def load_non_time_data():
    years = []
    ten_features=[]
    num = 0
    for root, dirs, files in os.walk(basedir):
        files = glob.glob(os.path.join(root,'*'+ext))
        for f in files:
            h5 = getter.open_h5_file_read(f)
            num += 1
            print(num)
            try:
                year = getter.get_year(h5)
                if year!=0:
                    years.append(year)
                    title_length = len(getter.get_title(h5))
                    terms_length = len(getter.get_artist_terms(h5))
                    tags_length = len(getter.get_artist_mbtags(h5))
                    hotness = getter.get_artist_hotttnesss(h5)
                    duration = getter.get_duration(h5)
                    loudness = getter.get_loudness(h5)
                    mode = getter.get_mode(h5)
                    release_length = len(getter.get_release(h5))
                    tempo = getter.get_tempo(h5)
                    name_length = len(getter.get_artist_name(h5))
                    ten_feature = np.hstack([title_length,tags_length, hotness, duration,
                                             terms_length, loudness, mode, release_length, tempo, name_length])
                    ten_features.append(ten_feature) 
            except:
                print(1)
            h5.close()
    return years,ten_features
def get_all_titles(basedir, ext='.h5'):
    titles = []
    artist_names = []
    terms = []
    loudness = []
    segments_loudness_max = []

    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)

            titles.append(hdf5_getters.get_title(h5))
            artist_names.append(hdf5_getters.get_artist_name(h5))
            try:
                terms.append(hdf5_getters.get_artist_terms(h5))
            except:
                pass
            loudness.append(hdf5_getters.get_loudness(h5))
            try:
                segments_loudness_max.append(
                    hdf5_getters.get_segments_loudness_max(h5))
            except:
                pass

            h5.close()
    return titles, artist_names, terms, loudness, segments_loudness_max
def get_all_titles(basedir,ext='.h5') :
    titles = []
    artist_names = []
    terms = []
    loudness = []
    segments_loudness_max = []
    
    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)
            
            titles.append(hdf5_getters.get_title(h5)) 
            artist_names.append(hdf5_getters.get_artist_name(h5))
            try:
                terms.append(hdf5_getters.get_artist_terms(h5))
            except:          
                pass
            loudness.append(hdf5_getters.get_loudness(h5))
            try:
                segments_loudness_max.append(hdf5_getters.get_segments_loudness_max(h5))
            except:              
                pass
                        
            h5.close()
    return titles, artist_names, terms, loudness, segments_loudness_max
Example #4
0
def extract_features(filename):
    h5 = hdf5_getters.open_h5_file_read(filename)
    f = [None] * len(features)
    f[features.index('track_id')] = hdf5_getters.get_track_id(h5, 0).item()
    f[features.index('song_id')] = hdf5_getters.get_song_id(h5, 0).item()
    f[features.index('hotttnesss')] = hdf5_getters.get_artist_hotttnesss(
        h5, 0).item()
    f[features.index('danceability')] = hdf5_getters.get_danceability(
        h5, 0).item()
    f[features.index('duration')] = hdf5_getters.get_duration(h5, 0).item()
    f[features.index('key')] = hdf5_getters.get_key(h5, 0).item()
    f[features.index('energy')] = hdf5_getters.get_energy(h5, 0).item()
    f[features.index('loudness')] = hdf5_getters.get_loudness(h5, 0).item()
    f[features.index('year')] = hdf5_getters.get_year(h5, 0).item()
    f[features.index('time_signature')] = hdf5_getters.get_time_signature(
        h5, 0).item()
    f[features.index('tempo')] = hdf5_getters.get_tempo(h5, 0).item()
    tags = ''
    for tag in hdf5_getters.get_artist_terms(h5):
        tags += ('%s|' % tag)
    # Remove trailing pipe.
    tags = tags[:len(tags) - 1]
    f[features.index('tags')] = tags
    h5.close()
    return f
Example #5
0
def get_mbtags(paths):
    mbtags = []
    for key, folder in paths.items():
        for file in folder:
            h5 = get.open_h5_file_read(key + '/' + file)
            tags = get.get_artist_terms(h5)
            mbtags += tags.tolist()
            h5.close()

