf5_getters.get_loudness(h5))
# print("Mode -- ", hdf5_getters.get_mode(h5))
# print("Mode Confidence -- ", hdf5_getters.get_mode_confidence(h5))
# print("Start of fade out -- ", hdf5_getters.get_start_of_fade_out(h5))
# print("Tempo -- ", hdf5_getters.get_tempo(h5))
# print("Time signature -- ", hdf5_getters.get_time_signature(h5))
# print("Time signature confidence -- ", hdf5_getters.get_time_signature_confidence(h5))
# print("Track ID -- ", hdf5_getters.get_track_id(h5))
# # print("Artist mbtags -- ", hdf5_getters.get_artist_mbtags(h5))
# # print("Artist mbtags count -- ", hdf5_getters.get_artist_mbtags_count(h5))
# print("Year -- ", hdf5_getters.get_year(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()
def parse_aggregate_songs(file_name,file_name2,artist_map):
"""
Given an aggregate filename and artist_map in the format
{artist_name: {data pertaining to artist}}
"""
"""
TODO:
-this function goes through each song, if artist not in there,
add all data necesary and add first song info.
else update any specific song info
-song info is a map from attributename:[values]
"""
#artist_map = {}
h5 = hdf5_getters.open_h5_file_read(file_name)
numSongs = hdf5_getters.get_num_songs(h5)
print 'Parsing song file...'
for i in range(numSongs):
artist_name = hdf5_getters.get_artist_name(h5,i)
#Filter location
longi = hdf5_getters.get_artist_longitude(h5,i)
lat = hdf5_getters.get_artist_latitude(h5,i)
loc = hdf5_getters.get_artist_location(h5,i)
if math.isnan(lat) or math.isnan(longi):
#skip if no location
continue
#filter year
yr = hdf5_getters.get_year(h5,i)
if yr == 0:
#skip if no year
continue
#filter hotttness and familiarity
familiarity = hdf5_getters.get_artist_familiarity(h5,i)
hotttness = hdf5_getters.get_artist_hotttnesss(h5,i)
if familiarity<=0.0 or hotttness<=0.0:
#skip if no hotttness or familiarity computations
continue
#TODO:MAYBE filter on dance and energy
timbre = hdf5_getters.get_segments_timbre(h5,i)
#timbre[#] gives len 12 array so for each arr in timbre, add up to get segment and add to corresponding 12 features and avg across each
if not artist_name in artist_map:
#have not encountered the artist yet, so populate new map
sub_map = {}
sub_map['artist_familiarity'] = familiarity
sub_map['artist_hotttnesss'] = hotttness
sub_map['artist_id'] = hdf5_getters.get_artist_id(h5,i)
#longi = hdf5_getters.get_artist_longitude(h5,i)
#lat = hdf5_getters.get_artist_latitude(h5,i)
#longi = None if math.isnan(longi) else longi
#lat = None if math.isnan(lat) else lat
sub_map['artist_latitude'] = lat
sub_map['artist_longitude'] = longi
sub_map['artist_location'] = loc
sub_map['artist_terms'] = hdf5_getters.get_artist_terms(h5,i)
#TODO:see if should weight by freq or weight for if the term matches one of the feature terms
sub_map['artist_terms_freq'] = list(hdf5_getters.get_artist_terms_freq(h5,i))
sub_map['artist_terms_weight'] = list(hdf5_getters.get_artist_terms_weight(h5,i))
#song-sepcific data
#TODO COMPUTE AN AVG TIMBRE FOR A SONG BY IDEA:
#SUMMING DOWN EACH 12 VECTOR FOR EACH PT IN SONG AND AVG THIS ACROSS SONG
dance = hdf5_getters.get_danceability(h5,i)
dance = None if dance == 0.0 else dance
energy = hdf5_getters.get_energy(h5,i)
energy = None if energy == 0.0 else energy
sub_map['danceability'] = [dance]
sub_map['duration'] = [hdf5_getters.get_duration(h5,i)]
sub_map['end_of_fade_in'] = [hdf5_getters.get_end_of_fade_in(h5,i)]
sub_map['energy'] = [energy]
#since each song has a key, ask if feature for keys should be num of songs that appear in that key or
#just binary if any of their songs has that key or just be avg of songs with that key
#same for mode, since its either major or minor...should it be count or avg.?
