bubble_plot.py 文件源码

def plot_without_z(df, x, y, z, count_table, bins_x, bins_y, x_is_numeric, y_is_numeric, ordered_x_values, ordered_y_values, normalization_by_all=False, log=False, maximal_bubble_size=4000):
    if normalization_by_all:
        count_table /= count_table.sum().sum()
    else:
        count_table = count_table.transpose()
        for col in count_table.columns:
            count_table[col] /= count_table[col].sum()
        count_table = count_table.transpose()
    if log:
        count_table = np.log(count_table)
        maximal_bubble_size /= 2
    size_factor = maximal_bubble_size/count_table.max().max()
    count_table_long = pd.melt(count_table.reset_index(), id_vars=x)
    x_values_dict = {x:i for i, x in enumerate(ordered_x_values)} \
        if not x_is_numeric else {xx:get_point(xx) for xx in ordered_x_values}
    y_values_dict = {x:i for i, x in enumerate(ordered_y_values)} \
        if not y_is_numeric else {xx: get_point(xx) for xx in ordered_y_values}
    xticks = np.arange(count_table.shape[0]) if not x_is_numeric else [get_point(xx) for xx in ordered_x_values]
    yticks = np.arange(count_table.shape[1]) if not y_is_numeric else [get_point(xx) for xx in ordered_y_values]
    xticklabels = ordered_x_values if not x_is_numeric else [get_point(xx) for xx in ordered_x_values]
    yticklabels = ordered_y_values if not y_is_numeric else [get_point(xx) for xx in ordered_y_values]
    count_table_long[x] = count_table_long[x].map(x_values_dict)
    count_table_long[y] = count_table_long[y].map(y_values_dict) 
    plt.scatter(count_table_long[x], count_table_long[y], s=size_factor*count_table_long['value'],
                c=count_table_long['value'], cmap='cool')

    return count_table_long, xticks, yticks, xticklabels, yticklabels