    return mbtags
Example #6
0
def Create_BoW(arg):
    print "Forming Bag of Words..."
    listing1 = os.listdir(arg)
    for a in listing1:
        listing2 = os.listdir(arg+a+'/')
        for b in listing2:
            listing3 = os.listdir(arg+a+'/'+b+'/')
            for c in listing3:
                listing4 = os.listdir(arg+a+'/'+b+'/'+c+'/')
                for d in listing4:
                    h5 = hdf5_getters.open_h5_file_read(arg+a+'/'+b+'/'+c+'/'+d)
                    art_t = hdf5_getters.get_artist_terms(h5)
                    for i in art_t:
                        Bag_Words[i]=1
                    h5.close()
    Bag_Words['UNK']=1
Example #7
0
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
Example #8
0
def Frequency(l, arg):
    print "Getting Frequency Distribution of BoW..."
    arr = np.zeros(l)
    listing1 = os.listdir(arg)
    for a in listing1:
        listing2 = os.listdir(arg+a+'/')
        for b in listing2:
            listing3 = os.listdir(arg+a+'/'+b+'/')
            for c in listing3:
                listing4 = os.listdir(arg+a+'/'+b+'/'+c+'/')
                for d in listing4:
                    h5 = hdf5_getters.open_h5_file_read(arg+a+'/'+b+'/'+c+'/'+d)
                    art_t = hdf5_getters.get_artist_terms(h5)
                    for i in art_t:
                        k = Bag_Words[i]
                        arr[k]+=1
                    h5.close()
    return arr
Example #9
0
def validate_song(h5_file,song):
	'''Returns true/false if song is valid or not. This is essentially cleanup and only lets through songs
	which have 'good' data (have a non-negligible duration, and have segments being most important)'''
	try:
		assert gt.get_year(h5_file, song)!='0'
		assert gt.get_duration(h5_file, song)>60.0
		assert gt.get_mode_confidence(h5_file, song)>0.2
		assert gt.get_key_confidence(h5_file, song)>0.2
		assert gt.get_time_signature_confidence(h5_file, song)>0.2
		terms=np.array(gt.get_artist_terms(h5_file, song))
		assert terms.size>0
		segments=np.array(gt.get_segments_start)
		assert segments.size>0
		sections=np.array(gt.get_sections_start)
		assert sections.size>0
	except:
		return False
	return True
def load_raw_data():
    years = []
    ten_features=[]
    timbres = []
    pitches = []
    min_length = 10000
    num = 0
    for root, dirs, files in os.walk(basedir):
        files = glob.glob(os.path.join(root,'*'+ext))
        for f in files:
            h5 = getter.open_h5_file_read(f)
            num += 1
            print(num)
            try:
                year = getter.get_year(h5)
                if year!=0:
                    timbre = getter.get_segments_timbre(h5)
                    s = np.size(timbre,0)
                    if s>=100:
                        if s<min_length:
                            min_length = s
                        pitch = getter.get_segments_pitches(h5)
                        years.append(year)
                        timbres.append(timbre)
                        pitches.append(pitch)
                        title_length = len(getter.get_title(h5))
                        terms_length = len(getter.get_artist_terms(h5))
                        tags_length = len(getter.get_artist_mbtags(h5))
                        hotness = getter.get_artist_hotttnesss(h5)
                        duration = getter.get_duration(h5)
                        loudness = getter.get_loudness(h5)
                        mode = getter.get_mode(h5)
                        release_length = len(getter.get_release(h5))
                        tempo = getter.get_tempo(h5)
                        name_length = len(getter.get_artist_name(h5))
                        ten_feature = np.hstack([title_length, hotness, duration, tags_length,
                                                 terms_length,loudness, mode, release_length, tempo, name_length])

                        ten_features.append(ten_feature) 
            except:
                print(1)
            h5.close()
    return years, timbres, pitches,min_length,ten_features
Example #11
0
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
Example #12
0
def get_all_attributes(filename):
    """
    This function does 3 simple things:
    - open the song file
    - get all required attributes
    - write it to a csv file 
    - close the files
    """
    with open('attributes.csv', 'a') as csvfile:
        try:
            # let's apply the previous function to all files
            csvwriter = csv.writer(csvfile, delimiter='\t')
            h5 = GETTERS.open_h5_file_read(filename)
            RESULTS = []
            RESULTS.append(GETTERS.get_year(h5))
            RESULTS.append(GETTERS.get_artist_id(h5))
            RESULTS.append(GETTERS.get_artist_name(h5))
            RESULTS.append(GETTERS.get_artist_mbid(h5))
            RESULTS.append(convert_terms(GETTERS.get_artist_terms(h5)))
            RESULTS.append(GETTERS.get_artist_hotttnesss(h5))
            RESULTS.append(GETTERS.get_artist_latitude(h5))
            RESULTS.append(GETTERS.get_artist_longitude(h5))
            RESULTS.append(GETTERS.get_artist_familiarity(h5))
            RESULTS.append(GETTERS.get_danceability(h5))
            RESULTS.append(GETTERS.get_duration(h5))
            RESULTS.append(GETTERS.get_energy(h5))
            RESULTS.append(GETTERS.get_loudness(h5))
            RESULTS.append(GETTERS.get_song_hotttnesss(h5))
            RESULTS.append(GETTERS.get_song_id(h5))
            RESULTS.append(GETTERS.get_tempo(h5))
            RESULTS.append(GETTERS.get_time_signature(h5))
            RESULTS.append(GETTERS.get_title(h5))
            RESULTS.append(GETTERS.get_track_id(h5))
            RESULTS.append(GETTERS.get_release(h5))
            csvwriter.writerow(RESULTS)
            h5.close()
        except AttributeError:
            pass
        i = 0

        for parent_folder in os.listdir(path):
            for sub_folder in os.listdir(path + '/' + parent_folder):
                for child_folder in os.listdir(path + '/' + parent_folder +
                                               '/' + sub_folder):
                    for file in os.listdir(path + '/' + parent_folder + '/' +
                                           sub_folder + '/' + child_folder):
                        with h5.open_h5_file_read(path + '/' + parent_folder +
                                                  '/' + sub_folder + '/' +
                                                  child_folder + '/' +
                                                  file) as ds:

                            row = []
                            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)]
Example #14
0
def classify(h5):
	output_array={}
	# duration
	duration=hdf5_getters.get_duration(h5)
	output_array["duration"]=duration	### ADDED VALUE TO ARRAY
	# number of bars
	bars=hdf5_getters.get_bars_start(h5)
	num_bars=len(bars)
	output_array["num_bars"]=num_bars	### ADDED VALUE TO ARRAY
	# mean and variance in bar length
	bar_length=numpy.ediff1d(bars)
	variance_bar_length=numpy.var(bar_length)
	output_array["variance_bar_length"]=variance_bar_length	### ADDED VALUE TO ARRAY
	# number of beats
	beats=hdf5_getters.get_beats_start(h5)
	num_beats=len(beats)
	output_array["num_beats"]=num_beats	### ADDED VALUE TO ARRAY
	# mean and variance in beats length
	beats_length=numpy.ediff1d(beats)
	variance_beats_length=numpy.var(bar_length)
	output_array["variance_beats_length"]=variance_beats_length	### ADDED VALUE TO ARRAY
	# danceability
	danceability=hdf5_getters.get_danceability(h5)
	output_array["danceability"]=danceability	### ADDED VALUE TO ARRAY
	# end of fade in
	end_of_fade_in=hdf5_getters.get_end_of_fade_in(h5)
	output_array["end_of_fade_in"]=end_of_fade_in	### ADDED VALUE TO ARRAY
	# energy
	energy=hdf5_getters.get_energy(h5)
	output_array["energy"]=energy	### ADDED VALUE TO ARRAY
	# key
	key=hdf5_getters.get_key(h5)
	output_array["key"]=int(key)	### ADDED VALUE TO ARRAY
	# loudness
	loudness=hdf5_getters.get_loudness(h5)
	output_array["loudness"]=loudness	### ADDED VALUE TO ARRAY
	# mode
	mode=hdf5_getters.get_mode(h5)
	output_array["mode"]=int(mode)	### ADDED VALUE TO ARRAY
	# number sections
	sections=hdf5_getters.get_sections_start(h5)
	num_sections=len(sections)
	output_array["num_sections"]=num_sections	### ADDED VALUE TO ARRAY
	# mean and variance in sections length
	sections_length=numpy.ediff1d(sections)
	variance_sections_length=numpy.var(sections)
	output_array["variance_sections_length"]=variance_sections_length	### ADDED VALUE TO ARRAY
	# number segments
	segments=hdf5_getters.get_segments_start(h5)
	num_segments=len(segments)
	output_array["num_segments"]=num_segments	### ADDED VALUE TO ARRAY
	# mean and variance in segments length
	segments_length=numpy.ediff1d(segments)
	variance_segments_length=numpy.var(segments)
	output_array["variance_segments_length"]=variance_segments_length	### ADDED VALUE TO ARRAY
	# segment loudness max
	segment_loudness_max_array=hdf5_getters.get_segments_loudness_max(h5)
	segment_loudness_max_time_array=hdf5_getters.get_segments_loudness_max_time(h5)
	segment_loudness_max_index=0
	for i in range(len(segment_loudness_max_array)):
		if segment_loudness_max_array[i]>segment_loudness_max_array[segment_loudness_max_index]:
			segment_loudness_max_index=i
	segment_loudness_max=segment_loudness_max_array[segment_loudness_max_index]
	segment_loudness_max_time=segment_loudness_max_time_array[segment_loudness_max_index]
	output_array["segment_loudness_max"]=segment_loudness_max	### ADDED VALUE TO ARRAY
	output_array["segment_loudness_time"]=segment_loudness_max_time	### ADDED VALUE TO ARRAY
			
	# POSSIBLE TODO: use average function instead and weight by segment length
	# segment loudness mean (start)
	segment_loudness_array=hdf5_getters.get_segments_loudness_start(h5)
	segment_loudness_mean=numpy.mean(segment_loudness_array)
	output_array["segment_loudness_mean"]=segment_loudness_mean	### ADDED VALUE TO ARRAY
	# segment loudness variance (start)
	segment_loudness_variance=numpy.var(segment_loudness_array)
	output_array["segment_loudness_variance"]=segment_loudness_variance	### ADDED VALUE TO ARRAY
	# segment pitches
	segment_pitches_array=hdf5_getters.get_segments_pitches(h5)
	segment_pitches_mean=numpy.mean(segment_pitches_array,axis=0).tolist()
	output_array["segment_pitches_mean"]=segment_pitches_mean
	# segment pitches variance (start)
	segment_pitches_variance=numpy.var(segment_pitches_array,axis=0).tolist()
	output_array["segment_pitches_variance"]=segment_pitches_variance
	# segment timbres
	segment_timbres_array=hdf5_getters.get_segments_timbre(h5)
	segment_timbres_mean=numpy.mean(segment_timbres_array,axis=0).tolist()
	output_array["segment_timbres_mean"]=segment_timbres_mean
	# segment timbres variance (start)
	segment_timbres_variance=numpy.var(segment_timbres_array,axis=0).tolist()
	output_array["segment_timbres_variance"]=segment_timbres_variance
	# hotttnesss
	hottness=hdf5_getters.get_song_hotttnesss(h5,0)
	output_array["hottness"]=hottness	### ADDED VALUE TO ARRAY
	# duration-start of fade out
	start_of_fade_out=hdf5_getters.get_start_of_fade_out(h5)
	fade_out=duration-start_of_fade_out
	output_array["fade_out"]=fade_out	### ADDED VALUE TO ARRAY
	# tatums
	tatums=hdf5_getters.get_tatums_start(h5)
	num_tatums=len(tatums)
	output_array["num_tatums"]=num_tatums	### ADDED VALUE TO ARRAY
	# mean and variance in tatums length
	tatums_length=numpy.ediff1d(tatums)
	variance_tatums_length=numpy.var(tatums_length)
	output_array["variance_tatums_length"]=variance_tatums_length	### ADDED VALUE TO ARRAY
	# tempo
	tempo=hdf5_getters.get_tempo(h5)
	output_array["tempo"]=tempo	### ADDED VALUE TO ARRAY
	# time signature
	time_signature=hdf5_getters.get_time_signature(h5)
	output_array["time_signature"]=int(time_signature)	### ADDED VALUE TO ARRAY
	# year
	year=hdf5_getters.get_year(h5)
	output_array["year"]=int(year)	### ADDED VALUE TO ARRAY
	# artist terms
	artist_terms=hdf5_getters.get_artist_terms(h5,0)
	output_array["artist_terms"]=artist_terms.tolist()
	artist_terms_freq=hdf5_getters.get_artist_terms_freq(h5,0)
	output_array["artist_terms_freq"]=artist_terms_freq.tolist()
	artist_name=hdf5_getters.get_artist_name(h5,0)
	output_array["artist_name"]=artist_name
	artist_id=hdf5_getters.get_artist_id(h5,0)
	output_array["artist_id"]=artist_id
	# title
	title=hdf5_getters.get_title(h5,0)
	output_array["title"]=title