sub_map['key'] = [hdf5_getters.get_key(h5,i)]
sub_map['loudness'] = [hdf5_getters.get_loudness(h5,i)]
sub_map['mode'] = [hdf5_getters.get_mode(h5,i)] #major or minor 0/1
s_hot = hdf5_getters.get_song_hotttnesss(h5,i)
s_hot = None if math.isnan(s_hot) else s_hot
sub_map['song_hotttnesss'] = [s_hot]
sub_map['start_of_fade_out'] = [hdf5_getters.get_start_of_fade_out(h5,i)]
sub_map['tempo'] = [hdf5_getters.get_tempo(h5,i)]
#should time signature be count as well? binary?
sub_map['time_signature'] = [hdf5_getters.get_time_signature(h5,i)]
sub_map['track_id'] = [hdf5_getters.get_track_id(h5,i)]
#should year be binary since they can have many songs across years and should it be year:count
sub_map['year'] = [yr]
artist_map[artist_name] = sub_map
else:
#artist already exists, so get its map and update song fields
dance = hdf5_getters.get_danceability(h5,i)
dance = None if dance == 0.0 else dance
energy = hdf5_getters.get_energy(h5,i)
energy = None if energy == 0.0 else energy
artist_map[artist_name]['danceability'].append(dance)
artist_map[artist_name]['duration'].append(hdf5_getters.get_duration(h5,i))
artist_map[artist_name]['end_of_fade_in'].append(hdf5_getters.get_end_of_fade_in(h5,i))
artist_map[artist_name]['energy'].append(energy)
artist_map[artist_name]['key'].append(hdf5_getters.get_key(h5,i))
artist_map[artist_name]['loudness'].append(hdf5_getters.get_loudness(h5,i))
artist_map[artist_name]['mode'].append(hdf5_getters.get_mode(h5,i)) #major or minor 0/1
s_hot = hdf5_getters.get_song_hotttnesss(h5,i)
s_hot = None if math.isnan(s_hot) else s_hot
artist_map[artist_name]['song_hotttnesss'].append(s_hot)
artist_map[artist_name]['start_of_fade_out'].append(hdf5_getters.get_start_of_fade_out(h5,i))
artist_map[artist_name]['tempo'].append(hdf5_getters.get_tempo(h5,i))
#should time signature be count as well? binary?
artist_map[artist_name]['time_signature'].append(hdf5_getters.get_time_signature(h5,i))
artist_map[artist_name]['track_id'].append(hdf5_getters.get_track_id(h5,i))
#should year be binary since they can have many songs across years and should it be year:count
artist_map[artist_name]['year'].append(yr)
h5 = hdf5_getters.open_h5_file_read(file_name2)
numSongs = hdf5_getters.get_num_songs(h5)
print 'Parsing song file2...'
