def main(args):
input_folder = args.i_path
threshold = args.threshold
mode = args.mode
intervals = args.resolution
print('LOADING PKL...')
artists = load_data(filename=input_folder)
print('PREPROCESSING ', d[mode])
X, y = gen_dataset(artists=artists, mode=mode)
X, y = remove_outlier(X=X, y=y, thresh=threshold)
X = normalize(X=X)
for lr in [10, 100, 500, 1000]:
print('TSNE with learning rate =', lr)
X_emb = tsne(X, lr=lr)
print('[TSNE-1 - TSNE-2]')
print('min values')
print(np.amin(X_emb, axis=0))
print('max values')
print(np.amax(X_emb, axis=0))
print('mean values')
print(np.mean(X_emb, axis=0))
print('variance values')
print(np.var(X_emb, axis=0))
#artists = optimize_artists_dictionary(artists)
#artists = attach_tsne_to_art_dict(artists=artists, X=X, y=y)
tsne_min = np.amin(X, axis=0)
tsne_max = np.amax(X, axis=0)
def main(args):
input_folder = args.i_path
threshold = args.threshold
mode = args.mode
print('LOADING PKL...')
artists = load_data(filename=input_folder)
print('PREPROCESSING ', d[mode])
X, y = gen_dataset(artists=artists, mode=mode)
X, y = remove_outlier(X=X, y=y, thresh=threshold)
X = normalize(X=X)
print('TSNE')
X = tsne(X=X, lr=1000)
artists = optimize_artists_dictionary(artists)
artists = attach_tsne_to_art_dict(artists=artists, X=X, y=y)
tsne_min = np.amin(X, axis=0)
tsne_max = np.amax(X, axis=0)
print('[TSNE-1 - TSNE-2]')
print('min values')
print(np.amin(X, axis=0))
print('max values')
print(np.amax(X, axis=0))
print('mean values')
print(np.mean(X, axis=0))
print('variance values')
print(np.var(X, axis=0))
artists = clean_similar_artists(artists=artists)
def main(args):
input_folder = args.i_path
global output_path
output_path = args.o_path
if output_path[-1] != '/':
output_path += '/'
global artists
print('LOADING PKL...')
artists = load_data(filename=input_folder)
print('PREPROCESSING')
X, y = gen_dataset(artists=artists, mode=3)
for t in np.arange(1, 3, 0.2):
A, b = remove_outlier(X=X, y=y, thresh=t)
def main(args):
input_folder = args.i_path
threshold = args.threshold
output_pkl = args.output_pkl
global output_path
output_path = args.o_path
if output_path[-1] != '/':
output_path += '/'
mode = args.mode
global artists
print('LOADING PKL...')
artists = load_data(filename=input_folder)
print('PREPROCESSING ', d[mode])
X, y = gen_dataset(artists=artists, mode=mode)
X, y = remove_outlier(X=X, y=y, thresh=threshold)
X = normalize(X=X)
print('TSNE')
X = tsne(X=X, lr=1000)
artists = optimize_artists_dictionary(artists)
artists = attach_tsne_to_art_dict(artists=artists, X=X, y=y)
min = np.amin(X, axis=0)
max = np.amax(X, axis=0)
dimension = 20
print('[TSNE-1 - TSNE-2]')
print('min values')
print(np.amin(X, axis=0))
print('max values')
print(np.amax(X, axis=0))
print('mean values')
print(np.mean(X, axis=0))
print('variance values')
print(np.var(X, axis=0))
artists = clean_similar_artists(artists=artists)
print('GENERATE HEATMAPS')
gen_heatmaps_master(dimension=dimension, min=min, max=max)
print('SAVING DATA')
save_data(artists, filename=output_pkl)
print('PLOT HEATMAPS in ', output_path)
plot_heatmaps_master(dimension=dimension, min=min, max=max)
def main(args):
input_folder = args.i_path
threshold = args.threshold
artists = load_data(filename=input_folder)
X, y = gen_dataset(artists=artists)
if PRINT_DISTRIBUTION:
#PRINT VALUES BEFORE OUTLIER REMOTION
feat_names = get_features_dict()
x = np.array(X)
for i in range(x.shape[1]):
ax = plt.hist(x[:, i], bins=200)
filename = args.o_path + '/BEFORE/' + feat_names[i] + '.png'
title = feat_names[i] + 'BEFORE outlier remotion'
plt.title(title)
plt.savefig(filename)
plt.close('all')
X, y = remove_outlier(X=X,
y=y,
thresh=threshold,
verbose=False,
save_histogram=True)
#X = normalize(X=X)
#X, y = remove_outliers_lof(data=X, y=y)
if PRINT_DISTRIBUTION:
# PRINT VALUES AFTER OUTLIER REMOTION
x = np.array(X)
for i in range(x.shape[1]):
ax = plt.hist(x[:, i], bins=200)
filename = args.o_path + '/AFTER/' + feat_names[i] + '.png'
title = feat_names[i] + 'AFTER outlier remotion'
plt.title(title)
plt.savefig(filename)
plt.close('all')