flotilla.visualize.predict module¶

Visualize the result of a classifcation or regression algorithm on the data.

class flotilla.visualize.predict.ClassifierViz(data_name, trait_name, predictor_name=None, *args, **kwargs)[source]¶

Bases: flotilla.compute.predict.Classifier, flotilla.visualize.predict.PredictorBaseViz

Visualize results from classification

check_a_feature(feature_name, **violinplot_kwargs)[source]¶

Make Violin Plots for a gene/probe’s value in the sets defined in sets

feature_name - gene/probe id. must be in the index of self._parent.X sets - list of sample ids violinplot_kwargs - extra parameters for violinplot

returns a list of lists with values for feature_name in each set of sets

class flotilla.visualize.predict.PredictorBaseViz(predictor_name, data_name, trait_name, X_data=None, trait=None, predictor_obj=None, predictor_scoring_fun=None, score_cutoff_fun=None, n_features_dependent_kwargs=None, constant_kwargs=None, is_categorical_trait=None, predictor_dataset_manager=None, predictor_config_manager=None, feature_renamer=None, groupby=None, color=None, pooled=None, order=None, violinplot_kws=None, data_type=None, label_to_color=None, label_to_marker=None, singles=None, outliers=None)[source]¶

Bases: flotilla.compute.predict.PredictorBase

do_pca(**plotting_kwargs)[source]¶

generate_scatter_table(excel_out=None, external_xref=[])[source]¶

make a table to make scatterplots... maybe for plot.ly excelOut: full path to an excel output location for scatter data external_xref: list of tuples containing (attribute name, function to map row index -> an attribute)

plot_scores(ax=None)[source]¶

plot kernel density of predictor scores and draw a vertical line where the cutoff was selected ax - ax to plot on. if None: plt.gca()

set_reducer_plotting_args(rpa)[source]¶

class flotilla.visualize.predict.RegressorViz(data_name, trait_name, predictor_name=None, *args, **kwargs)[source]¶

Bases: flotilla.compute.predict.Regressor, flotilla.visualize.predict.PredictorBaseViz