	return output_array
Example #15
0
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 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;
         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
            #bars_start = ','.join(str(e) for e in GETTERS.get_bars_start(h5, i)) # array
            #beats_confidence = ','.join(str(e) for e in GETTERS.get_beats_confidence(h5, i)) # array
            #beats_start = ','.join(str(e) for e in GETTERS.get_beats_start(h5, i)) # array
            danceability = GETTERS.get_danceability(h5, i)
            duration = GETTERS.get_duration(h5, i)
            end_of_fade_in = GETTERS.get_end_of_fade_in(h5, i)
            energy = GETTERS.get_energy(h5, i)
            key = GETTERS.get_key(h5, i)
            key_confidence = GETTERS.get_key_confidence(h5, i)
            loudness = GETTERS.get_loudness(h5, i)
            mode = GETTERS.get_mode(h5, i)
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 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)
Example #20
0
            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:
                    cursor.execute("INSERT INTO artist_genres VALUES ('" +
                                   artist_id + "','" + term + "')")
            for tag in mbtags:
                tag = tag.replace("'", "")
                cursor.execute(
                    "SELECT * FROM artist_genres WHERE artist_id='" +
                    artist_id + "' AND genre ='" + tag + "'")
                key = hdf5_getters.get_key(hdf)
                key_confidence = hdf5_getters.get_key_confidence(hdf)
                loudness = hdf5_getters.get_loudness(hdf)
                mode = hdf5_getters.get_mode(hdf)
                mode_confidence = hdf5_getters.get_mode_confidence(hdf)
                start_of_fade_out = hdf5_getters.get_start_of_fade_out(hdf)
                tempo = hdf5_getters.get_tempo(hdf)
                time_signature = hdf5_getters.get_time_signature(hdf)
                time_signature_confidence = hdf5_getters.get_time_signature_confidence(
                    hdf)
                track_id = hdf5_getters.get_track_id(hdf)
                year = hdf5_getters.get_year(hdf)

                similar_artists = hdf5_getters.get_similar_artists(hdf)

                artist_terms = hdf5_getters.get_artist_terms(hdf)
                artist_terms_freq = hdf5_getters.get_artist_terms_freq(hdf)
                artist_terms_weight = hdf5_getters.get_artist_terms_weight(hdf)

                segments_start = hdf5_getters.get_segments_start(hdf)

                segments_confidence = hdf5_getters.get_segments_confidence(hdf)
                segments_pitches = hdf5_getters.get_segments_pitches(hdf)
                segments_timbre = hdf5_getters.get_segments_timbre(hdf)

                segments_loudness_max = hdf5_getters.get_segments_loudness_max(
                    hdf)
                segments_loudness_max_time = hdf5_getters.get_segments_loudness_max_time(
                    hdf)
                segments_loudness_start = hdf5_getters.get_segments_loudness_start(
                    hdf)
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
Example #23
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:
                    cursor.execute("INSERT INTO artist_genres VALUES ('" + artist_id + "','" + term + "')")
            for tag in mbtags:
                tag = tag.replace("'","")
                cursor.execute("SELECT * FROM artist_genres WHERE artist_id='" + artist_id + "' AND genre ='" + tag + "'")
                if cursor.rowcount != 1:
                    cursor.execute("INSERT INTO artist_genres VALUES ('" + artist_id + "','" + tag + "')")

            ''' Store track tuples '''
Example #24
0
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
Example #25
0
 def setGenreList(self, h5File):
     genre = hdf5_getters.get_artist_terms(h5File)
     self.genreList = genre
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;
Example #27
0
 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
 #bars_start = ','.join(str(e) for e in GETTERS.get_bars_start(h5, i)) # array
 #beats_confidence = ','.join(str(e) for e in GETTERS.get_beats_confidence(h5, i)) # array
 #beats_start = ','.join(str(e) for e in GETTERS.get_beats_start(h5, i)) # array
 danceability = GETTERS.get_danceability(h5, i)
 duration = GETTERS.get_duration(h5, i)
 end_of_fade_in = GETTERS.get_end_of_fade_in(h5, i)
 energy = GETTERS.get_energy(h5, i)
 key = GETTERS.get_key(h5, i)
 key_confidence = GETTERS.get_key_confidence(h5, i)
 loudness = GETTERS.get_loudness(h5, i)
 mode = GETTERS.get_mode(h5, i)
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
                if process_completion % 400 == 0:
                    print "done :", process_completion/400.0, "%"
                    process_completion += 1
                else:
                    process_completion += 1

                tempPath = os.path.abspath(os.path.join(root,name))
                h5file = hdf5_getters.open_h5_file_read(tempPath)

                #meta info
                track_id_str = hdf5_getters.get_track_id(h5file)
                song_id_str = hdf5_getters.get_song_id(h5file)
                year = hdf5_getters.get_year(h5file)

                #genre info
                artist_terms = hdf5_getters.get_artist_terms(h5file)
                artist_mbtags = hdf5_getters.get_artist_mbtags(h5file)
                artist_mbtags_count = hdf5_getters.get_artist_mbtags_count(h5file)
                artist_terms_freq = hdf5_getters.get_artist_terms_freq(h5file)
                artist_terms_weight = hdf5_getters.get_artist_terms_weight(h5file)

