1 of 100: Stacked bar chart in matplotlib
At the beginning of the year I challenged myself to create all 100 visualizations using python and matplotlib from the 1 dataset,100 visualizations project and I am sharing with you the code for all the visualizations.
Note: Data Viz Project is copyright Ferdio and available under a Creative Commons Attribution – Non Commercial – No Derivatives 4.0 International license. I asked Ferdio and they told me they used a Design tool to create all the plots.
Collaborate
There are a ton of improvements that can be made on the code, so let me know in the comments any improvements you make and I will update the post accordingly!
This is the original viz that we are trying to recreate in matplotlib:

Watch me build it or keep on reading:
If you prefer to read, keep scrolling:
Import the packages
We will need the following packages:
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
Generate the data
We could actually go from numpy to matplotlib, but most data projects use pandas to transform the data, so I am using a pandas dataframe as the starting point.
color_dict = {"Norway": "#2B314D", "Denmark": "#A54836", "Sweden": "#5375D4", }
xylabel_color, grand_totals_color, grid_color, datalabels_color ='#757C85',"#101628", "#C8C9C9", "w"
data = {
"year": [2004, 2022, 2004, 2022, 2004, 2022],
"countries" : ["Sweden", "Sweden", "Denmark", "Denmark", "Norway", "Norway"],
"sites": [13,15,4,10,5,8]
}
df= pd.DataFrame(data)
index | year | countries | sites |
---|---|---|---|
0 | 2004 | Sweden | 13 |
1 | 2022 | Sweden | 15 |
2 | 2004 | Denmark | 4 |
3 | 2022 | Denmark | 10 |
4 | 2004 | Norway | 5 |
5 | 2022 | Norway | 8 |
We need to create the subtotals for each year and then we custom sort the data.
df['sub_total'] = df.groupby('year')['sites'].transform('sum')
#custom sort
sort_order_dict = {"Denmark":2, "Sweden":3, "Norway":1, 2004:4, 2022:5}
df = df.sort_values(by=['year','countries',], key=lambda x: x.map(sort_order_dict))
#map the colors of a dict to a dataframe
df['color']= df.countries.map(color_dict)
year | countries | sites | sub_total | color | |
---|---|---|---|---|---|
4 | 2004 | Norway | 5 | 22 | #2B314D |
2 | 2004 | Denmark | 4 | 22 | #A54836 |
0 | 2004 | Sweden | 13 | 22 | #5375D4 |
5 | 2022 | Norway | 8 | 33 | #2B314D |
3 | 2022 | Denmark | 10 | 33 | #A54836 |
1 | 2022 | Sweden | 15 | 33 | #5375D4 |
Define the variables
unique_countries = df.countries.unique()
years = df.year.unique()
colors = df.color
sub_total = df.sub_total.unique()
Plot the stacked bar chart
Now we are ready to plot the stacked bar chart.
fig, ax = plt.subplots(figsize=(7,10), facecolor = "#FFFFFF" )
bottom = np.zeros(len(years))
for country, color in zip(unique_countries, colors):
y = df[df["countries"] == country]["sites"].to_numpy()
ax.bar(range(len(years)), y, bottom = bottom, width= 0.6, color=color)
bottom +=y
# Show sum on each stacked bar
for i, total in enumerate(sub_total):
ax.text(i, total+1 , total, ha='center', size = 20, color = grand_totals_color) #weight='bold')
#add data labels
for bar in ax.patches:
ax.text(
bar.get_x() + bar.get_width() / 2, # Put the text in the middle of each bar. get_x returns the start, so we add half the width to get to the middle.
bar.get_height()/2 + bar.get_y(), # Vertically, add the height of the bar to the start of the bar, along with the offset.
round(bar.get_height()), # This is actual value we'll show.
ha='center', color=datalabels_color, size=16 )
#add country legend at the end bar only
offset_text = 1
for bar, country, color in zip(ax.patches[len(years)-1::len(years)], unique_countries, colors): #get every other element skip one
ax.text(
bar.get_x() + bar.get_width() + offset_text,
bar.get_height()/2 + bar.get_y(),
country,
ha='center', color=color, size=16 )
# We change the fontsize of minor ticks label
ax.tick_params(axis='both', which='major', length=0, labelsize=16,colors= xy_ticklabel_color,pad =15)
ax.xaxis.set_ticks(range(len(years)), labels =years)
#add vertical grid lines
ax.set_axisbelow(True) #set the grid lines in the BACK
ax.grid(True, axis='y', linestyle='solid', linewidth=1, color = grid_color)
ax.set_xlim(-1,len(years))
ax.set_ylim(0,df.sub_total.max()+4)
ax.spines[['left', 'right', 'top', 'bottom']].set_visible(False)
import IPython
s = IPython.extract_module_locals()[1]['__vsc_ipynb_file__']
filename = str( s[s.find("dataviz\\")+len("dataviz\\"):s.rfind(".ipynb")])
fig.savefig(r'C:/Users/Ruth Pozuelo/Documents/SynologyDrive/Matplotlib-Labs/100 dataviz/0.Images/' + filename +'.png',
bbox_inches = 'tight', facecolor=fig.get_facecolor(), transparent=False, dpi = 600)
The result:

Reader Interactions