def do_fit(self, dataframe: pd.DataFrame,
labeled_segments: List[AnalyticSegment],
deleted_segments: List[AnalyticSegment],
learning_info: LearningInfo) -> None:
data = utils.cut_dataframe(dataframe)
data = data['value']
last_pattern_center = self.state.pattern_center
self.state.pattern_center = utils.remove_duplicates_and_sort(
last_pattern_center + learning_info.segment_center_list)
self.state.pattern_model = utils.get_av_model(
learning_info.patterns_list)
convolve_list = utils.get_convolve(self.state.pattern_center,
self.state.pattern_model, data,
self.state.window_size)
correlation_list = utils.get_correlation(self.state.pattern_center,
self.state.pattern_model,
data, self.state.window_size)
del_conv_list = []
delete_pattern_timestamp = []
for segment in deleted_segments:
del_mid_index = segment.center_index
delete_pattern_timestamp.append(segment.pattern_timestamp)
deleted_pat = utils.get_interval(data, del_mid_index,
self.state.window_size)
deleted_pat = utils.subtract_min_without_nan(deleted_pat)
del_conv_pat = scipy.signal.fftconvolve(deleted_pat,
self.state.pattern_model)
if len(del_conv_pat): del_conv_list.append(max(del_conv_pat))
self.state.convolve_min, self.state.convolve_max = utils.get_min_max(
convolve_list, self.state.window_size / 3)
self.state.conv_del_min, self.state.conv_del_max = utils.get_min_max(
del_conv_list, self.state.window_size)
def _update_fiting_result(self,
state: ModelState,
confidences: list,
convolve_list: list,
del_conv_list: list,
height_list: Optional[list] = None) -> None:
state.confidence = float(min(confidences, default=1.5))
state.convolve_min, state.convolve_max = utils.get_min_max(
convolve_list, state.window_size)
state.conv_del_min, state.conv_del_max = utils.get_min_max(
del_conv_list, 0)
if height_list is not None:
state.height_min, state.height_max = utils.get_min_max(
height_list, 0)
def main():
print("Image:")
image = input("")
features = finding_face_landmark.finding_face_landmark(image)
if (len(features) == 0):
exit(0)
data_file_name = "features.csv"
X, Y, Q = utils.get_data(data_file_name, 2000)
x_min, x_max = utils.get_min_max(X)
X = utils.normalize_features(x_min, x_max, X)
test_file_name = "test.csv"
T, P, L = utils.get_data_test(test_file_name, x_min, x_max, len(X), Q, Y)
model_file_name = './my_test_model.ckpt'
neural_network = n.Neural_Network(X, Y, model_file_name)
# neural_network.training()
# neural_network.test(T,P)
features = utils.normalize_features(x_min, x_max, features)
predict = neural_network.predict([features])
image_path = Q[predict][0].strip()
metadata = 'C:\\ProjekatSoft\\wiki_crop\\wiki.mat'
name = utils.get_name(image_path, metadata)
percent = utils.get_percent(features, X[predict:predict + 1, :15][0])
utils.show_image('C:\\ProjekatSoft\\wiki_crop\\' + image_path, name,
percent)
def do_fit(self, dataframe: pd.DataFrame, labeled_segments: list, deleted_segments: list, learning_info: dict) -> None:
data = utils.cut_dataframe(dataframe)
data = data['value']
last_pattern_center = self.state.get('pattern_center', [])
self.state['pattern_center'] = list(set(last_pattern_center + learning_info['segment_center_list']))
self.state['pattern_model'] = utils.get_av_model(learning_info['patterns_list'])
convolve_list = utils.get_convolve(self.state['pattern_center'], self.state['pattern_model'], data, self.state['WINDOW_SIZE'])
correlation_list = utils.get_correlation(self.state['pattern_center'], self.state['pattern_model'], data, self.state['WINDOW_SIZE'])
del_conv_list = []
delete_pattern_timestamp = []
for segment in deleted_segments:
del_mid_index = segment.center_index
delete_pattern_timestamp.append(segment.pattern_timestamp)
deleted_pat = utils.get_interval(data, del_mid_index, self.state['WINDOW_SIZE'])
deleted_pat = utils.subtract_min_without_nan(deleted_pat)
del_conv_pat = scipy.signal.fftconvolve(deleted_pat, self.state['pattern_model'])
if len(del_conv_pat): del_conv_list.append(max(del_conv_pat))
self.state['convolve_min'], self.state['convolve_max'] = utils.get_min_max(convolve_list, self.state['WINDOW_SIZE'] / 3)
self.state['conv_del_min'], self.state['conv_del_max'] = utils.get_min_max(del_conv_list, self.state['WINDOW_SIZE'])
def group_projects(projects, by_programme=False, by_year=False):
""" group projects by theme.