                #factoring in mbtags counts & thresholding artist_terms
                idx = 0
                for countVal in artist_mbtags_count:
                    for rep in range(0,countVal-1):
                        artist_mbtags = numpy.append(artist_mbtags,artist_mbtags[idx])
                    idx += 1

                for i in range(0,len(artist_terms)):
                    if artist_terms_freq[i]*artist_terms_weight[i] < 0.16: #0.4*0.4 = 0.16
                        artist_terms[i]=""
Example #30
0
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 == 'Hotness'.lower():
                    csvRowString += "Hotness"
                elif attribute == 'Genre'.lower():
                    csvRowString += "Genre"
                elif attribute == 'ArtistLocationId'.lower():
                    csvRowString += "ArtistLocationId"
                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, Hotness, Genre, ArtistLocationId")
        #################################################

        csvAttributeList = re.split('\W+', csvRowString)
        for i, v in enumerate(csvAttributeList):
            csvAttributeList[i] = csvAttributeList[i].lower()
        outputFile1.write("SongNumber,");
        outputFile1.write(csvRowString + "\n");
        csvRowString = ""

    #################################################

    #TODO Enter base folder here
    #Set the basedir here, the root directory from which the search
    #for files stored in a (hierarchical data structure) will originate
    basedir = "MillionSongSubset\data" # "." As the default means the current directory
    ext = ".h5" #Set the extension here. H5 is the extension for HDF5 files.
    #################################################

    counter = 1
    dict = {}
    #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))
            if song.artistLocation not in dict.keys() and song.artistLocation is not "":
                dict[song.artistLocation] = counter
                counter += 1
            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.hotness = str(hdf5_getters.get_song_hotttnesss(songH5File))
            genres = hdf5_getters.get_artist_terms(songH5File)
            if len(genres) > 0:
                song.artist_terms = str(genres[0])
            else:
                song.artist_terms = None
            #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 == 'Hotness'.lower():
                    csvRowString += song.hotness
                elif attribute == 'Genre'.lower():
                    if song.artist_terms != None:
                        csvRowString += song.artist_terms
                elif attribute == 'ArtistLocationId'.lower():
                    if song.artistLocation is not "":
                        csvRowString += str(dict[song.artistLocation])
                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()
                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(
                str(list(hdf5_getters.get_artist_terms_weight(songH5File))))