for i in range(numSongs):
song_id = hdf5_getters.get_track_id(h5,i)
artist_name = hdf5_getters.get_artist_name(h5,i)
if artist_name in artist_map and song_id in artist_map[artist_name]['track_id']:
continue
#Filter location
longi = hdf5_getters.get_artist_longitude(h5,i)
lat = hdf5_getters.get_artist_latitude(h5,i)
loc = hdf5_getters.get_artist_location(h5,i)
if math.isnan(lat) or math.isnan(longi):
#skip if no location
continue
#filter year
yr = hdf5_getters.get_year(h5,i)
if yr == 0:
#skip if no year
continue
#filter hotttness and familiarity
familiarity = hdf5_getters.get_artist_familiarity(h5,i)
hotttness = hdf5_getters.get_artist_hotttnesss(h5,i)
if familiarity<=0.0 or hotttness<=0.0:
#skip if no hotttness or familiarity computations
continue
#TODO:MAYBE filter on dance and energy
timbre = hdf5_getters.get_segments_timbre(h5,i)
#timbre[#] gives len 12 array so for each arr in timbre, add up to get segment and add to corresponding 12 features and avg across each
if not artist_name in artist_map:
#have not encountered the artist yet, so populate new map
sub_map = {}
sub_map['artist_familiarity'] = familiarity
sub_map['artist_hotttnesss'] = hotttness
sub_map['artist_id'] = hdf5_getters.get_artist_id(h5,i)
#longi = hdf5_getters.get_artist_longitude(h5,i)
#lat = hdf5_getters.get_artist_latitude(h5,i)
#longi = None if math.isnan(longi) else longi
#lat = None if math.isnan(lat) else lat
sub_map['artist_latitude'] = lat
sub_map['artist_longitude'] = longi
sub_map['artist_location'] = loc
sub_map['artist_terms'] = hdf5_getters.get_artist_terms(h5,i)
#TODO:see if should weight by freq or weight for if the term matches one of the feature terms
sub_map['artist_terms_freq'] = list(hdf5_getters.get_artist_terms_freq(h5,i))
sub_map['artist_terms_weight'] = list(hdf5_getters.get_artist_terms_weight(h5,i))
#song-sepcific data
#TODO COMPUTE AN AVG TIMBRE FOR A SONG BY IDEA:
#SUMMING DOWN EACH 12 VECTOR FOR EACH PT IN SONG AND AVG THIS ACROSS SONG
dance = hdf5_getters.get_danceability(h5,i)
dance = None if dance == 0.0 else dance
energy = hdf5_getters.get_energy(h5,i)
energy = None if energy == 0.0 else energy
sub_map['danceability'] = [dance]
sub_map['duration'] = [hdf5_getters.get_duration(h5,i)]
sub_map['end_of_fade_in'] = [hdf5_getters.get_end_of_fade_in(h5,i)]
sub_map['energy'] = [energy]
#since each song has a key, ask if feature for keys should be num of songs that appear in that key or
#just binary if any of their songs has that key or just be avg of songs with that key
#same for mode, since its either major or minor...should it be count or avg.?
sub_map['key'] = [hdf5_getters.get_key(h5,i)]
sub_map['loudness'] = [hdf5_getters.get_loudness(h5,i)]
sub_map['mode'] = [hdf5_getters.get_mode(h5,i)] #major or minor 0/1
s_hot = hdf5_getters.get_song_hotttnesss(h5,i)
s_hot = None if math.isnan(s_hot) else s_hot
sub_map['song_hotttnesss'] = [s_hot]
sub_map['start_of_fade_out'] = [hdf5_getters.get_start_of_fade_out(h5,i)]
sub_map['tempo'] = [hdf5_getters.get_tempo(h5,i)]
#should time signature be count as well? binary?
sub_map['time_signature'] = [hdf5_getters.get_time_signature(h5,i)]
sub_map['track_id'] = [hdf5_getters.get_track_id(h5,i)]
#should year be binary since they can have many songs across years and should it be year:count
sub_map['year'] = [yr]
artist_map[artist_name] = sub_map
else:
#artist already exists, so get its map and update song fields
dance = hdf5_getters.get_danceability(h5,i)
dance = None if dance == 0.0 else dance
energy = hdf5_getters.get_energy(h5,i)
energy = None if energy == 0.0 else energy
artist_map[artist_name]['danceability'].append(dance)
artist_map[artist_name]['duration'].append(hdf5_getters.get_duration(h5,i))
artist_map[artist_name]['end_of_fade_in'].append(hdf5_getters.get_end_of_fade_in(h5,i))
artist_map[artist_name]['energy'].append(energy)
artist_map[artist_name]['key'].append(hdf5_getters.get_key(h5,i))
artist_map[artist_name]['loudness'].append(hdf5_getters.get_loudness(h5,i))
artist_map[artist_name]['mode'].append(hdf5_getters.get_mode(h5,i)) #major or minor 0/1
s_hot = hdf5_getters.get_song_hotttnesss(h5,i)
s_hot = None if math.isnan(s_hot) else s_hot
artist_map[artist_name]['song_hotttnesss'].append(s_hot)
artist_map[artist_name]['start_of_fade_out'].append(hdf5_getters.get_start_of_fade_out(h5,i))
artist_map[artist_name]['tempo'].append(hdf5_getters.get_tempo(h5,i))
#should time signature be count as well? binary?
