def feat_from_file(path): """ Extract a list of features in an array, already converted to string """ feats = [] h5 = GETTERS.open_h5_file_read(path) # basic info feats.append(GETTERS.get_track_id(h5)) feats.append(GETTERS.get_artist_name(h5).decode().replace(',', '')) feats.append(GETTERS.get_title(h5).decode().replace(',', '')) feats.append(GETTERS.get_loudness(h5)) feats.append(GETTERS.get_tempo(h5)) feats.append(GETTERS.get_time_signature(h5)) feats.append(GETTERS.get_key(h5)) feats.append(GETTERS.get_mode(h5)) feats.append(GETTERS.get_duration(h5)) # timbre timbre = GETTERS.get_segments_timbre(h5) avg_timbre = np.average(timbre, axis=0) for k in avg_timbre: feats.append(k) var_timbre = np.var(timbre, axis=0) for k in var_timbre: feats.append(k) # done with h5 file h5.close() # makes sure we return strings feats = map(lambda x: str(x), feats) return feats
def ingest(self): # Browse MSD summary file es_bulk_docs = {} msd_id = "" sng_idx = 0 for h5_fd, sng_idx in self.track_generator.get_track(): msd_doc = {} msd_id = hdf5_getters.get_track_id(h5_fd, sng_idx) for getter in getters: field_name = getter.split("get_")[-1] msd_field_name = "msd_" + field_name # prefixed for ES storage try: msd_field_value = hdf5_getters.__getattribute__(getter)(h5_fd, sng_idx) # Type conversions msd_field_value = Ingestor.convert_type(msd_field_value) msd_doc[msd_field_name] = msd_field_value except AttributeError, e: logger.debug("ERROR. AttributeError. {}".format(e)) pass es_bulk_docs[msd_id] = msd_doc # Ingest bulk if size is enough if len(es_bulk_docs) == es_bulk_size: logger.debug("{} files read. Bulk ingest.".format(sng_idx + 1)) logger.debug("Last MSD id read: {}".format(msd_id)) self.es_helper.ingest_to_es(es_bulk_docs) es_bulk_docs = {}
def feat_from_file(path): feats = [] h5 = GETTERS.open_h5_file_read(path) feats.append( GETTERS.get_track_id(h5) ) feats.append( GETTERS.get_title(h5) ) feats.append( GETTERS.get_artist_name(h5) ) feats.append( GETTERS.get_year(h5) ) feats.append( GETTERS.get_loudness(h5) ) feats.append( GETTERS.get_tempo(h5) ) feats.append( GETTERS.get_time_signature(h5) ) feats.append( GETTERS.get_key(h5) ) feats.append( GETTERS.get_mode(h5) ) feats.append( GETTERS.get_duration(h5) ) #timbre timbre = GETTERS.get_segments_timbre(h5) avg_timbre = np.average(timbre, axis=0) for k in avg_timbre: feats.append(k) var_timbre = np.var(timbre, axis=0) for k in var_timbre: feats.append(k) h5.close() return feats
def feat_from_file(path): """ Extract a list of features in an array, already converted to string """ feats = [] h5 = GETTERS.open_h5_file_read(path) # basic info feats.append( GETTERS.get_track_id(h5) ) feats.append( GETTERS.get_artist_name(h5).replace(',','') ) feats.append( GETTERS.get_title(h5).replace(',','') ) feats.append( GETTERS.get_loudness(h5) ) feats.append( GETTERS.get_tempo(h5) ) feats.append( GETTERS.get_time_signature(h5) ) feats.append( GETTERS.get_key(h5) ) feats.append( GETTERS.get_mode(h5) ) feats.append( GETTERS.get_duration(h5) ) # timbre timbre = GETTERS.get_segments_timbre(h5) avg_timbre = np.average(timbre,axis=0) for k in avg_timbre: feats.append(k) var_timbre = np.var(timbre,axis=0) for k in var_timbre: feats.append(k) # done with h5 file h5.close() # makes sure we return strings feats = map(lambda x: str(x), feats) return feats
def get_all_examples(basedir, genre_dict, ext='.h5'): """ From a base directory, goes through all subdirectories, and grabs all songs and their features and puts them into a pandas dataframe INPUT basedir - base directory of the dataset genre_dict - a dictionary mapping track id to genre based tagraum dataset ext - extension, .h5 by default RETURN dataframe containing all song examples """ features_vs_genre = pd.DataFrame() # iterate over all files in all subdirectories for root, dirs, files in os.walk(basedir): files = glob.glob(os.path.join(root, '*' + ext)) # # count files # count += len(files) # apply function to all files for f in files: h5 = GETTERS.open_h5_file_read(f) song_id = GETTERS.get_track_id(h5).decode('utf-8') if (song_id in genre_dict): genre = genre_dict[song_id] year = GETTERS.get_year(h5) duration = GETTERS.get_duration(h5) end_of_fade_in = GETTERS.get_end_of_fade_in(h5) loudness = GETTERS.get_loudness(h5) song_hotttnesss = GETTERS.get_song_hotttnesss(h5) tempo = GETTERS.get_tempo(h5) key = GETTERS.get_key(h5) key_confidence = GETTERS.get_key_confidence(h5) mode = GETTERS.get_mode(h5) mode_confidence = GETTERS.get_mode_confidence(h5) time_signature = GETTERS.get_time_signature(h5) time_signature_confidence = GETTERS.get_time_signature_confidence( h5) artist_name = GETTERS.get_artist_name(h5) title = GETTERS.get_title(h5) # length of sections_start array gives us number of start num_sections = len(GETTERS.get_sections_start(h5)) num_segments = len(GETTERS.get_segments_confidence(h5)) example = pd.DataFrame( data=[ (artist_name, title, song_id, genre, year, key, key_confidence, mode, mode_confidence, time_signature, time_signature_confidence, duration, end_of_fade_in, loudness, song_hotttnesss, tempo, num_sections) ], columns=[ 'artist_name', 'title', 'song_id', 'genre', 'year', 'key', 'key_confidence', 'mode', 'mode_confidence', 'time_signature', 'time_signature_confidence', 'duration', 'end_of_fade_in', 'loudness', 'song_hotttnesss', 'tempo', 'num_segments' ]) features_vs_genre = features_vs_genre.append(example) h5.close() return features_vs_genre
def func_to_desired_song_data(filename): h5 = GETTERS.open_h5_file_read(filename) track_id = GETTERS.get_track_id(h5) for song in random_songs: if song[0] == track_id: print("FOUND ONE!") title = replace_characters(GETTERS.get_title(h5)) artist = replace_characters(GETTERS.get_artist_name(h5)) year = GETTERS.get_year(h5) tempo = GETTERS.get_tempo(h5) key = GETTERS.get_key(h5) loudness = GETTERS.get_loudness(h5) energy = GETTERS.get_energy(h5) danceability = GETTERS.get_danceability(h5) time_signature = GETTERS.get_time_signature(h5) mode = GETTERS.get_mode(h5) hotttness = GETTERS.get_song_hotttnesss(h5) song_data = { 'title': title, 'artist': artist, 'year': year, 'tempo': tempo, 'key': key, 'loudness': loudness, 'energy': energy, 'danceability': danceability, 'time_signature': time_signature, 'mode': mode, 'hotttness': hotttness } all_the_data.append(song_data) h5.close()
def extract_features(filename): h5 = hdf5_getters.open_h5_file_read(filename) f = [None] * len(features) f[features.index('track_id')] = hdf5_getters.get_track_id(h5, 0).item() f[features.index('song_id')] = hdf5_getters.get_song_id(h5, 0).item() f[features.index('hotttnesss')] = hdf5_getters.get_artist_hotttnesss( h5, 0).item() f[features.index('danceability')] = hdf5_getters.get_danceability( h5, 0).item() f[features.index('duration')] = hdf5_getters.get_duration(h5, 0).item() f[features.index('key')] = hdf5_getters.get_key(h5, 0).item() f[features.index('energy')] = hdf5_getters.get_energy(h5, 0).item() f[features.index('loudness')] = hdf5_getters.get_loudness(h5, 0).item() f[features.index('year')] = hdf5_getters.get_year(h5, 0).item() f[features.index('time_signature')] = hdf5_getters.get_time_signature( h5, 0).item() f[features.index('tempo')] = hdf5_getters.get_tempo(h5, 0).item() tags = '' for tag in hdf5_getters.get_artist_terms(h5): tags += ('%s|' % tag) # Remove trailing pipe. tags = tags[:len(tags) - 1] f[features.index('tags')] = tags h5.close() return f
def 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)
def map(line): h5 = hdf5_getters.open_h5_file_read(line) if(h5): output_array=classifiers_base.classify(h5) yield(str(hdf5_getters.get_track_id(h5,0)),json.dumps(output_array)) h5.close() del output_array gc.collect()
def get_geography_information(h5file): h5 = GETTERS.open_h5_file_read(h5file) track_id = GETTERS.get_track_id(h5) artist_location = GETTERS.get_artist_location(h5) artist_latitude = GETTERS.get_artist_latitude(h5) artist_longitude = GETTERS.get_artist_longitude(h5) h5.close() return np.array([track_id, artist_location, artist_latitude, artist_longitude])
def get_geography_information(h5file): h5 = GETTERS.open_h5_file_read(h5file) track_id = GETTERS.get_track_id(h5) artist_location = GETTERS.get_artist_location(h5) artist_latitude = GETTERS.get_artist_latitude(h5) artist_longitude = GETTERS.get_artist_longitude(h5) h5.close() return np.array( [track_id, artist_location, artist_latitude, artist_longitude])
def process_filelist_train(filelist=None,testsongs=None,tmpfilename=None): """ Main function, process all files in the list (as long as their track_id is not in testsongs) INPUT filelist - a list of song files testsongs - set of track ID that we should not use tmpfilename - where to save our processed features """ # sanity check for arg in locals().values(): assert not arg is None,'process_filelist_train, missing an argument, something still None' if os.path.isfile(tmpfilename): print 'ERROR: file',tmpfilename,'already exists.' return # dimension fixed (12-dimensional timbre vector) ndim = 12 finaldim = 90 # create outputfile output = tables.openFile(tmpfilename, mode='a') group = output.createGroup("/",'data','TMP FILE FOR ARTIST RECOGNITION') output.createEArray(group,'feats',tables.Float64Atom(shape=()),(0,finaldim),'', expectedrows=len(filelist)) output.createEArray(group,'artist_id',tables.StringAtom(18,shape=()),(0,),'', expectedrows=len(filelist)) # iterate over files cnt_f = 0 for f in filelist: cnt_f += 1 # verbose if cnt_f % 50000 == 0: print 'training... checking file #',cnt_f # check what file/song is this h5 = GETTERS.open_h5_file_read(f) artist_id = GETTERS.get_artist_id(h5) track_id = GETTERS.get_track_id(h5) if track_id in testsongs: # just in case, but should not be necessary print 'Found test track_id during training? weird.',track_id h5.close() continue # extract features, then close file processed_feats = compute_features(h5) h5.close() if processed_feats is None: continue # save features to tmp file output.root.data.artist_id.append( np.array( [artist_id] ) ) output.root.data.feats.append( processed_feats ) # we're done, close output output.close() return
def func_to_get_desired_values(filename, returnValue = False): """ This function does 3 simple things: - open the song file - get the elements we want and put them in - close the file INPUT : filename - The name of the h5 file to be loaded """ global all_desired_data # Open file h5 = GETTERS.open_h5_file_read(filename) # Create and fill a record record = [] for element in elementsRequested: result = getattr(GETTERS, element)(h5) try: if result == '': result = 'Adlen - void' except: pass try: if isinstance(result, np.ndarray): if len(result) > 1: result = float(np.mean(result)) else: result = '' except: try: result = float(result) except: pass record.append(result) song_id = GETTERS.get_track_id(h5) artist_name = GETTERS.get_artist_name(h5) title = GETTERS.get_title(h5) artist_mbtags = GETTERS.get_artist_mbtags(h5) release = GETTERS.get_release(h5) song_id = unicode(song_id.decode('utf-8')) title = unicode(title.decode('utf-8')) artist_name = unicode(artist_name.decode('utf-8')) if not returnValue: all_desired_data.append([[[song_id, title, artist_name, elementsRequested], artist_name, title, artist_mbtags, release], record]) h5.close() if returnValue: return [[[song_id, title, artist_name, elementsRequested], artist_name, title, artist_mbtags, release], record]
def func_to_get_tags(filename): """ This function does 3 simple things: - open the song file - get artist ID and put it - close the file """ h5 = GETTERS.open_h5_file_read(filename) track_id = GETTERS.get_track_id(h5) tags = GETTERS.get_artist_mbtags(h5) if track_id in ids: for tag in tags: all_tags[tag] += 1 h5.close()
def get_url(h5_file): artist_name = GETTERS.get_artist_name(h5_file) track_name = GETTERS.get_title(h5_file) echo_nest_id = GETTERS.get_track_id(h5_file).lower() if echo_nest_id >= 0: preview = get_preview_from_trackid(echo_nest_id) if preview != '': return preview res = get_trackid_from_text_search(track_name, artistname=artist_name) if len(res) > 0: closest_track = get_closest_track(res, track_name) preview = get_preview_from_trackid(closest_track['id']) return preview return None
def getTrackInfo(starting_num): my_list = [] f = hdf5_getters.open_h5_file_read(filepath) progress_bar = tqdm(range(tracks_per_thread)) for iteration in progress_bar: i = int(iteration) + (starting_num*tracks_per_thread) track_id = hdf5_getters.get_track_id(f, i).decode() if track_id not in lyric_track_ids_set: continue # skip it an go on artist_name = hdf5_getters.get_artist_name(f, i).decode() duration = hdf5_getters.get_duration(f, i) loudness = hdf5_getters.get_loudness(f, i) tempo = hdf5_getters.get_tempo(f, i) title = hdf5_getters.get_title(f, i).decode() year = hdf5_getters.get_year(f, i) long_list = [track_id, artist_name, duration, loudness, tempo, title, year] my_list.append(long_list) progress_bar.set_description("Iteration %d" % i) f.close() return my_list
def get_all_data(target, basedir, ext='.h5') : # header target.write("%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\n" % ( "track_id", "song_id", "title", "artist_name", "artist_location", "artist_hotttnesss", "release", "year", "song_hotttnesss", "danceability", "duration", "loudness", "sample_rate", "tempo" )) count = 0 for root, dirs, files in os.walk(basedir): files = glob.glob(os.path.join(root,'*'+ext)) for f in files: for line in f: new_file = open("tmp.txt", 'w') new_file.write(line) h5 = hdf5_getters.open_h5_file_read(new_file) target.write("%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\n" % ( hdf5_getters.get_track_id(h5), hdf5_getters.get_song_id(h5), hdf5_getters.get_title(h5), hdf5_getters.get_artist_name(h5), hdf5_getters.get_artist_location(h5), hdf5_getters.get_artist_hotttnesss(h5), hdf5_getters.get_release(h5), hdf5_getters.get_year(h5), hdf5_getters.get_song_hotttnesss(h5), hdf5_getters.get_danceability(h5), hdf5_getters.get_duration(h5), hdf5_getters.get_loudness(h5), hdf5_getters.get_analysis_sample_rate(h5), hdf5_getters.get_tempo(h5) )) # show progress count += 1 print "%d/10000" % (count) h5.close()
def get_all_attributes(filename): """ This function does 3 simple things: - open the song file - get all required attributes - write it to a csv file - close the files """ with open('attributes.csv', 'a') as csvfile: try: # let's apply the previous function to all files csvwriter = csv.writer(csvfile, delimiter='\t') h5 = GETTERS.open_h5_file_read(filename) RESULTS = [] RESULTS.append(GETTERS.get_year(h5)) RESULTS.append(GETTERS.get_artist_id(h5)) RESULTS.append(GETTERS.get_artist_name(h5)) RESULTS.append(GETTERS.get_artist_mbid(h5)) RESULTS.append(convert_terms(GETTERS.get_artist_terms(h5))) RESULTS.append(GETTERS.get_artist_hotttnesss(h5)) RESULTS.append(GETTERS.get_artist_latitude(h5)) RESULTS.append(GETTERS.get_artist_longitude(h5)) RESULTS.append(GETTERS.get_artist_familiarity(h5)) RESULTS.append(GETTERS.get_danceability(h5)) RESULTS.append(GETTERS.get_duration(h5)) RESULTS.append(GETTERS.get_energy(h5)) RESULTS.append(GETTERS.get_loudness(h5)) RESULTS.append(GETTERS.get_song_hotttnesss(h5)) RESULTS.append(GETTERS.get_song_id(h5)) RESULTS.append(GETTERS.get_tempo(h5)) RESULTS.append(GETTERS.get_time_signature(h5)) RESULTS.append(GETTERS.get_title(h5)) RESULTS.append(GETTERS.get_track_id(h5)) RESULTS.append(GETTERS.get_release(h5)) csvwriter.writerow(RESULTS) h5.close() except AttributeError: pass
def func_to_get_track_data(filename): h5 = GETTERS.open_h5_file_read(filename) track_id = GETTERS.get_track_id(h5) funcs = [ GETTERS.get_duration, GETTERS.get_key, GETTERS.get_loudness, GETTERS.get_mode, GETTERS.get_tempo, GETTERS.get_time_signature ] segment_funcs = [ GETTERS.get_segments_pitches, GETTERS.get_segments_timbre, GETTERS.get_segments_loudness_max, GETTERS.get_segments_loudness_max_time ] if track_id in tracks: row_data = [track_id] for func in funcs: row_data.append(func(h5)) for func in segment_funcs: segment_mat = func(h5) row_data += condense_segments(segment_mat, new_size=num_segments) list_of_rows.append(row_data) h5.close() return None
