src/lookoutequipment/evaluation.py [336:385]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            total=max_plots, 
            desc='Preparing histograms'
        ):
            # We stop after reaching the number of plots we are interested in:
            if i > max_plots - 1:
                break

            try:
                # Get the anomaly and the normal values from the current signal:
                current_signal_values = self.df_list[tag][tag]
                
                current_signal_evaluation = self.df_list[tag].loc[self.ts_label_evaluation, tag]
                current_signal_training = self.df_list[tag].loc[self.ts_normal_training, tag]
                
                

                # Compute the bin width and bin edges to match the 
                # number of bins we want to have on each histogram:
                bin_width =(np.max(current_signal_values) - np.min(current_signal_values))/self.num_bins
                bins = np.arange(
                    np.min(current_signal_values), 
                    np.max(current_signal_values) + bin_width, 
                    bin_width
                )

                # Add both histograms in the same plot:
                axes[i].hist(current_signal_training, 
                         density=True, 
                         alpha=0.5, 
                         color=colors[1], 
                         bins=bins, 
                         edgecolor='#FFFFFF')
                axes[i].hist(current_signal_evaluation, 
                         alpha=0.5, 
                         density=True, 
                         color=colors[5], 
                         bins=bins, 
                         edgecolor='#FFFFFF')

            except Exception as e:
                print(e)
                axes[i] = plt.subplot(gs[i])

            # Removes all the decoration to leave only the histograms:
            axes[i].grid(False)
            axes[i].get_yaxis().set_visible(False)
            axes[i].get_xaxis().set_visible(False)

            # Title will be the tag name followed by the score:
            title = tag
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/lookoutequipment/evaluation.py [425:471]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            total=max_plots, 
            desc='Preparing histograms'
        ):
            # We stop after reaching the number of plots we are interested in:
            if i > max_plots - 1:
                break

            try:
                # Get the anomaly and the normal values from the current signal:
                current_signal_values = self.df_list[tag][tag]
                current_signal_evaluation = self.df_list[tag].loc[self.ts_label_evaluation, tag]
                current_signal_training = self.df_list[tag].loc[self.ts_normal_training, tag]

                # Compute the bin width and bin edges to match the 
                # number of bins we want to have on each histogram:
                bin_width =(np.max(current_signal_values) - np.min(current_signal_values))/self.num_bins
                bins = np.arange(
                    np.min(current_signal_values), 
                    np.max(current_signal_values) + bin_width, 
                    bin_width
                )

                # Add both histograms in the same plot:
                axes[i].hist(current_signal_training, 
                         density=True, 
                         alpha=0.5, 
                         color=colors[1], 
                         bins=bins, 
                         edgecolor='#FFFFFF')
                axes[i].hist(current_signal_evaluation, 
                         alpha=0.5, 
                         density=True, 
                         color=colors[5], 
                         bins=bins, 
                         edgecolor='#FFFFFF')

            except Exception as e:
                print(e)
                axes[i] = plt.subplot(gs[i])

            # Removes all the decoration to leave only the histograms:
            axes[i].grid(False)
            axes[i].get_yaxis().set_visible(False)
            axes[i].get_xaxis().set_visible(False)

            # Title will be the tag name followed by the score:
            title = tag
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -