FunctionFittedGroupedDEDXEstimatorTrainer Class Reference

Inheritance diagram for FunctionFittedGroupedDEDXEstimatorTrainer:

Collaboration diagram for FunctionFittedGroupedDEDXEstimatorTrainer:

Public Member Functions
def	__init__ (self, fit_function, dimension_of_fit_function, result_function, use_sigma_for_result_fitting)
def	plot_grouped_result (self, data)

Public Attributes
	dimension_of_fit_function
	cached value of the degrees of freedom in the fit
	fit_function
	cached copy of the fitting function
	train_function
	this class's training function

Detailed Description

Train a neural network for dE/dx-based particle identification

Definition at line 193 of file train.py.

Constructor & Destructor Documentation

__init__()

def __init__	(		self,
			fit_function,
			dimension_of_fit_function,
			result_function,
			use_sigma_for_result_fitting
	)

Constructor

Reimplemented from FittedGroupedDEDXEstimatorTrainer.

Reimplemented in GaussianEstimatorTrainer, LandauEstimatorTrainer, GaussianEstimatorTrainerSQRT, and LandauEstimatorTrainerSQRT.

Definition at line 196 of file train.py.

    def __init__(self, fit_function, dimension_of_fit_function, result_function, use_sigma_for_result_fitting):
        """Constructor"""
 
        
        self.dimension_of_fit_function = dimension_of_fit_function
        
        self.fit_function = fit_function
 
        FittedGroupedDEDXEstimatorTrainer.__init__(self, result_function, use_sigma_for_result_fitting)
 
        def train_function(fit_data):
            """Train on the fit to curated-data highest values whose truth value is known"""
            max_value = self.use_only_the_highest_values(fit_data, 1).p_bin_centers.values[0]
 
            if self.dimension_of_fit_function == 3:
                p0 = (1e3, max_value, 4e-2)
            elif self.dimension_of_fit_function == 6:
                p0 = (1e3, max_value, 4e-2, 1, 1, 1)
 
            popt, pcov = curve_fit(self.fit_function, fit_data.p_bin_centers, fit_data.number_of_p_values, p0=p0)
 
            return [np.sqrt(np.diag(pcov)[1]), popt]
 
        
        self.train_function = train_function
 

Member Function Documentation

plot_grouped_result()

def plot_grouped_result	(		self,
			data
	)

Plot the fitted grouped results

Reimplemented from FittedGroupedDEDXEstimatorTrainer.

Definition at line 222 of file train.py.

    def plot_grouped_result(self, data):
        """Plot the fitted grouped results"""
        FittedGroupedDEDXEstimatorTrainer.plot_grouped_result(self, data)
 
        dedx_binned_data, dedx_bins = self.create_dedx_bins(data)
 
        p_plot_data = np.linspace(data.p.min(), data.p.max(), 1000)
 
        # List to prevent bug in pd.DataFrame.apply
        already_plotted_list = []
 
        def plot_fitted_results(dedx_bin):
            dedx_bin_center = dedx_bin.mean().values[0]
 
            if dedx_bin_center not in already_plotted_list:
                fitted_results = self.result_parameters_for_each_dedx_bin[dedx_bin.mean()[self.dedx_column]]
                already_plotted_list.append(dedx_bin_center)
                unneeded, fit_options = fitted_results
 
                dedx_plot_data = self.fit_function(p_plot_data, *fitted_results[1])
                plt.plot(p_plot_data, dedx_plot_data)
 
            return True
 
        dedx_binned_data.apply(plot_fitted_results)
 
 

Member Data Documentation

dimension_of_fit_function

dimension_of_fit_function

cached value of the degrees of freedom in the fit

Definition at line 200 of file train.py.

fit_function

fit_function

cached copy of the fitting function

Definition at line 202 of file train.py.

train_function

train_function

this class's training function

Definition at line 220 of file train.py.

---

The documentation for this class was generated from the following file:

• tracking/studies/low_momentum_vxd_estimation/train.py