def run(filename, train_sample, train_label, test_sample, test_label, title, M,
thresh, CART_step):
train_sample, train_sample_size = Load.loadSample(train_sample)
train_label, train_label_size = Load.loadLabel(train_label)
assert train_sample_size == train_label_size, 'train_sample_size does not match train_label_size'
test_sample, test_sample_size = Load.loadSample(test_sample)
test_label, test_label_size = Load.loadLabel(test_label)
assert test_sample_size == test_label_size, 'test_sample_size does not match test_label_size'
train_sample = Preprocess.normalize(train_sample,
True).values.tolist() # list
test_sample = Preprocess.normalize(test_sample,
True).values.tolist() # list
label_to_index = {
label: index
for index, label in enumerate(set(train_label['x'].tolist()))
}
train_index = Preprocess.labelMap(train_label, label_to_index) # list
test_index = Preprocess.labelMap(test_label, label_to_index) # list
input_size = len(train_sample[0])
sample_size = len(train_sample)
sample_weights = [1 / sample_size for _ in range(sample_size)]
classifier_weights = []
classifier_thresholds = []
threshold_positions = []
test_corrs = []
test_times = [i + 1 for i in range(M)]
for i in range(M):
threshold, position, errors = Calc.CART(train_sample, train_index,
sample_weights, thresh,
CART_step)
total_error = Calc.gentleError(np.array(sample_weights),
np.array(errors))
classifier_weights.append(round(Calc.classifierError(total_error), 3))
classifier_thresholds.append(threshold)
threshold_positions.append(position)
sample_weights = Calc.updateVariableWeights(np.array(sample_weights),
total_error, errors)
# print('errors: {}'.format(errors))
# print('sample_weights: {}'.format(sample_weights))
# print('classifier_threshold: {} in {}'.format(threshold, position))
print('total_error: {}'.format(total_error))
print('threshold_positions: {}'.format(threshold_positions))
print('classifier_thresholds: {}'.format(classifier_thresholds))
print('classifier_weights: {}'.format(classifier_weights))
test_corr = 0
test_size = len(test_sample)
for sample, index in zip(test_sample, test_index):
vote = 0
for threshold, position, weight in zip(classifier_thresholds,
threshold_positions,
classifier_weights):
if sample[position] >= threshold:
vote += weight
elif sample[position] < threshold:
vote -= weight
if vote >= 0 and index == 1:
test_corr += 1
elif vote < 0 and index == 0:
test_corr += 1
test_corrs.append(round(test_corr / test_size, 3))
Log.log(filename, 'M: {}; correction: {}\n'.format(M, test_corrs[-1]))
print(
'-----------------thresh: {}; CART_step: {}; iter: {}-----------------'
.format(thresh, CART_step, i + 1))
Graph.draw(filename, test_times, test_corrs, test_times[-1], 1.0, title)
return test_corrs
# print(list(label_to_index.keys())[1])
nn_decision = 1
else:
# print(list(label_to_index.keys())[0])
nn_decision = 0
# print(test_label.values.tolist()[i][0])
if test_label.values.tolist()[i][0] == list(
label_to_index.keys())[nn_decision]:
# right
correct_count += 1
test_correct = correct_count / test_sample_size
Log.log(filename, 'k: {}; correct rate: {}\n'.format(k, test_correct))
return test_correct
if __name__ == '__main__':
Log.clearLog(filename)
rec = []
for k in range(1, 101):
rec.append(run(train_sample, train_label, test_sample, test_label, k))
maxi = max(rec)
mini = min(rec)
avrg = sum(rec) / len(rec)
stdv = np.std(rec, ddof=1)
Log.log(
filename, 'max: {}; min: {}; average: {}; std: {}'.format(
maxi, mini, avrg, stdv))
Graph.draw(filename, [i for i in range(1, 101)], rec, 100, 1.0, graph_name)