            temp = hdf5_getters.get_artist_mbtags(songH5File)
            song.artistMBTags = remove_trap_characters(str(list(temp)))
            song.artistMBTagsOuterCount = get_list_length(temp)
            song.artistMBTagsCount = remove_trap_characters(
                str(list(hdf5_getters.get_artist_mbtags_count(songH5File))))
            song.analysisSampleRate = remove_trap_characters(
                str(hdf5_getters.get_analysis_sample_rate(songH5File)))
            song.audioMD5 = remove_trap_characters(
def data_to_flat_file(basedir, ext='.h5'):
    """This function extract the information from the tables and creates the flat file."""
    count = 0
    #song counter
    list_to_write = []
    row_to_write = ""
    writer = csv.writer(open("metadata_wholeA.csv", "wb"))
    for root, dirs, files in os.walk(basedir):
        files = glob.glob(os.path.join(root, '*' + ext))
        for f in files:
            print f  #the name of the file
            h5 = hdf5_getters.open_h5_file_read(f)
            title = hdf5_getters.get_title(h5)
            title = title.replace('"', '')
            comma = title.find(',')  #eliminating commas in the title
            if comma != -1:
                print title
                time.sleep(1)
            album = hdf5_getters.get_release(h5)
            album = album.replace('"', '')  #eliminating commas in the album
            comma = album.find(',')
            if comma != -1:
                print album
                time.sleep(1)
            artist_name = hdf5_getters.get_artist_name(h5)
            comma = artist_name.find(',')
            if comma != -1:
                print artist_name
                time.sleep(1)
            artist_name = artist_name.replace('"',
                                              '')  #eliminating double quotes
            duration = hdf5_getters.get_duration(h5)
            samp_rt = hdf5_getters.get_analysis_sample_rate(h5)
            artist_7digitalid = hdf5_getters.get_artist_7digitalid(h5)
            artist_fam = hdf5_getters.get_artist_familiarity(h5)
            #checking if we get a "nan" if we do we change it to -1
            if numpy.isnan(artist_fam) == True:
                artist_fam = -1
            artist_hotness = hdf5_getters.get_artist_hotttnesss(h5)
            #checking if we get a "nan" if we do we change it to -1
            if numpy.isnan(artist_hotness) == True:
                artist_hotness = -1
            artist_id = hdf5_getters.get_artist_id(h5)
            artist_lat = hdf5_getters.get_artist_latitude(h5)
            #checking if we get a "nan" if we do we change it to -1
            if numpy.isnan(artist_lat) == True:
                artist_lat = -1
            artist_loc = hdf5_getters.get_artist_location(h5)
            #checks artist_loc to see if it is a hyperlink if it is set as empty string
            artist_loc = artist_loc.replace(",", "\,")
            if artist_loc.startswith("<a"):
                artist_loc = ""
            if len(artist_loc) > 100:
                artist_loc = ""
            artist_lon = hdf5_getters.get_artist_longitude(h5)
            #checking if we get a "nan" if we do we change it to -1
            if numpy.isnan(artist_lon) == True:
                artist_lon = -1
            artist_mbid = hdf5_getters.get_artist_mbid(h5)
            artist_pmid = hdf5_getters.get_artist_playmeid(h5)
            audio_md5 = hdf5_getters.get_audio_md5(h5)
            danceability = hdf5_getters.get_danceability(h5)
            #checking if we get a "nan" if we do we change it to -1
            if numpy.isnan(danceability) == True:
                danceability = -1
            end_fade_in = hdf5_getters.get_end_of_fade_in(h5)
            #checking if we get a "nan" if we do we change it to -1
            if numpy.isnan(end_fade_in) == True:
                end_fade_in = -1
            energy = hdf5_getters.get_energy(h5)
            #checking if we get a "nan" if we do we change it to -1
            if numpy.isnan(energy) == True:
                energy = -1
            song_key = hdf5_getters.get_key(h5)
            key_c = hdf5_getters.get_key_confidence(h5)
            #checking if we get a "nan" if we do we change it to -1
            if numpy.isnan(key_c) == True:
                key_c = -1
            loudness = hdf5_getters.get_loudness(h5)
            #checking if we get a "nan" if we do we change it to -1
            if numpy.isnan(loudness) == True:
                loudness = -1
            mode = hdf5_getters.get_mode(h5)
            mode_conf = hdf5_getters.get_mode_confidence(h5)
            #checking if we get a "nan" if we do we change it to -1
            if numpy.isnan(mode_conf) == True:
                mode_conf = -1
            release_7digitalid = hdf5_getters.get_release_7digitalid(h5)
            song_hot = hdf5_getters.get_song_hotttnesss(h5)
            #checking if we get a "nan" if we do we change it to -1
            if numpy.isnan(song_hot) == True:
                song_hot = -1
            song_id = hdf5_getters.get_song_id(h5)
            start_fade_out = hdf5_getters.get_start_of_fade_out(h5)
            tempo = hdf5_getters.get_tempo(h5)
            #checking if we get a "nan" if we do we change it to -1
            if numpy.isnan(tempo) == True:
                tempo = -1
            time_sig = hdf5_getters.get_time_signature(h5)
            time_sig_c = hdf5_getters.get_time_signature_confidence(h5)
            #checking if we get a "nan" if we do we change it to -1
            if numpy.isnan(time_sig_c) == True:
                time_sig_c = -1
            track_id = hdf5_getters.get_track_id(h5)
            track_7digitalid = hdf5_getters.get_track_7digitalid(h5)
            year = hdf5_getters.get_year(h5)
            bars_c = hdf5_getters.get_bars_confidence(h5)
            bars_c_avg = get_avg(bars_c)
            bars_c_max = get_max(bars_c)
            bars_c_min = get_min(bars_c)
            bars_c_stddev = get_stddev(bars_c)
            bars_c_count = get_count(bars_c)
            bars_c_sum = get_sum(bars_c)
            bars_start = hdf5_getters.get_bars_start(h5)
            bars_start_avg = get_avg(bars_start)
            bars_start_max = get_max(bars_start)
            bars_start_min = get_min(bars_start)
            bars_start_stddev = get_stddev(bars_start)
            bars_start_count = get_count(bars_start)
            bars_start_sum = get_sum(bars_start)
            beats_c = hdf5_getters.get_beats_confidence(h5)
            beats_c_avg = get_avg(beats_c)
            beats_c_max = get_max(beats_c)
            beats_c_min = get_min(beats_c)
            beats_c_stddev = get_stddev(beats_c)
            beats_c_count = get_count(beats_c)
            beats_c_sum = get_sum(beats_c)
            beats_start = hdf5_getters.get_beats_start(h5)
            beats_start_avg = get_avg(beats_start)
            beats_start_max = get_max(beats_start)
            beats_start_min = get_min(beats_start)
            beats_start_stddev = get_stddev(beats_start)
            beats_start_count = get_count(beats_start)
            beats_start_sum = get_sum(beats_start)
            sec_c = hdf5_getters.get_sections_confidence(h5)
            sec_c_avg = get_avg(sec_c)
            sec_c_max = get_max(sec_c)
            sec_c_min = get_min(sec_c)
            sec_c_stddev = get_stddev(sec_c)
            sec_c_count = get_count(sec_c)
            sec_c_sum = get_sum(sec_c)
            sec_start = hdf5_getters.get_sections_start(h5)
            sec_start_avg = get_avg(sec_start)
            sec_start_max = get_max(sec_start)
            sec_start_min = get_min(sec_start)
            sec_start_stddev = get_stddev(sec_start)
            sec_start_count = get_count(sec_start)
            sec_start_sum = get_sum(sec_start)
            seg_c = hdf5_getters.get_segments_confidence(h5)
            seg_c_avg = get_avg(seg_c)
            seg_c_max = get_max(seg_c)
            seg_c_min = get_min(seg_c)
            seg_c_stddev = get_stddev(seg_c)
            seg_c_count = get_count(seg_c)
            seg_c_sum = get_sum(seg_c)
            seg_loud_max = hdf5_getters.get_segments_loudness_max(h5)
            seg_loud_max_avg = get_avg(seg_loud_max)
            seg_loud_max_max = get_max(seg_loud_max)
            seg_loud_max_min = get_min(seg_loud_max)
            seg_loud_max_stddev = get_stddev(seg_loud_max)
            seg_loud_max_count = get_count(seg_loud_max)
            seg_loud_max_sum = get_sum(seg_loud_max)
            seg_loud_max_time = hdf5_getters.get_segments_loudness_max_time(h5)
            seg_loud_max_time_avg = get_avg(seg_loud_max_time)
            seg_loud_max_time_max = get_max(seg_loud_max_time)
            seg_loud_max_time_min = get_min(seg_loud_max_time)
            seg_loud_max_time_stddev = get_stddev(seg_loud_max_time)
            seg_loud_max_time_count = get_count(seg_loud_max_time)
            seg_loud_max_time_sum = get_sum(seg_loud_max_time)
            seg_loud_start = hdf5_getters.get_segments_loudness_start(h5)
            seg_loud_start_avg = get_avg(seg_loud_start)
            seg_loud_start_max = get_max(seg_loud_start)
            seg_loud_start_min = get_min(seg_loud_start)
            seg_loud_start_stddev = get_stddev(seg_loud_start)
            seg_loud_start_count = get_count(seg_loud_start)
            seg_loud_start_sum = get_sum(seg_loud_start)
            seg_pitch = hdf5_getters.get_segments_pitches(h5)
            pitch_size = len(seg_pitch)
            seg_start = hdf5_getters.get_segments_start(h5)
            seg_start_avg = get_avg(seg_start)
            seg_start_max = get_max(seg_start)
            seg_start_min = get_min(seg_start)
            seg_start_stddev = get_stddev(seg_start)
            seg_start_count = get_count(seg_start)
            seg_start_sum = get_sum(seg_start)
            seg_timbre = hdf5_getters.get_segments_timbre(h5)
            tatms_c = hdf5_getters.get_tatums_confidence(h5)
            tatms_c_avg = get_avg(tatms_c)
            tatms_c_max = get_max(tatms_c)
            tatms_c_min = get_min(tatms_c)
            tatms_c_stddev = get_stddev(tatms_c)
            tatms_c_count = get_count(tatms_c)
            tatms_c_sum = get_sum(tatms_c)
            tatms_start = hdf5_getters.get_tatums_start(h5)
            tatms_start_avg = get_avg(tatms_start)
            tatms_start_max = get_max(tatms_start)
            tatms_start_min = get_min(tatms_start)
            tatms_start_stddev = get_stddev(tatms_start)
            tatms_start_count = get_count(tatms_start)
            tatms_start_sum = get_sum(tatms_start)