def feat_from_file(path): """ Extract a list of features in an array, already converted to string """ feats = [] h5 = GETTERS.open_h5_file_read(path) # basic info feats.append(GETTERS.get_track_id(h5)) #feats.append( GETTERS.get_artist_name(h5).replace(',','') ) #feats.append( GETTERS.get_title(h5).replace(',','') ) feats.append(GETTERS.get_loudness(h5)) feats.append(GETTERS.get_tempo(h5)) feats.append(GETTERS.get_time_signature(h5)) feats.append(GETTERS.get_key(h5)) feats.append(GETTERS.get_mode(h5)) feats.append(GETTERS.get_duration(h5)) feats.append(GETTERS.get_hotnesss(h5)) segments_loudness = np.asarray(GETTERS.get_segments_loudness_max(h5)) max_segment_indice = np.argmax(segments_loudness) # timbre timbre = GETTERS.get_segments_timbre(h5) max_segment_timbre = timbre[max_segment_indice, :] avg_timbre = np.average(timbre, axis=0) for k in avg_timbre: feats.append(k) var_timbre = np.var(timbre, axis=0) for k in var_timbre: feats.append(k) for k in max_segment_timbre: feats.append(k) # done with h5 file h5.close() # makes sure we return strings feats = [str(x) for x in feats] return feats
def get_all_data(dir,ext,outDir): for root, dirs, files in os.walk(dir): files = glob.glob(os.path.join(root,'*'+ext)) for f in files: h5 = get.open_h5_file_read(f) keys = {} keys['trackId'] = get.get_track_id(h5) #keys['analysisSampleRate'] = get.get_analysis_sample_rate(h5) #keys['artistMbTags'] = arrToStr(get.get_artist_mbtags(h5)) #keys['artistMbId'] = get.get_artist_mbid(h5) #keys['artistName'] = get.get_artist_name(h5) #keys['artistPlayMeId'] = get.get_artist_playmeid(h5) #keys['artistTermsWeightArr'] = arrToStr(get.get_artist_terms_weight(h5)) #array #keys['artistTermsFreqArr'] = arrToStr(get.get_artist_terms_freq(h5)) #array #keys['artistTermsArr'] = arrToStr(get.get_artist_terms(h5)) # array""" #keys['audioMd5'] = get.get_audio_md5(h5) #keys['barsConfidence'] = arrToStr(get.get_bars_confidence(h5)) # #keys['barsStart'] = arrToStr(get.get_bars_start(h5)) # #keys['beatsConfidence'] = arrToStr(get.get_beats_confidence(h5)) # #keys['beatsStart']= arrToStr(get.get_beats_start(h5)) # #keys['danceability'] = get.get_danceability(h5) #keys['duration'] = get.get_duration(h5) #keys['endofFadeIn'] = get.get_end_of_fade_in(h5) #keys['energy'] = get.get_energy(h5) #keys['key'] = get.get_key(h5) keys['loudness'] = get.get_loudness(h5) #keys['keyConfidence'] = get.get_key_confidence(h5) #keys['mode'] = get.get_mode(h5) #keys['release'] = get.get_release(h5) #keys['release7DigitalId'] = get.get_release_7digitalid(h5) #keys['modeConfidence'] = get.get_mode_confidence(h5) #keys['sectionsConfidenceArr'] = arrToStr(get.get_sections_confidence(h5)) # #keys['sectionsStartArr'] = arrToStr(get.get_sections_start(h5)) #Segments data begin keys['segmentsStartArr'] = arrToStr(get.get_segments_start(h5)) # #keys['segmentsConfidenceArr'] = arrToStr(get.get_segments_confidence(h5)) # #keys['segmentsLoudnessMaxArr'] = arrToStr(get.get_segments_loudness_max_time(h5)) # #keys['segmentsLoudnessMaxTimeArr'] = arrToStr(get.get_segments_loudness_max_time(h5)) # #keys['segmentsLoudnessStartArr'] = arrToStr(get.get_segments_loudness_start(h5)) # keys['segmentsPitchesArr'] = arrToStr((np.array(get.get_segments_pitches(h5))).flatten()) # keys['segmentsTimbreArr'] = arrToStr((np.array(get.get_segments_timbre(h5))).flatten()) #Timbre data #Segments data End #keys['similarArtists'] = arrToStr(get.get_similar_artists(h5)) #keys['songHotness'] = get.get_song_hotttnesss(h5) keys['songId'] = get.get_song_id(h5) #keys['startOfFadeOut'] = get.get_start_of_fade_out(h5) #keys['tatumsConfidence'] = arrToStr(get.get_tatums_confidence(h5)) # #keys['tatumsStart'] = arrToStr(get.get_tatums_start(h5)) # #keys['tempo'] = get.get_tempo(h5) #keys['timeSignature'] = get.get_time_signature(h5) #keys['timeSignatureConfidence'] = get.get_time_signature_confidence(h5) keys['title'] = get.get_title(h5) #keys['track7DigitalId'] = get.get_track_7digitalid(h5) #keys['year'] = get.get_year(h5) with open(outDir,'a') as f: for key in ordering: f.write('{0}\t'.format(keys[key])) f.write('\n') """ for key in keys: print key print "---> " print keys[key] """ h5.close()
counter = 0 file_io_counter = 0 for root, dirs, files in os.walk(os.getcwd()): for name in files: if name.endswith(".h5"): if process_completion % 10000 == 0: print "done :", process_completion/10000.0, "%" process_completion += 1 else: process_completion += 1 tempPath = os.path.abspath(os.path.join(root,name)) h5file = hdf5_getters.open_h5_file_read(tempPath) #meta info track_id_str = hdf5_getters.get_track_id(h5file).replace(",","") song_id_str = hdf5_getters.get_song_id(h5file).replace(",","") title_str = hdf5_getters.get_title(h5file).replace(","," ") artist_name_str = hdf5_getters.get_artist_name(h5file).replace(","," ") artist_location_str = hdf5_getters.get_artist_location(h5file).replace(","," ") # song-level data info duration = hdf5_getters.get_duration(h5file) key = hdf5_getters.get_key(h5file) mode = hdf5_getters.get_mode(h5file) tempo = hdf5_getters.get_tempo(h5file) time_signature = hdf5_getters.get_time_signature(h5file) h5file.close() counter += 1
def func_to_get_track_ids(filename): h5 = GETTERS.open_h5_file_read(filename) id_ = GETTERS.get_track_id(h5) subset_ids.add(id_) h5.close()
def process_filelist_train(filelist=None, testartists=None, tmpfilename=None, npicks=None, winsize=None, finaldim=None, typecompress='picks'): """ Main function, process all files in the list (as long as their artist is not in testartist) INPUT filelist - a list of song files testartists - set of artist ID that we should not use tmpfilename - where to save our processed features npicks - number of segments to pick per song winsize - size of each segment we pick finaldim - how many values do we keep typecompress - one of 'picks' (win of btchroma), 'corrcoef' (correlation coefficients), 'cov' (covariance) """ # sanity check for arg in locals().values(): assert not arg is None, 'process_filelist_train, missing an argument, something still None' if os.path.isfile(tmpfilename): print 'ERROR: file', tmpfilename, 'already exists.' return # create outputfile output = tables.openFile(tmpfilename, mode='a') group = output.createGroup("/", 'data', 'TMP FILE FOR YEAR RECOGNITION') output.createEArray(group, 'feats', tables.Float64Atom(shape=()), (0, finaldim), '', expectedrows=len(filelist)) output.createEArray(group, 'year', tables.IntAtom(shape=()), (0, ), '', expectedrows=len(filelist)) output.createEArray(group, 'track_id', tables.StringAtom(18, shape=()), (0, ), '', expectedrows=len(filelist)) # random projection ndim = 12 # fixed in this dataset if typecompress == 'picks': randproj = RANDPROJ.proj_point5(ndim * winsize, finaldim) elif typecompress == 'corrcoeff' or typecompress == 'cov': randproj = RANDPROJ.proj_point5(ndim * ndim, finaldim) elif typecompress == 'avgcov': randproj = RANDPROJ.proj_point5(90, finaldim) else: assert False, 'Unknown type of compression: ' + str(typecompress) # iterate over files cnt_f = 0 for f in filelist: cnt_f += 1 # verbose if cnt_f % 50000 == 0: print 'training... checking file #', cnt_f # check file h5 = GETTERS.open_h5_file_read(f) artist_id = GETTERS.get_artist_id(h5) year = GETTERS.get_year(h5) track_id = GETTERS.get_track_id(h5) h5.close() if year <= 0 or artist_id in testartists: continue # we have a train artist with a song year, we're good bttimbre = get_bttimbre(f) if typecompress == 'picks': if bttimbre is None: continue # we even have normal features, awesome! processed_feats = CBTF.extract_and_compress(bttimbre, npicks, winsize, finaldim, randproj=randproj) elif typecompress == 'corrcoeff': h5 = GETTERS.open_h5_file_read(f) timbres = GETTERS.get_segments_timbre(h5).T h5.close() processed_feats = CBTF.corr_and_compress(timbres, finaldim, randproj=randproj) elif typecompress == 'cov': h5 = GETTERS.open_h5_file_read(f) timbres = GETTERS.get_segments_timbre(h5).T h5.close() processed_feats = CBTF.cov_and_compress(timbres, finaldim, randproj=randproj) elif typecompress == 'avgcov': h5 = GETTERS.open_h5_file_read(f) timbres = GETTERS.get_segments_timbre(h5).T h5.close() processed_feats = CBTF.avgcov_and_compress(timbres, finaldim, randproj=randproj) else: assert False, 'Unknown type of compression: ' + str(typecompress) # save them to tmp file n_p_feats = processed_feats.shape[0] output.root.data.year.append(np.array([year] * n_p_feats)) output.root.data.track_id.append(np.array([track_id] * n_p_feats)) output.root.data.feats.append(processed_feats) # we're done, close output output.close() return
def data_to_flat_file(basedir,ext='.h5') : """This function extract the information from the tables and creates the flat file.""" count = 0; #song counter list_to_write= [] row_to_write = "" writer = csv.writer(open("metadata_wholeA.csv", "wb")) for root, dirs, files in os.walk(basedir): files = glob.glob(os.path.join(root,'*'+ext)) for f in files: print f #the name of the file h5 = hdf5_getters.open_h5_file_read(f) title = hdf5_getters.get_title(h5) title= title.replace('"','') comma=title.find(',') #eliminating commas in the title if comma != -1: print title time.sleep(1) album = hdf5_getters.get_release(h5) album= album.replace('"','') #eliminating commas in the album comma=album.find(',') if comma != -1: print album time.sleep(1) artist_name = hdf5_getters.get_artist_name(h5) comma=artist_name.find(',') if comma != -1: print artist_name time.sleep(1) artist_name= artist_name.replace('"','') #eliminating double quotes duration = hdf5_getters.get_duration(h5) samp_rt = hdf5_getters.get_analysis_sample_rate(h5) artist_7digitalid = hdf5_getters.get_artist_7digitalid(h5) artist_fam = hdf5_getters.get_artist_familiarity(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(artist_fam) == True: artist_fam=-1 artist_hotness= hdf5_getters.get_artist_hotttnesss(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(artist_hotness) == True: artist_hotness=-1 artist_id = hdf5_getters.get_artist_id(h5) artist_lat = hdf5_getters.get_artist_latitude(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(artist_lat) == True: artist_lat=-1 artist_loc = hdf5_getters.get_artist_location(h5) #checks artist_loc to see if it is a hyperlink if it is set as empty string artist_loc = artist_loc.replace(",", "\,"); if artist_loc.startswith("<a"): artist_loc = "" if len(artist_loc) > 100: artist_loc = "" artist_lon = hdf5_getters.get_artist_longitude(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(artist_lon) == True: artist_lon=-1 artist_mbid = hdf5_getters.get_artist_mbid(h5) artist_pmid = hdf5_getters.get_artist_playmeid(h5) audio_md5 = hdf5_getters.get_audio_md5(h5) danceability = hdf5_getters.get_danceability(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(danceability) == True: danceability=-1 end_fade_in =hdf5_getters.get_end_of_fade_in(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(end_fade_in) == True: end_fade_in=-1 energy = hdf5_getters.get_energy(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(energy) == True: energy=-1 song_key = hdf5_getters.get_key(h5) key_c = hdf5_getters.get_key_confidence(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(key_c) == True: key_c=-1 loudness = hdf5_getters.get_loudness(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(loudness) == True: loudness=-1 mode = hdf5_getters.get_mode(h5) mode_conf = hdf5_getters.get_mode_confidence(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(mode_conf) == True: mode_conf=-1 release_7digitalid = hdf5_getters.get_release_7digitalid(h5) song_hot = hdf5_getters.get_song_hotttnesss(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(song_hot) == True: song_hot=-1 song_id = hdf5_getters.get_song_id(h5) start_fade_out = hdf5_getters.get_start_of_fade_out(h5) tempo = hdf5_getters.get_tempo(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(tempo) == True: tempo=-1 time_sig = hdf5_getters.get_time_signature(h5) time_sig_c = hdf5_getters.get_time_signature_confidence(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(time_sig_c) == True: time_sig_c=-1 track_id = hdf5_getters.get_track_id(h5) track_7digitalid = hdf5_getters.get_track_7digitalid(h5) year = hdf5_getters.get_year(h5) bars_c = hdf5_getters.get_bars_confidence(h5) bars_c_avg= get_avg(bars_c) bars_c_max= get_max(bars_c) bars_c_min = get_min(bars_c) bars_c_stddev= get_stddev(bars_c) bars_c_count = get_count(bars_c) bars_c_sum = get_sum(bars_c) bars_start = hdf5_getters.get_bars_start(h5) bars_start_avg = get_avg(bars_start) bars_start_max= get_max(bars_start) bars_start_min = get_min(bars_start) bars_start_stddev= get_stddev(bars_start) bars_start_count = get_count(bars_start) bars_start_sum = get_sum(bars_start) beats_c = hdf5_getters.get_beats_confidence(h5) beats_c_avg= get_avg(beats_c) beats_c_max= get_max(beats_c) beats_c_min = get_min(beats_c) beats_c_stddev= get_stddev(beats_c) beats_c_count = get_count(beats_c) beats_c_sum = get_sum(beats_c) beats_start = hdf5_getters.get_beats_start(h5) beats_start_avg = get_avg(beats_start) beats_start_max= get_max(beats_start) beats_start_min = get_min(beats_start) beats_start_stddev= get_stddev(beats_start) beats_start_count = get_count(beats_start) beats_start_sum = get_sum(beats_start) sec_c = hdf5_getters.get_sections_confidence(h5) sec_c_avg= get_avg(sec_c) sec_c_max= get_max(sec_c) sec_c_min = get_min(sec_c) sec_c_stddev= get_stddev(sec_c) sec_c_count = get_count(sec_c) sec_c_sum = get_sum(sec_c) sec_start = hdf5_getters.get_sections_start(h5) sec_start_avg = get_avg(sec_start) sec_start_max= get_max(sec_start) sec_start_min = get_min(sec_start) sec_start_stddev= get_stddev(sec_start) sec_start_count = get_count(sec_start) sec_start_sum = get_sum(sec_start) seg_c = hdf5_getters.get_segments_confidence(h5) seg_c_avg= get_avg(seg_c) seg_c_max= get_max(seg_c) seg_c_min = get_min(seg_c) seg_c_stddev= get_stddev(seg_c) seg_c_count = get_count(seg_c) seg_c_sum = get_sum(seg_c) seg_loud_max = hdf5_getters.get_segments_loudness_max(h5) seg_loud_max_avg= get_avg(seg_loud_max) seg_loud_max_max= get_max(seg_loud_max) seg_loud_max_min = get_min(seg_loud_max) seg_loud_max_stddev= get_stddev(seg_loud_max) seg_loud_max_count = get_count(seg_loud_max) seg_loud_max_sum = get_sum(seg_loud_max) seg_loud_max_time = hdf5_getters.get_segments_loudness_max_time(h5) seg_loud_max_time_avg= get_avg(seg_loud_max_time) seg_loud_max_time_max= get_max(seg_loud_max_time) seg_loud_max_time_min = get_min(seg_loud_max_time) seg_loud_max_time_stddev= get_stddev(seg_loud_max_time) seg_loud_max_time_count = get_count(seg_loud_max_time) seg_loud_max_time_sum = get_sum(seg_loud_max_time) seg_loud_start = hdf5_getters.get_segments_loudness_start(h5) seg_loud_start_avg= get_avg(seg_loud_start) seg_loud_start_max= get_max(seg_loud_start) seg_loud_start_min = get_min(seg_loud_start) seg_loud_start_stddev= get_stddev(seg_loud_start) seg_loud_start_count = get_count(seg_loud_start) seg_loud_start_sum = get_sum(seg_loud_start) seg_pitch = hdf5_getters.get_segments_pitches(h5) pitch_size = len(seg_pitch) seg_start = hdf5_getters.get_segments_start(h5) seg_start_avg= get_avg(seg_start) seg_start_max= get_max(seg_start) seg_start_min = get_min(seg_start) seg_start_stddev= get_stddev(seg_start) seg_start_count = get_count(seg_start) seg_start_sum = get_sum(seg_start) seg_timbre = hdf5_getters.get_segments_timbre(h5) tatms_c = hdf5_getters.get_tatums_confidence(h5) tatms_c_avg= get_avg(tatms_c) tatms_c_max= get_max(tatms_c) tatms_c_min = get_min(tatms_c) tatms_c_stddev= get_stddev(tatms_c) tatms_c_count = get_count(tatms_c) tatms_c_sum = get_sum(tatms_c) tatms_start = hdf5_getters.get_tatums_start(h5) tatms_start_avg= get_avg(tatms_start) tatms_start_max= get_max(tatms_start) tatms_start_min = get_min(tatms_start) tatms_start_stddev= get_stddev(tatms_start) tatms_start_count = get_count(tatms_start) tatms_start_sum = get_sum(tatms_start) #Getting the genres genre_set = 0 #flag to see if the genre has been set or not art_trm = hdf5_getters.get_artist_terms(h5) trm_freq = hdf5_getters.get_artist_terms_freq(h5) trn_wght = hdf5_getters.get_artist_terms_weight(h5) a_mb_tags = hdf5_getters.get_artist_mbtags(h5) genre_indexes=get_genre_indexes(trm_freq) #index of the highest freq final_genre=[] genres_so_far=[] for i in range(len(genre_indexes)): genre_tmp=get_genre(art_trm,genre_indexes[i]) #genre that corresponds to the highest freq genres_so_far=genre_dict.get_genre_in_dict(genre_tmp) #getting the genre from the dictionary if len(genres_so_far) != 0: for i in genres_so_far: final_genre.append(i) genre_set=1 #genre was found in dictionary if genre_set == 1: col_num=[] for genre in final_genre: column=int(genre) #getting the column number of the genre col_num.append(column) genre_array=genre_columns(col_num) #genre array else: genre_array=genre_columns(-1) #the genre was not found in the dictionary transpose_pitch= seg_pitch.transpose() #this is to tranpose the matrix,so we can have 12 rows #arrays containing the aggregate values of the 12 rows seg_pitch_avg=[] seg_pitch_max=[] seg_pitch_min=[] seg_pitch_stddev=[] seg_pitch_count=[] seg_pitch_sum=[] i=0 #Getting the aggregate values in the pitches array for row in transpose_pitch: seg_pitch_avg.append(get_avg(row)) seg_pitch_max.append(get_max(row)) seg_pitch_min.append(get_min(row)) seg_pitch_stddev.append(get_stddev(row)) seg_pitch_count.append(get_count(row)) seg_pitch_sum.append(get_sum(row)) i=i+1 #extracting information from the timbre array transpose_timbre = seg_pitch.transpose() #tranposing matrix, to have 12 rows #arrays containing the aggregate values of the 12 rows seg_timbre_avg=[] seg_timbre_max=[] seg_timbre_min=[] seg_timbre_stddev=[] seg_timbre_count=[] seg_timbre_sum=[] i=0 for row in transpose_timbre: seg_timbre_avg.append(get_avg(row)) seg_timbre_max.append(get_max(row)) seg_timbre_min.append(get_min(row)) seg_timbre_stddev.append(get_stddev(row)) seg_timbre_count.append(get_count(row)) seg_timbre_sum.append(get_sum(row)) i=i+1 #Writing to the flat file writer.writerow([title,album,artist_name,year,duration,seg_start_count, tempo]) h5.close() count=count+1; print count;
