stacked bar plot using matplotlib

I found this such a pain that I wrote a function to do it. I'm sharing it in the hope that others find it useful:

import numpy as np
import matplotlib.pyplot as plt

def plot_stacked_bar(data, series_labels, category_labels=None, 
                     show_values=False, value_format="{}", y_label=None, 
                     colors=None, grid=True, reverse=False):
    """Plots a stacked bar chart with the data and labels provided.

    Keyword arguments:
    data            -- 2-dimensional numpy array or nested list
                       containing data for each series in rows
    series_labels   -- list of series labels (these appear in
                       the legend)
    category_labels -- list of category labels (these appear
                       on the x-axis)
    show_values     -- If True then numeric value labels will 
                       be shown on each bar
    value_format    -- Format string for numeric value labels
                       (default is "{}")
    y_label         -- Label for y-axis (str)
    colors          -- List of color labels
    grid            -- If True display grid
    reverse         -- If True reverse the order that the
                       series are displayed (left-to-right
                       or right-to-left)
    """

    ny = len(data[0])
    ind = list(range(ny))

    axes = []
    cum_size = np.zeros(ny)

    data = np.array(data)

    if reverse:
        data = np.flip(data, axis=1)
        category_labels = reversed(category_labels)

    for i, row_data in enumerate(data):
        color = colors[i] if colors is not None else None
        axes.append(plt.bar(ind, row_data, bottom=cum_size, 
                            label=series_labels[i], color=color))
        cum_size += row_data

    if category_labels:
        plt.xticks(ind, category_labels)

    if y_label:
        plt.ylabel(y_label)

    plt.legend()

    if grid:
        plt.grid()

    if show_values:
        for axis in axes:
            for bar in axis:
                w, h = bar.get_width(), bar.get_height()
                plt.text(bar.get_x() + w/2, bar.get_y() + h/2, 
                         value_format.format(h), ha="center", 
                         va="center")

Example:

plt.figure(figsize=(6, 4))

series_labels = ['Series 1', 'Series 2']

data = [
    [0.2, 0.3, 0.35, 0.3],
    [0.8, 0.7, 0.6, 0.5]
]

category_labels = ['Cat A', 'Cat B', 'Cat C', 'Cat D']

plot_stacked_bar(
    data, 
    series_labels, 
    category_labels=category_labels, 
    show_values=True, 
    value_format="{:.1f}",
    colors=['tab:orange', 'tab:green'],
    y_label="Quantity (units)"
)

plt.savefig('bar.png')
plt.show()

stacked bar plot example


You need the bottom of each dataset to be the sum of all the datasets that came before. you may also need to convert the datasets to numpy arrays to add them together.

p1 = plt.bar(ind, dataset[1], width, color='r')
p2 = plt.bar(ind, dataset[2], width, bottom=dataset[1], color='b')
p3 = plt.bar(ind, dataset[3], width, 
             bottom=np.array(dataset[1])+np.array(dataset[2]), color='g')
p4 = plt.bar(ind, dataset[4], width,
             bottom=np.array(dataset[1])+np.array(dataset[2])+np.array(dataset[3]),
             color='c')

enter image description here

Alternatively, you could convert them to numpy arrays before you start plotting.

dataset1 = np.array(dataset[1])
dataset2 = np.array(dataset[2])
dataset3 = np.array(dataset[3])
dataset4 = np.array(dataset[4])

p1 = plt.bar(ind, dataset1, width, color='r')
p2 = plt.bar(ind, dataset2, width, bottom=dataset1, color='b')
p3 = plt.bar(ind, dataset3, width, bottom=dataset1+dataset2, color='g')
p4 = plt.bar(ind, dataset4, width, bottom=dataset1+dataset2+dataset3,
             color='c')

Or finally if you want to avoid converting to numpy arrays, you could use a list comprehension:

p1 = plt.bar(ind, dataset[1], width, color='r')
p2 = plt.bar(ind, dataset[2], width, bottom=dataset[1], color='b')
p3 = plt.bar(ind, dataset[3], width,
             bottom=[sum(x) for x in zip(dataset[1],dataset[2])], color='g')
p4 = plt.bar(ind, dataset[4], width,
             bottom=[sum(x) for x in zip(dataset[1],dataset[2],dataset[3])],
             color='c')