            #Getting the genres
            genre_set = 0  #flag to see if the genre has been set or not
            art_trm = hdf5_getters.get_artist_terms(h5)
            trm_freq = hdf5_getters.get_artist_terms_freq(h5)
            trn_wght = hdf5_getters.get_artist_terms_weight(h5)
            a_mb_tags = hdf5_getters.get_artist_mbtags(h5)
            genre_indexes = get_genre_indexes(
                trm_freq)  #index of the highest freq
            final_genre = []
            genres_so_far = []
            for i in range(len(genre_indexes)):
                genre_tmp = get_genre(
                    art_trm, genre_indexes[i]
                )  #genre that corresponds to the highest freq
                genres_so_far = genre_dict.get_genre_in_dict(
                    genre_tmp)  #getting the genre from the dictionary
                if len(genres_so_far) != 0:
                    for i in genres_so_far:
                        final_genre.append(i)
                        genre_set = 1  #genre was found in dictionary

            if genre_set == 1:
                col_num = []

                for genre in final_genre:
                    column = int(
                        genre)  #getting the column number of the genre
                    col_num.append(column)

                genre_array = genre_columns(col_num)  #genre array
            else:
                genre_array = genre_columns(
                    -1)  #the genre was not found in the dictionary

            transpose_pitch = seg_pitch.transpose(
            )  #this is to tranpose the matrix,so we can have 12 rows
            #arrays containing the aggregate values of the 12 rows
            seg_pitch_avg = []
            seg_pitch_max = []
            seg_pitch_min = []
            seg_pitch_stddev = []
            seg_pitch_count = []
            seg_pitch_sum = []
            i = 0
            #Getting the aggregate values in the pitches array
            for row in transpose_pitch:
                seg_pitch_avg.append(get_avg(row))
                seg_pitch_max.append(get_max(row))
                seg_pitch_min.append(get_min(row))
                seg_pitch_stddev.append(get_stddev(row))
                seg_pitch_count.append(get_count(row))
                seg_pitch_sum.append(get_sum(row))
                i = i + 1

            #extracting information from the timbre array
            transpose_timbre = seg_pitch.transpose(
            )  #tranposing matrix, to have 12 rows
            #arrays containing the aggregate values of the 12 rows
            seg_timbre_avg = []
            seg_timbre_max = []
            seg_timbre_min = []
            seg_timbre_stddev = []
            seg_timbre_count = []
            seg_timbre_sum = []
            i = 0
            for row in transpose_timbre:
                seg_timbre_avg.append(get_avg(row))
                seg_timbre_max.append(get_max(row))
                seg_timbre_min.append(get_min(row))
                seg_timbre_stddev.append(get_stddev(row))
                seg_timbre_count.append(get_count(row))
                seg_timbre_sum.append(get_sum(row))
                i = i + 1

        #Writing to the flat file
            writer.writerow([
                title, album, artist_name, year, duration, seg_start_count,
                tempo
            ])