def 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)
h5 = hdf5_getters.open_h5_file_read("files/msd_summary_file.h5") data = [] length = hdf5_getters.get_num_songs(h5) print("number of songs = ",length) count = 0; for i in range(0,length): tmp = []; if hdf5_getters.get_year(h5,songidx=i) == 0 : continue; #if math.isnan(hdf5_getters.get_artist_latitude(h5,songidx=i)) and hdf5_getters.get_artist_location(h5,songidx=i) =='': # continue; count+=1; tmp.append(str(hdf5_getters.get_track_id(h5,songidx=i)).replace("b'","").replace("'","")); tmp.append(hdf5_getters.get_year(h5,songidx=i)); #0 tmp.append(hdf5_getters.get_song_hotttnesss(h5,songidx=i)); #1 tmp.append(str(hdf5_getters.get_title(h5,songidx=i)).replace("b'","").replace("'","")); #2 tmp.append(str(hdf5_getters.get_artist_id(h5,songidx=i)).replace("b'","").replace("'","")); #3 tmp.append(hdf5_getters.get_artist_latitude(h5,songidx=i)); #4 tmp.append(hdf5_getters.get_artist_longitude(h5,songidx=i)); #5 tmp.append(str(hdf5_getters.get_artist_location(h5,songidx=i)).replace("b'","").replace("'","")); #6 tmp.append(str(hdf5_getters.get_artist_name(h5,songidx=i)).replace("b'","").replace("'","")); #7 tmp.append(str(hdf5_getters.get_song_id(h5,songidx=i)).replace("b'","").replace("'","")); data.append(tmp) print(count) h5.close() data = sorted(data, key = operator.itemgetter(1))
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
for name in files: if name.endswith(".h5"): if process_completion % 2350 == 0: print "done :", process_completion/2350.0, "%" process_completion += 1 header_counter += 1 else: process_completion += 1 header_counter += 1 tempPath = os.path.abspath(os.path.join(root,name)) h5SongFile = hdf5_getters.open_h5_file_read(tempPath) # create the sample row for feature matrix # initialize the list with track ID and song ID sampleRow = [hdf5_getters.get_track_id(h5SongFile), hdf5_getters.get_song_id(h5SongFile)] cnt = 0 for func in featureFunctions: cnt += 1 # print "functionNumber: ", cnt # print "BarStrctr: ", hdf5_getters.get_bars_start(h5SongFile) sampleRow += func(h5SongFile) # Construct the feature matrix that contains all the songs... # Data structure for featureMatrix will be list of lists, so that... # Numpy will be able to convert it to a matrix in a way that... # All list elements will become rows # featureMatrix += [sampleRow] featureMatrix = [sampleRow]
artist_long = g.get_artist_longitude(h5) artist_loc = g.get_artist_location(h5) song_idss = g.get_song_id(h5) song_speed = g.get_tempo(h5) song_bar = g.get_bars_start(h5) song_beat = g.get_beats_start(h5) song_time_signature = g.get_time_signature(h5) song_tat = g.get_tatums_start(h5) song_mode = g.get_mode(h5) song_key = g.get_key(h5) song_idss = g.get_song_id(h5) song_title = g.get_title(h5) song_duration = g.get_duration(h5) song_release_years = g.get_year(h5) song_hot = g.get_song_hotttnesss (h5) track_idss = g.get_track_id(h5) file_path.append(filepath) artist_names.append(artist_name) artist_familiarty.append(artist_familar) artist_hotness.append(artist_hot) artist_id.append(artist_ids) artist_latitude.append(artist_lat) artist_longitude.append(artist_long) artist_location.append(artist_loc) song_id.append(song_idss) song_tempo.append(song_speed) song_bars.append(song_bar) song_beats.append(song_beat) song_time_signatures.append(song_time_signature) song_tatum.append(song_tat)
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
import sys sys.path.append('/home/gaurav/PythonDir/ProjectWork/MSongsDB-master/PythonSrc') import hdf5_getters sumfile = '/home/gaurav/PythonDir/ProjectWork/MillionSongSubset/AdditionalFiles/subset_msd_summary_file.h5' h5 = hdf5_getters.open_h5_file_read(sumfile) for k in range(10000): #a_name = hdf5_getters.get_artist_name(h5,k) hot1 = hdf5_getters.get_song_hotttnesss(h5, k) #if a_name == 'Radiohead': if hot1: print hdf5_getters.get_track_id(h5, k), hot1 #Faster #h5 = hdf5_getters.open_h5_file_read(sumfile) #idxs = h5.root.metadata.songs.getWhereList('artist_name=="Radiohead"') #for idx in idxs: # print h5.root.analysis.songs.cols.track_id[idx]
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 ''' track_id = h.get_track_id(h5,0) track_title = h.get_title(h5,0) track_title = track_title.replace("'","") track_album = h.get_release(h5,0) track_album = track_album.replace("'","") track_duration = str(h.get_duration(h5,0)) track_year = str(h.get_year(h5,0)) cursor.execute("SELECT * FROM track WHERE track_id = '" + track_id + "'") rs = cursor.fetchall() if cursor.rowcount != 1: cursor.execute("INSERT INTO track VALUES ('" + track_id + "','" + track_title + "','" + artist_id + "','" + artist_name + "','" + track_album + "'," + track_duration + "," + track_year + ");") ''' Store track_analysis tuples ''' print ("Track ID: " + h.get_track_id(h5,0)) track_tempo = str(h.get_tempo(h5,0))
sys.path.append("/mnt/MSongsDB/PythonSrc") # this is where hdf5_getters.py is placed import hdf5_getters # This script converts the summary H5 files only 300MB to a csv file # Run only on the Master Node since h5_getters cannot open a remote(ie. HDFS) file if __name__ == "__main__": with open("fields.csv", "wb") as f: writer = csv.writer(f) # initialize the csv writer # for each track in the summary file, get the 11 fields and output to csv h5_file = hdf5_getters.open_h5_file_read("msd_summary_file.h5") for k in range(1000000): print "index!!!: ", k id = hdf5_getters.get_track_id(h5_file, k) # get track_id TRA13e39.. title = hdf5_getters.get_title(h5_file, k) # get song title artist_name = hdf5_getters.get_artist_name(h5_file, k) year = int(hdf5_getters.get_year(h5_file, k)) hotness = float(hdf5_getters.get_song_hotttnesss(h5_file, k)) artist_familiarity = float(hdf5_getters.get_artist_familiarity(h5_file, k)) f5 = int(hdf5_getters.get_key(h5_file, k)) # get key f2 = float(hdf5_getters.get_loudness(h5_file, k)) # get loudness f1 = float(hdf5_getters.get_tempo(h5_file, k)) # get tempo f4 = int(hdf5_getters.get_duration(h5_file, k)) # get duration f3 = float(hdf5_getters.get_time_signature(h5_file, k)) # get time signature # Get rid of missing info and change invalid numbers for meta data if not artist_name: artist_name = "unknown"
def process_filelist_test(filelist=None,model=None,tmpfilename=None, npicks=None,winsize=None,finaldim=None,K=1, typecompress='picks'): """ Main function, process all files in the list (as long as their artist is in testartist) INPUT filelist - a list of song files model - h5 file containing feats and year for all train songs tmpfilename - where to save our processed features npicks - number of segments to pick per song winsize - size of each segment we pick finaldim - how many values do we keep K - param of KNN (default 1) typecompress - feature type, 'picks', 'corrcoeff' or 'cov' must be the same as in training """ # sanity check for arg in locals().values(): assert not arg is None,'process_filelist_test, missing an argument, something still None' if os.path.isfile(tmpfilename): print 'ERROR: file',tmpfilename,'already exists.' return if not os.path.isfile(model): print 'ERROR: model',model,'does not exist.' return # create kdtree h5model = tables.openFile(model, mode='r') assert h5model.root.data.feats.shape[1]==finaldim,'inconsistency in final dim' kd = ANN.kdtree(h5model.root.data.feats) # create outputfile output = tables.openFile(tmpfilename, mode='a') group = output.createGroup("/",'data','TMP FILE FOR YEAR RECOGNITION') output.createEArray(group,'year_real',tables.IntAtom(shape=()),(0,),'', expectedrows=len(filelist)) output.createEArray(group,'year_pred',tables.Float64Atom(shape=()),(0,),'', expectedrows=len(filelist)) # random projection ndim = 12 # fixed in this dataset if typecompress == 'picks': randproj = RANDPROJ.proj_point5(ndim * winsize, finaldim) elif typecompress == 'corrcoeff' or typecompress=='cov': randproj = RANDPROJ.proj_point5(ndim * ndim, finaldim) elif typecompress == 'avgcov': randproj = RANDPROJ.proj_point5(90, finaldim) else: assert False,'Unknown type of compression: '+str(typecompress) # go through files cnt_f = 0 for f in filelist: cnt_f += 1 if cnt_f % 5000 == 0: print 'TESTING FILE #'+str(cnt_f) # check file h5 = GETTERS.open_h5_file_read(f) artist_id = GETTERS.get_artist_id(h5) year = GETTERS.get_year(h5) track_id = GETTERS.get_track_id(h5) h5.close() if year <= 0: # probably useless but... continue if typecompress == 'picks': # we have a train artist with a song year, we're good bttimbre = get_bttimbre(f) if bttimbre is None: continue # we even have normal features, awesome! processed_feats = CBTF.extract_and_compress(bttimbre,npicks,winsize,finaldim, randproj=randproj) elif typecompress == 'corrcoeff': h5 = GETTERS.open_h5_file_read(f) timbres = GETTERS.get_segments_timbre(h5).T h5.close() processed_feats = CBTF.corr_and_compress(timbres,finaldim,randproj=randproj) elif typecompress == 'cov': h5 = GETTERS.open_h5_file_read(f) timbres = GETTERS.get_segments_timbre(h5).T h5.close() processed_feats = CBTF.cov_and_compress(timbres,finaldim,randproj=randproj) elif typecompress == 'avgcov': h5 = GETTERS.open_h5_file_read(f) timbres = GETTERS.get_segments_timbre(h5).T h5.close() processed_feats = CBTF.avgcov_and_compress(timbres,finaldim,randproj=randproj) else: assert False,'Unknown type of compression: '+str(typecompress) if processed_feats is None: continue if processed_feats.shape[0] == 0: continue # do prediction year_pred = do_prediction(processed_feats,kd,h5model,K) # add pred and ground truth to output if not year_pred is None: output.root.data.year_real.append( [year] ) output.root.data.year_pred.append( [year_pred] ) # close output and model del kd h5model.close() output.close() # done return
def process_filelist_train(filelist=None,testartists=None,tmpfilename=None, npicks=None,winsize=None,finaldim=None,typecompress='picks'): """ Main function, process all files in the list (as long as their artist is not in testartist) INPUT filelist - a list of song files testartists - set of artist ID that we should not use tmpfilename - where to save our processed features npicks - number of segments to pick per song winsize - size of each segment we pick finaldim - how many values do we keep typecompress - one of 'picks' (win of btchroma), 'corrcoef' (correlation coefficients), 'cov' (covariance) """ # sanity check for arg in locals().values(): assert not arg is None,'process_filelist_train, missing an argument, something still None' if os.path.isfile(tmpfilename): print 'ERROR: file',tmpfilename,'already exists.' return # create outputfile output = tables.openFile(tmpfilename, mode='a') group = output.createGroup("/",'data','TMP FILE FOR YEAR RECOGNITION') output.createEArray(group,'feats',tables.Float64Atom(shape=()),(0,finaldim),'', expectedrows=len(filelist)) output.createEArray(group,'year',tables.IntAtom(shape=()),(0,),'', expectedrows=len(filelist)) output.createEArray(group,'track_id',tables.StringAtom(18,shape=()),(0,),'', expectedrows=len(filelist)) # random projection ndim = 12 # fixed in this dataset if typecompress == 'picks': randproj = RANDPROJ.proj_point5(ndim * winsize, finaldim) elif typecompress == 'corrcoeff' or typecompress == 'cov': randproj = RANDPROJ.proj_point5(ndim * ndim, finaldim) elif typecompress == 'avgcov': randproj = RANDPROJ.proj_point5(90, finaldim) else: assert False,'Unknown type of compression: '+str(typecompress) # iterate over files cnt_f = 0 for f in filelist: cnt_f += 1 # verbose if cnt_f % 50000 == 0: print 'training... checking file #',cnt_f # check file h5 = GETTERS.open_h5_file_read(f) artist_id = GETTERS.get_artist_id(h5) year = GETTERS.get_year(h5) track_id = GETTERS.get_track_id(h5) h5.close() if year <= 0 or artist_id in testartists: continue # we have a train artist with a song year, we're good bttimbre = get_bttimbre(f) if typecompress == 'picks': if bttimbre is None: continue # we even have normal features, awesome! processed_feats = CBTF.extract_and_compress(bttimbre,npicks,winsize,finaldim, randproj=randproj) elif typecompress == 'corrcoeff': h5 = GETTERS.open_h5_file_read(f) timbres = GETTERS.get_segments_timbre(h5).T h5.close() processed_feats = CBTF.corr_and_compress(timbres,finaldim,randproj=randproj) elif typecompress == 'cov': h5 = GETTERS.open_h5_file_read(f) timbres = GETTERS.get_segments_timbre(h5).T h5.close() processed_feats = CBTF.cov_and_compress(timbres,finaldim,randproj=randproj) elif typecompress == 'avgcov': h5 = GETTERS.open_h5_file_read(f) timbres = GETTERS.get_segments_timbre(h5).T h5.close() processed_feats = CBTF.avgcov_and_compress(timbres,finaldim,randproj=randproj) else: assert False,'Unknown type of compression: '+str(typecompress) # save them to tmp file n_p_feats = processed_feats.shape[0] output.root.data.year.append( np.array( [year] * n_p_feats ) ) output.root.data.track_id.append( np.array( [track_id] * n_p_feats ) ) output.root.data.feats.append( processed_feats ) # we're done, close output output.close() return
