def __init__(self):
"""
Initialize the program prompting the instruction to the program
"""
self.printProgramInfos()
self.datamanager = DataManager()
self.dataexplorer = DataExplorer()
def __init__(self):
"""
Initialize the program prompting the instruction to the program
"""
try:
self.printProgramInfos()
self.datamanager = DataManager()
self.dataexplorer = DataExplorer()
except:
raise VideoAnalysisException(" Error while initializing FlowManager Instance ")
def unpack_frame_forward(self):
# Unpack the data importer main frame
self.__step2_frame.pack_forget()
# Call the next step class (Data explorer)
DataExplorer(self.__root, self.__data_set, self.__project_title, self.__step2_frame).pack_frame()
from DataExplorer import DataExplorer from DataLoader import DataLoader from sklearn.linear_model import LinearRegression # First of all we load dataset and normalize it using DataLoader from Plotter import Plotter data_loader = DataLoader() data_loader.load_and_normalize_data() train_data = data_loader.get_train_data()[1:] test_data = data_loader.get_train_data()[:1] # Then we use DataExplorer to explore data. Info allows us to see how many null values exists. We also c data_explorer = DataExplorer() data_to_visualize = train_data[['WoodDeckSF', 'SalePrice']] data_explorer.describe(train_data) data_explorer.info(train_data) # And we use Plotter to create some data visualization plotter = Plotter() # plotter.plot(data_to_visualize, 'WoodDeckSF') # plotter.show_histogram(data_to_visualize) # plotter.show_box_plot(data_to_visualize) # Create model model = LinearRegression().fit(train_data, train_data['SalePrice']) r_sq = model.score(train_data, train_data['SalePrice'])
# PDFs (note labelling for correct plotting)
sig = ROOT.RooGaussian("sig", "sig", m, mean, sigma)
bkgr = ROOT.RooExponential("bkgr", "bkgr", m, exp_par)
model_gen = ROOT.RooAddPdf("model_gen",
"model_gen", ROOT.RooArgList(sig, bkgr),
ROOT.RooArgList(fraction))
model = ROOT.RooAddPdf('model', 'model', ROOT.RooArgList(sig, bkgr),
ROOT.RooArgList(N_sig, N_bkgr))
# Sample N_GEN events
data = model_gen.generate(ROOT.RooArgSet(m), N_GEN)
data = data.reduce(
f'{m.GetName()} > {m.getMin()} && {m.GetName()} < {m.getMax()}')
# Fit and plot'em all
DE = DataExplorer(label='test', data=data, model=model)
fit_results = DE.fit(minos=True)
c = ROOT.TCanvas()
frame = DE.plot_on_frame()
frame.Draw()
# Make pull distribution for the fit
c_pull = ROOT.TCanvas()
frame_pull = DE.plot_pull()
frame_pull.Draw()
# Plot likelihood profiles
c_ll = ROOT.TCanvas()
frame_ll = DE.plot_ll(poi=N_sig)
frame_ll.Draw()