artist_map[artist_name]['time_signature'].append(hdf5_getters.get_time_signature(h5,i))
artist_map[artist_name]['track_id'].append(hdf5_getters.get_track_id(h5,i))
#should year be binary since they can have many songs across years and should it be year:count
artist_map[artist_name]['year'].append(yr)
def get_fields(files):
tracks = []
counts = {}
field_counts = []
for file in files:
h5 = hdf5_getters.open_h5_file_read(file)
t = {}
t['artist_familiarity'] = hdf5_getters.get_artist_familiarity(
h5) # estimation
t['artist_hotttnesss'] = hdf5_getters.get_artist_hotttnesss(
h5) # estimation
t['artist_name'] = hdf5_getters.get_artist_name(h5) # artist name
t['release'] = hdf5_getters.get_release(h5) # album name
t['title'] = hdf5_getters.get_title(h5) # title
t['len_similar_artists'] = len(
hdf5_getters.get_similar_artists(h5)) # number of similar artists
t['analysis_sample_rate'] = hdf5_getters.get_analysis_sample_rate(
h5) # sample rate of the audio used ?????????
t['duration'] = hdf5_getters.get_duration(h5) # seconds
t['key'] = hdf5_getters.get_key(h5) # key the song is in
t['key_confidence'] = hdf5_getters.get_key_confidence(
h5) # confidence measure
t['loudness'] = hdf5_getters.get_loudness(h5) # overall loudness in dB
t['mode_confidence'] = hdf5_getters.get_mode_confidence(
h5) # confidence measure
t['start_of_fade_out'] = hdf5_getters.get_start_of_fade_out(
h5) # time in sec
t['tempo'] = hdf5_getters.get_tempo(h5) # estimated tempo in BPM
t['time_signature'] = hdf5_getters.get_time_signature(
h5) # estimate of number of beats per bar, e.g. 4
t['year'] = hdf5_getters.get_year(
h5) # song release year from MusicBrainz or 0
timbre = hdf5_getters.get_segments_timbre(
h5) # 2D float array, texture features (MFCC+PCA-like)
t['segments_timbre'] = timbre
t['timbre_avg'] = timbre.mean(axis=0) # list of 12 averages
cov_mat_timbre = np.cov(timbre, rowvar=False)
cov_timbre = []
for i in range(len(cov_mat_timbre)):
for j in range(len(cov_mat_timbre) - i):
cov_timbre.append(cov_mat_timbre[i][j])
t['timbre_cov'] = cov_timbre # list of 78 covariances
pitch = hdf5_getters.get_segments_pitches(
h5) # 2D float array, chroma feature, one value per note
t['segments_pitch'] = pitch
t['pitch_avg'] = pitch.mean(axis=0) # list of 12 averages
cov_mat_pitch = np.cov(pitch, rowvar=False)
cov_pitch = []
for i in range(len(cov_mat_pitch)):
for j in range(len(cov_mat_pitch) - i):
cov_pitch.append(cov_mat_timbre[i][j])