def data_to_flat_file(basedir,ext='.h5') : """This function extract the information from the tables and creates the flat file.""" count = 0; #song counter list_to_write= [] row_to_write = "" writer = csv.writer(open("metadata.csv", "wb")) for root, dirs, files in os.walk(basedir): files = glob.glob(os.path.join(root,'*'+ext)) for f in files: print f #the name of the file h5 = hdf5_getters.open_h5_file_read(f) title = hdf5_getters.get_title(h5) title= title.replace('"','') comma=title.find(',') #eliminating commas in the title if comma != -1: print title time.sleep(1) album = hdf5_getters.get_release(h5) album= album.replace('"','') #eliminating commas in the album comma=album.find(',') if comma != -1: print album time.sleep(1) artist_name = hdf5_getters.get_artist_name(h5) comma=artist_name.find(',') if comma != -1: print artist_name time.sleep(1) artist_name= artist_name.replace('"','') #eliminating double quotes duration = hdf5_getters.get_duration(h5) samp_rt = hdf5_getters.get_analysis_sample_rate(h5) artist_7digitalid = hdf5_getters.get_artist_7digitalid(h5) artist_fam = hdf5_getters.get_artist_familiarity(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(artist_fam) == True: artist_fam=-1 artist_hotness= hdf5_getters.get_artist_hotttnesss(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(artist_hotness) == True: artist_hotness=-1 artist_id = hdf5_getters.get_artist_id(h5) artist_lat = hdf5_getters.get_artist_latitude(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(artist_lat) == True: artist_lat=-1 artist_loc = hdf5_getters.get_artist_location(h5) #checks artist_loc to see if it is a hyperlink if it is set as empty string artist_loc = artist_loc.replace(",", "\,"); if artist_loc.startswith("<a"): artist_loc = "" if len(artist_loc) > 100: artist_loc = "" artist_lon = hdf5_getters.get_artist_longitude(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(artist_lon) == True: artist_lon=-1 artist_mbid = hdf5_getters.get_artist_mbid(h5) artist_pmid = hdf5_getters.get_artist_playmeid(h5) audio_md5 = hdf5_getters.get_audio_md5(h5) danceability = hdf5_getters.get_danceability(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(danceability) == True: danceability=-1 end_fade_in =hdf5_getters.get_end_of_fade_in(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(end_fade_in) == True: end_fade_in=-1 energy = hdf5_getters.get_energy(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(energy) == True: energy=-1 song_key = hdf5_getters.get_key(h5) key_c = hdf5_getters.get_key_confidence(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(key_c) == True: key_c=-1 loudness = hdf5_getters.get_loudness(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(loudness) == True: loudness=-1 mode = hdf5_getters.get_mode(h5) mode_conf = hdf5_getters.get_mode_confidence(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(mode_conf) == True: mode_conf=-1 release_7digitalid = hdf5_getters.get_release_7digitalid(h5) song_hot = hdf5_getters.get_song_hotttnesss(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(song_hot) == True: song_hot=-1 song_id = hdf5_getters.get_song_id(h5) start_fade_out = hdf5_getters.get_start_of_fade_out(h5) tempo = hdf5_getters.get_tempo(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(tempo) == True: tempo=-1 time_sig = hdf5_getters.get_time_signature(h5) time_sig_c = hdf5_getters.get_time_signature_confidence(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(time_sig_c) == True: time_sig_c=-1 track_id = hdf5_getters.get_track_id(h5) track_7digitalid = hdf5_getters.get_track_7digitalid(h5) year = hdf5_getters.get_year(h5) bars_c = hdf5_getters.get_bars_confidence(h5) bars_c_avg= get_avg(bars_c) bars_c_max= get_max(bars_c) bars_c_min = get_min(bars_c) bars_c_stddev= get_stddev(bars_c) bars_c_count = get_count(bars_c) bars_c_sum = get_sum(bars_c) bars_start = hdf5_getters.get_bars_start(h5) bars_start_avg = get_avg(bars_start) bars_start_max= get_max(bars_start) bars_start_min = get_min(bars_start) bars_start_stddev= get_stddev(bars_start) bars_start_count = get_count(bars_start) bars_start_sum = get_sum(bars_start) beats_c = hdf5_getters.get_beats_confidence(h5) beats_c_avg= get_avg(beats_c) beats_c_max= get_max(beats_c) beats_c_min = get_min(beats_c) beats_c_stddev= get_stddev(beats_c) beats_c_count = get_count(beats_c) beats_c_sum = get_sum(beats_c) beats_start = hdf5_getters.get_beats_start(h5) beats_start_avg = get_avg(beats_start) beats_start_max= get_max(beats_start) beats_start_min = get_min(beats_start) beats_start_stddev= get_stddev(beats_start) beats_start_count = get_count(beats_start) beats_start_sum = get_sum(beats_start) sec_c = hdf5_getters.get_sections_confidence(h5) sec_c_avg= get_avg(sec_c) sec_c_max= get_max(sec_c) sec_c_min = get_min(sec_c) sec_c_stddev= get_stddev(sec_c) sec_c_count = get_count(sec_c) sec_c_sum = get_sum(sec_c) sec_start = hdf5_getters.get_sections_start(h5) sec_start_avg = get_avg(sec_start) sec_start_max= get_max(sec_start) sec_start_min = get_min(sec_start) sec_start_stddev= get_stddev(sec_start) sec_start_count = get_count(sec_start) sec_start_sum = get_sum(sec_start) seg_c = hdf5_getters.get_segments_confidence(h5) seg_c_avg= get_avg(seg_c) seg_c_max= get_max(seg_c) seg_c_min = get_min(seg_c) seg_c_stddev= get_stddev(seg_c) seg_c_count = get_count(seg_c) seg_c_sum = get_sum(seg_c) seg_loud_max = hdf5_getters.get_segments_loudness_max(h5) seg_loud_max_avg= get_avg(seg_loud_max) seg_loud_max_max= get_max(seg_loud_max) seg_loud_max_min = get_min(seg_loud_max) seg_loud_max_stddev= get_stddev(seg_loud_max) seg_loud_max_count = get_count(seg_loud_max) seg_loud_max_sum = get_sum(seg_loud_max) seg_loud_max_time = hdf5_getters.get_segments_loudness_max_time(h5) seg_loud_max_time_avg= get_avg(seg_loud_max_time) seg_loud_max_time_max= get_max(seg_loud_max_time) seg_loud_max_time_min = get_min(seg_loud_max_time) seg_loud_max_time_stddev= get_stddev(seg_loud_max_time) seg_loud_max_time_count = get_count(seg_loud_max_time) seg_loud_max_time_sum = get_sum(seg_loud_max_time) seg_loud_start = hdf5_getters.get_segments_loudness_start(h5) seg_loud_start_avg= get_avg(seg_loud_start) seg_loud_start_max= get_max(seg_loud_start) seg_loud_start_min = get_min(seg_loud_start) seg_loud_start_stddev= get_stddev(seg_loud_start) seg_loud_start_count = get_count(seg_loud_start) seg_loud_start_sum = get_sum(seg_loud_start) seg_pitch = hdf5_getters.get_segments_pitches(h5) pitch_size = len(seg_pitch) seg_start = hdf5_getters.get_segments_start(h5) seg_start_avg= get_avg(seg_start) seg_start_max= get_max(seg_start) seg_start_min = get_min(seg_start) seg_start_stddev= get_stddev(seg_start) seg_start_count = get_count(seg_start) seg_start_sum = get_sum(seg_start) seg_timbre = hdf5_getters.get_segments_timbre(h5) tatms_c = hdf5_getters.get_tatums_confidence(h5) tatms_c_avg= get_avg(tatms_c) tatms_c_max= get_max(tatms_c) tatms_c_min = get_min(tatms_c) tatms_c_stddev= get_stddev(tatms_c) tatms_c_count = get_count(tatms_c) tatms_c_sum = get_sum(tatms_c) tatms_start = hdf5_getters.get_tatums_start(h5) tatms_start_avg= get_avg(tatms_start) tatms_start_max= get_max(tatms_start) tatms_start_min = get_min(tatms_start) tatms_start_stddev= get_stddev(tatms_start) tatms_start_count = get_count(tatms_start) tatms_start_sum = get_sum(tatms_start) #Getting the genres genre_set = 0 #flag to see if the genre has been set or not art_trm = hdf5_getters.get_artist_terms(h5) trm_freq = hdf5_getters.get_artist_terms_freq(h5) trn_wght = hdf5_getters.get_artist_terms_weight(h5) a_mb_tags = hdf5_getters.get_artist_mbtags(h5) genre_indexes=get_genre_indexes(trm_freq) #index of the highest freq final_genre=[] genres_so_far=[] for i in range(len(genre_indexes)): genre_tmp=get_genre(art_trm,genre_indexes[i]) #genre that corresponds to the highest freq genres_so_far=genre_dict.get_genre_in_dict(genre_tmp) #getting the genre from the dictionary if len(genres_so_far) != 0: for i in genres_so_far: final_genre.append(i) genre_set=1 #genre was found in dictionary if genre_set == 1: col_num=[] for genre in final_genre: column=int(genre) #getting the column number of the genre col_num.append(column) genre_array=genre_columns(col_num) #genre array else: genre_array=genre_columns(-1) #the genre was not found in the dictionary transpose_pitch= seg_pitch.transpose() #this is to tranpose the matrix,so we can have 12 rows #arrays containing the aggregate values of the 12 rows seg_pitch_avg=[] seg_pitch_max=[] seg_pitch_min=[] seg_pitch_stddev=[] seg_pitch_count=[] seg_pitch_sum=[] i=0 #Getting the aggregate values in the pitches array for row in transpose_pitch: seg_pitch_avg.append(get_avg(row)) seg_pitch_max.append(get_max(row)) seg_pitch_min.append(get_min(row)) seg_pitch_stddev.append(get_stddev(row)) seg_pitch_count.append(get_count(row)) seg_pitch_sum.append(get_sum(row)) i=i+1 #extracting information from the timbre array transpose_timbre = seg_pitch.transpose() #tranposing matrix, to have 12 rows #arrays containing the aggregate values of the 12 rows seg_timbre_avg=[] seg_timbre_max=[] seg_timbre_min=[] seg_timbre_stddev=[] seg_timbre_count=[] seg_timbre_sum=[] i=0 for row in transpose_timbre: seg_timbre_avg.append(get_avg(row)) seg_timbre_max.append(get_max(row)) seg_timbre_min.append(get_min(row)) seg_timbre_stddev.append(get_stddev(row)) seg_timbre_count.append(get_count(row)) seg_timbre_sum.append(get_sum(row)) i=i+1 #Writing to the flat file writer.writerow([title,album,artist_name,duration,samp_rt,artist_7digitalid,artist_fam,artist_hotness,artist_id,artist_lat,artist_loc,artist_lon,artist_mbid,genre_array[0],genre_array[1],genre_array[2], genre_array[3],genre_array[4],genre_array[5],genre_array[6],genre_array[7],genre_array[8],genre_array[9],genre_array[10],genre_array[11],genre_array[12],genre_array[13],genre_array[14],genre_array[15], genre_array[16],genre_array[17],genre_array[18],genre_array[19],genre_array[20],genre_array[21],genre_array[22],genre_array[23],genre_array[24],genre_array[25],genre_array[26], genre_array[27],genre_array[28],genre_array[29],genre_array[30],genre_array[31],genre_array[32],genre_array[33],genre_array[34],genre_array[35],genre_array[36],genre_array[37],genre_array[38], genre_array[39],genre_array[40],genre_array[41],genre_array[42],genre_array[43],genre_array[44],genre_array[45],genre_array[46],genre_array[47],genre_array[48],genre_array[49], genre_array[50],genre_array[51],genre_array[52],genre_array[53],genre_array[54],genre_array[55],genre_array[56],genre_array[57],genre_array[58],genre_array[59], genre_array[60],genre_array[61],genre_array[62],genre_array[63],genre_array[64],genre_array[65],genre_array[66],genre_array[67],genre_array[68],genre_array[69], genre_array[70],genre_array[71],genre_array[72],genre_array[73],genre_array[74],genre_array[75],genre_array[76],genre_array[77],genre_array[78],genre_array[79], genre_array[80],genre_array[81],genre_array[82],genre_array[83],genre_array[84],genre_array[85],genre_array[86],genre_array[87],genre_array[88],genre_array[89], genre_array[90],genre_array[91],genre_array[92],genre_array[93],genre_array[94],genre_array[95],genre_array[96],genre_array[97],genre_array[98],genre_array[99],genre_array[100],genre_array[101], genre_array[102],genre_array[103],genre_array[104],genre_array[105],genre_array[106],genre_array[107],genre_array[108],genre_array[109],genre_array[110],genre_array[111],genre_array[112], genre_array[113],genre_array[114],genre_array[115],genre_array[116],genre_array[117],genre_array[118],genre_array[119],genre_array[120],genre_array[121],genre_array[122],genre_array[123], genre_array[124],genre_array[125],genre_array[126],genre_array[127],genre_array[128],genre_array[129],genre_array[130],genre_array[131],genre_array[132], artist_pmid,audio_md5,danceability,end_fade_in,energy,song_key,key_c,loudness,mode,mode_conf,release_7digitalid,song_hot,song_id,start_fade_out,tempo,time_sig,time_sig_c,track_id,track_7digitalid,year,bars_c_avg,bars_c_max,bars_c_min,bars_c_stddev,bars_c_count,bars_c_sum,bars_start_avg,bars_start_max,bars_start_min,bars_start_stddev,bars_start_count,bars_start_sum,beats_c_avg,beats_c_max,beats_c_min,beats_c_stddev,beats_c_count,beats_c_sum,beats_start_avg,beats_start_max,beats_start_min, beats_start_stddev,beats_start_count,beats_start_sum, sec_c_avg,sec_c_max,sec_c_min,sec_c_stddev,sec_c_count,sec_c_sum,sec_start_avg,sec_start_max,sec_start_min,sec_start_stddev,sec_start_count,sec_start_sum,seg_c_avg,seg_c_max,seg_c_min,seg_c_stddev,seg_c_count,seg_c_sum,seg_loud_max_avg,seg_loud_max_max,seg_loud_max_min,seg_loud_max_stddev,seg_loud_max_count,seg_loud_max_sum,seg_loud_max_time_avg,seg_loud_max_time_max,seg_loud_max_time_min,seg_loud_max_time_stddev,seg_loud_max_time_count,seg_loud_max_time_sum,seg_loud_start_avg,seg_loud_start_max,seg_loud_start_min,seg_loud_start_stddev,seg_loud_start_count,seg_loud_start_sum,seg_pitch_avg[0],seg_pitch_max[0],seg_pitch_min[0],seg_pitch_stddev[0],seg_pitch_count[0],seg_pitch_sum[0],seg_pitch_avg[1],seg_pitch_max[1],seg_pitch_min[1],seg_pitch_stddev[1],seg_pitch_count[1],seg_pitch_sum[1],seg_pitch_avg[2],seg_pitch_max[2],seg_pitch_min[2],seg_pitch_stddev[2],seg_pitch_count[2],seg_pitch_sum[2],seg_pitch_avg[3],seg_pitch_max[3],seg_pitch_min[3],seg_pitch_stddev[3],seg_pitch_count[3],seg_pitch_sum[3],seg_pitch_avg[4],seg_pitch_max[4],seg_pitch_min[4],seg_pitch_stddev[4],seg_pitch_count[4],seg_pitch_sum[4],seg_pitch_avg[5],seg_pitch_max[5],seg_pitch_min[5],seg_pitch_stddev[5],seg_pitch_count[5],seg_pitch_sum[5],seg_pitch_avg[6],seg_pitch_max[6],seg_pitch_min[6],seg_pitch_stddev[6],seg_pitch_count[6],seg_pitch_sum[6],seg_pitch_avg[7],seg_pitch_max[7],seg_pitch_min[7],seg_pitch_stddev[7],seg_pitch_count[7],seg_pitch_sum[7],seg_pitch_avg[8],seg_pitch_max[8],seg_pitch_min[8],seg_pitch_stddev[8],seg_pitch_count[8],seg_pitch_sum[8],seg_pitch_avg[9],seg_pitch_max[9],seg_pitch_min[9],seg_pitch_stddev[9],seg_pitch_count[9],seg_pitch_sum[9],seg_pitch_avg[10],seg_pitch_max[10],seg_pitch_min[10],seg_pitch_stddev[10],seg_pitch_count[10],seg_pitch_sum[10],seg_pitch_avg[11],seg_pitch_max[11],seg_pitch_min[11], seg_pitch_stddev[11],seg_pitch_count[11],seg_pitch_sum[11],seg_start_avg,seg_start_max,seg_start_min,seg_start_stddev, seg_start_count,seg_start_sum,seg_timbre_avg[0],seg_timbre_max[0],seg_timbre_min[0],seg_timbre_stddev[0],seg_timbre_count[0], seg_timbre_sum[0],seg_timbre_avg[1],seg_timbre_max[1],seg_timbre_min[1],seg_timbre_stddev[1],seg_timbre_count[1], seg_timbre_sum[1],seg_timbre_avg[2],seg_timbre_max[2],seg_timbre_min[2],seg_timbre_stddev[2],seg_timbre_count[2], seg_timbre_sum[2],seg_timbre_avg[3],seg_timbre_max[3],seg_timbre_min[3],seg_timbre_stddev[3],seg_timbre_count[3], seg_timbre_sum[3],seg_timbre_avg[4],seg_timbre_max[4],seg_timbre_min[4],seg_timbre_stddev[4],seg_timbre_count[4], seg_timbre_sum[4],seg_timbre_avg[5],seg_timbre_max[5],seg_timbre_min[5],seg_timbre_stddev[5],seg_timbre_count[5], seg_timbre_sum[5],seg_timbre_avg[6],seg_timbre_max[6],seg_timbre_min[6],seg_timbre_stddev[6],seg_timbre_count[6], seg_timbre_sum[6],seg_timbre_avg[7],seg_timbre_max[7],seg_timbre_min[7],seg_timbre_stddev[7],seg_timbre_count[7], seg_timbre_sum[7],seg_timbre_avg[8],seg_timbre_max[8],seg_timbre_min[8],seg_timbre_stddev[8],seg_timbre_count[8], seg_timbre_sum[8],seg_timbre_avg[9],seg_timbre_max[9],seg_timbre_min[9],seg_timbre_stddev[9],seg_timbre_count[9], seg_timbre_sum[9],seg_timbre_avg[10],seg_timbre_max[10],seg_timbre_min[10],seg_timbre_stddev[10],seg_timbre_count[10], seg_timbre_sum[10],seg_timbre_avg[11],seg_timbre_max[11],seg_timbre_min[11],seg_timbre_stddev[11],seg_timbre_count[11], seg_timbre_sum[11],tatms_c_avg,tatms_c_max,tatms_c_min,tatms_c_stddev,tatms_c_count,tatms_c_sum,tatms_start_avg,tatms_start_max,tatms_start_min,tatms_start_stddev,tatms_start_count,tatms_start_sum]) h5.close() count=count+1; print count;
def process_filelist_test(filelist=None,model=None,tmpfilename=None,K=1): """ Main function, process all files in the list (as long as their track_id is not in testsongs) INPUT filelist - a list of song files model - h5 file containing feats and artist_id for all train songs tmpfilename - where to save our processed features K - K-nn parameter (default=1) """ # sanity check for arg in locals().values(): assert not arg is None,'process_filelist_train, missing an argument, something still None' if os.path.isfile(tmpfilename): print 'ERROR: file',tmpfilename,'already exists.' return if not os.path.isfile(model): print 'ERROR: model',model,'does not exist.' return # dimension fixed (12-dimensional timbre vector) ndim = 12 finaldim = 90 # create kdtree h5model = tables.openFile(model, mode='r') assert h5model.root.data.feats.shape[1]==finaldim,'inconsistency in final dim' kd = ANN.kdtree(h5model.root.data.feats) # create outputfile output = tables.openFile(tmpfilename, mode='a') group = output.createGroup("/",'data','TMP FILE FOR ARTIST RECOGNITION') output.createEArray(group,'artist_id_real',tables.StringAtom(18,shape=()),(0,),'', expectedrows=len(filelist)) output.createEArray(group,'artist_id_pred',tables.StringAtom(18,shape=()),(0,),'', expectedrows=len(filelist)) # iterate over files cnt_f = 0 for f in filelist: cnt_f += 1 # verbose if cnt_f % 50000 == 0: print 'training... checking file #',cnt_f # check what file/song is this h5 = GETTERS.open_h5_file_read(f) artist_id = GETTERS.get_artist_id(h5) track_id = GETTERS.get_track_id(h5) if track_id in testsongs: # just in case, but should not be necessary print 'Found test track_id during training? weird.',track_id h5.close() continue # extract features, then close file processed_feats = compute_features(h5) h5.close() if processed_feats is None: continue # do prediction artist_id_pred = do_prediction(processed_feats,kd,h5model,K) # save features to tmp file output.root.data.artist_id_real.append( np.array( [artist_id] ) ) output.root.data.artist_id_pred.append( np.array( [artist_id_pred] ) ) # we're done, close output output.close() return
def write_line(output, getter, data, song_nb): line = hdf5_getters.get_track_id(data).decode('UTF-8') h5getter = getattr(hdf5_getters, getter) line += '\t' + toJson(h5getter(data, song_nb)) line += '\n' output.write(line)