            h5.close()
            count = count + 1
            print count
Example #33
0
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;
Example #34
0
def classify(h5):
    output_array = {}
    # duration
    duration = hdf5_getters.get_duration(h5)
    output_array["duration"] = duration  ### ADDED VALUE TO ARRAY
    # number of bars
    bars = hdf5_getters.get_bars_start(h5)
    num_bars = len(bars)
    output_array["num_bars"] = num_bars  ### ADDED VALUE TO ARRAY
    # mean and variance in bar length
    bar_length = numpy.ediff1d(bars)
    variance_bar_length = numpy.var(bar_length)
    output_array[
        "variance_bar_length"] = variance_bar_length  ### ADDED VALUE TO ARRAY
    # number of beats
    beats = hdf5_getters.get_beats_start(h5)
    num_beats = len(beats)
    output_array["num_beats"] = num_beats  ### ADDED VALUE TO ARRAY
    # mean and variance in beats length
    beats_length = numpy.ediff1d(beats)
    variance_beats_length = numpy.var(bar_length)
    output_array[
        "variance_beats_length"] = variance_beats_length  ### ADDED VALUE TO ARRAY
    # danceability
    danceability = hdf5_getters.get_danceability(h5)
    output_array["danceability"] = danceability  ### ADDED VALUE TO ARRAY
    # end of fade in
    end_of_fade_in = hdf5_getters.get_end_of_fade_in(h5)
    output_array["end_of_fade_in"] = end_of_fade_in  ### ADDED VALUE TO ARRAY
    # energy
    energy = hdf5_getters.get_energy(h5)
    output_array["energy"] = energy  ### ADDED VALUE TO ARRAY
    # key
    key = hdf5_getters.get_key(h5)
    output_array["key"] = int(key)  ### ADDED VALUE TO ARRAY
    # loudness
    loudness = hdf5_getters.get_loudness(h5)
    output_array["loudness"] = loudness  ### ADDED VALUE TO ARRAY
    # mode
    mode = hdf5_getters.get_mode(h5)
    output_array["mode"] = int(mode)  ### ADDED VALUE TO ARRAY
    # number sections
    sections = hdf5_getters.get_sections_start(h5)
    num_sections = len(sections)
    output_array["num_sections"] = num_sections  ### ADDED VALUE TO ARRAY
    # mean and variance in sections length
    sections_length = numpy.ediff1d(sections)
    variance_sections_length = numpy.var(sections)
    output_array[
        "variance_sections_length"] = variance_sections_length  ### ADDED VALUE TO ARRAY
    # number segments
    segments = hdf5_getters.get_segments_start(h5)
    num_segments = len(segments)
    output_array["num_segments"] = num_segments  ### ADDED VALUE TO ARRAY
    # mean and variance in segments length
    segments_length = numpy.ediff1d(segments)
    variance_segments_length = numpy.var(segments)
    output_array[
        "variance_segments_length"] = variance_segments_length  ### ADDED VALUE TO ARRAY
    # segment loudness max
    segment_loudness_max_array = hdf5_getters.get_segments_loudness_max(h5)
    segment_loudness_max_time_array = hdf5_getters.get_segments_loudness_max_time(
        h5)
    segment_loudness_max_index = 0
    for i in range(len(segment_loudness_max_array)):
        if segment_loudness_max_array[i] > segment_loudness_max_array[
                segment_loudness_max_index]:
            segment_loudness_max_index = i
    segment_loudness_max = segment_loudness_max_array[
        segment_loudness_max_index]
    segment_loudness_max_time = segment_loudness_max_time_array[
        segment_loudness_max_index]
    output_array[
        "segment_loudness_max"] = segment_loudness_max  ### ADDED VALUE TO ARRAY
    output_array[
        "segment_loudness_time"] = segment_loudness_max_time  ### ADDED VALUE TO ARRAY

    # POSSIBLE TODO: use average function instead and weight by segment length
    # segment loudness mean (start)
    segment_loudness_array = hdf5_getters.get_segments_loudness_start(h5)
    segment_loudness_mean = numpy.mean(segment_loudness_array)
    output_array[
        "segment_loudness_mean"] = segment_loudness_mean  ### ADDED VALUE TO ARRAY
    # segment loudness variance (start)
    segment_loudness_variance = numpy.var(segment_loudness_array)
    output_array[
        "segment_loudness_variance"] = segment_loudness_variance  ### ADDED VALUE TO ARRAY
    # segment pitches
    segment_pitches_array = hdf5_getters.get_segments_pitches(h5)
    segment_pitches_mean = numpy.mean(segment_pitches_array, axis=0).tolist()
    output_array["segment_pitches_mean"] = segment_pitches_mean
    # segment pitches variance (start)
    segment_pitches_variance = numpy.var(segment_pitches_array,
                                         axis=0).tolist()
    output_array["segment_pitches_variance"] = segment_pitches_variance
    # segment timbres
    segment_timbres_array = hdf5_getters.get_segments_timbre(h5)
    segment_timbres_mean = numpy.mean(segment_timbres_array, axis=0).tolist()
    output_array["segment_timbres_mean"] = segment_timbres_mean
    # segment timbres variance (start)
    segment_timbres_variance = numpy.var(segment_timbres_array,
                                         axis=0).tolist()
    output_array["segment_timbres_variance"] = segment_timbres_variance
    # hotttnesss
    hottness = hdf5_getters.get_song_hotttnesss(h5, 0)
    output_array["hottness"] = hottness  ### ADDED VALUE TO ARRAY
    # duration-start of fade out
    start_of_fade_out = hdf5_getters.get_start_of_fade_out(h5)
    fade_out = duration - start_of_fade_out
    output_array["fade_out"] = fade_out  ### ADDED VALUE TO ARRAY
    # tatums
    tatums = hdf5_getters.get_tatums_start(h5)
    num_tatums = len(tatums)
    output_array["num_tatums"] = num_tatums  ### ADDED VALUE TO ARRAY
    # mean and variance in tatums length
    tatums_length = numpy.ediff1d(tatums)
    variance_tatums_length = numpy.var(tatums_length)
    output_array[
        "variance_tatums_length"] = variance_tatums_length  ### ADDED VALUE TO ARRAY
    # tempo
    tempo = hdf5_getters.get_tempo(h5)
    output_array["tempo"] = tempo  ### ADDED VALUE TO ARRAY
    # time signature
    time_signature = hdf5_getters.get_time_signature(h5)
    output_array["time_signature"] = int(
        time_signature)  ### ADDED VALUE TO ARRAY
    # year
    year = hdf5_getters.get_year(h5)
    output_array["year"] = int(year)  ### ADDED VALUE TO ARRAY
    # artist terms
    artist_terms = hdf5_getters.get_artist_terms(h5, 0)
    output_array["artist_terms"] = artist_terms.tolist()
    artist_terms_freq = hdf5_getters.get_artist_terms_freq(h5, 0)
    output_array["artist_terms_freq"] = artist_terms_freq.tolist()
    artist_name = hdf5_getters.get_artist_name(h5, 0)
    output_array["artist_name"] = artist_name
    artist_id = hdf5_getters.get_artist_id(h5, 0)
    output_array["artist_id"] = artist_id
    # title
    title = hdf5_getters.get_title(h5, 0)
    output_array["title"] = title

    return output_array
Example #35
0
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)
Example #36
0
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()
Example #37
0
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)