def set_train_dists(self, train_fnames):
# initialize empty histograms
# since histogram is accumulated as below, it needs to be initialized
# at every training
for c in preferences.CLASSES:
self.train_histograms[c] = {}
self.train_pdfs[c] = {}
for o in preferences.OBSERVABLES:
self.train_histograms[c][
o] = generic_tools.initialize_histogram(o)
# compute histograms for each class (using training set)
for c in preferences.CLASSES:
for train_fname in train_fnames[c]:
data = np.load(train_fname)
data_A, data_B = generic_tools.extract_individual_data(data)
obs_data = generic_tools.compute_observables(data_A, data_B)
for o in preferences.OBSERVABLES:
self.train_histograms[c][
o] += generic_tools.compute_histogram_1D(
o, obs_data[o])
for c in preferences.CLASSES:
for o in preferences.OBSERVABLES:
self.train_pdfs[c][o] = generic_tools.compute_pdf(
o, self.train_histograms[c][o])
def train(self, train_fnames):
train_histograms1D = {}
# initialize empty histograms
for o in preferences.OBSERVABLES:
train_histograms1D[o], self.train_pdfs1D[o] = {}, {}
for c in preferences.CLASSES:
train_histograms1D[o][c] = generic_tools.initialize_histogram(
o)
# compute histograms for each class
for c in preferences.CLASSES:
for file_path in train_fnames[c]:
data = np.load(file_path)
data_A, data_B = generic_tools.extract_individual_data(data)
obs_data = generic_tools.compute_observables(data_A, data_B)
for o in preferences.OBSERVABLES:
train_histograms1D[o][
c] += generic_tools.compute_histogram_1D(
o, obs_data[o])
for o in preferences.OBSERVABLES:
for c in preferences.CLASSES:
self.train_pdfs1D[o][c] = generic_tools.compute_pdf(
o, train_histograms1D[o][c])
def set_test_dists(self, test_fnames):
# initialize empty histograms
# since one histogram/pdf is computed for each element of test set
# as below, it needs to be initialized at every testing
for c in preferences.CLASSES:
self.test_histograms[c], self.test_pdfs[c] = {}, {}
for test_fname in test_fnames[c]:
self.test_histograms[c][test_fname], self.test_pdfs[c][
test_fname] = {}, {}
for o in preferences.OBSERVABLES:
self.test_histograms[c][test_fname][
o] = generic_tools.initialize_histogram(o)
self.test_pdfs[c][test_fname][o] = []
# compute histograms for each class (using test set)
for c in preferences.CLASSES:
for test_fname in test_fnames[c]:
data = np.load(test_fname)
data_A, data_B = generic_tools.extract_individual_data(data)
obs_data = generic_tools.compute_observables(data_A, data_B)
for o in preferences.OBSERVABLES:
self.test_histograms[c][test_fname][
o] = generic_tools.compute_histogram_1D(
o, obs_data[o])
for c in preferences.CLASSES:
for test_fname in test_fnames[c]:
for o in preferences.OBSERVABLES:
self.test_pdfs[c][test_fname][
o] = generic_tools.compute_pdf(
o, self.test_histograms[c][test_fname][o])
data_fnames = generic_tools.get_data_fnames('data/classes/')
for c in preferences.CLASSES:
for file_path in data_fnames[c]:
data = np.load(file_path)
data_A, data_B = generic_tools.extract_individual_data(data)
obs_data = generic_tools.compute_observables(data_A, data_B)
for o in preferences.OBSERVABLES:
edges = get_edges(o)
temp_hist = generic_tools.compute_histogram_1D(o, obs_data[o])
temp_pdf = generic_tools.compute_pdf(o, temp_hist)
histograms1D[o][c].append(temp_hist )
pdf1D[o][c].append( temp_pdf )
mean_pdfs[o][c].append( np.average(edges, weights=temp_pdf) )
print('Obs\tF_d\tv1\tv2')
print('-------------------------------')
for o in preferences.OBSERVABLES:
F_d, v1, v2 = get_fval(mean_pdfs[o])
print('{}\t{:2.3f}\t{}\t{}'.format(o, F_d, v1, v2))
print('\n**Check this page for computing p-value from f-statistics**')
print('http:stattrek.com/online-calculator/f-distribution.aspx ')
elapsed_time = time.time() - start_time