#segments_loudness_start = ','.join(str(e) for e in GETTERS.get_segments_loudness_start(h5, i)) # array #segments_pitches = ','.join(str(e) for e in GETTERS.get_segments_pitches(h5, i)) # array #segments_start = ','.join(str(e) for e in GETTERS.get_segments_start(h5, i)) # array #segments_timbre = ','.join(str(e) for e in GETTERS.get_segments_timbre(h5, i)) # array similar_artists = ','.join(str(e) for e in GETTERS.get_similar_artists(h5, i)) # array song_hotttnesss = GETTERS.get_song_hotttnesss(h5, i) song_id = GETTERS.get_song_id(h5, i) start_of_fade_out = GETTERS.get_start_of_fade_out(h5, i) #tatums_confidence = ','.join(str(e) for e in GETTERS.get_tatums_confidence(h5, i)) # array #tatums_start = ','.join(str(e) for e in GETTERS.get_tatums_start(h5, i)) # array tempo = GETTERS.get_tempo(h5, i) time_signature = GETTERS.get_time_signature(h5, i) time_signature_confidence = GETTERS.get_time_signature_confidence(h5, i) title = GETTERS.get_title(h5, i) track_7digitalid = GETTERS.get_track_7digitalid(h5, i) track_id = GETTERS.get_track_id(h5, i) year = GETTERS.get_year(h5, i) loops += 1 #row = {'analysis_sample_rate':analysis_sample_rate,'artist_7digitalid':artist_7digitalid,'artist_familiarity':artist_familiarity,'artist_hotttnesss':artist_hotttnesss,'artist_id':artist_id,'artist_latitude':artist_latitude,'artist_location':artist_location,'artist_longitude':artist_longitude,'artist_mbid':artist_mbid,'artist_mbtags_count':artist_mbtags_count,'artist_mbtags':artist_mbtags,'artist_name':artist_name,'artist_terms_freq':artist_terms_freq,'artist_terms_weight':artist_terms_weight,'artist_terms':artist_terms,'audio_md5':audio_md5,'bars_confidence':bars_confidence,'bars_start':bars_start,'beats_confidence':beats_confidence,'beats_start':beats_start,'danceability':danceability,'duration':duration,'end_of_fade_in':end_of_fade_in,'energy':energy,'key_confidence':key_confidence,'key':key,'loudness':loudness,'mode_confidence':mode_confidence,'mode':mode,'release_7digitalid':release_7digitalid,'release':release,'sections_confidence':sections_confidence,'sections_start':sections_start,'segments_confidence':segments_confidence,'segments_loudness_max_time':segments_loudness_max_time,'segments_loudness_max':segments_loudness_max,'segments_loudness_start':segments_loudness_start,'segments_pitches':segments_pitches,'segments_start':segments_start,'segments_timbre':segments_timbre,'similar_artists':similar_artists,'song_hotttnesss':song_hotttnesss,'song_id':song_id,'start_of_fade_out':start_of_fade_out,'tatums_confidence':tatums_confidence,'tatums_start':tatums_start,'tempo':tempo,'time_signature_confidence':time_signature_confidence,'time_signature':time_signature,'title':title,'track_7digitalid':track_7digitalid,'track_id':track_id,'year':year,} row = {'analysis_sample_rate':analysis_sample_rate,'artist_7digitalid':artist_7digitalid,'artist_familiarity':artist_familiarity,'artist_hotttnesss':artist_hotttnesss,'artist_id':artist_id,'artist_latitude':artist_latitude,'artist_location':artist_location,'artist_longitude':artist_longitude,'artist_mbid':artist_mbid,'artist_mbtags_count':artist_mbtags_count,'artist_mbtags':artist_mbtags,'artist_name':artist_name,'artist_terms':artist_terms,'danceability':danceability,'duration':duration,'end_of_fade_in':end_of_fade_in,'energy':energy,'key_confidence':key_confidence,'key':key,'loudness':loudness,'mode_confidence':mode_confidence,'mode':mode,'release_7digitalid':release_7digitalid,'release':release,'similar_artists':similar_artists,'song_hotttnesss':song_hotttnesss,'song_id':song_id,'start_of_fade_out':start_of_fade_out,'tempo':tempo,'time_signature_confidence':time_signature_confidence,'time_signature':time_signature,'title':title,'track_7digitalid':track_7digitalid,'track_id':track_id,'year':year, } key = (row['track_id']) #for k, v in row.items(): print k, type(v) cf.insert(key,row) #print "Artist: %s\nSong: %s\nDuration: %s\nYear: %s\nHotness: %s\nLoudness: %s\nDanceability:%s\n\n" % (artist_name, title, duration, year, song_hotttnesss, loudness, danceability)
def data_to_flat_file(basedir,ext='.h5') : """ This function extracts the information from the tables and creates the flat file. """ count = 0; #song counter list_to_write= [] group_index=0 row_to_write = "" writer = csv.writer(open("complete.csv", "wb")) for root, dirs, files in os.walk(basedir): files = glob.glob(os.path.join(root,'*'+ext)) for f in files: row=[] print f h5 = hdf5_getters.open_h5_file_read(f) title = hdf5_getters.get_title(h5) title= title.replace('"','') row.append(title) comma=title.find(',') if comma != -1: print title time.sleep(1) album = hdf5_getters.get_release(h5) album= album.replace('"','') row.append(album) comma=album.find(',') if comma != -1: print album time.sleep(1) artist_name = hdf5_getters.get_artist_name(h5) comma=artist_name.find(',') if comma != -1: print artist_name time.sleep(1) artist_name= artist_name.replace('"','') row.append(artist_name) duration = hdf5_getters.get_duration(h5) row.append(duration) samp_rt = hdf5_getters.get_analysis_sample_rate(h5) row.append(samp_rt) artist_7digitalid = hdf5_getters.get_artist_7digitalid(h5) row.append(artist_7digitalid) artist_fam = hdf5_getters.get_artist_familiarity(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(artist_fam) == True: artist_fam=-1 row.append(artist_fam) artist_hotness= hdf5_getters.get_artist_hotttnesss(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(artist_hotness) == True: artist_hotness=-1 row.append(artist_hotness) artist_id = hdf5_getters.get_artist_id(h5) row.append(artist_id) artist_lat = hdf5_getters.get_artist_latitude(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(artist_lat) == True: artist_lat=-1 row.append(artist_lat) artist_loc = hdf5_getters.get_artist_location(h5) row.append(artist_loc) artist_lon = hdf5_getters.get_artist_longitude(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(artist_lon) == True: artist_lon=-1 row.append(artist_lon) artist_mbid = hdf5_getters.get_artist_mbid(h5) row.append(artist_mbid) #Getting the genre art_trm = hdf5_getters.get_artist_terms(h5) trm_freq = hdf5_getters.get_artist_terms_freq(h5) trn_wght = hdf5_getters.get_artist_terms_weight(h5) a_mb_tags = hdf5_getters.get_artist_mbtags(h5) genre_indexes=get_genre_indexes(trm_freq) #index of the highest freq genre_set=0 #flag to see if the genre has been set or not final_genre=[] genres_so_far=[] for i in range(len(genre_indexes)): genre_tmp=get_genre(art_trm,genre_indexes[i]) #genre that corresponds to the highest freq genres_so_far=genre_dict.get_genre_in_dict(genre_tmp) #getting the genre from the dictionary if len(genres_so_far) != 0: for i in genres_so_far: final_genre.append(i) genre_set=1 if genre_set == 1: col_num=[] for i in final_genre: column=int(i) #getting the column number of the genre col_num.append(column) genre_array=genre_columns(col_num) #genre array for i in range(len(genre_array)): #appending the genre_array to the row row.append(genre_array[i]) else: genre_array=genre_columns(-1) #when there is no genre matched, return an array of [0...0] for i in range(len(genre_array)): #appending the genre_array to the row row.append(genre_array[i]) artist_pmid = hdf5_getters.get_artist_playmeid(h5) row.append(artist_pmid) audio_md5 = hdf5_getters.get_audio_md5(h5) row.append(audio_md5) danceability = hdf5_getters.get_danceability(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(danceability) == True: danceability=-1 row.append(danceability) end_fade_in =hdf5_getters.get_end_of_fade_in(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(end_fade_in) == True: end_fade_in=-1 row.append(end_fade_in) energy = hdf5_getters.get_energy(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(energy) == True: energy=-1 row.append(energy) song_key = hdf5_getters.get_key(h5) row.append(song_key) key_c = hdf5_getters.get_key_confidence(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(key_c) == True: key_c=-1 row.append(key_c) loudness = hdf5_getters.get_loudness(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(loudness) == True: loudness=-1 row.append(loudness) mode = hdf5_getters.get_mode(h5) row.append(mode) mode_conf = hdf5_getters.get_mode_confidence(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(mode_conf) == True: mode_conf=-1 row.append(mode_conf) release_7digitalid = hdf5_getters.get_release_7digitalid(h5) row.append(release_7digitalid) song_hot = hdf5_getters.get_song_hotttnesss(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(song_hot) == True: song_hot=-1 row.append(song_hot) song_id = hdf5_getters.get_song_id(h5) row.append(song_id) start_fade_out = hdf5_getters.get_start_of_fade_out(h5) row.append(start_fade_out) tempo = hdf5_getters.get_tempo(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(tempo) == True: tempo=-1 row.append(tempo) time_sig = hdf5_getters.get_time_signature(h5) row.append(time_sig) time_sig_c = hdf5_getters.get_time_signature_confidence(h5) #checking if we get a "nan" if we do we change it to -1 if numpy.isnan(time_sig_c) == True: time_sig_c=-1 row.append(time_sig_c) track_id = hdf5_getters.get_track_id(h5) row.append(track_id) track_7digitalid = hdf5_getters.get_track_7digitalid(h5) row.append(track_7digitalid) year = hdf5_getters.get_year(h5) row.append(year) bars_c = hdf5_getters.get_bars_confidence(h5) bars_start = hdf5_getters.get_bars_start(h5) row_bars_padding=padding(245) #this is the array that will be attached at the end of th row #--------------bars---------------" gral_info=[] gral_info=row[:] empty=[] for i,item in enumerate(bars_c): row.append(group_index) row.append(i) row.append(bars_c[i]) bars_c_avg= get_avg(bars_c) row.append(bars_c_avg) bars_c_max= get_max(bars_c) row.append(bars_c_max) bars_c_min = get_min(bars_c) row.append(bars_c_min) bars_c_stddev= get_stddev(bars_c) row.append(bars_c_stddev) bars_c_count = get_count(bars_c) row.append(bars_c_count) bars_c_sum = get_sum(bars_c) row.append(bars_c_sum) row.append(bars_start[i]) bars_start_avg = get_avg(bars_start) row.append(bars_start_avg) bars_start_max= get_max(bars_start) row.append(bars_start_max) bars_start_min = get_min(bars_start) row.append(bars_start_min) bars_start_stddev= get_stddev(bars_start) row.append(bars_start_stddev) bars_start_count = get_count(bars_start) row.append(bars_start_count) bars_start_sum = get_sum(bars_start) row.append(bars_start_sum) for i in row_bars_padding: row.append(i) writer.writerow(row) row=[] row=gral_info[:] #--------beats---------------" beats_c = hdf5_getters.get_beats_confidence(h5) group_index=1 row=[] row=gral_info[:] row_front=padding(14) #blanks left in front of the row(empty spaces for bars) row_beats_padding=padding(231) for i,item in enumerate(beats_c): row.append(group_index) row.append(i) for index in row_front: #padding blanks in front of the beats row.append(index) row.append(beats_c[i]) beats_c_avg= get_avg(beats_c) row.append(beats_c_avg) beats_c_max= get_max(beats_c) row.append(beats_c_max) beats_c_min = get_min(beats_c) row.append(beats_c_min) beats_c_stddev= get_stddev(beats_c) row.append(beats_c_stddev) beats_c_count = get_count(beats_c) row.append(beats_c_count) beats_c_sum = get_sum(beats_c) row.append(beats_c_sum) beats_start = hdf5_getters.get_beats_start(h5) row.append(beats_start[i]) beats_start_avg = get_avg(beats_start) row.append(beats_start_avg) beats_start_max= get_max(beats_start) row.append(beats_start_max) beats_start_min = get_min(beats_start) row.append(beats_start_min) beats_start_stddev= get_stddev(beats_start) row.append(beats_start_stddev) beats_start_count = get_count(beats_start) row.append(beats_start_count) beats_start_sum = get_sum(beats_start) row.append(beats_start_sum) for i in row_beats_padding: row.append(i) writer.writerow(row) row=[] row=gral_info[:] # "--------sections---------------" row_sec_padding=padding(217) #blank spaces left at the end of the row sec_c = hdf5_getters.get_sections_confidence(h5) group_index=2 row=[] row=gral_info[:] row_front=padding(28) #blank spaces left in front(empty spaces for bars,beats) for i,item in enumerate(sec_c): row.append(group_index) row.append(i) for index in row_front: #padding blanks in front of the sections row.append(index) row.append(sec_c[i]) sec_c_avg= get_avg(sec_c) row.append(sec_c_avg) sec_c_max= get_max(sec_c) row.append(sec_c_max) sec_c_min = get_min(sec_c) row.append(sec_c_min) sec_c_stddev= get_stddev(sec_c) row.append(sec_c_stddev) sec_c_count = get_count(sec_c) row.append(sec_c_count) sec_c_sum = get_sum(sec_c) row.append(sec_c_sum) sec_start = hdf5_getters.get_sections_start(h5) row.append(sec_start[i]) sec_start_avg = get_avg(sec_start) row.append(sec_start_avg) sec_start_max= get_max(sec_start) row.append(sec_start_max) sec_start_min = get_min(sec_start) row.append(sec_start_min) sec_start_stddev= get_stddev(sec_start) row.append(sec_start_stddev) sec_start_count = get_count(sec_start) row.append(sec_start_count) sec_start_sum = get_sum(sec_start) row.append(sec_start_sum) for i in row_sec_padding: #appending the blank spaces at the end of the row row.append(i) writer.writerow(row) row=[] row=gral_info[:] #--------segments---------------" row_seg_padding=padding(182) #blank spaces at the end of the row row_front=padding(42) #blank spaces left in front of segments seg_c = hdf5_getters.get_segments_confidence(h5) group_index=3 row=[] row=gral_info[:] for i,item in enumerate(seg_c): row.append(group_index) row.append(i) for index in row_front: #padding blanks in front of the segments row.append(index) row.append(seg_c[i]) seg_c_avg= get_avg(seg_c) row.append(seg_c_avg) seg_c_max= get_max(seg_c) row.append(seg_c_max) seg_c_min = get_min(seg_c) row.append(seg_c_min) seg_c_stddev= get_stddev(seg_c) row.append(seg_c_stddev) seg_c_count = get_count(seg_c) row.append(seg_c_count) seg_c_sum = get_sum(seg_c) row.append(seg_c_sum) seg_loud_max = hdf5_getters.get_segments_loudness_max(h5) row.append(seg_loud_max[i]) seg_loud_max_avg= get_avg(seg_loud_max) row.append(seg_loud_max_avg) seg_loud_max_max= get_max(seg_loud_max) row.append(seg_loud_max_max) seg_loud_max_min = get_min(seg_loud_max) row.append(seg_loud_max_min) seg_loud_max_stddev= get_stddev(seg_loud_max) row.append(seg_loud_max_stddev) seg_loud_max_count = get_count(seg_loud_max) row.append(seg_loud_max_count) seg_loud_max_sum = get_sum(seg_loud_max) row.append(seg_loud_max_sum) seg_loud_max_time = hdf5_getters.get_segments_loudness_max_time(h5) row.append(seg_loud_max_time[i]) seg_loud_max_time_avg= get_avg(seg_loud_max_time) row.append(seg_loud_max_time_avg) seg_loud_max_time_max= get_max(seg_loud_max_time) row.append(seg_loud_max_time_max) seg_loud_max_time_min = get_min(seg_loud_max_time) row.append(seg_loud_max_time_min) seg_loud_max_time_stddev= get_stddev(seg_loud_max_time) row.append(seg_loud_max_time_stddev) seg_loud_max_time_count = get_count(seg_loud_max_time) row.append(seg_loud_max_time_count) seg_loud_max_time_sum = get_sum(seg_loud_max_time) row.append(seg_loud_max_time_sum) seg_loud_start = hdf5_getters.get_segments_loudness_start(h5) row.append(seg_loud_start[i]) seg_loud_start_avg= get_avg(seg_loud_start) row.append(seg_loud_start_avg) seg_loud_start_max= get_max(seg_loud_start) row.append(seg_loud_start_max) seg_loud_start_min = get_min(seg_loud_start) row.append(seg_loud_start_min) seg_loud_start_stddev= get_stddev(seg_loud_start) row.append(seg_loud_start_stddev) seg_loud_start_count = get_count(seg_loud_start) row.append(seg_loud_start_count) seg_loud_start_sum = get_sum(seg_loud_start) row.append(seg_loud_start_sum) seg_start = hdf5_getters.get_segments_start(h5) row.append(seg_start[i]) seg_start_avg= get_avg(seg_start) row.append(seg_start_avg) seg_start_max= get_max(seg_start) row.append(seg_start_max) seg_start_min = get_min(seg_start) row.append(seg_start_min) seg_start_stddev= get_stddev(seg_start) row.append(seg_start_stddev) seg_start_count = get_count(seg_start) row.append(seg_start_count) seg_start_sum = get_sum(seg_start) row.append(seg_start_sum) for i in row_seg_padding: #appending blank spaces at the end of the row row.append(i) writer.writerow(row) row=[] row=gral_info[:] #----------segments pitch and timbre---------------" row_seg2_padding=padding(14) #blank spaces left at the end of the row row_front=padding(77) #blank