Violin Plots for Weighted Data in Matplotlib

violin_weighted_plot.py

import weighted
from matplotlib.cbook import violin_stats
from scipy import stats
import statsmodels.api as sm

def vdensity_with_weights(weights):
    ''' Outer function allows innder function access to weights. Matplotlib
    needs function to take in data and coords, so this seems like only way
    to 'pass' custom density function a set of weights '''
    
    def vdensity(data, coords):
        ''' Custom matplotlib weighted violin stats function '''
        # Using weights from closure, get KDE fomr statsmodels
        weighted_cost = sm.nonparametric.KDEUnivariate(data)
        weighted_cost.fit(fft=False, weights=weights)

        # Return y-values for graph of KDE by evaluating on coords
        return weighted_cost.evaluate(coords)
    return vdensity

def custom_violin_stats(data, weights):
    # Get weighted median and mean (using weighted module for median)
    median = weighted.quantile_1D(data, weights, 0.5)
    mean, sumw = np.ma.average(data, weights=list(weights), returned=True)
    
    # Use matplotlib violin_stats, which expects a function that takes in data and coords
    # which we get from closure above
    results = violin_stats(data, vdensity_with_weights(weights))
    
    # Update result dictionary with our updated info
    results[0][u"mean"] = mean
    results[0][u"median"] = median
    
    # No need to do this, since it should be populated from violin_stats
    # results[0][u"min"] =  np.min(data)
    # results[0][u"max"] =  np.max(data)

    return results

### Example
#vpstats1 = custom_violin_stats(np.asarray(df_column_data), np.asarray(df_column_weights))
#vplot = ax.violin(vpstats1, [pos_idx], vert=False, showmeans=True, showextrema=True, showmedians=True)
#current_color_palette = ...
#for pc in vplot['bodies']:
#    pc.set_facecolor(current_color_palette[pos_idx])
#    pc.set_edgecolor('black')

Hello!

It looks like you use the np module here (I assume that this is an alias for numpy) but you never import it. Am i right?

Thanks for this! I added a couple pieces to make this fully runnable, you can see it here: https://colab.research.google.com/drive/1cSnJGKJEqbllkPbF2z0cnfdwT40sUKKR