t['pitch_cov'] = cov_pitch # list of 78 covariances
# seg_pitch = hdf5_getters.get_segments_pitches(h5) # 2D float array, chroma feature, one value per note
# print(seg_pitch.shape)
# t['artist_latitude'] = hdf5_getters.get_artist_latitude(h5) # float, ????????????????????????????????????????
# t['artist_longitude'] = hdf5_getters.get_artist_longitude(h5) # float, ??????????????????????????????????????
# t['artist_location'] = hdf5_getters.get_artist_location(h5) # location name
# t['song_hotttnesss'] = hdf5_getters.get_song_hotttnesss(h5) # estimation
# t['danceability'] = hdf5_getters.get_danceability(h5) # estimation
# t['end_of_fade_in'] = hdf5_getters.get_end_of_fade_in(h5) # seconds at the beginning of the song
# t['energy'] = hdf5_getters.get_energy(h5) # energy from listener point of view
# t['mode'] = hdf5_getters.get_mode(h5) # major or minor
# t['time_signature_confidence'] = hdf5_getters.get_time_signature_confidence(h5) # confidence measure
# t['artist_mbtags_count'] = len(hdf5_getters.get_artist_mbtags_count(h5)) # array int, tag counts for musicbrainz tags
# bad types or non arithmatic numbers
'''
# t['audio_md5'] = hdf5_getters.get_audio_md5(h5) # hash code of the audio used for the analysis by The Echo Nest
# t['artist_terms_weight'] = hdf5_getters.get_artist_terms_weight(h5) # array float, echonest tags weight ?????
# t['artist_terms_freq'] = hdf5_getters.get_artist_terms_freq(h5) # array float, echonest tags freqs ??????????
# t['artist_terms'] = hdf5_getters.get_artist_terms(h5) # array string, echonest tags ?????????????????????????
# t['artist_id'] = hdf5_getters.get_artist_id(h5) # echonest id
# t['artist_mbid'] = hdf5_getters.get_artist_mbid(h5) # musicbrainz id
# t['artist_playmeid'] = hdf5_getters.get_artist_playmeid(h5) # playme id
# t['artist_7digitalid'] = hdf5_getters.get_artist_7digitalid(h5) # 7digital id
# t['release_7digitalid'] = hdf5_getters.get_release_7digitalid(h5) # 7digital id
# t['song_id'] = hdf5_getters.get_song_id(h5) # echonest id
# t['track_7digitalid'] = hdf5_getters.get_track_7digitalid(h5) # 7digital id
# t['similar_artists'] = hdf5_getters.get_similar_artists(h5) # string array of sim artist ids
# t['track_id'] = hdf5_getters.get_track_id(h5) # echonest track id
# t['segments_start'] = hdf5_getters.get_segments_start(h5) # array floats, musical events, ~ note onsets
# t['segments_confidence'] = hdf5_getters.get_segments_confidence(h5) # array floats, confidence measure
# t['segments_pitches'] = hdf5_getters.get_segments_pitches(h5) # 2D float array, chroma feature, one value per note
# t['segments_timbre'] = hdf5_getters.get_segments_timbre(h5) # 2D float array, texture features (MFCC+PCA-like)
# t['segments_loudness_max'] = hdf5_getters.get_segments_loudness_max(h5) # float array, max dB value
# t['segments_loudness_max_time'] = hdf5_getters.get_segments_loudness_max_time(h5) # float array, time of max dB value, i.e. end of attack
# t['segments_loudness_start'] = hdf5_getters.get_segments_loudness_start(h5) # array float, dB value at onset
# t['sections_start'] = hdf5_getters.get_sections_start(h5) # array float, largest grouping in a song, e.g. verse
# t['sections_confidence'] = hdf5_getters.get_sections_confidence(h5) # array float, confidence measure
# t['beats_start'] = hdf5_getters.get_beats_start(h5) # array float, result of beat tracking
# t['beats_confidence'] = hdf5_getters.get_beats_confidence(h5) # array float, confidence measure
# t['bars_start'] = hdf5_getters.get_bars_start(h5) # array float, beginning of bars, usually on a beat
# t['bars_confidence'] = hdf5_getters.get_bars_confidence(h5) # array float, confidence measure
# t['tatums_start'] = hdf5_getters.get_tatums_start(h5) # array float, smallest rythmic element
# t['tatums_confidence'] = hdf5_getters.get_tatums_confidence(h5) # array float, confidence measure
# t['artist_mbtags'] = hdf5_getters.get_artist_mbtags(h5) # array string, tags from musicbrainz.org
'''
