Print

19 of 100: Dumbell 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!

To be improved: The sort is not correct and the colors are not quite right. Will revise.

This is the original viz that we are trying to recreate in matplotlib:

Import the packages

We will need the following packages:

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from matplotlib.lines import Line2D
from matplotlib.colors import LinearSegmentedColormap

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.

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)
indexyearcountriessites
02004Sweden13
12022Sweden15
22004Denmark4
32022Denmark10
42004Norway5
52022Norway8

We need to create the percentage change, country code, the difference in sites between years and then sort the data.

df['pct_change'] = df.groupby('countries', sort=True)['sites'].apply(
     lambda x: x.pct_change()).to_numpy()*-1
df['ctry_code'] = df.countries.astype(str).str[:2].astype(str).str.upper()
df['diff'] = df.groupby(['countries'])['sites'].diff()
df['diff'].fillna(df.sites, inplace=True)

sort_order_dict =  {"Denmark":3, "Sweden":1, "Norway":2}
df = df.sort_values(by=['countries'], key= lambda x:x.map(sort_order_dict))
indexyearcountriessitespct_changectry_codediff
02004Sweden13NaNSW13.0
12022Sweden15-0.153846SW2.0
42004Norway5NaNNO5.0
52022Norway8-0.600000NO3.0
22004Denmark4NaNDE4.0
32022Denmark10-1.500000DE6.0

Define the variables

countries = df.countries.unique()
codes = df.ctry_code.unique()
pct_changes = df['pct_change'].max()

#color of the diamonds
colors = ["#CC5A43","#5375D4"]*3

# use a colormap
cmap = plt.cm.RdBu

x_coord = df.groupby('countries')['diff'].apply(lambda x: x.values) #convert the columns into numpy 2D array

Create a function to create the gradient bars

def gradientbars(bars, ax):
    colors = [(1, 0, 0), (0, 0, 1), ] # first color is red, last is blue
    cm = LinearSegmentedColormap.from_list(
            "Custom", colors, N=256) # Conver to color map 
    mat = np.indices((10,10))[1] # define a matrix for imshow
    lim = ax.get_xlim()+ax.get_ylim()
    for bar in bars:
        bar.set_zorder(1)
        bar.set_facecolor("none")
        
        # get the coordinates of the rectangle
        x_all = bar.get_paths()[0].vertices[:, 0]
        y_all = bar.get_paths()[0].vertices[:, 1]
        
        # Get the first coordinate (lower left corner)
        x,y = x_all[0], y_all[0]
        # Get the height and width of the rectangle
        h, w = max(y_all) - min(y_all), max(x_all) - min(x_all)
        # Show the colormap 
        ax.imshow(mat, extent=[x,x+w,y,y+h], aspect="auto", zorder=0, cmap=cm, alpha=0.2)
    ax.axis(lim)

Plot the chart

fig, ax = plt.subplots(figsize=(8,5), facecolor = "#FFFFFF")



bars = []
for i, (color, x_c, code, country) in enumerate(zip(colors,reversed(x_coord), codes,countries)):
    bar = ax.broken_barh([x_c], (i-0.15,0.3),facecolors=cmap(0.7),alpha= 0.2)
    bars.append(bar)
    #add country code
    ax.annotate(
            text=code, xy=(x_c[0]-1.5, i), 
            color='#C8C9C9', fontsize=12, 
            ha='left',va='center', )
    #add percentage
    ax.annotate(
            text=f"{x_c[1]/x_c[0] * 100:+.0f}%", xy=(x_c[0]+x_c[1]/2, i), 
            color='w', fontsize=12, 
            ha='center',va='center', )
    
gradientbars(bars, ax)
ax.scatter( df.sites, df.countries, marker="D", s=200, color = colors)

ax.set(xlim=[0, 16], ylim=[-1, 3])

# Major ticks every 20, minor ticks every 5
ax.xaxis.set_ticks(np.arange(0,20,5),labels = [0,5,10,15])
ax.tick_params(axis="x", which="major",length=0,labelsize=14,colors= '#C8C9C9')

ax.set_xticks(np.arange(0, 16, 1))
ax.grid(which='major', axis='x', linestyle='-', alpha=0.4, color = "#C8C9C9")
ax.set_axisbelow(True)
ax.set_yticks([])
ax.spines[['top', 'bottom', 'left', 'right']].set_visible(False)



#add legend
labels = ['2004','2022']
colors = ["#5375D4","#CC5A43",]
lines = [Line2D([0], [0], color=c,  marker='D',linestyle='', markersize=12,) for c in colors]
leg = ax.get_legend()
plt.figlegend( lines,labels,
           labelcolor="#C8C9C9",
           bbox_to_anchor=(0.3, -0.1), loc="lower center",
            ncols = 2,frameon=False, fontsize= 12)

The result:

19 of 100: Dumbell chart in matplotlib
Was this helpful?

Reader Interactions

Leave a Reply

Your email address will not be published. Required fields are marked *

Table of Contents