spaces left at the front of the segments and timbre seg_pitch = hdf5_getters.get_segments_pitches(h5) transpose_pitch= seg_pitch.transpose() #this is to tranpose the matrix,so we can have 12 rows group_index=4 row=[] row=gral_info[:] for i,item in enumerate(transpose_pitch[0]): row.append(group_index) row.append(i) for index in row_front: #padding blanks in front of segments and timbre row.append(index) row.append(transpose_pitch[0][i]) seg_pitch_avg= get_avg(transpose_pitch[0]) row.append(seg_pitch_avg) seg_pitch_max= get_max(transpose_pitch[0]) row.append(seg_pitch_max) seg_pitch_min = get_min(transpose_pitch[0]) row.append(seg_pitch_min) seg_pitch_stddev= get_stddev(transpose_pitch[0]) row.append(seg_pitch_stddev) seg_pitch_count = get_count(transpose_pitch[0]) row.append(seg_pitch_count) seg_pitch_sum = get_sum(transpose_pitch[0]) row.append(seg_pitch_sum) row.append(transpose_pitch[1][i]) seg_pitch_avg= get_avg(transpose_pitch[1]) row.append(seg_pitch_avg) seg_pitch_max= get_max(transpose_pitch[1]) row.append(seg_pitch_max) seg_pitch_min = get_min(transpose_pitch[1]) row.append(seg_pitch_min) seg_pitch_stddev= get_stddev(transpose_pitch[1]) row.append(seg_pitch_stddev) seg_pitch_count = get_count(transpose_pitch[1]) row.append(seg_pitch_count) seg_pitch_sum = get_sum(transpose_pitch[1]) row.append(seg_pitch_sum) row.append(transpose_pitch[2][i]) seg_pitch_avg= get_avg(transpose_pitch[2]) row.append(seg_pitch_avg) seg_pitch_max= get_max(transpose_pitch[2]) row.append(seg_pitch_max) seg_pitch_min = get_min(transpose_pitch[2]) row.append(seg_pitch_min) seg_pitch_stddev= get_stddev(transpose_pitch[2]) row.append(seg_pitch_stddev) seg_pitch_count = get_count(transpose_pitch[2]) row.append(seg_pitch_count) seg_pitch_sum = get_sum(transpose_pitch[2]) row.append(seg_pitch_sum) row.append(transpose_pitch[3][i]) seg_pitch_avg= get_avg(transpose_pitch[3]) row.append(seg_pitch_avg) seg_pitch_max= get_max(transpose_pitch[3]) row.append(seg_pitch_max) seg_pitch_min = get_min(transpose_pitch[3]) row.append(seg_pitch_min) seg_pitch_stddev= get_stddev(transpose_pitch[3]) row.append(seg_pitch_stddev) seg_pitch_count = get_count(transpose_pitch[3]) row.append(seg_pitch_count) seg_pitch_sum = get_sum(transpose_pitch[3]) row.append(seg_pitch_sum) row.append(transpose_pitch[4][i]) seg_pitch_avg= get_avg(transpose_pitch[4]) row.append(seg_pitch_avg) seg_pitch_max= get_max(transpose_pitch[4]) row.append(seg_pitch_max) seg_pitch_min = get_min(transpose_pitch[4]) row.append(seg_pitch_min) seg_pitch_stddev= get_stddev(transpose_pitch[4]) row.append(seg_pitch_stddev) seg_pitch_count = get_count(transpose_pitch[4]) row.append(seg_pitch_count) seg_pitch_sum = get_sum(transpose_pitch[4]) row.append(seg_pitch_sum) row.append(transpose_pitch[5][i]) seg_pitch_avg= get_avg(transpose_pitch[5]) row.append(seg_pitch_avg) seg_pitch_max= get_max(transpose_pitch[5]) row.append(seg_pitch_max) seg_pitch_min = get_min(transpose_pitch[5]) row.append(seg_pitch_min) seg_pitch_stddev= get_stddev(transpose_pitch[5]) row.append(seg_pitch_stddev) seg_pitch_count = get_count(transpose_pitch[5]) row.append(seg_pitch_count) seg_pitch_sum = get_sum(transpose_pitch[5]) row.append(seg_pitch_sum) row.append(transpose_pitch[6][i]) seg_pitch_avg= get_avg(transpose_pitch[6]) row.append(seg_pitch_avg) seg_pitch_max= get_max(transpose_pitch[6]) row.append(seg_pitch_max) seg_pitch_min = get_min(transpose_pitch[6]) row.append(seg_pitch_min) seg_pitch_stddev= get_stddev(transpose_pitch[6]) row.append(seg_pitch_stddev) seg_pitch_count = get_count(transpose_pitch[6]) row.append(seg_pitch_count) seg_pitch_sum = get_sum(transpose_pitch[6]) row.append(seg_pitch_sum) row.append(transpose_pitch[7][i]) seg_pitch_avg= get_avg(transpose_pitch[7]) row.append(seg_pitch_avg) seg_pitch_max= get_max(transpose_pitch[7]) row.append(seg_pitch_max) seg_pitch_min = get_min(transpose_pitch[7]) row.append(seg_pitch_min) seg_pitch_stddev= get_stddev(transpose_pitch[7]) row.append(seg_pitch_stddev) seg_pitch_count = get_count(transpose_pitch[7]) row.append(seg_pitch_count) seg_pitch_sum = get_sum(transpose_pitch[7]) row.append(seg_pitch_sum) row.append(transpose_pitch[8][i]) seg_pitch_avg= get_avg(transpose_pitch[8]) row.append(seg_pitch_avg) seg_pitch_max= get_max(transpose_pitch[8]) row.append(seg_pitch_max) seg_pitch_min = get_min(transpose_pitch[8]) row.append(seg_pitch_min) seg_pitch_stddev= get_stddev(transpose_pitch[8]) row.append(seg_pitch_stddev) seg_pitch_count = get_count(transpose_pitch[8]) row.append(seg_pitch_count) seg_pitch_sum = get_sum(transpose_pitch[8]) row.append(seg_pitch_sum) row.append(transpose_pitch[9][i]) seg_pitch_avg= get_avg(transpose_pitch[9]) row.append(seg_pitch_avg) seg_pitch_max= get_max(transpose_pitch[9]) row.append(seg_pitch_max) seg_pitch_min = get_min(transpose_pitch[9]) row.append(seg_pitch_min) seg_pitch_stddev= get_stddev(transpose_pitch[9]) row.append(seg_pitch_stddev) seg_pitch_count = get_count(transpose_pitch[9]) row.append(seg_pitch_count) seg_pitch_sum = get_sum(transpose_pitch[9]) row.append(seg_pitch_sum) row.append(transpose_pitch[10][i]) seg_pitch_avg= get_avg(transpose_pitch[10]) row.append(seg_pitch_avg) seg_pitch_max= get_max(transpose_pitch[10]) row.append(seg_pitch_max) seg_pitch_min = get_min(transpose_pitch[10]) row.append(seg_pitch_min) seg_pitch_stddev= get_stddev(transpose_pitch[10]) row.append(seg_pitch_stddev) seg_pitch_count = get_count(transpose_pitch[10]) row.append(seg_pitch_count) seg_pitch_sum = get_sum(transpose_pitch[10]) row.append(seg_pitch_sum) row.append(transpose_pitch[11][i]) seg_pitch_avg= get_avg(transpose_pitch[11]) row.append(seg_pitch_avg) seg_pitch_max= get_max(transpose_pitch[11]) row.append(seg_pitch_max) seg_pitch_min = get_min(transpose_pitch[11]) row.append(seg_pitch_min) seg_pitch_stddev= get_stddev(transpose_pitch[11]) row.append(seg_pitch_stddev) seg_pitch_count = get_count(transpose_pitch[11]) row.append(seg_pitch_count) seg_pitch_sum = get_sum(transpose_pitch[11]) row.append(seg_pitch_sum) #timbre arrays seg_timbre = hdf5_getters.get_segments_timbre(h5) transpose_timbre = seg_pitch.transpose() #tranposing matrix, to have 12 rows row.append(transpose_timbre[0][i]) seg_timbre_avg= get_avg(transpose_timbre[0]) row.append(seg_timbre_avg) seg_timbre_max= get_max(transpose_timbre[0]) row.append(seg_timbre_max) seg_timbre_min = get_min(transpose_timbre[0]) row.append(seg_timbre_min) seg_timbre_stddev=get_stddev(transpose_timbre[0]) row.append(seg_timbre_stddev) seg_timbre_count = get_count(transpose_timbre[0]) row.append(seg_timbre_count) seg_timbre_sum = get_sum(transpose_timbre[0]) row.append(seg_timbre_sum) row.append(transpose_timbre[1][i]) seg_timbre_avg= get_avg(transpose_timbre[1]) row.append(seg_timbre_avg) seg_timbre_max= get_max(transpose_timbre[1]) row.append(seg_timbre_max) seg_timbre_min = get_min(transpose_timbre[1]) row.append(seg_timbre_min) seg_timbre_stddev= get_stddev(transpose_timbre[1]) row.append(seg_timbre_stddev) seg_timbre_count = get_count(transpose_timbre[1]) row.append(seg_timbre_count) seg_timbre_sum = get_sum(transpose_timbre[1]) row.append(seg_timbre_sum) row.append(transpose_timbre[2][i]) seg_timbre_avg= get_avg(transpose_timbre[2]) row.append(seg_timbre_avg) seg_timbre_max= get_max(transpose_timbre[2]) row.append(seg_timbre_max) seg_timbre_min = get_min(transpose_timbre[2]) row.append(seg_timbre_min) seg_timbre_stddev= get_stddev(transpose_timbre[2]) row.append(seg_timbre_stddev) seg_timbre_count = get_count(transpose_timbre[2]) row.append(seg_timbre_count) seg_timbre_sum = get_sum(transpose_timbre[2]) row.append(seg_timbre_sum) row.append(transpose_timbre[3][i]) seg_timbre_avg= get_avg(transpose_timbre[3]) row.append(seg_timbre_avg) seg_timbre_max= get_max(transpose_timbre[3]) row.append(seg_timbre_max) seg_timbre_min = get_min(transpose_timbre[3]) row.append(seg_timbre_min) seg_timbre_stddev= get_stddev(transpose_timbre[3]) row.append(seg_timbre_stddev) seg_timbre_count = get_count(transpose_timbre[3]) row.append(seg_timbre_count) seg_timbre_sum = get_sum(transpose_timbre[3]) row.append(seg_timbre_sum) row.append(transpose_timbre[4][i]) seg_timbre_avg= get_avg(transpose_timbre[4]) row.append(seg_timbre_avg) seg_timbre_max= get_max(transpose_timbre[4]) row.append(seg_timbre_max) seg_timbre_min = get_min(transpose_timbre[4]) row.append(seg_timbre_min) seg_timbre_stddev= get_stddev(transpose_timbre[4]) row.append(seg_timbre_stddev) seg_timbre_count = get_count(transpose_timbre[4]) row.append(seg_timbre_count) seg_timbre_sum = get_sum(transpose_timbre[4]) row.append(seg_timbre_sum) row.append(transpose_timbre[5][i]) seg_timbre_avg= get_avg(transpose_timbre[5]) row.append(seg_timbre_avg) seg_timbre_max= get_max(transpose_timbre[5]) row.append(seg_timbre_max) seg_timbre_min = get_min(transpose_timbre[5]) row.append(seg_timbre_min) seg_timbre_stddev= get_stddev(transpose_timbre[5]) row.append(seg_timbre_stddev) seg_timbre_count = get_count(transpose_timbre[5]) row.append(seg_timbre_count) seg_timbre_sum = get_sum(transpose_timbre[5]) row.append(seg_timbre_sum) row.append(transpose_timbre[6][i]) seg_timbre_avg= get_avg(transpose_timbre[6]) row.append(seg_timbre_avg) seg_timbre_max= get_max(transpose_timbre[6]) row.append(seg_timbre_max) seg_timbre_min = get_min(transpose_timbre[6]) row.append(seg_timbre_min) seg_timbre_stddev= get_stddev(transpose_timbre[6]) row.append(seg_timbre_stddev) seg_timbre_count = get_count(transpose_timbre[6]) row.append(seg_timbre_count) seg_timbre_sum = get_sum(transpose_timbre[6]) row.append(seg_timbre_sum) row.append(transpose_timbre[7][i]) seg_timbre_avg= get_avg(transpose_timbre[7]) row.append(seg_timbre_avg) seg_timbre_max= get_max(transpose_timbre[7]) row.append(seg_timbre_max) seg_timbre_min = get_min(transpose_timbre[7]) row.append(seg_timbre_min) seg_timbre_stddev= get_stddev(transpose_timbre[7]) row.append(seg_timbre_stddev) seg_timbre_count = get_count(transpose_timbre[7]) row.append(seg_timbre_count) seg_timbre_sum = get_sum(transpose_timbre[7]) row.append(seg_timbre_sum) row.append(transpose_timbre[8][i]) seg_timbre_avg= get_avg(transpose_timbre[8]) row.append(seg_timbre_avg) seg_timbre_max= get_max(transpose_timbre[8]) row.append(seg_timbre_max) seg_timbre_min = get_min(transpose_timbre[8]) row.append(seg_timbre_min) seg_timbre_stddev= get_stddev(transpose_timbre[8]) row.append(seg_timbre_stddev) seg_timbre_count = get_count(transpose_timbre[8]) row.append(seg_timbre_count) seg_timbre_sum = get_sum(transpose_timbre[8]) row.append(seg_timbre_sum) row.append(transpose_timbre[9][i]) seg_timbre_avg= get_avg(transpose_timbre[9]) row.append(seg_timbre_avg) seg_timbre_max= get_max(transpose_timbre[9]) row.append(seg_timbre_max) seg_timbre_min = get_min(transpose_timbre[9]) row.append(seg_timbre_min) seg_timbre_stddev= get_stddev(transpose_timbre[9]) row.append(seg_timbre_stddev) seg_timbre_count = get_count(transpose_timbre[9]) row.append(seg_timbre_count) seg_timbre_sum = get_sum(transpose_timbre[9]) row.append(seg_timbre_sum) row.append(transpose_timbre[10][i]) seg_timbre_avg= get_avg(transpose_timbre[10]) row.append(seg_timbre_avg) seg_timbre_max= get_max(transpose_timbre[10]) row.append(seg_timbre_max) seg_timbre_min = get_min(transpose_timbre[10]) row.append(seg_timbre_min) seg_timbre_stddev= get_stddev(transpose_timbre[10]) row.append(seg_timbre_stddev) seg_timbre_count = get_count(transpose_timbre[10]) row.append(seg_timbre_count) seg_timbre_sum = get_sum(transpose_timbre[10]) row.append(seg_timbre_sum) row.append(transpose_timbre[11][i]) seg_timbre_avg= get_avg(transpose_timbre[11]) row.append(seg_timbre_avg) seg_timbre_max= get_max(transpose_timbre[11]) row.append(seg_timbre_max) seg_timbre_min = get_min(transpose_timbre[11]) row.append(seg_timbre_min) seg_timbre_stddev= get_stddev(transpose_timbre[11]) row.append(seg_timbre_stddev) seg_timbre_count = get_count(transpose_timbre[11]) row.append(seg_timbre_count) seg_timbre_sum = get_sum(transpose_timbre[11]) row.append(seg_timbre_sum) for item in row_seg2_padding: row.append(item) writer.writerow(row) row=[] row=gral_info[:] # "--------tatums---------------" tatms_c = hdf5_getters.get_tatums_confidence(h5) group_index=5 row_front=padding(245) #blank spaces left in front of tatums row=[] row=gral_info[:] for i,item in enumerate(tatms_c): row.append(group_index) row.append(i) for item in row_front: #appending blank spaces at the front of the row row.append(item) row.append(tatms_c[i]) tatms_c_avg= get_avg(tatms_c) row.append(tatms_c_avg) tatms_c_max= get_max(tatms_c) row.append(tatms_c_max) tatms_c_min = get_min(tatms_c) row.append(tatms_c_min) tatms_c_stddev= get_stddev(tatms_c) row.append(tatms_c_stddev) tatms_c_count = get_count(tatms_c) row.append(tatms_c_count) tatms_c_sum = get_sum(tatms_c) row.append(tatms_c_sum) tatms_start = hdf5_getters.get_tatums_start(h5) row.append(tatms_start[i]) tatms_start_avg= get_avg(tatms_start) row.append(tatms_start_avg) tatms_start_max= get_max(tatms_start) row.append(tatms_start_max) tatms_start_min = get_min(tatms_start) row.append(tatms_start_min) tatms_start_stddev= get_stddev(tatms_start) row.append(tatms_start_stddev) tatms_start_count = get_count(tatms_start) row.append(tatms_start_count) tatms_start_sum = get_sum(tatms_start) row.append(tatms_start_sum) writer.writerow(row) row=[] row=gral_info[:] transpose_pitch= seg_pitch.transpose() #this is to tranpose the matrix,so we can have 12 rows #arrays containing the aggregate values of the 12 rows seg_pitch_avg=[] seg_pitch_max=[] seg_pitch_min=[] seg_pitch_stddev=[] seg_pitch_count=[] seg_pitch_sum=[] i=0 #Getting the aggregate values in the pitches array for row in transpose_pitch: seg_pitch_avg.append(get_avg(row)) seg_pitch_max.append(get_max(row)) seg_pitch_min.append(get_min(row)) seg_pitch_stddev.append(get_stddev(row)) seg_pitch_count.append(get_count(row)) seg_pitch_sum.append(get_sum(row)) i=i+1 #extracting information from the timbre array transpose_timbre = seg_pitch.transpose() #tranposing matrix, to have 12 rows #arrays containing the aggregate values of the 12 rows seg_timbre_avg=[] seg_timbre_max=[] seg_timbre_min=[] seg_timbre_stddev=[] seg_timbre_count=[] seg_timbre_sum=[] i=0 for row in transpose_timbre: seg_timbre_avg.append(get_avg(row)) seg_timbre_max.append(get_max(row)) seg_timbre_min.append(get_min(row)) seg_timbre_stddev.append(get_stddev(row)) seg_timbre_count.append(get_count(row)) seg_timbre_sum.append(get_sum(row)) i=i+1 h5.close() count=count+1; print count;
def process_filelist_test(filelist=None, model=None, tmpfilename=None, npicks=None, winsize=None, finaldim=None, K=1, typecompress='picks'): """ Main function, process all files in the list (as long as their artist is in testartist) INPUT filelist - a list of song files model - h5 file containing feats and year for all train songs tmpfilename - where to save our processed features npicks - number of segments to pick per song winsize - size of each segment we pick finaldim - how many values do we keep K - param of KNN (default 1) typecompress - feature type, 'picks', 'corrcoeff' or 'cov' must be the same as in training """ # sanity check for arg in locals().values(): assert not arg is None, 'process_filelist_test, missing an argument, something still None' if os.path.isfile(tmpfilename): print 'ERROR: file', tmpfilename, 'already exists.' return if not os.path.isfile(model): print 'ERROR: model', model, 'does not exist.' return # create kdtree h5model = tables.openFile(model, mode='r') assert h5model.root.data.feats.shape[ 1] == finaldim, 'inconsistency in final dim' kd = ANN.kdtree(h5model.root.data.feats) # create outputfile output = tables.openFile(tmpfilename, mode='a') group = output.createGroup("/", 'data', 'TMP FILE FOR YEAR RECOGNITION') output.createEArray(group, 'year_real', tables.IntAtom(shape=()), (0, ), '', expectedrows=len(filelist)) output.createEArray(group, 'year_pred', tables.Float64Atom(shape=()), (0, ), '', expectedrows=len(filelist)) # random projection ndim = 12 # fixed in this dataset if typecompress == 'picks': randproj = RANDPROJ.proj_point5(ndim * winsize, finaldim) elif typecompress == 'corrcoeff' or typecompress == 'cov': randproj = RANDPROJ.proj_point5(ndim * ndim, finaldim) elif typecompress == 'avgcov': randproj = RANDPROJ.proj_point5(90, finaldim) else: assert False, 'Unknown type of compression: ' + str(typecompress) # go through files cnt_f = 0 for f in filelist: cnt_f += 1 if cnt_f % 5000 == 0: print 'TESTING FILE #' + str(cnt_f) # check file h5 = GETTERS.open_h5_file_read(f) artist_id = GETTERS.get_artist_id(h5) year = GETTERS.get_year(h5) track_id = GETTERS.get_track_id(h5) h5.close() if year <= 0: # probably useless but... continue if typecompress == 'picks': # we have a train artist with a song year, we're good bttimbre = get_bttimbre(f) if bttimbre is None: continue # we even have normal features, awesome! processed_feats = CBTF.extract_and_compress(bttimbre, npicks, winsize, finaldim, randproj=randproj) elif typecompress == 'corrcoeff': h5 = GETTERS.open_h5_file_read(f) timbres = GETTERS.get_segments_timbre(h5).T h5.close() processed_feats = CBTF.corr_and_compress(timbres, finaldim, randproj=randproj) elif typecompress == 'cov': h5 = GETTERS.open_h5_file_read(f) timbres = GETTERS.get_segments_timbre(h5).T h5.close() processed_feats = CBTF.cov_and_compress(timbres, finaldim, randproj=randproj) elif typecompress == 'avgcov': h5 = GETTERS.open_h5_file_read(f) timbres = GETTERS.get_segments_timbre(h5).T h5.close() processed_feats = CBTF.avgcov_and_compress(timbres, finaldim, randproj=randproj) else: assert False, 'Unknown type of compression: ' + str(typecompress) if processed_feats is None: continue if processed_feats.shape[0] == 0: continue # do prediction year_pred = do_prediction(processed_feats, kd, h5model, K) # add pred and ground truth to output if not year_pred is None: output.root.data.year_real.append([year]) output.root.data.year_pred.append([year_pred]) # close output and model del kd h5model.close() output.close() # done return