h5.close()
for key, value in t.items():
if isinstance(value, float) and math.isnan(value):
pass
if type(value) is np.ndarray:
if key in counts.keys():
counts[key] += 1
else:
counts[key] = 1
elif value:
if key in counts.keys():
counts[key] += 1
else:
counts[key] = 1
elif key not in counts.keys():
counts[key] = 0
count = 0
for key, value in t.items():
if isinstance(value, float) and math.isnan(value):
pass
elif type(value) is np.ndarray:
count += 1
elif value:
count += 1
field_counts.append(count)
# progress bar
if num_of_tracks >= 100:
i = files.index(file) + 1
scale = num_of_tracks / 100
if i % math.ceil(len(files) * .05) == 0:
sys.stdout.write('\r')
# the exact output you're looking for:
sys.stdout.write("Loading dataframe: [%-100s] %d%%" %
('=' * int(i // scale), 1 / scale * i))
sys.stdout.flush()
time.sleep(.01)
tracks.append(t)
print()
return tracks, counts, field_counts
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)
def getArtistFamiliarity(h5):
#Returns the artist familiarity value
return [hdf5_getters.get_artist_familiarity(h5)]
cnt = 0
loops = 0
for alpha in string.ascii_uppercase :
for root, dirs, files in os.walk('/mnt/million-songs/data/'+alpha):
files = glob.glob(os.path.join(root,'*'+'.h5'))
for f in files :
h5 = GETTERS.open_h5_file_read(f)
num_songs = GETTERS.get_num_songs(h5)
print f, num_songs
for i in range(num_songs):
analysis_sample_rate = GETTERS.get_analysis_sample_rate(h5, i)
artist_7digitalid = GETTERS.get_artist_7digitalid(h5, i)
artist_familiarity = GETTERS.get_artist_familiarity(h5, i)
artist_hotttnesss = GETTERS.get_artist_hotttnesss(h5, i)
artist_id = GETTERS.get_artist_id(h5, i)
artist_latitude = GETTERS.get_artist_latitude(h5, i)
artist_location = GETTERS.get_artist_location(h5, i)
artist_longitude = GETTERS.get_artist_longitude(h5, i)
artist_mbid = GETTERS.get_artist_mbid(h5, i)
artist_mbtags = ','.join(str(e) for e in GETTERS.get_artist_mbtags(h5, i)) # array
artist_mbtags_count = ','.join(str(e) for e in GETTERS.get_artist_mbtags_count(h5, i)) # array
artist_name = GETTERS.get_artist_name(h5, i)
artist_playmeid = GETTERS.get_artist_playmeid(h5, i)
artist_terms = ','.join(str(e) for e in GETTERS.get_artist_terms(h5, i)) # array
#artist_terms_freq = ','.join(str(e) for e in GETTERS.get_artist_terms_freq(h5, i)) # array
#artist_terms_weight = ','.join(str(e) for e in GETTERS.get_artist_terms_weight(h5, i)) # array
#audio_md5 = GETTERS.get_audio_md5(h5, i)
#bars_confidence = ','.join(str(e) for e in GETTERS.get_bars_confidence(h5, i)) # array
for subdir, dirs, files in os.walk("data/"):
for file in files:
f = os.path.join(subdir, file)
if ".h5" in f:
h5 = h.open_h5_file_read(f)
print ("----------")
''' Store artist tuples '''
artist_id = h.get_artist_id(h5,0)
artist_name = h.get_artist_name(h5,0)
artist_name = artist_name.replace("'","")
artist_hottness = str(h.get_artist_hotttnesss(h5,0))
print artist_hottness
if artist_hottness == "nan":
artist_hottness = "0.0"
artist_familiarity = str(h.get_artist_familiarity(h5,0))
if artist_familiarity == "nan":
artist_familiarity = "0.0"
cursor.execute("SELECT * FROM artist WHERE artist_id = '" + artist_id + "'")
rs = cursor.fetchall()
if cursor.rowcount != 1:
cursor.execute("INSERT INTO artist VALUES ('" + artist_id + "','" + artist_name + "'," + artist_hottness + "," + artist_familiarity + ");")
''' Store artist_genres tuples '''
terms = h.get_artist_terms(h5,0)
mbtags = h.get_artist_mbtags(h5,0)
for term in terms:
term = term.replace("'","")
cursor.execute("SELECT * FROM artist_genres WHERE artist_id='" + artist_id + "' AND genre ='" + term + "'")
