# this method is slow, because it keeps calling a feature reduction
# method for each bar and each estimator. We will globally reduce the
# features before starting
global_f_select = MultiSelectKBest(f_classif,
pooling_function=np.min,
k=3000)
res2 = first_layer_predictor2.fit_transform(
global_f_select.fit_transform(data, stimuli), stimuli)
# Now visualise the predictions.
from viz import get_bars, draw_words, pad, make_collage
bars = get_bars(img_size=(50, 50))
words1 = draw_words(res1, bars)
words2 = draw_words(res2, bars)
words = draw_words(stimuli, bars)
stacked = np.concatenate([words1, words2, words], axis=1)
# pad this slightly in order to be able to distinguish groups
stacked = pad(stacked, [0, 10, 10])
num_x = 8
num_y = 12
start_at = 0
collage = make_collage(stacked[start_at:start_at + (num_x * num_y)].\
reshape(num_x, num_y, stacked.shape[1], stacked.shape[2]))
# Use the layer 1 results to learn a second level classifier on letters
forests = [ExtraTreesClassifier(n_estimators=200) for i in range(4)]
letter_length = stimuli.shape[1] / 4
predictions = []
for i, forest in zip(range(0, stimuli.shape[1], letter_length), forests):
forest.fit(train_data, train_target[:, i:i + letter_length])
predictions.append(np.array(forest.predict_proba(test_data)).T[1])
predictions = np.hstack(predictions)
# visualise the random forests result
from viz import get_bars, draw_words, pad, make_collage
bars = get_bars(img_size=(50, 50))
words_layer1 = draw_words(res1[200:], bars)
words_forest = draw_words(p, bars)
words_forest_by_letters = draw_words(predictions, bars)
words = draw_words(stimuli[200:], bars)
stacked = np.concatenate(
[words_layer1, words_forest, words_forest_by_letters, words], axis=1)
# pad this slightly in order to be able to distinguish groups
stacked = pad(stacked, [0, 10, 10])
num_x = 5
num_y = 8
start_at = 0
# this method is slow, because it keeps calling a feature reduction
# method for each bar and each estimator. We will globally reduce the
# features before starting
global_f_select = MultiSelectKBest(f_classif,
pooling_function=np.min,
k=3000)
#res2 = first_layer_predictor2.fit_transform(
# global_f_select.fit_transform(data, stimuli), stimuli)
res2 = first_layer_predictor2.fit_transform(data, stimuli)
# Now visualise the predictions.
from viz import get_bars, draw_words, pad, make_collage
bars = get_bars(img_size=(50, 50))
words1 = draw_words(res1, bars)
words2 = draw_words(res2, bars)
words = draw_words(stimuli, bars)
stacked = np.concatenate([words1, words2, words], axis=1)
# pad this slightly in order to be able to distinguish groups
stacked = pad(stacked, [0, 10, 10])
num_x = 8
num_y = 12
start_at = 0
collage = make_collage(stacked[start_at:start_at + (num_x * num_y)].\
reshape(num_x, num_y, stacked.shape[1], stacked.shape[2]))
forests = [ExtraTreesClassifier(n_estimators=200) for i in range(4)]
letter_length = stimuli.shape[1] / 4
predictions = []
for i, forest in zip(
range(0, stimuli.shape[1], letter_length),
forests):
forest.fit(train_data, train_target[:, i:i + letter_length])
predictions.append(np.array(forest.predict_proba(test_data)).T[1])
predictions = np.hstack(predictions)
# visualise the random forests result
from viz import get_bars, draw_words, pad, make_collage
bars = get_bars(img_size=(50, 50))
words_layer1 = draw_words(res1[200:], bars)
words_forest = draw_words(p, bars)
words_forest_by_letters = draw_words(predictions, bars)
words = draw_words(stimuli[200:], bars)
stacked = np.concatenate([words_layer1, words_forest,
words_forest_by_letters, words], axis=1)
# pad this slightly in order to be able to distinguish groups
stacked = pad(stacked, [0, 10, 10])
num_x = 5
num_y = 8
start_at = 0