def write_line(output, getter,data,song_nb): line = hdf5_getters.get_track_id(data).decode('UTF-8') h5getter = getattr(hdf5_getters, getter) line += '\t' + toJson(h5getter(data,song_nb)) line += '\n' output.write(line)
counter = 0 file_io_counter = 0 for root, dirs, files in os.walk(os.getcwd()): for name in files: if name.endswith(".h5"): if process_completion % 10000 == 0: print "done :", process_completion/10000.0, "%" process_completion += 1 else: process_completion += 1 tempPath = os.path.abspath(os.path.join(root,name)) h5file = hdf5_getters.open_h5_file_read(tempPath) #data extract 1 track_id_str = hdf5_getters.get_track_id(h5file) song_id_str = hdf5_getters.get_song_id(h5file) album_name_str = unicodedata.normalize('NFKD', unicode(hdf5_getters.get_release(h5file),encoding='ASCII',errors='ignore')) album_name_str = str(album_name_str).replace(","," ").replace("'","").replace("-"," ").replace("("," ").replace(")"," ").replace("/"," ").replace("\\"," ") year_str = str(hdf5_getters.get_year(h5file)) counter += 1 file_io_counter += 1 if file_io_counter % 100 == 0: if counter == 1: my_array_data_extract_1 = numpy.array([track_id_str, song_id_str, album_name_str, year_str]) else : my_array_data_extract_1 = numpy.vstack((my_array_data_extract_1,numpy.array([track_id_str, song_id_str, album_name_str, year_str]))) f_handle = file('msd_data_extract_1.bin','a') numpy.savetxt(f_handle, my_array_data_extract_1, delimiter='|',fmt='%s')
# This script converts the summary H5 files only 300MB to a csv file # Run only on the Master Node since h5_getters cannot open a remote(ie. HDFS) file if __name__ == "__main__": with open("fields.csv", "wb") as f: writer = csv.writer(f) #initialize the csv writer # for each track in the summary file, get the 11 fields and output to csv h5_file = hdf5_getters.open_h5_file_read('msd_summary_file.h5') for k in range(1000000): print "index!!!: ", k id = hdf5_getters.get_track_id(h5_file,k) #get track_id TRA13e39.. title = hdf5_getters.get_title(h5_file,k) # get song title artist_name = hdf5_getters.get_artist_name(h5_file,k) year = int(hdf5_getters.get_year(h5_file,k)) hotness= float(hdf5_getters.get_song_hotttnesss(h5_file,k)) artist_familiarity = float(hdf5_getters.get_artist_familiarity(h5_file,k)) f5 = int(hdf5_getters.get_key(h5_file,k)) #get key f2 = float(hdf5_getters.get_loudness(h5_file,k)) #get loudness f1 = float(hdf5_getters.get_tempo(h5_file,k)) #get tempo f4 = int(hdf5_getters.get_duration(h5_file,k)) #get duration f3 = float(hdf5_getters.get_time_signature(h5_file,k)) #get time signature # Get rid of missing info and change invalid numbers for meta data if not artist_name:
def main(): outputFile1 = open('SongCSV.csv', 'w') csvRowString = "" ################################################# #if you want to prompt the user for the order of attributes in the csv, #leave the prompt boolean set to True #else, set 'prompt' to False and set the order of attributes in the 'else' #clause prompt = False ################################################# if prompt == True: while prompt: prompt = False csvAttributeString = raw_input("\n\nIn what order would you like the colums of the CSV file?\n" + "Please delineate with commas. The options are: " + "AlbumName, AlbumID, ArtistID, ArtistLatitude, ArtistLocation, ArtistLongitude,"+ " ArtistName, Danceability, Duration, KeySignature, KeySignatureConfidence, Tempo," + " SongID, TimeSignature, TimeSignatureConfidence, Title, and Year.\n\n" + "For example, you may write \"Title, Tempo, Duration\"...\n\n" + "...or exit by typing 'exit'.\n\n") csvAttributeList = re.split('\W+', csvAttributeString) for i, v in enumerate(csvAttributeList): csvAttributeList[i] = csvAttributeList[i].lower() for attribute in csvAttributeList: # print "Here is the attribute: " + attribute + " \n" if attribute == 'AlbumID'.lower(): csvRowString += 'AlbumID' elif attribute == 'AlbumName'.lower(): csvRowString += 'AlbumName' elif attribute == 'ArtistID'.lower(): csvRowString += 'ArtistID' elif attribute == 'ArtistLatitude'.lower(): csvRowString += 'ArtistLatitude' elif attribute == 'ArtistLocation'.lower(): csvRowString += 'ArtistLocation' elif attribute == 'ArtistLongitude'.lower(): csvRowString += 'ArtistLongitude' elif attribute == 'ArtistName'.lower(): csvRowString += 'ArtistName' elif attribute == 'Danceability'.lower(): csvRowString += 'Danceability' elif attribute == 'Duration'.lower(): csvRowString += 'Duration' elif attribute == 'KeySignature'.lower(): csvRowString += 'KeySignature' elif attribute == 'KeySignatureConfidence'.lower(): csvRowString += 'KeySignatureConfidence' elif attribute == 'SongID'.lower(): csvRowString += "SongID" elif attribute == 'Tempo'.lower(): csvRowString += 'Tempo' elif attribute == 'TimeSignature'.lower(): csvRowString += 'TimeSignature' elif attribute == 'TimeSignatureConfidence'.lower(): csvRowString += 'TimeSignatureConfidence' elif attribute == 'Title'.lower(): csvRowString += 'Title' elif attribute == 'Year'.lower(): csvRowString += 'Year' elif attribute == 'track_id'.lower(): csvRowString += 'track_id' elif attribute == 'artist_familiarity'.lower(): csvRowString += 'artist_familiarity' elif attribute == 'artist_hotttnesss'.lower(): csvRowString += 'artist_hotttnesss' elif attribute == 'artist_mbid'.lower(): csvRowString += 'artist_mbid' elif attribute == 'artist_playmeid'.lower(): csvRowString += 'artist_playmeid' elif attribute == 'artist_7digitalid'.lower(): csvRowString += 'artist_7digitalid' elif attribute == 'release'.lower(): csvRowString += 'release' elif attribute == 'release_7digitalid'.lower(): csvRowString += 'release_7digitalid' elif attribute == 'song_hotttnesss'.lower(): csvRowString += 'song_hotttnesss' elif attribute == 'track_7digitalid'.lower(): csvRowString += 'track_7digitalid' elif attribute == 'analysis_sample_rate'.lower(): csvRowString += 'analysis_sample_rate' elif attribute == 'audio_md5'.lower(): csvRowString += 'audio_md5' elif attribute == 'end_of_fade_in'.lower(): csvRowString += 'end_of_fade_in' elif attribute == 'energy'.lower(): csvRowString += 'energy' elif attribute == 'key'.lower(): csvRowString += 'key' elif attribute == 'key_confidence'.lower(): csvRowString += 'key_confidence' elif attribute == 'loudness'.lower(): csvRowString += 'loudness' elif attribute == 'mode'.lower(): csvRowString += 'mode' elif attribute == 'mode_confidence'.lower(): csvRowString += 'mode_confidence' elif attribute == 'start_of_fade_out'.lower(): csvRowString += 'start_of_fade_out' elif attribute == 'Exit'.lower(): sys.exit() else: prompt = True print "==============" print "I believe there has been an error with the input." print "==============" break csvRowString += "," lastIndex = len(csvRowString) csvRowString = csvRowString[0:lastIndex-1] csvRowString += "\n" outputFile1.write(csvRowString); csvRowString = "" #else, if you want to hard code the order of the csv file and not prompt #the user, else: ################################################# #change the order of the csv file here #Default is to list all available attributes (in alphabetical order) csvRowString = ("SongID,AlbumID,AlbumName,ArtistID,ArtistLatitude,ArtistLocation,"+ "ArtistLongitude,ArtistName,Danceability,Duration,KeySignature,"+ "KeySignatureConfidence,Tempo,TimeSignature,TimeSignatureConfidence,"+ "Title,Year,track_id,artist_hotttnesss,artist_mbid,artist_playmeid,artist_7digitalid,"+ "release,release_7digitalid,song_hotttnesss,track_7digitalid,analysis_sample_rate,audio_md5,"+ "end_of_fade_in,energy,key,key_confidence,loudness,mode,mode_confidence,start_of_fade_out") ################################################# csvAttributeList = re.split('\W+', csvRowString) for i, v in enumerate(csvAttributeList): csvAttributeList[i] = csvAttributeList[i].lower() outputFile1.write("SongNumber,"); outputFile1.write(csvRowString + "\n"); csvRowString = "" ################################################# #Set the basedir here, the root directory from which the search #for files stored in a (hierarchical data structure) will originate basedir = "/vagrant/genrepython/MillionSongSubset" # "." As the default means the current directory ext = ".h5" #Set the extension here. H5 is the extension for HDF5 files. ################################################# #FOR LOOP for root, dirs, files in os.walk(basedir): files = glob.glob(os.path.join(root,'*'+ext)) for f in files: print f songH5File = hdf5_getters.open_h5_file_read(f) song = Song(str(hdf5_getters.get_song_id(songH5File))) testDanceability = hdf5_getters.get_danceability(songH5File) # print type(testDanceability) # print ("Here is the danceability: ") + str(testDanceability) song.artistID = str(hdf5_getters.get_artist_id(songH5File)) song.albumID = str(hdf5_getters.get_release_7digitalid(songH5File)) song.albumName = str(hdf5_getters.get_release(songH5File)) song.artistLatitude = str(hdf5_getters.get_artist_latitude(songH5File)) song.artistLocation = str(hdf5_getters.get_artist_location(songH5File)) song.artistLongitude = str(hdf5_getters.get_artist_longitude(songH5File)) song.artistName = str(hdf5_getters.get_artist_name(songH5File)) song.danceability = str(hdf5_getters.get_danceability(songH5File)) song.duration = str(hdf5_getters.get_duration(songH5File)) # song.setGenreList() song.keySignature = str(hdf5_getters.get_key(songH5File)) song.keySignatureConfidence = str(hdf5_getters.get_key_confidence(songH5File)) # song.lyrics = None # song.popularity = None song.tempo = str(hdf5_getters.get_tempo(songH5File)) song.timeSignature = str(hdf5_getters.get_time_signature(songH5File)) song.timeSignatureConfidence = str(hdf5_getters.get_time_signature_confidence(songH5File)) song.title = str(hdf5_getters.get_title(songH5File)) song.year = str(hdf5_getters.get_year(songH5File)) song.track_id = str(hdf5_getters.get_track_id(songH5File)) song.artist_familiarity = str(hdf5_getters.get_artist_familiarity(songH5File)) song.artist_hotttnesss = str(hdf5_getters.get_artist_hotttnesss(songH5File)) song.artist_mbid = str(hdf5_getters.get_artist_mbid(songH5File)) song.artist_playmeid = str(hdf5_getters.get_artist_playmeid(songH5File)) song.artist_7digitalid = str(hdf5_getters.get_artist_7digitalid(songH5File)) song.release = str(hdf5_getters.get_release(songH5File)) song.release_7digitalid = str(hdf5_getters.get_release_7digitalid(songH5File)) song.song_hotttnesss = str(hdf5_getters.get_song_hotttnesss(songH5File)) song.track_7digitalid = str(hdf5_getters.get_track_7digitalid(songH5File)) song.analysis_sample_rate = str(hdf5_getters.get_analysis_sample_rate(songH5File)) song.audio_md5 = str(hdf5_getters.get_audio_md5(songH5File)) song.end_of_fade_in = str(hdf5_getters.get_end_of_fade_in(songH5File)) song.energy = str(hdf5_getters.get_energy(songH5File)) song.key = str(hdf5_getters.get_key(songH5File)) song.key_confidence = str(hdf5_getters.get_key_confidence(songH5File)) song.loudness = str(hdf5_getters.get_loudness(songH5File)) song.mode = str(hdf5_getters.get_mode(songH5File)) song.mode_confidence = str(hdf5_getters.get_mode_confidence(songH5File)) song.start_of_fade_out = str(hdf5_getters.get_start_of_fade_out(songH5File)) #print song count csvRowString += str(song.songCount) + "," for attribute in csvAttributeList: # print "Here is the attribute: " + attribute + " \n" if attribute == 'AlbumID'.lower(): csvRowString += song.albumID elif attribute == 'AlbumName'.lower(): albumName = song.albumName albumName = albumName.replace(',',"") csvRowString += "\"" + albumName + "\"" elif attribute == 'ArtistID'.lower(): csvRowString += "\"" + song.artistID + "\"" elif attribute == 'ArtistLatitude'.lower(): latitude = song.artistLatitude if latitude == 'nan': latitude = '' csvRowString += latitude elif attribute == 'ArtistLocation'.lower(): location = song.artistLocation location = location.replace(',','') csvRowString += "\"" + location + "\"" elif attribute == 'ArtistLongitude'.lower(): longitude = song.artistLongitude if longitude == 'nan': longitude = '' csvRowString += longitude elif attribute == 'ArtistName'.lower(): csvRowString += "\"" + song.artistName + "\"" elif attribute == 'Danceability'.lower(): csvRowString += song.danceability elif attribute == 'Duration'.lower(): csvRowString += song.duration elif attribute == 'KeySignature'.lower(): csvRowString += song.keySignature elif attribute == 'KeySignatureConfidence'.lower(): # print "key sig conf: " + song.timeSignatureConfidence csvRowString += song.keySignatureConfidence elif attribute == 'SongID'.lower(): csvRowString += "\"" + song.id + "\"" elif attribute == 'Tempo'.lower(): # print "Tempo: " + song.tempo csvRowString += song.tempo elif attribute == 'TimeSignature'.lower(): csvRowString += song.timeSignature elif attribute == 'TimeSignatureConfidence'.lower(): # print "time sig conf: " + song.timeSignatureConfidence csvRowString += song.timeSignatureConfidence elif attribute == 'Title'.lower(): csvRowString += "\"" + song.title + "\"" elif attribute == 'Year'.lower(): csvRowString += song.year elif attribute == 'track_id'.lower(): csvRowString += song.track_id elif attribute == 'artist_familiarity'.lower(): csvRowString += song.artist_familiarity elif attribute == 'artist_hotttnesss'.lower(): csvRowString += song.artist_hotttnesss elif attribute == 'artist_mbid'.lower(): csvRowString += song.artist_mbid elif attribute == 'artist_playmeid'.lower(): csvRowString += song.artist_playmeid elif attribute == 'artist_7digitalid'.lower(): csvRowString += song.artist_7digitalid elif attribute == 'release'.lower(): csvRowString += song.release elif attribute == 'release_7digitalid'.lower(): csvRowString += song.release_7digitalid elif attribute == 'song_hotttnesss'.lower(): csvRowString += song.song_hotttnesss elif attribute == 'track_7digitalid'.lower(): csvRowString += song.track_7digitalid elif attribute == 'analysis_sample_rate'.lower(): csvRowString += song.analysis_sample_rate elif attribute == 'audio_md5'.lower(): csvRowString += song.audio_md5 elif attribute == 'end_of_fade_in'.lower(): csvRowString += song.end_of_fade_in elif attribute == 'energy'.lower(): csvRowString += song.energy elif attribute == 'key'.lower(): csvRowString += song.key elif attribute == 'key_confidence'.lower(): csvRowString += song.key_confidence elif attribute == 'loudness'.lower(): csvRowString += song.loudness elif attribute == 'mode'.lower(): csvRowString += song.mode elif attribute == 'mode_confidence'.lower(): csvRowString += song.mode_confidence elif attribute == 'start_of_fade_out'.lower(): csvRowString += song.start_of_fade_out else: csvRowString += "Erm. This didn't work. Error. :( :(\n" csvRowString += "," #Remove the final comma from each row in the csv lastIndex = len(csvRowString) csvRowString = csvRowString[0:lastIndex-1] csvRowString += "\n" outputFile1.write(csvRowString) csvRowString = "" songH5File.close() outputFile1.close()
