def plot_data_mean_std()

in train_procgen/graph_util.py [0:0]

• 14 lines of code
• 4 McCabe index (conditional complexity)

def plot_data_mean_std(ax, data_y, color_idx=0, data_x=None, x_scale=1, smoothing=0, first_valid=0, label=None):
    color = COLORS[color_idx]
    hexcolor = '#%02x%02x%02x' % color

    data_y = data_y[:,first_valid:]
    nx, num_datapoint = np.shape(data_y)

    if smoothing > 0:
        for i in range(nx):
            data_y[i,...] = ema(data_y[i,...], smoothing)

    if data_x is None:
        data_x = (np.array(range(num_datapoint)) + first_valid) * x_scale

    data_mean = np.mean(data_y, axis=0)
    data_std = np.std(data_y, axis=0, ddof=1)

    ax.plot(data_x, data_mean, color=hexcolor, label=label, linestyle='solid', alpha=1, rasterized=True)
    ax.fill_between(data_x, data_mean - data_std, data_mean + data_std, color=hexcolor, alpha=.25, linewidth=0.0, rasterized=True)