"""
min_y = max_y = None
if by_year:
min_y, max_y = get_min_max(projects, key=lambda x: x['call year'])
mapping = {}
for programme in PROGRAMMES:
for name in PROGRAMMES[programme]:
if min_y is None or max_y is None:
mapping[name] = programme if by_programme else name
else:
for year in range(min_y, max_y + 1):
mapping['{0}_{1}'.format(year, name)] = '{0}_{1}'.format(
year, programme if by_programme else name)
matrices = {}
for key in mapping:
matrices[mapping[key]] = []
for project in projects:
name = project['Theme']
if by_year:
name = '{0}_{1}'.format(project['call year'], name)
key = mapping.get(name, None)
if key is None:
print "error: unknown theme ``{0}''".format(project['Theme'])
continue
matrices[key].append(project)
matrices = {key: value for key, value in matrices.iteritems() if len(value)}
for key in matrices:
print "Grouped {0} projects under ``{1}''".format(
len(matrices[key]), key)
return matrices
def main():
ROOT.gROOT.SetBatch()
ROOT.TGaxis.SetMaxDigits(5)
file = ROOT.TFile('inputs/interference_functions.root')
masses = [400, 600, 800]
widths = [0.01, 0.05, 0.1]
l_width = 3
tot, sig, Hh, HB = None, None, None, None
#for big_bad_index in range( 100 ):
canvas, pad, pads = utils.create_special_canvas(
'plot_interference_example')
tot_hist, sig_hist, Hh_hist, HB_hist = {}, {}, {}, {}
for index, (mass, width) in enumerate(product(masses, widths)):
pads[index + 1].cd()
tot = file.Get('tot___m%d___w%d' % (mass, width * 100))
sig = file.Get('sig___m%d___w%d' % (mass, width * 100))
Hh = file.Get('Hh___m%d___w%d' % (mass, width * 100))
HB = file.Get('HB___m%d___w%d' % (mass, width * 100))
x_min, x_max = utils.get_extremes(
mass, width) #utils.get_min_max_shift( mass, width )
mw_str = '_hist___m%d___w%d' % (mass, width * 100)
tot_hist['tot' + mw_str] = ROOT.TH1F('tot' + mw_str, '', 1000, x_min,
x_max)
tot_hist['tot' + mw_str].Add(tot, 1.)
integral = tot_hist['tot' + mw_str].Integral()
tot_hist['tot' + mw_str].Scale(1. / integral)
sig_hist['sig' + mw_str] = ROOT.TH1F('sig' + mw_str, '', 1000, x_min,
x_max)
sig_hist['sig' + mw_str].Add(sig, 1. / integral)
Hh_hist['Hh' + mw_str] = ROOT.TH1F('Hh' + mw_str, '', 1000, x_min,
x_max)
Hh_hist['Hh' + mw_str].Add(Hh, 1. / integral)
HB_hist['HB' + mw_str] = ROOT.TH1F('HB' + mw_str, '', 1000, x_min,
x_max)
HB_hist['HB' + mw_str].Add(HB, 1. / integral)
#print integral
#integral = 1.
y_min, y_max = utils.get_min_max(tot_hist['tot' + mw_str],
sig_hist['sig' + mw_str],
Hh_hist['Hh' + mw_str],
HB_hist['HB' + mw_str])
#y_min, y_max = -0.0015, 0.0075
tot_hist['tot' + mw_str].SetMinimum(y_min)
tot_hist['tot' + mw_str].SetMaximum(y_max)
tot_hist['tot' + mw_str].Draw('c')
tot_hist['tot' + mw_str].GetXaxis().SetLabelSize(10)
tot_hist['tot' + mw_str].GetYaxis().SetLabelSize(10)
tot_hist['tot' + mw_str].SetLineWidth(l_width)
sig_hist['sig' + mw_str].SetLineColor(ROOT.kOrange + 10)
sig_hist['sig' + mw_str].SetLineStyle(2)
sig_hist['sig' + mw_str].SetLineWidth(l_width)
sig_hist['sig' + mw_str].Draw('c same')
Hh_hist['Hh' + mw_str].SetLineColor(ROOT.kGreen + 1)
Hh_hist['Hh' + mw_str].SetLineStyle(4)
Hh_hist['Hh' + mw_str].SetLineWidth(l_width)
Hh_hist['Hh' + mw_str].Draw('c same')
HB_hist['HB' + mw_str].SetLineColor(ROOT.kBlue)
HB_hist['HB' + mw_str].SetLineStyle(3)
HB_hist['HB' + mw_str].SetLineWidth(l_width)
HB_hist['HB' + mw_str].Draw('c same')
tot_hist['tot' + mw_str].Draw('c same')
l = utils.draw_small_latex(mass, width)
canvas.cd()
x_l1, y_l1, latex1 = utils.draw_special_latex()
latex1.DrawLatex(x_l1, y_l1 - 0.045, utils.plot_tag)
l2 = utils.draw_x_axis_latex('Particle-level ' +
utils.m4l) #it{m_{4l}} [GeV]' )
l3 = utils.draw_y_axis_latex('1/N #upoint dN/d#it{m}_{4#it{l}} [GeV^{-1}]')
leg = utils.create_special_legend()
leg.AddEntry(tot_hist['tot' + mw_str], 'Signal + Interference', 'l')
leg.AddEntry(sig_hist['sig' + mw_str], 'Signal only', 'l')
leg.AddEntry(Hh_hist['Hh' + mw_str], '#it{H-h} Interference', 'l')
leg.AddEntry(HB_hist['HB' + mw_str], '#it{H-B} Interference', 'l')
leg.Draw()
utils.save(canvas)
ROOT.TGaxis.SetMaxDigits(4)