def load_x(ds, preset):
feature_parts = [Dataset.load_part(ds, part) for part in preset.get('features', [])]
prediction_parts = [load_prediction(ds, p, mode=preset.get('predictions_mode', 'fulltrain')) for p in preset.get('predictions', [])]
prediction_parts = [p.clip(lower=0.1).values.reshape((p.shape[0], 1)) for p in prediction_parts]
if 'prediction_transform' in preset:
prediction_parts = map(preset['prediction_transform'], prediction_parts)
return hstack(feature_parts + prediction_parts)
def main():
p = argparse.ArgumentParser(description='Display a kernel.')
p.add_argument('-out', help='output to *.png file instead of viewing')
p.add_argument('k', nargs='*', help='path to kernel(s)')
args = p.parse_args()
out = None
for fn in args.k:
print('Loading', fn)
step, kernel = util.load_kernel(fn)
print(' Step', step)
print(' Kernel shape is', kernel.shape)
print(' Min', np.min(kernel))
print(' Max', np.max(kernel))
print(' Mean', np.mean(kernel))
print(' Sum', np.sum(kernel))
print(' Sum of abs', np.sum(np.abs(kernel)))
print(' RMS', np.sqrt(np.mean(kernel * kernel)))
render = util.vis_hwoi(kernel, doubles=2)
render = util.hstack([render, util.make_label(fn)], 5)
if out is None:
out = render
else:
out = util.vstack([out, render], 5)
out = util.border(out, 5)
if args.out is not None:
util.save_image(args.out, out)
print('Written to', args.out)
else:
print('Press ESC to close window.')
def render_fn():
return out
util.viewer(None, render_fn)
def render():
"""Returns an image showing the current weights and output."""
# TODO: vertically align labels.
t0 = time.time()
rout, rdiff, rw = sess.run([actual_img, diff, w1])
render_out = util.vstack([
util.hstack([
util.vstack([util.cache_label('input:'), vimg1], 5),
util.vstack([
util.cache_label('actual:'),
util.vis_nhwc(rout, doubles=0, gamma=args.gamma)
], 5),
util.vstack([util.cache_label('expected:'), vimg2], 5),
], 5),
util.cache_label('difference:'),
util.vis_nhwc(rdiff, doubles=0),
util.cache_label('kernel:'),
util.vis_hwoi(rw, doubles=2),
], 5)
render_out = util.border(render_out, 5)
t1 = time.time()
render_time[0] += t1 - t0
return render_out
opt_eval_x = train_x[opt_eval_idx]
opt_eval_y = train_y[opt_eval_idx]
opt_eval_r = train_r.slice(opt_eval_idx)
if len(feature_builders) > 0: # TODO: Move inside of bagging loop
print(" Building per-fold features...")
opt_train_x = [opt_train_x]
opt_eval_x = [opt_eval_x]
for fb in feature_builders:
opt_train_x.append(fb.fit_transform(opt_train_r))
opt_eval_x.append(fb.transform(opt_eval_r))
opt_train_x = hstack(opt_train_x)
opt_eval_x = hstack(opt_eval_x)
param_grid = preset.get('param_grid', [])
if len(param_grid) > 0:
if preset['opt_method'] != "grid_search":
preset['model'].optimize(
opt_train_x,
y_transform(opt_train_y),
opt_eval_x,
y_transform(opt_eval_y),
param_grid,
eval_func=lambda yt, yp: accuracy_score(
y_inv_transform(yt), y_inv_transform(yp)))
else:
preset['model'].grid_search(
n_components = 500 # 500 components explain 99.8% of variance
print "Loading data..."
train_num = Dataset.load_part('train', 'numeric')
train_cat = Dataset.load_part('train', 'categorical_dummy')
test_num = Dataset.load_part('test', 'numeric')
test_cat = Dataset.load_part('test', 'categorical_dummy')
train_cnt = train_num.shape[0]
print "Combining data..."
all_data = hstack((scale(vstack(
(train_num, test_num)).astype(np.float64)).astype(np.float32),
vstack((train_cat, test_cat))))
del train_num, train_cat, test_num, test_cat
print "Fitting svd..."
svd = TruncatedSVD(n_components)
res = svd.fit_transform(all_data)
print "Explained variance ratio: %.5f" % np.sum(svd.explained_variance_ratio_)
print "Saving..."
Dataset.save_part_features('svd', ['svd%d' % i for i in xrange(n_components)])
Dataset(svd=res[:train_cnt]).save('train')