def main(): outputFile = open('songs.csv', 'w') writer = csv.writer(outputFile) csvRowString = "song_number,artist_familiarity,artist_hotttnesss,artist_id,artist_mbid,artist_playmeid,artist_7digitalid,artist_latitude,artist_longitude,artist_location,artist_name,release,release_7digitalid,song_id,song_hotttnesss,title,track_7digitalid,analysis_sample_rate,audio_md5,danceability,duration,end_of_fade_in,energy,key,key_confidence,loudness,mode,mode_confidence,start_of_fade_out,tempo,time_signature,time_signature_confidence,track_id,year" outputFile.write(csvRowString + "\n") csvRowString = "" ################################################# #Set the basedir here, the root directory from which the search #for files stored in a (hierarchical data structure) will originate basedir = "." # "." As the default means the current directory ext = ".H5" #Set the extension here. H5 is the extension for HDF5 files. ################################################# #FOR LOOP songCount = 0 for root, dirs, files in os.walk(basedir): files = glob.glob(os.path.join(root, '*' + ext)) for f in files: print(f) songH5File = hdf5_getters.open_h5_file_read(f) values = [ songCount, hdf5_getters.get_artist_familiarity(songH5File), hdf5_getters.get_artist_hotttnesss(songH5File), hdf5_getters.get_artist_id(songH5File), hdf5_getters.get_artist_mbid(songH5File), hdf5_getters.get_artist_playmeid(songH5File), hdf5_getters.get_artist_7digitalid(songH5File), hdf5_getters.get_artist_latitude(songH5File), hdf5_getters.get_artist_longitude(songH5File), hdf5_getters.get_artist_location(songH5File), hdf5_getters.get_artist_name(songH5File), hdf5_getters.get_release(songH5File), hdf5_getters.get_release_7digitalid(songH5File), hdf5_getters.get_song_id(songH5File), hdf5_getters.get_song_hotttnesss(songH5File), hdf5_getters.get_title(songH5File), hdf5_getters.get_track_7digitalid(songH5File), hdf5_getters.get_analysis_sample_rate(songH5File), hdf5_getters.get_audio_md5(songH5File), hdf5_getters.get_danceability(songH5File), hdf5_getters.get_duration(songH5File), hdf5_getters.get_end_of_fade_in(songH5File), hdf5_getters.get_energy(songH5File), hdf5_getters.get_key(songH5File), hdf5_getters.get_key_confidence(songH5File), hdf5_getters.get_loudness(songH5File), hdf5_getters.get_mode(songH5File), hdf5_getters.get_mode_confidence(songH5File), hdf5_getters.get_start_of_fade_out(songH5File), hdf5_getters.get_tempo(songH5File), hdf5_getters.get_time_signature(songH5File), hdf5_getters.get_time_signature_confidence(songH5File), hdf5_getters.get_track_id(songH5File), hdf5_getters.get_year(songH5File) ] songH5File.close() songCount = songCount + 1 writer.writerow(values) outputFile.close()
#segments_timbre = ','.join(str(e) for e in GETTERS.get_segments_timbre(h5, i)) # array similar_artists = ','.join( str(e) for e in GETTERS.get_similar_artists(h5, i)) # array song_hotttnesss = GETTERS.get_song_hotttnesss(h5, i) song_id = GETTERS.get_song_id(h5, i) start_of_fade_out = GETTERS.get_start_of_fade_out(h5, i) #tatums_confidence = ','.join(str(e) for e in GETTERS.get_tatums_confidence(h5, i)) # array #tatums_start = ','.join(str(e) for e in GETTERS.get_tatums_start(h5, i)) # array tempo = GETTERS.get_tempo(h5, i) time_signature = GETTERS.get_time_signature(h5, i) time_signature_confidence = GETTERS.get_time_signature_confidence( h5, i) title = GETTERS.get_title(h5, i) track_7digitalid = GETTERS.get_track_7digitalid(h5, i) track_id = GETTERS.get_track_id(h5, i) year = GETTERS.get_year(h5, i) loops += 1 #row = {'analysis_sample_rate':analysis_sample_rate,'artist_7digitalid':artist_7digitalid,'artist_familiarity':artist_familiarity,'artist_hotttnesss':artist_hotttnesss,'artist_id':artist_id,'artist_latitude':artist_latitude,'artist_location':artist_location,'artist_longitude':artist_longitude,'artist_mbid':artist_mbid,'artist_mbtags_count':artist_mbtags_count,'artist_mbtags':artist_mbtags,'artist_name':artist_name,'artist_terms_freq':artist_terms_freq,'artist_terms_weight':artist_terms_weight,'artist_terms':artist_terms,'audio_md5':audio_md5,'bars_confidence':bars_confidence,'bars_start':bars_start,'beats_confidence':beats_confidence,'beats_start':beats_start,'danceability':danceability,'duration':duration,'end_of_fade_in':end_of_fade_in,'energy':energy,'key_confidence':key_confidence,'key':key,'loudness':loudness,'mode_confidence':mode_confidence,'mode':mode,'release_7digitalid':release_7digitalid,'release':release,'sections_confidence':sections_confidence,'sections_start':sections_start,'segments_confidence':segments_confidence,'segments_loudness_max_time':segments_loudness_max_time,'segments_loudness_max':segments_loudness_max,'segments_loudness_start':segments_loudness_start,'segments_pitches':segments_pitches,'segments_start':segments_start,'segments_timbre':segments_timbre,'similar_artists':similar_artists,'song_hotttnesss':song_hotttnesss,'song_id':song_id,'start_of_fade_out':start_of_fade_out,'tatums_confidence':tatums_confidence,'tatums_start':tatums_start,'tempo':tempo,'time_signature_confidence':time_signature_confidence,'time_signature':time_signature,'title':title,'track_7digitalid':track_7digitalid,'track_id':track_id,'year':year,} row = { 'analysis_sample_rate': analysis_sample_rate, 'artist_7digitalid': artist_7digitalid, 'artist_familiarity': artist_familiarity, 'artist_hotttnesss': artist_hotttnesss, 'artist_id': artist_id, 'artist_latitude': artist_latitude, 'artist_location': artist_location, 'artist_longitude': artist_longitude, 'artist_mbid': artist_mbid, 'artist_mbtags_count': artist_mbtags_count,
int( math.floor(len(timbre_pitches_old)) / smoothing_factor)): segments = segments_timbre_old[(smoothing_factor * i):(smoothing_factor * (i + 1))] # calculate mean frequency of each note over a block of 5 time segments segments_mean = map(mean, zip(*segments)) segments_timbre_smoothed.append(segments_mean) print('song count: {0}'.format(count + 1)) h5_subdict = dict() h5_subdict['title'] = hdf5_getters.get_title(h5) h5_subdict['artist_name'] = hdf5_getters.get_artist_name(h5) h5_subdict['year'] = hdf5_getters.get_year(h5) h5_subdict['chord_changes'] = chord_changes h5_subdict['duration'] = hdf5_getters.get_duration(h5) h5_subdict['timbre'] = segments_timbre_smoothed track_id = hdf5_getters.get_track_id(h5) all_song_data[track_id] = h5_subdict print( 'Song {0} finished processing. Total time elapsed: {1} seconds' .format(count, str(time.time() - start_time))) h5.close() all_song_data_sorted = dict( sorted(all_song_data.items(), key=lambda k: k[1]['year'])) sortedpitchdata = 'output/msd_EDM_sortedpitchdata_' + re.sub( '/', '', sys.argv[1]) + '.txt' with open(sortedpitchdata, 'w') as text_file: text_file.write(str(all_song_data_sorted))
def main(): outputFile1 = open('SongCSV.csv', 'w') csvRowString = "" ################################################# #if you want to prompt the user for the order of attributes in the csv, #leave the prompt boolean set to True #else, set 'prompt' to False and set the order of attributes in the 'else' #clause prompt = False ################################################# if prompt == True: while prompt: prompt = False csvAttributeString = raw_input( "\n\nIn what order would you like the colums of the CSV file?\n" + "Please delineate with commas. The options are: " + "AlbumName, AlbumID, ArtistID, ArtistLatitude, ArtistLocation, ArtistLongitude," + " ArtistName, Danceability, Duration, KeySignature, KeySignatureConfidence, Tempo," + " SongID, TimeSignature, TimeSignatureConfidence, Title, and Year.\n\n" + "For example, you may write \"Title, Tempo, Duration\"...\n\n" + "...or exit by typing 'exit'.\n\n") csvAttributeList = re.split('\W+', csvAttributeString) for i, v in enumerate(csvAttributeList): csvAttributeList[i] = csvAttributeList[i].lower() for attribute in csvAttributeList: # print "Here is the attribute: " + attribute + " \n" if attribute == 'AlbumID'.lower(): csvRowString += 'AlbumID' elif attribute == 'AlbumName'.lower(): csvRowString += 'AlbumName' elif attribute == 'ArtistID'.lower(): csvRowString += 'ArtistID' elif attribute == 'ArtistLatitude'.lower(): csvRowString += 'ArtistLatitude' elif attribute == 'ArtistLocation'.lower(): csvRowString += 'ArtistLocation' elif attribute == 'ArtistLongitude'.lower(): csvRowString += 'ArtistLongitude' elif attribute == 'ArtistName'.lower(): csvRowString += 'ArtistName' elif attribute == 'Danceability'.lower(): csvRowString += 'Danceability' elif attribute == 'Duration'.lower(): csvRowString += 'Duration' elif attribute == 'KeySignature'.lower(): csvRowString += 'KeySignature' elif attribute == 'KeySignatureConfidence'.lower(): csvRowString += 'KeySignatureConfidence' elif attribute == 'SongID'.lower(): csvRowString += "SongID" elif attribute == 'Tempo'.lower(): csvRowString += 'Tempo' elif attribute == 'TimeSignature'.lower(): csvRowString += 'TimeSignature' elif attribute == 'TimeSignatureConfidence'.lower(): csvRowString += 'TimeSignatureConfidence' elif attribute == 'Title'.lower(): csvRowString += 'Title' elif attribute == 'Year'.lower(): csvRowString += 'Year' elif attribute == 'Exit'.lower(): sys.exit() else: prompt = True print "==============" print "I believe there has been an error with the input." print "==============" break csvRowString += "," lastIndex = len(csvRowString) csvRowString = csvRowString[0:lastIndex - 1] csvRowString += "\n" outputFile1.write(csvRowString) csvRowString = "" #else, if you want to hard code the order of the csv file and not prompt #the user, else: ################################################# #change the order of the csv file here #Default is to list all available attributes (in alphabetical order) csvRowString = ( "SongID,AlbumID,AlbumName,TrackId,ArtistID,ArtistLatitude,ArtistLocation," + "ArtistLongitude,ArtistName,Danceability,Duration,KeySignature," + "KeySignatureConfidence,Tempo,TimeSignature,TimeSignatureConfidence," + "Title,Year") ################################################# csvAttributeList = re.split('\W+', csvRowString) for i, v in enumerate(csvAttributeList): csvAttributeList[i] = csvAttributeList[i].lower() outputFile1.write("SongNumber,") outputFile1.write(csvRowString + "\n") csvRowString = "" ################################################# #Set the basedir here, the root directory from which the search #for files stored in a (hierarchical data structure) will originate basedir = "/home/umwangye/millonsong/MillionSongSubset/data/" # "." As the default means the current directory ext = ".h5" #Set the extension here. H5 is the extension for HDF5 files. ################################################# #FOR LOOP for root, dirs, files in os.walk(basedir): files = glob.glob(os.path.join(root, '*' + ext)) for f in files: print f songH5File = hdf5_getters.open_h5_file_read(f) #song = Song(str(hdf5_getters.get_song_id(songH5File))) #testDanceability = hdf5_getters.get_danceability(songH5File) # print type(testDanceability) # print ("Here is the danceability: ") + str(testDanceability) numPerH5 = hdf5_getters.get_num_songs(songH5File) for cnt in range(numPerH5): song = Song(str(hdf5_getters.get_song_id(songH5File, cnt))) song.trackId = str(hdf5_getters.get_track_id(songH5File, cnt)) song.artistID = str(hdf5_getters.get_artist_id( songH5File, cnt)) song.albumID = str( hdf5_getters.get_release_7digitalid(songH5File, cnt)) song.albumName = str(hdf5_getters.get_release(songH5File, cnt)) song.artistLatitude = str( hdf5_getters.get_artist_latitude(songH5File, cnt)) song.artistLocation = str( hdf5_getters.get_artist_location(songH5File, cnt)) song.artistLongitude = str( hdf5_getters.get_artist_longitude(songH5File, cnt)) song.artistName = str( hdf5_getters.get_artist_name(songH5File, cnt)) song.danceability = str( hdf5_getters.get_danceability(songH5File, cnt)) song.duration = str(hdf5_getters.get_duration(songH5File, cnt)) # song.setGenreList() song.keySignature = str(hdf5_getters.get_key(songH5File, cnt)) song.keySignatureConfidence = str( hdf5_getters.get_key_confidence(songH5File, cnt)) # song.lyrics = None # song.popularity = None song.tempo = str(hdf5_getters.get_tempo(songH5File, cnt)) song.timeSignature = str( hdf5_getters.get_time_signature(songH5File, cnt)) song.timeSignatureConfidence = str( hdf5_getters.get_time_signature_confidence( songH5File, cnt)) song.title = str(hdf5_getters.get_title(songH5File, cnt)) song.year = str(hdf5_getters.get_year(songH5File, cnt)) #print song count csvRowString += str(song.songCount) + "," for attribute in csvAttributeList: # print "Here is the attribute: " + attribute + " \n" if attribute == 'AlbumID'.lower(): csvRowString += song.albumID elif attribute == 'AlbumName'.lower(): albumName = song.albumName albumName = albumName.replace(',', "") csvRowString += "\"" + albumName + "\"" elif attribute == 'TrackId'.lower(): csvRowString += song.trackId elif attribute == 'ArtistID'.lower(): csvRowString += "\"" + song.artistID + "\"" elif attribute == 'ArtistLatitude'.lower(): latitude = song.artistLatitude if latitude == 'nan': latitude = '' csvRowString += latitude elif attribute == 'ArtistLocation'.lower(): location = song.artistLocation location = location.replace(',', '') csvRowString += "\"" + location + "\"" elif attribute == 'ArtistLongitude'.lower(): longitude = song.artistLongitude if longitude == 'nan': longitude = '' csvRowString += longitude elif attribute == 'ArtistName'.lower(): csvRowString += "\"" + song.artistName + "\"" elif attribute == 'Danceability'.lower(): csvRowString += song.danceability elif attribute == 'Duration'.lower(): csvRowString += song.duration elif attribute == 'KeySignature'.lower(): csvRowString += song.keySignature elif attribute == 'KeySignatureConfidence'.lower(): # print "key sig conf: " + song.timeSignatureConfidence csvRowString += song.keySignatureConfidence elif attribute == 'SongID'.lower(): csvRowString += "\"" + song.id + "\"" elif attribute == 'Tempo'.lower(): # print "Tempo: " + song.tempo csvRowString += song.tempo elif attribute == 'TimeSignature'.lower(): csvRowString += song.timeSignature elif attribute == 'TimeSignatureConfidence'.lower(): # print "time sig conf: " + song.timeSignatureConfidence csvRowString += song.timeSignatureConfidence elif attribute == 'Title'.lower(): csvRowString += "\"" + song.title + "\"" elif attribute == 'Year'.lower(): csvRowString += song.year else: csvRowString += "Erm. This didn't work. Error. :( :(\n" csvRowString += "," #Remove the final comma from each row in the csv lastIndex = len(csvRowString) csvRowString = csvRowString[0:lastIndex - 1] csvRowString += "\n" outputFile1.write(csvRowString) csvRowString = "" songH5File.close() outputFile1.close()
# to one of 196 categories for a chord shift chord_shift = 12*(key_shift - 1) + note_shift chord_changes[chord_shift] += 1 # print ('chord shift: {0}'.format(chord_shift)) pitch_segs_data.append(chord_changes) '''Now smooth out the timbre segments based on BPM''' segments_timbre_old = hdf5_getters.get_segments_timbre(h5) segments_timbre_smoothed = [] for i in range(0,int(math.floor(len(timbre_pitches_old))/smoothing_factor)): segments = segments_timbre_old[(smoothing_factor*i):(smoothing_factor*(i+1))] # calculate mean frequency of each note over a block of 5 time segments segments_mean = map(mean, zip(*segments)) segments_timbre_smoothed.append(segments_mean) print ('song count: {0}'.format(count+1)) h5_subdict = dict() h5_subdict['title'] = hdf5_getters.get_title(h5) h5_subdict['artist_name'] = hdf5_getters.get_artist_name(h5) h5_subdict['year'] = hdf5_getters.get_year(h5) h5_subdict['chord_changes'] = chord_changes h5_subdict['duration'] = hdf5_getters.get_duration(h5) h5_subdict['timbre'] = segments_timbre_smoothed track_id = hdf5_getters.get_track_id(h5) all_song_data[track_id] = h5_subdict print('Song {0} finished processing. Total time elapsed: {1} seconds'.format(count,str(time.time() - start_time))) h5.close() all_song_data_sorted = dict(sorted(all_song_data.items(), key=lambda k: k[1]['year'])) sortedpitchdata = 'output/msd_EDM_sortedpitchdata_' + re.sub('/','',sys.argv[1]) + '.txt' with open(sortedpitchdata, 'w') as text_file: text_file.write(str(all_song_data_sorted))