if cursor.rowcount != 1:
def fill_attributes(song, songH5File):
#----------------------------non array attributes-------------------------------
song.analysisSampleRate = str(
hdf5_getters.get_analysis_sample_rate(songH5File))
song.artistDigitalID = str(hdf5_getters.get_artist_7digitalid(songH5File))
song.artistFamiliarity = str(
hdf5_getters.get_artist_familiarity(songH5File))
song.artistHotness = str(hdf5_getters.get_artist_hottness(songH5File))
song.artistID = str(hdf5_getters.get_artist_id(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.artistmbID = str(hdf5_getters.get_artist_mbid(songH5File))
song.artistName = str(hdf5_getters.get_artist_name(songH5File))
song.artistPlayMeID = str(hdf5_getters.get_artist_playmeid(songH5File))
song.audioMD5 = str(hdf5_getters.get_audio_md5(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.segementsConfidence = str(
hdf5_getters.get_segments_confidence(songH5File))
song.segementsConfidence = str(
hdf5_getters.get_sections_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.release = str(hdf5_getters.get_release(songH5File))
song.releaseDigitalID = str(
hdf5_getters.get_release_7digitalid(songH5File))
song.songHotttnesss = str(hdf5_getters.get_song_hotttnesss(songH5File))
song.startOfFadeOut = str(hdf5_getters.get_start_of_fade_out(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.trackID = str(hdf5_getters.get_track_id(songH5File))
song.trackDigitalID = str(hdf5_getters.get_track_7digitalid(songH5File))
song.year = str(hdf5_getters.get_year(songH5File))
#-------------------------------array attributes--------------------------------------
#array float
song.beatsStart_mean, song.beatsStart_var = convert_array_to_meanvar(
hdf5_getters.get_beats_start(songH5File))
#array float
song.artistTermsFreq_mean, song.artistTermsFreq_var = convert_array_to_meanvar(
hdf5_getters.get_artist_terms_freq(songH5File))
#array float
song.artistTermsWeight_mean, song.artistTermsWeight_var = convert_array_to_meanvar(
hdf5_getters.get_artist_terms_weight(songH5File))
#array int
song.artistmbTagsCount_mean, song.artistmbTagsCount_var = convert_array_to_meanvar(
hdf5_getters.get_artist_mbtags_count(songH5File))
#array float
song.barsConfidence_mean, song.barsConfidence_var = convert_array_to_meanvar(
hdf5_getters.get_bars_confidence(songH5File))
#array float
song.barsStart_mean, song.barsStart_var = convert_array_to_meanvar(
hdf5_getters.get_bars_start(songH5File))
#array float
song.beatsConfidence_mean, song.beatsConfidence_var = convert_array_to_meanvar(
hdf5_getters.get_beats_confidence(songH5File))
#array float
song.sectionsConfidence_mean, song.sectionsConfidence_var = convert_array_to_meanvar(
hdf5_getters.get_sections_confidence(songH5File))
#array float
song.sectionsStart_mean, song.sectionsStart_var = convert_array_to_meanvar(
hdf5_getters.get_sections_start(songH5File))
#array float
song.segmentsConfidence_mean, song.segmentsConfidence_var = convert_array_to_meanvar(
hdf5_getters.get_segments_confidence(songH5File))
#array float
song.segmentsLoudness_mean, song.segmentsLoudness_var = convert_array_to_meanvar(
hdf5_getters.get_segments_loudness_max(songH5File))
#array float
song.segmentsLoudnessMaxTime_mean, song.segmentsLoudnessMaxTime_var = convert_array_to_meanvar(
hdf5_getters.get_segments_loudness_max_time(songH5File))
#array float
song.segmentsLoudnessMaxStart_mean, song.segmentsLoudnessMaxStart_var = convert_array_to_meanvar(
hdf5_getters.get_segments_loudness_start(songH5File))
#array float
song.segmentsStart_mean, song.segmentsStart_var = convert_array_to_meanvar(
hdf5_getters.get_segments_start(songH5File))
#array float
song.tatumsConfidence_mean, song.tatumsConfidence_var = convert_array_to_meanvar(
hdf5_getters.get_tatums_confidence(songH5File))
#array float
song.tatumsStart_mean, song.tatumsStart_var = convert_array_to_meanvar(
hdf5_getters.get_tatums_start(songH5File))
#array2d float
song.segmentsTimbre_mean, song.segmentsTimbre_var = covert_2darray_to_meanvar(
hdf5_getters.get_segments_timbre(songH5File))
#array2d float
song.segmentsPitches_mean, song.segmentsPitches_var = covert_2darray_to_meanvar(
hdf5_getters.get_segments_pitches(songH5File))
#------------------------array string attributes------------------------
song.similarArtists = convert_array_to_string(
hdf5_getters.get_similar_artists(songH5File)) #array string
song.artistTerms = convert_array_to_string(
hdf5_getters.get_artist_terms(songH5File)) #array string
song.artistmbTags = convert_array_to_string(
hdf5_getters.get_artist_mbtags(songH5File)) #array string
return song
def func_to_extract_features(filename):
"""
This function does 3 simple things:
- open the song file
- get artist ID and put it
- close the file
"""
global cntnan
global cntdanceability
global listfeatures
global listhotness
global listyear
global listloudness
global listkey
global listmode
global listduration
cf = []
h5 = GETTERS.open_h5_file_read(filename)
nanfound = 0
#Get target feature: song hotness
#FEATURE 0
song_hotness = GETTERS.get_song_hotttnesss(h5)
if math.isnan(song_hotness):
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(song_hotness)
#FEATURE 1
#Get song loudness
song_loudness = GETTERS.get_loudness(h5)
if math.isnan(song_loudness):
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(song_loudness)
#FEATURE 2
#Get key of the song
song_key = GETTERS.get_key(h5)
if math.isnan(song_key):
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(song_key)
#FEATURE 3
#Get duration of the song
song_duration = GETTERS.get_duration(h5)
if math.isnan(song_duration):
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(song_duration)
#FEATURE 4-15
#Get Average Pitch Class across all segments
#Get the pitches (12 pitches histogram for each segment)
pitches = GETTERS.get_segments_pitches(h5)
M = np.mat(pitches)
meanpitches = M.mean(axis=0)
pitches_arr = np.asarray(meanpitches)
pitches_list = []
for i in range(0,12):
pitches_list.append(pitches_arr[0][i])
cf.append(pitches_list)
#FEATURE 16, 27
#Get Average Timbre Class across all segments
timbres = GETTERS.get_segments_timbre(h5)
M = np.mat(timbres)
meantimbres = M.mean(axis=0)
timbre_arr = np.asarray(meantimbres)
timbre_list = []
for i in range(0,12):
timbre_list.append(timbre_arr[0][i])
cf.append(timbre_list)
#FEATURE 28
#Get song year
song_year = GETTERS.get_year(h5)
if song_year == 0:
nanfound = 1
cntnan = cntnan + 1
else:
cf.append(song_year)
#FEATURE 29
#Get song tempo
song_tempo = GETTERS.get_tempo(h5)
cf.append(song_tempo)
#Feature 30
#Get max loudness for each segment
max_loudness_arr = GETTERS.get_segments_loudness_max(h5)
start_loudness_arr = GETTERS.get_segments_loudness_start(h5)
if nanfound == 0:
cf.append(max(max_loudness_arr)-min(start_loudness_arr))
#Feature 31
artist_familiarity = GETTERS.get_artist_familiarity(h5)
cf.append(artist_familiarity)
#Feature 32
song_title = GETTERS.get_title(h5)
cf.append(song_title)
#Featture 33
artist_name = GETTERS.get_artist_name(h5)
cf.append(artist_name)
#Feature 34
#location = GETTERS.get_artist_location(h5)
#cf.append(location)
#Tags
artist_mbtags = GETTERS.get_artist_mbtags(h5)
if not artist_mbtags.size:
genre = "Unknown"
else:
artist_mbcount = np.array(GETTERS.get_artist_mbtags_count(h5))
index_max = artist_mbcount.argmax(axis=0)
genre = artist_mbtags[index_max]
if genre == 'espa\xc3\xb1ol':
genre = "Unknown"
cf.append(genre)
if nanfound == 0:
strlist = list_to_csv(cf)
listfeatures.append(strlist)
mydict.setdefault(artist_name,[]).append(song_hotness)
h5.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)
